From 38163af068810b388f6723a681dfd8c7b3680d38 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 14 Oct 2025 23:54:58 +0000 Subject: bpf: Introduce SK_BPF_BYPASS_PROT_MEM. If a socket has sk->sk_bypass_prot_mem flagged, the socket opts out of the global protocol memory accounting. This is easily controlled by net.core.bypass_prot_mem sysctl, but it lacks flexibility. Let's support flagging (and clearing) sk->sk_bypass_prot_mem via bpf_setsockopt() at the BPF_CGROUP_INET_SOCK_CREATE hook. int val = 1; bpf_setsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM, &val, sizeof(val)); As with net.core.bypass_prot_mem, this is inherited to child sockets, and BPF always takes precedence over sysctl at socket(2) and accept(2). SK_BPF_BYPASS_PROT_MEM is only supported at BPF_CGROUP_INET_SOCK_CREATE and not supported on other hooks for some reasons: 1. UDP charges memory under sk->sk_receive_queue.lock instead of lock_sock() 2. Modifying the flag after skb is charged to sk requires such adjustment during bpf_setsockopt() and complicates the logic unnecessarily We can support other hooks later if a real use case justifies that. Most changes are inline and hard to trace, but a microbenchmark on __sk_mem_raise_allocated() during neper/tcp_stream showed that more samples completed faster with sk->sk_bypass_prot_mem == 1. This will be more visible under tcp_mem pressure (but it's not a fair comparison). # bpftrace -e 'kprobe:__sk_mem_raise_allocated { @start[tid] = nsecs; } kretprobe:__sk_mem_raise_allocated /@start[tid]/ { @end[tid] = nsecs - @start[tid]; @times = hist(@end[tid]); delete(@start[tid]); }' # tcp_stream -6 -F 1000 -N -T 256 Without bpf prog: [128, 256) 3846 | | [256, 512) 1505326 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [512, 1K) 1371006 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ | [1K, 2K) 198207 |@@@@@@ | [2K, 4K) 31199 |@ | With bpf prog in the next patch: (must be attached before tcp_stream) # bpftool prog load sk_bypass_prot_mem.bpf.o /sys/fs/bpf/test type cgroup/sock_create # bpftool cgroup attach /sys/fs/cgroup/test cgroup_inet_sock_create pinned /sys/fs/bpf/test [128, 256) 6413 | | [256, 512) 1868425 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [512, 1K) 1101697 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ | [1K, 2K) 117031 |@@@@ | [2K, 4K) 11773 | | Signed-off-by: Kuniyuki Iwashima Signed-off-by: Martin KaFai Lau Acked-by: Roman Gushchin Link: https://patch.msgid.link/20251014235604.3057003-6-kuniyu@google.com --- include/uapi/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6829936d33f5..6eb75ad900b1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7200,6 +7200,8 @@ enum { TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ + SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ + }; enum { -- cgit v1.2.3 From a63ca4236e6799cf4343f9aec9d92afdfa582446 Mon Sep 17 00:00:00 2001 From: Ackerley Tng Date: Thu, 16 Oct 2025 10:28:44 -0700 Subject: KVM: guest_memfd: Use guest mem inodes instead of anonymous inodes guest_memfd's inode represents memory the guest_memfd is providing. guest_memfd's file represents a struct kvm's view of that memory. Using a custom inode allows customization of the inode teardown process via callbacks. For example, ->evict_inode() allows customization of the truncation process on file close, and ->destroy_inode() and ->free_inode() allow customization of the inode freeing process. Customizing the truncation process allows flexibility in management of guest_memfd memory and customization of the inode freeing process allows proper cleanup of memory metadata stored on the inode. Memory metadata is more appropriately stored on the inode (as opposed to the file), since the metadata is for the memory and is not unique to a specific binding and struct kvm. Acked-by: David Hildenbrand Co-developed-by: Fuad Tabba Signed-off-by: Fuad Tabba Signed-off-by: Ackerley Tng Signed-off-by: Shivank Garg Tested-by: Ashish Kalra [sean: drop helpers, open code logic in __kvm_gmem_create()] Link: https://lore.kernel.org/r/20251016172853.52451-4-seanjc@google.com Signed-off-by: Sean Christopherson --- include/uapi/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index bb575f3ab45e..638ca21b7a90 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -103,5 +103,6 @@ #define DEVMEM_MAGIC 0x454d444d /* "DMEM" */ #define SECRETMEM_MAGIC 0x5345434d /* "SECM" */ #define PID_FS_MAGIC 0x50494446 /* "PIDF" */ +#define GUEST_MEMFD_MAGIC 0x474d454d /* "GMEM" */ #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From ca4709843b7e72f96976cd6b35bca148a4071673 Mon Sep 17 00:00:00 2001 From: David Yang Date: Fri, 17 Oct 2025 14:08:54 +0800 Subject: net: dsa: tag_yt921x: add support for Motorcomm YT921x tags Add support for Motorcomm YT921x tags, which includes a proper configurable ethertype field (default to 0x9988). Signed-off-by: David Yang Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20251017060859.326450-3-mmyangfl@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 69e0457eb200..cfd200c87e5e 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -114,6 +114,7 @@ #define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_YT921X 0x9988 /* Motorcomm YT921x DSA [ 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 ] */ -- cgit v1.2.3 From 1cba30bf9fdd6c982708f3587f609a30c370d889 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 16 Oct 2025 11:09:38 -0700 Subject: io_uring: add support for IORING_SETUP_SQE_MIXED Normal rings support 64b SQEs for posting submissions, while certain features require the ring to be configured with IORING_SETUP_SQE128, as they need to convey more information per submission. This, in turn, makes ALL the SQEs be 128b in size. This is somewhat wasteful and inefficient, particularly when only certain SQEs need to be of the bigger variant. This adds support for setting up a ring with mixed SQE sizes, using IORING_SETUP_SQE_MIXED. When setup in this mode, SQEs posted to the ring may be either 64b or 128b in size. If a SQE is 128b in size, then opcode will be set to a variante to indicate that this is the case. Any other non-128b opcode will assume the SQ's default size. SQEs on these types of mixed rings may also utilize NOP with skip success set. This can happen if the ring is one (small) SQE entry away from wrapping, and an attempt is made to get a 128b SQE. As SQEs must be contiguous in the SQ ring, a 128b SQE cannot wrap the ring. For this case, a single NOP SQE should be inserted with the SKIP_SUCCESS flag set. The kernel will process this as a normal NOP and without posting a CQE. Signed-off-by: Keith Busch [axboe: {} style fix and assign sqe before opcode read] 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 263bed13473e..04797a9b76bc 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -231,6 +231,12 @@ enum io_uring_sqe_flags_bit { */ #define IORING_SETUP_CQE_MIXED (1U << 18) +/* + * Allow both 64b and 128b SQEs. If a 128b SQE is posted, it will have + * a 128b opcode. + */ +#define IORING_SETUP_SQE_MIXED (1U << 19) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -295,6 +301,8 @@ enum io_uring_op { IORING_OP_READV_FIXED, IORING_OP_WRITEV_FIXED, IORING_OP_PIPE, + IORING_OP_NOP128, + IORING_OP_URING_CMD128, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 0d8627cc936de8ea04f3cc1e6921c63fb72cc199 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 22 Oct 2025 13:41:06 +0200 Subject: blktrace: add definitions for blk_user_trace_setup2 Add definitions for a version 2 of the blk_user_trace_setup ioctl. This new ioctl will enable a different struct layout of the binary data passed to user-space when using a new version of the blktrace utility requesting the new struct layout. Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 16 ++++++++++++++++ include/uapi/linux/fs.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 1bfb635e309b..a6958708d477 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -129,6 +129,7 @@ enum { }; #define BLKTRACE_BDEV_SIZE 32 +#define BLKTRACE_BDEV_SIZE2 64 /* * User setup structure passed with BLKTRACESETUP @@ -143,4 +144,19 @@ struct blk_user_trace_setup { __u32 pid; }; +/* + * User setup structure passed with BLKTRACESETUP2 + */ +struct blk_user_trace_setup2 { + char name[BLKTRACE_BDEV_SIZE2]; /* output */ + __u64 act_mask; /* input */ + __u32 buf_size; /* input */ + __u32 buf_nr; /* input */ + __u64 start_lba; + __u64 end_lba; + __u32 pid; + __u32 flags; /* currently unused */ + __u64 reserved[11]; +}; + #endif /* _UAPIBLKTRACE_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index beb4c2d1e41c..957ce3343a4f 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -300,6 +300,7 @@ struct file_attr { #define BLKGETDISKSEQ _IOR(0x12,128,__u64) /* 130-136 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */ /* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */ +#define BLKTRACESETUP2 _IOWR(0x12, 142, struct blk_user_trace_setup2) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From c44347d606260f36a81f6d8415a5af33cb3015fa Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 22 Oct 2025 13:41:08 +0200 Subject: blktrace: add definitions for struct blk_io_trace2 Add definitions for the extended version of the blktrace protocol using a wider action type to be able to record new actions in the kernel. Reviewed-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index a6958708d477..9f9834d76e00 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -94,6 +94,7 @@ enum blktrace_notify { #define BLK_IO_TRACE_MAGIC 0x65617400 #define BLK_IO_TRACE_VERSION 0x07 +#define BLK_IO_TRACE2_VERSION 0x08 /* * The trace itself @@ -113,6 +114,21 @@ struct blk_io_trace { /* cgroup id will be stored here if exists */ }; +struct blk_io_trace2 { + __u32 magic; /* MAGIC << 8 | BLK_IO_TRACE2_VERSION */ + __u32 sequence; /* event number */ + __u64 time; /* in nanoseconds */ + __u64 sector; /* disk offset */ + __u32 bytes; /* transfer length */ + __u32 pid; /* who did it */ + __u64 action; /* what happened */ + __u32 device; /* device number */ + __u32 cpu; /* on what cpu did it happen */ + __u16 error; /* completion error */ + __u16 pdu_len; /* length of data after this trace */ + __u8 pad[12]; + /* cgroup id will be stored here if it exists */ +}; /* * The remap event */ -- cgit v1.2.3 From f9ee38bbf70fb20584625849a253c8652176fa66 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 22 Oct 2025 13:41:12 +0200 Subject: blktrace: add block trace commands for zone operations Add block trace commands for zone operations. These commands can only be handled with version 2 of the blktrace protocol. For version 1, warn if a command that does not fit into the 16 bits reserved for the command in this version is passed in. Reviewed-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 9f9834d76e00..190a3c5ab0a0 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -26,11 +26,20 @@ enum blktrace_cat { BLK_TC_DRV_DATA = 1 << 14, /* binary per-driver data */ BLK_TC_FUA = 1 << 15, /* fua requests */ - BLK_TC_END = 1 << 15, /* we've run out of bits! */ + BLK_TC_END_V1 = 1 << 15, /* we've run out of bits! */ + + BLK_TC_ZONE_APPEND = 1ull << 16, /* zone append */ + BLK_TC_ZONE_RESET = 1ull << 17, /* zone reset */ + BLK_TC_ZONE_RESET_ALL = 1ull << 18, /* zone reset all */ + BLK_TC_ZONE_FINISH = 1ull << 19, /* zone finish */ + BLK_TC_ZONE_OPEN = 1ull << 20, /* zone open */ + BLK_TC_ZONE_CLOSE = 1ull << 21, /* zone close */ + + BLK_TC_END_V2 = 1ull << 21, }; #define BLK_TC_SHIFT (16) -#define BLK_TC_ACT(act) ((act) << BLK_TC_SHIFT) +#define BLK_TC_ACT(act) ((u64)(act) << BLK_TC_SHIFT) /* * Basic trace actions -- cgit v1.2.3 From 1c164fcc1b08e75f1cad1532718f09cddc0ddebe Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 22 Oct 2025 13:41:13 +0200 Subject: blktrace: expose ZONE APPEND completions to blktrace Expose ZONE APPEND completions as a block trace completion action to blktrace. As tracing of zoned block commands needs the upper 32bit of the widened 64bit action, only add traces to blktrace if user-space has requested version 2 of the blktrace protocol. Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 190a3c5ab0a0..289872e51fc5 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -97,6 +97,9 @@ enum blktrace_notify { #define BLK_TA_ABORT (__BLK_TA_ABORT | BLK_TC_ACT(BLK_TC_QUEUE)) #define BLK_TA_DRV_DATA (__BLK_TA_DRV_DATA | BLK_TC_ACT(BLK_TC_DRV_DATA)) +#define BLK_TA_ZONE_APPEND (__BLK_TA_COMPLETE |\ + BLK_TC_ACT(BLK_TC_ZONE_APPEND)) + #define BLK_TN_PROCESS (__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY)) #define BLK_TN_TIMESTAMP (__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY)) #define BLK_TN_MESSAGE (__BLK_TN_MESSAGE | BLK_TC_ACT(BLK_TC_NOTIFY)) -- cgit v1.2.3 From 3f6722816a73e2017599d965683dbe71833afd7a Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 22 Oct 2025 13:41:14 +0200 Subject: blktrace: trace zone write plugging operations Trace zone write plugging operations on block devices. As tracing of zoned block commands needs the upper 32bit of the widened 64bit action, only add traces to blktrace if user-space has requested version 2 of the blktrace protocol. Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 289872e51fc5..30f3d2589365 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -62,6 +62,8 @@ enum blktrace_act { __BLK_TA_REMAP, /* bio was remapped */ __BLK_TA_ABORT, /* request aborted */ __BLK_TA_DRV_DATA, /* driver-specific binary data */ + __BLK_TA_ZONE_PLUG, /* zone write plug was plugged */ + __BLK_TA_ZONE_UNPLUG, /* zone write plug was unplugged */ __BLK_TA_CGROUP = 1 << 8, /* from a cgroup*/ }; @@ -99,6 +101,9 @@ enum blktrace_notify { #define BLK_TA_ZONE_APPEND (__BLK_TA_COMPLETE |\ BLK_TC_ACT(BLK_TC_ZONE_APPEND)) +#define BLK_TA_ZONE_PLUG (__BLK_TA_ZONE_PLUG | BLK_TC_ACT(BLK_TC_QUEUE)) +#define BLK_TA_ZONE_UNPLUG (__BLK_TA_ZONE_UNPLUG |\ + BLK_TC_ACT(BLK_TC_QUEUE)) #define BLK_TN_PROCESS (__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY)) #define BLK_TN_TIMESTAMP (__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY)) -- cgit v1.2.3 From bd26631ccdfd11701fa29e665a7f041875ba9423 Mon Sep 17 00:00:00 2001 From: Changwoo Min Date: Tue, 21 Oct 2025 07:09:07 +0900 Subject: PM: EM: Add em.yaml and autogen files Add a generic netlink spec in YAML format and autogenerate boilerplate code using ynl-regen.sh to introduce a generic netlink for the energy model. It allows a userspace program to read the performance domain and its energy model. It notifies the userspace program when a performance domain is created or deleted or its energy model is updated through a multicast interface. Specifically, it supports two commands: - EM_CMD_GET_PDS: Get the list of information for all performance domains. - EM_CMD_GET_PD_TABLE: Get the energy model table of a performance domain. Also, it supports three notification events: - EM_CMD_PD_CREATED: When a performance domain is created. - EM_CMD_PD_DELETED: When a performance domain is deleted. - EM_CMD_PD_UPDATED: When the energy model table of a performance domain is updated. Finally, update MAINTAINERS to include new files. Signed-off-by: Changwoo Min Reviewed-by: Lukasz Luba Link: https://patch.msgid.link/20251020220914.320832-4-changwoo@igalia.com Signed-off-by: Rafael J. Wysocki --- include/uapi/linux/energy_model.h | 62 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/uapi/linux/energy_model.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/energy_model.h b/include/uapi/linux/energy_model.h new file mode 100644 index 000000000000..4ec4c0eabbbb --- /dev/null +++ b/include/uapi/linux/energy_model.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/em.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_ENERGY_MODEL_H +#define _UAPI_LINUX_ENERGY_MODEL_H + +#define EM_FAMILY_NAME "em" +#define EM_FAMILY_VERSION 1 + +enum { + EM_A_PDS_PD = 1, + + __EM_A_PDS_MAX, + EM_A_PDS_MAX = (__EM_A_PDS_MAX - 1) +}; + +enum { + EM_A_PD_PAD = 1, + EM_A_PD_PD_ID, + EM_A_PD_FLAGS, + EM_A_PD_CPUS, + + __EM_A_PD_MAX, + EM_A_PD_MAX = (__EM_A_PD_MAX - 1) +}; + +enum { + EM_A_PD_TABLE_PD_ID = 1, + EM_A_PD_TABLE_PS, + + __EM_A_PD_TABLE_MAX, + EM_A_PD_TABLE_MAX = (__EM_A_PD_TABLE_MAX - 1) +}; + +enum { + EM_A_PS_PAD = 1, + EM_A_PS_PERFORMANCE, + EM_A_PS_FREQUENCY, + EM_A_PS_POWER, + EM_A_PS_COST, + EM_A_PS_FLAGS, + + __EM_A_PS_MAX, + EM_A_PS_MAX = (__EM_A_PS_MAX - 1) +}; + +enum { + EM_CMD_GET_PDS = 1, + EM_CMD_GET_PD_TABLE, + EM_CMD_PD_CREATED, + EM_CMD_PD_UPDATED, + EM_CMD_PD_DELETED, + + __EM_CMD_MAX, + EM_CMD_MAX = (__EM_CMD_MAX - 1) +}; + +#define EM_MCGRP_EVENT "event" + +#endif /* _UAPI_LINUX_ENERGY_MODEL_H */ -- cgit v1.2.3 From 531b87d865eb9e625c2e46ec8f06a65a6157ee45 Mon Sep 17 00:00:00 2001 From: Mykyta Yatsenko Date: Sun, 26 Oct 2025 20:38:45 +0000 Subject: bpf: widen dynptr size/offset to 64 bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Dynptr currently caps size and offset at 24 bits, which isn’t sufficient for file-backed use cases; even 32 bits can be limiting. Refactor dynptr helpers/kfuncs to use 64-bit size and offset, ensuring consistency across the APIs. This change does not affect internals of xdp, skb or other dynptrs, which continue to behave as before. Also it does not break binary compatibility. The widening enables large-file access support via dynptr, implemented in the next patches. Signed-off-by: Mykyta Yatsenko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20251026203853.135105-3-mykyta.yatsenko5@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6829936d33f5..77edd0253989 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5618,7 +5618,7 @@ union bpf_attr { * Return * *sk* if casting is valid, or **NULL** otherwise. * - * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * long bpf_dynptr_from_mem(void *data, u64 size, u64 flags, struct bpf_dynptr *ptr) * Description * Get a dynptr to local memory *data*. * @@ -5661,7 +5661,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u64 len, const struct bpf_dynptr *src, u64 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5671,7 +5671,7 @@ union bpf_attr { * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if * *flags* is not 0. * - * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u64 offset, void *src, u64 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5692,7 +5692,7 @@ union bpf_attr { * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs, * other errors correspond to errors returned by **bpf_skb_store_bytes**\ (). * - * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u64 offset, u64 len) * Description * Get a pointer to the underlying dynptr data. * -- cgit v1.2.3 From 82cb5be6ad64198a3a028aeb49dcc7f6224d558a Mon Sep 17 00:00:00 2001 From: Wilfred Mallawa Date: Wed, 22 Oct 2025 10:19:36 +1000 Subject: net/tls: support setting the maximum payload size During a handshake, an endpoint may specify a maximum record size limit. Currently, the kernel defaults to TLS_MAX_PAYLOAD_SIZE (16KB) for the maximum record size. Meaning that, the outgoing records from the kernel can exceed a lower size negotiated during the handshake. In such a case, the TLS endpoint must send a fatal "record_overflow" alert [1], and thus the record is discarded. Upcoming Western Digital NVMe-TCP hardware controllers implement TLS support. For these devices, supporting TLS record size negotiation is necessary because the maximum TLS record size supported by the controller is less than the default 16KB currently used by the kernel. Currently, there is no way to inform the kernel of such a limit. This patch adds support to a new setsockopt() option `TLS_TX_MAX_PAYLOAD_LEN` that allows for setting the maximum plaintext fragment size. Once set, outgoing records are no larger than the size specified. This option can be used to specify the record size limit. [1] https://www.rfc-editor.org/rfc/rfc8449 Signed-off-by: Wilfred Mallawa Reviewed-by: Sabrina Dubroca Link: https://patch.msgid.link/20251022001937.20155-1-wilfred.opensource@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index b66a800389cc..b8b9c42f848c 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -41,6 +41,7 @@ #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 */ +#define TLS_TX_MAX_PAYLOAD_LEN 5 /* Maximum plaintext size */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -194,6 +195,7 @@ enum { TLS_INFO_RXCONF, TLS_INFO_ZC_RO_TX, TLS_INFO_RX_NO_PAD, + TLS_INFO_TX_MAX_PAYLOAD_LEN, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) -- cgit v1.2.3 From feeaf1346f80ffb181b6f9b739628103aa73b067 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Sat, 18 Oct 2025 11:57:36 +0800 Subject: bpf: Add overwrite mode for BPF ring buffer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the BPF ring buffer is full, a new event cannot be recorded until one or more old events are consumed to make enough space for it. In cases such as fault diagnostics, where recent events are more useful than older ones, this mechanism may lead to critical events being lost. So add overwrite mode for BPF ring buffer to address it. In this mode, the new event overwrites the oldest event when the buffer is full. The basic idea is as follows: 1. producer_pos tracks the next position to record new event. When there is enough free space, producer_pos is simply advanced by producer to make space for the new event. 2. To avoid waiting for consumer when the buffer is full, a new variable, overwrite_pos, is introduced for producer. It points to the oldest event committed in the buffer. It is advanced by producer to discard one or more oldest events to make space for the new event when the buffer is full. 3. pending_pos tracks the oldest event to be committed. pending_pos is never passed by producer_pos, so multiple producers never write to the same position at the same time. The following example diagrams show how it works in a 4096-byte ring buffer. 1. At first, {producer,overwrite,pending,consumer}_pos are all set to 0. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | | +-----------------------------------------------------------------------+ ^ | | producer_pos = 0 overwrite_pos = 0 pending_pos = 0 consumer_pos = 0 2. Now reserve a 512-byte event A. There is enough free space, so A is allocated at offset 0. And producer_pos is advanced to 512, the end of A. Since A is not submitted, the BUSY bit is set. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | A | | | [BUSY] | | +-----------------------------------------------------------------------+ ^ ^ | | | | | producer_pos = 512 | overwrite_pos = 0 pending_pos = 0 consumer_pos = 0 3. Reserve event B, size 1024. B is allocated at offset 512 with BUSY bit set, and producer_pos is advanced to the end of B. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | A | B | | | [BUSY] | [BUSY] | | +-----------------------------------------------------------------------+ ^ ^ | | | | | producer_pos = 1536 | overwrite_pos = 0 pending_pos = 0 consumer_pos = 0 4. Reserve event C, size 2048. C is allocated at offset 1536, and producer_pos is advanced to 3584. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | | A | B | C | | | [BUSY] | [BUSY] | [BUSY] | | +-----------------------------------------------------------------------+ ^ ^ | | | | | producer_pos = 3584 | overwrite_pos = 0 pending_pos = 0 consumer_pos = 0 5. Submit event A. The BUSY bit of A is cleared. B becomes the oldest event to be committed, so pending_pos is advanced to 512, the start of B. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | | A | B | C | | | | [BUSY] | [BUSY] | | +-----------------------------------------------------------------------+ ^ ^ ^ | | | | | | | pending_pos = 512 producer_pos = 3584 | overwrite_pos = 0 consumer_pos = 0 6. Submit event B. The BUSY bit of B is cleared, and pending_pos is advanced to the start of C, which is now the oldest event to be committed. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | | A | B | C | | | | | [BUSY] | | +-----------------------------------------------------------------------+ ^ ^ ^ | | | | | | | pending_pos = 1536 producer_pos = 3584 | overwrite_pos = 0 consumer_pos = 0 7. Reserve event D, size 1536 (3 * 512). There are 2048 bytes not being written between producer_pos (currently 3584) and pending_pos, so D is allocated at offset 3584, and producer_pos is advanced by 1536 (from 3584 to 5120). Since event D will overwrite all bytes of event A and the first 512 bytes of event B, overwrite_pos is advanced to the start of event C, the oldest event that is not overwritten. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | | D End | | C | D Begin| | [BUSY] | | [BUSY] | [BUSY] | +-----------------------------------------------------------------------+ ^ ^ ^ | | | | | pending_pos = 1536 | | overwrite_pos = 1536 | | | producer_pos=5120 | consumer_pos = 0 8. Reserve event E, size 1024. Although there are 512 bytes not being written between producer_pos and pending_pos, E cannot be reserved, as it would overwrite the first 512 bytes of event C, which is still being written. 9. Submit event C and D. pending_pos is advanced to the end of D. 0 512 1024 1536 2048 2560 3072 3584 4096 +-----------------------------------------------------------------------+ | | | | | | D End | | C | D Begin| | | | | | +-----------------------------------------------------------------------+ ^ ^ ^ | | | | | overwrite_pos = 1536 | | | producer_pos=5120 | pending_pos=5120 | consumer_pos = 0 The performance data for overwrite mode will be provided in a follow-up patch that adds overwrite-mode benchmarks. A sample of performance data for non-overwrite mode, collected on an x86_64 CPU and an arm64 CPU, before and after this patch, is shown below. As we can see, no obvious performance regression occurs. - x86_64 (AMD EPYC 9654) Before: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 11.623 ± 0.027M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 15.812 ± 0.014M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 7.871 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 6.703 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 2.896 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 2.054 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 1.864 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 1.580 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 1.484 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 1.369 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.316 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 1.272 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 1.239 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 1.226 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 1.213 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 1.193 ± 0.001M/s (drops 0.000 ± 0.000M/s) After: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 11.845 ± 0.036M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 15.889 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 8.155 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 6.708 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 2.918 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 2.065 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 1.870 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 1.582 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 1.482 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 1.372 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.323 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 1.264 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 1.236 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 1.209 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 1.189 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 1.165 ± 0.002M/s (drops 0.000 ± 0.000M/s) - arm64 (HiSilicon Kunpeng 920) Before: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 11.310 ± 0.623M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 9.947 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 6.634 ± 0.011M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 4.502 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.888 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.372 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 3.189 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 2.998 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 3.086 ± 0.018M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.845 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 2.815 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.771 ± 0.009M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.814 ± 0.011M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.752 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.695 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 2.710 ± 0.006M/s (drops 0.000 ± 0.000M/s) After: Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 11.283 ± 0.550M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 9.993 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 6.898 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 5.257 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.830 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.528 ± 0.013M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 3.265 ± 0.018M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 2.990 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 2.929 ± 0.014M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.898 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 2.818 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.789 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.770 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.651 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.669 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 2.695 ± 0.009M/s (drops 0.000 ± 0.000M/s) Signed-off-by: Xu Kuohai Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20251018035738.4039621-2-xukuohai@huaweicloud.com --- include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 77edd0253989..1d73f165394d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1430,6 +1430,9 @@ enum { /* Do not translate kernel bpf_arena pointers to user pointers */ BPF_F_NO_USER_CONV = (1U << 18), + +/* Enable BPF ringbuf overwrite mode */ + BPF_F_RB_OVERWRITE = (1U << 19), }; /* Flags for BPF_PROG_QUERY. */ @@ -6231,6 +6234,7 @@ enum { BPF_RB_RING_SIZE = 1, BPF_RB_CONS_POS = 2, BPF_RB_PROD_POS = 3, + BPF_RB_OVERWRITE_POS = 4, }; /* BPF ring buffer constants */ -- cgit v1.2.3 From f74ee32963f1b74865fe679e2475450434fea51c Mon Sep 17 00:00:00 2001 From: Qinxin Xia Date: Tue, 28 Oct 2025 20:09:00 +0800 Subject: tools/dma: move dma_map_benchmark from selftests to tools/dma dma_map_benchmark is a standalone developer tool rather than an automated selftest. It has no pass/fail criteria, expects manual invocation, and is built as a normal userspace binary. Move it to tools/dma/ and add a minimal Makefile. Suggested-by: Marek Szyprowski Suggested-by: Barry Song Signed-off-by: Qinxin Xia Acked-by: Barry Song Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20251028120900.2265511-3-xiaqinxin@huawei.com --- include/uapi/linux/map_benchmark.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/uapi/linux/map_benchmark.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.h new file mode 100644 index 000000000000..c2d91088a40d --- /dev/null +++ b/include/uapi/linux/map_benchmark.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2022-2025 HiSilicon Limited. + */ + +#ifndef _UAPI_DMA_BENCHMARK_H +#define _UAPI_DMA_BENCHMARK_H + +#include + +#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) +#define DMA_MAP_MAX_THREADS 1024 +#define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) + +#define DMA_MAP_BIDIRECTIONAL 0 +#define DMA_MAP_TO_DEVICE 1 +#define DMA_MAP_FROM_DEVICE 2 + +struct map_benchmark { + __u64 avg_map_100ns; /* average map latency in 100ns */ + __u64 map_stddev; /* standard deviation of map latency */ + __u64 avg_unmap_100ns; /* as above */ + __u64 unmap_stddev; + __u32 threads; /* how many threads will do map/unmap in parallel */ + __u32 seconds; /* how long the test will last */ + __s32 node; /* which numa node this benchmark will run on */ + __u32 dma_bits; /* DMA addressing capability */ + __u32 dma_dir; /* DMA data direction */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ +}; + +#endif /* _UAPI_DMA_BENCHMARK_H */ -- cgit v1.2.3 From c69993ecdd4dfde2b7da08b022052a33b203da07 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Oct 2025 15:17:05 +0200 Subject: perf: Support deferred user unwind Add support for deferred userspace unwind to perf. Where perf currently relies on in-place stack unwinding; from NMI context and all that. This moves the userspace part of the unwind to right before the return-to-userspace. This has two distinct benefits, the biggest is that it moves the unwind to a faultable context. It becomes possible to fault in debug info (.eh_frame, SFrame etc.) that might not otherwise be readily available. And secondly, it de-duplicates the user callchain where multiple samples happen during the same kernel entry. To facilitate this the perf interface is extended with a new record type: PERF_RECORD_CALLCHAIN_DEFERRED and two new attribute flags: perf_event_attr::defer_callchain - to request the user unwind be deferred perf_event_attr::defer_output - to request PERF_RECORD_CALLCHAIN_DEFERRED records The existing PERF_RECORD_SAMPLE callchain section gets a new context type: PERF_CONTEXT_USER_DEFERRED After which will come a single entry, denoting the 'cookie' of the deferred callchain that should be attached here, matching the 'cookie' field of the above mentioned PERF_RECORD_CALLCHAIN_DEFERRED. The 'defer_callchain' flag is expected on all events with PERF_SAMPLE_CALLCHAIN. The 'defer_output' flag is expect on the event responsible for collecting side-band events (like mmap, comm etc.). Setting 'defer_output' on multiple events will get you duplicated PERF_RECORD_CALLCHAIN_DEFERRED records. Based on earlier patches by Josh and Steven. Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20251023150002.GR4067720@noisy.programming.kicks-ass.net --- include/uapi/linux/perf_event.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 78a362b80027..d292f96bc06f 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -463,7 +463,9 @@ struct perf_event_attr { inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ - __reserved_1 : 26; + defer_callchain: 1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */ + defer_output : 1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */ + __reserved_1 : 24; union { __u32 wakeup_events; /* wake up every n events */ @@ -1239,6 +1241,22 @@ enum perf_event_type { */ PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + /* + * This user callchain capture was deferred until shortly before + * returning to user space. Previous samples would have kernel + * callchains only and they need to be stitched with this to make full + * callchains. + * + * struct { + * struct perf_event_header header; + * u64 cookie; + * u64 nr; + * u64 ips[nr]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CALLCHAIN_DEFERRED = 22, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -1269,6 +1287,7 @@ enum perf_callchain_context { PERF_CONTEXT_HV = (__u64)-32, PERF_CONTEXT_KERNEL = (__u64)-128, PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_USER_DEFERRED = (__u64)-640, PERF_CONTEXT_GUEST = (__u64)-2048, PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, -- cgit v1.2.3 From 4061c43a99772c66c378cfacaa71550ab3b35909 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 28 Oct 2025 09:45:48 +0100 Subject: pidfs: add missing PIDFD_INFO_SIZE_VER1 We grew struct pidfd_info not too long ago. Link: https://patch.msgid.link/20251028-work-coredump-signal-v1-3-ca449b7b7aa0@kernel.org Fixes: 1d8db6fd698d ("pidfs, coredump: add PIDFD_INFO_COREDUMP") Reviewed-by: Alexander Mikhalitsyn Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- include/uapi/linux/pidfd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 957db425d459..6ccbabd9a68d 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -28,6 +28,7 @@ #define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ +#define PIDFD_INFO_SIZE_VER1 72 /* sizeof second published struct */ /* * Values for @coredump_mask in pidfd_info. -- cgit v1.2.3 From dfd78546c95330db2252e0d7e937a15ab5eddb4e Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 28 Oct 2025 09:45:50 +0100 Subject: pidfd: add a new supported_mask field Some of the future fields in struct pidfd_info can be optional. If the kernel has nothing to emit in that field, then it doesn't set the flag in the reply. This presents a problem: There is currently no way to know what mask flags the kernel supports since one can't always count on them being in the reply. Add a new PIDFD_INFO_SUPPORTED_MASK flag and field that the kernel can set in the reply. Userspace can use this to determine if the fields it requires from the kernel are supported. This also gives us a way to deprecate fields in the future, if that should become necessary. Link: https://patch.msgid.link/20251028-work-coredump-signal-v1-5-ca449b7b7aa0@kernel.org Reviewed-by: Alexander Mikhalitsyn Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- include/uapi/linux/pidfd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 6ccbabd9a68d..e05caa0e00fe 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -26,9 +26,11 @@ #define PIDFD_INFO_CGROUPID (1UL << 2) /* Always returned if available, even if not requested */ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ #define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ +#define PIDFD_INFO_SUPPORTED_MASK (1UL << 5) /* Want/got supported mask flags */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ #define PIDFD_INFO_SIZE_VER1 72 /* sizeof second published struct */ +#define PIDFD_INFO_SIZE_VER2 80 /* sizeof third published struct */ /* * Values for @coredump_mask in pidfd_info. @@ -94,6 +96,7 @@ struct pidfd_info { __s32 exit_code; __u32 coredump_mask; __u32 __spare1; + __u64 supported_mask; /* Mask flags that this kernel supports */ }; #define PIDFS_IOCTL_MAGIC 0xFF -- cgit v1.2.3 From 036375522be8425874e9e0f907c7127e315c7a52 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 28 Oct 2025 09:45:53 +0100 Subject: pidfs: expose coredump signal Userspace needs access to the signal that caused the coredump before the coredumping process has been reaped. Expose it as part of the coredump information in struct pidfd_info. After the process has been reaped that info is also available as part of PIDFD_INFO_EXIT's exit_code field. Link: https://patch.msgid.link/20251028-work-coredump-signal-v1-8-ca449b7b7aa0@kernel.org Reviewed-by: Alexander Mikhalitsyn Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- include/uapi/linux/pidfd.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index e05caa0e00fe..ea9a6811fc76 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -27,6 +27,7 @@ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ #define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ #define PIDFD_INFO_SUPPORTED_MASK (1UL << 5) /* Want/got supported mask flags */ +#define PIDFD_INFO_COREDUMP_SIGNAL (1UL << 6) /* Always returned if PIDFD_INFO_COREDUMP is requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ #define PIDFD_INFO_SIZE_VER1 72 /* sizeof second published struct */ @@ -94,8 +95,10 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; - __u32 coredump_mask; - __u32 __spare1; + struct /* coredump info */ { + __u32 coredump_mask; + __u32 coredump_signal; + }; __u64 supported_mask; /* Mask flags that this kernel supports */ }; -- cgit v1.2.3 From 30176bf7c871681df506f3165ffe76ec462db991 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Wed, 29 Oct 2025 16:32:06 +0100 Subject: dpll: add phase-adjust-gran pin attribute Phase-adjust values are currently limited by a min-max range. Some hardware requires, for certain pin types, that values be multiples of a specific granularity, as in the zl3073x driver. Add a `phase-adjust-gran` pin attribute and an appropriate field in dpll_pin_properties. If set by the driver, use its value to validate user-provided phase-adjust values. Reviewed-by: Michal Schmidt Reviewed-by: Petr Oros Tested-by: Prathosh Satish Signed-off-by: Ivan Vecera Reviewed-by: Jiri Pirko Reviewed-by: Arkadiusz Kubalewski Link: https://patch.msgid.link/20251029153207.178448-2-ivecera@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/dpll.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index ab1725a954d7..69d35570ac4f 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -251,6 +251,7 @@ enum dpll_a_pin { DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, DPLL_A_PIN_ESYNC_PULSE, DPLL_A_PIN_REFERENCE_SYNC, + DPLL_A_PIN_PHASE_ADJUST_GRAN, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) -- cgit v1.2.3 From bc49af56eea866c34d21bf582f65b02fc8c06ec3 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Tue, 28 Oct 2025 20:34:23 -0700 Subject: blktrace: add support for REQ_OP_WRITE_ZEROES tracing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, REQ_OP_WRITE_ZEROES operations are not handled in the blktrace infrastructure, resulting in incorrect or missing operation labels in ftrace blktrace output. This manifests as write-zeroes operations appearing with incorrect labels like "N" instead of a proper "WZ" designation. This patch adds complete support for REQ_OP_WRITE_ZEROES across the blktrace infrastructure: Add BLK_TC_WRITE_ZEROES trace category in blktrace_api.h and update BLK_TC_END_V2 marker accordingly Map REQ_OP_WRITE_ZEROES to BLK_TC_WRITE_ZEROES in __blk_add_trace() to ensure proper trace event categorization Update fill_rwbs() to generate "WZ" label for write-zeroes operations in ftrace output, making them easily identifiable Add "write-zeroes" string mapping in act_to_str array for debugfs filter interface Update blk_fill_rwbs() to handle REQ_OP_WRITE_ZEROES for block layer event tracing With this fix, write-zeroes operations are now correctly traced and displayed. =========================================================== BEFORE THIS PATCH =========================================================== blkdiscard -z -o 0 -l 40960 /dev/nvme0n1 blkdiscard-3809 [030] ..... 1212.253701: block_bio_queue: 259,0 NS 0 + 80 [blkdiscard] blkdiscard-3809 [030] ..... 1212.253703: block_getrq: 259,0 NS 0 + 80 [blkdiscard] blkdiscard-3809 [030] ..... 1212.253704: block_io_start: 259,0 NS 40960 () 0 + 80 be,0,4 [blkdiscard] blkdiscard-3809 [030] ..... 1212.253704: block_plug: [blkdiscard] blkdiscard-3809 [030] ..... 1212.253706: block_unplug: [blkdiscard] 1 blkdiscard-3809 [030] ..... 1212.253706: block_rq_insert: 259,0 NS 40960 () 0 + 80 be,0,4 [blkdiscard] kworker/30:1H-566 [030] ..... 1212.253726: block_rq_issue: 259,0 NS 40960 () 0 + 80 be,0,4 [kworker/30:1H] -0 [030] d.h1. 1212.253957: block_rq_complete: 259,0 NS () 0 + 80 be,0,4 [0] -0 [030] dNh1. 1212.253960: block_io_done: 259,0 NS 0 () 0 + 0 none,0,0 [swapper/30] Trace Event Breakdown: Event | Device | Op | Sector | Sectors | Byte Size | Calculation block_bio_queue | 259,0 | NS | 0 | 80 | - | 80 × 512 = 40,960 block_getrq | 259,0 | NS | 0 | 80 | - | 80 × 512 = 40,960 block_io_start | 259,0 | NS | 0 | 80 | 40960 | Direct from trace block_rq_insert | 259,0 | NS | 0 | 80 | 40960 | Direct from trace block_rq_issue | 259,0 | NS | 0 | 80 | 40960 | Direct from trace block_rq_complete | 259,0 | NS | 0 | 80 | - | 80 × 512 = 40,960 block_io_done | 259,0 | NS | 0 | 0 | 0 | Completion (no data) Total Bytes Transferred: Sectors: 80 Bytes: 80 × 512 = 40,960 bytes =========================================================== AFTER THIS PATCH =========================================================== blkdiscard -z -o 0 -l 40960 /dev/nvme0n1 blkdiscard-2477 [020] ..... 960.989131: block_bio_queue: 259,0 WZS 0 + 80 [blkdiscard] blkdiscard-2477 [020] ..... 960.989134: block_getrq: 259,0 WZS 0 + 80 [blkdiscard] blkdiscard-2477 [020] ..... 960.989135: block_io_start: 259,0 WZS 40960 () 0 + 80 be,0,4 [blkdiscard] blkdiscard-2477 [020] ..... 960.989138: block_plug: [blkdiscard] blkdiscard-2477 [020] ..... 960.989140: block_unplug: [blkdiscard] 1 blkdiscard-2477 [020] ..... 960.989141: block_rq_insert: 259,0 WZS 40960 () 0 + 80 be,0,4 [blkdiscard] kworker/20:1H-736 [020] ..... 960.989166: block_rq_issue: 259,0 WZS 40960 () 0 + 80 be,0,4 [kworker/20:1H] -0 [020] d.h1. 960.989476: block_rq_complete: 259,0 WZS () 0 + 80 be,0,4 [0] -0 [020] dNh1. 960.989482: block_io_done: 259,0 WZS 0 () 0 + 0 none,0,0 [swapper/20] Trace Event Breakdown: Event | Device | Op | Sector | Sectors | Byte Size | Calculation block_bio_queue | 259,0 | WZS | 0 | 80 | - | 80 × 512 = 40,960 block_getrq | 259,0 | WZS | 0 | 80 | - | 80 × 512 = 40,960 block_io_start | 259,0 | WZS | 0 | 80 | 40960 | Direct from trace block_rq_insert | 259,0 | WZS | 0 | 80 | 40960 | Direct from trace block_rq_issue | 259,0 | WZS | 0 | 80 | 40960 | Direct from trace block_rq_complete | 259,0 | WZS | 0 | 80 | - | 80 × 512 = 40,960 block_io_done | 259,0 | WZS | 0 | 0 | 0 | Completion (no data) Total Bytes Transferred: Sectors: 80 Bytes: 80 × 512 = 40,960 bytes Tested with ftrace blktrace on NVMe devices using blkdiscard with the -z (write-zeroes) flag. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 30f3d2589365..7c092d9f3aa4 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -35,7 +35,9 @@ enum blktrace_cat { BLK_TC_ZONE_OPEN = 1ull << 20, /* zone open */ BLK_TC_ZONE_CLOSE = 1ull << 21, /* zone close */ - BLK_TC_END_V2 = 1ull << 21, + BLK_TC_WRITE_ZEROES = 1ull << 22, /* write-zeroes */ + + BLK_TC_END_V2 = 1ull << 22, }; #define BLK_TC_SHIFT (16) -- cgit v1.2.3 From 3760342fd6312416491d536144e39297fa5b1950 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 29 Oct 2025 13:20:28 +0100 Subject: nstree: assign fixed ids to the initial namespaces The initial set of namespace comes with fixed inode numbers making it easy for userspace to identify them solely based on that information. This has long preceeded anything here. Similarly, let's assign fixed namespace ids for the initial namespaces. Kill the cookie and use a sequentially increasing number. This has the nice side-effect that the owning user namespace will always have a namespace id that is smaller than any of it's descendant namespaces. Link: https://patch.msgid.link/20251029-work-namespace-nstree-listns-v4-15-2e6f823ebdc0@kernel.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index e098759ec917..f8bc2aad74d6 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -67,4 +67,18 @@ struct nsfs_file_handle { #define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */ #define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */ +enum init_ns_id { + IPC_NS_INIT_ID = 1ULL, + UTS_NS_INIT_ID = 2ULL, + USER_NS_INIT_ID = 3ULL, + PID_NS_INIT_ID = 4ULL, + CGROUP_NS_INIT_ID = 5ULL, + TIME_NS_INIT_ID = 6ULL, + NET_NS_INIT_ID = 7ULL, + MNT_NS_INIT_ID = 8ULL, +#ifdef __KERNEL__ + NS_LAST_INIT_ID = MNT_NS_INIT_ID, +#endif +}; + #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From 76b6f5dfb3fda76fce1f9990d6fa58adc711122b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 29 Oct 2025 13:20:32 +0100 Subject: nstree: add listns() Add a new listns() system call that allows userspace to iterate through namespaces in the system. This provides a programmatic interface to discover and inspect namespaces, enhancing existing namespace apis. Currently, there is no direct way for userspace to enumerate namespaces in the system. Applications must resort to scanning /proc//ns/ across all processes, which is: 1. Inefficient - requires iterating over all processes 2. Incomplete - misses inactive namespaces that aren't attached to any running process but are kept alive by file descriptors, bind mounts, or parent namespace references 3. Permission-heavy - requires access to /proc for many processes 4. No ordering or ownership. 5. No filtering per namespace type: Must always iterate and check all namespaces. The list goes on. The listns() system call solves these problems by providing direct kernel-level enumeration of namespaces. It is similar to listmount() but obviously tailored to namespaces. /* * @req: Pointer to struct ns_id_req specifying search parameters * @ns_ids: User buffer to receive namespace IDs * @nr_ns_ids: Size of ns_ids buffer (maximum number of IDs to return) * @flags: Reserved for future use (must be 0) */ ssize_t listns(const struct ns_id_req *req, u64 *ns_ids, size_t nr_ns_ids, unsigned int flags); Returns: - On success: Number of namespace IDs written to ns_ids - On error: Negative error code /* * @size: Structure size * @ns_id: Starting point for iteration; use 0 for first call, then * use the last returned ID for subsequent calls to paginate * @ns_type: Bitmask of namespace types to include (from enum ns_type): * 0: Return all namespace types * MNT_NS: Mount namespaces * NET_NS: Network namespaces * USER_NS: User namespaces * etc. Can be OR'd together * @user_ns_id: Filter results to namespaces owned by this user namespace: * 0: Return all namespaces (subject to permission checks) * LISTNS_CURRENT_USER: Namespaces owned by caller's user namespace * Other value: Namespaces owned by the specified user namespace ID */ struct ns_id_req { __u32 size; /* sizeof(struct ns_id_req) */ __u32 spare; /* Reserved, must be 0 */ __u64 ns_id; /* Last seen namespace ID (for pagination) */ __u32 ns_type; /* Filter by namespace type(s) */ __u32 spare2; /* Reserved, must be 0 */ __u64 user_ns_id; /* Filter by owning user namespace */ }; Example 1: List all namespaces void list_all_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, /* Start from beginning */ .ns_type = 0, /* All types */ .user_ns_id = 0, /* All user namespaces */ }; uint64_t ids[100]; ssize_t ret; printf("All namespaces in the system:\n"); do { ret = listns(&req, ids, 100, 0); if (ret < 0) { perror("listns"); break; } for (ssize_t i = 0; i < ret; i++) printf(" Namespace ID: %llu\n", (unsigned long long)ids[i]); /* Continue from last seen ID */ if (ret > 0) req.ns_id = ids[ret - 1]; } while (ret == 100); /* Buffer was full, more may exist */ } Example 2: List network namespaces only void list_network_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = NET_NS, /* Only network namespaces */ .user_ns_id = 0, }; uint64_t ids[100]; ssize_t ret; ret = listns(&req, ids, 100, 0); if (ret < 0) { perror("listns"); return; } printf("Network namespaces: %zd found\n", ret); for (ssize_t i = 0; i < ret; i++) printf(" netns ID: %llu\n", (unsigned long long)ids[i]); } Example 3: List namespaces owned by current user namespace void list_owned_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = 0, /* All types */ .user_ns_id = LISTNS_CURRENT_USER, /* Current userns */ }; uint64_t ids[100]; ssize_t ret; ret = listns(&req, ids, 100, 0); if (ret < 0) { perror("listns"); return; } printf("Namespaces owned by my user namespace: %zd\n", ret); for (ssize_t i = 0; i < ret; i++) printf(" ns ID: %llu\n", (unsigned long long)ids[i]); } Example 4: List multiple namespace types void list_network_and_mount_namespaces(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = NET_NS | MNT_NS, /* Network and mount */ .user_ns_id = 0, }; uint64_t ids[100]; ssize_t ret; ret = listns(&req, ids, 100, 0); printf("Network and mount namespaces: %zd found\n", ret); } Example 5: Pagination through large namespace sets void list_all_with_pagination(void) { struct ns_id_req req = { .size = sizeof(req), .ns_id = 0, .ns_type = 0, .user_ns_id = 0, }; uint64_t ids[50]; size_t total = 0; ssize_t ret; printf("Enumerating all namespaces with pagination:\n"); while (1) { ret = listns(&req, ids, 50, 0); if (ret < 0) { perror("listns"); break; } if (ret == 0) break; /* No more namespaces */ total += ret; printf(" Batch: %zd namespaces\n", ret); /* Last ID in this batch becomes start of next batch */ req.ns_id = ids[ret - 1]; if (ret < 50) break; /* Partial batch = end of results */ } printf("Total: %zu namespaces\n", total); } Permission Model listns() respects namespace isolation and capabilities: (1) Global listing (user_ns_id = 0): - Requires CAP_SYS_ADMIN in the namespace's owning user namespace - OR the namespace must be in the caller's namespace context (e.g., a namespace the caller is currently using) - User namespaces additionally allow listing if the caller has CAP_SYS_ADMIN in that user namespace itself (2) Owner-filtered listing (user_ns_id != 0): - Requires CAP_SYS_ADMIN in the specified owner user namespace - OR the namespace must be in the caller's namespace context - This allows unprivileged processes to enumerate namespaces they own (3) Visibility: - Only "active" namespaces are listed - A namespace is active if it has a non-zero __ns_ref_active count - This includes namespaces used by running processes, held by open file descriptors, or kept active by bind mounts - Inactive namespaces (kept alive only by internal kernel references) are not visible via listns() Link: https://patch.msgid.link/20251029-work-namespace-nstree-listns-v4-19-2e6f823ebdc0@kernel.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index f8bc2aad74d6..a25e38d1c874 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -81,4 +81,48 @@ enum init_ns_id { #endif }; +enum ns_type { + TIME_NS = (1ULL << 7), /* CLONE_NEWTIME */ + MNT_NS = (1ULL << 17), /* CLONE_NEWNS */ + CGROUP_NS = (1ULL << 25), /* CLONE_NEWCGROUP */ + UTS_NS = (1ULL << 26), /* CLONE_NEWUTS */ + IPC_NS = (1ULL << 27), /* CLONE_NEWIPC */ + USER_NS = (1ULL << 28), /* CLONE_NEWUSER */ + PID_NS = (1ULL << 29), /* CLONE_NEWPID */ + NET_NS = (1ULL << 30), /* CLONE_NEWNET */ +}; + +/** + * struct ns_id_req - namespace ID request structure + * @size: size of this structure + * @spare: reserved for future use + * @filter: filter mask + * @ns_id: last namespace id + * @user_ns_id: owning user namespace ID + * + * Structure for passing namespace ID and miscellaneous parameters to + * statns(2) and listns(2). + * + * For statns(2) @param represents the request mask. + * For listns(2) @param represents the last listed mount id (or zero). + */ +struct ns_id_req { + __u32 size; + __u32 spare; + __u64 ns_id; + struct /* listns */ { + __u32 ns_type; + __u32 spare2; + __u64 user_ns_id; + }; +}; + +/* + * Special @user_ns_id value that can be passed to listns() + */ +#define LISTNS_CURRENT_USER 0xffffffffffffffff /* Caller's userns */ + +/* List of all ns_id_req versions. */ +#define NS_ID_REQ_SIZE_VER0 32 /* sizeof first published struct */ + #endif /* __LINUX_NSFS_H */ -- cgit v1.2.3 From c18d4b190a46651726c9a952667c74d2deb33c28 Mon Sep 17 00:00:00 2001 From: Samiullah Khawaja Date: Tue, 28 Oct 2025 20:30:05 +0000 Subject: net: Extend NAPI threaded polling to allow kthread based busy polling Add a new state NAPI_STATE_THREADED_BUSY_POLL to the NAPI state enum to enable and disable threaded busy polling. When threaded busy polling is enabled for a NAPI, enable NAPI_STATE_THREADED also. When the threaded NAPI is scheduled, set NAPI_STATE_IN_BUSY_POLL to signal napi_complete_done not to rearm interrupts. Whenever NAPI_STATE_THREADED_BUSY_POLL is unset, the NAPI_STATE_IN_BUSY_POLL will be unset, napi_complete_done unsets the NAPI_STATE_SCHED_THREADED bit also, which in turn will make the kthread go to sleep. Signed-off-by: Samiullah Khawaja Reviewed-by: Willem de Bruijn Acked-by: Martin Karsten Tested-by: Martin Karsten Link: https://patch.msgid.link/20251028203007.575686-2-skhawaja@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/netdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 48eb49aa03d4..048c8de1a130 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -80,6 +80,7 @@ enum netdev_qstats_scope { enum netdev_napi_threaded { NETDEV_NAPI_THREADED_DISABLED, NETDEV_NAPI_THREADED_ENABLED, + NETDEV_NAPI_THREADED_BUSY_POLL, }; enum { -- cgit v1.2.3 From e6e93fb01302e9b7a15d17f3b8a00eff8a601654 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 27 Oct 2025 13:27:59 +0100 Subject: ethtool: netlink: add ETHTOOL_MSG_MSE_GET and wire up PHY MSE access Introduce the userspace entry point for PHY MSE diagnostics via ethtool netlink. This exposes the core API added previously and returns both capability information and one or more snapshots. Userspace sends ETHTOOL_MSG_MSE_GET. The reply carries: - ETHTOOL_A_MSE_CAPABILITIES: scale limits and timing information - ETHTOOL_A_MSE_CHANNEL_* nests: one or more snapshots (per-channel if available, otherwise WORST, otherwise LINK) Link down returns -ENETDOWN. Changes: - YAML: add attribute sets (mse, mse-capabilities, mse-snapshot) and the mse-get operation - UAPI (generated): add ETHTOOL_A_MSE_* enums and message IDs, ETHTOOL_MSG_MSE_GET/REPLY - ethtool core: add net/ethtool/mse.c implementing the request, register genl op, and hook into ethnl dispatch - docs: document MSE_GET in ethtool-netlink.rst The include/uapi/linux/ethtool_netlink_generated.h is generated from Documentation/netlink/specs/ethtool.yaml. Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20251027122801.982364-3-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool_netlink_generated.h | 35 ++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 0e8ac0d974e2..b71b175df46d 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -803,6 +803,39 @@ enum { ETHTOOL_A_PSE_NTF_MAX = (__ETHTOOL_A_PSE_NTF_CNT - 1) }; +enum { + ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE = 1, + ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE, + ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS, + ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS, + + __ETHTOOL_A_MSE_CAPABILITIES_CNT, + ETHTOOL_A_MSE_CAPABILITIES_MAX = (__ETHTOOL_A_MSE_CAPABILITIES_CNT - 1) +}; + +enum { + ETHTOOL_A_MSE_SNAPSHOT_AVERAGE_MSE = 1, + ETHTOOL_A_MSE_SNAPSHOT_PEAK_MSE, + ETHTOOL_A_MSE_SNAPSHOT_WORST_PEAK_MSE, + + __ETHTOOL_A_MSE_SNAPSHOT_CNT, + ETHTOOL_A_MSE_SNAPSHOT_MAX = (__ETHTOOL_A_MSE_SNAPSHOT_CNT - 1) +}; + +enum { + ETHTOOL_A_MSE_HEADER = 1, + ETHTOOL_A_MSE_CAPABILITIES, + ETHTOOL_A_MSE_CHANNEL_A, + ETHTOOL_A_MSE_CHANNEL_B, + ETHTOOL_A_MSE_CHANNEL_C, + ETHTOOL_A_MSE_CHANNEL_D, + ETHTOOL_A_MSE_WORST_CHANNEL, + ETHTOOL_A_MSE_LINK, + + __ETHTOOL_A_MSE_CNT, + ETHTOOL_A_MSE_MAX = (__ETHTOOL_A_MSE_CNT - 1) +}; + enum { ETHTOOL_MSG_USER_NONE = 0, ETHTOOL_MSG_STRSET_GET = 1, @@ -855,6 +888,7 @@ enum { ETHTOOL_MSG_RSS_SET, ETHTOOL_MSG_RSS_CREATE_ACT, ETHTOOL_MSG_RSS_DELETE_ACT, + ETHTOOL_MSG_MSE_GET, __ETHTOOL_MSG_USER_CNT, ETHTOOL_MSG_USER_MAX = (__ETHTOOL_MSG_USER_CNT - 1) @@ -915,6 +949,7 @@ enum { ETHTOOL_MSG_RSS_CREATE_ACT_REPLY, ETHTOOL_MSG_RSS_CREATE_NTF, ETHTOOL_MSG_RSS_DELETE_NTF, + ETHTOOL_MSG_MSE_GET_REPLY, __ETHTOOL_MSG_KERNEL_CNT, ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1) -- cgit v1.2.3 From f16469ee733ac52b2373216803699cbb05e82786 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 31 Oct 2025 14:28:54 -0700 Subject: PCI/IDE: Enumerate Selective Stream IDE capabilities Link encryption is a new PCIe feature enumerated by "PCIe r7.0 section 7.9.26 IDE Extended Capability". It is both a standalone port + endpoint capability, and a building block for the security protocol defined by "PCIe r7.0 section 11 TEE Device Interface Security Protocol (TDISP)". That protocol coordinates device security setup between a platform TSM (TEE Security Manager) and a device DSM (Device Security Manager). While the platform TSM can allocate resources like Stream ID and manage keys, it still requires system software to manage the IDE capability register block. Add register definitions and basic enumeration in preparation for Selective IDE Stream establishment. A follow on change selects the new CONFIG_PCI_IDE symbol. Note that while the IDE specification defines both a point-to-point "Link Stream" and a Root Port to endpoint "Selective Stream", only "Selective Stream" is considered for Linux as that is the predominant mode expected by Trusted Execution Environment Security Managers (TSMs), and it is the security model that limits the number of PCI components within the TCB in a PCIe topology with switches. Co-developed-by: Alexey Kardashevskiy Signed-off-by: Alexey Kardashevskiy Co-developed-by: Xu Yilun Signed-off-by: Xu Yilun Reviewed-by: Jonathan Cameron Reviewed-by: Alexey Kardashevskiy Reviewed-by: Aneesh Kumar K.V Link: https://patch.msgid.link/20251031212902.2256310-3-dan.j.williams@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/pci_regs.h | 81 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 07e06aafec50..05bd22d9e352 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -754,6 +754,7 @@ #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ +#define PCI_EXT_CAP_ID_IDE 0x30 /* Integrity and Data Encryption */ #define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT @@ -1249,4 +1250,84 @@ #define PCI_DVSEC_CXL_PORT_CTL 0x0c #define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 +/* Integrity and Data Encryption Extended Capability */ +#define PCI_IDE_CAP 0x04 +#define PCI_IDE_CAP_LINK 0x1 /* Link IDE Stream Supported */ +#define PCI_IDE_CAP_SELECTIVE 0x2 /* Selective IDE Streams Supported */ +#define PCI_IDE_CAP_FLOWTHROUGH 0x4 /* Flow-Through IDE Stream Supported */ +#define PCI_IDE_CAP_PARTIAL_HEADER_ENC 0x8 /* Partial Header Encryption Supported */ +#define PCI_IDE_CAP_AGGREGATION 0x10 /* Aggregation Supported */ +#define PCI_IDE_CAP_PCRC 0x20 /* PCRC Supported */ +#define PCI_IDE_CAP_IDE_KM 0x40 /* IDE_KM Protocol Supported */ +#define PCI_IDE_CAP_SEL_CFG 0x80 /* Selective IDE for Config Request Support */ +#define PCI_IDE_CAP_ALG __GENMASK(12, 8) /* Supported Algorithms */ +#define PCI_IDE_CAP_ALG_AES_GCM_256 0 /* AES-GCM 256 key size, 96b MAC */ +#define PCI_IDE_CAP_LINK_TC_NUM __GENMASK(15, 13) /* Link IDE TCs */ +#define PCI_IDE_CAP_SEL_NUM __GENMASK(23, 16) /* Supported Selective IDE Streams */ +#define PCI_IDE_CAP_TEE_LIMITED 0x1000000 /* TEE-Limited Stream Supported */ +#define PCI_IDE_CTL 0x08 +#define PCI_IDE_CTL_FLOWTHROUGH_IDE 0x4 /* Flow-Through IDE Stream Enabled */ + +#define PCI_IDE_LINK_STREAM_0 0xc /* First Link Stream Register Block */ +#define PCI_IDE_LINK_BLOCK_SIZE 8 +/* Link IDE Stream block, up to PCI_IDE_CAP_LINK_TC_NUM */ +#define PCI_IDE_LINK_CTL_0 0x00 /* First Link Control Register Offset in block */ +#define PCI_IDE_LINK_CTL_EN 0x1 /* Link IDE Stream Enable */ +#define PCI_IDE_LINK_CTL_TX_AGGR_NPR __GENMASK(3, 2) /* Tx Aggregation Mode NPR */ +#define PCI_IDE_LINK_CTL_TX_AGGR_PR __GENMASK(5, 4) /* Tx Aggregation Mode PR */ +#define PCI_IDE_LINK_CTL_TX_AGGR_CPL __GENMASK(7, 6) /* Tx Aggregation Mode CPL */ +#define PCI_IDE_LINK_CTL_PCRC_EN 0x100 /* PCRC Enable */ +#define PCI_IDE_LINK_CTL_PART_ENC __GENMASK(13, 10) /* Partial Header Encryption Mode */ +#define PCI_IDE_LINK_CTL_ALG __GENMASK(18, 14) /* Selection from PCI_IDE_CAP_ALG */ +#define PCI_IDE_LINK_CTL_TC __GENMASK(21, 19) /* Traffic Class */ +#define PCI_IDE_LINK_CTL_ID __GENMASK(31, 24) /* Stream ID */ +#define PCI_IDE_LINK_STS_0 0x4 /* First Link Status Register Offset in block */ +#define PCI_IDE_LINK_STS_STATE __GENMASK(3, 0) /* Link IDE Stream State */ +#define PCI_IDE_LINK_STS_IDE_FAIL 0x80000000 /* IDE fail message received */ + +/* Selective IDE Stream block, up to PCI_IDE_CAP_SELECTIVE_STREAMS_NUM */ +/* Selective IDE Stream Capability Register */ +#define PCI_IDE_SEL_CAP 0x00 +#define PCI_IDE_SEL_CAP_ASSOC_NUM __GENMASK(3, 0) +/* Selective IDE Stream Control Register */ +#define PCI_IDE_SEL_CTL 0x04 +#define PCI_IDE_SEL_CTL_EN 0x1 /* Selective IDE Stream Enable */ +#define PCI_IDE_SEL_CTL_TX_AGGR_NPR __GENMASK(3, 2) /* Tx Aggregation Mode NPR */ +#define PCI_IDE_SEL_CTL_TX_AGGR_PR __GENMASK(5, 4) /* Tx Aggregation Mode PR */ +#define PCI_IDE_SEL_CTL_TX_AGGR_CPL __GENMASK(7, 6) /* Tx Aggregation Mode CPL */ +#define PCI_IDE_SEL_CTL_PCRC_EN 0x100 /* PCRC Enable */ +#define PCI_IDE_SEL_CTL_CFG_EN 0x200 /* Selective IDE for Configuration Requests */ +#define PCI_IDE_SEL_CTL_PART_ENC __GENMASK(13, 10) /* Partial Header Encryption Mode */ +#define PCI_IDE_SEL_CTL_ALG __GENMASK(18, 14) /* Selection from PCI_IDE_CAP_ALG */ +#define PCI_IDE_SEL_CTL_TC __GENMASK(21, 19) /* Traffic Class */ +#define PCI_IDE_SEL_CTL_DEFAULT 0x400000 /* Default Stream */ +#define PCI_IDE_SEL_CTL_TEE_LIMITED 0x800000 /* TEE-Limited Stream */ +#define PCI_IDE_SEL_CTL_ID __GENMASK(31, 24) /* Stream ID */ +#define PCI_IDE_SEL_CTL_ID_MAX 255 +/* Selective IDE Stream Status Register */ +#define PCI_IDE_SEL_STS 0x08 +#define PCI_IDE_SEL_STS_STATE __GENMASK(3, 0) /* Selective IDE Stream State */ +#define PCI_IDE_SEL_STS_STATE_INSECURE 0 +#define PCI_IDE_SEL_STS_STATE_SECURE 2 +#define PCI_IDE_SEL_STS_IDE_FAIL 0x80000000 /* IDE fail message received */ +/* IDE RID Association Register 1 */ +#define PCI_IDE_SEL_RID_1 0x0c +#define PCI_IDE_SEL_RID_1_LIMIT __GENMASK(23, 8) +/* IDE RID Association Register 2 */ +#define PCI_IDE_SEL_RID_2 0x10 +#define PCI_IDE_SEL_RID_2_VALID 0x1 +#define PCI_IDE_SEL_RID_2_BASE __GENMASK(23, 8) +#define PCI_IDE_SEL_RID_2_SEG __GENMASK(31, 24) +/* Selective IDE Address Association Register Block, up to PCI_IDE_SEL_CAP_ASSOC_NUM */ +#define PCI_IDE_SEL_ADDR_BLOCK_SIZE 12 +#define PCI_IDE_SEL_ADDR_1(x) (20 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) +#define PCI_IDE_SEL_ADDR_1_VALID 0x1 +#define PCI_IDE_SEL_ADDR_1_BASE_LOW __GENMASK(19, 8) +#define PCI_IDE_SEL_ADDR_1_LIMIT_LOW __GENMASK(31, 20) +/* IDE Address Association Register 2 is "Memory Limit Upper" */ +#define PCI_IDE_SEL_ADDR_2(x) (24 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) +/* IDE Address Association Register 3 is "Memory Base Upper" */ +#define PCI_IDE_SEL_ADDR_3(x) (28 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) +#define PCI_IDE_SEL_BLOCK_SIZE(nr_assoc) (20 + PCI_IDE_SEL_ADDR_BLOCK_SIZE * (nr_assoc)) + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 3225f52cde56f46789a4972d3c54df8a4d75f022 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 31 Oct 2025 14:28:56 -0700 Subject: PCI/TSM: Establish Secure Sessions and Link Encryption The PCIe 7.0 specification, section 11, defines the Trusted Execution Environment (TEE) Device Interface Security Protocol (TDISP). This protocol definition builds upon Component Measurement and Authentication (CMA), and link Integrity and Data Encryption (IDE). It adds support for assigning devices (PCI physical or virtual function) to a confidential VM such that the assigned device is enabled to access guest private memory protected by technologies like Intel TDX, AMD SEV-SNP, RISCV COVE, or ARM CCA. The "TSM" (TEE Security Manager) is a concept in the TDISP specification of an agent that mediates between a "DSM" (Device Security Manager) and system software in both a VMM and a confidential VM. A VMM uses TSM ABIs to setup link security and assign devices. A confidential VM uses TSM ABIs to transition an assigned device into the TDISP "RUN" state and validate its configuration. From a Linux perspective the TSM abstracts many of the details of TDISP, IDE, and CMA. Some of those details leak through at times, but for the most part TDISP is an internal implementation detail of the TSM. CONFIG_PCI_TSM adds an "authenticated" attribute and "tsm/" subdirectory to pci-sysfs. Consider that the TSM driver may itself be a PCI driver. Userspace can watch for the arrival of a "TSM" device, /sys/class/tsm/tsm0/uevent KOBJ_CHANGE, to know when the PCI core has initialized TSM services. The operations that can be executed against a PCI device are split into two mutually exclusive operation sets, "Link" and "Security" (struct pci_tsm_{link,security}_ops). The "Link" operations manage physical link security properties and communication with the device's Device Security Manager firmware. These are the host side operations in TDISP. The "Security" operations coordinate the security state of the assigned virtual device (TDI). These are the guest side operations in TDISP. Only "link" (Secure Session and physical Link Encryption) operations are defined at this stage. There are placeholders for the device security (Trusted Computing Base entry / exit) operations. The locking allows for multiple devices to be executing commands simultaneously, one outstanding command per-device and an rwsem synchronizes the implementation relative to TSM registration/unregistration events. Thanks to Wu Hao for his work on an early draft of this support. Cc: Lukas Wunner Cc: Samuel Ortiz Acked-by: Bjorn Helgaas Reviewed-by: Jonathan Cameron Reviewed-by: Alexey Kardashevskiy Co-developed-by: Xu Yilun Signed-off-by: Xu Yilun Link: https://patch.msgid.link/20251031212902.2256310-5-dan.j.williams@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 05bd22d9e352..f2759c1097bc 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -503,6 +503,7 @@ #define PCI_EXP_DEVCAP_PWR_VAL 0x03fc0000 /* Slot Power Limit Value */ #define PCI_EXP_DEVCAP_PWR_SCL 0x0c000000 /* Slot Power Limit Scale */ #define PCI_EXP_DEVCAP_FLR 0x10000000 /* Function Level Reset */ +#define PCI_EXP_DEVCAP_TEE 0x40000000 /* TEE I/O (TDISP) Support */ #define PCI_EXP_DEVCTL 0x08 /* Device Control */ #define PCI_EXP_DEVCTL_CERE 0x0001 /* Correctable Error Reporting En. */ #define PCI_EXP_DEVCTL_NFERE 0x0002 /* Non-Fatal Error Reporting Enable */ -- cgit v1.2.3 From c0c1262fbfbafe943dbccd5f97b500b72dbd2205 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 31 Oct 2025 14:28:57 -0700 Subject: PCI: Add PCIe Device 3 Extended Capability enumeration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe r7.0 Section 7.7.9 Device 3 Extended Capability Structure, defines the canonical location for determining the Flit Mode of a device. This status is a dependency for PCIe IDE enabling. Add a new fm_enabled flag to 'struct pci_dev'. Cc: Lukas Wunner Cc: Ilpo Järvinen Cc: Bjorn Helgaas Cc: Samuel Ortiz Cc: Alexey Kardashevskiy Cc: Xu Yilun Acked-by: Bjorn Helgaas Reviewed-by: Jonathan Cameron Link: https://patch.msgid.link/20251031212902.2256310-6-dan.j.williams@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/pci_regs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f2759c1097bc..3add74ae2594 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -755,6 +755,7 @@ #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ +#define PCI_EXT_CAP_ID_DEV3 0x2F /* Device 3 Capability/Control/Status */ #define PCI_EXT_CAP_ID_IDE 0x30 /* Integrity and Data Encryption */ #define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT @@ -1246,6 +1247,12 @@ /* Deprecated old name, replaced with PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE */ #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE +/* Device 3 Extended Capability */ +#define PCI_DEV3_CAP 0x04 /* Device 3 Capabilities Register */ +#define PCI_DEV3_CTL 0x08 /* Device 3 Control Register */ +#define PCI_DEV3_STA 0x0c /* Device 3 Status Register */ +#define PCI_DEV3_STA_SEGMENT 0x8 /* Segment Captured (end-to-end flit-mode detected) */ + /* Compute Express Link (CXL r3.1, sec 8.1.5) */ #define PCI_DVSEC_CXL_PORT 3 #define PCI_DVSEC_CXL_PORT_CTL 0x0c -- cgit v1.2.3 From d923739e2e356424cc566143a3323c62cd6ed067 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 27 Oct 2025 09:44:26 +0100 Subject: rseq: Simplify the event notification Since commit 0190e4198e47 ("rseq: Deprecate RSEQ_CS_FLAG_NO_RESTART_ON_* flags") the bits in task::rseq_event_mask are meaningless and just extra work in terms of setting them individually. Aside of that the only relevant point where an event has to be raised is context switch. Neither the CPU nor MM CID can change without going through a context switch. Collapse them all into a single boolean which simplifies the code a lot and remove the pointless invocations which have been sprinkled all over the place for no value. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Mathieu Desnoyers Link: https://patch.msgid.link/20251027084306.336978188@linutronix.de --- include/uapi/linux/rseq.h | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index c233aae5eac9..1b76d508400c 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -114,20 +114,13 @@ struct rseq { /* * Restartable sequences flags field. * - * This field should only be updated by the thread which - * registered this data structure. Read by the kernel. - * Mainly used for single-stepping through rseq critical sections - * with debuggers. - * - * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT - * Inhibit instruction sequence block restart on preemption - * for this thread. - * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL - * Inhibit instruction sequence block restart on signal - * delivery for this thread. - * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE - * Inhibit instruction sequence block restart on migration for - * this thread. + * This field was initially intended to allow event masking for + * single-stepping through rseq critical sections with debuggers. + * The kernel does not support this anymore and the relevant bits + * are checked for being always false: + * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT + * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL + * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE */ __u32 flags; -- cgit v1.2.3 From f88191c7f3618405f1fc5c331a94ebfe601c5b08 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Sat, 1 Nov 2025 18:56:51 +0100 Subject: mptcp: pm: in-kernel: record fullmesh endp nb Instead of iterating over all endpoints, under RCU read lock, just to check if one of them as the fullmesh flag, we can keep a counter of fullmesh endpoint, similar to what is done with the other flags. This counter is now checked, before iterating over all endpoints. Similar to the other counters, this new one is also exposed. A userspace app can then know when it is being used in a fullmesh mode, with potentially (too) many subflows. Reviewed-by: Geliang Tang Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251101-net-next-mptcp-fm-endp-nb-bind-v1-1-b4166772d6bb@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 87cfab874e24..04eea6d1d0a9 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -70,7 +70,8 @@ struct mptcp_info { __u64 mptcpi_bytes_acked; __u8 mptcpi_subflows_total; __u8 mptcpi_endp_laminar_max; - __u8 reserved[2]; + __u8 mptcpi_endp_fullmesh_max; + __u8 reserved; __u32 mptcpi_last_data_sent; __u32 mptcpi_last_data_recv; __u32 mptcpi_last_ack_recv; -- cgit v1.2.3 From 0bf0e2e4666822b62d7ad6473dc37fd6b377b5f1 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 5 Nov 2025 06:22:41 +0900 Subject: block: track zone conditions The function blk_revalidate_zone_cond() already caches the condition of all zones of a zoned block device in the zones_cond array of a gendisk. However, the zone conditions are updated only when the device is scanned or revalidated. Implement tracking of the runtime changes to zone conditions using the new cond field in struct blk_zone_wplug. The size of this structure remains 112 Bytes as the new field replaces the 4 Bytes padding at the end of the structure. Beause zones that do not have a zone write plug can be in the empty, implicit open, explicit open or full condition, the zones_cond array of a disk is used to track the conditions, of zones that do not have a zone write plug. The condition of such zone is updated in the disk zones_cond array when a zone reset, reset all or finish operation is executed, and also when a zone write plug is removed from the disk hash table when the zone becomes full. Since a device may automatically close an implicitly open zone when writing to an empty or closed zone, if the total number of open zones has reached the device limit, the BLK_ZONE_COND_IMP_OPEN and BLK_ZONE_COND_CLOSED zone conditions cannot be precisely tracked. To overcome this, the zone condition BLK_ZONE_COND_ACTIVE is introduced to represent a zone that has the condition BLK_ZONE_COND_IMP_OPEN, BLK_ZONE_COND_EXP_OPEN or BLK_ZONE_COND_CLOSED. This follows the definition of an active zone as defined in the NVMe Zoned Namespace specifications. As such, for a zoned device that has a limit on the maximum number of open zones, we will never have more zones in the BLK_ZONE_COND_ACTIVE condition than the device limit. This is compatible with the SCSI ZBC and ATA ZAC specifications for SMR HDDs as these devices do not have a limit on the number of active zones. The function disk_zone_wplug_set_wp_offset() is modified to use the new helper disk_zone_wplug_update_cond() to update a zone write plug condition whenever a zone write plug write offset is updated on submission or merging of write BIOs to a zone. The functions blk_zone_reset_bio_endio(), blk_zone_reset_all_bio_endio() and blk_zone_finish_bio_endio() are modified to update the condition of the zones targeted by reset, reset_all and finish operations, either using though disk_zone_wplug_set_wp_offset() for zones that have a zone write plug, or using the disk_zone_set_cond() helper to update the zones_cond array of the disk for zones that do not have a zone write plug. When a zone write plug is removed from the disk hash table (when the zone becomes empty or full), the condition of struct blk_zone_wplug is used to update the disk zones_cond array. Conversely, when a zone write plug is added to the disk hash table, the zones_cond array is used to initialize the zone write plug condition. Signed-off-by: Damien Le Moal Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index f85743ef6e7d..5c7662971414 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -48,6 +48,8 @@ enum blk_zone_type { * FINISH ZONE command. * @BLK_ZONE_COND_READONLY: The zone is read-only. * @BLK_ZONE_COND_OFFLINE: The zone is offline (sectors cannot be read/written). + * @BLK_ZONE_COND_ACTIVE: The zone is either implicitly open, explicitly open, + * or closed. * * The Zone Condition state machine in the ZBC/ZAC standards maps the above * deinitions as: @@ -61,6 +63,13 @@ enum blk_zone_type { * * Conditions 0x5 to 0xC are reserved by the current ZBC/ZAC spec and should * be considered invalid. + * + * The condition BLK_ZONE_COND_ACTIVE is used only with cached zone reports. + * It is used to report any of the BLK_ZONE_COND_IMP_OPEN, + * BLK_ZONE_COND_EXP_OPEN and BLK_ZONE_COND_CLOSED conditions. Conversely, a + * regular zone report will never report a zone condition using + * BLK_ZONE_COND_ACTIVE and instead use the conditions BLK_ZONE_COND_IMP_OPEN, + * BLK_ZONE_COND_EXP_OPEN or BLK_ZONE_COND_CLOSED as reported by the device. */ enum blk_zone_cond { BLK_ZONE_COND_NOT_WP = 0x0, @@ -71,6 +80,8 @@ enum blk_zone_cond { BLK_ZONE_COND_READONLY = 0xD, BLK_ZONE_COND_FULL = 0xE, BLK_ZONE_COND_OFFLINE = 0xF, + + BLK_ZONE_COND_ACTIVE = 0xFF, }; /** -- cgit v1.2.3 From b30ffcdc0c15a88f8866529d3532454e02571221 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 5 Nov 2025 06:22:45 +0900 Subject: block: introduce BLKREPORTZONESV2 ioctl Introduce the new BLKREPORTZONESV2 ioctl command to allow user applications access to the fast zone report implemented by blkdev_report_zones_cached(). This new ioctl is defined as number 142 and is documented in include/uapi/linux/fs.h. Unlike the existing BLKREPORTZONES ioctl, this new ioctl uses the flags field of struct blk_zone_report also as an input. If the user sets the BLK_ZONE_REP_CACHED flag as an input, then blkdev_report_zones_cached() is used to generate the zone report using cached zone information. If this flag is not set, then BLKREPORTZONESV2 behaves in the same manner as BLKREPORTZONES and the zone report is generated by accessing the zoned device. Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 35 ++++++++++++++++++++++++++++++----- include/uapi/linux/fs.h | 2 +- 2 files changed, 31 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 5c7662971414..e33f02703350 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -87,10 +87,20 @@ enum blk_zone_cond { /** * enum blk_zone_report_flags - Feature flags of reported zone descriptors. * - * @BLK_ZONE_REP_CAPACITY: Zone descriptor has capacity field. + * @BLK_ZONE_REP_CAPACITY: Output only. Indicates that zone descriptors in a + * zone report have a valid capacity field. + * @BLK_ZONE_REP_CACHED: Input only. Indicates that the zone report should be + * generated using cached zone information. In this case, + * the implicit open, explicit open and closed zone + * conditions are all reported with the + * BLK_ZONE_COND_ACTIVE condition. */ enum blk_zone_report_flags { - BLK_ZONE_REP_CAPACITY = (1 << 0), + /* Output flags */ + BLK_ZONE_REP_CAPACITY = (1U << 0), + + /* Input flags */ + BLK_ZONE_REP_CACHED = (1U << 31), }; /** @@ -133,6 +143,10 @@ struct blk_zone { * @sector: starting sector of report * @nr_zones: IN maximum / OUT actual * @flags: one or more flags as defined by enum blk_zone_report_flags. + * @flags: one or more flags as defined by enum blk_zone_report_flags. + * With BLKREPORTZONE, this field is ignored as an input and is valid + * only as an output. Using BLKREPORTZONEV2, this field is used as both + * input and output. * @zones: Space to hold @nr_zones @zones entries on reply. * * The array of at most @nr_zones must follow this structure in memory. @@ -159,9 +173,19 @@ struct blk_zone_range { /** * Zoned block device ioctl's: * - * @BLKREPORTZONE: Get zone information. Takes a zone report as argument. - * The zone report will start from the zone containing the - * sector specified in the report request structure. + * @BLKREPORTZONE: Get zone information from a zoned device. Takes a zone report + * as argument. The zone report will start from the zone + * containing the sector specified in struct blk_zone_report. + * The flags field of struct blk_zone_report is used as an + * output only and ignored as an input. + * DEPRECATED, use BLKREPORTZONEV2 instead. + * @BLKREPORTZONEV2: Same as @BLKREPORTZONE but uses the flags field of + * struct blk_zone_report as an input, allowing to get a zone + * report using cached zone information if the flag + * BLK_ZONE_REP_CACHED is set. In such case, the zone report + * may include zones with the condition @BLK_ZONE_COND_ACTIVE + * (c.f. the description of this condition above for more + * details). * @BLKRESETZONE: Reset the write pointer of the zones in the specified * sector range. The sector range must be zone aligned. * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors. @@ -180,5 +204,6 @@ struct blk_zone_range { #define BLKOPENZONE _IOW(0x12, 134, struct blk_zone_range) #define BLKCLOSEZONE _IOW(0x12, 135, struct blk_zone_range) #define BLKFINISHZONE _IOW(0x12, 136, struct blk_zone_range) +#define BLKREPORTZONEV2 _IOWR(0x12, 142, struct blk_zone_report) #endif /* _UAPI_BLKZONED_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 957ce3343a4f..66ca526cf786 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -298,7 +298,7 @@ struct file_attr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) #define BLKGETDISKSEQ _IOR(0x12,128,__u64) -/* 130-136 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */ +/* 130-136 and 142 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */ /* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */ #define BLKTRACESETUP2 _IOWR(0x12, 142, struct blk_user_trace_setup2) -- cgit v1.2.3 From b4ce5923e780d6896d4aaf19de5a27652b8bf1ea Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 5 Nov 2025 09:03:59 +0000 Subject: bpf, x86: add new map type: instructions array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On bpf(BPF_PROG_LOAD) syscall user-supplied BPF programs are translated by the verifier into "xlated" BPF programs. During this process the original instructions offsets might be adjusted and/or individual instructions might be replaced by new sets of instructions, or deleted. Add a new BPF map type which is aimed to keep track of how, for a given program, the original instructions were relocated during the verification. Also, besides keeping track of the original -> xlated mapping, make x86 JIT to build the xlated -> jitted mapping for every instruction listed in an instruction array. This is required for every future application of instruction arrays: static keys, indirect jumps and indirect calls. A map of the BPF_MAP_TYPE_INSN_ARRAY type must be created with a u32 keys and value of size 8. The values have different semantics for userspace and for BPF space. For userspace a value consists of two u32 values – xlated and jitted offsets. For BPF side the value is a real pointer to a jitted instruction. On map creation/initialization, before loading the program, each element of the map should be initialized to point to an instruction offset within the program. Before the program load such maps should be made frozen. After the program verification xlated and jitted offsets can be read via the bpf(2) syscall. If a tracked instruction is removed by the verifier, then the xlated offset is set to (u32)-1 which is considered to be too big for a valid BPF program offset. One such a map can, obviously, be used to track one and only one BPF program. If the verification process was unsuccessful, then the same map can be re-used to verify the program with a different log level. However, if the program was loaded fine, then such a map, being frozen in any case, can't be reused by other programs even after the program release. Example. Consider the following original and xlated programs: Original prog: Xlated prog: 0: r1 = 0x0 0: r1 = 0 1: *(u32 *)(r10 - 0x4) = r1 1: *(u32 *)(r10 -4) = r1 2: r2 = r10 2: r2 = r10 3: r2 += -0x4 3: r2 += -4 4: r1 = 0x0 ll 4: r1 = map[id:88] 6: call 0x1 6: r1 += 272 7: r0 = *(u32 *)(r2 +0) 8: if r0 >= 0x1 goto pc+3 9: r0 <<= 3 10: r0 += r1 11: goto pc+1 12: r0 = 0 7: r6 = r0 13: r6 = r0 8: if r6 == 0x0 goto +0x2 14: if r6 == 0x0 goto pc+4 9: call 0x76 15: r0 = 0xffffffff8d2079c0 17: r0 = *(u64 *)(r0 +0) 10: *(u64 *)(r6 + 0x0) = r0 18: *(u64 *)(r6 +0) = r0 11: r0 = 0x0 19: r0 = 0x0 12: exit 20: exit An instruction array map, containing, e.g., instructions [0,4,7,12] will be translated by the verifier to [0,4,13,20]. A map with index 5 (the middle of 16-byte instruction) or indexes greater than 12 (outside the program boundaries) would be rejected. The functionality provided by this patch will be extended in consequent patches to implement BPF Static Keys, indirect jumps, and indirect calls. Signed-off-by: Anton Protopopov Reviewed-by: Eduard Zingerman Link: https://lore.kernel.org/r/20251105090410.1250500-2-a.s.protopopov@gmail.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1d73f165394d..f5713f59ac10 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1026,6 +1026,7 @@ enum bpf_map_type { BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, BPF_MAP_TYPE_ARENA, + BPF_MAP_TYPE_INSN_ARRAY, __MAX_BPF_MAP_TYPE }; @@ -7649,4 +7650,24 @@ enum bpf_kfunc_flags { BPF_F_PAD_ZEROS = (1ULL << 0), }; +/* + * Values of a BPF_MAP_TYPE_INSN_ARRAY entry must be of this type. + * + * Before the map is used the orig_off field should point to an + * instruction inside the program being loaded. The other fields + * must be set to 0. + * + * After the program is loaded, the xlated_off will be adjusted + * by the verifier to point to the index of the original instruction + * in the xlated program. If the instruction is deleted, it will + * be set to (u32)-1. The jitted_off will be set to the corresponding + * offset in the jitted image of the program. + */ +struct bpf_insn_array_value { + __u32 orig_off; + __u32 xlated_off; + __u32 jitted_off; + __u32 :32; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From c6230446b1a6f3c91effafd99f604de455da52e5 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Mon, 3 Nov 2025 12:20:20 +0000 Subject: net: dsa: add tagging driver for MaxLinear GSW1xx switch family Add support for a new DSA tagging protocol driver for the MaxLinear GSW1xx switch family. The GSW1xx switches use a proprietary 8-byte special tag inserted between the source MAC address and the EtherType field to indicate the source and destination ports for frames traversing the CPU port. Implement the tag handling logic to insert the special tag on transmit and parse it on receive. Signed-off-by: Daniel Golle Reviewed-by: Alexander Sverdlin Tested-by: Alexander Sverdlin Link: https://patch.msgid.link/0e973ebfd9433c30c96f50670da9e9449a0d98f2.1762170107.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index cfd200c87e5e..2c93b7b731c8 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -92,6 +92,7 @@ #define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ +#define ETH_P_MXLGSW 0x88C3 /* MaxLinear GSW DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ -- cgit v1.2.3 From dae4a92399fa8d68aa917db6bb3245f83021e762 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 5 Nov 2025 16:26:02 -0800 Subject: psp: report basic stats from the core Track and report stats common to all psp devices from the core. A 'stale-event' is when the core marks the rx state of an active psp_assoc as incapable of authenticating psp encapsulated data. Signed-off-by: Daniel Zahka Link: https://patch.msgid.link/20251106002608.1578518-2-daniel.zahka@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/psp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/psp.h b/include/uapi/linux/psp.h index 607c42c39ba5..31592760ad79 100644 --- a/include/uapi/linux/psp.h +++ b/include/uapi/linux/psp.h @@ -45,6 +45,15 @@ enum { PSP_A_KEYS_MAX = (__PSP_A_KEYS_MAX - 1) }; +enum { + PSP_A_STATS_DEV_ID = 1, + PSP_A_STATS_KEY_ROTATIONS, + PSP_A_STATS_STALE_EVENTS, + + __PSP_A_STATS_MAX, + PSP_A_STATS_MAX = (__PSP_A_STATS_MAX - 1) +}; + enum { PSP_CMD_DEV_GET = 1, PSP_CMD_DEV_ADD_NTF, @@ -55,6 +64,7 @@ enum { PSP_CMD_KEY_ROTATE_NTF, PSP_CMD_RX_ASSOC, PSP_CMD_TX_ASSOC, + PSP_CMD_GET_STATS, __PSP_CMD_MAX, PSP_CMD_MAX = (__PSP_CMD_MAX - 1) -- cgit v1.2.3 From f05d26198cf2c71f25f6bbe62ca4481c15543922 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 5 Nov 2025 16:26:04 -0800 Subject: psp: add stats from psp spec to driver facing api Provide a driver api for reporting device statistics required by the "Implementation Requirements" section of the PSP Architecture Specification. Use a warning to ensure drivers report stats required by the spec. Signed-off-by: Daniel Zahka Link: https://patch.msgid.link/20251106002608.1578518-4-daniel.zahka@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/psp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/psp.h b/include/uapi/linux/psp.h index 31592760ad79..d8449c043ba1 100644 --- a/include/uapi/linux/psp.h +++ b/include/uapi/linux/psp.h @@ -49,6 +49,14 @@ enum { PSP_A_STATS_DEV_ID = 1, PSP_A_STATS_KEY_ROTATIONS, PSP_A_STATS_STALE_EVENTS, + PSP_A_STATS_RX_PACKETS, + PSP_A_STATS_RX_BYTES, + PSP_A_STATS_RX_AUTH_FAIL, + PSP_A_STATS_RX_ERROR, + PSP_A_STATS_RX_BAD, + PSP_A_STATS_TX_PACKETS, + PSP_A_STATS_TX_BYTES, + PSP_A_STATS_TX_ERROR, __PSP_A_STATS_MAX, PSP_A_STATS_MAX = (__PSP_A_STATS_MAX - 1) -- cgit v1.2.3 From 62ed1b58224636185fa689db81224b8c8af46473 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Mon, 3 Nov 2025 20:57:57 +0800 Subject: md: allow configuring logical block size Previously, raid array used the maximum logical block size (LBS) of all member disks. Adding a larger LBS disk at runtime could unexpectedly increase RAID's LBS, risking corruption of existing partitions. This can be reproduced by: ``` # LBS of sd[de] is 512 bytes, sdf is 4096 bytes. mdadm -CRq /dev/md0 -l1 -n3 /dev/sd[de] missing --assume-clean # LBS is 512 cat /sys/block/md0/queue/logical_block_size # create partition md0p1 parted -s /dev/md0 mklabel gpt mkpart primary 1MiB 100% lsblk | grep md0p1 # LBS becomes 4096 after adding sdf mdadm --add -q /dev/md0 /dev/sdf cat /sys/block/md0/queue/logical_block_size # partition lost partprobe /dev/md0 lsblk | grep md0p1 ``` Simply restricting larger-LBS disks is inflexible. In some scenarios, only disks with 512 bytes LBS are available currently, but later, disks with 4KB LBS may be added to the array. Making LBS configurable is the best way to solve this scenario. After this patch, the raid will: - store LBS in disk metadata - add a read-write sysfs 'mdX/logical_block_size' Future mdadm should support setting LBS via metadata field during RAID creation and the new sysfs. Though the kernel allows runtime LBS changes, users should avoid modifying it after creating partitions or filesystems to prevent compatibility issues. Only 1.x metadata supports configurable LBS. 0.90 metadata inits all fields to default values at auto-detect. Supporting 0.90 would require more extensive changes and no such use case has been observed. Note that many RAID paths rely on PAGE_SIZE alignment, including for metadata I/O. A larger LBS than PAGE_SIZE will result in metadata read/write failures. So this config should be prevented. Link: https://lore.kernel.org/linux-raid/20251103125757.1405796-6-linan666@huaweicloud.com Signed-off-by: Li Nan Reviewed-by: Xiao Ni Signed-off-by: Yu Kuai --- include/uapi/linux/raid/md_p.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index ac74133a4768..310068bb2a1d 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -291,7 +291,8 @@ struct mdp_superblock_1 { __le64 resync_offset; /* data before this offset (from data_offset) known to be in sync */ __le32 sb_csum; /* checksum up to devs[max_dev] */ __le32 max_dev; /* size of devs[] array to consider */ - __u8 pad3[64-32]; /* set to 0 when writing */ + __le32 logical_block_size; /* same as q->limits->logical_block_size */ + __u8 pad3[64-36]; /* set to 0 when writing */ /* device state information. Indexed by dev_number. * 2 bytes per device -- cgit v1.2.3 From 0e535824d0bcf7c9bb0532d902283c31c78cd6f3 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 7 Nov 2025 23:04:02 -0800 Subject: devlink: Introduce switchdev_inactive eswitch mode Adds DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE attribute to UAPI and documentation. Before having traffic flow through an eswitch, a user may want to have the ability to block traffic towards the FDB until FDB is fully programmed and the user is ready to send traffic to it. For example: when two eswitches are present for vports in a multi-PF setup, one eswitch may take over the traffic from the other when the user chooses. Before this take over, a user may want to first program the inactive eswitch and then once ready redirect traffic to this new eswitch. switchdev modes transition semantics: legacy->switchdev_inactive: Create switchdev mode normally, traffic not allowed to flow yet. switchdev_inactive->switchdev: Enable traffic to flow. switchdev->switchdev_inactive: Block traffic on the FDB, FDB and representros state and content is preserved. When eswitch is configured to this mode, traffic is ignored/dropped on this eswitch FDB, while current configuration is kept, e.g FDB rules and netdev representros are kept available, FDB programming is allowed. Example: # start inactive switchdev devlink dev eswitch set pci/0000:08:00.1 mode switchdev_inactive # setup TC rules, representors etc .. # activate devlink dev eswitch set pci/0000:08:00.1 mode switchdev Signed-off-by: Saeed Mahameed Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20251108070404.1551708-2-saeed@kernel.org Signed-off-by: Paolo Abeni --- include/uapi/linux/devlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index bcad11a787a5..157f11d3fb72 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -181,6 +181,7 @@ enum devlink_sb_threshold_type { enum devlink_eswitch_mode { DEVLINK_ESWITCH_MODE_LEGACY, DEVLINK_ESWITCH_MODE_SWITCHDEV, + DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE, }; enum devlink_eswitch_inline_mode { -- cgit v1.2.3 From 1602bad16d7df82faca6d7c70821117684a66f49 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 11 Nov 2025 09:12:58 -0500 Subject: vfs: expose delegation support to userland Now that support for recallable directory delegations is available, expose this functionality to userland with new F_SETDELEG and F_GETDELEG commands for fcntl(). Note that this also allows userland to request a FL_DELEG type lease on files too. Userland applications that do will get signalled when there are metadata changes in addition to just data changes (which is a limitation of FL_LEASE leases). These commands accept a new "struct delegation" argument that contains a flags field for future expansion. Signed-off-by: Jeff Layton Link: https://patch.msgid.link/20251111-dir-deleg-ro-v6-17-52f3feebb2f2@kernel.org Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/uapi/linux/fcntl.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 3741ea1b73d8..008fac15e573 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -79,6 +79,17 @@ */ #define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET +/* Set/Get delegations */ +#define F_GETDELEG (F_LINUX_SPECIFIC_BASE + 15) +#define F_SETDELEG (F_LINUX_SPECIFIC_BASE + 16) + +/* Argument structure for F_GETDELEG and F_SETDELEG */ +struct delegation { + uint32_t d_flags; /* Must be 0 */ + uint16_t d_type; /* F_RDLCK, F_WRLCK, F_UNLCK */ + uint16_t __pad; /* Must be 0 */ +}; + /* * Types of directory notifications that may be requested. */ -- cgit v1.2.3 From ad9c62bd8946621ed02ac94131a921222508a8bc Mon Sep 17 00:00:00 2001 From: Jiaqi Yan Date: Mon, 13 Oct 2025 18:59:01 +0000 Subject: KVM: arm64: VM exit to userspace to handle SEA When APEI fails to handle a stage-2 synchronous external abort (SEA), today KVM injects an asynchronous SError to the VCPU then resumes it, which usually results in unpleasant guest kernel panic. One major situation of guest SEA is when vCPU consumes recoverable uncorrected memory error (UER). Although SError and guest kernel panic effectively stops the propagation of corrupted memory, guest may re-use the corrupted memory if auto-rebooted; in worse case, guest boot may run into poisoned memory. So there is room to recover from an UER in a more graceful manner. Alternatively KVM can redirect the synchronous SEA event to VMM to - Reduce blast radius if possible. VMM can inject a SEA to VCPU via KVM's existing KVM_SET_VCPU_EVENTS API. If the memory poison consumption or fault is not from guest kernel, blast radius can be limited to the triggering thread in guest userspace, so VM can keep running. - Allow VMM to protect from future memory poison consumption by unmapping the page from stage-2, or to interrupt guest of the poisoned page so guest kernel can unmap it from stage-1 page table. - Allow VMM to track SEA events that VM customers care about, to restart VM when certain number of distinct poison events have happened, to provide observability to customers in log management UI. Introduce an userspace-visible feature to enable VMM handle SEA: - KVM_CAP_ARM_SEA_TO_USER. As the alternative fallback behavior when host APEI fails to claim a SEA, userspace can opt in this new capability to let KVM exit to userspace during SEA if it is not owned by host. - KVM_EXIT_ARM_SEA. A new exit reason is introduced for this. KVM fills kvm_run.arm_sea with as much as possible information about the SEA, enabling VMM to emulate SEA to guest by itself. - Sanitized ESR_EL2. The general rule is to keep only the bits useful for userspace and relevant to guest memory. - Flags indicating if faulting guest physical address is valid. - Faulting guest physical and virtual addresses if valid. Signed-off-by: Jiaqi Yan Co-developed-by: Oliver Upton Signed-off-by: Oliver Upton Link: https://msgid.link/20251013185903.1372553-2-jiaqiyan@google.com Signed-off-by: Oliver Upton --- include/uapi/linux/kvm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 52f6000ab020..1e541193e98d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -179,6 +179,7 @@ struct kvm_xen_exit { #define KVM_EXIT_LOONGARCH_IOCSR 38 #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 +#define KVM_EXIT_ARM_SEA 41 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -473,6 +474,14 @@ struct kvm_run { } setup_event_notify; }; } tdx; + /* KVM_EXIT_ARM_SEA */ + struct { +#define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID (1ULL << 0) + __u64 flags; + __u64 esr; + __u64 gva; + __u64 gpa; + } arm_sea; /* Fix the size of the union. */ char padding[256]; }; @@ -963,6 +972,7 @@ struct kvm_enable_cap { #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 #define KVM_CAP_GUEST_MEMFD_FLAGS 244 +#define KVM_CAP_ARM_SEA_TO_USER 245 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From 2647e2ecc096d2330d6b6a34a3a1f0a99828c14c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Nov 2025 10:48:57 +0000 Subject: io_uring/query: introduce zcrx query Add a new query type IO_URING_QUERY_ZCRX returning the user some basic information about the interface, which includes allowed flags for areas and registration and supported IORING_REGISTER_ZCRX_CTRL subcodes. There is also a chicken-egg problem with user provided refill queue memory, where offsets and size information is returned after registration, but to properly allocate memory you need to know it beforehand, which is why the userspace currently has to guess the RQ headers size and severely overestimates it. Return the size information. It's split into "size" and "alignment" fields because for default placement modes the user is interested in the aligned size, however if it gets support for more flexible placement, it'll need to only know the actual header size. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/query.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 3539ccbfd064..fc0cb1580e47 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -18,6 +18,7 @@ struct io_uring_query_hdr { enum { IO_URING_QUERY_OPCODES = 0, + IO_URING_QUERY_ZCRX = 1, __IO_URING_QUERY_MAX, }; @@ -41,4 +42,19 @@ struct io_uring_query_opcode { __u32 __pad; }; +struct io_uring_query_zcrx { + /* Bitmask of supported ZCRX_REG_* flags, */ + __u64 register_flags; + /* Bitmask of all supported IORING_ZCRX_AREA_* flags */ + __u64 area_flags; + /* The number of supported ZCRX_CTRL_* opcodes */ + __u32 nr_ctrl_opcodes; + __u32 __resv1; + /* The refill ring header size */ + __u32 rq_hdr_size; + /* The alignment for the header */ + __u32 rq_hdr_alignment; + __u64 __resv2; +}; + #endif -- cgit v1.2.3 From 4aaa9bc4d5921363490d95fe66c4db086a915799 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Nov 2025 10:48:58 +0000 Subject: io_uring/query: introduce rings info query Same problem as with zcrx in the previous patch, the user needs to know SQ/CQ header sizes to allocated memory before setup to use it for user provided rings, i.e. IORING_SETUP_NO_MMAP, however that information is only returned after registration, hence the user is guessing kernel implementation details. Return the header size and alignment, which is split with the same motivation, to allow the user to know the real structure size without alignment in case there will be more flexible placement schemes in the future. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/query.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index fc0cb1580e47..2456e6c5ebb5 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -19,6 +19,7 @@ struct io_uring_query_hdr { enum { IO_URING_QUERY_OPCODES = 0, IO_URING_QUERY_ZCRX = 1, + IO_URING_QUERY_SCQ = 2, __IO_URING_QUERY_MAX, }; @@ -57,4 +58,11 @@ struct io_uring_query_zcrx { __u64 __resv2; }; +struct io_uring_query_scq { + /* The SQ/CQ rings header size */ + __u64 hdr_size; + /* The alignment for the header */ + __u64 hdr_alignment; +}; + #endif -- cgit v1.2.3 From d663976dad68de9b2e3df59cc31f0a24ee4c4511 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Nov 2025 10:46:12 +0000 Subject: io_uring/zcrx: introduce IORING_REGISTER_ZCRX_CTRL It'll be annoying and take enough of boilerplate code to implement new zcrx features as separate io_uring register opcode. Introduce IORING_REGISTER_ZCRX_CTRL that will multiplex such calls to zcrx. Note, there are no real users of the opcode in this patch. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index e96080db3e4d..0e1d353fab1d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -697,6 +697,9 @@ enum io_uring_register_op { /* query various aspects of io_uring, see linux/io_uring/query.h */ IORING_REGISTER_QUERY = 35, + /* auxiliary zcrx configuration, see enum zcrx_ctrl_op */ + IORING_REGISTER_ZCRX_CTRL = 36, + /* this goes last */ IORING_REGISTER_LAST, @@ -1078,6 +1081,16 @@ struct io_uring_zcrx_ifq_reg { __u64 __resv[3]; }; +enum zcrx_ctrl_op { + __ZCRX_CTRL_LAST, +}; + +struct zcrx_ctrl { + __u32 zcrx_id; + __u32 op; /* see enum zcrx_ctrl_op */ + __u64 __resv[8]; +}; + #ifdef __cplusplus } #endif -- cgit v1.2.3 From 475eb39b00478b1898bc9080344dcd8e86c53c7a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Nov 2025 10:46:13 +0000 Subject: io_uring/zcrx: add sync refill queue flushing Add an zcrx interface via IORING_REGISTER_ZCRX_CTRL that forces the kernel to flush / consume entries from the refill queue. Just as with the IORING_REGISTER_ZCRX_REFILL attempt, the motivation is to address cases where the refill queue becomes full, and the user can't return buffers and needs to stash them. It's still a slow path, and the user should size refill queue appropriately, but it should be helpful for handling temporary traffic spikes and other unpredictable conditions. The interface is simpler comparing to ZCRX_REFILL as it doesn't need temporary refill entry arrays and gives natural batching, whereas ZCRX_REFILL requires even more user logic to be somewhat efficient. Also, add a structure for the operation. It's not currently used but can serve for future improvements like limiting the number of buffers to process, etc. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0e1d353fab1d..db47fced2cc6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1082,13 +1082,21 @@ struct io_uring_zcrx_ifq_reg { }; enum zcrx_ctrl_op { + ZCRX_CTRL_FLUSH_RQ, + __ZCRX_CTRL_LAST, }; +struct zcrx_ctrl_flush_rq { + __u64 __resv[6]; +}; + struct zcrx_ctrl { __u32 zcrx_id; __u32 op; /* see enum zcrx_ctrl_op */ - __u64 __resv[8]; + __u64 __resv[2]; + + struct zcrx_ctrl_flush_rq zc_flush; }; #ifdef __cplusplus -- cgit v1.2.3 From d7af80b213e5675664b14f12240cb282e81773d5 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 13 Nov 2025 10:46:16 +0000 Subject: io_uring/zcrx: export zcrx via a file Add an option to wrap a zcrx instance into a file and expose it to the user space. Currently, users can't do anything meaningful with the file, but it'll be used in a next patch to import it into another io_uring instance. It's implemented as a new op called ZCRX_CTRL_EXPORT for the IORING_REGISTER_ZCRX_CTRL registration opcode. Signed-off-by: David Wei Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index db47fced2cc6..4bedc0310a55 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1083,6 +1083,7 @@ struct io_uring_zcrx_ifq_reg { enum zcrx_ctrl_op { ZCRX_CTRL_FLUSH_RQ, + ZCRX_CTRL_EXPORT, __ZCRX_CTRL_LAST, }; @@ -1091,12 +1092,20 @@ struct zcrx_ctrl_flush_rq { __u64 __resv[6]; }; +struct zcrx_ctrl_export { + __u32 zcrx_fd; + __u32 __resv1[11]; +}; + struct zcrx_ctrl { __u32 zcrx_id; __u32 op; /* see enum zcrx_ctrl_op */ __u64 __resv[2]; - struct zcrx_ctrl_flush_rq zc_flush; + union { + struct zcrx_ctrl_export zc_export; + struct zcrx_ctrl_flush_rq zc_flush; + }; }; #ifdef __cplusplus -- cgit v1.2.3 From 00d91481279fb2df8c46d19090578afd523ca630 Mon Sep 17 00:00:00 2001 From: David Wei Date: Thu, 13 Nov 2025 10:46:18 +0000 Subject: io_uring/zcrx: share an ifq between rings Add a way to share an ifq from a src ring that is real (i.e. bound to a HW RX queue) with other rings. This is done by passing a new flag IORING_ZCRX_IFQ_REG_IMPORT in the registration struct io_uring_zcrx_ifq_reg, alongside the fd of an exported zcrx ifq. Signed-off-by: David Wei Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 4bedc0310a55..deb772222b6d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1063,6 +1063,10 @@ struct io_uring_zcrx_area_reg { __u64 __resv2[2]; }; +enum zcrx_reg_flags { + ZCRX_REG_IMPORT = 1, +}; + /* * Argument for IORING_REGISTER_ZCRX_IFQ */ -- cgit v1.2.3 From e36dbd1cf3dfc4ce18e9f7a80183b53cae257e30 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Fri, 4 Jul 2025 17:43:19 +0200 Subject: media: uapi: Introduce V4L2 generic ISP types Introduce v4l2-isp.h in the Linux kernel uAPI. The header includes types for generic ISP configuration parameters and will be extended in the future with support for generic ISP statistics formats. Generic ISP parameters support is provided by introducing two new types that represent an extensible and versioned buffer of ISP configuration parameters. The v4l2_params_buffer represents the container for the ISP configuration data block. The generic type is defined with a 0-sized data member that the ISP driver implementations shall properly size according to their capabilities. The v4l2_params_block_header structure represents the header to be prepend to each ISP configuration block. Signed-off-by: Daniel Scally Reviewed-by: Daniel Scally Reviewed-by: Laurent Pinchart Reviewed-by: Michael Riesch Acked-by: Sakari Ailus Tested-by: Lad Prabhakar Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- include/uapi/linux/media/v4l2-isp.h | 102 ++++++++++++++++++++++++++++++++++++ 1 file changed, 102 insertions(+) create mode 100644 include/uapi/linux/media/v4l2-isp.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/v4l2-isp.h b/include/uapi/linux/media/v4l2-isp.h new file mode 100644 index 000000000000..779168f9058e --- /dev/null +++ b/include/uapi/linux/media/v4l2-isp.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Video4Linux2 generic ISP parameters and statistics support + * + * Copyright (C) 2025 Ideas On Board Oy + * Author: Jacopo Mondi + */ + +#ifndef _UAPI_V4L2_ISP_H_ +#define _UAPI_V4L2_ISP_H_ + +#include +#include + +/** + * enum v4l2_isp_params_version - V4L2 ISP parameters versioning + * + * @V4L2_ISP_PARAMS_VERSION_V0: First version of the V4L2 ISP parameters format + * (for compatibility) + * @V4L2_ISP_PARAMS_VERSION_V1: First version of the V4L2 ISP parameters format + * + * V0 and V1 are identical in order to support drivers compatible with the V4L2 + * ISP parameters format already upstreamed which use either 0 or 1 as their + * versioning identifier. Both V0 and V1 refers to the first version of the + * V4L2 ISP parameters format. + * + * Future revisions of the V4L2 ISP parameters format should start from the + * value of 2. + */ +enum v4l2_isp_params_version { + V4L2_ISP_PARAMS_VERSION_V0 = 0, + V4L2_ISP_PARAMS_VERSION_V1 +}; + +#define V4L2_ISP_PARAMS_FL_BLOCK_DISABLE (1U << 0) +#define V4L2_ISP_PARAMS_FL_BLOCK_ENABLE (1U << 1) + +/* + * Reserve the first 8 bits for V4L2_ISP_PARAMS_FL_* flag. + * + * Driver-specific flags should be defined as: + * #define DRIVER_SPECIFIC_FLAG0 ((1U << V4L2_ISP_PARAMS_FL_DRIVER_FLAGS(0)) + * #define DRIVER_SPECIFIC_FLAG1 ((1U << V4L2_ISP_PARAMS_FL_DRIVER_FLAGS(1)) + */ +#define V4L2_ISP_PARAMS_FL_DRIVER_FLAGS(n) ((n) + 8) + +/** + * struct v4l2_isp_params_block_header - V4L2 extensible parameters block header + * @type: The parameters block type (driver-specific) + * @flags: A bitmask of block flags (driver-specific) + * @size: Size (in bytes) of the parameters block, including this header + * + * This structure represents the common part of all the ISP configuration + * blocks. Each parameters block shall embed an instance of this structure type + * as its first member, followed by the block-specific configuration data. + * + * The @type field is an ISP driver-specific value that identifies the block + * type. The @size field specifies the size of the parameters block. + * + * The @flags field is a bitmask of per-block flags V4L2_PARAMS_ISP_FL_* and + * driver-specific flags specified by the driver header. + */ +struct v4l2_isp_params_block_header { + __u16 type; + __u16 flags; + __u32 size; +} __attribute__((aligned(8))); + +/** + * struct v4l2_isp_params_buffer - V4L2 extensible parameters configuration + * @version: The parameters buffer version (driver-specific) + * @data_size: The configuration data effective size, excluding this header + * @data: The configuration data + * + * This structure contains the configuration parameters of the ISP algorithms, + * serialized by userspace into a data buffer. Each configuration parameter + * block is represented by a block-specific structure which contains a + * :c:type:`v4l2_isp_params_block_header` entry as first member. Userspace + * populates the @data buffer with configuration parameters for the blocks that + * it intends to configure. As a consequence, the data buffer effective size + * changes according to the number of ISP blocks that userspace intends to + * configure and is set by userspace in the @data_size field. + * + * The parameters buffer is versioned by the @version field to allow modifying + * and extending its definition. Userspace shall populate the @version field to + * inform the driver about the version it intends to use. The driver will parse + * and handle the @data buffer according to the data layout specific to the + * indicated version and return an error if the desired version is not + * supported. + * + * For each ISP block that userspace wants to configure, a block-specific + * structure is appended to the @data buffer, one after the other without gaps + * in between. Userspace shall populate the @data_size field with the effective + * size, in bytes, of the @data buffer. + */ +struct v4l2_isp_params_buffer { + __u32 version; + __u32 data_size; + __u8 data[] __counted_by(data_size); +}; + +#endif /* _UAPI_V4L2_ISP_H_ */ -- cgit v1.2.3 From 1e8152db64bdee9f13e84e516c2b8a9bb10f025e Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Mon, 7 Jul 2025 14:13:53 +0200 Subject: media: uapi: Convert RkISP1 to V4L2 extensible params With the introduction of common types for extensible parameters format, convert the rkisp1-config.h header to use the new types. Factor out the documentation that is now part of the common header and only keep the driver-specific on in place. The conversion to use common types doesn't impact userspace as the new types are either identical to the ones already existing in the RkISP1 uAPI or are 1-to-1 type convertible. Reviewed-by: Daniel Scally Reviewed-by: Laurent Pinchart Reviewed-by: Michael Riesch Acked-by: Sakari Ailus Tested-by: Lad Prabhakar Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- include/uapi/linux/rkisp1-config.h | 107 +++++++++---------------------------- 1 file changed, 24 insertions(+), 83 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 3b060ea6eed7..b2d2a71f7baf 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -7,8 +7,13 @@ #ifndef _UAPI_RKISP1_CONFIG_H #define _UAPI_RKISP1_CONFIG_H +#ifdef __KERNEL__ +#include +#endif /* __KERNEL__ */ #include +#include + /* Defect Pixel Cluster Detection */ #define RKISP1_CIF_ISP_MODULE_DPCC (1U << 0) /* Black Level Subtraction */ @@ -1158,79 +1163,26 @@ enum rkisp1_ext_params_block_type { RKISP1_EXT_PARAMS_BLOCK_TYPE_WDR, }; -#define RKISP1_EXT_PARAMS_FL_BLOCK_DISABLE (1U << 0) -#define RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE (1U << 1) +/* For backward compatibility */ +#define RKISP1_EXT_PARAMS_FL_BLOCK_DISABLE V4L2_ISP_PARAMS_FL_BLOCK_DISABLE +#define RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE V4L2_ISP_PARAMS_FL_BLOCK_ENABLE /* A bitmask of parameters blocks supported on the current hardware. */ #define RKISP1_CID_SUPPORTED_PARAMS_BLOCKS (V4L2_CID_USER_RKISP1_BASE + 0x01) /** - * struct rkisp1_ext_params_block_header - RkISP1 extensible parameters block - * header + * rkisp1_ext_params_block_header - RkISP1 extensible parameters block header * * This structure represents the common part of all the ISP configuration - * blocks. Each parameters block shall embed an instance of this structure type - * as its first member, followed by the block-specific configuration data. The - * driver inspects this common header to discern the block type and its size and - * properly handle the block content by casting it to the correct block-specific - * type. + * blocks and is identical to :c:type:`v4l2_isp_params_block_header`. * - * The @type field is one of the values enumerated by + * The type field is one of the values enumerated by * :c:type:`rkisp1_ext_params_block_type` and specifies how the data should be - * interpreted by the driver. The @size field specifies the size of the - * parameters block and is used by the driver for validation purposes. - * - * The @flags field is a bitmask of per-block flags RKISP1_EXT_PARAMS_FL_*. - * - * When userspace wants to configure and enable an ISP block it shall fully - * populate the block configuration and set the - * RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE bit in the @flags field. - * - * When userspace simply wants to disable an ISP block the - * RKISP1_EXT_PARAMS_FL_BLOCK_DISABLE bit should be set in @flags field. The - * driver ignores the rest of the block configuration structure in this case. - * - * If a new configuration of an ISP block has to be applied userspace shall - * fully populate the ISP block configuration and omit setting the - * RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE and RKISP1_EXT_PARAMS_FL_BLOCK_DISABLE bits - * in the @flags field. - * - * Setting both the RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE and - * RKISP1_EXT_PARAMS_FL_BLOCK_DISABLE bits in the @flags field is not allowed - * and not accepted by the driver. - * - * Userspace is responsible for correctly populating the parameters block header - * fields (@type, @flags and @size) and the block-specific parameters. - * - * For example: + * interpreted by the driver. * - * .. code-block:: c - * - * void populate_bls(struct rkisp1_ext_params_block_header *block) { - * struct rkisp1_ext_params_bls_config *bls = - * (struct rkisp1_ext_params_bls_config *)block; - * - * bls->header.type = RKISP1_EXT_PARAMS_BLOCK_ID_BLS; - * bls->header.flags = RKISP1_EXT_PARAMS_FL_BLOCK_ENABLE; - * bls->header.size = sizeof(*bls); - * - * bls->config.enable_auto = 0; - * bls->config.fixed_val.r = blackLevelRed_; - * bls->config.fixed_val.gr = blackLevelGreenR_; - * bls->config.fixed_val.gb = blackLevelGreenB_; - * bls->config.fixed_val.b = blackLevelBlue_; - * } - * - * @type: The parameters block type, see - * :c:type:`rkisp1_ext_params_block_type` - * @flags: A bitmask of block flags - * @size: Size (in bytes) of the parameters block, including this header + * The flags field is a bitmask of per-block flags RKISP1_EXT_PARAMS_FL_*. */ -struct rkisp1_ext_params_block_header { - __u16 type; - __u16 flags; - __u32 size; -}; +#define rkisp1_ext_params_block_header v4l2_isp_params_block_header /** * struct rkisp1_ext_params_bls_config - RkISP1 extensible params BLS config @@ -1588,27 +1540,14 @@ struct rkisp1_ext_params_wdr_config { * @RKISP1_EXT_PARAM_BUFFER_V1: First version of RkISP1 extensible parameters */ enum rksip1_ext_param_buffer_version { - RKISP1_EXT_PARAM_BUFFER_V1 = 1, + RKISP1_EXT_PARAM_BUFFER_V1 = V4L2_ISP_PARAMS_VERSION_V1, }; /** * struct rkisp1_ext_params_cfg - RkISP1 extensible parameters configuration * - * This struct contains the configuration parameters of the RkISP1 ISP - * algorithms, serialized by userspace into a data buffer. Each configuration - * parameter block is represented by a block-specific structure which contains a - * :c:type:`rkisp1_ext_params_block_header` entry as first member. Userspace - * populates the @data buffer with configuration parameters for the blocks that - * it intends to configure. As a consequence, the data buffer effective size - * changes according to the number of ISP blocks that userspace intends to - * configure and is set by userspace in the @data_size field. - * - * The parameters buffer is versioned by the @version field to allow modifying - * and extending its definition. Userspace shall populate the @version field to - * inform the driver about the version it intends to use. The driver will parse - * and handle the @data buffer according to the data layout specific to the - * indicated version and return an error if the desired version is not - * supported. + * This is the driver-specific implementation of + * :c:type:`v4l2_isp_params_buffer`. * * Currently the single RKISP1_EXT_PARAM_BUFFER_V1 version is supported. * When a new format version will be added, a mechanism for userspace to query @@ -1624,11 +1563,6 @@ enum rksip1_ext_param_buffer_version { * the maximum value represents the blocks supported by the kernel driver, * independently of the device instance. * - * For each ISP block that userspace wants to configure, a block-specific - * structure is appended to the @data buffer, one after the other without gaps - * in between nor overlaps. Userspace shall populate the @data_size field with - * the effective size, in bytes, of the @data buffer. - * * The expected memory layout of the parameters buffer is:: * * +-------------------- struct rkisp1_ext_params_cfg -------------------+ @@ -1678,4 +1612,11 @@ struct rkisp1_ext_params_cfg { __u8 data[RKISP1_EXT_PARAMS_MAX_SIZE]; }; +#ifdef __KERNEL__ +/* Make sure the header is type-convertible to the generic v4l2 params one */ +static_assert((sizeof(struct rkisp1_ext_params_cfg) - + RKISP1_EXT_PARAMS_MAX_SIZE) == + sizeof(struct v4l2_isp_params_buffer)); +#endif /* __KERNEL__ */ + #endif /* _UAPI_RKISP1_CONFIG_H */ -- cgit v1.2.3 From 45662082855c6acd1719c11e077388cbccf3baf2 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Mon, 7 Jul 2025 14:18:52 +0200 Subject: media: uapi: Convert Amlogic C3 to V4L2 extensible params With the introduction of common types for extensible parameters format, convert the c3-isp-config.h header to use the new types. Factor-out the documentation that is now part of the common header and only keep the driver-specific on in place. The conversion to use common types doesn't impact userspace as the new types are either identical to the ones already existing in the C3 ISP uAPI or are 1-to-1 type convertible. Reviewed-by: Daniel Scally Reviewed-by: Keke Li Reviewed-by: Laurent Pinchart Acked-by: Sakari Ailus Tested-by: Lad Prabhakar Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- include/uapi/linux/media/amlogic/c3-isp-config.h | 92 +++++++----------------- 1 file changed, 24 insertions(+), 68 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/amlogic/c3-isp-config.h b/include/uapi/linux/media/amlogic/c3-isp-config.h index ed085ea62a57..0a3c1cc55ccb 100644 --- a/include/uapi/linux/media/amlogic/c3-isp-config.h +++ b/include/uapi/linux/media/amlogic/c3-isp-config.h @@ -6,8 +6,13 @@ #ifndef _UAPI_C3_ISP_CONFIG_H_ #define _UAPI_C3_ISP_CONFIG_H_ +#ifdef __KERNEL__ +#include +#endif /* __KERNEL__ */ #include +#include + /* * Frames are split into zones of almost equal width and height - a zone is a * rectangular tile of a frame. The metering blocks within the ISP collect @@ -141,7 +146,7 @@ struct c3_isp_stats_info { * @C3_ISP_PARAMS_BUFFER_V0: First version of C3 ISP parameters block */ enum c3_isp_params_buffer_version { - C3_ISP_PARAMS_BUFFER_V0, + C3_ISP_PARAMS_BUFFER_V0 = V4L2_ISP_PARAMS_VERSION_V0, }; /** @@ -176,62 +181,23 @@ enum c3_isp_params_block_type { C3_ISP_PARAMS_BLOCK_SENTINEL }; -#define C3_ISP_PARAMS_BLOCK_FL_DISABLE (1U << 0) -#define C3_ISP_PARAMS_BLOCK_FL_ENABLE (1U << 1) +/* For backward compatibility */ +#define C3_ISP_PARAMS_BLOCK_FL_DISABLE V4L2_ISP_PARAMS_FL_BLOCK_DISABLE +#define C3_ISP_PARAMS_BLOCK_FL_ENABLE V4L2_ISP_PARAMS_FL_BLOCK_ENABLE /** * struct c3_isp_params_block_header - C3 ISP parameter block header * * This structure represents the common part of all the ISP configuration - * blocks. Each parameters block shall embed an instance of this structure type - * as its first member, followed by the block-specific configuration data. The - * driver inspects this common header to discern the block type and its size and - * properly handle the block content by casting it to the correct block-specific - * type. + * blocks and is identical to :c:type:`v4l2_isp_params_block_header`. * - * The @type field is one of the values enumerated by + * The type field is one of the values enumerated by * :c:type:`c3_isp_params_block_type` and specifies how the data should be - * interpreted by the driver. The @size field specifies the size of the - * parameters block and is used by the driver for validation purposes. The - * @flags field is a bitmask of per-block flags C3_ISP_PARAMS_FL*. - * - * When userspace wants to disable an ISP block the - * C3_ISP_PARAMS_BLOCK_FL_DISABLED bit should be set in the @flags field. In - * this case userspace may optionally omit the remainder of the configuration - * block, which will be ignored by the driver. - * - * When a new configuration of an ISP block needs to be applied userspace - * shall fully populate the ISP block and omit setting the - * C3_ISP_PARAMS_BLOCK_FL_DISABLED bit in the @flags field. - * - * Userspace is responsible for correctly populating the parameters block header - * fields (@type, @flags and @size) and the block-specific parameters. - * - * For example: - * - * .. code-block:: c + * interpreted by the driver. * - * void populate_pst_gamma(struct c3_isp_params_block_header *block) { - * struct c3_isp_params_pst_gamma *gamma = - * (struct c3_isp_params_pst_gamma *)block; - * - * gamma->header.type = C3_ISP_PARAMS_BLOCK_PST_GAMMA; - * gamma->header.flags = C3_ISP_PARAMS_BLOCK_FL_ENABLE; - * gamma->header.size = sizeof(*gamma); - * - * for (unsigned int i = 0; i < 129; i++) - * gamma->pst_gamma_lut[i] = i; - * } - * - * @type: The parameters block type from :c:type:`c3_isp_params_block_type` - * @flags: A bitmask of block flags - * @size: Size (in bytes) of the parameters block, including this header + * The flags field is a bitmask of per-block flags C3_ISP_PARAMS_FL_*. */ -struct c3_isp_params_block_header { - __u16 type; - __u16 flags; - __u32 size; -}; +#define c3_isp_params_block_header v4l2_isp_params_block_header /** * struct c3_isp_params_awb_gains - Gains for auto-white balance @@ -498,26 +464,10 @@ struct c3_isp_params_blc { /** * struct c3_isp_params_cfg - C3 ISP configuration parameters * - * This struct contains the configuration parameters of the C3 ISP - * algorithms, serialized by userspace into an opaque data buffer. Each - * configuration parameter block is represented by a block-specific structure - * which contains a :c:type:`c3_isp_param_block_header` entry as first - * member. Userspace populates the @data buffer with configuration parameters - * for the blocks that it intends to configure. As a consequence, the data - * buffer effective size changes according to the number of ISP blocks that - * userspace intends to configure. - * - * The parameters buffer is versioned by the @version field to allow modifying - * and extending its definition. Userspace should populate the @version field to - * inform the driver about the version it intends to use. The driver will parse - * and handle the @data buffer according to the data layout specific to the - * indicated revision and return an error if the desired revision is not - * supported. - * - * For each ISP block that userspace wants to configure, a block-specific - * structure is appended to the @data buffer, one after the other without gaps - * in between nor overlaps. Userspace shall populate the @total_size field with - * the effective size, in bytes, of the @data buffer. + * This is the driver-specific implementation of + * :c:type:`v4l2_isp_params_buffer`. + * + * Currently only C3_ISP_PARAM_BUFFER_V0 is supported. * * The expected memory layout of the parameters buffer is:: * @@ -561,4 +511,10 @@ struct c3_isp_params_cfg { __u8 data[C3_ISP_PARAMS_MAX_SIZE]; }; +#ifdef __KERNEL__ +/* Make sure the header is type-convertible to the generic v4l2 params one */ +static_assert((sizeof(struct c3_isp_params_cfg) - C3_ISP_PARAMS_MAX_SIZE) == + sizeof(struct v4l2_isp_params_buffer)); +#endif /* __KERNEL__ */ + #endif -- cgit v1.2.3 From ec4ac3cb7198070611987a6e91829fce0f4ce6d0 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 11 Nov 2025 16:15:45 +0000 Subject: media: uapi: Add MEDIA_BUS_FMT_RGB202020_1X60 format code The Mali-C55 ISP by ARM requires 20-bits per colour channel input on the bus. Add a new media bus format code to represent it. Reviewed-by: Lad Prabhakar Tested-by: Lad Prabhakar Reviewed-by: Laurent Pinchart Acked-by: Nayden Kanchev Co-developed-by: Jacopo Mondi Signed-off-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Hans Verkuil --- include/uapi/linux/media-bus-format.h | 3 ++- 1 file changed, 2 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 ff62056feed5..62ad82fd285a 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 0x1028 */ +/* RGB - next is 0x1029 */ #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 @@ -74,6 +74,7 @@ #define MEDIA_BUS_FMT_RGB888_1X36_CPADLO 0x1021 #define MEDIA_BUS_FMT_RGB121212_1X36 0x1019 #define MEDIA_BUS_FMT_RGB161616_1X48 0x101a +#define MEDIA_BUS_FMT_RGB202020_1X60 0x1028 /* YUV (including grey) - next is 0x202f */ #define MEDIA_BUS_FMT_Y8_1X8 0x2001 -- cgit v1.2.3 From 2477ab037621632c3ec167187dc9e7afac2ba7f2 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 11 Nov 2025 16:15:46 +0000 Subject: media: uapi: Add 20-bit bayer formats The Mali-C55 requires input data be in 20-bit format, MSB aligned. Add some new media bus format macros to represent that input format. Reviewed-by: Lad Prabhakar Tested-by: Lad Prabhakar Reviewed-by: Laurent Pinchart Co-developed-by: Jacopo Mondi Signed-off-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Hans Verkuil --- 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 62ad82fd285a..6005f033e62c 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -124,7 +124,7 @@ #define MEDIA_BUS_FMT_YUV16_1X48 0x202a #define MEDIA_BUS_FMT_UYYVYY16_0_5X48 0x202b -/* Bayer - next is 0x3021 */ +/* Bayer - next is 0x3025 */ #define MEDIA_BUS_FMT_SBGGR8_1X8 0x3001 #define MEDIA_BUS_FMT_SGBRG8_1X8 0x3013 #define MEDIA_BUS_FMT_SGRBG8_1X8 0x3002 @@ -157,6 +157,10 @@ #define MEDIA_BUS_FMT_SGBRG16_1X16 0x301e #define MEDIA_BUS_FMT_SGRBG16_1X16 0x301f #define MEDIA_BUS_FMT_SRGGB16_1X16 0x3020 +#define MEDIA_BUS_FMT_SBGGR20_1X20 0x3021 +#define MEDIA_BUS_FMT_SGBRG20_1X20 0x3022 +#define MEDIA_BUS_FMT_SGRBG20_1X20 0x3023 +#define MEDIA_BUS_FMT_SRGGB20_1X20 0x3024 /* JPEG compressed formats - next is 0x4002 */ #define MEDIA_BUS_FMT_JPEG_1X8 0x4001 -- cgit v1.2.3 From 8d0bbed21ef737195277c0af8c30511fb72e608b Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 11 Nov 2025 16:15:48 +0000 Subject: media: uapi: Add controls for Mali-C55 ISP Add definitions and documentation for the custom control that will be needed by the Mali-C55 ISP driver. This will be a read only bitmask of the driver's capabilities, informing userspace of which blocks are fitted and which are absent. Tested-by: Lad Prabhakar Reviewed-by: Lad Prabhakar Reviewed-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil --- include/uapi/linux/media/arm/mali-c55-config.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/v4l2-controls.h | 6 ++++++ 2 files changed, 32 insertions(+) create mode 100644 include/uapi/linux/media/arm/mali-c55-config.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/arm/mali-c55-config.h b/include/uapi/linux/media/arm/mali-c55-config.h new file mode 100644 index 000000000000..7fddece54ada --- /dev/null +++ b/include/uapi/linux/media/arm/mali-c55-config.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ARM Mali-C55 ISP Driver - Userspace API + * + * Copyright (C) 2023 Ideas on Board Oy + */ + +#ifndef __UAPI_MALI_C55_CONFIG_H +#define __UAPI_MALI_C55_CONFIG_H + +#include + +#define V4L2_CID_MALI_C55_CAPABILITIES (V4L2_CID_USER_MALI_C55_BASE + 0x0) +#define MALI_C55_GPS_PONG (1U << 0) +#define MALI_C55_GPS_WDR (1U << 1) +#define MALI_C55_GPS_COMPRESSION (1U << 2) +#define MALI_C55_GPS_TEMPER (1U << 3) +#define MALI_C55_GPS_SINTER_LITE (1U << 4) +#define MALI_C55_GPS_SINTER (1U << 5) +#define MALI_C55_GPS_IRIDIX_LTM (1U << 6) +#define MALI_C55_GPS_IRIDIX_GTM (1U << 7) +#define MALI_C55_GPS_CNR (1U << 8) +#define MALI_C55_GPS_FRSCALER (1U << 9) +#define MALI_C55_GPS_DS_PIPE (1U << 10) + +#endif /* __UAPI_MALI_C55_CONFIG_H */ diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 2d30107e047e..f84ed133a6c9 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -228,6 +228,12 @@ enum v4l2_colorfx { */ #define V4L2_CID_USER_RKISP1_BASE (V4L2_CID_USER_BASE + 0x1220) +/* + * The base for the Arm Mali-C55 ISP driver controls. + * We reserve 16 controls for this driver + */ +#define V4L2_CID_USER_MALI_C55_BASE (V4L2_CID_USER_BASE + 0x1230) + /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls * and the 'MPEG' part of the define is historical */ -- cgit v1.2.3 From 4d36f732366aeb32bf3486545e597500a3bf0994 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 11 Nov 2025 16:15:52 +0000 Subject: media: Add MALI_C55_3A_STATS meta format Add a new meta format for the Mali-C55 ISP's 3A Statistics along with a new descriptor entry. Tested-by: Lad Prabhakar Reviewed-by: Laurent Pinchart Acked-by: Nayden Kanchev Co-developed-by: Jacopo Mondi Signed-off-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index becd08fdbddb..cba4b1311667 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -884,6 +884,9 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RPI_FE_CFG v4l2_fourcc('R', 'P', 'F', 'C') /* PiSP FE configuration */ #define V4L2_META_FMT_RPI_FE_STATS v4l2_fourcc('R', 'P', 'F', 'S') /* PiSP FE stats */ +/* Vendor specific - used for Arm Mali-C55 ISP */ +#define V4L2_META_FMT_MALI_C55_STATS v4l2_fourcc('C', '5', '5', 'S') /* ARM Mali-C55 3A Statistics */ + #ifdef __KERNEL__ /* * Line-based metadata formats. Remember to update v4l_fill_fmtdesc() when -- cgit v1.2.3 From c7f832f6f8129bb666346cb4805805ad056059b7 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 11 Nov 2025 16:15:53 +0000 Subject: media: uapi: Add 3a stats buffer for mali-c55 Describe the format of the 3A statistics buffers in the userspace API header for the mali-c55 ISP. Tested-by: Lad Prabhakar Reviewed-by: Laurent Pinchart Acked-by: Nayden Kanchev Co-developed-by: Jacopo Mondi Signed-off-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Hans Verkuil --- include/uapi/linux/media/arm/mali-c55-config.h | 170 +++++++++++++++++++++++++ 1 file changed, 170 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/arm/mali-c55-config.h b/include/uapi/linux/media/arm/mali-c55-config.h index 7fddece54ada..e31fb8ffa10a 100644 --- a/include/uapi/linux/media/arm/mali-c55-config.h +++ b/include/uapi/linux/media/arm/mali-c55-config.h @@ -8,6 +8,7 @@ #ifndef __UAPI_MALI_C55_CONFIG_H #define __UAPI_MALI_C55_CONFIG_H +#include #include #define V4L2_CID_MALI_C55_CAPABILITIES (V4L2_CID_USER_MALI_C55_BASE + 0x0) @@ -23,4 +24,173 @@ #define MALI_C55_GPS_FRSCALER (1U << 9) #define MALI_C55_GPS_DS_PIPE (1U << 10) +/* + * Frames are split into zones of almost equal width and height - a zone is a + * rectangular tile of a frame. The metering blocks within the ISP collect + * aggregated statistics per zone. A maximum of 15x15 zones can be configured, + * and so the statistics buffer within the hardware is sized to accommodate + * that. + * + * The utilised number of zones is runtime configurable. + */ +#define MALI_C55_MAX_ZONES (15 * 15) + +/** + * struct mali_c55_ae_1024bin_hist - Auto Exposure 1024-bin histogram statistics + * + * @bins: 1024 element array of 16-bit pixel counts. + * + * The 1024-bin histogram module collects image-global but zone-weighted + * intensity distributions of pixels in fixed-width bins. The modules can be + * configured into different "plane modes" which affect the contents of the + * collected statistics. In plane mode 0, pixel intensities are taken regardless + * of colour plane into a single 1024-bin histogram with a bin width of 4. In + * plane mode 1, four 256-bin histograms with a bin width of 16 are collected - + * one for each CFA colour plane. In plane modes 4, 5, 6 and 7 two 512-bin + * histograms with a bin width of 8 are collected - in each mode one of the + * colour planes is collected into the first histogram and all the others are + * combined into the second. The histograms are stored consecutively in the bins + * array. + * + * The 16-bit pixel counts are stored as a 4-bit exponent in the most + * significant bits followed by a 12-bit mantissa. Conversion to a usable + * format can be done according to the following pseudo-code:: + * + * if (e == 0) { + * bin = m * 2; + * } else { + * bin = (m + 4096) * 2^e + * } + * + * where + * e is the exponent value in range 0..15 + * m is the mantissa value in range 0..4095 + * + * The pixels used in calculating the statistics can be masked using three + * methods: + * + * 1. Pixels can be skipped in X and Y directions independently. + * 2. Minimum/Maximum intensities can be configured + * 3. Zones can be differentially weighted, including 0 weighted to mask them + * + * The data for this histogram can be collected from different tap points in the + * ISP depending on configuration - after the white balance or digital gain + * blocks, or immediately after the input crossbar. + */ +struct mali_c55_ae_1024bin_hist { + __u16 bins[1024]; +} __attribute__((packed)); + +/** + * struct mali_c55_ae_5bin_hist - Auto Exposure 5-bin histogram statistics + * + * @hist0: 16-bit normalised pixel count for the 0th intensity bin + * @hist1: 16-bit normalised pixel count for the 1st intensity bin + * @hist3: 16-bit normalised pixel count for the 3rd intensity bin + * @hist4: 16-bit normalised pixel count for the 4th intensity bin + * + * The ISP generates a 5-bin histogram of normalised pixel counts within bins of + * pixel intensity for each of 225 possible zones within a frame. The centre bin + * of the histogram for each zone is not available from the hardware and must be + * calculated by subtracting the values of hist0, hist1, hist3 and hist4 from + * 0xffff as in the following equation: + * + * hist2 = 0xffff - (hist0 + hist1 + hist3 + hist4) + */ +struct mali_c55_ae_5bin_hist { + __u16 hist0; + __u16 hist1; + __u16 hist3; + __u16 hist4; +} __attribute__((packed)); + +/** + * struct mali_c55_awb_average_ratios - Auto White Balance colour ratios + * + * @avg_rg_gr: Average R/G or G/R ratio in Q4.8 format. + * @avg_bg_br: Average B/G or B/R ratio in Q4.8 format. + * @num_pixels: The number of pixels used in the AWB calculation + * + * The ISP calculates and collects average colour ratios for each zone in an + * image and stores them in Q4.8 format (the lowest 8 bits are fractional, with + * bits [11:8] representing the integer). The exact ratios collected (either + * R/G, B/G or G/R, B/R) are configurable through the parameters buffer. The + * value of the 4 high bits is undefined. + */ +struct mali_c55_awb_average_ratios { + __u16 avg_rg_gr; + __u16 avg_bg_br; + __u32 num_pixels; +} __attribute__((packed)); + +/** + * struct mali_c55_af_statistics - Auto Focus edge and intensity statistics + * + * @intensity_stats: Packed mantissa and exponent value for pixel intensity + * @edge_stats: Packed mantissa and exponent values for edge intensity + * + * The ISP collects the squared sum of pixel intensities for each zone within a + * configurable Region of Interest on the frame. Additionally, the same data are + * collected after being passed through a bandpass filter which removes high and + * low frequency components - these are referred to as the edge statistics. + * + * The intensity and edge statistics for a zone can be used to calculate the + * contrast information for a zone + * + * C = E2 / I2 + * + * Where I2 is the intensity statistic for a zone and E2 is the edge statistic + * for that zone. Optimum focus is reached when C is at its maximum. + * + * The intensity and edge statistics are stored packed into a non-standard 16 + * bit floating point format, where the 7 most significant bits represent the + * exponent and the 9 least significant bits the mantissa. This format can be + * unpacked with the following pseudocode:: + * + * if (e == 0) { + * x = m; + * } else { + * x = 2^e-1 * (m + 2^9) + * } + * + * where + * e is the exponent value in range 0..127 + * m is the mantissa value in range 0..511 + */ +struct mali_c55_af_statistics { + __u16 intensity_stats; + __u16 edge_stats; +} __attribute__((packed)); + +/** + * struct mali_c55_stats_buffer - 3A statistics for the mali-c55 ISP + * + * @ae_1024bin_hist: 1024-bin frame-global pixel intensity histogram + * @iridix_1024bin_hist: Post-Iridix block 1024-bin histogram + * @ae_5bin_hists: 5-bin pixel intensity histograms for AEC + * @reserved1: Undefined buffer space + * @awb_ratios: Color balance ratios for Auto White Balance + * @reserved2: Undefined buffer space + * @af_statistics: Pixel intensity statistics for Auto Focus + * @reserved3: Undefined buffer space + * + * This struct describes the metering statistics space in the Mali-C55 ISP's + * hardware in its entirety. The space between each defined area is marked as + * "unknown" and may not be 0, but should not be used. The @ae_5bin_hists, + * @awb_ratios and @af_statistics members are arrays of statistics per-zone. + * The zones are arranged in the array in raster order starting from the top + * left corner of the image. + */ + +struct mali_c55_stats_buffer { + struct mali_c55_ae_1024bin_hist ae_1024bin_hist; + struct mali_c55_ae_1024bin_hist iridix_1024bin_hist; + struct mali_c55_ae_5bin_hist ae_5bin_hists[MALI_C55_MAX_ZONES]; + __u32 reserved1[14]; + struct mali_c55_awb_average_ratios awb_ratios[MALI_C55_MAX_ZONES]; + __u32 reserved2[14]; + struct mali_c55_af_statistics af_statistics[MALI_C55_MAX_ZONES]; + __u32 reserved3[15]; +} __attribute__((packed)); + #endif /* __UAPI_MALI_C55_CONFIG_H */ -- cgit v1.2.3 From 1ab3cb233d61131b2d02650f8ed9e4e077fd4508 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Tue, 11 Nov 2025 16:15:56 +0000 Subject: media: mali-c55: Add image formats for Mali-C55 parameters buffer Add a new V4L2 meta format code for the Mali-C55 parameters. Tested-by: Lad Prabhakar Reviewed-by: Laurent Pinchart Acked-by: Nayden Kanchev Signed-off-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index cba4b1311667..add08188f068 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -885,6 +885,7 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RPI_FE_STATS v4l2_fourcc('R', 'P', 'F', 'S') /* PiSP FE stats */ /* Vendor specific - used for Arm Mali-C55 ISP */ +#define V4L2_META_FMT_MALI_C55_PARAMS v4l2_fourcc('C', '5', '5', 'P') /* ARM Mali-C55 Parameters */ #define V4L2_META_FMT_MALI_C55_STATS v4l2_fourcc('C', '5', '5', 'S') /* ARM Mali-C55 3A Statistics */ #ifdef __KERNEL__ -- cgit v1.2.3 From 08a99369f44eeb63eacc56fe42f4c67a6c7dbc37 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 11 Nov 2025 16:15:57 +0000 Subject: media: uapi: Add parameters structs to mali-c55-config.h Add structures describing the ISP parameters to mali-c55-config.h Tested-by: Lad Prabhakar Acked-by: Nayden Kanchev Co-developed-by: Jacopo Mondi Signed-off-by: Jacopo Mondi Signed-off-by: Daniel Scally Signed-off-by: Hans Verkuil --- include/uapi/linux/media/arm/mali-c55-config.h | 598 +++++++++++++++++++++++++ 1 file changed, 598 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/arm/mali-c55-config.h b/include/uapi/linux/media/arm/mali-c55-config.h index e31fb8ffa10a..109082c5694f 100644 --- a/include/uapi/linux/media/arm/mali-c55-config.h +++ b/include/uapi/linux/media/arm/mali-c55-config.h @@ -10,6 +10,7 @@ #include #include +#include #define V4L2_CID_MALI_C55_CAPABILITIES (V4L2_CID_USER_MALI_C55_BASE + 0x0) #define MALI_C55_GPS_PONG (1U << 0) @@ -193,4 +194,601 @@ struct mali_c55_stats_buffer { __u32 reserved3[15]; } __attribute__((packed)); +/** + * enum mali_c55_param_buffer_version - Mali-C55 parameters block versioning + * + * @MALI_C55_PARAM_BUFFER_V1: First version of Mali-C55 parameters block + */ +enum mali_c55_param_buffer_version { + MALI_C55_PARAM_BUFFER_V1, +}; + +/** + * enum mali_c55_param_block_type - Enumeration of Mali-C55 parameter blocks + * + * This enumeration defines the types of Mali-C55 parameters block. Each block + * configures a specific processing block of the Mali-C55 ISP. The block + * type allows the driver to correctly interpret the parameters block data. + * + * It is the responsibility of userspace to correctly set the type of each + * parameters block. + * + * @MALI_C55_PARAM_BLOCK_SENSOR_OFFS: Sensor pre-shading black level offset + * @MALI_C55_PARAM_BLOCK_AEXP_HIST: Auto-exposure 1024-bin histogram + * configuration + * @MALI_C55_PARAM_BLOCK_AEXP_IHIST: Post-Iridix auto-exposure 1024-bin + * histogram configuration + * @MALI_C55_PARAM_BLOCK_AEXP_HIST_WEIGHTS: Auto-exposure 1024-bin histogram + * weighting + * @MALI_C55_PARAM_BLOCK_AEXP_IHIST_WEIGHTS: Post-Iridix auto-exposure 1024-bin + * histogram weighting + * @MALI_C55_PARAM_BLOCK_DIGITAL_GAIN: Digital gain + * @MALI_C55_PARAM_BLOCK_AWB_GAINS: Auto-white balance gains + * @MALI_C55_PARAM_BLOCK_AWB_CONFIG: Auto-white balance statistics config + * @MALI_C55_PARAM_BLOCK_AWB_GAINS_AEXP: Auto-white balance gains for AEXP-0 tap + * @MALI_C55_PARAM_MESH_SHADING_CONFIG : Mesh shading tables configuration + * @MALI_C55_PARAM_MESH_SHADING_SELECTION: Mesh shading table selection + */ +enum mali_c55_param_block_type { + MALI_C55_PARAM_BLOCK_SENSOR_OFFS, + MALI_C55_PARAM_BLOCK_AEXP_HIST, + MALI_C55_PARAM_BLOCK_AEXP_IHIST, + MALI_C55_PARAM_BLOCK_AEXP_HIST_WEIGHTS, + MALI_C55_PARAM_BLOCK_AEXP_IHIST_WEIGHTS, + MALI_C55_PARAM_BLOCK_DIGITAL_GAIN, + MALI_C55_PARAM_BLOCK_AWB_GAINS, + MALI_C55_PARAM_BLOCK_AWB_CONFIG, + MALI_C55_PARAM_BLOCK_AWB_GAINS_AEXP, + MALI_C55_PARAM_MESH_SHADING_CONFIG, + MALI_C55_PARAM_MESH_SHADING_SELECTION, +}; + +/** + * struct mali_c55_params_sensor_off_preshading - offset subtraction for each + * color channel + * + * Provides removal of the sensor black level from the sensor data. Separate + * offsets are provided for each of the four Bayer component color channels + * which are defaulted to R, Gr, Gb, B. + * + * header.type should be set to MALI_C55_PARAM_BLOCK_SENSOR_OFFS from + * :c:type:`mali_c55_param_block_type` for this block. + * + * @header: The Mali-C55 parameters block header + * @chan00: Offset for color channel 00 (default: R) + * @chan01: Offset for color channel 01 (default: Gr) + * @chan10: Offset for color channel 10 (default: Gb) + * @chan11: Offset for color channel 11 (default: B) + */ +struct mali_c55_params_sensor_off_preshading { + struct v4l2_isp_params_block_header header; + __u32 chan00; + __u32 chan01; + __u32 chan10; + __u32 chan11; +}; + +/** + * enum mali_c55_aexp_hist_tap_points - Tap points for the AEXP histogram + * @MALI_C55_AEXP_HIST_TAP_WB: After static white balance + * @MALI_C55_AEXP_HIST_TAP_FS: After WDR Frame Stitch + * @MALI_C55_AEXP_HIST_TAP_TPG: After the test pattern generator + */ +enum mali_c55_aexp_hist_tap_points { + MALI_C55_AEXP_HIST_TAP_WB = 0, + MALI_C55_AEXP_HIST_TAP_FS, + MALI_C55_AEXP_HIST_TAP_TPG, +}; + +/** + * enum mali_c55_aexp_skip_x - Horizontal pixel skipping + * @MALI_C55_AEXP_SKIP_X_EVERY_2ND: Collect every 2nd pixel horizontally + * @MALI_C55_AEXP_SKIP_X_EVERY_3RD: Collect every 3rd pixel horizontally + * @MALI_C55_AEXP_SKIP_X_EVERY_4TH: Collect every 4th pixel horizontally + * @MALI_C55_AEXP_SKIP_X_EVERY_5TH: Collect every 5th pixel horizontally + * @MALI_C55_AEXP_SKIP_X_EVERY_8TH: Collect every 8th pixel horizontally + * @MALI_C55_AEXP_SKIP_X_EVERY_9TH: Collect every 9th pixel horizontally + */ +enum mali_c55_aexp_skip_x { + MALI_C55_AEXP_SKIP_X_EVERY_2ND, + MALI_C55_AEXP_SKIP_X_EVERY_3RD, + MALI_C55_AEXP_SKIP_X_EVERY_4TH, + MALI_C55_AEXP_SKIP_X_EVERY_5TH, + MALI_C55_AEXP_SKIP_X_EVERY_8TH, + MALI_C55_AEXP_SKIP_X_EVERY_9TH +}; + +/** + * enum mali_c55_aexp_skip_y - Vertical pixel skipping + * @MALI_C55_AEXP_SKIP_Y_ALL: Collect every single pixel vertically + * @MALI_C55_AEXP_SKIP_Y_EVERY_2ND: Collect every 2nd pixel vertically + * @MALI_C55_AEXP_SKIP_Y_EVERY_3RD: Collect every 3rd pixel vertically + * @MALI_C55_AEXP_SKIP_Y_EVERY_4TH: Collect every 4th pixel vertically + * @MALI_C55_AEXP_SKIP_Y_EVERY_5TH: Collect every 5th pixel vertically + * @MALI_C55_AEXP_SKIP_Y_EVERY_8TH: Collect every 8th pixel vertically + * @MALI_C55_AEXP_SKIP_Y_EVERY_9TH: Collect every 9th pixel vertically + */ +enum mali_c55_aexp_skip_y { + MALI_C55_AEXP_SKIP_Y_ALL, + MALI_C55_AEXP_SKIP_Y_EVERY_2ND, + MALI_C55_AEXP_SKIP_Y_EVERY_3RD, + MALI_C55_AEXP_SKIP_Y_EVERY_4TH, + MALI_C55_AEXP_SKIP_Y_EVERY_5TH, + MALI_C55_AEXP_SKIP_Y_EVERY_8TH, + MALI_C55_AEXP_SKIP_Y_EVERY_9TH +}; + +/** + * enum mali_c55_aexp_row_column_offset - Start from the first or second row or + * column + * @MALI_C55_AEXP_FIRST_ROW_OR_COL: Start from the first row / column + * @MALI_C55_AEXP_SECOND_ROW_OR_COL: Start from the second row / column + */ +enum mali_c55_aexp_row_column_offset { + MALI_C55_AEXP_FIRST_ROW_OR_COL = 1, + MALI_C55_AEXP_SECOND_ROW_OR_COL = 2, +}; + +/** + * enum mali_c55_aexp_hist_plane_mode - Mode for the AEXP Histograms + * @MALI_C55_AEXP_HIST_COMBINED: All color planes in one 1024-bin histogram + * @MALI_C55_AEXP_HIST_SEPARATE: Each color plane in one 256-bin histogram with a bin width of 16 + * @MALI_C55_AEXP_HIST_FOCUS_00: Top left plane in the first bank, rest in second bank + * @MALI_C55_AEXP_HIST_FOCUS_01: Top right plane in the first bank, rest in second bank + * @MALI_C55_AEXP_HIST_FOCUS_10: Bottom left plane in the first bank, rest in second bank + * @MALI_C55_AEXP_HIST_FOCUS_11: Bottom right plane in the first bank, rest in second bank + * + * In the "focus" modes statistics are collected into two 512-bin histograms + * with a bin width of 8. One colour plane is in the first histogram with the + * remainder combined into the second. The four options represent which of the + * four positions in a bayer pattern are the focused plane. + */ +enum mali_c55_aexp_hist_plane_mode { + MALI_C55_AEXP_HIST_COMBINED = 0, + MALI_C55_AEXP_HIST_SEPARATE = 1, + MALI_C55_AEXP_HIST_FOCUS_00 = 4, + MALI_C55_AEXP_HIST_FOCUS_01 = 5, + MALI_C55_AEXP_HIST_FOCUS_10 = 6, + MALI_C55_AEXP_HIST_FOCUS_11 = 7, +}; + +/** + * struct mali_c55_params_aexp_hist - configuration for AEXP metering hists + * + * This struct allows users to configure the 1024-bin AEXP histograms. Broadly + * speaking the parameters allow you to mask particular regions of the image and + * to select different kinds of histogram. + * + * The skip_x, offset_x, skip_y and offset_y fields allow users to ignore or + * mask pixels in the frame by their position relative to the top left pixel. + * First, the skip_y, offset_x and offset_y fields define which of the pixels + * within each 2x2 region will be counted in the statistics. + * + * If skip_y == 0 then two pixels from each covered region will be counted. If + * both offset_x and offset_y are zero, then the two left-most pixels in each + * 2x2 pixel region will be counted. Setting offset_x = 1 will discount the top + * left pixel and count the top right pixel. Setting offset_y = 1 will discount + * the bottom left pixel and count the bottom right pixel. + * + * If skip_y != 0 then only a single pixel from each region covered by the + * pattern will be counted. In this case offset_x controls whether the pixel + * that's counted is in the left (if offset_x == 0) or right (if offset_x == 1) + * column and offset_y controls whether the pixel that's counted is in the top + * (if offset_y == 0) or bottom (if offset_y == 1) row. + * + * The skip_x and skip_y fields control how the 2x2 pixel region is repeated + * across the image data. The first instance of the region is always in the top + * left of the image data. The skip_x field controls how many pixels are ignored + * in the x direction before the pixel masking region is repeated. The skip_y + * field controls how many pixels are ignored in the y direction before the + * pixel masking region is repeated. + * + * These fields can be used to reduce the number of pixels counted for the + * statistics, but it's important to be careful to configure them correctly. + * Some combinations of values will result in colour components from the input + * data being ignored entirely, for example in the following configuration: + * + * skip_x = 0 + * offset_x = 0 + * skip_y = 0 + * offset_y = 0 + * + * Only the R and Gb components of RGGB data that was input would be collected. + * Similarly in the following configuration: + * + * skip_x = 0 + * offset_x = 0 + * skip_y = 1 + * offset_y = 1 + * + * Only the Gb component of RGGB data that was input would be collected. To + * correct things such that all 4 colour components were included it would be + * necessary to set the skip_x and skip_y fields in a way that resulted in all + * four colour components being collected: + * + * skip_x = 1 + * offset_x = 0 + * skip_y = 1 + * offset_y = 1 + * + * header.type should be set to one of either MALI_C55_PARAM_BLOCK_AEXP_HIST or + * MALI_C55_PARAM_BLOCK_AEXP_IHIST from :c:type:`mali_c55_param_block_type`. + * + * @header: The Mali-C55 parameters block header + * @skip_x: Horizontal decimation. See enum mali_c55_aexp_skip_x + * @offset_x: Skip the first column, or not. See enum mali_c55_aexp_row_column_offset + * @skip_y: Vertical decimation. See enum mali_c55_aexp_skip_y + * @offset_y: Skip the first row, or not. See enum mali_c55_aexp_row_column_offset + * @scale_bottom: Scale pixels in bottom half of intensity range: 0=1x ,1=2x, 2=4x, 4=8x, 4=16x + * @scale_top: scale pixels in top half of intensity range: 0=1x ,1=2x, 2=4x, 4=8x, 4=16x + * @plane_mode: Plane separation mode. See enum mali_c55_aexp_hist_plane_mode + * @tap_point: Tap point for histogram from enum mali_c55_aexp_hist_tap_points. + * This parameter is unused for the post-Iridix Histogram + */ +struct mali_c55_params_aexp_hist { + struct v4l2_isp_params_block_header header; + __u8 skip_x; + __u8 offset_x; + __u8 skip_y; + __u8 offset_y; + __u8 scale_bottom; + __u8 scale_top; + __u8 plane_mode; + __u8 tap_point; +}; + +/** + * struct mali_c55_params_aexp_weights - Array of weights for AEXP metering + * + * This struct allows users to configure the weighting for both of the 1024-bin + * AEXP histograms. The pixel data collected for each zone is multiplied by the + * corresponding weight from this array, which may be zero if the intention is + * to mask off the zone entirely. + * + * header.type should be set to one of either MALI_C55_PARAM_BLOCK_AEXP_HIST_WEIGHTS + * or MALI_C55_PARAM_BLOCK_AEXP_IHIST_WEIGHTS from :c:type:`mali_c55_param_block_type`. + * + * @header: The Mali-C55 parameters block header + * @nodes_used_horiz: Number of active zones horizontally [0..15] + * @nodes_used_vert: Number of active zones vertically [0..15] + * @zone_weights: Zone weighting. Index is row*col where 0,0 is the top + * left zone continuing in raster order. Each zone can be + * weighted in the range [0..15]. The number of rows and + * columns is defined by @nodes_used_vert and + * @nodes_used_horiz + */ +struct mali_c55_params_aexp_weights { + struct v4l2_isp_params_block_header header; + __u8 nodes_used_horiz; + __u8 nodes_used_vert; + __u8 zone_weights[MALI_C55_MAX_ZONES]; +}; + +/** + * struct mali_c55_params_digital_gain - Digital gain value + * + * This struct carries a digital gain value to set in the ISP. + * + * header.type should be set to MALI_C55_PARAM_BLOCK_DIGITAL_GAIN from + * :c:type:`mali_c55_param_block_type` for this block. + * + * @header: The Mali-C55 parameters block header + * @gain: The digital gain value to apply, in Q5.8 format. + */ +struct mali_c55_params_digital_gain { + struct v4l2_isp_params_block_header header; + __u16 gain; +}; + +/** + * enum mali_c55_awb_stats_mode - Statistics mode for AWB + * @MALI_C55_AWB_MODE_GRBR: Statistics collected as Green/Red and Blue/Red ratios + * @MALI_C55_AWB_MODE_RGBG: Statistics collected as Red/Green and Blue/Green ratios + */ +enum mali_c55_awb_stats_mode { + MALI_C55_AWB_MODE_GRBR = 0, + MALI_C55_AWB_MODE_RGBG, +}; + +/** + * struct mali_c55_params_awb_gains - Gain settings for auto white balance + * + * This struct allows users to configure the gains for auto-white balance. There + * are four gain settings corresponding to each colour channel in the bayer + * domain. Although named generically, the association between the gain applied + * and the colour channel is done automatically within the ISP depending on the + * input format, and so the following mapping always holds true:: + * + * gain00 = R + * gain01 = Gr + * gain10 = Gb + * gain11 = B + * + * All of the gains are stored in Q4.8 format. + * + * header.type should be set to one of either MALI_C55_PARAM_BLOCK_AWB_GAINS or + * MALI_C55_PARAM_BLOCK_AWB_GAINS_AEXP from :c:type:`mali_c55_param_block_type`. + * + * @header: The Mali-C55 parameters block header + * @gain00: Multiplier for colour channel 00 + * @gain01: Multiplier for colour channel 01 + * @gain10: Multiplier for colour channel 10 + * @gain11: Multiplier for colour channel 11 + */ +struct mali_c55_params_awb_gains { + struct v4l2_isp_params_block_header header; + __u16 gain00; + __u16 gain01; + __u16 gain10; + __u16 gain11; +}; + +/** + * enum mali_c55_params_awb_tap_points - Tap points for the AWB statistics + * @MALI_C55_AWB_STATS_TAP_PF: Immediately after the Purple Fringe block + * @MALI_C55_AWB_STATS_TAP_CNR: Immediately after the CNR block + */ +enum mali_c55_params_awb_tap_points { + MALI_C55_AWB_STATS_TAP_PF = 0, + MALI_C55_AWB_STATS_TAP_CNR, +}; + +/** + * struct mali_c55_params_awb_config - Stats settings for auto-white balance + * + * This struct allows the configuration of the statistics generated for auto + * white balance. Pixel intensity limits can be set to exclude overly bright or + * dark regions of an image from the statistics entirely. Colour ratio minima + * and maxima can be set to discount pixels who's ratios fall outside the + * defined boundaries; there are two sets of registers to do this - the + * "min/max" ratios which bound a region and the "high/low" ratios which further + * trim the upper and lower ratios. For example with the boundaries configured + * as follows, only pixels whos colour ratios falls into the region marked "A" + * would be counted:: + * + * cr_high + * 2.0 | | + * | cb_max --> _________________________v_____ + * 1.8 | | \ | + * | | \ | + * 1.6 | | \ | + * | | \ | + * c 1.4 | cb_low -->|\ A \|<-- cb_high + * b | | \ | + * 1.2 | | \ | + * r | | \ | + * a 1.0 | cb_min --> |____\_________________________| + * t | ^ ^ ^ + * i 0.8 | | | | + * o | cr_min | cr_max + * s 0.6 | | + * | cr_low + * 0.4 | + * | + * 0.2 | + * | + * 0.0 |_______________________________________________________________ + * 0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 2.0 + * cr ratios + * + * header.type should be set to MALI_C55_PARAM_BLOCK_AWB_CONFIG from + * :c:type:`mali_c55_param_block_type` for this block. + * + * @header: The Mali-C55 parameters block header + * @tap_point: The tap point from enum mali_c55_params_awb_tap_points + * @stats_mode: AWB statistics collection mode, see :c:type:`mali_c55_awb_stats_mode` + * @white_level: Upper pixel intensity (I.E. raw pixel values) limit + * @black_level: Lower pixel intensity (I.E. raw pixel values) limit + * @cr_max: Maximum R/G ratio (Q4.8 format) + * @cr_min: Minimum R/G ratio (Q4.8 format) + * @cb_max: Maximum B/G ratio (Q4.8 format) + * @cb_min: Minimum B/G ratio (Q4.8 format) + * @nodes_used_horiz: Number of active zones horizontally [0..15] + * @nodes_used_vert: Number of active zones vertically [0..15] + * @cr_high: R/G ratio trim high (Q4.8 format) + * @cr_low: R/G ratio trim low (Q4.8 format) + * @cb_high: B/G ratio trim high (Q4.8 format) + * @cb_low: B/G ratio trim low (Q4.8 format) + */ +struct mali_c55_params_awb_config { + struct v4l2_isp_params_block_header header; + __u8 tap_point; + __u8 stats_mode; + __u16 white_level; + __u16 black_level; + __u16 cr_max; + __u16 cr_min; + __u16 cb_max; + __u16 cb_min; + __u8 nodes_used_horiz; + __u8 nodes_used_vert; + __u16 cr_high; + __u16 cr_low; + __u16 cb_high; + __u16 cb_low; +}; + +#define MALI_C55_NUM_MESH_SHADING_ELEMENTS 3072 + +/** + * struct mali_c55_params_mesh_shading_config - Mesh shading configuration + * + * The mesh shading correction module allows programming a separate table of + * either 16x16 or 32x32 node coefficients for 3 different light sources. The + * final correction coefficients applied are computed by blending the + * coefficients from two tables together. + * + * A page of 1024 32-bit integers is associated to each colour channel, with + * pages stored consecutively in memory. Each 32-bit integer packs 3 8-bit + * correction coefficients for a single node, one for each of the three light + * sources. The 8 most significant bits are unused. The following table + * describes the layout:: + * + * +----------- Page (Colour Plane) 0 -------------+ + * | @mesh[i] | Mesh Point | Bits | Light Source | + * +-----------+------------+-------+--------------+ + * | 0 | 0,0 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * | 1 | 0,1 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * | ... | ... | ... | ... | + * +-----------+------------+-------+--------------+ + * | 1023 | 31,31 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +----------- Page (Colour Plane) 1 -------------+ + * | @mesh[i] | Mesh Point | Bits | Light Source | + * +-----------+------------+-------+--------------+ + * | 1024 | 0,0 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * | 1025 | 0,1 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * | ... | ... | ... | ... | + * +-----------+------------+-------+--------------+ + * | 2047 | 31,31 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +----------- Page (Colour Plane) 2 -------------+ + * | @mesh[i] | Mesh Point | Bits | Light Source | + * +-----------+------------+-------+--------------+ + * | 2048 | 0,0 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * | 2049 | 0,1 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * | ... | ... | ... | ... | + * +-----------+------------+-------+--------------+ + * | 3071 | 31,31 | 16,23 | LS2 | + * | | | 08-15 | LS1 | + * | | | 00-07 | LS0 | + * +-----------+------------+-------+--------------+ + * + * The @mesh_scale member determines the precision and minimum and maximum gain. + * For example if @mesh_scale is 0 and therefore selects 0 - 2x gain, a value of + * 0 in a coefficient means 0.0 gain, a value of 128 means 1.0 gain and 255 + * means 2.0 gain. + * + * header.type should be set to MALI_C55_PARAM_MESH_SHADING_CONFIG from + * :c:type:`mali_c55_param_block_type` for this block. + * + * @header: The Mali-C55 parameters block header + * @mesh_show: Output the mesh data rather than image data + * @mesh_scale: Set the precision and maximum gain range of mesh shading + * - 0 = 0-2x gain + * - 1 = 0-4x gain + * - 2 = 0-8x gain + * - 3 = 0-16x gain + * - 4 = 1-2x gain + * - 5 = 1-3x gain + * - 6 = 1-5x gain + * - 7 = 1-9x gain + * @mesh_page_r: Mesh page select for red colour plane [0..2] + * @mesh_page_g: Mesh page select for green colour plane [0..2] + * @mesh_page_b: Mesh page select for blue colour plane [0..2] + * @mesh_width: Number of horizontal nodes minus 1 [15,31] + * @mesh_height: Number of vertical nodes minus 1 [15,31] + * @mesh: Mesh shading correction tables + */ +struct mali_c55_params_mesh_shading_config { + struct v4l2_isp_params_block_header header; + __u8 mesh_show; + __u8 mesh_scale; + __u8 mesh_page_r; + __u8 mesh_page_g; + __u8 mesh_page_b; + __u8 mesh_width; + __u8 mesh_height; + __u32 mesh[MALI_C55_NUM_MESH_SHADING_ELEMENTS]; +}; + +/** enum mali_c55_params_mesh_alpha_bank - Mesh shading table bank selection + * @MALI_C55_MESH_ALPHA_BANK_LS0_AND_LS1 - Select Light Sources 0 and 1 + * @MALI_C55_MESH_ALPHA_BANK_LS1_AND_LS2 - Select Light Sources 1 and 2 + * @MALI_C55_MESH_ALPHA_BANK_LS0_AND_LS2 - Select Light Sources 0 and 2 + */ +enum mali_c55_params_mesh_alpha_bank { + MALI_C55_MESH_ALPHA_BANK_LS0_AND_LS1 = 0, + MALI_C55_MESH_ALPHA_BANK_LS1_AND_LS2 = 1, + MALI_C55_MESH_ALPHA_BANK_LS0_AND_LS2 = 4 +}; + +/** + * struct mali_c55_params_mesh_shading_selection - Mesh table selection + * + * The module computes the final correction coefficients by blending the ones + * from two light source tables, which are selected (independently for each + * colour channel) by the @mesh_alpha_bank_r/g/b fields. + * + * The final blended coefficients for each node are calculated using the + * following equation: + * + * Final coefficient = (a * LS\ :sub:`b`\ + (256 - a) * LS\ :sub:`a`\) / 256 + * + * Where a is the @mesh_alpha_r/g/b value, and LS\ :sub:`a`\ and LS\ :sub:`b`\ + * are the node cofficients for the two tables selected by the + * @mesh_alpha_bank_r/g/b value. + * + * The scale of the applied correction may also be controlled by tuning the + * @mesh_strength member. This is a modifier to the final coefficients which can + * be used to globally reduce the gains applied. + * + * header.type should be set to MALI_C55_PARAM_MESH_SHADING_SELECTION from + * :c:type:`mali_c55_param_block_type` for this block. + * + * @header: The Mali-C55 parameters block header + * @mesh_alpha_bank_r: Red mesh table select (c:type:`enum mali_c55_params_mesh_alpha_bank`) + * @mesh_alpha_bank_g: Green mesh table select (c:type:`enum mali_c55_params_mesh_alpha_bank`) + * @mesh_alpha_bank_b: Blue mesh table select (c:type:`enum mali_c55_params_mesh_alpha_bank`) + * @mesh_alpha_r: Blend coefficient for R [0..255] + * @mesh_alpha_g: Blend coefficient for G [0..255] + * @mesh_alpha_b: Blend coefficient for B [0..255] + * @mesh_strength: Mesh strength in Q4.12 format [0..4096] + */ +struct mali_c55_params_mesh_shading_selection { + struct v4l2_isp_params_block_header header; + __u8 mesh_alpha_bank_r; + __u8 mesh_alpha_bank_g; + __u8 mesh_alpha_bank_b; + __u8 mesh_alpha_r; + __u8 mesh_alpha_g; + __u8 mesh_alpha_b; + __u16 mesh_strength; +}; + +/** + * define MALI_C55_PARAMS_MAX_SIZE - Maximum size of all Mali C55 Parameters + * + * Though the parameters for the Mali-C55 are passed as optional blocks, the + * driver still needs to know the absolute maximum size so that it can allocate + * a buffer sized appropriately to accommodate userspace attempting to set all + * possible parameters in a single frame. + * + * Some structs are in this list multiple times. Where that's the case, it just + * reflects the fact that the same struct can be used with multiple different + * header types from :c:type:`mali_c55_param_block_type`. + */ +#define MALI_C55_PARAMS_MAX_SIZE \ + (sizeof(struct mali_c55_params_sensor_off_preshading) + \ + sizeof(struct mali_c55_params_aexp_hist) + \ + sizeof(struct mali_c55_params_aexp_weights) + \ + sizeof(struct mali_c55_params_aexp_hist) + \ + sizeof(struct mali_c55_params_aexp_weights) + \ + sizeof(struct mali_c55_params_digital_gain) + \ + sizeof(struct mali_c55_params_awb_gains) + \ + sizeof(struct mali_c55_params_awb_config) + \ + sizeof(struct mali_c55_params_awb_gains) + \ + sizeof(struct mali_c55_params_mesh_shading_config) + \ + sizeof(struct mali_c55_params_mesh_shading_selection)) + #endif /* __UAPI_MALI_C55_CONFIG_H */ -- cgit v1.2.3 From f91bc8f61abf0e1d23108ae9871c60d7612a09b2 Mon Sep 17 00:00:00 2001 From: Magnus Kulke Date: Thu, 6 Nov 2025 14:13:31 -0800 Subject: mshv: Allow mappings that overlap in uaddr Currently the MSHV driver rejects mappings that would overlap in userspace. Some VMMs require the same memory to be mapped to different parts of the guest's address space, and so working around this restriction is difficult. The hypervisor itself doesn't prohibit mappings that overlap in uaddr, (really in SPA; system physical addresses), so supporting this in the driver doesn't require any extra work: only the checks need to be removed. Since no userspace code until now has been able to overlap regions in userspace, relaxing this constraint can't break any existing code. Signed-off-by: Magnus Kulke Signed-off-by: Nuno Das Neves Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/uapi/linux/mshv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mshv.h b/include/uapi/linux/mshv.h index 876bfe4e4227..374f75e198bc 100644 --- a/include/uapi/linux/mshv.h +++ b/include/uapi/linux/mshv.h @@ -89,7 +89,7 @@ enum { * @rsvd: MBZ * * Map or unmap a region of userspace memory to Guest Physical Addresses (GPA). - * Mappings can't overlap in GPA space or userspace. + * Mappings can't overlap in GPA space. * To unmap, these fields must match an existing mapping. */ struct mshv_user_mem_region { -- cgit v1.2.3 From c91fe5f162f278d4aa960d06d2dbc42f9857593a Mon Sep 17 00:00:00 2001 From: Muminul Islam Date: Thu, 13 Nov 2025 11:45:33 -0800 Subject: mshv: Extend create partition ioctl to support cpu features The existing mshv create partition ioctl does not provide a way to specify which cpu features are enabled in the guest. Instead, it attempts to enable all features and those that are not supported are silently disabled by the hypervisor. This was done to reduce unnecessary complexity and is sufficient for many cases. However, new scenarios require fine-grained control over these features. Define a new mshv_create_partition_v2 structure which supports passing the disabled processor and xsave feature bits through to the create partition hypercall directly. Introduce a new flag MSHV_PT_BIT_CPU_AND_XSAVE_FEATURES which enables the new structure. If unset, the original mshv_create_partition struct is used, with the old behavior of enabling all features. Co-developed-by: Jinank Jain Signed-off-by: Jinank Jain Signed-off-by: Muminul Islam Signed-off-by: Nuno Das Neves Reviewed-by: Michael Kelley Signed-off-by: Wei Liu --- include/uapi/linux/mshv.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mshv.h b/include/uapi/linux/mshv.h index 374f75e198bc..b645d17cc531 100644 --- a/include/uapi/linux/mshv.h +++ b/include/uapi/linux/mshv.h @@ -26,6 +26,7 @@ enum { MSHV_PT_BIT_LAPIC, MSHV_PT_BIT_X2APIC, MSHV_PT_BIT_GPA_SUPER_PAGES, + MSHV_PT_BIT_CPU_AND_XSAVE_FEATURES, MSHV_PT_BIT_COUNT, }; @@ -41,6 +42,8 @@ enum { * @pt_flags: Bitmask of 1 << MSHV_PT_BIT_* * @pt_isolation: MSHV_PT_ISOLATION_* * + * This is the initial/v1 version for backward compatibility. + * * Returns a file descriptor to act as a handle to a guest partition. * At this point the partition is not yet initialized in the hypervisor. * Some operations must be done with the partition in this state, e.g. setting @@ -52,6 +55,37 @@ struct mshv_create_partition { __u64 pt_isolation; }; +#define MSHV_NUM_CPU_FEATURES_BANKS 2 + +/** + * struct mshv_create_partition_v2 + * + * This is extended version of the above initial MSHV_CREATE_PARTITION + * ioctl and allows for following additional parameters: + * + * @pt_num_cpu_fbanks: Must be set to MSHV_NUM_CPU_FEATURES_BANKS. + * @pt_cpu_fbanks: Disabled processor feature banks array. + * @pt_disabled_xsave: Disabled xsave feature bits. + * + * pt_cpu_fbanks and pt_disabled_xsave are passed through as-is to the create + * partition hypercall. + * + * Returns : same as above original mshv_create_partition + */ +struct mshv_create_partition_v2 { + __u64 pt_flags; + __u64 pt_isolation; + __u16 pt_num_cpu_fbanks; + __u8 pt_rsvd[6]; /* MBZ */ + __u64 pt_cpu_fbanks[MSHV_NUM_CPU_FEATURES_BANKS]; + __u64 pt_rsvd1[2]; /* MBZ */ +#if defined(__x86_64__) + __u64 pt_disabled_xsave; +#else + __u64 pt_rsvd2; /* MBZ */ +#endif +} __packed; + /* /dev/mshv */ #define MSHV_CREATE_PARTITION _IOW(MSHV_IOCTL, 0x00, struct mshv_create_partition) -- cgit v1.2.3 From 491c5dc98b848c4781addd514caed95039e5366c Mon Sep 17 00:00:00 2001 From: Yael Chemla Date: Wed, 19 Nov 2025 22:48:15 +0200 Subject: net: ethtool: Add support for 1600Gbps speed Add support for 1600Gbps link modes based on 200Gbps per lane [1]. This includes the adopted IEEE 802.3dj copper and optical PMDs that use 200G/lane signaling [2]. Add the following PMD types: - KR8 (backplane) - CR8 (copper cable) - DR8 (SMF 500m) - DR8-2 (SMF 2km) These modes are defined in the 802.3dj specifications. References: [1] https://www.ieee802.org/3/dj/public/23_03/opsasnick_3dj_01a_2303.pdf [2] https://www.ieee802.org/3/dj/projdoc/objectives_P802d3dj_240314.pdf Signed-off-by: Yael Chemla Reviewed-by: Shahar Shitrit Signed-off-by: Tariq Toukan Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/1763585297-1243980-2-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8bd5ea5469d9..eb7ff2602fbb 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2077,6 +2077,10 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT = 118, ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT = 119, ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT = 120, + ETHTOOL_LINK_MODE_1600000baseCR8_Full_BIT = 121, + ETHTOOL_LINK_MODE_1600000baseKR8_Full_BIT = 122, + ETHTOOL_LINK_MODE_1600000baseDR8_Full_BIT = 123, + ETHTOOL_LINK_MODE_1600000baseDR8_2_Full_BIT = 124, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS @@ -2190,6 +2194,7 @@ enum ethtool_link_mode_bit_indices { #define SPEED_200000 200000 #define SPEED_400000 400000 #define SPEED_800000 800000 +#define SPEED_1600000 1600000 #define SPEED_UNKNOWN -1 -- cgit v1.2.3 From 2a367002ed321e884276c3d7232a362ddd1bf7d6 Mon Sep 17 00:00:00 2001 From: Daniel Zahka Date: Tue, 18 Nov 2025 18:50:33 -0800 Subject: devlink: support default values for param-get and param-set Support querying and resetting to default param values. Introduce two new devlink netlink attrs: DEVLINK_ATTR_PARAM_VALUE_DEFAULT and DEVLINK_ATTR_PARAM_RESET_DEFAULT. The former is used to contain an optional parameter value inside of the param_value nested attribute. The latter is used in param-set requests from userspace to indicate that the driver should reset the param to its default value. To implement this, two new functions are added to the devlink driver api: devlink_param::get_default() and devlink_param::reset_default(). These callbacks allow drivers to implement default param actions for runtime and permanent cmodes. For driverinit params, the core latches the last value set by a driver via devl_param_driverinit_value_set(), and uses that as the default value for a param. Because default parameter values are optional, it would be impossible to discern whether or not a param of type bool has default value of false or not provided if the default value is encoded using a netlink flag type. For this reason, when a DEVLINK_PARAM_TYPE_BOOL has an associated default value, the default value is encoded using a u8 type. Signed-off-by: Daniel Zahka Link: https://patch.msgid.link/20251119025038.651131-4-daniel.zahka@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 157f11d3fb72..e7d6b6d13470 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -639,6 +639,9 @@ enum devlink_attr { DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD, /* u64 */ + DEVLINK_ATTR_PARAM_VALUE_DEFAULT, /* dynamic */ + DEVLINK_ATTR_PARAM_RESET_DEFAULT, /* flag */ + /* Add new attributes above here, update the spec in * Documentation/netlink/specs/devlink.yaml and re-generate * net/devlink/netlink_gen.c. -- cgit v1.2.3 From 5d74781ebc86c5fa9e9d6934024c505412de9b52 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 20 Nov 2025 11:28:29 +0200 Subject: vfio/pci: Add dma-buf export support for MMIO regions Add support for exporting PCI device MMIO regions through dma-buf, enabling safe sharing of non-struct page memory with controlled lifetime management. This allows RDMA and other subsystems to import dma-buf FDs and build them into memory regions for PCI P2P operations. The implementation provides a revocable attachment mechanism using dma-buf move operations. MMIO regions are normally pinned as BARs don't change physical addresses, but access is revoked when the VFIO device is closed or a PCI reset is issued. This ensures kernel self-defense against potentially hostile userspace. Currently VFIO can take MMIO regions from the device's BAR and map them into a PFNMAP VMA with special PTEs. This mapping type ensures the memory cannot be used with things like pin_user_pages(), hmm, and so on. In practice only the user process CPU and KVM can safely make use of these VMA. When VFIO shuts down these VMAs are cleaned by unmap_mapping_range() to prevent any UAF of the MMIO beyond driver unbind. However, VFIO type 1 has an insecure behavior where it uses follow_pfnmap_*() to fish a MMIO PFN out of a VMA and program it back into the IOMMU. This has a long history of enabling P2P DMA inside VMs, but has serious lifetime problems by allowing a UAF of the MMIO after the VFIO driver has been unbound. Introduce DMABUF as a new safe way to export a FD based handle for the MMIO regions. This can be consumed by existing DMABUF importers like RDMA or DRM without opening an UAF. A following series will add an importer to iommufd to obsolete the type 1 code and allow safe UAF-free MMIO P2P in VM cases. DMABUF has a built in synchronous invalidation mechanism called move_notify. VFIO keeps track of all drivers importing its MMIO and can invoke a synchronous invalidation callback to tell the importing drivers to DMA unmap and forget about the MMIO pfns. This process is being called revoke. This synchronous invalidation fully prevents any lifecycle problems. VFIO will do this before unbinding its driver ensuring there is no UAF of the MMIO beyond the driver lifecycle. Further, VFIO has additional behavior to block access to the MMIO during things like Function Level Reset. This is because some poor platforms may experience a MCE type crash when touching MMIO of a PCI device that is undergoing a reset. Today this is done by using unmap_mapping_range() on the VMAs. Extend that into the DMABUF world and temporarily revoke the MMIO from the DMABUF importers during FLR as well. This will more robustly prevent an errant P2P from possibly upsetting the platform. A DMABUF FD is a preferred handle for MMIO compared to using something like a pgmap because: - VFIO is supported, including its P2P feature, on archs that don't support pgmap - PCI devices have all sorts of BAR sizes, including ones smaller than a section so a pgmap cannot always be created - It is undesirable to waste a lot of memory for struct pages, especially for a case like a GPU with ~100GB of BAR size - We want a synchronous revoke semantic to support FLR with light hardware requirements Use the P2P subsystem to help generate the DMA mapping. This is a significant upgrade over the abuse of dma_map_resource() that has historically been used by DMABUF exporters. Experience with an OOT version of this patch shows that real systems do need this. This approach deals with all the P2P scenarios: - Non-zero PCI bus_offset - ACS flags routing traffic to the IOMMU - ACS flags that bypass the IOMMU - though vfio noiommu is required to hit this. There will be further work to formalize the revoke semantic in DMABUF. For now this acts like a move_notify dynamic exporter where importer fault handling will get a failure when they attempt to map. This means that only fully restartable fault capable importers can import the VFIO DMABUFs. A future revoke semantic should open this up to more HW as the HW only needs to invalidate, not handle restartable faults. Signed-off-by: Jason Gunthorpe Signed-off-by: Vivek Kasireddy Reviewed-by: Kevin Tian Signed-off-by: Leon Romanovsky Acked-by: Ankit Agrawal Link: https://lore.kernel.org/r/20251120-dmabuf-vfio-v9-10-d7f71607f371@nvidia.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 75100bf009ba..ac2329f24141 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -14,6 +14,7 @@ #include #include +#include #define VFIO_API_VERSION 0 @@ -1478,6 +1479,33 @@ struct vfio_device_feature_bus_master { }; #define VFIO_DEVICE_FEATURE_BUS_MASTER 10 +/** + * Upon VFIO_DEVICE_FEATURE_GET create a dma_buf fd for the + * regions selected. + * + * open_flags are the typical flags passed to open(2), eg O_RDWR, O_CLOEXEC, + * etc. offset/length specify a slice of the region to create the dmabuf from. + * nr_ranges is the total number of (P2P DMA) ranges that comprise the dmabuf. + * + * flags should be 0. + * + * Return: The fd number on success, -1 and errno is set on failure. + */ +#define VFIO_DEVICE_FEATURE_DMA_BUF 11 + +struct vfio_region_dma_range { + __u64 offset; + __u64 length; +}; + +struct vfio_device_feature_dma_buf { + __u32 region_index; + __u32 open_flags; + __u32 flags; + __u32 nr_ranges; + struct vfio_region_dma_range dma_ranges[] __counted_by(nr_ranges); +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit v1.2.3 From 8e8678e740ecde2ae4a0404fd9b4ed2b726e236d Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 8 Jul 2025 12:57:57 +0000 Subject: KVM: s390: Add capability that forwards operation exceptions Setting KVM_CAP_S390_USER_OPEREXEC will forward all operation exceptions to user space. This also includes the 0x0000 instructions managed by KVM_CAP_S390_USER_INSTR0. It's helpful if user space wants to emulate instructions which do not (yet) have an opcode. While we're at it refine the documentation for KVM_CAP_S390_USER_INSTR0. Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Acked-by: Christian Borntraeger Signed-off-by: Janosch Frank --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 52f6000ab020..8ab07396ce3b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -963,6 +963,7 @@ struct kvm_enable_cap { #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 #define KVM_CAP_GUEST_MEMFD_FLAGS 244 +#define KVM_CAP_S390_USER_OPEREXEC 245 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From a67df6d1b939ca98e1ad403f53e3ee57299b8c44 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 11 Nov 2025 14:46:10 +0100 Subject: uapi: cdc.h: cleanly provide for more interfaces and countries The spec requires at least one interface respectively country. It allows multiple ones. This needs to be clearly said in the UAPI. This is subject to sanity checking in cdc_parse_cdc_header(), thus we can trust the length. Signed-off-by: Oliver Neukum Link: https://patch.msgid.link/20251111134641.4118827-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/cdc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index 1924cf665448..7bd5d12d8b26 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -104,8 +104,10 @@ struct usb_cdc_union_desc { __u8 bDescriptorSubType; __u8 bMasterInterface0; - __u8 bSlaveInterface0; - /* ... and there could be other slave interfaces */ + union { + __u8 bSlaveInterface0; + __DECLARE_FLEX_ARRAY(__u8, bSlaveInterfaces); + }; } __attribute__ ((packed)); /* "Country Selection Functional Descriptor" from CDC spec 5.2.3.9 */ @@ -115,8 +117,10 @@ struct usb_cdc_country_functional_desc { __u8 bDescriptorSubType; __u8 iCountryCodeRelDate; - __le16 wCountyCode0; - /* ... and there can be a lot of country codes */ + union { + __le16 wCountryCode0; + __DECLARE_FLEX_ARRAY(__le16, wCountryCodes); + }; } __attribute__ ((packed)); /* "Network Channel Terminal Functional Descriptor" from CDC spec 5.2.3.11 */ -- cgit v1.2.3 From cbbfba4847b8a5299d36e002bf864b21bb83295d Mon Sep 17 00:00:00 2001 From: James Clark Date: Tue, 11 Nov 2025 11:37:55 +0000 Subject: perf: Add perf_event_attr::config4 Arm FEAT_SPE_FDS adds the ability to filter on the data source of a packet using another 64-bits of event filtering control. As the existing perf_event_attr::configN fields are all used up for SPE PMU, an additional field is needed. Add a new 'config4' field. Reviewed-by: Leo Yan Tested-by: Leo Yan Reviewed-by: Ian Rogers Acked-by: Peter Zijlstra (Intel) Signed-off-by: James Clark Signed-off-by: Will Deacon --- include/uapi/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 78a362b80027..0d0ed85ad8cb 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -382,6 +382,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER6 120 /* Add: aux_sample_size */ #define PERF_ATTR_SIZE_VER7 128 /* Add: sig_data */ #define PERF_ATTR_SIZE_VER8 136 /* Add: config3 */ +#define PERF_ATTR_SIZE_VER9 144 /* add: config4 */ /* * 'struct perf_event_attr' contains various attributes that define @@ -543,6 +544,7 @@ struct perf_event_attr { __u64 sig_data; __u64 config3; /* extension of config2 */ + __u64 config4; /* extension of config3 */ }; /* -- cgit v1.2.3 From e6ab504633e4c06e35377ecf3c8cbc304de79858 Mon Sep 17 00:00:00 2001 From: Dave Penkler Date: Mon, 17 Nov 2025 15:40:21 +0100 Subject: staging: gpib: Destage gpib Move the gpib drivers out of staging and into the "real" part of the kernel. This entails: - Remove the gpib Kconfig menu and Makefile build rule from staging. - Remove gpib/uapi from the header file search path in subdir-ccflags of the gpib Makefile - move the gpib/uapi files to include/uapi/linux - Move the gpib tree out of staging to drivers. - Remove the word "Linux" from the gpib Kconfig file. - Add the gpib Kconfig menu and Makefile build rule to drivers Signed-off-by: Dave Penkler Link: https://patch.msgid.link/20251117144021.23569-5-dpenkler@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/gpib.h | 104 +++++++++++++++++++++++++ include/uapi/linux/gpib_ioctl.h | 167 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 271 insertions(+) create mode 100644 include/uapi/linux/gpib.h create mode 100644 include/uapi/linux/gpib_ioctl.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gpib.h b/include/uapi/linux/gpib.h new file mode 100644 index 000000000000..2a7f5eeb9777 --- /dev/null +++ b/include/uapi/linux/gpib.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +/*************************************************************************** + * copyright : (C) 2002 by Frank Mori Hess + ***************************************************************************/ + +#ifndef _GPIB_H +#define _GPIB_H + +#define GPIB_MAX_NUM_BOARDS 16 +#define GPIB_MAX_NUM_DESCRIPTORS 0x1000 + +enum ibsta_bit_numbers { + DCAS_NUM = 0, + DTAS_NUM = 1, + LACS_NUM = 2, + TACS_NUM = 3, + ATN_NUM = 4, + CIC_NUM = 5, + REM_NUM = 6, + LOK_NUM = 7, + CMPL_NUM = 8, + EVENT_NUM = 9, + SPOLL_NUM = 10, + RQS_NUM = 11, + SRQI_NUM = 12, + END_NUM = 13, + TIMO_NUM = 14, + ERR_NUM = 15 +}; + +/* IBSTA status bits (returned by all functions) */ +enum ibsta_bits { + DCAS = (1 << DCAS_NUM), /* device clear state */ + DTAS = (1 << DTAS_NUM), /* device trigger state */ + LACS = (1 << LACS_NUM), /* GPIB interface is addressed as Listener */ + TACS = (1 << TACS_NUM), /* GPIB interface is addressed as Talker */ + ATN = (1 << ATN_NUM), /* Attention is asserted */ + CIC = (1 << CIC_NUM), /* GPIB interface is Controller-in-Charge */ + REM = (1 << REM_NUM), /* remote state */ + LOK = (1 << LOK_NUM), /* lockout state */ + CMPL = (1 << CMPL_NUM), /* I/O is complete */ + EVENT = (1 << EVENT_NUM), /* DCAS, DTAS, or IFC has occurred */ + SPOLL = (1 << SPOLL_NUM), /* board serial polled by busmaster */ + RQS = (1 << RQS_NUM), /* Device requesting service */ + SRQI = (1 << SRQI_NUM), /* SRQ is asserted */ + END = (1 << END_NUM), /* EOI or EOS encountered */ + TIMO = (1 << TIMO_NUM), /* Time limit on I/O or wait function exceeded */ + ERR = (1 << ERR_NUM), /* Function call terminated on error */ + + device_status_mask = ERR | TIMO | END | CMPL | RQS, + board_status_mask = ERR | TIMO | END | CMPL | SPOLL | + EVENT | LOK | REM | CIC | ATN | TACS | LACS | DTAS | DCAS | SRQI, +}; + +/* End-of-string (EOS) modes for use with ibeos */ + +enum eos_flags { + EOS_MASK = 0x1c00, + REOS = 0x0400, /* Terminate reads on EOS */ + XEOS = 0x800, /* assert EOI when EOS char is sent */ + BIN = 0x1000 /* Do 8-bit compare on EOS */ +}; + +/* GPIB Bus Control Lines bit vector */ +enum bus_control_line { + VALID_DAV = 0x01, + VALID_NDAC = 0x02, + VALID_NRFD = 0x04, + VALID_IFC = 0x08, + VALID_REN = 0x10, + VALID_SRQ = 0x20, + VALID_ATN = 0x40, + VALID_EOI = 0x80, + VALID_ALL = 0xff, + BUS_DAV = 0x0100, /* DAV line status bit */ + BUS_NDAC = 0x0200, /* NDAC line status bit */ + BUS_NRFD = 0x0400, /* NRFD line status bit */ + BUS_IFC = 0x0800, /* IFC line status bit */ + BUS_REN = 0x1000, /* REN line status bit */ + BUS_SRQ = 0x2000, /* SRQ line status bit */ + BUS_ATN = 0x4000, /* ATN line status bit */ + BUS_EOI = 0x8000 /* EOI line status bit */ +}; + +enum ppe_bits { + PPC_DISABLE = 0x10, + PPC_SENSE = 0x8, /* parallel poll sense bit */ + PPC_DIO_MASK = 0x7 +}; + +enum { + request_service_bit = 0x40, +}; + +enum gpib_events { + EVENT_NONE = 0, + EVENT_DEV_TRG = 1, + EVENT_DEV_CLR = 2, + EVENT_IFC = 3 +}; + +#endif /* _GPIB_H */ + diff --git a/include/uapi/linux/gpib_ioctl.h b/include/uapi/linux/gpib_ioctl.h new file mode 100644 index 000000000000..d544d8e4362c --- /dev/null +++ b/include/uapi/linux/gpib_ioctl.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +/*************************************************************************** + * copyright : (C) 2002 by Frank Mori Hess + ***************************************************************************/ + +#ifndef _GPIB_IOCTL_H +#define _GPIB_IOCTL_H + +#include +#include + +#define GPIB_CODE 160 + +struct gpib_board_type_ioctl { + char name[100]; +}; + +/* argument for read/write/command ioctls */ +struct gpib_read_write_ioctl { + __u64 buffer_ptr; + __u32 requested_transfer_count; + __u32 completed_transfer_count; + __s32 end; /* end flag return for reads, end io suppression request for cmd*/ + __s32 handle; +}; + +struct gpib_open_dev_ioctl { + __u32 handle; + __u32 pad; + __s32 sad; + __u32 is_board; +}; + +struct gpib_close_dev_ioctl { + __u32 handle; +}; + +struct gpib_serial_poll_ioctl { + __u32 pad; + __s32 sad; + __u8 status_byte; + __u8 padding[3]; /* align to 32 bit boundary */ +}; + +struct gpib_eos_ioctl { + __s32 eos; + __s32 eos_flags; +}; + +struct gpib_wait_ioctl { + __s32 handle; + __s32 wait_mask; + __s32 clear_mask; + __s32 set_mask; + __s32 ibsta; + __s32 pad; + __s32 sad; + __u32 usec_timeout; +}; + +struct gpib_online_ioctl { + __u64 init_data_ptr; + __s32 init_data_length; + __s32 online; +}; + +struct gpib_spoll_bytes_ioctl { + __u32 num_bytes; + __u32 pad; + __s32 sad; +}; + +struct gpib_board_info_ioctl { + __u32 pad; + __s32 sad; + __s32 parallel_poll_configuration; + __s32 autopolling; + __s32 is_system_controller; + __u32 t1_delay; + unsigned ist : 1; + unsigned no_7_bit_eos : 1; + unsigned padding :30; /* align to 32 bit boundary */ +}; + +struct gpib_select_pci_ioctl { + __s32 pci_bus; + __s32 pci_slot; +}; + +struct gpib_ppoll_config_ioctl { + __u8 config; + unsigned set_ist : 1; + unsigned clear_ist : 1; + unsigned padding :22; /* align to 32 bit boundary */ +}; + +struct gpib_pad_ioctl { + __u32 handle; + __u32 pad; +}; + +struct gpib_sad_ioctl { + __u32 handle; + __s32 sad; +}; + +/* select a piece of hardware to attach by its sysfs device path */ +struct gpib_select_device_path_ioctl { + char device_path[0x1000]; +}; + +/* update status byte and request service */ +struct gpib_request_service2 { + __u8 status_byte; + __u8 padding[3]; /* align to 32 bit boundary */ + __s32 new_reason_for_service; +}; + +/* Standard functions. */ +enum gpib_ioctl { + IBRD = _IOWR(GPIB_CODE, 100, struct gpib_read_write_ioctl), + IBWRT = _IOWR(GPIB_CODE, 101, struct gpib_read_write_ioctl), + IBCMD = _IOWR(GPIB_CODE, 102, struct gpib_read_write_ioctl), + IBOPENDEV = _IOWR(GPIB_CODE, 3, struct gpib_open_dev_ioctl), + IBCLOSEDEV = _IOW(GPIB_CODE, 4, struct gpib_close_dev_ioctl), + IBWAIT = _IOWR(GPIB_CODE, 5, struct gpib_wait_ioctl), + IBRPP = _IOWR(GPIB_CODE, 6, __u8), + + IBSIC = _IOW(GPIB_CODE, 9, __u32), + IBSRE = _IOW(GPIB_CODE, 10, __s32), + IBGTS = _IO(GPIB_CODE, 11), + IBCAC = _IOW(GPIB_CODE, 12, __s32), + IBLINES = _IOR(GPIB_CODE, 14, __s16), + IBPAD = _IOW(GPIB_CODE, 15, struct gpib_pad_ioctl), + IBSAD = _IOW(GPIB_CODE, 16, struct gpib_sad_ioctl), + IBTMO = _IOW(GPIB_CODE, 17, __u32), + IBRSP = _IOWR(GPIB_CODE, 18, struct gpib_serial_poll_ioctl), + IBEOS = _IOW(GPIB_CODE, 19, struct gpib_eos_ioctl), + IBRSV = _IOW(GPIB_CODE, 20, __u8), + CFCBASE = _IOW(GPIB_CODE, 21, __u64), + CFCIRQ = _IOW(GPIB_CODE, 22, __u32), + CFCDMA = _IOW(GPIB_CODE, 23, __u32), + CFCBOARDTYPE = _IOW(GPIB_CODE, 24, struct gpib_board_type_ioctl), + + IBMUTEX = _IOW(GPIB_CODE, 26, __s32), + IBSPOLL_BYTES = _IOWR(GPIB_CODE, 27, struct gpib_spoll_bytes_ioctl), + IBPPC = _IOW(GPIB_CODE, 28, struct gpib_ppoll_config_ioctl), + IBBOARD_INFO = _IOR(GPIB_CODE, 29, struct gpib_board_info_ioctl), + + IBQUERY_BOARD_RSV = _IOR(GPIB_CODE, 31, __s32), + IBSELECT_PCI = _IOWR(GPIB_CODE, 32, struct gpib_select_pci_ioctl), + IBEVENT = _IOR(GPIB_CODE, 33, __s16), + IBRSC = _IOW(GPIB_CODE, 34, __s32), + IB_T1_DELAY = _IOW(GPIB_CODE, 35, __u32), + IBLOC = _IO(GPIB_CODE, 36), + + IBAUTOSPOLL = _IOW(GPIB_CODE, 38, __s16), + IBONL = _IOW(GPIB_CODE, 39, struct gpib_online_ioctl), + IBPP2_SET = _IOW(GPIB_CODE, 40, __s16), + IBPP2_GET = _IOR(GPIB_CODE, 41, __s16), + IBSELECT_DEVICE_PATH = _IOW(GPIB_CODE, 43, struct gpib_select_device_path_ioctl), + /* 44 was IBSELECT_SERIAL_NUMBER */ + IBRSV2 = _IOW(GPIB_CODE, 45, struct gpib_request_service2) +}; + +#endif /* _GPIB_IOCTL_H */ -- cgit v1.2.3 From 6b1ac78dd0f29fe66421c460c12ec15e45af38c3 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 13 Oct 2025 10:22:04 +1030 Subject: btrfs: implement shutdown ioctl The shutdown ioctl should follow the XFS one, which use magic number 'X', and ioctl number 125, with a uint32 as flags. For now btrfs don't distinguish DEFAULT and LOGFLUSH flags (just like f2fs), both will freeze the fs first (implies committing the current transaction), setting the SHUTDOWN flag and finally thaw the fs. For NOLOGFLUSH flag, the freeze/thaw part is skipped thus the current transaction is aborted. The new shutdown ioctl is hidden behind experimental features for more testing. Reviewed-by: Johannes Thumshirn Reviewed-by: Anand Jain Tested-by: Anand Jain Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 8e710bbb688e..e8fd92789423 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -1099,6 +1099,12 @@ enum btrfs_err_code { BTRFS_ERROR_DEV_RAID1C4_MIN_NOT_MET, }; +/* Flags for IOC_SHUTDOWN, must match XFS_FSOP_GOING_FLAGS_* flags. */ +#define BTRFS_SHUTDOWN_FLAGS_DEFAULT 0x0 +#define BTRFS_SHUTDOWN_FLAGS_LOGFLUSH 0x1 +#define BTRFS_SHUTDOWN_FLAGS_NOLOGFLUSH 0x2 +#define BTRFS_SHUTDOWN_FLAGS_LAST 0x3 + #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \ struct btrfs_ioctl_vol_args) #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \ @@ -1220,6 +1226,9 @@ enum btrfs_err_code { #define BTRFS_IOC_SUBVOL_SYNC_WAIT _IOW(BTRFS_IOCTL_MAGIC, 65, \ struct btrfs_ioctl_subvol_wait) +/* Shutdown ioctl should follow XFS's interfaces, thus not using btrfs magic. */ +#define BTRFS_IOC_SHUTDOWN _IOR('X', 125, __u32) + #ifdef __cplusplus } #endif -- cgit v1.2.3 From 1c6a92a5a5de7ebf94526dee7068926e6d5b1b01 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 24 Nov 2025 18:28:34 -0800 Subject: wifi: nl80211: vendor-cmd: intel: fix a blank kernel-doc line warning Delete an empty line prevent a kernel-doc warning: Warning: ../include/uapi/linux/nl80211-vnd-intel.h:86 bad line: Fixes: 3d2a2544eae9 ("nl80211: vendor-cmd: add Intel vendor commands for iwlmei usage") Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20251125022834.3171742-1-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211-vnd-intel.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211-vnd-intel.h b/include/uapi/linux/nl80211-vnd-intel.h index 4ed7d0b24512..79ccc9401d50 100644 --- a/include/uapi/linux/nl80211-vnd-intel.h +++ b/include/uapi/linux/nl80211-vnd-intel.h @@ -84,7 +84,6 @@ enum iwl_vendor_auth_akm_mode { * * @NUM_IWL_MVM_VENDOR_ATTR: number of vendor attributes * @MAX_IWL_MVM_VENDOR_ATTR: highest vendor attribute number - */ enum iwl_mvm_vendor_attr { __IWL_MVM_VENDOR_ATTR_INVALID = 0x00, -- cgit v1.2.3 From 68e83f3472667aac18d577587102f4bf77d0bd06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= Date: Thu, 20 Nov 2025 17:44:27 +0000 Subject: tools: ynl-gen: add regeneration comment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a comment on regeneration to the generated files. The comment is placed after the YNL-GEN line[1], as to not interfere with ynl-regen.sh's detection logic. [1] and after the optional YNL-ARG line. Link: https://lore.kernel.org/r/aR5m174O7pklKrMR@zx2c4.com/ Suggested-by: Jason A. Donenfeld Signed-off-by: Asbjørn Sloth Tønnesen Acked-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251120174429.390574-3-ast@fiberby.net Signed-off-by: Jakub Kicinski --- include/uapi/linux/android/binder_netlink.h | 1 + include/uapi/linux/dpll.h | 1 + include/uapi/linux/ethtool_netlink_generated.h | 1 + include/uapi/linux/fou.h | 1 + include/uapi/linux/handshake.h | 1 + include/uapi/linux/if_team.h | 1 + include/uapi/linux/lockd_netlink.h | 1 + include/uapi/linux/mptcp_pm.h | 1 + include/uapi/linux/net_shaper.h | 1 + include/uapi/linux/netdev.h | 1 + include/uapi/linux/nfsd_netlink.h | 1 + include/uapi/linux/ovpn.h | 1 + include/uapi/linux/psp.h | 1 + 13 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/android/binder_netlink.h b/include/uapi/linux/android/binder_netlink.h index b218f96d6668..bf69833c9a19 100644 --- a/include/uapi/linux/android/binder_netlink.h +++ b/include/uapi/linux/android/binder_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/binder.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_ANDROID_BINDER_NETLINK_H #define _UAPI_LINUX_ANDROID_BINDER_NETLINK_H diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 69d35570ac4f..b7ff9c44f9aa 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/dpll.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_DPLL_H #define _UAPI_LINUX_DPLL_H diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index b71b175df46d..556a0c834df5 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/ethtool.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H #define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index b5cd3e7b3775..bb6bef74d2d1 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_FOU_H #define _UAPI_LINUX_FOU_H diff --git a/include/uapi/linux/handshake.h b/include/uapi/linux/handshake.h index 662e7de46c54..d7e40f594888 100644 --- a/include/uapi/linux/handshake.h +++ b/include/uapi/linux/handshake.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/handshake.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_HANDSHAKE_H #define _UAPI_LINUX_HANDSHAKE_H diff --git a/include/uapi/linux/if_team.h b/include/uapi/linux/if_team.h index a5c06243a435..f4cd839ae725 100644 --- a/include/uapi/linux/if_team.h +++ b/include/uapi/linux/if_team.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/team.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_IF_TEAM_H #define _UAPI_LINUX_IF_TEAM_H diff --git a/include/uapi/linux/lockd_netlink.h b/include/uapi/linux/lockd_netlink.h index 21c65aec3bc6..2d766a0fa6ea 100644 --- a/include/uapi/linux/lockd_netlink.h +++ b/include/uapi/linux/lockd_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/lockd.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_LOCKD_NETLINK_H #define _UAPI_LINUX_LOCKD_NETLINK_H diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index bf44a5cf5b5a..c97d060ee90b 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_MPTCP_PM_H #define _UAPI_LINUX_MPTCP_PM_H diff --git a/include/uapi/linux/net_shaper.h b/include/uapi/linux/net_shaper.h index d8834b59f7d7..3dd22c2930d9 100644 --- a/include/uapi/linux/net_shaper.h +++ b/include/uapi/linux/net_shaper.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/net_shaper.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NET_SHAPER_H #define _UAPI_LINUX_NET_SHAPER_H diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 048c8de1a130..e0b579a1df4f 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NETDEV_H #define _UAPI_LINUX_NETDEV_H diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 887cbd12b695..e157e2009ea8 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/nfsd.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NFSD_NETLINK_H #define _UAPI_LINUX_NFSD_NETLINK_H diff --git a/include/uapi/linux/ovpn.h b/include/uapi/linux/ovpn.h index 680d1522dc87..959b41def61f 100644 --- a/include/uapi/linux/ovpn.h +++ b/include/uapi/linux/ovpn.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/ovpn.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_OVPN_H #define _UAPI_LINUX_OVPN_H diff --git a/include/uapi/linux/psp.h b/include/uapi/linux/psp.h index d8449c043ba1..a3a336488dc3 100644 --- a/include/uapi/linux/psp.h +++ b/include/uapi/linux/psp.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/psp.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_PSP_H #define _UAPI_LINUX_PSP_H -- cgit v1.2.3 From 60f511f443e552ef5b5cd79ec2b881f4323e19c9 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 26 Nov 2025 11:16:05 +0100 Subject: can: netlink: add CAN_CTRLMODE_RESTRICTED ISO 11898-1:2024 adds a new restricted operation mode. This mode is added as a mandatory feature for nodes which support CAN XL and is retrofitted as optional for legacy nodes (i.e. the ones which only support Classical CAN and CAN FD). The restricted operation mode is nearly the same as the listen only mode: the node can not send data frames or remote frames and can not send dominant bits if an error occurs. The only exception is that the node shall still send the acknowledgment bit. A second niche exception is that the node may still send a data frame containing a time reference message if the node is a primary time provider, but because the time provider feature is not yet implemented in the kernel, this second exception is not relevant to us at the moment. Add the CAN_CTRLMODE_RESTRICTED control mode flag and update the can_dev_dropped_skb() helper function accordingly. Finally, bail out if both CAN_CTRLMODE_LISTENONLY and CAN_CTRLMODE_RESTRICTED are provided. Signed-off-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20251126-canxl-v8-4-e7e3eb74f889@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index ef62f56eaaef..fafd1cce4798 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -103,6 +103,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */ #define CAN_CTRLMODE_TDC_AUTO 0x200 /* FD transceiver automatically calculates TDCV */ #define CAN_CTRLMODE_TDC_MANUAL 0x400 /* FD TDCV is manually set up by user */ +#define CAN_CTRLMODE_RESTRICTED 0x800 /* Restricted operation mode */ /* * CAN device statistics -- cgit v1.2.3 From e63281614747c73f25b708c75bc696c4e76f5588 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 26 Nov 2025 11:16:06 +0100 Subject: can: netlink: add initial CAN XL support CAN XL uses bittiming parameters different from Classical CAN and CAN FD. Thus, all the data bittiming parameters, including TDC, need to be duplicated for CAN XL. Add the CAN XL netlink interface for all the features which are common with CAN FD. Any new CAN XL specific features are added later on. The first time CAN XL is activated, the MTU is set by default to CANXL_MAX_MTU. The user may then configure a custom MTU within the CANXL_MIN_MTU to CANXL_MAX_MTU range, in which case, the custom MTU value will be kept as long as CAN XL remains active. Signed-off-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20251126-canxl-v8-5-e7e3eb74f889@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index fafd1cce4798..c2c96c5978a8 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -104,6 +104,9 @@ struct can_ctrlmode { #define CAN_CTRLMODE_TDC_AUTO 0x200 /* FD transceiver automatically calculates TDCV */ #define CAN_CTRLMODE_TDC_MANUAL 0x400 /* FD TDCV is manually set up by user */ #define CAN_CTRLMODE_RESTRICTED 0x800 /* Restricted operation mode */ +#define CAN_CTRLMODE_XL 0x1000 /* CAN XL mode */ +#define CAN_CTRLMODE_XL_TDC_AUTO 0x2000 /* XL transceiver automatically calculates TDCV */ +#define CAN_CTRLMODE_XL_TDC_MANUAL 0x4000 /* XL TDCV is manually set up by user */ /* * CAN device statistics @@ -139,6 +142,10 @@ enum { IFLA_CAN_BITRATE_MAX, IFLA_CAN_TDC, /* FD */ IFLA_CAN_CTRLMODE_EXT, + IFLA_CAN_XL_DATA_BITTIMING, + IFLA_CAN_XL_DATA_BITTIMING_CONST, + IFLA_CAN_XL_DATA_BITRATE_CONST, + IFLA_CAN_XL_TDC, /* add new constants above here */ __IFLA_CAN_MAX, -- cgit v1.2.3 From 233134af208689c2d5d40896f5740473a74e3cb2 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 26 Nov 2025 11:16:07 +0100 Subject: can: netlink: add CAN_CTRLMODE_XL_TMS flag The Transceiver Mode Switching (TMS) indicates whether the CAN XL controller shall use the PWM or NRZ encoding during the data phase. The term "transceiver mode switching" is used in both ISO 11898-1 and CiA 612-2 (although only the latter one uses the abbreviation TMS). We adopt the same naming convention here for consistency. Add the CAN_CTRLMODE_XL_TMS flag to the list of the CAN control modes. Add can_validate_xl_flags() to check the coherency of the TMS flag. That function will be reused in upcoming changes to validate the other CAN XL flags. Signed-off-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20251126-canxl-v8-6-e7e3eb74f889@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index c2c96c5978a8..ebafb091d80f 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -107,6 +107,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_XL 0x1000 /* CAN XL mode */ #define CAN_CTRLMODE_XL_TDC_AUTO 0x2000 /* XL transceiver automatically calculates TDCV */ #define CAN_CTRLMODE_XL_TDC_MANUAL 0x4000 /* XL TDCV is manually set up by user */ +#define CAN_CTRLMODE_XL_TMS 0x8000 /* Transceiver Mode Switching */ /* * CAN device statistics -- cgit v1.2.3 From 46552323fa6779beb1ea558254dfd56021174c93 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 26 Nov 2025 11:16:12 +0100 Subject: can: netlink: add PWM netlink interface When the TMS is switched on, the node uses PWM (Pulse Width Modulation) during the data phase instead of the classic NRZ (Non Return to Zero) encoding. PWM is configured by three parameters: - PWMS: Pulse Width Modulation Short phase - PWML: Pulse Width Modulation Long phase - PWMO: Pulse Width Modulation Offset time For each of these parameters, define three IFLA symbols: - IFLA_CAN_PWM_PWM*_MIN: the minimum allowed value. - IFLA_CAN_PWM_PWM*_MAX: the maximum allowed value. - IFLA_CAN_PWM_PWM*: the runtime value. This results in a total of nine IFLA symbols which are all nested in a parent IFLA_CAN_XL_PWM symbol. IFLA_CAN_PWM_PWM*_MIN and IFLA_CAN_PWM_PWM*_MAX define the range of allowed values and will match the value statically configured by the device in struct can_pwm_const. IFLA_CAN_PWM_PWM* match the runtime values stored in struct can_pwm. Those parameters may only be configured when the tms mode is on. If the PWMS, PWML and PWMO parameters are provided, check that all the needed parameters are present using can_validate_pwm(), then check their value using can_validate_pwm_bittiming(). PWMO defaults to zero if omitted. Otherwise, if CAN_CTRLMODE_XL_TMS is true but none of the PWM parameters are provided, calculate them using can_calc_pwm(). Signed-off-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp Link: https://patch.msgid.link/20251126-canxl-v8-11-e7e3eb74f889@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index ebafb091d80f..c30d16746159 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -5,6 +5,7 @@ * Definitions for the CAN netlink interface * * Copyright (c) 2009 Wolfgang Grandegger + * Copyright (c) 2021-2025 Vincent Mailhol * * This program is free software; you can redistribute it and/or modify * it under the terms of the version 2 of the GNU General Public License @@ -147,6 +148,7 @@ enum { IFLA_CAN_XL_DATA_BITTIMING_CONST, IFLA_CAN_XL_DATA_BITRATE_CONST, IFLA_CAN_XL_TDC, + IFLA_CAN_XL_PWM, /* add new constants above here */ __IFLA_CAN_MAX, @@ -188,6 +190,29 @@ enum { IFLA_CAN_CTRLMODE_MAX = __IFLA_CAN_CTRLMODE - 1 }; +/* + * CAN FD/XL Pulse-Width Modulation (PWM) + * + * Please refer to struct can_pwm_const and can_pwm in + * include/linux/can/bittiming.h for further details. + */ +enum { + IFLA_CAN_PWM_UNSPEC, + IFLA_CAN_PWM_PWMS_MIN, /* u32 */ + IFLA_CAN_PWM_PWMS_MAX, /* u32 */ + IFLA_CAN_PWM_PWML_MIN, /* u32 */ + IFLA_CAN_PWM_PWML_MAX, /* u32 */ + IFLA_CAN_PWM_PWMO_MIN, /* u32 */ + IFLA_CAN_PWM_PWMO_MAX, /* u32 */ + IFLA_CAN_PWM_PWMS, /* u32 */ + IFLA_CAN_PWM_PWML, /* u32 */ + IFLA_CAN_PWM_PWMO, /* u32 */ + + /* add new constants above here */ + __IFLA_CAN_PWM, + IFLA_CAN_PWM_MAX = __IFLA_CAN_PWM - 1 +}; + /* u16 termination range: 1..65535 Ohms */ #define CAN_TERMINATION_DISABLED 0 -- cgit v1.2.3 From f0fdaa4ad55b7c6e46a5ccb9102bc9a96cad360f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 27 Oct 2025 21:04:09 -0700 Subject: virt: acrn: split acrn_mmio_dev_res out of acrn_mmiodev Add struct acrn_mmio_dev_res before struct acrn_mmio_dev. The former is used in the latter and breaking them up provides better kernel-doc documentation for the struct members. Suggested-by: Fei Li Signed-off-by: Randy Dunlap Acked-by: Fei Li Link: https://patch.msgid.link/20251028040409.868254-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/acrn.h | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 7b714c1902eb..79e7855a8c42 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -418,26 +418,32 @@ struct acrn_pcidev { }; /** - * struct acrn_mmiodev - Info for assigning or de-assigning a MMIO device - * @name: Name of the MMIO device. - * @res[].user_vm_pa: Physical address of User VM of the MMIO region - * for the MMIO device. - * @res[].service_vm_pa: Physical address of Service VM of the MMIO - * region for the MMIO device. - * @res[].size: Size of the MMIO region for the MMIO device. - * @res[].mem_type: Memory type of the MMIO region for the MMIO - * device. + * struct acrn_mmio_dev_res - MMIO device resource description + * @user_vm_pa: Physical address of User VM of the MMIO region + * for the MMIO device. + * @service_vm_pa: Physical address of Service VM of the MMIO + * region for the MMIO device. + * @size: Size of the MMIO region for the MMIO device. + * @mem_type: Memory type of the MMIO region for the MMIO + * device. + */ +struct acrn_mmio_dev_res { + __u64 user_vm_pa; + __u64 service_vm_pa; + __u64 size; + __u64 mem_type; +}; + +/** + * struct acrn_mmiodev - Info for assigning or de-assigning an MMIO device + * @name: Name of the MMIO device. + * @res: Array of MMIO device descriptions * * This structure will be passed to hypervisor directly. */ struct acrn_mmiodev { __u8 name[8]; - struct { - __u64 user_vm_pa; - __u64 service_vm_pa; - __u64 size; - __u64 mem_type; - } res[ACRN_MMIODEV_RES_NUM]; + struct acrn_mmio_dev_res res[ACRN_MMIODEV_RES_NUM]; }; /** -- cgit v1.2.3 From 81c45c62dc3eefd83af8eb8df10e45705e8e3a47 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Mon, 3 Nov 2025 09:27:55 -0800 Subject: iommu/arm-smmu-v3-iommufd: Allow attaching nested domain for GBPA cases A vDEVICE has been a hard requirement for attaching a nested domain to the device. This makes sense when installing a guest STE, since a vSID must be present and given to the kernel during the vDEVICE allocation. But, when CR0.SMMUEN is disabled, VM doesn't really need a vSID to program the vSMMU behavior as GBPA will take effect, in which case the vSTE in the nested domain could have carried the bypass or abort configuration in GBPA register. Thus, having such a hard requirement doesn't work well for GBPA. Skip vmaster allocation in arm_smmu_attach_prepare_vmaster() for an abort or bypass vSTE. Note that device on this attachment won't report vevents. Update the uAPI doc accordingly. Link: https://patch.msgid.link/r/20251103172755.2026145-1-nicolinc@nvidia.com Tested-by: Shameer Kolothum Signed-off-by: Nicolin Chen Reviewed-by: Jason Gunthorpe Reviewed-by: Pranjal Shrivastava Tested-by: Shuai Xue Signed-off-by: Jason Gunthorpe --- include/uapi/linux/iommufd.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index c218c89e0e2e..2c41920b641d 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -450,6 +450,16 @@ struct iommu_hwpt_vtd_s1 { * nested domain will translate the same as the nesting parent. The S1 will * install a Context Descriptor Table pointing at userspace memory translated * by the nesting parent. + * + * It's suggested to allocate a vDEVICE object carrying vSID and then re-attach + * the nested domain, as soon as the vSID is available in the VMM level: + * + * - when Cfg=translate, a vDEVICE must be allocated prior to attaching to the + * allocated nested domain, as CD/ATS invalidations and vevents need a vSID. + * - when Cfg=bypass/abort, a vDEVICE is not enforced during the nested domain + * attachment, to support a GBPA case where VM sets CR0.SMMUEN=0. However, if + * VM sets CR0.SMMUEN=1 while missing a vDEVICE object, kernel would fail to + * report events to the VM. E.g. F_TRANSLATION when guest STE.Cfg=abort. */ struct iommu_hwpt_arm_smmuv3 { __aligned_le64 ste[2]; -- cgit v1.2.3 From 5d24321e4c159088604512d7a5c5cf634d23e01a Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Tue, 25 Nov 2025 16:18:01 -0500 Subject: io_uring: Introduce getsockname io_uring cmd Introduce a socket-specific io_uring_cmd to support getsockname/getpeername via io_uring. I made this an io_uring_cmd instead of a new operation to avoid polluting the command namespace with what is exclusively a socket operation. In addition, since we don't need to conform to existing interfaces, this merges the getsockname/getpeername in a single operation, since the implementation is pretty much the same. This has been frequently requested, for instance at [1] and more recently in the project Discord channel. The main use-case is to support fixed socket file descriptors. [1] https://github.com/axboe/liburing/issues/1356 Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index deb772222b6d..b5b23c0d5283 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1009,6 +1009,7 @@ enum io_uring_socket_op { SOCKET_URING_OP_GETSOCKOPT, SOCKET_URING_OP_SETSOCKOPT, SOCKET_URING_OP_TX_TIMESTAMP, + SOCKET_URING_OP_GETSOCKNAME, }; /* -- cgit v1.2.3 From e6c43c95009035a63091cd49736886f883127510 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 21 Nov 2025 08:39:55 -0800 Subject: net: phy: Add MDIO_PMA_CTRL1_SPEED for 2.5G and 5G to reflect PMA values The 2.5G and 5G values are not consistent between the PCS CTRL1 and PMA CTRL1 values. In order to avoid confusion between the two I am updating the values to include "PMA" in the name similar to values used in similar places. To avoid breaking UAPI I have retained the original macros and just defined them as the new PMA based defines. Signed-off-by: Alexander Duyck Link: https://patch.msgid.link/176374319569.959489.6610469879021800710.stgit@ahduyck-xeon-server.home.arpa Signed-off-by: Paolo Abeni --- include/uapi/linux/mdio.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 6975f182b22c..9ee6eeae64b8 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -116,10 +116,18 @@ #define MDIO_CTRL1_SPEED10G (MDIO_CTRL1_SPEEDSELEXT | 0x00) /* 10PASS-TS/2BASE-TL */ #define MDIO_CTRL1_SPEED10P2B (MDIO_CTRL1_SPEEDSELEXT | 0x04) +/* Note: the MDIO_CTRL1_SPEED_XXX values for everything past 10PASS-TS/2BASE-TL + * do not match between the PCS and PMA values. Any additions past this point + * should be PMA or PCS specific. The following 2 defines are workarounds for + * values added before this was caught. They should be considered deprecated. + */ +#define MDIO_CTRL1_SPEED2_5G MDIO_PMA_CTRL1_SPEED2_5G +#define MDIO_CTRL1_SPEED5G MDIO_PMA_CTRL1_SPEED5G /* 2.5 Gb/s */ -#define MDIO_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) +#define MDIO_PMA_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 5 Gb/s */ -#define MDIO_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) +#define MDIO_PMA_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) + /* Status register 1. */ #define MDIO_STAT1_LPOWERABLE 0x0002 /* Low-power ability */ -- cgit v1.2.3 From 7622d55276932bfeb947b7b6cbf7ea0aa41feeb8 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 21 Nov 2025 08:40:02 -0800 Subject: net: pcs: xpcs: Add support for 25G, 50G, and 100G interfaces With this change we are adding support for 25G, 50G, and 100G interface types to the XPCS driver. This had supposedly been enabled with the addition of XLGMII but I don't see any capability for configuration there so I suspect it may need to be refactored in the future. With this change we can enable the XPCS driver with the selected interface and it should be able to detect link, speed, and report the link status to the phylink interface. Signed-off-by: Alexander Duyck Link: https://patch.msgid.link/176374320248.959489.11649590675011158859.stgit@ahduyck-xeon-server.home.arpa Signed-off-by: Paolo Abeni --- include/uapi/linux/mdio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 9ee6eeae64b8..f23cab33e586 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -123,6 +123,12 @@ */ #define MDIO_CTRL1_SPEED2_5G MDIO_PMA_CTRL1_SPEED2_5G #define MDIO_CTRL1_SPEED5G MDIO_PMA_CTRL1_SPEED5G +/* 100 Gb/s */ +#define MDIO_PCS_CTRL1_SPEED100G (MDIO_CTRL1_SPEEDSELEXT | 0x10) +/* 25 Gb/s */ +#define MDIO_PCS_CTRL1_SPEED25G (MDIO_CTRL1_SPEEDSELEXT | 0x14) +/* 50 Gb/s */ +#define MDIO_PCS_CTRL1_SPEED50G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 2.5 Gb/s */ #define MDIO_PMA_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 5 Gb/s */ -- cgit v1.2.3 From 39e138173ae7641e952b456d2de7ad2ac03e8d88 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 21 Nov 2025 08:40:09 -0800 Subject: net: pcs: xpcs: Fix PMA identifier handling in XPCS The XPCS driver was mangling the PMA identifier as the original code appears to have been focused on just capturing the OUI. Rather than store a mangled ID it is better to work with the actual PMA ID and instead just mask out the values that don't apply rather than shifting them and reordering them as you still don't get the original OUI for the NIC without having to bitswap the values as per the definition of the layout in IEEE 802.3-2022 22.2.4.3.1. By laying it out as it was in the hardware it is also less likely for us to have an unintentional collision as the enum values will occupy the revision number area while the OUI occupies the upper 22 bits. Signed-off-by: Alexander Duyck Link: https://patch.msgid.link/176374320920.959489.17267159479370601070.stgit@ahduyck-xeon-server.home.arpa Signed-off-by: Paolo Abeni --- include/uapi/linux/mdio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index f23cab33e586..8d769f100de6 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -147,6 +147,11 @@ #define MDIO_AN_STAT1_PAGE 0x0040 /* Page received */ #define MDIO_AN_STAT1_XNP 0x0080 /* Extended next page status */ +/* Device Identifier 2 */ +#define MDIO_DEVID2_OUI 0xfc00 /* OUI Portion of PHY ID */ +#define MDIO_DEVID2_MODEL_NUM 0x03f0 /* Manufacturer's Model Number */ +#define MDIO_DEVID2_REV_NUM 0x000f /* Revision Number */ + /* Speed register. */ #define MDIO_SPEED_10G 0x0001 /* 10G capable */ #define MDIO_PMA_SPEED_2B 0x0002 /* 2BASE-TL capable */ -- cgit v1.2.3 From 9e2fd062fa1713a33380cc97ef324d086dd45ba5 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Tue, 25 Nov 2025 11:58:31 -0500 Subject: liveupdate: luo_core: Live Update Orchestrator MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Live Update Orchestrator", v8. This series introduces the Live Update Orchestrator, a kernel subsystem designed to facilitate live kernel updates using a kexec-based reboot. This capability is critical for cloud environments, allowing hypervisors to be updated with minimal downtime for running virtual machines. LUO achieves this by preserving the state of selected resources, such as memory, devices and their dependencies, across the kernel transition. As a key feature, this series includes support for preserving memfd file descriptors, which allows critical in-memory data, such as guest RAM or any other large memory region, to be maintained in RAM across the kexec reboot. The other series that use LUO, are VFIO [1], IOMMU [2], and PCI [3] preservations. Github repo of this series [4]. The core of LUO is a framework for managing the lifecycle of preserved resources through a userspace-driven interface. Key features include: - Session Management Userspace agent (i.e. luod [5]) creates named sessions, each represented by a file descriptor (via centralized agent that controls /dev/liveupdate). The lifecycle of all preserved resources within a session is tied to this FD, ensuring automatic kernel cleanup if the controlling userspace agent crashes or exits unexpectedly. - File Preservation A handler-based framework allows specific file types (demonstrated here with memfd) to be preserved. Handlers manage the serialization, restoration, and lifecycle of their specific file types. - File-Lifecycle-Bound State A new mechanism for managing shared global state whose lifecycle is tied to the preservation of one or more files. This is crucial for subsystems like IOMMU or HugeTLB, where multiple file descriptors may depend on a single, shared underlying resource that must be preserved only once. - KHO Integration LUO drives the Kexec Handover framework programmatically to pass its serialized metadata to the next kernel. The LUO state is finalized and added to the kexec image just before the reboot is triggered. In the future this step will also be removed once stateless KHO is merged [6]. - Userspace Interface Control is provided via ioctl commands on /dev/liveupdate for creating and retrieving sessions, as well as on session file descriptors for managing individual files. - Testing The series includes a set of selftests, including userspace API validation, kexec-based lifecycle tests for various session and file scenarios, and a new in-kernel test module to validate the FLB logic. Introduce LUO, a mechanism intended to facilitate kernel updates while keeping designated devices operational across the transition (e.g., via kexec). The primary use case is updating hypervisors with minimal disruption to running virtual machines. For userspace side of hypervisor update we have copyless migration. LUO is for updating the kernel. This initial patch lays the groundwork for the LUO subsystem. Further functionality, including the implementation of state transition logic, integration with KHO, and hooks for subsystems and file descriptors, will be added in subsequent patches. Create a character device at /dev/liveupdate. A new uAPI header, , will define the necessary structures. The magic number for IOCTL is registered in Documentation/userspace-api/ioctl/ioctl-number.rst. Link: https://lkml.kernel.org/r/20251125165850.3389713-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20251125165850.3389713-2-pasha.tatashin@soleen.com Link: https://lore.kernel.org/all/20251018000713.677779-1-vipinsh@google.com/ [1] Link: https://lore.kernel.org/linux-iommu/20250928190624.3735830-1-skhawaja@google.com [2] Link: https://lore.kernel.org/linux-pci/20250916-luo-pci-v2-0-c494053c3c08@kernel.org [3] Link: https://github.com/googleprodkernel/linux-liveupdate/tree/luo/v8 [4] Link: https://tinyurl.com/luoddesign [5] Link: https://lore.kernel.org/all/20251020100306.2709352-1-jasonmiu@google.com [6] Link: https://lore.kernel.org/all/20251115233409.768044-1-pasha.tatashin@soleen.com [7] Link: https://github.com/soleen/linux/blob/luo/v8b03/diff.v7.v8 [8] Signed-off-by: Pasha Tatashin Reviewed-by: Pratyush Yadav Reviewed-by: Mike Rapoport (Microsoft) Tested-by: David Matlack Cc: Aleksander Lobakin Cc: Alexander Graf Cc: Alice Ryhl Cc: Andriy Shevchenko Cc: anish kumar Cc: Anna Schumaker Cc: Bartosz Golaszewski Cc: Bjorn Helgaas Cc: Borislav Betkov Cc: Chanwoo Choi Cc: Chen Ridong Cc: Chris Li Cc: Christian Brauner Cc: Daniel Wagner Cc: Danilo Krummrich Cc: Dan Williams Cc: David Hildenbrand Cc: David Jeffery Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Guixin Liu Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ilpo Järvinen Cc: Ingo Molnar Cc: Ira Weiny Cc: Jann Horn Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Joanthan Cameron Cc: Joel Granados Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lennart Poettering Cc: Leon Romanovsky Cc: Leon Romanovsky Cc: Lukas Wunner Cc: Marc Rutland Cc: Masahiro Yamada Cc: Matthew Maurer Cc: Miguel Ojeda Cc: Myugnjoo Ham Cc: Parav Pandit Cc: Randy Dunlap Cc: Roman Gushchin Cc: Saeed Mahameed Cc: Samiullah Khawaja Cc: Song Liu Cc: Steven Rostedt Cc: Stuart Hayes Cc: Tejun Heo Cc: Thomas Gleinxer Cc: Thomas Weißschuh Cc: Vincent Guittot Cc: William Tu Cc: Yoann Congal Cc: Zijun Hu Cc: Pratyush Yadav Cc: Zhu Yanjun Signed-off-by: Andrew Morton --- include/uapi/linux/liveupdate.h | 46 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 include/uapi/linux/liveupdate.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h new file mode 100644 index 000000000000..df34c1642c4d --- /dev/null +++ b/include/uapi/linux/liveupdate.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +/* + * Userspace interface for /dev/liveupdate + * Live Update Orchestrator + * + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +#ifndef _UAPI_LIVEUPDATE_H +#define _UAPI_LIVEUPDATE_H + +#include +#include + +/** + * DOC: General ioctl format + * + * The ioctl interface follows a general format to allow for extensibility. Each + * ioctl is passed in a structure pointer as the argument providing the size of + * the structure in the first u32. The kernel checks that any structure space + * beyond what it understands is 0. This allows userspace to use the backward + * compatible portion while consistently using the newer, larger, structures. + * + * ioctls use a standard meaning for common errnos: + * + * - ENOTTY: The IOCTL number itself is not supported at all + * - E2BIG: The IOCTL number is supported, but the provided structure has + * non-zero in a part the kernel does not understand. + * - EOPNOTSUPP: The IOCTL number is supported, and the structure is + * understood, however a known field has a value the kernel does not + * understand or support. + * - EINVAL: Everything about the IOCTL was understood, but a field is not + * correct. + * - ENOENT: A provided token does not exist. + * - ENOMEM: Out of memory. + * - EOVERFLOW: Mathematics overflowed. + * + * As well as additional errnos, within specific ioctls. + */ + +/* The ioctl type, documented in ioctl-number.rst */ +#define LIVEUPDATE_IOCTL_TYPE 0xBA + +#endif /* _UAPI_LIVEUPDATE_H */ -- cgit v1.2.3 From 0153094d03df5a2e834a19c59b255649a258ae46 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Tue, 25 Nov 2025 11:58:34 -0500 Subject: liveupdate: luo_session: add sessions support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce concept of "Live Update Sessions" within the LUO framework. LUO sessions provide a mechanism to group and manage `struct file *` instances (representing file descriptors) that need to be preserved across a kexec-based live update. Each session is identified by a unique name and acts as a container for file objects whose state is critical to a userspace workload, such as a virtual machine or a high-performance database, aiming to maintain their functionality across a kernel transition. This groundwork establishes the framework for preserving file-backed state across kernel updates, with the actual file data preservation mechanisms to be implemented in subsequent patches. [dan.carpenter@linaro.org: fix use after free in luo_session_deserialize()] Link: https://lkml.kernel.org/r/c5dd637d7eed3a3be48c5e9fedb881596a3b1f5a.1764163896.git.dan.carpenter@linaro.org Link: https://lkml.kernel.org/r/20251125165850.3389713-5-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Signed-off-by: Dan Carpenter Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Pratyush Yadav Tested-by: David Matlack Cc: Aleksander Lobakin Cc: Alexander Graf Cc: Alice Ryhl Cc: Andriy Shevchenko Cc: anish kumar Cc: Anna Schumaker Cc: Bartosz Golaszewski Cc: Bjorn Helgaas Cc: Borislav Betkov Cc: Chanwoo Choi Cc: Chen Ridong Cc: Chris Li Cc: Christian Brauner Cc: Daniel Wagner Cc: Danilo Krummrich Cc: Dan Williams Cc: David Hildenbrand Cc: David Jeffery Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Guixin Liu Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ilpo Järvinen Cc: Ingo Molnar Cc: Ira Weiny Cc: Jann Horn Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Joanthan Cameron Cc: Joel Granados Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lennart Poettering Cc: Leon Romanovsky Cc: Leon Romanovsky Cc: Lukas Wunner Cc: Marc Rutland Cc: Masahiro Yamada Cc: Matthew Maurer Cc: Miguel Ojeda Cc: Myugnjoo Ham Cc: Parav Pandit Cc: Pratyush Yadav Cc: Randy Dunlap Cc: Roman Gushchin Cc: Saeed Mahameed Cc: Samiullah Khawaja Cc: Song Liu Cc: Steven Rostedt Cc: Stuart Hayes Cc: Tejun Heo Cc: Thomas Gleinxer Cc: Thomas Weißschuh Cc: Vincent Guittot Cc: William Tu Cc: Yoann Congal Cc: Zhu Yanjun Cc: Zijun Hu Signed-off-by: Andrew Morton --- include/uapi/linux/liveupdate.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h index df34c1642c4d..40578ae19668 100644 --- a/include/uapi/linux/liveupdate.h +++ b/include/uapi/linux/liveupdate.h @@ -43,4 +43,7 @@ /* The ioctl type, documented in ioctl-number.rst */ #define LIVEUPDATE_IOCTL_TYPE 0xBA +/* The maximum length of session name including null termination */ +#define LIVEUPDATE_SESSION_NAME_LENGTH 64 + #endif /* _UAPI_LIVEUPDATE_H */ -- cgit v1.2.3 From 81cd25d263a182b3dcdc8af3b92e4b8e4db336de Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Tue, 25 Nov 2025 11:58:35 -0500 Subject: liveupdate: luo_core: add user interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce the user-space interface for the Live Update Orchestrator via ioctl commands, enabling external control over the live update process and management of preserved resources. The idea is that there is going to be a single userspace agent driving the live update, therefore, only a single process can ever hold this device opened at a time. The following ioctl commands are introduced: LIVEUPDATE_IOCTL_CREATE_SESSION Provides a way for userspace to create a named session for grouping file descriptors that need to be preserved. It returns a new file descriptor representing the session. LIVEUPDATE_IOCTL_RETRIEVE_SESSION Allows the userspace agent in the new kernel to reclaim a preserved session by its name, receiving a new file descriptor to manage the restored resources. Link: https://lkml.kernel.org/r/20251125165850.3389713-6-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Reviewed-by: Mike Rapoport (Microsoft) Reviewed-by: Pratyush Yadav Tested-by: David Matlack Cc: Aleksander Lobakin Cc: Alexander Graf Cc: Alice Ryhl Cc: Andriy Shevchenko Cc: anish kumar Cc: Anna Schumaker Cc: Bartosz Golaszewski Cc: Bjorn Helgaas Cc: Borislav Betkov Cc: Chanwoo Choi Cc: Chen Ridong Cc: Chris Li Cc: Christian Brauner Cc: Daniel Wagner Cc: Danilo Krummrich Cc: Dan Williams Cc: David Hildenbrand Cc: David Jeffery Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Guixin Liu Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ilpo Järvinen Cc: Ingo Molnar Cc: Ira Weiny Cc: Jann Horn Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Joanthan Cameron Cc: Joel Granados Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lennart Poettering Cc: Leon Romanovsky Cc: Leon Romanovsky Cc: Lukas Wunner Cc: Marc Rutland Cc: Masahiro Yamada Cc: Matthew Maurer Cc: Miguel Ojeda Cc: Myugnjoo Ham Cc: Parav Pandit Cc: Pratyush Yadav Cc: Randy Dunlap Cc: Roman Gushchin Cc: Saeed Mahameed Cc: Samiullah Khawaja Cc: Song Liu Cc: Steven Rostedt Cc: Stuart Hayes Cc: Tejun Heo Cc: Thomas Gleinxer Cc: Thomas Weißschuh Cc: Vincent Guittot Cc: William Tu Cc: Yoann Congal Cc: Zhu Yanjun Cc: Zijun Hu Signed-off-by: Andrew Morton --- include/uapi/linux/liveupdate.h | 64 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h index 40578ae19668..1183cf984b5f 100644 --- a/include/uapi/linux/liveupdate.h +++ b/include/uapi/linux/liveupdate.h @@ -46,4 +46,68 @@ /* The maximum length of session name including null termination */ #define LIVEUPDATE_SESSION_NAME_LENGTH 64 +/* The /dev/liveupdate ioctl commands */ +enum { + LIVEUPDATE_CMD_BASE = 0x00, + LIVEUPDATE_CMD_CREATE_SESSION = LIVEUPDATE_CMD_BASE, + LIVEUPDATE_CMD_RETRIEVE_SESSION = 0x01, +}; + +/** + * struct liveupdate_ioctl_create_session - ioctl(LIVEUPDATE_IOCTL_CREATE_SESSION) + * @size: Input; sizeof(struct liveupdate_ioctl_create_session) + * @fd: Output; The new file descriptor for the created session. + * @name: Input; A null-terminated string for the session name, max + * length %LIVEUPDATE_SESSION_NAME_LENGTH including termination + * character. + * + * Creates a new live update session for managing preserved resources. + * This ioctl can only be called on the main /dev/liveupdate device. + * + * Return: 0 on success, negative error code on failure. + */ +struct liveupdate_ioctl_create_session { + __u32 size; + __s32 fd; + __u8 name[LIVEUPDATE_SESSION_NAME_LENGTH]; +}; + +#define LIVEUPDATE_IOCTL_CREATE_SESSION \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_CREATE_SESSION) + +/** + * struct liveupdate_ioctl_retrieve_session - ioctl(LIVEUPDATE_IOCTL_RETRIEVE_SESSION) + * @size: Input; sizeof(struct liveupdate_ioctl_retrieve_session) + * @fd: Output; The new file descriptor for the retrieved session. + * @name: Input; A null-terminated string identifying the session to retrieve. + * The name must exactly match the name used when the session was + * created in the previous kernel. + * + * Retrieves a handle (a new file descriptor) for a preserved session by its + * name. This is the primary mechanism for a userspace agent to regain control + * of its preserved resources after a live update. + * + * The userspace application provides the null-terminated `name` of a session + * it created before the live update. If a preserved session with a matching + * name is found, the kernel instantiates it and returns a new file descriptor + * in the `fd` field. This new session FD can then be used for all file-specific + * operations, such as restoring individual file descriptors with + * LIVEUPDATE_SESSION_RETRIEVE_FD. + * + * It is the responsibility of the userspace application to know the names of + * the sessions it needs to retrieve. If no session with the given name is + * found, the ioctl will fail with -ENOENT. + * + * This ioctl can only be called on the main /dev/liveupdate device when the + * system is in the LIVEUPDATE_STATE_UPDATED state. + */ +struct liveupdate_ioctl_retrieve_session { + __u32 size; + __s32 fd; + __u8 name[LIVEUPDATE_SESSION_NAME_LENGTH]; +}; + +#define LIVEUPDATE_IOCTL_RETRIEVE_SESSION \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_RETRIEVE_SESSION) + #endif /* _UAPI_LIVEUPDATE_H */ -- cgit v1.2.3 From 16cec0d265219f14a7fcebcc43aeb69205adba56 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Tue, 25 Nov 2025 11:58:37 -0500 Subject: liveupdate: luo_session: add ioctls for file preservation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introducing the userspace interface and internal logic required to manage the lifecycle of file descriptors within a session. Previously, a session was merely a container; this change makes it a functional management unit. The following capabilities are added: A new set of ioctl commands are added, which operate on the file descriptor returned by CREATE_SESSION. This allows userspace to: - LIVEUPDATE_SESSION_PRESERVE_FD: Add a file descriptor to a session to be preserved across the live update. - LIVEUPDATE_SESSION_RETRIEVE_FD: Retrieve a preserved file in the new kernel using its unique token. - LIVEUPDATE_SESSION_FINISH: finish session The session's .release handler is enhanced to be state-aware. When a session's file descriptor is closed, it correctly unpreserves the session based on its current state before freeing all associated file resources. Link: https://lkml.kernel.org/r/20251125165850.3389713-8-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Reviewed-by: Pratyush Yadav Reviewed-by: Mike Rapoport (Microsoft) Tested-by: David Matlack Cc: Aleksander Lobakin Cc: Alexander Graf Cc: Alice Ryhl Cc: Andriy Shevchenko Cc: anish kumar Cc: Anna Schumaker Cc: Bartosz Golaszewski Cc: Bjorn Helgaas Cc: Borislav Betkov Cc: Chanwoo Choi Cc: Chen Ridong Cc: Chris Li Cc: Christian Brauner Cc: Daniel Wagner Cc: Danilo Krummrich Cc: Dan Williams Cc: David Hildenbrand Cc: David Jeffery Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Guixin Liu Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ilpo Järvinen Cc: Ingo Molnar Cc: Ira Weiny Cc: Jann Horn Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Joanthan Cameron Cc: Joel Granados Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Lennart Poettering Cc: Leon Romanovsky Cc: Leon Romanovsky Cc: Lukas Wunner Cc: Marc Rutland Cc: Masahiro Yamada Cc: Matthew Maurer Cc: Miguel Ojeda Cc: Myugnjoo Ham Cc: Parav Pandit Cc: Pratyush Yadav Cc: Randy Dunlap Cc: Roman Gushchin Cc: Saeed Mahameed Cc: Samiullah Khawaja Cc: Song Liu Cc: Steven Rostedt Cc: Stuart Hayes Cc: Tejun Heo Cc: Thomas Gleinxer Cc: Thomas Weißschuh Cc: Vincent Guittot Cc: William Tu Cc: Yoann Congal Cc: Zhu Yanjun Cc: Zijun Hu Signed-off-by: Andrew Morton --- include/uapi/linux/liveupdate.h | 103 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h index 1183cf984b5f..30bc66ee9436 100644 --- a/include/uapi/linux/liveupdate.h +++ b/include/uapi/linux/liveupdate.h @@ -53,6 +53,14 @@ enum { LIVEUPDATE_CMD_RETRIEVE_SESSION = 0x01, }; +/* ioctl commands for session file descriptors */ +enum { + LIVEUPDATE_CMD_SESSION_BASE = 0x40, + LIVEUPDATE_CMD_SESSION_PRESERVE_FD = LIVEUPDATE_CMD_SESSION_BASE, + LIVEUPDATE_CMD_SESSION_RETRIEVE_FD = 0x41, + LIVEUPDATE_CMD_SESSION_FINISH = 0x42, +}; + /** * struct liveupdate_ioctl_create_session - ioctl(LIVEUPDATE_IOCTL_CREATE_SESSION) * @size: Input; sizeof(struct liveupdate_ioctl_create_session) @@ -110,4 +118,99 @@ struct liveupdate_ioctl_retrieve_session { #define LIVEUPDATE_IOCTL_RETRIEVE_SESSION \ _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_RETRIEVE_SESSION) +/* Session specific IOCTLs */ + +/** + * struct liveupdate_session_preserve_fd - ioctl(LIVEUPDATE_SESSION_PRESERVE_FD) + * @size: Input; sizeof(struct liveupdate_session_preserve_fd) + * @fd: Input; The user-space file descriptor to be preserved. + * @token: Input; An opaque, unique token for preserved resource. + * + * Holds parameters for preserving a file descriptor. + * + * User sets the @fd field identifying the file descriptor to preserve + * (e.g., memfd, kvm, iommufd, VFIO). The kernel validates if this FD type + * and its dependencies are supported for preservation. If validation passes, + * the kernel marks the FD internally and *initiates the process* of preparing + * its state for saving. The actual snapshotting of the state typically occurs + * during the subsequent %LIVEUPDATE_IOCTL_PREPARE execution phase, though + * some finalization might occur during freeze. + * On successful validation and initiation, the kernel uses the @token + * field with an opaque identifier representing the resource being preserved. + * This token confirms the FD is targeted for preservation and is required for + * the subsequent %LIVEUPDATE_SESSION_RETRIEVE_FD call after the live update. + * + * Return: 0 on success (validation passed, preservation initiated), negative + * error code on failure (e.g., unsupported FD type, dependency issue, + * validation failed). + */ +struct liveupdate_session_preserve_fd { + __u32 size; + __s32 fd; + __aligned_u64 token; +}; + +#define LIVEUPDATE_SESSION_PRESERVE_FD \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_PRESERVE_FD) + +/** + * struct liveupdate_session_retrieve_fd - ioctl(LIVEUPDATE_SESSION_RETRIEVE_FD) + * @size: Input; sizeof(struct liveupdate_session_retrieve_fd) + * @fd: Output; The new file descriptor representing the fully restored + * kernel resource. + * @token: Input; An opaque, token that was used to preserve the resource. + * + * Retrieve a previously preserved file descriptor. + * + * User sets the @token field to the value obtained from a successful + * %LIVEUPDATE_IOCTL_FD_PRESERVE call before the live update. On success, + * the kernel restores the state (saved during the PREPARE/FREEZE phases) + * associated with the token and populates the @fd field with a new file + * descriptor referencing the restored resource in the current (new) kernel. + * This operation must be performed *before* signaling completion via + * %LIVEUPDATE_IOCTL_FINISH. + * + * Return: 0 on success, negative error code on failure (e.g., invalid token). + */ +struct liveupdate_session_retrieve_fd { + __u32 size; + __s32 fd; + __aligned_u64 token; +}; + +#define LIVEUPDATE_SESSION_RETRIEVE_FD \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_RETRIEVE_FD) + +/** + * struct liveupdate_session_finish - ioctl(LIVEUPDATE_SESSION_FINISH) + * @size: Input; sizeof(struct liveupdate_session_finish) + * @reserved: Input; Must be zero. Reserved for future use. + * + * Signals the completion of the restoration process for a retrieved session. + * This is the final operation that should be performed on a session file + * descriptor after a live update. + * + * This ioctl must be called once all required file descriptors for the session + * have been successfully retrieved (using %LIVEUPDATE_SESSION_RETRIEVE_FD) and + * are fully restored from the userspace and kernel perspective. + * + * Upon success, the kernel releases its ownership of the preserved resources + * associated with this session. This allows internal resources to be freed, + * typically by decrementing reference counts on the underlying preserved + * objects. + * + * If this operation fails, the resources remain preserved in memory. Userspace + * may attempt to call finish again. The resources will otherwise be reset + * during the next live update cycle. + * + * Return: 0 on success, negative error code on failure. + */ +struct liveupdate_session_finish { + __u32 size; + __u32 reserved; +}; + +#define LIVEUPDATE_SESSION_FINISH \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_FINISH) + #endif /* _UAPI_LIVEUPDATE_H */ -- cgit v1.2.3 From 3fa805c37dd4d3e72ae5c58800f3f46ab3ca1f70 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 10 Oct 2025 03:36:50 -0700 Subject: vmcoreinfo: track and log recoverable hardware errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a generic infrastructure for tracking recoverable hardware errors (HW errors that are visible to the OS but does not cause a panic) and record them for vmcore consumption. This aids post-mortem crash analysis tools by preserving a count and timestamp for the last occurrence of such errors. On the other side, correctable errors, which the OS typically remains unaware of because the underlying hardware handles them transparently, are less relevant for crash dump and therefore are NOT tracked in this infrastructure. Add centralized logging for sources of recoverable hardware errors based on the subsystem it has been notified. hwerror_data is write-only at kernel runtime, and it is meant to be read from vmcore using tools like crash/drgn. For example, this is how it looks like when opening the crashdump from drgn. >>> prog['hwerror_data'] (struct hwerror_info[1]){ { .count = (int)844, .timestamp = (time64_t)1752852018, }, ... This helps fleet operators quickly triage whether a crash may be influenced by hardware recoverable errors (which executes a uncommon code path in the kernel), especially when recoverable errors occurred shortly before a panic, such as the bug fixed by commit ee62ce7a1d90 ("page_pool: Track DMA-mapped pages and unmap them when destroying the pool") This is not intended to replace full hardware diagnostics but provides a fast way to correlate hardware events with kernel panics quickly. Rare machine check exceptions—like those indicated by mce_flags.p5 or mce_flags.winchip—are not accounted for in this method, as they fall outside the intended usage scope for this feature's user base. [leitao@debian.org: add hw-recoverable-errors to toctree] Link: https://lkml.kernel.org/r/20251127-vmcoreinfo_fix-v1-1-26f5b1c43da9@debian.org Link: https://lkml.kernel.org/r/20251010-vmcore_hw_error-v5-1-636ede3efe44@debian.org Signed-off-by: Breno Leitao Suggested-by: Tony Luck Suggested-by: Shuai Xue Reviewed-by: Shuai Xue Reviewed-by: Hanjun Guo [APEI] Cc: Bjorn Helgaas Cc: Bob Moore Cc: Borislav Betkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: Konrad Rzessutek Wilk Cc: Len Brown Cc: Mahesh Salgaonkar Cc: Mauro Carvalho Chehab Cc: "Oliver O'Halloran" Cc: Omar Sandoval Cc: Thomas Gleinxer Signed-off-by: Andrew Morton --- include/uapi/linux/vmcore.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vmcore.h b/include/uapi/linux/vmcore.h index 3e9da91866ff..2ba89fafa518 100644 --- a/include/uapi/linux/vmcore.h +++ b/include/uapi/linux/vmcore.h @@ -15,4 +15,13 @@ struct vmcoredd_header { __u8 dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Device dump's name */ }; +enum hwerr_error_type { + HWERR_RECOV_CPU, + HWERR_RECOV_MEMORY, + HWERR_RECOV_PCI, + HWERR_RECOV_CXL, + HWERR_RECOV_OTHERS, + HWERR_RECOV_MAX, +}; + #endif /* _UAPI_VMCORE_H */ -- cgit v1.2.3 From c4f0ab06e1e0c1331e6febd03538a7f621f15134 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 1 Nov 2025 12:20:50 -0700 Subject: netfilter: ip6t_srh: fix UAPI kernel-doc comments format Fix the kernel-doc format for struct members to be "@member" instead of "@ member" to avoid kernel-doc warnings. Warning: ip6t_srh.h:60 struct member 'next_hdr' not described in 'ip6t_srh' Warning: ip6t_srh.h:60 struct member 'hdr_len' not described in 'ip6t_srh' Warning: ip6t_srh.h:60 struct member 'segs_left' not described in 'ip6t_srh' Warning: ip6t_srh.h:60 struct member 'last_entry' not described in 'ip6t_srh' Warning: ip6t_srh.h:60 struct member 'tag' not described in 'ip6t_srh' Warning: ip6t_srh.h:60 struct member 'mt_flags' not described in 'ip6t_srh' Warning: ip6t_srh.h:60 struct member 'mt_invflags' not described in 'ip6t_srh' Warning: ip6t_srh.h:93 struct member 'next_hdr' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'hdr_len' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'segs_left' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'last_entry' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'tag' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'psid_addr' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'nsid_addr' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'lsid_addr' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'psid_msk' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'nsid_msk' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'lsid_msk' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'mt_flags' not described in 'ip6t_srh1' Warning: ip6t_srh.h:93 struct member 'mt_invflags' not described in 'ip6t_srh1' Signed-off-by: Randy Dunlap Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter_ipv6/ip6t_srh.h | 40 ++++++++++++++-------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_srh.h b/include/uapi/linux/netfilter_ipv6/ip6t_srh.h index 54ed83360dac..80c66c8ece82 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_srh.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_srh.h @@ -41,13 +41,13 @@ /** * struct ip6t_srh - SRH match options - * @ next_hdr: Next header field of SRH - * @ hdr_len: Extension header length field of SRH - * @ segs_left: Segments left field of SRH - * @ last_entry: Last entry field of SRH - * @ tag: Tag field of SRH - * @ mt_flags: match options - * @ mt_invflags: Invert the sense of match options + * @next_hdr: Next header field of SRH + * @hdr_len: Extension header length field of SRH + * @segs_left: Segments left field of SRH + * @last_entry: Last entry field of SRH + * @tag: Tag field of SRH + * @mt_flags: match options + * @mt_invflags: Invert the sense of match options */ struct ip6t_srh { @@ -62,19 +62,19 @@ struct ip6t_srh { /** * struct ip6t_srh1 - SRH match options (revision 1) - * @ next_hdr: Next header field of SRH - * @ hdr_len: Extension header length field of SRH - * @ segs_left: Segments left field of SRH - * @ last_entry: Last entry field of SRH - * @ tag: Tag field of SRH - * @ psid_addr: Address of previous SID in SRH SID list - * @ nsid_addr: Address of NEXT SID in SRH SID list - * @ lsid_addr: Address of LAST SID in SRH SID list - * @ psid_msk: Mask of previous SID in SRH SID list - * @ nsid_msk: Mask of next SID in SRH SID list - * @ lsid_msk: MAsk of last SID in SRH SID list - * @ mt_flags: match options - * @ mt_invflags: Invert the sense of match options + * @next_hdr: Next header field of SRH + * @hdr_len: Extension header length field of SRH + * @segs_left: Segments left field of SRH + * @last_entry: Last entry field of SRH + * @tag: Tag field of SRH + * @psid_addr: Address of previous SID in SRH SID list + * @nsid_addr: Address of NEXT SID in SRH SID list + * @lsid_addr: Address of LAST SID in SRH SID list + * @psid_msk: Mask of previous SID in SRH SID list + * @nsid_msk: Mask of next SID in SRH SID list + * @lsid_msk: MAsk of last SID in SRH SID list + * @mt_flags: match options + * @mt_invflags: Invert the sense of match options */ struct ip6t_srh1 { -- cgit v1.2.3 From d3a439e55c193b930e0007967cf8d7a29890449b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 1 Nov 2025 12:20:38 -0700 Subject: netfilter: nf_tables: improve UAPI kernel-doc comments In include/uapi/linux/netfilter/nf_tables.h, correct the kernel-doc comments for mistyped enum names and enum values to avoid these kernel-doc warnings and improve the documentation: nf_tables.h:896: warning: Enum value 'NFT_EXTHDR_OP_TCPOPT' not described in enum 'nft_exthdr_op' nf_tables.h:896: warning: Excess enum value 'NFT_EXTHDR_OP_TCP' description in 'nft_exthdr_op' nf_tables.h:1210: warning: expecting prototype for enum nft_flow_attributes. Prototype was for enum nft_offload_attributes instead nf_tables.h:1428: warning: expecting prototype for enum nft_reject_code. Prototype was for enum nft_reject_inet_code instead (add beginning '@' to each enum value description:) nf_tables.h:1493: warning: Enum value 'NFTA_TPROXY_FAMILY' not described in enum 'nft_tproxy_attributes' nf_tables.h:1493: warning: Enum value 'NFTA_TPROXY_REG_ADDR' not described in enum 'nft_tproxy_attributes' nf_tables.h:1493: warning: Enum value 'NFTA_TPROXY_REG_PORT' not described in enum 'nft_tproxy_attributes' nf_tables.h:1796: warning: expecting prototype for enum nft_device_attributes. Prototype was for enum nft_devices_attributes instead Signed-off-by: Randy Dunlap Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 7c0c915f0306..45c71f7d21c2 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -881,7 +881,7 @@ enum nft_exthdr_flags { * enum nft_exthdr_op - nf_tables match options * * @NFT_EXTHDR_OP_IPV6: match against ipv6 extension headers - * @NFT_EXTHDR_OP_TCP: match against tcp options + * @NFT_EXTHDR_OP_TCPOPT: match against tcp options * @NFT_EXTHDR_OP_IPV4: match against ipv4 options * @NFT_EXTHDR_OP_SCTP: match against sctp chunks * @NFT_EXTHDR_OP_DCCP: match against dccp otions @@ -1200,7 +1200,7 @@ enum nft_ct_attributes { #define NFTA_CT_MAX (__NFTA_CT_MAX - 1) /** - * enum nft_flow_attributes - ct offload expression attributes + * enum nft_offload_attributes - ct offload expression attributes * @NFTA_FLOW_TABLE_NAME: flow table name (NLA_STRING) */ enum nft_offload_attributes { @@ -1410,7 +1410,7 @@ enum nft_reject_types { }; /** - * enum nft_reject_code - Generic reject codes for IPv4/IPv6 + * enum nft_reject_inet_code - Generic reject codes for IPv4/IPv6 * * @NFT_REJECT_ICMPX_NO_ROUTE: no route to host / network unreachable * @NFT_REJECT_ICMPX_PORT_UNREACH: port unreachable @@ -1480,9 +1480,9 @@ enum nft_nat_attributes { /** * enum nft_tproxy_attributes - nf_tables tproxy expression netlink attributes * - * NFTA_TPROXY_FAMILY: Target address family (NLA_U32: nft_registers) - * NFTA_TPROXY_REG_ADDR: Target address register (NLA_U32: nft_registers) - * NFTA_TPROXY_REG_PORT: Target port register (NLA_U32: nft_registers) + * @NFTA_TPROXY_FAMILY: Target address family (NLA_U32: nft_registers) + * @NFTA_TPROXY_REG_ADDR: Target address register (NLA_U32: nft_registers) + * @NFTA_TPROXY_REG_PORT: Target port register (NLA_U32: nft_registers) */ enum nft_tproxy_attributes { NFTA_TPROXY_UNSPEC, @@ -1783,7 +1783,7 @@ enum nft_synproxy_attributes { #define NFTA_SYNPROXY_MAX (__NFTA_SYNPROXY_MAX - 1) /** - * enum nft_device_attributes - nf_tables device netlink attributes + * enum nft_devices_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) * @NFTA_DEVICE_PREFIX: device name prefix, a simple wildcard (NLA_STRING) -- cgit v1.2.3 From 6557cae0a2a1952645e5df50e1d6eb7267ea2131 Mon Sep 17 00:00:00 2001 From: Peter Enderborg Date: Wed, 26 Nov 2025 14:54:06 +0100 Subject: if_ether.h: Clarify ethertype validity for gsw1xx dsa This 0x88C3 is registered to Infineon Technologies Corporate Research ST and are used by MaxLinear. Infineon made a spin off called Lantiq. Lantiq was acquired by Intel MaxLinear acquired Intels Connected Home division. The product FAQ from MaxLinear describes it's history from the F24S. The driver for the gsw1xx is based on Lantiq showing it's similarities. Ref https://standards-oui.ieee.org/ethertype/eth.txt Signed-off-by: Peter Enderborg Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 2c93b7b731c8..df9d44a11540 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -92,7 +92,9 @@ #define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ -#define ETH_P_MXLGSW 0x88C3 /* MaxLinear GSW DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_MXLGSW 0x88C3 /* Infineon Technologies Corporate Research ST + * Used by MaxLinear GSW DSA + */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ -- cgit v1.2.3 From 4be9e04ebf75a5c4478c1c6295e2122e5dc98f5f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 28 Nov 2025 10:55:09 +0100 Subject: vfs: add needed headers for new struct delegation definition The definition of struct delegation uses stdint.h integer types. Add the necessary headers to ensure that always works. Fixes: 1602bad16d7d ("vfs: expose delegation support to userland") Signed-off-by: Jeff Layton Signed-off-by: Christian Brauner --- include/uapi/linux/fcntl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 008fac15e573..5e277fd955aa 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -4,6 +4,11 @@ #include #include +#ifdef __KERNEL__ +#include +#else +#include +#endif #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) -- cgit v1.2.3 From 414690746d2da0dc9a931f8c02d83e5834141251 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 24 Nov 2025 18:28:08 -0800 Subject: i2c: i2c.h: fix a bad kernel-doc line Change an empty line into a blank kernel-doc line to prevent a kernel-doc warning: Warning: ../include/uapi/linux/i2c.h:38 bad line: Fixes: bfb3939c51d5 ("i2c: refactor documentation of struct i2c_msg") Signed-off-by: Randy Dunlap Signed-off-by: Wolfram Sang --- include/uapi/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index a2db2a56c8b0..2a226657d9f8 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -36,7 +36,7 @@ * * Only if I2C_FUNC_NOSTART is set: * %I2C_M_NOSTART: skip repeated start sequence - + * * Only if I2C_FUNC_PROTOCOL_MANGLING is set: * %I2C_M_NO_RD_ACK: in a read message, master ACK/NACK bit is skipped * %I2C_M_IGNORE_NAK: treat NACK from client as ACK -- cgit v1.2.3 From 205dd7a5d6ad6f4c8e8fcd3c3b95a7c0e7067fee Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 18 Nov 2025 18:06:31 -0500 Subject: virtio_pci: drop kernel.h virtio UAPI headers really have no business pulling in kernel.h Replace it with const.h which seems to be what's needed for __KERNEL_DIV_ROUND_UP. Fixes: 7c1ae151e812 ("virtio_pci: Introduce device parts access commands") Cc: Yishai Hadas Cc: Alex Williamson Message-ID: <7a73b6c6af67e13b86633cd7bf11ad56b5d9809b.1763535341.git.mst@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index c691ac210ce2..e732e3456e27 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -40,7 +40,7 @@ #define _LINUX_VIRTIO_PCI_H #include -#include +#include #ifndef VIRTIO_PCI_NO_LEGACY -- cgit v1.2.3 From 6b0f4ca079dbe6ae4aa57e529d67c7dc00d63577 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= Date: Wed, 26 Nov 2025 17:35:37 +0000 Subject: wireguard: netlink: add YNL specification MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a near[1] complete YNL specification for WireGuard, documenting the protocol in a machine-readable format, rather than comments in wireguard.h, and eases usage from C and non-C programming languages alike. The generated C library will be featured in a later patch, so in this patch I will use the in-kernel python client for examples. This makes the documentation in the UAPI header redundant, it is therefore removed. The in-line documentation in the spec is based on the existing comment in wireguard.h, and once released it will be available in the kernel documentation at: https://docs.kernel.org/netlink/specs/wireguard.html (until then run: make htmldocs) Generate wireguard.rst from this spec: $ make -C tools/net/ynl/generated/ wireguard.rst Query wireguard interface through pyynl: $ sudo ./tools/net/ynl/pyynl/cli.py --family wireguard \ --dump get-device \ --json '{"ifindex":3}' [{'fwmark': 0, 'ifindex': 3, 'ifname': 'wg-test', 'listen-port': 54318, 'peers': [{0: {'allowedips': [{0: {'cidr-mask': 0, 'family': 2, 'ipaddr': '0.0.0.0'}}, {0: {'cidr-mask': 0, 'family': 10, 'ipaddr': '::'}}], 'endpoint': b'[...]', 'last-handshake-time': {'nsec': 42, 'sec': 42}, 'persistent-keepalive-interval': 42, 'preshared-key': '[...]', 'protocol-version': 1, 'public-key': '[...]', 'rx-bytes': 42, 'tx-bytes': 42}}], 'private-key': '[...]', 'public-key': '[...]'}] Add another allowed IP prefix: $ sudo ./tools/net/ynl/pyynl/cli.py --family wireguard \ --do set-device --json '{"ifindex":3,"peers":[ {"public-key":"6a df b1 83 a4 ..","allowedips":[ {"cidr-mask":0,"family":10,"ipaddr":"::"}]}]}' [1] As can be seen above, the "endpoint" is only dumped as binary data, as it can't be fully described in YNL. It's either a struct sockaddr_in or struct sockaddr_in6 depending on the attribute length. Signed-off-by: Asbjørn Sloth Tønnesen Signed-off-by: Jason A. Donenfeld --- include/uapi/linux/wireguard.h | 129 ----------------------------------------- 1 file changed, 129 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/wireguard.h b/include/uapi/linux/wireguard.h index 8c26391196d5..dee4401e0b5d 100644 --- a/include/uapi/linux/wireguard.h +++ b/include/uapi/linux/wireguard.h @@ -1,135 +1,6 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. - * - * Documentation - * ============= - * - * The below enums and macros are for interfacing with WireGuard, using generic - * netlink, with family WG_GENL_NAME and version WG_GENL_VERSION. It defines two - * methods: get and set. Note that while they share many common attributes, - * these two functions actually accept a slightly different set of inputs and - * outputs. - * - * WG_CMD_GET_DEVICE - * ----------------- - * - * May only be called via NLM_F_REQUEST | NLM_F_DUMP. The command should contain - * one but not both of: - * - * WGDEVICE_A_IFINDEX: NLA_U32 - * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1 - * - * The kernel will then return several messages (NLM_F_MULTI) containing the - * following tree of nested items: - * - * WGDEVICE_A_IFINDEX: NLA_U32 - * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1 - * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN - * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN - * WGDEVICE_A_LISTEN_PORT: NLA_U16 - * WGDEVICE_A_FWMARK: NLA_U32 - * WGDEVICE_A_PEERS: NLA_NESTED - * 0: NLA_NESTED - * WGPEER_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN - * WGPEER_A_PRESHARED_KEY: NLA_EXACT_LEN, len WG_KEY_LEN - * WGPEER_A_ENDPOINT: NLA_MIN_LEN(struct sockaddr), struct sockaddr_in or struct sockaddr_in6 - * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16 - * WGPEER_A_LAST_HANDSHAKE_TIME: NLA_EXACT_LEN, struct __kernel_timespec - * WGPEER_A_RX_BYTES: NLA_U64 - * WGPEER_A_TX_BYTES: NLA_U64 - * WGPEER_A_ALLOWEDIPS: NLA_NESTED - * 0: NLA_NESTED - * WGALLOWEDIP_A_FAMILY: NLA_U16 - * WGALLOWEDIP_A_IPADDR: NLA_MIN_LEN(struct in_addr), struct in_addr or struct in6_addr - * WGALLOWEDIP_A_CIDR_MASK: NLA_U8 - * 0: NLA_NESTED - * ... - * 0: NLA_NESTED - * ... - * ... - * WGPEER_A_PROTOCOL_VERSION: NLA_U32 - * 0: NLA_NESTED - * ... - * ... - * - * It is possible that all of the allowed IPs of a single peer will not - * fit within a single netlink message. In that case, the same peer will - * be written in the following message, except it will only contain - * WGPEER_A_PUBLIC_KEY and WGPEER_A_ALLOWEDIPS. This may occur several - * times in a row for the same peer. It is then up to the receiver to - * coalesce adjacent peers. Likewise, it is possible that all peers will - * not fit within a single message. So, subsequent peers will be sent - * in following messages, except those will only contain WGDEVICE_A_IFNAME - * and WGDEVICE_A_PEERS. It is then up to the receiver to coalesce these - * messages to form the complete list of peers. - * - * Since this is an NLA_F_DUMP command, the final message will always be - * NLMSG_DONE, even if an error occurs. However, this NLMSG_DONE message - * contains an integer error code. It is either zero or a negative error - * code corresponding to the errno. - * - * WG_CMD_SET_DEVICE - * ----------------- - * - * May only be called via NLM_F_REQUEST. The command should contain the - * following tree of nested items, containing one but not both of - * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME: - * - * WGDEVICE_A_IFINDEX: NLA_U32 - * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1 - * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current - * peers should be removed prior to adding the list below. - * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove - * WGDEVICE_A_LISTEN_PORT: NLA_U16, 0 to choose randomly - * WGDEVICE_A_FWMARK: NLA_U32, 0 to disable - * WGDEVICE_A_PEERS: NLA_NESTED - * 0: NLA_NESTED - * WGPEER_A_PUBLIC_KEY: len WG_KEY_LEN - * WGPEER_A_FLAGS: NLA_U32, 0 and/or WGPEER_F_REMOVE_ME if the - * specified peer should not exist at the end of the - * operation, rather than added/updated and/or - * WGPEER_F_REPLACE_ALLOWEDIPS if all current allowed - * IPs of this peer should be removed prior to adding - * the list below and/or WGPEER_F_UPDATE_ONLY if the - * peer should only be set if it already exists. - * WGPEER_A_PRESHARED_KEY: len WG_KEY_LEN, all zeros to remove - * WGPEER_A_ENDPOINT: struct sockaddr_in or struct sockaddr_in6 - * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16, 0 to disable - * WGPEER_A_ALLOWEDIPS: NLA_NESTED - * 0: NLA_NESTED - * WGALLOWEDIP_A_FAMILY: NLA_U16 - * WGALLOWEDIP_A_IPADDR: struct in_addr or struct in6_addr - * WGALLOWEDIP_A_CIDR_MASK: NLA_U8 - * WGALLOWEDIP_A_FLAGS: NLA_U32, WGALLOWEDIP_F_REMOVE_ME if - * the specified IP should be removed; - * otherwise, this IP will be added if - * it is not already present. - * 0: NLA_NESTED - * ... - * 0: NLA_NESTED - * ... - * ... - * WGPEER_A_PROTOCOL_VERSION: NLA_U32, should not be set or used at - * all by most users of this API, as the - * most recent protocol will be used when - * this is unset. Otherwise, must be set - * to 1. - * 0: NLA_NESTED - * ... - * ... - * - * It is possible that the amount of configuration data exceeds that of - * the maximum message length accepted by the kernel. In that case, several - * messages should be sent one after another, with each successive one - * filling in information not contained in the prior. Note that if - * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably - * should not be specified in fragments that come after, so that the list - * of peers is only cleared the first time but appended after. Likewise for - * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message - * of a peer, it likely should not be specified in subsequent fragments. - * - * If an error occurs, NLMSG_ERROR will reply containing an errno. */ #ifndef _WG_UAPI_WIREGUARD_H -- cgit v1.2.3 From b5c5a82bf5cb96e14a6627ef21be962052a0c6d8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= Date: Wed, 26 Nov 2025 17:35:38 +0000 Subject: wireguard: uapi: move enum wg_cmd MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch moves enum wg_cmd to the end of the file, where ynl-gen would generate it. This is an incremental step towards adopting an UAPI header generated by ynl-gen. This is split out to keep the patches readable. This is a trivial patch with no behavioural changes intended. Signed-off-by: Asbjørn Sloth Tønnesen Signed-off-by: Jason A. Donenfeld --- include/uapi/linux/wireguard.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/wireguard.h b/include/uapi/linux/wireguard.h index dee4401e0b5d..3ebfffd61269 100644 --- a/include/uapi/linux/wireguard.h +++ b/include/uapi/linux/wireguard.h @@ -11,13 +11,6 @@ #define WG_KEY_LEN 32 -enum wg_cmd { - WG_CMD_GET_DEVICE, - WG_CMD_SET_DEVICE, - __WG_CMD_MAX -}; -#define WG_CMD_MAX (__WG_CMD_MAX - 1) - enum wgdevice_flag { WGDEVICE_F_REPLACE_PEERS = 1U << 0, __WGDEVICE_F_ALL = WGDEVICE_F_REPLACE_PEERS @@ -73,4 +66,12 @@ enum wgallowedip_attribute { }; #define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1) +enum wg_cmd { + WG_CMD_GET_DEVICE, + WG_CMD_SET_DEVICE, + + __WG_CMD_MAX +}; +#define WG_CMD_MAX (__WG_CMD_MAX - 1) + #endif /* _WG_UAPI_WIREGUARD_H */ -- cgit v1.2.3 From 8d974872ab29eeb93a5b0b698007257d8be07968 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= Date: Wed, 26 Nov 2025 17:35:39 +0000 Subject: wireguard: uapi: move flag enums MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the wg*_flag enums, so they are defined above the attribute set enums, where ynl-gen would place them. This is an incremental step towards adopting an UAPI header generated by ynl-gen. This is split out to keep the patches readable. This is a trivial patch with no behavioural changes intended. Signed-off-by: Asbjørn Sloth Tønnesen Signed-off-by: Jason A. Donenfeld --- include/uapi/linux/wireguard.h | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/wireguard.h b/include/uapi/linux/wireguard.h index 3ebfffd61269..a2815f4f2910 100644 --- a/include/uapi/linux/wireguard.h +++ b/include/uapi/linux/wireguard.h @@ -15,6 +15,20 @@ enum wgdevice_flag { WGDEVICE_F_REPLACE_PEERS = 1U << 0, __WGDEVICE_F_ALL = WGDEVICE_F_REPLACE_PEERS }; + +enum wgpeer_flag { + WGPEER_F_REMOVE_ME = 1U << 0, + WGPEER_F_REPLACE_ALLOWEDIPS = 1U << 1, + WGPEER_F_UPDATE_ONLY = 1U << 2, + __WGPEER_F_ALL = WGPEER_F_REMOVE_ME | WGPEER_F_REPLACE_ALLOWEDIPS | + WGPEER_F_UPDATE_ONLY +}; + +enum wgallowedip_flag { + WGALLOWEDIP_F_REMOVE_ME = 1U << 0, + __WGALLOWEDIP_F_ALL = WGALLOWEDIP_F_REMOVE_ME +}; + enum wgdevice_attribute { WGDEVICE_A_UNSPEC, WGDEVICE_A_IFINDEX, @@ -29,13 +43,6 @@ enum wgdevice_attribute { }; #define WGDEVICE_A_MAX (__WGDEVICE_A_LAST - 1) -enum wgpeer_flag { - WGPEER_F_REMOVE_ME = 1U << 0, - WGPEER_F_REPLACE_ALLOWEDIPS = 1U << 1, - WGPEER_F_UPDATE_ONLY = 1U << 2, - __WGPEER_F_ALL = WGPEER_F_REMOVE_ME | WGPEER_F_REPLACE_ALLOWEDIPS | - WGPEER_F_UPDATE_ONLY -}; enum wgpeer_attribute { WGPEER_A_UNSPEC, WGPEER_A_PUBLIC_KEY, @@ -52,10 +59,6 @@ enum wgpeer_attribute { }; #define WGPEER_A_MAX (__WGPEER_A_LAST - 1) -enum wgallowedip_flag { - WGALLOWEDIP_F_REMOVE_ME = 1U << 0, - __WGALLOWEDIP_F_ALL = WGALLOWEDIP_F_REMOVE_ME -}; enum wgallowedip_attribute { WGALLOWEDIP_A_UNSPEC, WGALLOWEDIP_A_FAMILY, -- cgit v1.2.3 From 88cedad45ba14097e06d2c9f6578688097a94691 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= Date: Wed, 26 Nov 2025 17:35:40 +0000 Subject: wireguard: uapi: generate header with ynl-gen MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use ynl-gen to generate the UAPI header for WireGuard. The cosmetic changes in this patch confirms that the spec is aligned with the implementation. By using the generated version, it ensures that they stay in sync. Changes in the generated header: * Trivial header guard rename. * Trivial white space changes. * Trivial comment changes. * Precompute bitflags in ynl-gen (see [1]). * Drop __*_F_ALL constants (see [1]). [1] https://lore.kernel.org/r/20251014123201.6ecfd146@kernel.org/ No behavioural changes intended. Signed-off-by: Asbjørn Sloth Tønnesen Signed-off-by: Jason A. Donenfeld --- include/uapi/linux/wireguard.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/wireguard.h b/include/uapi/linux/wireguard.h index a2815f4f2910..a100b9715b08 100644 --- a/include/uapi/linux/wireguard.h +++ b/include/uapi/linux/wireguard.h @@ -1,32 +1,29 @@ -/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ -/* - * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. - */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/wireguard.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ -#ifndef _WG_UAPI_WIREGUARD_H -#define _WG_UAPI_WIREGUARD_H +#ifndef _UAPI_LINUX_WIREGUARD_H +#define _UAPI_LINUX_WIREGUARD_H -#define WG_GENL_NAME "wireguard" -#define WG_GENL_VERSION 1 +#define WG_GENL_NAME "wireguard" +#define WG_GENL_VERSION 1 -#define WG_KEY_LEN 32 +#define WG_KEY_LEN 32 enum wgdevice_flag { - WGDEVICE_F_REPLACE_PEERS = 1U << 0, - __WGDEVICE_F_ALL = WGDEVICE_F_REPLACE_PEERS + WGDEVICE_F_REPLACE_PEERS = 1, }; enum wgpeer_flag { - WGPEER_F_REMOVE_ME = 1U << 0, - WGPEER_F_REPLACE_ALLOWEDIPS = 1U << 1, - WGPEER_F_UPDATE_ONLY = 1U << 2, - __WGPEER_F_ALL = WGPEER_F_REMOVE_ME | WGPEER_F_REPLACE_ALLOWEDIPS | - WGPEER_F_UPDATE_ONLY + WGPEER_F_REMOVE_ME = 1, + WGPEER_F_REPLACE_ALLOWEDIPS = 2, + WGPEER_F_UPDATE_ONLY = 4, }; enum wgallowedip_flag { - WGALLOWEDIP_F_REMOVE_ME = 1U << 0, - __WGALLOWEDIP_F_ALL = WGALLOWEDIP_F_REMOVE_ME + WGALLOWEDIP_F_REMOVE_ME = 1, }; enum wgdevice_attribute { @@ -39,6 +36,7 @@ enum wgdevice_attribute { WGDEVICE_A_LISTEN_PORT, WGDEVICE_A_FWMARK, WGDEVICE_A_PEERS, + __WGDEVICE_A_LAST }; #define WGDEVICE_A_MAX (__WGDEVICE_A_LAST - 1) @@ -55,6 +53,7 @@ enum wgpeer_attribute { WGPEER_A_TX_BYTES, WGPEER_A_ALLOWEDIPS, WGPEER_A_PROTOCOL_VERSION, + __WGPEER_A_LAST }; #define WGPEER_A_MAX (__WGPEER_A_LAST - 1) @@ -65,6 +64,7 @@ enum wgallowedip_attribute { WGALLOWEDIP_A_IPADDR, WGALLOWEDIP_A_CIDR_MASK, WGALLOWEDIP_A_FLAGS, + __WGALLOWEDIP_A_LAST }; #define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1) @@ -77,4 +77,4 @@ enum wg_cmd { }; #define WG_CMD_MAX (__WG_CMD_MAX - 1) -#endif /* _WG_UAPI_WIREGUARD_H */ +#endif /* _UAPI_LINUX_WIREGUARD_H */ -- cgit v1.2.3 From c3859de858aa7ae0d0a5ca21e8ee9792f2f256b6 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 2 Dec 2025 13:44:47 +1100 Subject: psp-sev: Assign numbers to all status codes and add new Make the definitions explicit. Add some more new codes. The following patches will be using SPDM_REQUEST and EXPAND_BUFFER_LENGTH_REQUEST, others are useful for the PSP FW diagnostics. Signed-off-by: Alexey Kardashevskiy Link: https://patch.msgid.link/20251202024449.542361-3-aik@amd.com Acked-by: Tom Lendacky Signed-off-by: Dan Williams --- include/uapi/linux/psp-sev.h | 66 +++++++++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index c2fd324623c4..2b5b042eb73b 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -47,32 +47,32 @@ typedef enum { * with possible values from the specification. */ SEV_RET_NO_FW_CALL = -1, - SEV_RET_SUCCESS = 0, - SEV_RET_INVALID_PLATFORM_STATE, - SEV_RET_INVALID_GUEST_STATE, - SEV_RET_INAVLID_CONFIG, + SEV_RET_SUCCESS = 0, + SEV_RET_INVALID_PLATFORM_STATE = 0x0001, + SEV_RET_INVALID_GUEST_STATE = 0x0002, + SEV_RET_INAVLID_CONFIG = 0x0003, SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, - SEV_RET_INVALID_LEN, - SEV_RET_ALREADY_OWNED, - SEV_RET_INVALID_CERTIFICATE, - SEV_RET_POLICY_FAILURE, - SEV_RET_INACTIVE, - SEV_RET_INVALID_ADDRESS, - SEV_RET_BAD_SIGNATURE, - SEV_RET_BAD_MEASUREMENT, - SEV_RET_ASID_OWNED, - SEV_RET_INVALID_ASID, - SEV_RET_WBINVD_REQUIRED, - SEV_RET_DFFLUSH_REQUIRED, - SEV_RET_INVALID_GUEST, - SEV_RET_INVALID_COMMAND, - SEV_RET_ACTIVE, - SEV_RET_HWSEV_RET_PLATFORM, - SEV_RET_HWSEV_RET_UNSAFE, - SEV_RET_UNSUPPORTED, - SEV_RET_INVALID_PARAM, - SEV_RET_RESOURCE_LIMIT, - SEV_RET_SECURE_DATA_INVALID, + SEV_RET_INVALID_LEN = 0x0004, + SEV_RET_ALREADY_OWNED = 0x0005, + SEV_RET_INVALID_CERTIFICATE = 0x0006, + SEV_RET_POLICY_FAILURE = 0x0007, + SEV_RET_INACTIVE = 0x0008, + SEV_RET_INVALID_ADDRESS = 0x0009, + SEV_RET_BAD_SIGNATURE = 0x000A, + SEV_RET_BAD_MEASUREMENT = 0x000B, + SEV_RET_ASID_OWNED = 0x000C, + SEV_RET_INVALID_ASID = 0x000D, + SEV_RET_WBINVD_REQUIRED = 0x000E, + SEV_RET_DFFLUSH_REQUIRED = 0x000F, + SEV_RET_INVALID_GUEST = 0x0010, + SEV_RET_INVALID_COMMAND = 0x0011, + SEV_RET_ACTIVE = 0x0012, + SEV_RET_HWSEV_RET_PLATFORM = 0x0013, + SEV_RET_HWSEV_RET_UNSAFE = 0x0014, + SEV_RET_UNSUPPORTED = 0x0015, + SEV_RET_INVALID_PARAM = 0x0016, + SEV_RET_RESOURCE_LIMIT = 0x0017, + SEV_RET_SECURE_DATA_INVALID = 0x0018, SEV_RET_INVALID_PAGE_SIZE = 0x0019, SEV_RET_INVALID_PAGE_STATE = 0x001A, SEV_RET_INVALID_MDATA_ENTRY = 0x001B, @@ -87,6 +87,22 @@ typedef enum { SEV_RET_RESTORE_REQUIRED = 0x0025, SEV_RET_RMP_INITIALIZATION_FAILED = 0x0026, SEV_RET_INVALID_KEY = 0x0027, + SEV_RET_SHUTDOWN_INCOMPLETE = 0x0028, + SEV_RET_INCORRECT_BUFFER_LENGTH = 0x0030, + SEV_RET_EXPAND_BUFFER_LENGTH_REQUEST = 0x0031, + SEV_RET_SPDM_REQUEST = 0x0032, + SEV_RET_SPDM_ERROR = 0x0033, + SEV_RET_SEV_STATUS_ERR_IN_DEV_CONN = 0x0035, + SEV_RET_SEV_STATUS_INVALID_DEV_CTX = 0x0036, + SEV_RET_SEV_STATUS_INVALID_TDI_CTX = 0x0037, + SEV_RET_SEV_STATUS_INVALID_TDI = 0x0038, + SEV_RET_SEV_STATUS_RECLAIM_REQUIRED = 0x0039, + SEV_RET_IN_USE = 0x003A, + SEV_RET_SEV_STATUS_INVALID_DEV_STATE = 0x003B, + SEV_RET_SEV_STATUS_INVALID_TDI_STATE = 0x003C, + SEV_RET_SEV_STATUS_DEV_CERT_CHANGED = 0x003D, + SEV_RET_SEV_STATUS_RESYNC_REQ = 0x003E, + SEV_RET_SEV_STATUS_RESPONSE_TOO_LARGE = 0x003F, SEV_RET_MAX, } sev_ret_code; -- cgit v1.2.3 From f7231cff1f3ff8259bef02dc4999bc132abf29cf Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Wed, 3 Dec 2025 08:55:34 +0000 Subject: media: uapi: c3-isp: Fix documentation warning Building htmldocs generates a warning: WARNING: include/uapi/linux/media/amlogic/c3-isp-config.h:199 error: Cannot parse struct or union! Which correctly highlights that the c3_isp_params_block_header symbol is wrongly documented as a struct while it's a plain #define instead. Fix this by removing the 'struct' identifier from the documentation of the c3_isp_params_block_header symbol. [ribalda: Add Closes:] Reported-by: Stephen Rothwell Closes: https://lore.kernel.org/all/20251127131425.4b5b6644@canb.auug.org.au/ Fixes: 45662082855c ("media: uapi: Convert Amlogic C3 to V4L2 extensible params") Cc: stable@vger.kernel.org Signed-off-by: Jacopo Mondi Signed-off-by: Ricardo Ribalda Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media/amlogic/c3-isp-config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/amlogic/c3-isp-config.h b/include/uapi/linux/media/amlogic/c3-isp-config.h index 0a3c1cc55ccb..92db5dcdda18 100644 --- a/include/uapi/linux/media/amlogic/c3-isp-config.h +++ b/include/uapi/linux/media/amlogic/c3-isp-config.h @@ -186,7 +186,7 @@ enum c3_isp_params_block_type { #define C3_ISP_PARAMS_BLOCK_FL_ENABLE V4L2_ISP_PARAMS_FL_BLOCK_ENABLE /** - * struct c3_isp_params_block_header - C3 ISP parameter block header + * c3_isp_params_block_header - C3 ISP parameter block header * * This structure represents the common part of all the ISP configuration * blocks and is identical to :c:type:`v4l2_isp_params_block_header`. -- cgit v1.2.3 From 22a1ffea5f805dfa21b64d1c7b5fe39c0c78c997 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Mon, 1 Dec 2025 16:43:28 -0500 Subject: block: add IOC_PR_READ_KEYS ioctl Add a Persistent Reservations ioctl to read the list of currently registered reservation keys. This calls the pr_ops->read_keys() function that was previously added in commit c787f1baa503 ("block: Add PR callouts for read keys and reservation") but was only used by the in-kernel SCSI target so far. The IOC_PR_READ_KEYS ioctl is necessary so that userspace applications that rely on Persistent Reservations ioctls have a way of inspecting the current state. Cluster managers and validation tests need this functionality. Signed-off-by: Stefan Hajnoczi Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/uapi/linux/pr.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h index d8126415966f..fcb74eab92c8 100644 --- a/include/uapi/linux/pr.h +++ b/include/uapi/linux/pr.h @@ -56,6 +56,12 @@ struct pr_clear { __u32 __pad; }; +struct pr_read_keys { + __u32 generation; + __u32 num_keys; + __u64 keys_ptr; +}; + #define PR_FL_IGNORE_KEY (1 << 0) /* ignore existing key */ #define IOC_PR_REGISTER _IOW('p', 200, struct pr_registration) @@ -64,5 +70,6 @@ struct pr_clear { #define IOC_PR_PREEMPT _IOW('p', 203, struct pr_preempt) #define IOC_PR_PREEMPT_ABORT _IOW('p', 204, struct pr_preempt) #define IOC_PR_CLEAR _IOW('p', 205, struct pr_clear) +#define IOC_PR_READ_KEYS _IOWR('p', 206, struct pr_read_keys) #endif /* _UAPI_PR_H */ -- cgit v1.2.3 From 3e2cb9ee76c27f57bfdb7b4753b909594d4fa31a Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Mon, 1 Dec 2025 16:43:29 -0500 Subject: block: add IOC_PR_READ_RESERVATION ioctl Add a Persistent Reservations ioctl to read the current reservation. This calls the pr_ops->read_reservation() function that was previously added in commit c787f1baa503 ("block: Add PR callouts for read keys and reservation") but was only used by the in-kernel SCSI target so far. The IOC_PR_READ_RESERVATION ioctl is necessary so that userspace applications that rely on Persistent Reservations ioctls have a way of inspecting the current state. Cluster managers and validation tests need this functionality. Signed-off-by: Stefan Hajnoczi Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/uapi/linux/pr.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h index fcb74eab92c8..847f3051057a 100644 --- a/include/uapi/linux/pr.h +++ b/include/uapi/linux/pr.h @@ -62,6 +62,12 @@ struct pr_read_keys { __u64 keys_ptr; }; +struct pr_read_reservation { + __u64 key; + __u32 generation; + __u32 type; +}; + #define PR_FL_IGNORE_KEY (1 << 0) /* ignore existing key */ #define IOC_PR_REGISTER _IOW('p', 200, struct pr_registration) @@ -71,5 +77,6 @@ struct pr_read_keys { #define IOC_PR_PREEMPT_ABORT _IOW('p', 204, struct pr_preempt) #define IOC_PR_CLEAR _IOW('p', 205, struct pr_clear) #define IOC_PR_READ_KEYS _IOWR('p', 206, struct pr_read_keys) +#define IOC_PR_READ_RESERVATION _IOR('p', 207, struct pr_read_reservation) #endif /* _UAPI_PR_H */ -- cgit v1.2.3 From fe93446b5ebdaa89a8f97b15668c077921a65140 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 3 Dec 2025 14:57:57 +0100 Subject: vfs: use UAPI types for new struct delegation definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using libc types and headers from the UAPI headers is problematic as it introduces a dependency on a full C toolchain. Use the fixed-width integer types provided by the UAPI headers instead. Fixes: 1602bad16d7d ("vfs: expose delegation support to userland") Fixes: 4be9e04ebf75 ("vfs: add needed headers for new struct delegation definition") Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20251203-uapi-fcntl-v1-1-490c67bf3425@linutronix.de Acked-by: Arnd Bergmann Acked-by: Jeff Layton Signed-off-by: Christian Brauner --- include/uapi/linux/fcntl.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 5e277fd955aa..aadfbf6e0cb3 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -4,11 +4,7 @@ #include #include -#ifdef __KERNEL__ #include -#else -#include -#endif #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) @@ -90,9 +86,9 @@ /* Argument structure for F_GETDELEG and F_SETDELEG */ struct delegation { - uint32_t d_flags; /* Must be 0 */ - uint16_t d_type; /* F_RDLCK, F_WRLCK, F_UNLCK */ - uint16_t __pad; /* Must be 0 */ + __u32 d_flags; /* Must be 0 */ + __u16 d_type; /* F_RDLCK, F_WRLCK, F_UNLCK */ + __u16 __pad; /* Must be 0 */ }; /* -- cgit v1.2.3 From 7bfe3b8ea6e30437e01fcb8e4f56ef6e4d986d0f Mon Sep 17 00:00:00 2001 From: Naman Jain Date: Thu, 13 Nov 2025 04:41:49 +0000 Subject: Drivers: hv: Introduce mshv_vtl driver Provide an interface for Virtual Machine Monitor like OpenVMM and its use as OpenHCL paravisor to control VTL0 (Virtual trust Level). Expose devices and support IOCTLs for features like VTL creation, VTL0 memory management, context switch, making hypercalls, mapping VTL0 address space to VTL2 userspace, getting new VMBus messages and channel events in VTL2 etc. Co-developed-by: Roman Kisel Signed-off-by: Roman Kisel Co-developed-by: Saurabh Sengar Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Signed-off-by: Naman Jain Signed-off-by: Wei Liu --- include/uapi/linux/mshv.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mshv.h b/include/uapi/linux/mshv.h index b645d17cc531..dee3ece28ce5 100644 --- a/include/uapi/linux/mshv.h +++ b/include/uapi/linux/mshv.h @@ -322,4 +322,84 @@ struct mshv_get_set_vp_state { * #define MSHV_ROOT_HVCALL _IOWR(MSHV_IOCTL, 0x07, struct mshv_root_hvcall) */ +/* Structure definitions, macros and IOCTLs for mshv_vtl */ + +#define MSHV_CAP_CORE_API_STABLE 0x0 +#define MSHV_CAP_REGISTER_PAGE 0x1 +#define MSHV_CAP_VTL_RETURN_ACTION 0x2 +#define MSHV_CAP_DR6_SHARED 0x3 +#define MSHV_MAX_RUN_MSG_SIZE 256 + +struct mshv_vp_registers { + __u32 count; /* supports only 1 register at a time */ + __u32 reserved; /* Reserved for alignment or future use */ + __u64 regs_ptr; /* pointer to struct hv_register_assoc */ +}; + +struct mshv_vtl_set_eventfd { + __s32 fd; + __u32 flag; +}; + +struct mshv_vtl_signal_event { + __u32 connection_id; + __u32 flag; +}; + +struct mshv_vtl_sint_post_msg { + __u64 message_type; + __u32 connection_id; + __u32 payload_size; /* Must not exceed HV_MESSAGE_PAYLOAD_BYTE_COUNT */ + __u64 payload_ptr; /* pointer to message payload (bytes) */ +}; + +struct mshv_vtl_ram_disposition { + __u64 start_pfn; + __u64 last_pfn; +}; + +struct mshv_vtl_set_poll_file { + __u32 cpu; + __u32 fd; +}; + +struct mshv_vtl_hvcall_setup { + __u64 bitmap_array_size; /* stores number of bytes */ + __u64 allow_bitmap_ptr; +}; + +struct mshv_vtl_hvcall { + __u64 control; /* Hypercall control code */ + __u64 input_size; /* Size of the input data */ + __u64 input_ptr; /* Pointer to the input struct */ + __u64 status; /* Status of the hypercall (output) */ + __u64 output_size; /* Size of the output data */ + __u64 output_ptr; /* Pointer to the output struct */ +}; + +struct mshv_sint_mask { + __u8 mask; + __u8 reserved[7]; +}; + +/* /dev/mshv device IOCTL */ +#define MSHV_CHECK_EXTENSION _IOW(MSHV_IOCTL, 0x00, __u32) + +/* vtl device */ +#define MSHV_CREATE_VTL _IOR(MSHV_IOCTL, 0x1D, char) +#define MSHV_ADD_VTL0_MEMORY _IOW(MSHV_IOCTL, 0x21, struct mshv_vtl_ram_disposition) +#define MSHV_SET_POLL_FILE _IOW(MSHV_IOCTL, 0x25, struct mshv_vtl_set_poll_file) +#define MSHV_RETURN_TO_LOWER_VTL _IO(MSHV_IOCTL, 0x27) +#define MSHV_GET_VP_REGISTERS _IOWR(MSHV_IOCTL, 0x05, struct mshv_vp_registers) +#define MSHV_SET_VP_REGISTERS _IOW(MSHV_IOCTL, 0x06, struct mshv_vp_registers) + +/* VMBus device IOCTLs */ +#define MSHV_SINT_SIGNAL_EVENT _IOW(MSHV_IOCTL, 0x22, struct mshv_vtl_signal_event) +#define MSHV_SINT_POST_MESSAGE _IOW(MSHV_IOCTL, 0x23, struct mshv_vtl_sint_post_msg) +#define MSHV_SINT_SET_EVENTFD _IOW(MSHV_IOCTL, 0x24, struct mshv_vtl_set_eventfd) +#define MSHV_SINT_PAUSE_MESSAGE_STREAM _IOW(MSHV_IOCTL, 0x25, struct mshv_sint_mask) + +/* hv_hvcall device */ +#define MSHV_HVCALL_SETUP _IOW(MSHV_IOCTL, 0x1E, struct mshv_vtl_hvcall_setup) +#define MSHV_HVCALL _IOWR(MSHV_IOCTL, 0x1F, struct mshv_vtl_hvcall) #endif -- cgit v1.2.3 From b5709f6d26d65f6bb9711f4b5f98469fd507cb5b Mon Sep 17 00:00:00 2001 From: Amery Hung Date: Wed, 3 Dec 2025 15:37:44 -0800 Subject: bpf: Support associating BPF program with struct_ops Add a new BPF command BPF_PROG_ASSOC_STRUCT_OPS to allow associating a BPF program with a struct_ops map. This command takes a file descriptor of a struct_ops map and a BPF program and set prog->aux->st_ops_assoc to the kdata of the struct_ops map. The command does not accept a struct_ops program nor a non-struct_ops map. Programs of a struct_ops map is automatically associated with the map during map update. If a program is shared between two struct_ops maps, prog->aux->st_ops_assoc will be poisoned to indicate that the associated struct_ops is ambiguous. The pointer, once poisoned, cannot be reset since we have lost track of associated struct_ops. For other program types, the associated struct_ops map, once set, cannot be changed later. This restriction may be lifted in the future if there is a use case. A kernel helper bpf_prog_get_assoc_struct_ops() can be used to retrieve the associated struct_ops pointer. The returned pointer, if not NULL, is guaranteed to be valid and point to a fully updated struct_ops struct. For struct_ops program reused in multiple struct_ops map, the return will be NULL. prog->aux->st_ops_assoc is protected by bumping the refcount for non-struct_ops programs and RCU for struct_ops programs. Since it would be inefficient to track programs associated with a struct_ops map, every non-struct_ops program will bump the refcount of the map to make sure st_ops_assoc stays valid. For a struct_ops program, it is protected by RCU as map_free will wait for an RCU grace period before disassociating the program with the map. The helper must be called in BPF program context or RCU read-side critical section. struct_ops implementers should note that the struct_ops returned may not be initialized nor attached yet. The struct_ops implementer will be responsible for tracking and checking the state of the associated struct_ops map if the use case expects an initialized or attached struct_ops. Signed-off-by: Amery Hung Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20251203233748.668365-3-ameryhung@gmail.com --- include/uapi/linux/bpf.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f8d8513eda27..84ced3ed2d21 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -918,6 +918,16 @@ union bpf_iter_link_info { * Number of bytes read from the stream on success, or -1 if an * error occurred (in which case, *errno* is set appropriately). * + * BPF_PROG_ASSOC_STRUCT_OPS + * Description + * Associate a BPF program with a struct_ops map. The struct_ops + * map is identified by *map_fd* and the BPF program is + * identified by *prog_fd*. + * + * Return + * 0 on success or -1 if an error occurred (in which case, + * *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -974,6 +984,7 @@ enum bpf_cmd { BPF_PROG_BIND_MAP, BPF_TOKEN_CREATE, BPF_PROG_STREAM_READ_BY_FD, + BPF_PROG_ASSOC_STRUCT_OPS, __MAX_BPF_CMD, }; @@ -1894,6 +1905,12 @@ union bpf_attr { __u32 prog_fd; } prog_stream_read; + struct { + __u32 map_fd; + __u32 prog_fd; + __u32 flags; + } prog_assoc_struct_ops; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From cc6b66d661fda4fb94c0099dd92b83f8de5c1bf4 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Thu, 21 Aug 2025 17:22:44 +0800 Subject: amdkfd: introduce new ioctl AMDKFD_IOC_CREATE_PROCESS This commit implemetns a new ioctl AMDKFD_IOC_CREATE_PROCESS that creates a new secondary kfd_progress on the FD. To keep backward compatibility, userspace programs need to invoke this ioctl explicitly on a FD to create a secondary kfd_process which replacing its primary kfd_process. This commit bumps ioctl minor version. Signed-off-by: Zhu Lingshan Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 5d1727a6d040..84aa24c02715 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -44,9 +44,10 @@ * - 1.16 - Add contiguous VRAM allocation flag * - 1.17 - Add SDMA queue creation with target SDMA engine ID * - 1.18 - Rename pad in set_memory_policy_args to misc_process_flag + * - 1.19 - Add a new ioctl to craete secondary kfd processes */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 18 +#define KFD_IOCTL_MINOR_VERSION 19 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -1671,7 +1672,10 @@ struct kfd_ioctl_dbg_trap_args { #define AMDKFD_IOC_DBG_TRAP \ AMDKFD_IOWR(0x26, struct kfd_ioctl_dbg_trap_args) +#define AMDKFD_IOC_CREATE_PROCESS \ + AMDKFD_IO(0x27) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x27 +#define AMDKFD_COMMAND_END 0x28 #endif -- cgit v1.2.3 From 7a5fb05b5b18e531989aa55b10dfa4be0633207e Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 5 Dec 2025 08:04:41 -0600 Subject: amdkfd: Bump ABI to indicate presence of Trap handler support for expert scheduling commit 0f0c8a6983db ("drm/amdkfd: Trap handler support for expert scheduling mode") introduced support for a trap handler when expert scheduling mode. However userspace needs to know whether or not a trap handler support is present. Bump the KFD IOCTL API so that userspace can key off this to decide. Suggested-by: Stella Laurenzo Fixes: 423888879412 ("drm/amdkfd: Trap handler support for expert scheduling mode") Reviewed-by: Kent Russell Signed-off-by: Mario Limonciello 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 84aa24c02715..4d0c1a53f9d5 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -45,9 +45,10 @@ * - 1.17 - Add SDMA queue creation with target SDMA engine ID * - 1.18 - Rename pad in set_memory_policy_args to misc_process_flag * - 1.19 - Add a new ioctl to craete secondary kfd processes + * - 1.20 - Trap handler support for expert scheduling mode available */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 19 +#define KFD_IOCTL_MINOR_VERSION 20 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From e56cadaa27fd156106c5583ed98976927c6febc9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 6 Dec 2025 16:47:40 -0800 Subject: ynl: add regen hint to new headers Recent commit 68e83f347266 ("tools: ynl-gen: add regeneration comment") added a hint how to regenerate the code to the headers. Update the new headers from this release cycle to also include it. Reviewed-by: Simon Horman Link: https://patch.msgid.link/20251207004740.1657799-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/energy_model.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/energy_model.h b/include/uapi/linux/energy_model.h index 4ec4c0eabbbb..0bcad967854f 100644 --- a/include/uapi/linux/energy_model.h +++ b/include/uapi/linux/energy_model.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/em.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_ENERGY_MODEL_H #define _UAPI_LINUX_ENERGY_MODEL_H -- cgit v1.2.3 From 0ace3297a7301911e52d8195cb1006414897c859 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 5 Dec 2025 19:55:14 +0100 Subject: mptcp: pm: ignore unknown endpoint flags Before this patch, the kernel was saving any flags set by the userspace, even unknown ones. This doesn't cause critical issues because the kernel is only looking at specific ones. But on the other hand, endpoints dumps could tell the userspace some recent flags seem to be supported on older kernel versions. Instead, ignore all unknown flags when parsing them. By doing that, the userspace can continue to set unsupported flags, but it has a way to verify what is supported by the kernel. Note that it sounds better to continue accepting unsupported flags not to change the behaviour, but also that eases things on the userspace side by adding "optional" endpoint types only supported by newer kernel versions without having to deal with the different kernel versions. A note for the backports: there will be conflicts in mptcp.h on older versions not having the mentioned flags, the new line should still be added last, and the '5' needs to be adapted to have the same value as the last entry. Fixes: 01cacb00b35c ("mptcp: add netlink-based PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20251205-net-mptcp-misc-fixes-6-19-rc1-v1-1-9e4781a6c1b8@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 04eea6d1d0a9..72a5d030154e 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -40,6 +40,7 @@ #define MPTCP_PM_ADDR_FLAG_FULLMESH _BITUL(3) #define MPTCP_PM_ADDR_FLAG_IMPLICIT _BITUL(4) #define MPTCP_PM_ADDR_FLAG_LAMINAR _BITUL(5) +#define MPTCP_PM_ADDR_FLAGS_MASK GENMASK(5, 0) struct mptcp_info { __u8 mptcpi_subflows; -- cgit v1.2.3 From 0e5032237ee5530147fbdf33134297e1490d5ec3 Mon Sep 17 00:00:00 2001 From: Bhavik Sachdev Date: Sat, 29 Nov 2025 14:41:21 +0530 Subject: statmount: accept fd as a parameter Extend `struct mnt_id_req` to take in a fd and introduce STATMOUNT_BY_FD flag. When a valid fd is provided and STATMOUNT_BY_FD is set, statmount will return mountinfo about the mount the fd is on. This even works for "unmounted" mounts (mounts that have been umounted using umount2(mnt, MNT_DETACH)), if you have access to a file descriptor on that mount. These "umounted" mounts will have no mountpoint and no valid mount namespace. Hence, we unset the STATMOUNT_MNT_POINT and STATMOUNT_MNT_NS_ID in statmount.mask for "unmounted" mounts. In case of STATMOUNT_BY_FD, given that we already have access to an fd on the mount, accessing mount information without a capability check seems fine because of the following reasons: - All fs related information is available via fstatfs() without any capability check. - Mount information is also available via /proc/pid/mountinfo (without any capability check). - Given that we have access to a fd on the mount which tells us that we had access to the mount at some point (or someone that had access gave us the fd). So, we should be able to access mount info. Co-developed-by: Pavel Tikhomirov Signed-off-by: Pavel Tikhomirov Signed-off-by: Bhavik Sachdev Link: https://patch.msgid.link/20251129091455.757724-3-b.sachdev1904@gmail.com Acked-by: Andrei Vagin Signed-off-by: Christian Brauner --- include/uapi/linux/mount.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 5d3f8c9e3a62..18c624405268 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -197,7 +197,10 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 mnt_ns_fd; + union { + __u32 mnt_ns_fd; + __u32 mnt_fd; + }; __u64 mnt_id; __u64 param; __u64 mnt_ns_id; @@ -232,4 +235,9 @@ struct mnt_id_req { #define LSMT_ROOT 0xffffffffffffffff /* root mount */ #define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ +/* + * @flag bits for statmount(2) + */ +#define STATMOUNT_BY_FD 0x00000001U /* want mountinfo for given fd */ + #endif /* _UAPI_LINUX_MOUNT_H */ -- cgit v1.2.3 From e83f63da2ac776fbc30861e4ce8b798df6ee8a7a Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Mon, 23 Jun 2025 14:12:58 -0400 Subject: drm/amdkfd: allow debug subscription to lds violations on gfx 1250 GFX 1250 allows the debugger to subcribe to LDS out-of-range read/write memory violations. Bump IOCTL minor version and flag KFD capabilities for enablement hint. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 4 +++- include/uapi/linux/kfd_sysfs.h | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 4d0c1a53f9d5..6e91875c10ba 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -46,9 +46,10 @@ * - 1.18 - Rename pad in set_memory_policy_args to misc_process_flag * - 1.19 - Add a new ioctl to craete secondary kfd processes * - 1.20 - Trap handler support for expert scheduling mode available + * - 1.21 - Debugger support to subscribe to LDS out-of-address exceptions */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 20 +#define KFD_IOCTL_MINOR_VERSION 21 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -947,6 +948,7 @@ enum kfd_dbg_trap_address_watch_mode { enum kfd_dbg_trap_flags { KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP = 1, KFD_DBG_TRAP_FLAG_SINGLE_ALU_OP = 2, + KFD_DBG_TRAP_FLAG_LDS_OUT_OF_ADDR_RANGE = 4 }; /* Trap exceptions */ diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h index 1125fe47959f..0b6ce2f3c887 100644 --- a/include/uapi/linux/kfd_sysfs.h +++ b/include/uapi/linux/kfd_sysfs.h @@ -64,7 +64,8 @@ #define HSA_CAP_RESERVED 0x000f8000 #define HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED 0x00000001 -#define HSA_CAP2_RESERVED 0xfffffffe +#define HSA_CAP2_TRAP_DEBUG_LDS_OUT_OF_ADDR_RANGE_SUPPORTED 0x00000002 +#define HSA_CAP2_RESERVED 0xfffffffc /* debug_prop bits in node properties */ #define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK 0x0000000f -- cgit v1.2.3 From a58383fa45c706bda3bf4a1955c3a0327dbec7e7 Mon Sep 17 00:00:00 2001 From: Deepanshu Kartikey Date: Wed, 17 Dec 2025 07:17:12 +0530 Subject: block: add allocation size check in blkdev_pr_read_keys() blkdev_pr_read_keys() takes num_keys from userspace and uses it to calculate the allocation size for keys_info via struct_size(). While there is a check for SIZE_MAX (integer overflow), there is no upper bound validation on the allocation size itself. A malicious or buggy userspace can pass a large num_keys value that doesn't trigger overflow but still results in an excessive allocation attempt, causing a warning in the page allocator when the order exceeds MAX_PAGE_ORDER. Fix this by introducing PR_KEYS_MAX to limit the number of keys to a sane value. This makes the SIZE_MAX check redundant, so remove it. Also switch to kvzalloc/kvfree to handle larger allocations gracefully. Fixes: 22a1ffea5f80 ("block: add IOC_PR_READ_KEYS ioctl") Tested-by: syzbot+660d079d90f8a1baf54d@syzkaller.appspotmail.com Reported-by: syzbot+660d079d90f8a1baf54d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=660d079d90f8a1baf54d Link: https://lore.kernel.org/all/20251212013510.3576091-1-kartikey406@gmail.com/T/ [v1] Signed-off-by: Deepanshu Kartikey Reviewed-by: Martin K. Petersen Reviewed-by: Stefan Hajnoczi Signed-off-by: Jens Axboe --- include/uapi/linux/pr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h index 847f3051057a..f0ecb1677317 100644 --- a/include/uapi/linux/pr.h +++ b/include/uapi/linux/pr.h @@ -79,4 +79,6 @@ struct pr_read_reservation { #define IOC_PR_READ_KEYS _IOWR('p', 206, struct pr_read_keys) #define IOC_PR_READ_RESERVATION _IOR('p', 207, struct pr_read_reservation) +#define PR_KEYS_MAX (1u << 16) + #endif /* _UAPI_PR_H */ -- cgit v1.2.3 From cb8fe62f87ad21f4c174aec480694c9b4b8b01c4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 20 Dec 2025 03:04:26 +0900 Subject: nilfs2: convert nilfs_super_block to kernel-doc Eliminate 40+ kernel-doc warnings in nilfs2_ondisk.h by converting all of the struct member comments to kernel-doc comments. Fix one misnamed struct member in nilfs_direct_node. Object files before and after are the same size and content. Examples of warnings: Warning: include/uapi/linux/nilfs2_ondisk.h:202 struct member 's_rev_level' not described in 'nilfs_super_block' Warning: include/uapi/linux/nilfs2_ondisk.h:202 struct member 's_minor_rev_level' not described in 'nilfs_super_block' Warning: include/uapi/linux/nilfs2_ondisk.h:202 struct member 's_magic' not described in 'nilfs_super_block' Warning: include/uapi/linux/nilfs2_ondisk.h:202 struct member 's_bytes' not described in 'nilfs_super_block' Warning: include/uapi/linux/nilfs2_ondisk.h:202 struct member 's_flags' not described in 'nilfs_super_block' Signed-off-by: Randy Dunlap Signed-off-by: Ryusuke Konishi Signed-off-by: Viacheslav Dubeyko --- include/uapi/linux/nilfs2_ondisk.h | 163 ++++++++++++++++++++++--------------- 1 file changed, 97 insertions(+), 66 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nilfs2_ondisk.h b/include/uapi/linux/nilfs2_ondisk.h index 3196cc44a002..b3442b16ff6a 100644 --- a/include/uapi/linux/nilfs2_ondisk.h +++ b/include/uapi/linux/nilfs2_ondisk.h @@ -133,73 +133,104 @@ struct nilfs_super_root { /** * struct nilfs_super_block - structure of super block on disk + * @s_rev_level: Revision level + * @s_minor_rev_level: minor revision level + * @s_magic: Magic signature + * @s_bytes: Bytes count of CRC calculation for + * this structure. s_reserved is excluded. + * @s_flags: flags + * @s_crc_seed: Seed value of CRC calculation + * @s_sum: Check sum of super block + * @s_log_block_size: Block size represented as follows: + * blocksize = 1 << (s_log_block_size + 10) + * @s_nsegments: Number of segments in filesystem + * @s_dev_size: block device size in bytes + * @s_first_data_block: 1st seg disk block number + * @s_blocks_per_segment: number of blocks per full segment + * @s_r_segments_percentage: Reserved segments percentage + * @s_last_cno: Last checkpoint number + * @s_last_pseg: disk block addr pseg written last + * @s_last_seq: seq. number of seg written last + * @s_free_blocks_count: Free blocks count + * @s_ctime: Creation time (execution time of newfs) + * @s_mtime: Mount time + * @s_wtime: Write time + * @s_mnt_count: Mount count + * @s_max_mnt_count: Maximal mount count + * @s_state: File system state + * @s_errors: Behaviour when detecting errors + * @s_lastcheck: time of last check + * @s_checkinterval: max. time between checks + * @s_creator_os: OS + * @s_def_resuid: Default uid for reserved blocks + * @s_def_resgid: Default gid for reserved blocks + * @s_first_ino: First non-reserved inode + * @s_inode_size: Size of an inode + * @s_dat_entry_size: Size of a dat entry + * @s_checkpoint_size: Size of a checkpoint + * @s_segment_usage_size: Size of a segment usage + * @s_uuid: 128-bit uuid for volume + * @s_volume_name: volume name + * @s_c_interval: Commit interval of segment + * @s_c_block_max: Threshold of data amount for the + * segment construction + * @s_feature_compat: Compatible feature set + * @s_feature_compat_ro: Read-only compatible feature set + * @s_feature_incompat: Incompatible feature set + * @s_reserved: padding to the end of the block */ struct nilfs_super_block { -/*00*/ __le32 s_rev_level; /* Revision level */ - __le16 s_minor_rev_level; /* minor revision level */ - __le16 s_magic; /* Magic signature */ - - __le16 s_bytes; /* - * Bytes count of CRC calculation - * for this structure. s_reserved - * is excluded. - */ - __le16 s_flags; /* flags */ - __le32 s_crc_seed; /* Seed value of CRC calculation */ -/*10*/ __le32 s_sum; /* Check sum of super block */ - - __le32 s_log_block_size; /* - * Block size represented as follows - * blocksize = - * 1 << (s_log_block_size + 10) - */ - __le64 s_nsegments; /* Number of segments in filesystem */ -/*20*/ __le64 s_dev_size; /* block device size in bytes */ - __le64 s_first_data_block; /* 1st seg disk block number */ -/*30*/ __le32 s_blocks_per_segment; /* number of blocks per full segment */ - __le32 s_r_segments_percentage; /* Reserved segments percentage */ - - __le64 s_last_cno; /* Last checkpoint number */ -/*40*/ __le64 s_last_pseg; /* disk block addr pseg written last */ - __le64 s_last_seq; /* seq. number of seg written last */ -/*50*/ __le64 s_free_blocks_count; /* Free blocks count */ - - __le64 s_ctime; /* - * Creation time (execution time of - * newfs) - */ -/*60*/ __le64 s_mtime; /* Mount time */ - __le64 s_wtime; /* Write time */ -/*70*/ __le16 s_mnt_count; /* Mount count */ - __le16 s_max_mnt_count; /* Maximal mount count */ - __le16 s_state; /* File system state */ - __le16 s_errors; /* Behaviour when detecting errors */ - __le64 s_lastcheck; /* time of last check */ - -/*80*/ __le32 s_checkinterval; /* max. time between checks */ - __le32 s_creator_os; /* OS */ - __le16 s_def_resuid; /* Default uid for reserved blocks */ - __le16 s_def_resgid; /* Default gid for reserved blocks */ - __le32 s_first_ino; /* First non-reserved inode */ - -/*90*/ __le16 s_inode_size; /* Size of an inode */ - __le16 s_dat_entry_size; /* Size of a dat entry */ - __le16 s_checkpoint_size; /* Size of a checkpoint */ - __le16 s_segment_usage_size; /* Size of a segment usage */ - -/*98*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ -/*A8*/ char s_volume_name[80] /* volume name */ - __kernel_nonstring; - -/*F8*/ __le32 s_c_interval; /* Commit interval of segment */ - __le32 s_c_block_max; /* - * Threshold of data amount for - * the segment construction - */ -/*100*/ __le64 s_feature_compat; /* Compatible feature set */ - __le64 s_feature_compat_ro; /* Read-only compatible feature set */ - __le64 s_feature_incompat; /* Incompatible feature set */ - __u32 s_reserved[186]; /* padding to the end of the block */ +/*00*/ __le32 s_rev_level; + __le16 s_minor_rev_level; + __le16 s_magic; + + __le16 s_bytes; + __le16 s_flags; + __le32 s_crc_seed; +/*10*/ __le32 s_sum; + + __le32 s_log_block_size; + __le64 s_nsegments; +/*20*/ __le64 s_dev_size; + __le64 s_first_data_block; +/*30*/ __le32 s_blocks_per_segment; + __le32 s_r_segments_percentage; + + __le64 s_last_cno; +/*40*/ __le64 s_last_pseg; + __le64 s_last_seq; +/*50*/ __le64 s_free_blocks_count; + + __le64 s_ctime; +/*60*/ __le64 s_mtime; + __le64 s_wtime; +/*70*/ __le16 s_mnt_count; + __le16 s_max_mnt_count; + __le16 s_state; + __le16 s_errors; + __le64 s_lastcheck; + +/*80*/ __le32 s_checkinterval; + __le32 s_creator_os; + __le16 s_def_resuid; + __le16 s_def_resgid; + __le32 s_first_ino; + +/*90*/ __le16 s_inode_size; + __le16 s_dat_entry_size; + __le16 s_checkpoint_size; + __le16 s_segment_usage_size; + +/*98*/ __u8 s_uuid[16]; +/*A8*/ char s_volume_name[80] __kernel_nonstring; + +/*F8*/ __le32 s_c_interval; + __le32 s_c_block_max; + +/*100*/ __le64 s_feature_compat; + __le64 s_feature_compat_ro; + __le64 s_feature_incompat; + __u32 s_reserved[186]; }; /* @@ -449,7 +480,7 @@ struct nilfs_btree_node { /** * struct nilfs_direct_node - header of built-in bmap array * @dn_flags: flags - * @dn_pad: padding + * @pad: padding */ struct nilfs_direct_node { __u8 dn_flags; -- cgit v1.2.3 From 6fd8a09f48d6fee184207f4e15e939898a3947f9 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 20 Dec 2025 03:04:27 +0900 Subject: nilfs2: fix missing struct keywords in nilfs2_api.h kernel-doc Eliminate the following kernel-doc warnings in nilfs2_api.h: Warning: include/uapi/linux/nilfs2_api.h:65 cannot understand function prototype: 'struct nilfs_suinfo' Warning: include/uapi/linux/nilfs2_api.h:101 cannot understand function prototype: 'struct nilfs_suinfo_update' This ensures that the documentation for nilfs_suinfo and nilfs_suinfo_update is correctly parsed and generated by adding the missing 'struct' keyword to their kernel-doc comments. Signed-off-by: Ryusuke Konishi Signed-off-by: Viacheslav Dubeyko --- include/uapi/linux/nilfs2_api.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nilfs2_api.h b/include/uapi/linux/nilfs2_api.h index 8b9b89104f3d..d1b6fcde2fb8 100644 --- a/include/uapi/linux/nilfs2_api.h +++ b/include/uapi/linux/nilfs2_api.h @@ -58,7 +58,7 @@ NILFS_CPINFO_FNS(INVALID, invalid) NILFS_CPINFO_FNS(MINOR, minor) /** - * nilfs_suinfo - segment usage information + * struct nilfs_suinfo - segment usage information * @sui_lastmod: timestamp of last modification * @sui_nblocks: number of written blocks in segment * @sui_flags: segment usage flags @@ -93,7 +93,7 @@ static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si) } /** - * nilfs_suinfo_update - segment usage information update + * struct nilfs_suinfo_update - segment usage information update * @sup_segnum: segment number * @sup_flags: flags for which fields are active in sup_sui * @sup_reserved: reserved necessary for alignment -- cgit v1.2.3 From 98b9f207afa53aff2edb0e52910c4348b456b37d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 22 Dec 2025 09:04:13 +0100 Subject: dmaengine: idxd: uapi: use UAPI types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using libc types and headers from the UAPI headers is problematic as it introduces a dependency on a full C toolchain. Use the fixed-width integer types provided by the UAPI headers instead. Signed-off-by: Thomas Weißschuh Acked-by: Arnd Bergmann Link: https://patch.msgid.link/20251222-uapi-idxd-v1-1-baa183adb20d@linutronix.de Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 270 +++++++++++++++++++++++----------------------- 1 file changed, 133 insertions(+), 137 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 3d1987e1bb2d..fdcc8eefb925 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -3,11 +3,7 @@ #ifndef _USR_IDXD_H_ #define _USR_IDXD_H_ -#ifdef __KERNEL__ #include -#else -#include -#endif /* Driver command error status */ enum idxd_scmd_stat { @@ -176,132 +172,132 @@ enum iax_completion_status { #define DSA_COMP_STATUS(status) ((status) & DSA_COMP_STATUS_MASK) struct dsa_hw_desc { - uint32_t pasid:20; - uint32_t rsvd:11; - uint32_t priv:1; - uint32_t flags:24; - uint32_t opcode:8; - uint64_t completion_addr; + __u32 pasid:20; + __u32 rsvd:11; + __u32 priv:1; + __u32 flags:24; + __u32 opcode:8; + __u64 completion_addr; union { - uint64_t src_addr; - uint64_t rdback_addr; - uint64_t pattern; - uint64_t desc_list_addr; - uint64_t pattern_lower; - uint64_t transl_fetch_addr; + __u64 src_addr; + __u64 rdback_addr; + __u64 pattern; + __u64 desc_list_addr; + __u64 pattern_lower; + __u64 transl_fetch_addr; }; union { - uint64_t dst_addr; - uint64_t rdback_addr2; - uint64_t src2_addr; - uint64_t comp_pattern; + __u64 dst_addr; + __u64 rdback_addr2; + __u64 src2_addr; + __u64 comp_pattern; }; union { - uint32_t xfer_size; - uint32_t desc_count; - uint32_t region_size; + __u32 xfer_size; + __u32 desc_count; + __u32 region_size; }; - uint16_t int_handle; - uint16_t rsvd1; + __u16 int_handle; + __u16 rsvd1; union { - uint8_t expected_res; + __u8 expected_res; /* create delta record */ struct { - uint64_t delta_addr; - uint32_t max_delta_size; - uint32_t delt_rsvd; - uint8_t expected_res_mask; + __u64 delta_addr; + __u32 max_delta_size; + __u32 delt_rsvd; + __u8 expected_res_mask; }; - uint32_t delta_rec_size; - uint64_t dest2; + __u32 delta_rec_size; + __u64 dest2; /* CRC */ struct { - uint32_t crc_seed; - uint32_t crc_rsvd; - uint64_t seed_addr; + __u32 crc_seed; + __u32 crc_rsvd; + __u64 seed_addr; }; /* DIF check or strip */ struct { - uint8_t src_dif_flags; - uint8_t dif_chk_res; - uint8_t dif_chk_flags; - uint8_t dif_chk_res2[5]; - uint32_t chk_ref_tag_seed; - uint16_t chk_app_tag_mask; - uint16_t chk_app_tag_seed; + __u8 src_dif_flags; + __u8 dif_chk_res; + __u8 dif_chk_flags; + __u8 dif_chk_res2[5]; + __u32 chk_ref_tag_seed; + __u16 chk_app_tag_mask; + __u16 chk_app_tag_seed; }; /* DIF insert */ struct { - uint8_t dif_ins_res; - uint8_t dest_dif_flag; - uint8_t dif_ins_flags; - uint8_t dif_ins_res2[13]; - uint32_t ins_ref_tag_seed; - uint16_t ins_app_tag_mask; - uint16_t ins_app_tag_seed; + __u8 dif_ins_res; + __u8 dest_dif_flag; + __u8 dif_ins_flags; + __u8 dif_ins_res2[13]; + __u32 ins_ref_tag_seed; + __u16 ins_app_tag_mask; + __u16 ins_app_tag_seed; }; /* DIF update */ struct { - uint8_t src_upd_flags; - uint8_t upd_dest_flags; - uint8_t dif_upd_flags; - uint8_t dif_upd_res[5]; - uint32_t src_ref_tag_seed; - uint16_t src_app_tag_mask; - uint16_t src_app_tag_seed; - uint32_t dest_ref_tag_seed; - uint16_t dest_app_tag_mask; - uint16_t dest_app_tag_seed; + __u8 src_upd_flags; + __u8 upd_dest_flags; + __u8 dif_upd_flags; + __u8 dif_upd_res[5]; + __u32 src_ref_tag_seed; + __u16 src_app_tag_mask; + __u16 src_app_tag_seed; + __u32 dest_ref_tag_seed; + __u16 dest_app_tag_mask; + __u16 dest_app_tag_seed; }; /* Fill */ - uint64_t pattern_upper; + __u64 pattern_upper; /* Translation fetch */ struct { - uint64_t transl_fetch_res; - uint32_t region_stride; + __u64 transl_fetch_res; + __u32 region_stride; }; /* DIX generate */ struct { - uint8_t dix_gen_res; - uint8_t dest_dif_flags; - uint8_t dif_flags; - uint8_t dix_gen_res2[13]; - uint32_t ref_tag_seed; - uint16_t app_tag_mask; - uint16_t app_tag_seed; + __u8 dix_gen_res; + __u8 dest_dif_flags; + __u8 dif_flags; + __u8 dix_gen_res2[13]; + __u32 ref_tag_seed; + __u16 app_tag_mask; + __u16 app_tag_seed; }; - uint8_t op_specific[24]; + __u8 op_specific[24]; }; } __attribute__((packed)); struct iax_hw_desc { - uint32_t pasid:20; - uint32_t rsvd:11; - uint32_t priv:1; - uint32_t flags:24; - uint32_t opcode:8; - uint64_t completion_addr; - uint64_t src1_addr; - uint64_t dst_addr; - uint32_t src1_size; - uint16_t int_handle; + __u32 pasid:20; + __u32 rsvd:11; + __u32 priv:1; + __u32 flags:24; + __u32 opcode:8; + __u64 completion_addr; + __u64 src1_addr; + __u64 dst_addr; + __u32 src1_size; + __u16 int_handle; union { - uint16_t compr_flags; - uint16_t decompr_flags; + __u16 compr_flags; + __u16 decompr_flags; }; - uint64_t src2_addr; - uint32_t max_dst_size; - uint32_t src2_size; - uint32_t filter_flags; - uint32_t num_inputs; + __u64 src2_addr; + __u32 max_dst_size; + __u32 src2_size; + __u32 filter_flags; + __u32 num_inputs; } __attribute__((packed)); struct dsa_raw_desc { - uint64_t field[8]; + __u64 field[8]; } __attribute__((packed)); /* @@ -309,91 +305,91 @@ struct dsa_raw_desc { * volatile and prevent the compiler from optimize the read. */ struct dsa_completion_record { - volatile uint8_t status; + volatile __u8 status; union { - uint8_t result; - uint8_t dif_status; + __u8 result; + __u8 dif_status; }; - uint8_t fault_info; - uint8_t rsvd; + __u8 fault_info; + __u8 rsvd; union { - uint32_t bytes_completed; - uint32_t descs_completed; + __u32 bytes_completed; + __u32 descs_completed; }; - uint64_t fault_addr; + __u64 fault_addr; union { /* common record */ struct { - uint32_t invalid_flags:24; - uint32_t rsvd2:8; + __u32 invalid_flags:24; + __u32 rsvd2:8; }; - uint32_t delta_rec_size; - uint64_t crc_val; + __u32 delta_rec_size; + __u64 crc_val; /* DIF check & strip */ struct { - uint32_t dif_chk_ref_tag; - uint16_t dif_chk_app_tag_mask; - uint16_t dif_chk_app_tag; + __u32 dif_chk_ref_tag; + __u16 dif_chk_app_tag_mask; + __u16 dif_chk_app_tag; }; /* DIF insert */ struct { - uint64_t dif_ins_res; - uint32_t dif_ins_ref_tag; - uint16_t dif_ins_app_tag_mask; - uint16_t dif_ins_app_tag; + __u64 dif_ins_res; + __u32 dif_ins_ref_tag; + __u16 dif_ins_app_tag_mask; + __u16 dif_ins_app_tag; }; /* DIF update */ struct { - uint32_t dif_upd_src_ref_tag; - uint16_t dif_upd_src_app_tag_mask; - uint16_t dif_upd_src_app_tag; - uint32_t dif_upd_dest_ref_tag; - uint16_t dif_upd_dest_app_tag_mask; - uint16_t dif_upd_dest_app_tag; + __u32 dif_upd_src_ref_tag; + __u16 dif_upd_src_app_tag_mask; + __u16 dif_upd_src_app_tag; + __u32 dif_upd_dest_ref_tag; + __u16 dif_upd_dest_app_tag_mask; + __u16 dif_upd_dest_app_tag; }; /* DIX generate */ struct { - uint64_t dix_gen_res; - uint32_t dix_ref_tag; - uint16_t dix_app_tag_mask; - uint16_t dix_app_tag; + __u64 dix_gen_res; + __u32 dix_ref_tag; + __u16 dix_app_tag_mask; + __u16 dix_app_tag; }; - uint8_t op_specific[16]; + __u8 op_specific[16]; }; } __attribute__((packed)); struct dsa_raw_completion_record { - uint64_t field[4]; + __u64 field[4]; } __attribute__((packed)); struct iax_completion_record { - volatile uint8_t status; - uint8_t error_code; - uint8_t fault_info; - uint8_t rsvd; - uint32_t bytes_completed; - uint64_t fault_addr; - uint32_t invalid_flags; - uint32_t rsvd2; - uint32_t output_size; - uint8_t output_bits; - uint8_t rsvd3; - uint16_t xor_csum; - uint32_t crc; - uint32_t min; - uint32_t max; - uint32_t sum; - uint64_t rsvd4[2]; + volatile __u8 status; + __u8 error_code; + __u8 fault_info; + __u8 rsvd; + __u32 bytes_completed; + __u64 fault_addr; + __u32 invalid_flags; + __u32 rsvd2; + __u32 output_size; + __u8 output_bits; + __u8 rsvd3; + __u16 xor_csum; + __u32 crc; + __u32 min; + __u32 max; + __u32 sum; + __u64 rsvd4[2]; } __attribute__((packed)); struct iax_raw_completion_record { - uint64_t field[8]; + __u64 field[8]; } __attribute__((packed)); #endif -- cgit v1.2.3 From 9e541b3cee70a3bbe86b176c903c23b29fe033cd Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Wed, 10 Dec 2025 21:29:05 +0800 Subject: PCI: trace: Add generic RAS tracepoint for hotplug event MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Hotplug events are critical indicators for analyzing hardware health, and surprise link downs can significantly impact system performance and reliability. Define a new TRACING_SYSTEM named "pci", add a generic RAS tracepoint for hotplug event to help health checks. Add enum pci_hotplug_event in include/uapi/linux/pci.h so applications like rasdaemon can register tracepoint event handlers for it. The following output is generated when a device is hotplugged: $ echo 1 > /sys/kernel/debug/tracing/events/pci/pci_hp_event/enable $ cat /sys/kernel/debug/tracing/trace_pipe irq/51-pciehp-88 [001] ..... 1311.177459: pci_hp_event: 0000:00:02.0 slot:10, event:CARD_PRESENT irq/51-pciehp-88 [001] ..... 1311.177566: pci_hp_event: 0000:00:02.0 slot:10, event:LINK_UP Suggested-by: Lukas Wunner Signed-off-by: Shuai Xue Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Wunner Reviewed-by: Jonathan Cameron Reviewed-by: Steven Rostedt (Google) # for trace event Reviewed-by: Ilpo Järvinen Link: https://patch.msgid.link/20251210132907.58799-2-xueshuai@linux.alibaba.com --- include/uapi/linux/pci.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci.h b/include/uapi/linux/pci.h index a769eefc5139..4f150028965d 100644 --- a/include/uapi/linux/pci.h +++ b/include/uapi/linux/pci.h @@ -39,4 +39,11 @@ #define PCIIOC_MMAP_IS_MEM (PCIIOC_BASE | 0x02) /* Set mmap state to MEM space. */ #define PCIIOC_WRITE_COMBINE (PCIIOC_BASE | 0x03) /* Enable/disable write-combining. */ +enum pci_hotplug_event { + PCI_HOTPLUG_LINK_UP, + PCI_HOTPLUG_LINK_DOWN, + PCI_HOTPLUG_CARD_PRESENT, + PCI_HOTPLUG_CARD_NOT_PRESENT, +}; + #endif /* _UAPILINUX_PCI_H */ -- cgit v1.2.3 From 3dd57ddec9e3a98387196a3f53b8c036977d8c0f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 16 Dec 2025 08:19:39 +0000 Subject: get rid of bogus __user in struct xattr_args::value The first member of struct xattr_args is declared as __aligned_u64 __user value; which makes no sense whatsoever; __user is a qualifier and what that declaration says is "all struct xattr_args instances have .value _stored_ in user address space, no matter where the rest of the structure happens to be". Something like "int __user *p" stands for "value of p is a pointer to an instance of int that happens to live in user address space"; it says nothing about location of p itself, just as const char *p declares a pointer to unmodifiable char rather than an unmodifiable pointer to char. With xattr_args the intent clearly had been "the 64bit value represents a _pointer_ to object in user address space", but __user has nothing to do with that. All it gets us is a couple of bogus warnings in fs/xattr.c where (userland) instance of xattr_args is copied to local variable of that type (in kernel address space), followed by access to its members. Since we've told sparse that args.value must somehow be located in userland memory, we get warned that looking at that 64bit unsigned integer (in a variable already on kernel stack) is not allowed. Note that sparse has no way to express "this integer shall never be cast into a pointer to be dereferenced directly" and I don't see any way to assign a sane semantics to that. In any case, __user is not it. Signed-off-by: Al Viro Link: https://patch.msgid.link/20251216081939.GQ1712166@ZenIV Signed-off-by: Christian Brauner --- include/uapi/linux/xattr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index c7c85bb504ba..2e5aef48fa7e 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -23,7 +23,7 @@ #define XATTR_REPLACE 0x2 /* set value, fail if attr does not exist */ struct xattr_args { - __aligned_u64 __user value; + __aligned_u64 value; __u32 size; __u32 flags; }; -- cgit v1.2.3 From 3c4629b68dbe18e454cce4b864c530268cffbeed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 22 Dec 2025 09:00:33 +0100 Subject: virtio: uapi: avoid usage of libc types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using libc types and headers from the UAPI headers is problematic as it introduces a dependency on a full C toolchain. On Linux 'unsigned long' works as a replacement for 'uintptr_t' and does not depend on libc. Signed-off-by: Thomas Weißschuh Acked-by: Arnd Bergmann Signed-off-by: Michael S. Tsirkin Message-Id: <20251222-uapi-virtio-v1-1-29390f87bcad@linutronix.de> --- include/uapi/linux/virtio_ring.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index f8c20d3de8da..3c478582a3c2 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -31,9 +31,6 @@ * SUCH DAMAGE. * * Copyright Rusty Russell IBM Corporation 2007. */ -#ifndef __KERNEL__ -#include -#endif #include #include @@ -202,7 +199,7 @@ static inline void vring_init(struct vring *vr, unsigned int num, void *p, vr->num = num; vr->desc = p; vr->avail = (struct vring_avail *)((char *)p + num * sizeof(struct vring_desc)); - vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16) + vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__virtio16) + align-1) & ~(align - 1)); } -- cgit v1.2.3 From 40fc797ba18328e57ed1cb213b4b5e48f86f4c7c Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Mon, 15 Dec 2025 18:17:09 +0000 Subject: binder: fix trivial typo in uapi header As reported by codespell: include/uapi/linux/android/binder.h:281: interupted ==> interrupted Signed-off-by: Carlos Llamas Reviewed-by: Alice Ryhl Link: https://patch.msgid.link/20251215181724.3811977-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 03ee4c7010d7..701cad36de43 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -278,7 +278,7 @@ enum { * NOTE: Two special error codes you should check for when calling * in to the driver are: * - * EINTR -- The operation has been interupted. This should be + * EINTR -- The operation has been interrupted. This should be * handled by retrying the ioctl() until a different error code * is returned. * -- cgit v1.2.3 From c6c209ceb87f64a6ceebe61761951dcbbf4a0baa Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 9 Dec 2025 19:28:49 -0500 Subject: NFSD: Remove NFSERR_EAGAIN I haven't found an NFSERR_EAGAIN in RFCs 1094, 1813, 7530, or 8881. None of these RFCs have an NFS status code that match the numeric value "11". Based on the meaning of the EAGAIN errno, I presume the use of this status in NFSD means NFS4ERR_DELAY. So replace the one usage of nfserr_eagain, and remove it from NFSD's NFS status conversion tables. As far as I can tell, NFSERR_EAGAIN has existed since the pre-git era, but was not actually used by any code until commit f4e44b393389 ("NFSD: delay unmount source's export after inter-server copy completed."), at which time it become possible for NFSD to return a status code of 11 (which is not valid NFS protocol). Fixes: f4e44b393389 ("NFSD: delay unmount source's export after inter-server copy completed.") Cc: stable@vger.kernel.org Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/uapi/linux/nfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index f356f2ba3814..71c7196d3281 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -49,7 +49,6 @@ NFSERR_NOENT = 2, /* v2 v3 v4 */ NFSERR_IO = 5, /* v2 v3 v4 */ NFSERR_NXIO = 6, /* v2 v3 v4 */ - NFSERR_EAGAIN = 11, /* v2 v3 */ NFSERR_ACCES = 13, /* v2 v3 v4 */ NFSERR_EXIST = 17, /* v2 v3 v4 */ NFSERR_XDEV = 18, /* v3 v4 */ -- cgit v1.2.3 From c51bb53d5c68041dd02f66d9b638cda33647623e Mon Sep 17 00:00:00 2001 From: David Yat Sin Date: Tue, 18 Mar 2025 19:49:55 +0000 Subject: drm/amdkfd: Add metadata ring buffer for compute Add support for separate ring-buffer for metadata packets when using compute queues. Userspace application allocate the metadata ring-buffer and the queue ring-buffer with a single allocation. The metadata ring-buffer starts after the queue ring-buffer. Signed-off-by: David Yat Sin Reviewed-by: Philip Yang Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 6e91875c10ba..047bcb1cc078 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -47,9 +47,10 @@ * - 1.19 - Add a new ioctl to craete secondary kfd processes * - 1.20 - Trap handler support for expert scheduling mode available * - 1.21 - Debugger support to subscribe to LDS out-of-address exceptions + * - 1.22 - Add queue creation with metadata ring base address */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 21 +#define KFD_IOCTL_MINOR_VERSION 22 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -87,7 +88,7 @@ struct kfd_ioctl_create_queue_args { __u32 ctx_save_restore_size; /* to KFD */ __u32 ctl_stack_size; /* to KFD */ __u32 sdma_engine_id; /* to KFD */ - __u32 pad; + __u32 metadata_ring_size; /* to KFD */ }; struct kfd_ioctl_destroy_queue_args { -- cgit v1.2.3 From 22cd0db47f4f65ebe8afc8c34ab120c47c73da2a Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Mon, 15 Dec 2025 13:08:12 +0100 Subject: media: uapi: mali-c55-config: Remove version identifier The Mali C55 driver uses the v4l2-isp framework, which defines its own versioning number which does not need to be defined again in each platform-specific header. Remove the definition of mali_c55_param_buffer_version enumeration from the Mali C55 uAPI header. Signed-off-by: Jacopo Mondi Reviewed-by: Daniel Scally Signed-off-by: Hans Verkuil --- include/uapi/linux/media/arm/mali-c55-config.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/media/arm/mali-c55-config.h b/include/uapi/linux/media/arm/mali-c55-config.h index 109082c5694f..3d335f950eeb 100644 --- a/include/uapi/linux/media/arm/mali-c55-config.h +++ b/include/uapi/linux/media/arm/mali-c55-config.h @@ -194,15 +194,6 @@ struct mali_c55_stats_buffer { __u32 reserved3[15]; } __attribute__((packed)); -/** - * enum mali_c55_param_buffer_version - Mali-C55 parameters block versioning - * - * @MALI_C55_PARAM_BUFFER_V1: First version of Mali-C55 parameters block - */ -enum mali_c55_param_buffer_version { - MALI_C55_PARAM_BUFFER_V1, -}; - /** * enum mali_c55_param_block_type - Enumeration of Mali-C55 parameter blocks * -- cgit v1.2.3 From 2b421662c7887a0649fe409155a1f101562d0fa9 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Wed, 7 Jan 2026 10:20:16 +0800 Subject: bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags and check them for following APIs: * 'map_lookup_elem()' * 'map_update_elem()' * 'generic_map_lookup_batch()' * 'generic_map_update_batch()' And, get the correct value size for these APIs. Acked-by: Andrii Nakryiko Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260107022022.12843-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 84ced3ed2d21..2a2ade4be60f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1384,6 +1384,8 @@ enum { BPF_NOEXIST = 1, /* create new element if it didn't exist */ BPF_EXIST = 2, /* update existing element */ BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */ + BPF_F_CPU = 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */ + BPF_F_ALL_CPUS = 16, /* update value across all CPUs for percpu maps */ }; /* flags for BPF_MAP_CREATE command */ -- cgit v1.2.3 From da142f3d373a6ddaca0119615a8db2175ddc4121 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 5 Dec 2025 15:26:55 -0800 Subject: KVM: Remove subtle "struct kvm_stats_desc" pseudo-overlay Remove KVM's internal pseudo-overlay of kvm_stats_desc, which subtly aliases the flexible name[] in the uAPI definition with a fixed-size array of the same name. The unusual embedded structure results in compiler warnings due to -Wflex-array-member-not-at-end, and also necessitates an extra level of dereferencing in KVM. To avoid the "overlay", define the uAPI structure to have a fixed-size name when building for the kernel. Opportunistically clean up the indentation for the stats macros, and replace spaces with tabs. No functional change intended. Reported-by: Gustavo A. R. Silva Closes: https://lore.kernel.org/all/aPfNKRpLfhmhYqfP@kspp Acked-by: Marc Zyngier Acked-by: Christian Borntraeger [..] Acked-by: Anup Patel Reviewed-by: Bibo Mao Acked-by: Gustavo A. R. Silva Link: https://patch.msgid.link/20251205232655.445294-1-seanjc@google.com Signed-off-by: Sean Christopherson --- include/uapi/linux/kvm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dddb781b0507..76bd54848b11 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -14,6 +14,10 @@ #include #include +#ifdef __KERNEL__ +#include +#endif + #define KVM_API_VERSION 12 /* @@ -1579,7 +1583,11 @@ struct kvm_stats_desc { __u16 size; __u32 offset; __u32 bucket_size; +#ifdef __KERNEL__ + char name[KVM_STATS_NAME_SIZE]; +#else char name[]; +#endif }; #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) -- cgit v1.2.3 From caa07a815d6ee32586beb66f67e7e3c103a02efd Mon Sep 17 00:00:00 2001 From: Changwoo Min Date: Thu, 8 Jan 2026 14:32:10 +0900 Subject: PM: EM: Rename em.yaml to dev-energymodel.yaml MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The EM YNL specification used many acronyms, including ‘em’, ‘pd’, ‘ps’, etc. While the acronyms are short and convenient, they could be confusing. So, let’s spell them out to be more specific. The following changes were made in the spec. Note that the protocol name cannot exceed GENL_NAMSIZ (16). em -> dev-energymodel pds -> perf-domains pd -> perf-domain pd-id -> perf-domain-id pd-table -> perf-table ps -> perf-state get-pds -> get-perf-domains get-pd-table -> get-perf-table pd-created -> perf-domain-created pd-updated -> perf-domain-updated pd-deleted -> perf-domain-deleted In addition. doc strings were added to the spec. based on the comments in energy_model.h. Two flag attributes (perf-state-flags and perf-domain-flags) were added for easily interpreting the bit flags. Finally, the autogenerated files and em_netlink.c were updated accordingly to reflect the name changes. Suggested-by: Donald Hunter Reviewed-by: Lukasz Luba Reviewed-by: Donald Hunter Signed-off-by: Changwoo Min Link: https://patch.msgid.link/20260108053212.642478-3-changwoo@igalia.com Signed-off-by: Rafael J. Wysocki --- include/uapi/linux/dev_energymodel.h | 89 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/energy_model.h | 63 ------------------------- 2 files changed, 89 insertions(+), 63 deletions(-) create mode 100644 include/uapi/linux/dev_energymodel.h delete mode 100644 include/uapi/linux/energy_model.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dev_energymodel.h b/include/uapi/linux/dev_energymodel.h new file mode 100644 index 000000000000..3399967e1f93 --- /dev/null +++ b/include/uapi/linux/dev_energymodel.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_DEV_ENERGYMODEL_H +#define _UAPI_LINUX_DEV_ENERGYMODEL_H + +#define DEV_ENERGYMODEL_FAMILY_NAME "dev-energymodel" +#define DEV_ENERGYMODEL_FAMILY_VERSION 1 + +/** + * enum dev_energymodel_perf_state_flags + * @DEV_ENERGYMODEL_PERF_STATE_FLAGS_PERF_STATE_INEFFICIENT: The performance + * state is inefficient. There is in this perf-domain, another performance + * state with a higher frequency but a lower or equal power cost. + */ +enum dev_energymodel_perf_state_flags { + DEV_ENERGYMODEL_PERF_STATE_FLAGS_PERF_STATE_INEFFICIENT = 1, +}; + +/** + * enum dev_energymodel_perf_domain_flags + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_MICROWATTS: The power values + * are in micro-Watts or some other scale. + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip + * inefficient states when estimating energy consumption. + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL: The power values + * are artificial and might be created by platform missing real power + * information. + */ +enum dev_energymodel_perf_domain_flags { + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_MICROWATTS = 1, + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_SKIP_INEFFICIENCIES = 2, + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL = 4, +}; + +enum { + DEV_ENERGYMODEL_A_PERF_DOMAINS_PERF_DOMAIN = 1, + + __DEV_ENERGYMODEL_A_PERF_DOMAINS_MAX, + DEV_ENERGYMODEL_A_PERF_DOMAINS_MAX = (__DEV_ENERGYMODEL_A_PERF_DOMAINS_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD = 1, + DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS, + DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS, + + __DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX, + DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX = (__DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID = 1, + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE, + + __DEV_ENERGYMODEL_A_PERF_TABLE_MAX, + DEV_ENERGYMODEL_A_PERF_TABLE_MAX = (__DEV_ENERGYMODEL_A_PERF_TABLE_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_STATE_PAD = 1, + DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE, + DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY, + DEV_ENERGYMODEL_A_PERF_STATE_POWER, + DEV_ENERGYMODEL_A_PERF_STATE_COST, + DEV_ENERGYMODEL_A_PERF_STATE_FLAGS, + + __DEV_ENERGYMODEL_A_PERF_STATE_MAX, + DEV_ENERGYMODEL_A_PERF_STATE_MAX = (__DEV_ENERGYMODEL_A_PERF_STATE_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS = 1, + DEV_ENERGYMODEL_CMD_GET_PERF_TABLE, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_CREATED, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_UPDATED, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_DELETED, + + __DEV_ENERGYMODEL_CMD_MAX, + DEV_ENERGYMODEL_CMD_MAX = (__DEV_ENERGYMODEL_CMD_MAX - 1) +}; + +#define DEV_ENERGYMODEL_MCGRP_EVENT "event" + +#endif /* _UAPI_LINUX_DEV_ENERGYMODEL_H */ diff --git a/include/uapi/linux/energy_model.h b/include/uapi/linux/energy_model.h deleted file mode 100644 index 0bcad967854f..000000000000 --- a/include/uapi/linux/energy_model.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ -/* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ -/* YNL-GEN uapi header */ -/* To regenerate run: tools/net/ynl/ynl-regen.sh */ - -#ifndef _UAPI_LINUX_ENERGY_MODEL_H -#define _UAPI_LINUX_ENERGY_MODEL_H - -#define EM_FAMILY_NAME "em" -#define EM_FAMILY_VERSION 1 - -enum { - EM_A_PDS_PD = 1, - - __EM_A_PDS_MAX, - EM_A_PDS_MAX = (__EM_A_PDS_MAX - 1) -}; - -enum { - EM_A_PD_PAD = 1, - EM_A_PD_PD_ID, - EM_A_PD_FLAGS, - EM_A_PD_CPUS, - - __EM_A_PD_MAX, - EM_A_PD_MAX = (__EM_A_PD_MAX - 1) -}; - -enum { - EM_A_PD_TABLE_PD_ID = 1, - EM_A_PD_TABLE_PS, - - __EM_A_PD_TABLE_MAX, - EM_A_PD_TABLE_MAX = (__EM_A_PD_TABLE_MAX - 1) -}; - -enum { - EM_A_PS_PAD = 1, - EM_A_PS_PERFORMANCE, - EM_A_PS_FREQUENCY, - EM_A_PS_POWER, - EM_A_PS_COST, - EM_A_PS_FLAGS, - - __EM_A_PS_MAX, - EM_A_PS_MAX = (__EM_A_PS_MAX - 1) -}; - -enum { - EM_CMD_GET_PDS = 1, - EM_CMD_GET_PD_TABLE, - EM_CMD_PD_CREATED, - EM_CMD_PD_UPDATED, - EM_CMD_PD_DELETED, - - __EM_CMD_MAX, - EM_CMD_MAX = (__EM_CMD_MAX - 1) -}; - -#define EM_MCGRP_EVENT "event" - -#endif /* _UAPI_LINUX_ENERGY_MODEL_H */ -- cgit v1.2.3 From 380ff27af25e49e2cb2ff8fd0ecd7c95be2976ee Mon Sep 17 00:00:00 2001 From: Changwoo Min Date: Thu, 8 Jan 2026 14:32:12 +0900 Subject: PM: EM: Add dump to get-perf-domains in the EM YNL spec Add dump to get-perf-domains, so that a user can fetch either information about a specific performance domain with do or information about all performance domains with dump. Share the reply format of do and dump using perf-domain-attrs, so remove perf-domains. The YNL spec, autogenerated files, and the do implementation are updated, and the dump implementation is added. Suggested-by: Donald Hunter Reviewed-by: Lukasz Luba Reviewed-by: Donald Hunter Signed-off-by: Changwoo Min Link: https://patch.msgid.link/20260108053212.642478-5-changwoo@igalia.com Signed-off-by: Rafael J. Wysocki --- include/uapi/linux/dev_energymodel.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dev_energymodel.h b/include/uapi/linux/dev_energymodel.h index 3399967e1f93..355d8885c9a0 100644 --- a/include/uapi/linux/dev_energymodel.h +++ b/include/uapi/linux/dev_energymodel.h @@ -36,13 +36,6 @@ enum dev_energymodel_perf_domain_flags { DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL = 4, }; -enum { - DEV_ENERGYMODEL_A_PERF_DOMAINS_PERF_DOMAIN = 1, - - __DEV_ENERGYMODEL_A_PERF_DOMAINS_MAX, - DEV_ENERGYMODEL_A_PERF_DOMAINS_MAX = (__DEV_ENERGYMODEL_A_PERF_DOMAINS_MAX - 1) -}; - enum { DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD = 1, DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, -- cgit v1.2.3 From c279e83953d937470f8a6e69b69f62608714f13f Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Mon, 15 Dec 2025 13:42:19 -0800 Subject: iommu: Introduce pci_dev_reset_iommu_prepare/done() PCIe permits a device to ignore ATS invalidation TLPs while processing a reset. This creates a problem visible to the OS where an ATS invalidation command will time out. E.g. an SVA domain will have no coordination with a reset event and can racily issue ATS invalidations to a resetting device. The OS should do something to mitigate this as we do not want production systems to be reporting critical ATS failures, especially in a hypervisor environment. Broadly, OS could arrange to ignore the timeouts, block page table mutations to prevent invalidations, or disable and block ATS. The PCIe r6.0, sec 10.3.1 IMPLEMENTATION NOTE recommends SW to disable and block ATS before initiating a Function Level Reset. It also mentions that other reset methods could have the same vulnerability as well. Provide a callback from the PCI subsystem that will enclose the reset and have the iommu core temporarily change all the attached RID/PASID domains group->blocking_domain so that the IOMMU hardware would fence any incoming ATS queries. And IOMMU drivers should also synchronously stop issuing new ATS invalidations and wait for all ATS invalidations to complete. This can avoid any ATS invaliation timeouts. However, if there is a domain attachment/replacement happening during an ongoing reset, ATS routines may be re-activated between the two function calls. So, introduce a new resetting_domain in the iommu_group structure to reject any concurrent attach_dev/set_dev_pasid call during a reset for a concern of compatibility failure. Since this changes the behavior of an attach operation, update the uAPI accordingly. Note that there are two corner cases: 1. Devices in the same iommu_group Since an attachment is always per iommu_group, this means that any sibling devices in the iommu_group cannot change domain, to prevent race conditions. 2. An SR-IOV PF that is being reset while its VF is not In such case, the VF itself is already broken. So, there is no point in preventing PF from going through the iommu reset. Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Tested-by: Dheeraj Kumar Srivastava Signed-off-by: Nicolin Chen Signed-off-by: Joerg Roedel --- include/uapi/linux/vfio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ac2329f24141..bb7b89330d35 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -964,6 +964,10 @@ struct vfio_device_bind_iommufd { * hwpt corresponding to the given pt_id. * * Return: 0 on success, -errno on failure. + * + * When a device is resetting, -EBUSY will be returned to reject any concurrent + * attachment to the resetting device itself or any sibling device in the IOMMU + * group having the resetting device. */ struct vfio_device_attach_iommufd_pt { __u32 argsz; -- cgit v1.2.3 From bc87b14594e30720a5c1546c24e0f5f08d34eb40 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 8 Jan 2026 10:35:21 -0800 Subject: bnxt_en: Implement ethtool_ops -> get_link_ext_state() Map the link_down_reason from the FW to the ethtool link_ext_state when it is available. Also log it to the link down dmesg when it is available. Add 2 new link_ext_state enums to the UAPI: ETHTOOL_LINK_EXT_STATE_OTP_SPEED_VIOLATION ETHTOOL_LINK_EXT_STATE_BMC_REQUEST_DOWN to cover OTP (one-time-programmable) speed restrictions and BMC (Baseboard management controller) forcing the link down. Reviewed-by: Andy Gospodarek Reviewed-by: Kalesh AP Reviewed-by: Pavan Chebbi Signed-off-by: Michael Chan Link: https://patch.msgid.link/20260108183521.215610-7-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index eb7ff2602fbb..5daa8f225b67 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -603,6 +603,8 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, ETHTOOL_LINK_EXT_STATE_OVERHEAT, ETHTOOL_LINK_EXT_STATE_MODULE, + ETHTOOL_LINK_EXT_STATE_OTP_SPEED_VIOLATION, + ETHTOOL_LINK_EXT_STATE_BMC_REQUEST_DOWN, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ -- cgit v1.2.3 From 2e4b28c48f88ce9e263957b1d944cf5349952f88 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 11 Jan 2026 16:53:48 +0100 Subject: treewide: Update email address In a vain attempt to consolidate the email zoo switch everything to the kernel.org account. Signed-off-by: Thomas Gleixner Signed-off-by: Linus Torvalds --- include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c44a8fb3e418..72f03153dd32 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -2,7 +2,7 @@ /* * Performance events: * - * Copyright (C) 2008-2009, Thomas Gleixner + * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * -- cgit v1.2.3 From 576ee5dfd459abe8e29bee8b204cd259e60b4e18 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 12 Jan 2026 16:47:10 +0100 Subject: fs: add immutable rootfs Currently pivot_root() doesn't work on the real rootfs because it cannot be unmounted. Userspace has to do a recursive removal of the initramfs contents manually before continuing the boot. Really all we want from the real rootfs is to serve as the parent mount for anything that is actually useful such as the tmpfs or ramfs for initramfs unpacking or the rootfs itself. There's no need for the real rootfs to actually be anything meaningful or useful. Add a immutable rootfs called "nullfs" that can be selected via the "nullfs_rootfs" kernel command line option. The kernel will mount a tmpfs/ramfs on top of it, unpack the initramfs and fire up userspace which mounts the rootfs and can then just do: chdir(rootfs); pivot_root(".", "."); umount2(".", MNT_DETACH); and be done with it. (Ofc, userspace can also choose to retain the initramfs contents by using something like pivot_root(".", "/initramfs") without unmounting it.) Technically this also means that the rootfs mount in unprivileged namespaces doesn't need to become MNT_LOCKED anymore as it's guaranteed that the immutable rootfs remains permanently empty so there cannot be anything revealed by unmounting the covering mount. In the future this will also allow us to create completely empty mount namespaces without risking to leak anything. systemd already handles this all correctly as it tries to pivot_root() first and falls back to MS_MOVE only when that fails. This goes back to various discussion in previous years and a LPC 2024 presentation about this very topic. Link: https://patch.msgid.link/20260112-work-immutable-rootfs-v2-3-88dd1c34a204@kernel.org Signed-off-by: Christian Brauner --- include/uapi/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 638ca21b7a90..4f2da935a76c 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -104,5 +104,6 @@ #define SECRETMEM_MAGIC 0x5345434d /* "SECM" */ #define PID_FS_MAGIC 0x50494446 /* "PIDF" */ #define GUEST_MEMFD_MAGIC 0x474d454d /* "GMEM" */ +#define NULL_FS_MAGIC 0x4E554C4C /* "NULL" */ #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From 6abbb8703aeeb645a681ab6ad155e0b450413787 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?G=C3=BCnther=20Noack?= Date: Sun, 11 Jan 2026 18:52:04 +0100 Subject: landlock: Clarify documentation for the IOCTL access right MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the description of the LANDLOCK_ACCESS_FS_IOCTL_DEV access right together with the file access rights. This group of access rights applies to files (in this case device files), and they can be added to file or directory inodes using landlock_add_rule(2). The check for that works the same for all file access rights, including LANDLOCK_ACCESS_FS_IOCTL_DEV. Invoking ioctl(2) on directory FDs can not currently be restricted with Landlock. Having it grouped separately in the documentation is a remnant from earlier revisions of the LANDLOCK_ACCESS_FS_IOCTL_DEV patch set. Link: https://lore.kernel.org/all/20260108.Thaex5ruach2@digikod.net/ Signed-off-by: Günther Noack Link: https://lore.kernel.org/r/20260111175203.6545-2-gnoack3000@gmail.com Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 37 +++++++++++++++++-------------------- 1 file changed, 17 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index f030adc462ee..75fd7f5e6cc3 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -216,6 +216,23 @@ struct landlock_net_port_attr { * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with * ``O_TRUNC``. This access right is available since the third version of the * Landlock ABI. + * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened + * character or block device. + * + * This access right applies to all `ioctl(2)` commands implemented by device + * drivers. However, the following common IOCTL commands continue to be + * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: + * + * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), + * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), + * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, + * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) + * * Some IOCTL commands which do not make sense when used with devices, but + * whose implementations are safe and return the right error codes + * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) + * + * This access right is available since the fifth version of the Landlock + * ABI. * * Whether an opened file can be truncated with :manpage:`ftruncate(2)` or used * with `ioctl(2)` is determined during :manpage:`open(2)`, in the same way as @@ -275,26 +292,6 @@ struct landlock_net_port_attr { * If multiple requirements are not met, the ``EACCES`` error code takes * precedence over ``EXDEV``. * - * The following access right applies both to files and directories: - * - * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened - * character or block device. - * - * This access right applies to all `ioctl(2)` commands implemented by device - * drivers. However, the following common IOCTL commands continue to be - * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: - * - * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), - * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), - * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, - * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) - * * Some IOCTL commands which do not make sense when used with devices, but - * whose implementations are safe and return the right error codes - * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) - * - * This access right is available since the fifth version of the Landlock - * ABI. - * * .. warning:: * * It is currently not possible to restrict some file-related actions -- cgit v1.2.3 From 98bf2256855eb682433a33e6a7c4bce35191ca99 Mon Sep 17 00:00:00 2001 From: Stanley Zhang Date: Thu, 8 Jan 2026 02:19:31 -0700 Subject: ublk: support UBLK_PARAM_TYPE_INTEGRITY in device creation Add a feature flag UBLK_F_INTEGRITY for a ublk server to request integrity/metadata support when creating a ublk device. The ublk server can also check for the feature flag on the created device or the result of UBLK_U_CMD_GET_FEATURES to tell if the ublk driver supports it. UBLK_F_INTEGRITY requires UBLK_F_USER_COPY, as user copy is the only data copy mode initially supported for integrity data. Add UBLK_PARAM_TYPE_INTEGRITY and struct ublk_param_integrity to struct ublk_params to specify the integrity params of a ublk device. UBLK_PARAM_TYPE_INTEGRITY requires UBLK_F_INTEGRITY and a nonzero metadata_size. The LBMD_PI_CAP_* and LBMD_PI_CSUM_* values from the linux/fs.h UAPI header are used for the flags and csum_type fields. If the UBLK_PARAM_TYPE_INTEGRITY flag is set, validate the integrity parameters and apply them to the blk_integrity limits. The struct ublk_param_integrity validations are based on the checks in blk_validate_integrity_limits(). Any invalid parameters should be rejected before being applied to struct blk_integrity. [csander: drop redundant pi_tuple_size field, use block metadata UAPI constants, add param validation] Signed-off-by: Stanley Zhang Signed-off-by: Caleb Sander Mateos Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index ec77dabba45b..4c141d7e4710 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -311,6 +311,12 @@ */ #define UBLK_F_BUF_REG_OFF_DAEMON (1ULL << 14) +/* + * ublk device supports requests with integrity/metadata buffer. + * Requires UBLK_F_USER_COPY. + */ +#define UBLK_F_INTEGRITY (1ULL << 16) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -600,6 +606,17 @@ struct ublk_param_segment { __u8 pad[2]; }; +struct ublk_param_integrity { + __u32 flags; /* LBMD_PI_CAP_* from linux/fs.h */ + __u16 max_integrity_segments; /* 0 means no limit */ + __u8 interval_exp; + __u8 metadata_size; /* UBLK_PARAM_TYPE_INTEGRITY requires nonzero */ + __u8 pi_offset; + __u8 csum_type; /* LBMD_PI_CSUM_* from linux/fs.h */ + __u8 tag_size; + __u8 pad[5]; +}; + struct ublk_params { /* * Total length of parameters, userspace has to set 'len' for both @@ -614,6 +631,7 @@ struct ublk_params { #define UBLK_PARAM_TYPE_ZONED (1 << 3) #define UBLK_PARAM_TYPE_DMA_ALIGN (1 << 4) #define UBLK_PARAM_TYPE_SEGMENT (1 << 5) +#define UBLK_PARAM_TYPE_INTEGRITY (1 << 6) /* requires UBLK_F_INTEGRITY */ __u32 types; /* types of parameter included */ struct ublk_param_basic basic; @@ -622,6 +640,7 @@ struct ublk_params { struct ublk_param_zoned zoned; struct ublk_param_dma_align dma; struct ublk_param_segment seg; + struct ublk_param_integrity integrity; }; #endif -- cgit v1.2.3 From f82f0a16a8270b17211254beeb123d11a0f279cd Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Thu, 8 Jan 2026 02:19:32 -0700 Subject: ublk: set UBLK_IO_F_INTEGRITY in ublksrv_io_desc Indicate to the ublk server when an incoming request has integrity data by setting UBLK_IO_F_INTEGRITY in the ublksrv_io_desc's op_flags field. Signed-off-by: Caleb Sander Mateos Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 4c141d7e4710..dfde4aee39eb 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -414,6 +414,8 @@ struct ublksrv_ctrl_dev_info { * passed in. */ #define UBLK_IO_F_NEED_REG_BUF (1U << 17) +/* Request has an integrity data buffer */ +#define UBLK_IO_F_INTEGRITY (1UL << 18) /* * io cmd is described by this structure, and stored in share memory, indexed -- cgit v1.2.3 From be82a89066d595da334f6e153ababcedc3f92ad6 Mon Sep 17 00:00:00 2001 From: Stanley Zhang Date: Thu, 8 Jan 2026 02:19:37 -0700 Subject: ublk: implement integrity user copy Add a function ublk_copy_user_integrity() to copy integrity information between a request and a user iov_iter. This mirrors the existing ublk_copy_user_pages() but operates on request integrity data instead of regular data. Check UBLKSRV_IO_INTEGRITY_FLAG in iocb->ki_pos in ublk_user_copy() to choose between copying data or integrity data. [csander: change offset units from data bytes to integrity data bytes, fix CONFIG_BLK_DEV_INTEGRITY=n build, rebase on user copy refactor] Signed-off-by: Stanley Zhang Signed-off-by: Caleb Sander Mateos Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index dfde4aee39eb..61ac5d8e1078 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -134,6 +134,10 @@ #define UBLKSRV_IO_BUF_TOTAL_BITS (UBLK_QID_OFF + UBLK_QID_BITS) #define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) +/* Copy to/from request integrity buffer instead of data buffer */ +#define UBLK_INTEGRITY_FLAG_OFF 62 +#define UBLKSRV_IO_INTEGRITY_FLAG (1ULL << UBLK_INTEGRITY_FLAG_OFF) + /* * ublk server can register data buffers for incoming I/O requests with a sparse * io_uring buffer table. The request buffer can then be used as the data buffer -- cgit v1.2.3 From e6ce36ccc86f6d447808a6e620f56d440d74aa19 Mon Sep 17 00:00:00 2001 From: Askar Safin Date: Wed, 19 Nov 2025 22:24:07 +0000 Subject: init: remove /proc/sys/kernel/real-root-dev It is not used anymore. Signed-off-by: Askar Safin Link: https://patch.msgid.link/20251119222407.3333257-4-safinaskar@gmail.com Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/uapi/linux/sysctl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 63d1464cb71c..1c7fe0f4dca4 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -92,7 +92,6 @@ enum KERN_DOMAINNAME=8, /* string: domainname */ KERN_PANIC=15, /* int: panic timeout */ - KERN_REALROOTDEV=16, /* real root device to mount after initrd */ KERN_SPARC_REBOOT=21, /* reboot command on Sparc */ KERN_CTLALTDEL=22, /* int: allow ctl-alt-del to reboot */ -- cgit v1.2.3 From e1cbdf78f60c35a1a320ca401852fd6a73624a4a Mon Sep 17 00:00:00 2001 From: Lachlan Hodges Date: Fri, 9 Jan 2026 19:14:39 +1100 Subject: wifi: cfg80211: include S1G_NO_PRIMARY flag when sending channel When sending a channel ensure we include the IEEE80211_CHAN_S1G_NO_PRIMARY flag. Signed-off-by: Lachlan Hodges Link: https://patch.msgid.link/20260109081439.3168-1-lachlan.hodges@morsemicro.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8134f10e4e6c..964e1c779cdd 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4444,6 +4444,9 @@ enum nl80211_wmm_rule { * channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_NO_16MHZ: 16 MHz operation is not allowed on this * channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_S1G_NO_PRIMARY: Channel is not permitted for use + * as a primary channel. Does not prevent the channel from existing + * as a non-primary subchannel. Only applicable to S1G channels. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4492,6 +4495,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_4MHZ, NL80211_FREQUENCY_ATTR_NO_8MHZ, NL80211_FREQUENCY_ATTR_NO_16MHZ, + NL80211_FREQUENCY_ATTR_S1G_NO_PRIMARY, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, -- cgit v1.2.3 From 93ada1b3da398b492c45429cef1a1c9651d5c7ba Mon Sep 17 00:00:00 2001 From: Yoav Cohen Date: Tue, 13 Jan 2026 00:05:01 +0200 Subject: ublk: add UBLK_CMD_TRY_STOP_DEV command Add a best-effort stop command, UBLK_CMD_TRY_STOP_DEV, which only stops a ublk device when it has no active openers. Unlike UBLK_CMD_STOP_DEV, this command does not disrupt existing users. New opens are blocked only after disk_openers has reached zero; if the device is busy, the command returns -EBUSY and leaves it running. The ub->block_open flag is used only to close a race with an in-progress open and does not otherwise change open behavior. Advertise support via the UBLK_F_SAFE_STOP_DEV feature flag. Signed-off-by: Yoav Cohen Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 61ac5d8e1078..90f47da4f435 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -55,7 +55,8 @@ _IOWR('u', 0x15, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_QUIESCE_DEV \ _IOWR('u', 0x16, struct ublksrv_ctrl_cmd) - +#define UBLK_U_CMD_TRY_STOP_DEV \ + _IOWR('u', 0x17, struct ublksrv_ctrl_cmd) /* * 64bits are enough now, and it should be easy to extend in case of * running out of feature flags @@ -321,6 +322,12 @@ */ #define UBLK_F_INTEGRITY (1ULL << 16) +/* + * The device supports the UBLK_CMD_TRY_STOP_DEV command, which + * allows stopping the device only if there are no openers. + */ +#define UBLK_F_SAFE_STOP_DEV (1ULL << 17) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From 406fc2e9ca65e0df345ebf4ce95aa87cb6416f35 Mon Sep 17 00:00:00 2001 From: Deepa Guthyappa Madivalara Date: Wed, 10 Dec 2025 10:59:04 -0800 Subject: media: uapi: videodev2: Add support for AV1 stateful decoder Introduce a new pixel format, V4L2_PIX_FMT_AV1, to the Video4Linux2(V4L2) API. This format is intended for AV1 bitstreams in stateful decoding/encoding workflows. The fourcc code 'AV10' is used to distinguish this format from the existing V4L2_PIX_FMT_AV1_FRAME, which is used for stateless AV1 decoder implementation. Reviewed-by: Bryan O'Donoghue Reviewed-by: Nicolas Dufresne Reviewed-by: Hans Verkuil Signed-off-by: Deepa Guthyappa Madivalara Tested-by: Val Packett Signed-off-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index add08188f068..848e86617d5c 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -775,6 +775,7 @@ struct v4l2_pix_format { #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 */ #define V4L2_PIX_FMT_AV1_FRAME v4l2_fourcc('A', 'V', '1', 'F') /* AV1 parsed frame */ +#define V4L2_PIX_FMT_AV1 v4l2_fourcc('A', 'V', '0', '1') /* AV1 */ #define V4L2_PIX_FMT_SPK v4l2_fourcc('S', 'P', 'K', '0') /* Sorenson Spark */ #define V4L2_PIX_FMT_RV30 v4l2_fourcc('R', 'V', '3', '0') /* RealVideo 8 */ #define V4L2_PIX_FMT_RV40 v4l2_fourcc('R', 'V', '4', '0') /* RealVideo 9 & 10 */ -- cgit v1.2.3 From 1bddd758bac21fbbd8a06af746ec7b6d878a9d2c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonas=20K=C3=B6ppeler?= Date: Fri, 9 Jan 2026 14:15:34 +0100 Subject: net/sched: sch_cake: share shaper state across sub-instances of cake_mq MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit adds shared shaper state across the cake instances beneath a cake_mq qdisc. It works by periodically tracking the number of active instances, and scaling the configured rate by the number of active queues. The scan is lockless and simply reads the qlen and the last_active state variable of each of the instances configured beneath the parent cake_mq instance. Locking is not required since the values are only updated by the owning instance, and eventual consistency is sufficient for the purpose of estimating the number of active queues. The interval for scanning the number of active queues is set to 200 us. We found this to be a good tradeoff between overhead and response time. For a detailed analysis of this aspect see the Netdevconf talk: https://netdevconf.info/0x19/docs/netdev-0x19-paper16-talk-paper.pdf Reviewed-by: Jamal Hadi Salim Signed-off-by: Jonas Köppeler Signed-off-by: Toke Høiland-Jørgensen Link: https://patch.msgid.link/20260109-mq-cake-sub-qdisc-v8-5-8d613fece5d8@redhat.com Signed-off-by: Paolo Abeni --- include/uapi/linux/pkt_sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index c2da76e78bad..66e8072f44df 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1036,6 +1036,7 @@ enum { TCA_CAKE_STATS_DROP_NEXT_US, TCA_CAKE_STATS_P_DROP, TCA_CAKE_STATS_BLUE_TIMER_US, + TCA_CAKE_STATS_ACTIVE_QUEUES, __TCA_CAKE_STATS_MAX }; #define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1) -- cgit v1.2.3 From f29c852149f94dc1975c64fa919b3dd62db04d23 Mon Sep 17 00:00:00 2001 From: Ainy Kumari Date: Wed, 14 Jan 2026 16:48:52 +0530 Subject: wifi: cfg80211: add support for EPPKE Authentication Protocol Add an extended feature flag NL80211_EXT_FEATURE_EPPKE to allow a driver to indicate support for the Enhanced Privacy Protection Key Exchange (EPPKE) authentication protocol in non-AP STA mode, as defined in "IEEE P802.11bi/D3.0, 12.16.9". In case of SME in userspace, the Authentication frame body is prepared in userspace while the driver finalizes the Authentication frame once it receives the required fields and elements. The driver indicates support for EPPKE using the extended feature flag so that userspace can initiate EPPKE authentication. When the feature flag is set, process EPPKE Authentication frames from userspace in non-AP STA mode. If the flag is not set, reject EPPKE Authentication frames. Define a new authentication type NL80211_AUTHTYPE_EPPKE for EPPKE. Signed-off-by: Ainy Kumari Co-developed-by: Kavita Kavita Signed-off-by: Kavita Kavita Link: https://patch.msgid.link/20260114111900.2196941-2-kavita.kavita@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 964e1c779cdd..351d4d176f87 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5429,6 +5429,7 @@ enum nl80211_bss_status { * @NL80211_AUTHTYPE_FILS_SK: Fast Initial Link Setup shared key * @NL80211_AUTHTYPE_FILS_SK_PFS: Fast Initial Link Setup shared key with PFS * @NL80211_AUTHTYPE_FILS_PK: Fast Initial Link Setup public key + * @NL80211_AUTHTYPE_EPPKE: Enhanced Privacy Protection Key Exchange * @__NL80211_AUTHTYPE_NUM: internal * @NL80211_AUTHTYPE_MAX: maximum valid auth algorithm * @NL80211_AUTHTYPE_AUTOMATIC: determine automatically (if necessary by @@ -5444,6 +5445,7 @@ enum nl80211_auth_type { NL80211_AUTHTYPE_FILS_SK, NL80211_AUTHTYPE_FILS_SK_PFS, NL80211_AUTHTYPE_FILS_PK, + NL80211_AUTHTYPE_EPPKE, /* keep last */ __NL80211_AUTHTYPE_NUM, @@ -6748,6 +6750,10 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_BEACON_RATE_EHT: Driver supports beacon rate * configuration (AP/mesh) with EHT rates. * + * @NL80211_EXT_FEATURE_EPPKE: Driver supports Enhanced Privacy Protection + * Key Exchange (EPPKE) with user space SME (NL80211_CMD_AUTHENTICATE) + * in non-AP STA mode. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6824,6 +6830,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_DFS_CONCURRENT, NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT, NL80211_EXT_FEATURE_BEACON_RATE_EHT, + NL80211_EXT_FEATURE_EPPKE, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 9d17a040c15d4b99484f13cf08dd45a9e308beeb Mon Sep 17 00:00:00 2001 From: Ainy Kumari Date: Wed, 14 Jan 2026 16:48:53 +0530 Subject: wifi: cfg80211: add feature flag for (re)association frame encryption Introduce an extended feature flag that allows drivers to signal support for encryption of (Re)Association Request and Response frames in both non-AP STA and AP mode, as specified in specification "IEEE P802.11bi/D3.0, 12.16.6". Signed-off-by: Ainy Kumari Signed-off-by: Kavita Kavita Link: https://patch.msgid.link/20260114111900.2196941-3-kavita.kavita@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 351d4d176f87..60573334e086 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -6754,6 +6754,11 @@ enum nl80211_feature_flags { * Key Exchange (EPPKE) with user space SME (NL80211_CMD_AUTHENTICATE) * in non-AP STA mode. * + * @NL80211_EXT_FEATURE_ASSOC_FRAME_ENCRYPTION: This specifies that the + * driver supports encryption of (Re)Association Request and Response + * frames in both non‑AP STA and AP mode as specified in + * "IEEE P802.11bi/D3.0, 12.16.6". + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6831,6 +6836,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT, NL80211_EXT_FEATURE_BEACON_RATE_EHT, NL80211_EXT_FEATURE_EPPKE, + NL80211_EXT_FEATURE_ASSOC_FRAME_ENCRYPTION, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 6ee3a22c61cdf57d71592ec9f3b9439cd5d0c75f Mon Sep 17 00:00:00 2001 From: Sai Pratyusha Magam Date: Wed, 14 Jan 2026 16:48:55 +0530 Subject: wifi: nl80211: Add support for EPP peer indication Introduce a new netlink attribute NL80211_ATTR_EPP_PEER to be used with NL80211_CMD_NEW_STA and NL80211_CMD_ADD_LINK_STA for the userspace to indicate that a non-AP STA is an Enhanced Privacy Protection (EPP) peer. Co-developed-by: Rohan Dutta Signed-off-by: Rohan Dutta Signed-off-by: Sai Pratyusha Magam Signed-off-by: Kavita Kavita Link: https://patch.msgid.link/20260114111900.2196941-5-kavita.kavita@oss.qualcomm.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 60573334e086..eb92296457c9 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2973,6 +2973,9 @@ enum nl80211_commands { * primary channel is 2 MHz wide, and the control channel designates * the 1 MHz primary subchannel within that 2 MHz primary. * + * @NL80211_ATTR_EPP_PEER: A flag attribute to indicate if the peer is an EPP + * STA. Used with %NL80211_CMD_NEW_STA and %NL80211_CMD_ADD_LINK_STA + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3541,6 +3544,8 @@ enum nl80211_attrs { NL80211_ATTR_S1G_PRIMARY_2MHZ, + NL80211_ATTR_EPP_PEER, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From dacbfc16780837aa3e00c684d89492d211fd809f Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Mon, 5 Jan 2026 13:24:03 +0100 Subject: crypto: af_alg - Annotate struct af_alg_iv with __counted_by Add the __counted_by() compiler attribute to the flexible array member 'iv' to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and CONFIG_FORTIFY_SOURCE. Reviewed-by: Simon Horman Signed-off-by: Thorsten Blum Link: https://patch.msgid.link/20260105122402.2685-2-thorsten.blum@linux.dev Signed-off-by: Kees Cook --- include/uapi/linux/if_alg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index b35871cbeed7..4f51e198ac2e 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[]; + __u8 iv[] __counted_by(ivlen); }; /* Socket options */ -- cgit v1.2.3 From d2bdcde9626cbea0c44a6aaa33b440c8adf81e09 Mon Sep 17 00:00:00 2001 From: Dapeng Mi Date: Wed, 14 Jan 2026 09:17:45 +0800 Subject: perf/x86/intel: Add support for PEBS memory auxiliary info field in DMR With the introduction of the OMR feature, the PEBS memory auxiliary info field for load and store latency events has been restructured for DMR. The memory auxiliary info field's bit[8] indicates whether a L2 cache miss occurred for a memory load or store instruction. If bit[8] is 0, it signifies no L2 cache miss, and bits[7:0] specify the exact cache data source (up to the L2 cache level). If bit[8] is 1, bits[7:0] represent the OMR encoding, indicating the specific L3 cache or memory region involved in the memory access. A significant enhancement is OMR encoding provides up to 8 fine-grained memory regions besides the cache region. A significant enhancement for OMR encoding is the ability to provide up to 8 fine-grained memory regions in addition to the cache region, offering more detailed insights into memory access regions. For detailed information on the memory auxiliary info encoding, please refer to section 16.2 "PEBS LOAD LATENCY AND STORE LATENCY FACILITY" in the ISE documentation. This patch ensures that the PEBS memory auxiliary info field is correctly interpreted and utilized in DMR. Signed-off-by: Dapeng Mi Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260114011750.350569-3-dapeng1.mi@linux.intel.com --- include/uapi/linux/perf_event.h | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c44a8fb3e418..533393ec94d0 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1330,14 +1330,16 @@ union perf_mem_data_src { mem_snoopx : 2, /* Snoop mode, ext */ mem_blk : 3, /* Access blocked */ mem_hops : 3, /* Hop level */ - mem_rsvd : 18; + mem_region : 5, /* cache/memory regions */ + mem_rsvd : 13; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd : 18, + __u64 mem_rsvd : 13, + mem_region : 5, /* cache/memory regions */ mem_hops : 3, /* Hop level */ mem_blk : 3, /* Access blocked */ mem_snoopx : 2, /* Snoop mode, ext */ @@ -1394,7 +1396,7 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ #define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ -/* 0x007 available */ +#define PERF_MEM_LVLNUM_L0 0x0007 /* L0 */ #define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ @@ -1447,6 +1449,25 @@ union perf_mem_data_src { /* 5-7 available */ #define PERF_MEM_HOPS_SHIFT 43 +/* Cache/Memory region */ +#define PERF_MEM_REGION_NA 0x0 /* Invalid */ +#define PERF_MEM_REGION_RSVD 0x01 /* Reserved */ +#define PERF_MEM_REGION_L_SHARE 0x02 /* Local CA shared cache */ +#define PERF_MEM_REGION_L_NON_SHARE 0x03 /* Local CA non-shared cache */ +#define PERF_MEM_REGION_O_IO 0x04 /* Other CA IO agent */ +#define PERF_MEM_REGION_O_SHARE 0x05 /* Other CA shared cache */ +#define PERF_MEM_REGION_O_NON_SHARE 0x06 /* Other CA non-shared cache */ +#define PERF_MEM_REGION_MMIO 0x07 /* MMIO */ +#define PERF_MEM_REGION_MEM0 0x08 /* Memory region 0 */ +#define PERF_MEM_REGION_MEM1 0x09 /* Memory region 1 */ +#define PERF_MEM_REGION_MEM2 0x0a /* Memory region 2 */ +#define PERF_MEM_REGION_MEM3 0x0b /* Memory region 3 */ +#define PERF_MEM_REGION_MEM4 0x0c /* Memory region 4 */ +#define PERF_MEM_REGION_MEM5 0x0d /* Memory region 5 */ +#define PERF_MEM_REGION_MEM6 0x0e /* Memory region 6 */ +#define PERF_MEM_REGION_MEM7 0x0f /* Memory region 7 */ +#define PERF_MEM_REGION_SHIFT 46 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit v1.2.3 From 567873005dca1be0a3b3e2e309a8f0de14d2b827 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 15 Jan 2026 08:05:44 +0200 Subject: ethtool: Clarify len/n_stats fields in/out semantics Document that the 'len' field in ethtool_gstrings and 'n_stats' field in ethtool_stats optionally serve dual purposes: on entry they specify the number of items requested, and on return they indicate the number actually returned (which is not necessarily the same). Signed-off-by: Gal Pressman Reviewed-by: Dragos Tatulea Link: https://patch.msgid.link/20260115060544.481550-1-gal@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 5daa8f225b67..bbfe6e1cf01b 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1096,13 +1096,20 @@ enum ethtool_module_fw_flash_status { * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS * @string_set: String set ID; one of &enum ethtool_stringset - * @len: On return, the number of strings in the string set + * @len: Number of strings in the string set * @data: Buffer for strings. Each string is null-padded to a size of * %ETH_GSTRING_LEN. * * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in * the string set. They must allocate a buffer of the appropriate * size immediately following this structure. + * + * Setting @len on input is optional (though preferred), but must be zeroed + * otherwise. + * When set, @len will return the requested count if it matches the actual + * count; otherwise, it will be zero. + * This prevents issues when the number of strings is different than the + * userspace allocation. */ struct ethtool_gstrings { __u32 cmd; @@ -1179,13 +1186,20 @@ struct ethtool_test { /** * struct ethtool_stats - device-specific statistics * @cmd: Command number = %ETHTOOL_GSTATS - * @n_stats: On return, the number of statistics + * @n_stats: Number of statistics * @data: Array of statistics * * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the * number of statistics that will be returned. They must allocate a * buffer of the appropriate size (8 * number of statistics) * immediately following this structure. + * + * Setting @n_stats on input is optional (though preferred), but must be zeroed + * otherwise. + * When set, @n_stats will return the requested count if it matches the actual + * count; otherwise, it will be zero. + * This prevents issues when the number of stats is different than the + * userspace allocation. */ struct ethtool_stats { __u32 cmd; -- cgit v1.2.3 From d89ccbf3dde727d91a242a5a3f3b70a90579b057 Mon Sep 17 00:00:00 2001 From: Richard Leitner Date: Tue, 9 Dec 2025 23:44:36 +0100 Subject: media: v4l: ctrls: add a control for flash/strobe duration Add a V4L2_CID_FLASH_DURATION control to set the duration of a flash/strobe pulse. This controls the length of the flash/strobe pulse output by device (typically a camera sensor) and connected to the flash controller. This is different to the V4L2_CID_FLASH_TIMEOUT control, which is implemented by the flash controller and defines a limit after which the flash is "forcefully" turned off again. Reviewed-by: Laurent Pinchart Signed-off-by: Richard Leitner Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-controls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index f84ed133a6c9..357845830fe9 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1192,6 +1192,7 @@ enum v4l2_flash_strobe_source { #define V4L2_CID_FLASH_CHARGE (V4L2_CID_FLASH_CLASS_BASE + 11) #define V4L2_CID_FLASH_READY (V4L2_CID_FLASH_CLASS_BASE + 12) +#define V4L2_CID_FLASH_DURATION (V4L2_CID_FLASH_CLASS_BASE + 13) /* JPEG-class control IDs */ -- cgit v1.2.3 From 5be4154f6255d92d9d2ad5da658d7d33a655386f Mon Sep 17 00:00:00 2001 From: Richard Leitner Date: Tue, 9 Dec 2025 23:44:37 +0100 Subject: media: v4l: ctrls: add a control for enabling strobe output Add a control V4L2_CID_FLASH_STROBE_OE to en- or disable the strobe output of v4l2 devices (most likely sensors). Signed-off-by: Richard Leitner Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-controls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 357845830fe9..572622e4535e 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1193,6 +1193,7 @@ enum v4l2_flash_strobe_source { #define V4L2_CID_FLASH_CHARGE (V4L2_CID_FLASH_CLASS_BASE + 11) #define V4L2_CID_FLASH_READY (V4L2_CID_FLASH_CLASS_BASE + 12) #define V4L2_CID_FLASH_DURATION (V4L2_CID_FLASH_CLASS_BASE + 13) +#define V4L2_CID_FLASH_STROBE_OE (V4L2_CID_FLASH_CLASS_BASE + 14) /* JPEG-class control IDs */ -- cgit v1.2.3 From 10d28cffb3f6ec7ad67f0a4cd32c2afa92909452 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 3 Dec 2025 16:24:38 +0000 Subject: comedi: Fix getting range information for subdevices 16 to 255 The `COMEDI_RANGEINFO` ioctl does not work properly for subdevice indices above 15. Currently, the only in-tree COMEDI drivers that support more than 16 subdevices are the "8255" driver and the "comedi_bond" driver. Making the ioctl work for subdevice indices up to 255 is achievable. It needs minor changes to the handling of the `COMEDI_RANGEINFO` and `COMEDI_CHANINFO` ioctls that should be mostly harmless to user-space, apart from making them less broken. Details follow... The `COMEDI_RANGEINFO` ioctl command gets the list of supported ranges (usually with units of volts or milliamps) for a COMEDI subdevice or channel. (Only some subdevices have per-channel range tables, indicated by the `SDF_RANGETYPE` flag in the subdevice information.) It uses a `range_type` value and a user-space pointer, both supplied by user-space, but the `range_type` value should match what was obtained using the `COMEDI_CHANINFO` ioctl (if the subdevice has per-channel range tables) or `COMEDI_SUBDINFO` ioctl (if the subdevice uses a single range table for all channels). Bits 15 to 0 of the `range_type` value contain the length of the range table, which is the only part that user-space should care about (so it can use a suitably sized buffer to fetch the range table). Bits 23 to 16 store the channel index, which is assumed to be no more than 255 if the subdevice has per-channel range tables, and is set to 0 if the subdevice has a single range table. For `range_type` values produced by the `COMEDI_SUBDINFO` ioctl, bits 31 to 24 contain the subdevice index, which is assumed to be no more than 255. But for `range_type` values produced by the `COMEDI_CHANINFO` ioctl, bits 27 to 24 contain the subdevice index, which is assumed to be no more than 15, and bits 31 to 28 contain the COMEDI device's minor device number for some unknown reason lost in the mists of time. The `COMEDI_RANGEINFO` ioctl extract the length from bits 15 to 0 of the user-supplied `range_type` value, extracts the channel index from bits 23 to 16 (only used if the subdevice has per-channel range tables), extracts the subdevice index from bits 27 to 24, and ignores bits 31 to 28. So for subdevice indices 16 to 255, the `COMEDI_SUBDINFO` or `COMEDI_CHANINFO` ioctl will report a `range_type` value that doesn't work with the `COMEDI_RANGEINFO` ioctl. It will either get the range table for the subdevice index modulo 16, or will fail with `-EINVAL`. To fix this, always use bits 31 to 24 of the `range_type` value to hold the subdevice index (assumed to be no more than 255). This affects the `COMEDI_CHANINFO` and `COMEDI_RANGEINFO` ioctls. There should not be anything in user-space that depends on the old, broken usage, although it may now see different values in bits 31 to 28 of the `range_type` values reported by the `COMEDI_CHANINFO` ioctl for subdevices that have per-channel subdevices. User-space should not be trying to decode bits 31 to 16 of the `range_type` values anyway. Fixes: ed9eccbe8970 ("Staging: add comedi core") Cc: stable@vger.kernel.org #5.17+ Signed-off-by: Ian Abbott Link: https://patch.msgid.link/20251203162438.176841-1-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/comedi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/comedi.h b/include/uapi/linux/comedi.h index 7314e5ee0a1e..798ec9a39e12 100644 --- a/include/uapi/linux/comedi.h +++ b/include/uapi/linux/comedi.h @@ -640,7 +640,7 @@ struct comedi_chaninfo { /** * struct comedi_rangeinfo - used to retrieve the range table for a channel - * @range_type: Encodes subdevice index (bits 27:24), channel index + * @range_type: Encodes subdevice index (bits 31:24), channel index * (bits 23:16) and range table length (bits 15:0). * @range_ptr: Pointer to array of @struct comedi_krange to be filled * in with the range table for the channel or subdevice. -- cgit v1.2.3 From 9b8a0ba68246a61d903ce62c35c303b1501df28b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 29 Dec 2025 14:03:24 +0100 Subject: mount: add OPEN_TREE_NAMESPACE When creating containers the setup usually involves using CLONE_NEWNS via clone3() or unshare(). This copies the caller's complete mount namespace. The runtime will also assemble a new rootfs and then use pivot_root() to switch the old mount tree with the new rootfs. Afterward it will recursively umount the old mount tree thereby getting rid of all mounts. On a basic system here where the mount table isn't particularly large this still copies about 30 mounts. Copying all of these mounts only to get rid of them later is pretty wasteful. This is exacerbated if intermediary mount namespaces are used that only exist for a very short amount of time and are immediately destroyed again causing a ton of mounts to be copied and destroyed needlessly. With a large mount table and a system where thousands or ten-thousands of containers are spawned in parallel this quickly becomes a bottleneck increasing contention on the semaphore. Extend open_tree() with a new OPEN_TREE_NAMESPACE flag. Similar to OPEN_TREE_CLONE only the indicated mount tree is copied. Instead of returning a file descriptor referring to that mount tree OPEN_TREE_NAMESPACE will cause open_tree() to return a file descriptor to a new mount namespace. In that new mount namespace the copied mount tree has been mounted on top of a copy of the real rootfs. The caller can setns() into that mount namespace and perform any additionally required setup such as move_mount() detached mounts in there. This allows OPEN_TREE_NAMESPACE to function as a combined unshare(CLONE_NEWNS) and pivot_root(). A caller may for example choose to create an extremely minimal rootfs: fd_mntns = open_tree(-EBADF, "/var/lib/containers/wootwoot", OPEN_TREE_NAMESPACE); This will create a mount namespace where "wootwoot" has become the rootfs mounted on top of the real rootfs. The caller can now setns() into this new mount namespace and assemble additional mounts. This also works with user namespaces: unshare(CLONE_NEWUSER); fd_mntns = open_tree(-EBADF, "/var/lib/containers/wootwoot", OPEN_TREE_NAMESPACE); which creates a new mount namespace owned by the earlier created user namespace with "wootwoot" as the rootfs mounted on top of the real rootfs. Link: https://patch.msgid.link/20251229-work-empty-namespace-v1-1-bfb24c7b061f@kernel.org Tested-by: Jeff Layton Reviewed-by: Aleksa Sarai Reviewed-by: Jeff Layton Suggested-by: Christian Brauner Suggested-by: Aleksa Sarai Signed-off-by: Christian Brauner --- include/uapi/linux/mount.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 18c624405268..d9d86598d100 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -61,7 +61,8 @@ /* * open_tree() flags. */ -#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */ +#define OPEN_TREE_CLONE (1 << 0) /* Clone the target tree and attach the clone */ +#define OPEN_TREE_NAMESPACE (1 << 1) /* Clone the target tree into a new mount namespace */ #define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ /* -- cgit v1.2.3 From 1e5271393d777f6159d896943b4c44c4f3ecff52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Thu, 15 Jan 2026 08:35:44 +0100 Subject: hyper-v: Mark inner union in hv_kvp_exchg_msg_value as packed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The unpacked union within a packed struct generates alignment warnings on clang for 32-bit ARM: ./usr/include/linux/hyperv.h:361:2: error: field within 'struct hv_kvp_exchg_msg_value' is less aligned than 'union hv_kvp_exchg_msg_value::(anonymous at ./usr/include/linux/hyperv.h:361:2)' and is usually due to 'struct hv_kvp_exchg_msg_value' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] 361 | union { | ^ With the recent changes to compile-test the UAPI headers in more cases, this warning in combination with CONFIG_WERROR breaks the build. Fix the warning. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202512140314.DzDxpIVn-lkp@intel.com/ Reported-by: Nathan Chancellor Closes: https://lore.kernel.org/linux-kbuild/20260110-uapi-test-disable-headers-arm-clang-unaligned-access-v1-1-b7b0fa541daa@kernel.org/ Suggested-by: Arnd Bergmann Link: https://lore.kernel.org/linux-kbuild/29b2e736-d462-45b7-a0a9-85f8d8a3de56@app.fastmail.com/ Signed-off-by: Thomas Weißschuh Acked-by: Wei Liu (Microsoft) Tested-by: Nicolas Schier Reviewed-by: Nicolas Schier Acked-by: Greg Kroah-Hartman Link: https://patch.msgid.link/20260115-kbuild-alignment-vbox-v1-1-076aed1623ff@linutronix.de Signed-off-by: Nathan Chancellor --- include/uapi/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index aaa502a7bff4..1749b35ab2c2 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -362,7 +362,7 @@ struct hv_kvp_exchg_msg_value { __u8 value[HV_KVP_EXCHANGE_MAX_VALUE_SIZE]; __u32 value_u32; __u64 value_u64; - }; + } __attribute__((packed)); } __attribute__((packed)); struct hv_kvp_msg_enumerate { -- cgit v1.2.3 From c25d01e1c4f2d43f47af87c00e223f5ca7c71792 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Thu, 15 Jan 2026 08:35:45 +0100 Subject: virt: vbox: uapi: Mark inner unions in packed structs as packed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The unpacked unions within a packed struct generates alignment warnings on clang for 32-bit ARM: ./usr/include/linux/vbox_vmmdev_types.h:239:4: error: field u within 'struct vmmdev_hgcm_function_parameter32' is less aligned than 'union (unnamed union at ./usr/include/linux/vbox_vmmdev_types.h:223:2)' and is usually due to 'struct vmmdev_hgcm_function_parameter32' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] 239 | } u; | ^ ./usr/include/linux/vbox_vmmdev_types.h:254:6: error: field u within 'struct vmmdev_hgcm_function_parameter64::(anonymous union)::(unnamed at ./usr/include/linux/vbox_vmmdev_types.h:249:3)' is less aligned than 'union (unnamed union at ./usr/include/linux/vbox_vmmdev_types.h:251:4)' and is usually due to 'struct vmmdev_hgcm_function_parameter64::(anonymous union)::(unnamed at ./usr/include/linux/vbox_vmmdev_types.h:249:3)' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] With the recent changes to compile-test the UAPI headers in more cases, these warning in combination with CONFIG_WERROR breaks the build. Fix the warnings. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202512140314.DzDxpIVn-lkp@intel.com/ Reported-by: Nathan Chancellor Closes: https://lore.kernel.org/linux-kbuild/20260110-uapi-test-disable-headers-arm-clang-unaligned-access-v1-1-b7b0fa541daa@kernel.org/ Suggested-by: Arnd Bergmann Link: https://lore.kernel.org/linux-kbuild/29b2e736-d462-45b7-a0a9-85f8d8a3de56@app.fastmail.com/ Signed-off-by: Thomas Weißschuh Tested-by: Nicolas Schier Reviewed-by: Nicolas Schier Acked-by: Greg Kroah-Hartman Link: https://patch.msgid.link/20260115-kbuild-alignment-vbox-v1-2-076aed1623ff@linutronix.de Signed-off-by: Nathan Chancellor --- include/uapi/linux/vbox_vmmdev_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vbox_vmmdev_types.h b/include/uapi/linux/vbox_vmmdev_types.h index 6073858d52a2..11f3627c3729 100644 --- a/include/uapi/linux/vbox_vmmdev_types.h +++ b/include/uapi/linux/vbox_vmmdev_types.h @@ -236,7 +236,7 @@ struct vmmdev_hgcm_function_parameter32 { /** Relative to the request header. */ __u32 offset; } page_list; - } u; + } __packed u; } __packed; VMMDEV_ASSERT_SIZE(vmmdev_hgcm_function_parameter32, 4 + 8); @@ -251,7 +251,7 @@ struct vmmdev_hgcm_function_parameter64 { union { __u64 phys_addr; __u64 linear_addr; - } u; + } __packed u; } __packed pointer; struct { /** Size of the buffer described by the page list. */ -- cgit v1.2.3 From 150a04d817d8f5be5a4f92799827cdc8d7e45989 Mon Sep 17 00:00:00 2001 From: Bill Wendling Date: Fri, 16 Jan 2026 00:57:57 +0000 Subject: compiler_types.h: Attributes: Add __counted_by_ptr macro Introduce __counted_by_ptr(), which works like __counted_by(), but for pointer struct members. struct foo { int a, b, c; char *buffer __counted_by_ptr(bytes); short nr_bars; struct bar *bars __counted_by_ptr(nr_bars); size_t bytes; }; Because "counted_by" can only be applied to pointer members in very recent compiler versions, its application ends up needing to be distinct from flexibe array "counted_by" annotations, hence a separate macro. This is a reworking of Kees' previous patch [1]. Link: https://lore.kernel.org/all/20251020220118.1226740-1-kees@kernel.org/ [1] Co-developed-by: Kees Cook Signed-off-by: Bill Wendling Link: https://patch.msgid.link/20260116005838.2419118-1-morbo@google.com Signed-off-by: Kees Cook --- include/uapi/linux/stddef.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 9a28f7d9a334..111b097ec00b 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -72,6 +72,10 @@ #define __counted_by_be(m) #endif +#ifndef __counted_by_ptr +#define __counted_by_ptr(m) +#endif + #ifdef __KERNEL__ #define __kernel_nonstring __nonstring #else -- cgit v1.2.3 From ca9d74eb5f6aea6eee746aae648382332dbcf24e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 13 Jan 2026 08:44:17 +0100 Subject: uapi: add INT_MAX and INT_MIN constants MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some UAPI headers use INT_MAX and INT_MIN. Currently they include for their definitions, which introduces a problematic dependency on libc. Add custom, namespaced definitions of INT_MAX and INT_MIN using the same values as the regular kernel code. These definitions are not added to uapi/linux/limits.h, as that header will conflict with libc definitions on some platforms. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20260113-uapi-limits-v2-1-93c20f4b2c1a@linutronix.de Signed-off-by: Jakub Kicinski --- include/uapi/linux/typelimits.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 include/uapi/linux/typelimits.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/typelimits.h b/include/uapi/linux/typelimits.h new file mode 100644 index 000000000000..8166c639b518 --- /dev/null +++ b/include/uapi/linux/typelimits.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_TYPELIMITS_H +#define _UAPI_LINUX_TYPELIMITS_H + +#define __KERNEL_INT_MAX ((int)(~0U >> 1)) +#define __KERNEL_INT_MIN (-__KERNEL_INT_MAX - 1) + +#endif /* _UAPI_LINUX_TYPELIMITS_H */ -- cgit v1.2.3 From a8a11e5237aed71b7f5f9d33c554ef06fe974311 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 13 Jan 2026 08:44:18 +0100 Subject: ethtool: uapi: Use UAPI definition of INT_MAX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using to gain access to INT_MAX introduces a dependency on a libc, which UAPI headers should not do. Use the equivalent UAPI constant. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20260113-uapi-limits-v2-2-93c20f4b2c1a@linutronix.de Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index bbfe6e1cf01b..ce9aeb65a8e1 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -15,13 +15,10 @@ #define _UAPI_LINUX_ETHTOOL_H #include +#include #include #include -#ifndef __KERNEL__ -#include /* for INT_MAX */ -#endif - /* All structures exposed to userland should be defined such that they * have the same layout for 32-bit and 64-bit userland. */ @@ -2216,7 +2213,7 @@ enum ethtool_link_mode_bit_indices { static inline int ethtool_validate_speed(__u32 speed) { - return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN; + return speed <= __KERNEL_INT_MAX || speed == (__u32)SPEED_UNKNOWN; } /* Duplex, half or full. */ -- cgit v1.2.3 From 0b3877bec78b0f26a280078a15f8992426de1db7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 13 Jan 2026 08:44:19 +0100 Subject: netfilter: uapi: Use UAPI definition of INT_MAX and INT_MIN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using to gain access to INT_MAX and INT_MIN introduces a dependency on a libc, which UAPI headers should not do. Use the equivalent UAPI constants. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20260113-uapi-limits-v2-3-93c20f4b2c1a@linutronix.de Signed-off-by: Jakub Kicinski --- include/uapi/linux/netfilter_bridge.h | 9 +++------ include/uapi/linux/netfilter_ipv4.h | 9 ++++----- include/uapi/linux/netfilter_ipv6.h | 7 +++---- 3 files changed, 10 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 1610fdbab98d..f6e8d1e05c97 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -10,10 +10,7 @@ #include #include #include - -#ifndef __KERNEL__ -#include /* for INT_MIN, INT_MAX */ -#endif +#include /* Bridge Hooks */ /* After promisc drops, checksum checks. */ @@ -31,14 +28,14 @@ #define NF_BR_NUMHOOKS 6 enum nf_br_hook_priorities { - NF_BR_PRI_FIRST = INT_MIN, + NF_BR_PRI_FIRST = __KERNEL_INT_MIN, NF_BR_PRI_NAT_DST_BRIDGED = -300, NF_BR_PRI_FILTER_BRIDGED = -200, NF_BR_PRI_BRNF = 0, NF_BR_PRI_NAT_DST_OTHER = 100, NF_BR_PRI_FILTER_OTHER = 200, NF_BR_PRI_NAT_SRC = 300, - NF_BR_PRI_LAST = INT_MAX, + NF_BR_PRI_LAST = __KERNEL_INT_MAX, }; #endif /* _UAPI__LINUX_BRIDGE_NETFILTER_H */ diff --git a/include/uapi/linux/netfilter_ipv4.h b/include/uapi/linux/netfilter_ipv4.h index 155e77d6a42d..439d3c59862b 100644 --- a/include/uapi/linux/netfilter_ipv4.h +++ b/include/uapi/linux/netfilter_ipv4.h @@ -7,12 +7,11 @@ #include +#include /* only for userspace compatibility */ #ifndef __KERNEL__ -#include /* for INT_MIN, INT_MAX */ - /* IP Hooks */ /* After promisc drops, checksum checks. */ #define NF_IP_PRE_ROUTING 0 @@ -28,7 +27,7 @@ #endif /* ! __KERNEL__ */ enum nf_ip_hook_priorities { - NF_IP_PRI_FIRST = INT_MIN, + NF_IP_PRI_FIRST = __KERNEL_INT_MIN, NF_IP_PRI_RAW_BEFORE_DEFRAG = -450, NF_IP_PRI_CONNTRACK_DEFRAG = -400, NF_IP_PRI_RAW = -300, @@ -41,8 +40,8 @@ enum nf_ip_hook_priorities { NF_IP_PRI_NAT_SRC = 100, NF_IP_PRI_SELINUX_LAST = 225, NF_IP_PRI_CONNTRACK_HELPER = 300, - NF_IP_PRI_CONNTRACK_CONFIRM = INT_MAX, - NF_IP_PRI_LAST = INT_MAX, + NF_IP_PRI_CONNTRACK_CONFIRM = __KERNEL_INT_MAX, + NF_IP_PRI_LAST = __KERNEL_INT_MAX, }; /* Arguments for setsockopt SOL_IP: */ diff --git a/include/uapi/linux/netfilter_ipv6.h b/include/uapi/linux/netfilter_ipv6.h index 80aa9b0799af..0e40d00b37fa 100644 --- a/include/uapi/linux/netfilter_ipv6.h +++ b/include/uapi/linux/netfilter_ipv6.h @@ -10,12 +10,11 @@ #include +#include /* only for userspace compatibility */ #ifndef __KERNEL__ -#include /* for INT_MIN, INT_MAX */ - /* IP6 Hooks */ /* After promisc drops, checksum checks. */ #define NF_IP6_PRE_ROUTING 0 @@ -32,7 +31,7 @@ enum nf_ip6_hook_priorities { - NF_IP6_PRI_FIRST = INT_MIN, + NF_IP6_PRI_FIRST = __KERNEL_INT_MIN, NF_IP6_PRI_RAW_BEFORE_DEFRAG = -450, NF_IP6_PRI_CONNTRACK_DEFRAG = -400, NF_IP6_PRI_RAW = -300, @@ -45,7 +44,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_NAT_SRC = 100, NF_IP6_PRI_SELINUX_LAST = 225, NF_IP6_PRI_CONNTRACK_HELPER = 300, - NF_IP6_PRI_LAST = INT_MAX, + NF_IP6_PRI_LAST = __KERNEL_INT_MAX, }; -- cgit v1.2.3 From 7d8b06ecc45bd679dec58d2cc2bd86223d4e076d Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 15 Jan 2026 06:08:02 +0000 Subject: iommu/amd: Add support for hw_info for iommu capability query AMD IOMMU Extended Feature (EFR) and Extended Feature 2 (EFR2) registers specify features supported by each IOMMU hardware instance. The IOMMU driver checks each feature-specific bits before enabling each feature at run time. For IOMMUFD, the hypervisor passes the raw value of amd_iommu_efr and amd_iommu_efr2 to VMM via iommufd IOMMU_DEVICE_GET_HW_INFO ioctl. Reviewed-by: Nicolin Chen Reviewed-by: Vasant Hegde Reviewed-by: Jason Gunthorpe Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- include/uapi/linux/iommufd.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 2c41920b641d..3db37f6042a0 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -623,6 +623,32 @@ struct iommu_hw_info_tegra241_cmdqv { __u8 __reserved; }; +/** + * struct iommu_hw_info_amd - AMD IOMMU device info + * + * @efr : Value of AMD IOMMU Extended Feature Register (EFR) + * @efr2: Value of AMD IOMMU Extended Feature 2 Register (EFR2) + * + * Please See description of these registers in the following sections of + * the AMD I/O Virtualization Technology (IOMMU) Specification. + * (https://docs.amd.com/v/u/en-US/48882_3.10_PUB) + * + * - MMIO Offset 0030h IOMMU Extended Feature Register + * - MMIO Offset 01A0h IOMMU Extended Feature 2 Register + * + * Note: The EFR and EFR2 are raw values reported by hardware. + * VMM is responsible to determine the appropriate flags to be exposed to + * the VM since cetertain features are not currently supported by the kernel + * for HW-vIOMMU. + * + * Current VMM-allowed list of feature flags are: + * - EFR[GTSup, GASup, GioSup, PPRSup, EPHSup, GATS, GLX, PASmax] + */ +struct iommu_hw_info_amd { + __aligned_u64 efr; + __aligned_u64 efr2; +}; + /** * enum iommu_hw_info_type - IOMMU Hardware Info Types * @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware @@ -632,6 +658,7 @@ struct iommu_hw_info_tegra241_cmdqv { * @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type * @IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM * SMMUv3) info type + * @IOMMU_HW_INFO_TYPE_AMD: AMD IOMMU info type */ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_NONE = 0, @@ -639,6 +666,7 @@ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2, IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV = 3, + IOMMU_HW_INFO_TYPE_AMD = 4, }; /** -- cgit v1.2.3 From e05698c10d980ac0a0b57ed81ec9353b9e9533c6 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 15 Jan 2026 06:08:06 +0000 Subject: iommufd: Introduce data struct for AMD nested domain allocation Introduce IOMMU_HWPT_DATA_AMD_GUEST data type for IOMMU guest page table, which is used for stage-1 in nested translation. The data structure contains information necessary for setting up the AMD HW-vIOMMU support. Reviewed-by: Jason Gunthorpe Reviewed-by: Nicolin Chen Reviewed-by: Vasant Hegde Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- include/uapi/linux/iommufd.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 3db37f6042a0..1dafbc552d37 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -465,16 +465,27 @@ struct iommu_hwpt_arm_smmuv3 { __aligned_le64 ste[2]; }; +/** + * struct iommu_hwpt_amd_guest - AMD IOMMU guest I/O page table data + * (IOMMU_HWPT_DATA_AMD_GUEST) + * @dte: Guest Device Table Entry (DTE) + */ +struct iommu_hwpt_amd_guest { + __aligned_u64 dte[4]; +}; + /** * enum iommu_hwpt_data_type - IOMMU HWPT Data Type * @IOMMU_HWPT_DATA_NONE: no data * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table * @IOMMU_HWPT_DATA_ARM_SMMUV3: ARM SMMUv3 Context Descriptor Table + * @IOMMU_HWPT_DATA_AMD_GUEST: AMD IOMMU guest page table */ enum iommu_hwpt_data_type { IOMMU_HWPT_DATA_NONE = 0, IOMMU_HWPT_DATA_VTD_S1 = 1, IOMMU_HWPT_DATA_ARM_SMMUV3 = 2, + IOMMU_HWPT_DATA_AMD_GUEST = 3, }; /** -- cgit v1.2.3 From cd16edba1c6a24af138e1a5ded2711231fffa99f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 4 Dec 2025 11:19:10 +0100 Subject: ext4: fix ext4_tune_sb_params padding The padding at the end of struct ext4_tune_sb_params is architecture specific and in particular is different between x86-32 and x86-64, since the __u64 member only enforces struct alignment on the latter. This shows up as a new warning when test-building the headers with -Wpadded: include/linux/ext4.h:144:1: error: padding struct size to alignment boundary with 4 bytes [-Werror=padded] All members inside the structure are naturally aligned, so the only difference here is the amount of padding at the end. Make the padding explicit, to have a consistent sizeof(struct ext4_tune_sb_params) of 232 on all architectures and avoid adding compat ioctl handling for EXT4_IOC_GET_TUNE_SB_PARAM/EXT4_IOC_SET_TUNE_SB_PARAM. This is an ABI break on x86-32 but hopefully this can go into 6.18.y early enough as a fixup so no actual users will be affected. Alternatively, the kernel could handle the ioctl commands for both sizes (232 and 228 bytes) on all architectures. Fixes: 04a91570ac67 ("ext4: implemet new ioctls to set and get superblock parameters") Signed-off-by: Arnd Bergmann Reviewed-by: Jan Kara Link: https://patch.msgid.link/20251204101914.1037148-1-arnd@kernel.org Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- include/uapi/linux/ext4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ext4.h b/include/uapi/linux/ext4.h index 411dcc1e4a35..9c683991c32f 100644 --- a/include/uapi/linux/ext4.h +++ b/include/uapi/linux/ext4.h @@ -139,7 +139,7 @@ struct ext4_tune_sb_params { __u32 clear_feature_incompat_mask; __u32 clear_feature_ro_compat_mask; __u8 mount_opts[64]; - __u8 pad[64]; + __u8 pad[68]; }; #define EXT4_TUNE_FL_ERRORS_BEHAVIOR 0x00000001 -- cgit v1.2.3 From 8a42938a28941da29bf3e4cd2af877b0d5d929e1 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Wed, 7 Jan 2026 14:22:54 +0200 Subject: wifi: nl80211: ignore cluster id after NAN started After NAN was started, cluster id updates from the user space should not happen, since the device already started a cluster with the previousely provided id. Since NL80211_CMD_CHANGE_NAN_CONFIG requires to set the full NAN configuration, we can't require that NL80211_NAN_CONF_CLUSTER_ID won't be included in this command, and keeping the last confgiured value just to be able to compare it against the new one seems a bit overkill. Therefore, just ignore cluster id in this command and clarify the documentation. Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260107142229.fb55e5853269.I10d18c8f69d98b28916596d6da4207c15ea4abb5@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index eb92296457c9..b0f050e36fa4 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -11,7 +11,7 @@ * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2025 Intel Corporation + * Copyright (C) 2018-2026 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 @@ -7454,6 +7454,8 @@ enum nl80211_nan_band_conf_attributes { * address that can take values from 50-6F-9A-01-00-00 to * 50-6F-9A-01-FF-FF. This attribute is optional. If not present, * a random Cluster ID will be chosen. + * This attribute will be ignored in NL80211_CMD_CHANGE_NAN_CONFIG + * since after NAN was started, the cluster ID can no longer change. * @NL80211_NAN_CONF_EXTRA_ATTRS: Additional NAN attributes to be * published in the beacons. This is an optional byte array. * @NL80211_NAN_CONF_VENDOR_ELEMS: Vendor-specific elements that will -- cgit v1.2.3 From a9927022c4491ba44249af079e8799ce56f8053c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 15 Jan 2026 12:56:44 +0100 Subject: net: ethtool: Add support for 80Gbps speed USB4 v2 link used in peer-to-peer networking is symmetric 80Gbps so in order to support reading this link speed, add support for it to ethtool. Signed-off-by: Mika Westerberg Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20260115115646.328898-3-mika.westerberg@linux.intel.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index ce9aeb65a8e1..b74b80508553 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2203,6 +2203,7 @@ enum ethtool_link_mode_bit_indices { #define SPEED_40000 40000 #define SPEED_50000 50000 #define SPEED_56000 56000 +#define SPEED_80000 80000 #define SPEED_100000 100000 #define SPEED_200000 200000 #define SPEED_400000 400000 -- cgit v1.2.3 From 50b359896fe55d0443ed550e1fabba71d242031a Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Sun, 18 Jan 2026 09:51:15 +0200 Subject: wifi: cfg80211: ignore link disabled flag from userspace When the AP has an advertised TID to Link Mapping (TTLM) it shall include the element in the association response. As such, when this element is present it needs to be used for the currently dormant links. See Draft P802.11REVmf_D1.0 section 35.3.7.2.3 ("Negotiation of TTLM") for the details. The flag is also not usable in case userspace wants to specify a negotiated TTLM during association. Note that for the link reconfiguration case, mac80211 did not use the information. Draft P802.11REVmf_D1.0 states in section 35.3.6.4 ("Link reconfiguration to the setup links) that we "shall operate with all the TIDs mapped to the newly added links ..." All this means that the flag is not needed. The implementation should parse the information from the association response. Signed-off-by: Benjamin Berg Reviewed-by: Johannes Berg Reviewed-by: Ilan Peer Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260118093904.754e057896a5.Ifd06f5ef839a93bfd54d0593dc932870f95f3242@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8134f10e4e6c..8433bac48112 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2880,8 +2880,9 @@ enum nl80211_commands { * index. If the userspace includes more RNR elements than number of * MBSSID elements then these will be added in every EMA beacon. * - * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is - * disabled. + * @NL80211_ATTR_MLO_LINK_DISABLED: Unused. It was used to indicate that a link + * is disabled during association. However, the AP will send the + * information by including a TTLM in the association response. * * @NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA: Include BSS usage data, i.e. * include BSSes that can only be used in restricted scenarios and/or -- cgit v1.2.3 From a5546e18f77c0cb15d434bf5b92647687fe483e3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 15 Jan 2026 09:25:48 +0100 Subject: net: Add queue-create operation Add a ynl netdev family operation called queue-create that creates a new queue on a netdevice: name: queue-create attribute-set: queue flags: [admin-perm] do: request: attributes: - ifindex - type - lease reply: &queue-create-op attributes: - id This is a generic operation such that it can be extended for various use cases in future. Right now it is mandatory to specify ifindex, the queue type which is enforced to rx and a lease. The newly created queue id is returned to the caller. A queue from a virtual device can have a lease which refers to another queue from a physical device. This is useful for memory providers and AF_XDP operations which take an ifindex and queue id to allow applications to bind against virtual devices in containers. The lease couples both queues together and allows to proxy the operations from a virtual device in a container to the physical device. In future, the nested lease attribute can be lifted and made optional for other use-cases such as dynamic queue creation for physical netdevs. The lack of lease and the specification of the physical device as an ifindex will imply that we need a real queue to be allocated. Similarly, the queue type enforcement to rx can then be lifted as well to support tx. An early implementation had only driver-specific integration [0], but in order for other virtual devices to reuse, it makes sense to have this as a generic API in core net. For leasing queues, the virtual netdev must have real_num_rx_queue less than num_rx_queues at the time of calling queue-create. The queue-type must be rx as only rx queues are supported for leasing for now. We also enforce that the queue-create ifindex must point to a virtual device, and that the nested lease attribute's ifindex must point to a physical device. The nested lease attribute set contains a netns-id attribute which is currently only intended for dumping as part of the queue-get operation. Also, it is modeled as an s32 type similarly as done elsewhere in the stack. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Link: https://bpfconf.ebpf.io/bpfconf2025/bpfconf2025_material/lsfmmbpf_2025_netkit_borkmann.pdf [0] Acked-by: Stanislav Fomichev Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20260115082603.219152-2-daniel@iogearbox.net Signed-off-by: Paolo Abeni --- include/uapi/linux/netdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e0b579a1df4f..7df1056a35fd 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -160,6 +160,7 @@ enum { NETDEV_A_QUEUE_DMABUF, NETDEV_A_QUEUE_IO_URING, NETDEV_A_QUEUE_XSK, + NETDEV_A_QUEUE_LEASE, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) @@ -202,6 +203,15 @@ enum { NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) }; +enum { + NETDEV_A_LEASE_IFINDEX = 1, + NETDEV_A_LEASE_QUEUE, + NETDEV_A_LEASE_NETNS_ID, + + __NETDEV_A_LEASE_MAX, + NETDEV_A_LEASE_MAX = (__NETDEV_A_LEASE_MAX - 1) +}; + enum { NETDEV_A_DMABUF_IFINDEX = 1, NETDEV_A_DMABUF_QUEUES, @@ -228,6 +238,7 @@ enum { NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, NETDEV_CMD_BIND_TX, + NETDEV_CMD_QUEUE_CREATE, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From b5c3fa4a0b16d4a7d0bd0e5626a13fec0024030a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 15 Jan 2026 09:25:56 +0100 Subject: netkit: Add single device mode for netkit Add a single device mode for netkit instead of netkit pairs. The primary target for the paired devices is to connect network namespaces, of course, and support has been implemented in projects like Cilium [0]. For the rxq leasing the plan is to support two main scenarios related to single device mode: * For the use-case of io_uring zero-copy, the control plane can either set up a netkit pair where the peer device can perform rxq leasing which is then tied to the lifetime of the peer device, or the control plane can use a regular netkit pair to connect the hostns to a Pod/container and dynamically add/remove rxq leasing through a single device without having to interrupt the device pair. In the case of io_uring, the memory pool is used as skb non-linear pages, and thus the skb will go its way through the regular stack into netkit. Things like the netkit policy when no BPF is attached or skb scrubbing etc apply as-is in case the paired devices are used, or if the backend memory is tied to the single device and traffic goes through a paired device. * For the use-case of AF_XDP, the control plane needs to use netkit in the single device mode. The single device mode currently enforces only a pass policy when no BPF is attached, and does not yet support BPF link attachments for AF_XDP. skbs sent to that device get dropped at the moment. Given AF_XDP operates at a lower layer of the stack tying this to the netkit pair did not make sense. In future, the plan is to allow BPF at the XDP layer which can: i) process traffic coming from the AF_XDP application (e.g. QEMU with AF_XDP backend) to filter egress traffic or to push selected egress traffic up to the single netkit device to the local stack (e.g. DHCP requests), and ii) vice-versa skbs sent to the single netkit into the AF_XDP application (e.g. DHCP replies). Also, the control-plane can dynamically manage rxq leasing for the single netkit device without having to interrupt (e.g. down/up cycle) the main netkit pair for the Pod which has traffic going in and out. Signed-off-by: Daniel Borkmann Co-developed-by: David Wei Signed-off-by: David Wei Reviewed-by: Jordan Rife Reviewed-by: Nikolay Aleksandrov Link: https://docs.cilium.io/en/stable/operations/performance/tuning/#netkit-device-mode [0] Link: https://patch.msgid.link/20260115082603.219152-10-daniel@iogearbox.net Signed-off-by: Paolo Abeni --- include/uapi/linux/if_link.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3b491d96e52e..bbd565757298 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1296,6 +1296,11 @@ enum netkit_mode { NETKIT_L3, }; +enum netkit_pairing { + NETKIT_DEVICE_PAIR, + NETKIT_DEVICE_SINGLE, +}; + /* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to * the BPF program if attached. This also means the latter can * consume the two fields if they were populated earlier. @@ -1320,6 +1325,7 @@ enum { IFLA_NETKIT_PEER_SCRUB, IFLA_NETKIT_HEADROOM, IFLA_NETKIT_TAILROOM, + IFLA_NETKIT_PAIRING, __IFLA_NETKIT_MAX, }; #define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) -- cgit v1.2.3 From 8766d61a1d33cb5f15bfdd6ce9832bbe1fc649c2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 20 Jan 2026 18:04:55 -0800 Subject: Revert "Merge branch 'netkit-support-for-io_uring-zero-copy-and-af_xdp'" This reverts commit 77b9c4a438fc66e2ab004c411056b3fb71a54f2c, reversing changes made to 4515ec4ad58a37e70a9e1256c0b993958c9b7497: 931420a2fc36 ("selftests/net: Add netkit container tests") ab771c938d9a ("selftests/net: Make NetDrvContEnv support queue leasing") 6be87fbb2776 ("selftests/net: Add env for container based tests") 61d99ce3dfc2 ("selftests/net: Add bpf skb forwarding program") 920da3634194 ("netkit: Add xsk support for af_xdp applications") eef51113f8af ("netkit: Add netkit notifier to check for unregistering devices") b5ef109d22d4 ("netkit: Implement rtnl_link_ops->alloc and ndo_queue_create") b5c3fa4a0b16 ("netkit: Add single device mode for netkit") 0073d2fd679d ("xsk: Proxy pool management for leased queues") 1ecea95dd3b5 ("xsk: Extend xsk_rcv_check validation") 804bf334d08a ("net: Proxy netdev_queue_get_dma_dev for leased queues") 0caa9a8ddec3 ("net: Proxy net_mp_{open,close}_rxq for leased queues") ff8889ff9107 ("net, ethtool: Disallow leased real rxqs to be resized") 9e2103f36110 ("net: Add lease info to queue-get response") 31127deddef4 ("net: Implement netdev_nl_queue_create_doit") a5546e18f77c ("net: Add queue-create operation") The series will conflict with io_uring work, and the code needs more polish. Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 6 ------ include/uapi/linux/netdev.h | 11 ----------- 2 files changed, 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index bbd565757298..3b491d96e52e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1296,11 +1296,6 @@ enum netkit_mode { NETKIT_L3, }; -enum netkit_pairing { - NETKIT_DEVICE_PAIR, - NETKIT_DEVICE_SINGLE, -}; - /* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to * the BPF program if attached. This also means the latter can * consume the two fields if they were populated earlier. @@ -1325,7 +1320,6 @@ enum { IFLA_NETKIT_PEER_SCRUB, IFLA_NETKIT_HEADROOM, IFLA_NETKIT_TAILROOM, - IFLA_NETKIT_PAIRING, __IFLA_NETKIT_MAX, }; #define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 7df1056a35fd..e0b579a1df4f 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -160,7 +160,6 @@ enum { NETDEV_A_QUEUE_DMABUF, NETDEV_A_QUEUE_IO_URING, NETDEV_A_QUEUE_XSK, - NETDEV_A_QUEUE_LEASE, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) @@ -203,15 +202,6 @@ enum { NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) }; -enum { - NETDEV_A_LEASE_IFINDEX = 1, - NETDEV_A_LEASE_QUEUE, - NETDEV_A_LEASE_NETNS_ID, - - __NETDEV_A_LEASE_MAX, - NETDEV_A_LEASE_MAX = (__NETDEV_A_LEASE_MAX - 1) -}; - enum { NETDEV_A_DMABUF_IFINDEX = 1, NETDEV_A_DMABUF_QUEUES, @@ -238,7 +228,6 @@ enum { NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, NETDEV_CMD_BIND_TX, - NETDEV_CMD_QUEUE_CREATE, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From 64dd89ae01f2708a508e028c28b7906e4702a9a7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 15 Dec 2025 12:57:53 -0500 Subject: mm/block/fs: remove laptop_mode Laptop mode was introduced to save battery, by delaying and consolidating writes and thereby maximize the time rotating hard drives wouldn't have to spin. Luckily, rotating hard drives, with their high spin-up times and power draw, are a thing of the past for battery-powered devices. Reclaim has also since changed to not write single filesystem pages anymore, and regular filesystem writeback is lumpy by design. The juice doesn't appear worth the squeeze anymore. The footprint of the feature is small, but nevertheless it's a complicating factor in mm, block, filesystems. Developers don't think about it, and it likely hasn't been tested with new reclaim and writeback changes in years. Let's sunset it. Keep the sysctl with a deprecation warning around for a few more cycles, but remove all functionality behind it. [akpm@linux-foundation.org: fix Documentation/admin-guide/laptops/index.rst] Link: https://lkml.kernel.org/r/20251216185201.GH905277@cmpxchg.org Signed-off-by: Johannes Weiner Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Acked-by: Jens Axboe Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Deepanshu Kartikey Signed-off-by: Andrew Morton --- include/uapi/linux/sysctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 63d1464cb71c..6ea9ea8413fa 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -183,7 +183,7 @@ enum VM_LOWMEM_RESERVE_RATIO=20,/* reservation ratio for lower memory zones */ VM_MIN_FREE_KBYTES=21, /* Minimum free kilobytes to maintain */ VM_MAX_MAP_COUNT=22, /* int: Maximum number of mmaps/address-space */ - VM_LAPTOP_MODE=23, /* vm laptop mode */ + VM_BLOCK_DUMP=24, /* block dump mode */ VM_HUGETLB_GROUP=25, /* permitted hugetlb group */ VM_VFS_CACHE_PRESSURE=26, /* dcache/icache reclaim pressure */ -- cgit v1.2.3 From fa05705107a40131a8335ad37817153709261738 Mon Sep 17 00:00:00 2001 From: Detlev Casanova Date: Fri, 9 Jan 2026 11:15:18 -0500 Subject: media: v4l2-ctrls: Add hevc_ext_sps_[ls]t_rps controls The vdpu381 decoder found on newer Rockchip SoC need the information from the long term and short term ref pic sets from the SPS. So far, it wasn't included in the v4l2 API, so add it with new dynamic sized controls. Each element of the hevc_ext_sps_lt_rps array contains the long term ref pic set at that index. Each element of the hevc_ext_sps_st_rps contains the short term ref pic set at that index, as the raw data. It is the role of the drivers to calculate the reference sets values. Reviewed-by: Nicolas Dufresne Signed-off-by: Detlev Casanova Signed-off-by: Nicolas Dufresne Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-controls.h | 61 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/videodev2.h | 2 ++ 2 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 572622e4535e..68dd0c4e47b2 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -2101,6 +2101,8 @@ struct v4l2_ctrl_mpeg2_quantisation { #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) +#define V4L2_CID_STATELESS_HEVC_EXT_SPS_ST_RPS (V4L2_CID_CODEC_STATELESS_BASE + 408) +#define V4L2_CID_STATELESS_HEVC_EXT_SPS_LT_RPS (V4L2_CID_CODEC_STATELESS_BASE + 409) enum v4l2_stateless_hevc_decode_mode { V4L2_STATELESS_HEVC_DECODE_MODE_SLICE_BASED, @@ -2556,6 +2558,65 @@ struct v4l2_ctrl_hevc_scaling_matrix { __u8 scaling_list_dc_coef_32x32[2]; }; +#define V4L2_HEVC_EXT_SPS_ST_RPS_FLAG_INTER_REF_PIC_SET_PRED 0x1 + +/* + * struct v4l2_ctrl_hevc_ext_sps_st_rps - HEVC short term RPS parameters + * + * Dynamic size 1-dimension array for short term RPS. The number of elements + * is v4l2_ctrl_hevc_sps::num_short_term_ref_pic_sets. It can contain up to 65 elements. + * + * @delta_idx_minus1: Specifies the delta compare to the index. See details in section 7.4.8 + * "Short-term reference picture set semantics" of the specification. + * @delta_rps_sign: Sign of the delta as specified in section 7.4.8 "Short-term reference picture + * set semantics" of the specification. + * @abs_delta_rps_minus1: Absolute delta RPS as specified in section 7.4.8 "Short-term reference + * picture set semantics" of the specification. + * @num_negative_pics: Number of short-term RPS entries that have picture order count values less + * than the picture order count value of the current picture. + * @num_positive_pics: Number of short-term RPS entries that have picture order count values + * greater than the picture order count value of the current picture. + * @used_by_curr_pic: Bit j specifies if short-term RPS j is used by the current picture. + * @use_delta_flag: Bit j equals to 1 specifies that the j-th entry in the source candidate + * short-term RPS is included in this candidate short-term RPS. + * @delta_poc_s0_minus1: Specifies the negative picture order count delta for the i-th entry in + * the short-term RPS. See details in section 7.4.8 "Short-term reference + * picture set semantics" of the specification. + * @delta_poc_s1_minus1: Specifies the positive picture order count delta for the i-th entry in + * the short-term RPS. See details in section 7.4.8 "Short-term reference + * picture set semantics" of the specification. + * @flags: See V4L2_HEVC_EXT_SPS_ST_RPS_FLAG_{} + */ +struct v4l2_ctrl_hevc_ext_sps_st_rps { + __u8 delta_idx_minus1; + __u8 delta_rps_sign; + __u8 num_negative_pics; + __u8 num_positive_pics; + __u32 used_by_curr_pic; + __u32 use_delta_flag; + __u16 abs_delta_rps_minus1; + __u16 delta_poc_s0_minus1[16]; + __u16 delta_poc_s1_minus1[16]; + __u16 flags; +}; + +#define V4L2_HEVC_EXT_SPS_LT_RPS_FLAG_USED_LT 0x1 + +/* + * struct v4l2_ctrl_hevc_ext_sps_lt_rps - HEVC long term RPS parameters + * + * Dynamic size 1-dimension array for long term RPS. The number of elements + * is v4l2_ctrl_hevc_sps::num_long_term_ref_pics_sps. It can contain up to 65 elements. + * + * @lt_ref_pic_poc_lsb_sps: picture order count modulo MaxPicOrderCntLsb of the i-th candidate + * long-term reference picture. + * @flags: See V4L2_HEVC_EXT_SPS_LT_RPS_FLAG_{} + */ +struct v4l2_ctrl_hevc_ext_sps_lt_rps { + __u16 lt_ref_pic_poc_lsb_sps; + __u16 flags; +}; + /* Stateless VP9 controls */ #define V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED 0x1 diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 848e86617d5c..eda4492e40dc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1986,6 +1986,8 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS = 0x0272, V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX = 0x0273, V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS = 0x0274, + V4L2_CTRL_TYPE_HEVC_EXT_SPS_ST_RPS = 0x0275, + V4L2_CTRL_TYPE_HEVC_EXT_SPS_LT_RPS = 0x0276, V4L2_CTRL_TYPE_AV1_SEQUENCE = 0x280, V4L2_CTRL_TYPE_AV1_TILE_GROUP_ENTRY = 0x281, -- cgit v1.2.3 From f5f2bad67a45cd1ef6f5b727da104694a81b3666 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Jan 2026 08:31:49 +0100 Subject: block: make the new blkzoned UAPI constants discoverable The Linux 6.19 merge window added the new BLKREPORTZONESV2 ioctl, and with it the new BLK_ZONE_REP_CACHED and BLK_ZONE_COND_ACTIVE constants. The two constants are defined as part of enums, which makes it very painful for userspace to discover if they are present in the installed system headers. Use the #define to the same name trick to make them trivially discoverable using CPP directives. Fixes: 0bf0e2e46668 ("block: track zone conditions") Fixes: b30ffcdc0c15 ("block: introduce BLKREPORTZONESV2 ioctl") Reported-by: Andrey Albershteyn Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index e33f02703350..663836120966 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -81,7 +81,8 @@ enum blk_zone_cond { BLK_ZONE_COND_FULL = 0xE, BLK_ZONE_COND_OFFLINE = 0xF, - BLK_ZONE_COND_ACTIVE = 0xFF, + BLK_ZONE_COND_ACTIVE = 0xFF, /* added in Linux 6.19 */ +#define BLK_ZONE_COND_ACTIVE BLK_ZONE_COND_ACTIVE }; /** @@ -100,7 +101,8 @@ enum blk_zone_report_flags { BLK_ZONE_REP_CAPACITY = (1U << 0), /* Input flags */ - BLK_ZONE_REP_CACHED = (1U << 31), + BLK_ZONE_REP_CACHED = (1U << 31), /* added in Linux 6.19 */ +#define BLK_ZONE_REP_CACHED BLK_ZONE_REP_CACHED }; /** -- cgit v1.2.3 From d7a5da7a0f7fa7ff081140c4f6f971db98882703 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 15 Dec 2025 17:52:04 +0100 Subject: rseq: Add fields and constants for time slice extension Aside of a Kconfig knob add the following items: - Two flag bits for the rseq user space ABI, which allow user space to query the availability and enablement without a syscall. - A new member to the user space ABI struct rseq, which is going to be used to communicate request and grant between kernel and user space. - A rseq state struct to hold the kernel state of this - Documentation of the new mechanism Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20251215155708.669472597@linutronix.de --- include/uapi/linux/rseq.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 1b76d508400c..6afc219d1545 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -23,9 +23,15 @@ enum rseq_flags { }; enum rseq_cs_flags_bit { + /* Historical and unsupported bits */ RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0, RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1, RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2, + /* (3) Intentional gap to put new bits into a separate byte */ + + /* User read only feature flags */ + RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT = 4, + RSEQ_CS_FLAG_SLICE_EXT_ENABLED_BIT = 5, }; enum rseq_cs_flags { @@ -35,6 +41,11 @@ enum rseq_cs_flags { (1U << RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT), RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE = (1U << RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT), + + RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE = + (1U << RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT), + RSEQ_CS_FLAG_SLICE_EXT_ENABLED = + (1U << RSEQ_CS_FLAG_SLICE_EXT_ENABLED_BIT), }; /* @@ -53,6 +64,27 @@ struct rseq_cs { __u64 abort_ip; } __attribute__((aligned(4 * sizeof(__u64)))); +/** + * rseq_slice_ctrl - Time slice extension control structure + * @all: Compound value + * @request: Request for a time slice extension + * @granted: Granted time slice extension + * + * @request is set by user space and can be cleared by user space or kernel + * space. @granted is set and cleared by the kernel and must only be read + * by user space. + */ +struct rseq_slice_ctrl { + union { + __u32 all; + struct { + __u8 request; + __u8 granted; + __u16 __reserved; + }; + }; +}; + /* * struct rseq is aligned on 4 * 8 bytes to ensure it is always * contained within a single cache-line. @@ -141,6 +173,12 @@ struct rseq { */ __u32 mm_cid; + /* + * Time slice extension control structure. CPU local updates from + * kernel and user space. + */ + struct rseq_slice_ctrl slice_ctrl; + /* * Flexible array member at end of structure, after last feature field. */ -- cgit v1.2.3 From 28621ec2d46c6adf7d33a6facbd83e2fa566bd34 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 15 Dec 2025 17:52:12 +0100 Subject: rseq: Add prctl() to enable time slice extensions Implement a prctl() so that tasks can enable the time slice extension mechanism. This fails, when time slice extensions are disabled at compile time or on the kernel command line and when no rseq pointer is registered in the kernel. That allows to implement a single trivial check in the exit to user mode hotpath, to decide whether the whole mechanism needs to be invoked. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20251215155708.858717691@linutronix.de --- include/uapi/linux/prctl.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 51c4e8c82b1e..79944b7ae50a 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -386,4 +386,14 @@ struct prctl_mm_map { # define PR_FUTEX_HASH_SET_SLOTS 1 # define PR_FUTEX_HASH_GET_SLOTS 2 +/* RSEQ time slice extensions */ +#define PR_RSEQ_SLICE_EXTENSION 79 +# define PR_RSEQ_SLICE_EXTENSION_GET 1 +# define PR_RSEQ_SLICE_EXTENSION_SET 2 +/* + * Bits for RSEQ_SLICE_EXTENSION_GET/SET + * PR_RSEQ_SLICE_EXT_ENABLE: Enable + */ +# define PR_RSEQ_SLICE_EXT_ENABLE 0x01 + #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From d6200245c75e832af2087bc60ba2e6641a90eee9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 19 Jan 2026 11:23:57 +0100 Subject: rseq: Allow registering RSEQ with slice extension Since glibc cares about the number of syscalls required to initialize a new thread, allow initializing rseq with slice extension on. This avoids having to do another prctl(). Requested-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260121143207.814193010@infradead.org --- include/uapi/linux/rseq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 6afc219d1545..863c4a00a66b 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -19,7 +19,8 @@ enum rseq_cpu_id_state { }; enum rseq_flags { - RSEQ_FLAG_UNREGISTER = (1 << 0), + RSEQ_FLAG_UNREGISTER = (1 << 0), + RSEQ_FLAG_SLICE_EXT_DEFAULT_ON = (1 << 1), }; enum rseq_cs_flags_bit { -- cgit v1.2.3 From f174a9ffcd48d78a45d560c02ce4071ded036b53 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Jan 2026 10:29:22 +0800 Subject: KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots The main use of {LD,ST}64B* is to talk to a device, which is hopefully directly assigned to the guest and requires no additional handling. However, this does not preclude a VMM from exposing a virtual device to the guest, and to allow 64 byte accesses as part of the programming interface. A direct consequence of this is that we need to be able to forward such access to userspace. Given that such a contraption is very unlikely to ever exist, we choose to offer a limited service: userspace gets (as part of a new exit reason) the ESR, the IPA, and that's it. It is fully expected to handle the full semantics of the instructions, deal with ACCDATA, the return values and increment PC. Much fun. A canonical implementation can also simply inject an abort and be done with it. Frankly, don't try to do anything else unless you have time to waste. Acked-by: Arnd Bergmann Acked-by: Oliver Upton Signed-off-by: Marc Zyngier Signed-off-by: Yicong Yang Signed-off-by: Zhou Wang Signed-off-by: Will Deacon --- include/uapi/linux/kvm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dddb781b0507..88cca0e22ece 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -180,6 +180,7 @@ struct kvm_xen_exit { #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 #define KVM_EXIT_ARM_SEA 41 +#define KVM_EXIT_ARM_LDST64B 42 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -402,7 +403,7 @@ struct kvm_run { } eoi; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; - /* KVM_EXIT_ARM_NISV */ + /* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */ struct { __u64 esr_iss; __u64 fault_ipa; -- cgit v1.2.3 From 0f7afd80d81b739c4a9a6e4e24109ba1030c9c56 Mon Sep 17 00:00:00 2001 From: Terry Bowman Date: Wed, 14 Jan 2026 12:20:22 -0600 Subject: PCI: Move CXL DVSEC definitions into uapi/linux/pci_regs.h The CXL DVSECs are currently defined in cxl/core/cxlpci.h. These are not accessible to other subsystems. Move these to uapi/linux/pci_regs.h. The CXL DVSEC definitions will be renamed and reformatted to fit better with existing defines. Signed-off-by: Terry Bowman Reviewed-by: Dave Jiang Reviewed-by: Jonathan Cameron Reviewed-by: Dan Williams Signed-off-by: Dan Williams Acked-by: Bjorn Helgaas Link: https://patch.msgid.link/20260114182055.46029-2-terry.bowman@amd.com Signed-off-by: Dave Jiang --- include/uapi/linux/pci_regs.h | 64 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 59 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 3add74ae2594..6c4b6f19b18e 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1253,11 +1253,6 @@ #define PCI_DEV3_STA 0x0c /* Device 3 Status Register */ #define PCI_DEV3_STA_SEGMENT 0x8 /* Segment Captured (end-to-end flit-mode detected) */ -/* Compute Express Link (CXL r3.1, sec 8.1.5) */ -#define PCI_DVSEC_CXL_PORT 3 -#define PCI_DVSEC_CXL_PORT_CTL 0x0c -#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 - /* Integrity and Data Encryption Extended Capability */ #define PCI_IDE_CAP 0x04 #define PCI_IDE_CAP_LINK 0x1 /* Link IDE Stream Supported */ @@ -1338,4 +1333,63 @@ #define PCI_IDE_SEL_ADDR_3(x) (28 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) #define PCI_IDE_SEL_BLOCK_SIZE(nr_assoc) (20 + PCI_IDE_SEL_ADDR_BLOCK_SIZE * (nr_assoc)) +/* Compute Express Link (CXL r3.1, sec 8.1.5) */ +#define PCI_DVSEC_CXL_PORT 3 +#define PCI_DVSEC_CXL_PORT_CTL 0x0c +#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 + +/* + * Compute Express Link (CXL r3.2, sec 8.1) + * + * Note that CXL DVSEC id 3 and 7 to be ignored when the CXL link state + * is "disconnected" (CXL r3.2, sec 9.12.3). Re-enumerate these + * registers on downstream link-up events. + */ +#define PCI_DVSEC_HEADER1_LENGTH_MASK __GENMASK(31, 20) + +/* CXL 3.2 8.1.3: PCIe DVSEC for CXL Device */ +#define CXL_DVSEC_PCIE_DEVICE 0 +#define CXL_DVSEC_CAP_OFFSET 0xA +#define CXL_DVSEC_MEM_CAPABLE _BITUL(2) +#define CXL_DVSEC_HDM_COUNT_MASK __GENMASK(5, 4) +#define CXL_DVSEC_CTRL_OFFSET 0xC +#define CXL_DVSEC_MEM_ENABLE _BITUL(2) +#define CXL_DVSEC_RANGE_SIZE_HIGH(i) (0x18 + (i * 0x10)) +#define CXL_DVSEC_RANGE_SIZE_LOW(i) (0x1C + (i * 0x10)) +#define CXL_DVSEC_MEM_INFO_VALID _BITUL(0) +#define CXL_DVSEC_MEM_ACTIVE _BITUL(1) +#define CXL_DVSEC_MEM_SIZE_LOW_MASK __GENMASK(31, 28) +#define CXL_DVSEC_RANGE_BASE_HIGH(i) (0x20 + (i * 0x10)) +#define CXL_DVSEC_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) +#define CXL_DVSEC_MEM_BASE_LOW_MASK __GENMASK(31, 28) + +#define CXL_DVSEC_RANGE_MAX 2 + +/* CXL 3.2 8.1.4: Non-CXL Function Map DVSEC */ +#define CXL_DVSEC_FUNCTION_MAP 2 + +/* CXL 3.2 8.1.5: Extensions DVSEC for Ports */ +#define CXL_DVSEC_PORT 3 +#define CXL_DVSEC_PORT_CTL 0x0c +#define CXL_DVSEC_PORT_CTL_UNMASK_SBR 0x00000001 + +/* CXL 3.2 8.1.6: GPF DVSEC for CXL Port */ +#define CXL_DVSEC_PORT_GPF 4 +#define CXL_DVSEC_PORT_GPF_PHASE_1_CONTROL_OFFSET 0x0C +#define CXL_DVSEC_PORT_GPF_PHASE_1_TMO_BASE_MASK __GENMASK(3, 0) +#define CXL_DVSEC_PORT_GPF_PHASE_1_TMO_SCALE_MASK __GENMASK(11, 8) +#define CXL_DVSEC_PORT_GPF_PHASE_2_CONTROL_OFFSET 0xE +#define CXL_DVSEC_PORT_GPF_PHASE_2_TMO_BASE_MASK __GENMASK(3, 0) +#define CXL_DVSEC_PORT_GPF_PHASE_2_TMO_SCALE_MASK __GENMASK(11, 8) + +/* CXL 3.2 8.1.7: GPF DVSEC for CXL Device */ +#define CXL_DVSEC_DEVICE_GPF 5 + +/* CXL 3.2 8.1.9: Register Locator DVSEC */ +#define CXL_DVSEC_REG_LOCATOR 8 +#define CXL_DVSEC_REG_LOCATOR_BLOCK1_OFFSET 0xC +#define CXL_DVSEC_REG_LOCATOR_BIR_MASK __GENMASK(2, 0) +#define CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK __GENMASK(15, 8) +#define CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK __GENMASK(31, 16) + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 6612bd9ff0b1001cff5f5d79db6ce44427d2e99c Mon Sep 17 00:00:00 2001 From: Terry Bowman Date: Wed, 14 Jan 2026 12:20:23 -0600 Subject: PCI: Update CXL DVSEC definitions CXL DVSEC definitions were recently moved into uapi/pci_regs.h, but the newly added macros do not follow the file's existing naming conventions. The current format uses CXL_DVSEC_XYZ, while the new CXL entries must instead use the PCI_DVSEC_CXL_XYZ prefix to match the conventions already established in pci_regs.h. The new CXL DVSEC macros also introduce _MASK and _OFFSET suffixes, which are not used anywhere else in the file. These suffixes lengthen the identifiers and reduce readability. Remove _MASK and _OFFSET from the recently added definitions. Additionally, remove PCI_DVSEC_HEADER1_LENGTH, as it duplicates the existing PCI_DVSEC_HEADER1_LEN() macro. Update all existing references to use the new macro names. Finally, update the inline documentation to reference the latest revision of the CXL specification. Signed-off-by: Terry Bowman Reviewed-by: Dan Williams Acked-by: Bjorn Helgaas Link: https://patch.msgid.link/20260114182055.46029-3-terry.bowman@amd.com Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- include/uapi/linux/pci_regs.h | 94 ++++++++++++++++++++----------------------- 1 file changed, 44 insertions(+), 50 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 6c4b6f19b18e..662582bdccf0 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1333,63 +1333,57 @@ #define PCI_IDE_SEL_ADDR_3(x) (28 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) #define PCI_IDE_SEL_BLOCK_SIZE(nr_assoc) (20 + PCI_IDE_SEL_ADDR_BLOCK_SIZE * (nr_assoc)) -/* Compute Express Link (CXL r3.1, sec 8.1.5) */ -#define PCI_DVSEC_CXL_PORT 3 -#define PCI_DVSEC_CXL_PORT_CTL 0x0c -#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 - /* - * Compute Express Link (CXL r3.2, sec 8.1) + * Compute Express Link (CXL r4.0, sec 8.1) * * Note that CXL DVSEC id 3 and 7 to be ignored when the CXL link state - * is "disconnected" (CXL r3.2, sec 9.12.3). Re-enumerate these + * is "disconnected" (CXL r4.0, sec 9.12.3). Re-enumerate these * registers on downstream link-up events. */ -#define PCI_DVSEC_HEADER1_LENGTH_MASK __GENMASK(31, 20) - -/* CXL 3.2 8.1.3: PCIe DVSEC for CXL Device */ -#define CXL_DVSEC_PCIE_DEVICE 0 -#define CXL_DVSEC_CAP_OFFSET 0xA -#define CXL_DVSEC_MEM_CAPABLE _BITUL(2) -#define CXL_DVSEC_HDM_COUNT_MASK __GENMASK(5, 4) -#define CXL_DVSEC_CTRL_OFFSET 0xC -#define CXL_DVSEC_MEM_ENABLE _BITUL(2) -#define CXL_DVSEC_RANGE_SIZE_HIGH(i) (0x18 + (i * 0x10)) -#define CXL_DVSEC_RANGE_SIZE_LOW(i) (0x1C + (i * 0x10)) -#define CXL_DVSEC_MEM_INFO_VALID _BITUL(0) -#define CXL_DVSEC_MEM_ACTIVE _BITUL(1) -#define CXL_DVSEC_MEM_SIZE_LOW_MASK __GENMASK(31, 28) -#define CXL_DVSEC_RANGE_BASE_HIGH(i) (0x20 + (i * 0x10)) -#define CXL_DVSEC_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) -#define CXL_DVSEC_MEM_BASE_LOW_MASK __GENMASK(31, 28) + +/* CXL r4.0, 8.1.3: PCIe DVSEC for CXL Device */ +#define PCI_DVSEC_CXL_DEVICE 0 +#define PCI_DVSEC_CXL_CAP 0xA +#define PCI_DVSEC_CXL_MEM_CAPABLE _BITUL(2) +#define PCI_DVSEC_CXL_HDM_COUNT __GENMASK(5, 4) +#define PCI_DVSEC_CXL_CTRL 0xC +#define PCI_DVSEC_CXL_MEM_ENABLE _BITUL(2) +#define PCI_DVSEC_CXL_RANGE_SIZE_HIGH(i) (0x18 + (i * 0x10)) +#define PCI_DVSEC_CXL_RANGE_SIZE_LOW(i) (0x1C + (i * 0x10)) +#define PCI_DVSEC_CXL_MEM_INFO_VALID _BITUL(0) +#define PCI_DVSEC_CXL_MEM_ACTIVE _BITUL(1) +#define PCI_DVSEC_CXL_MEM_SIZE_LOW __GENMASK(31, 28) +#define PCI_DVSEC_CXL_RANGE_BASE_HIGH(i) (0x20 + (i * 0x10)) +#define PCI_DVSEC_CXL_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) +#define PCI_DVSEC_CXL_MEM_BASE_LOW __GENMASK(31, 28) #define CXL_DVSEC_RANGE_MAX 2 -/* CXL 3.2 8.1.4: Non-CXL Function Map DVSEC */ -#define CXL_DVSEC_FUNCTION_MAP 2 - -/* CXL 3.2 8.1.5: Extensions DVSEC for Ports */ -#define CXL_DVSEC_PORT 3 -#define CXL_DVSEC_PORT_CTL 0x0c -#define CXL_DVSEC_PORT_CTL_UNMASK_SBR 0x00000001 - -/* CXL 3.2 8.1.6: GPF DVSEC for CXL Port */ -#define CXL_DVSEC_PORT_GPF 4 -#define CXL_DVSEC_PORT_GPF_PHASE_1_CONTROL_OFFSET 0x0C -#define CXL_DVSEC_PORT_GPF_PHASE_1_TMO_BASE_MASK __GENMASK(3, 0) -#define CXL_DVSEC_PORT_GPF_PHASE_1_TMO_SCALE_MASK __GENMASK(11, 8) -#define CXL_DVSEC_PORT_GPF_PHASE_2_CONTROL_OFFSET 0xE -#define CXL_DVSEC_PORT_GPF_PHASE_2_TMO_BASE_MASK __GENMASK(3, 0) -#define CXL_DVSEC_PORT_GPF_PHASE_2_TMO_SCALE_MASK __GENMASK(11, 8) - -/* CXL 3.2 8.1.7: GPF DVSEC for CXL Device */ -#define CXL_DVSEC_DEVICE_GPF 5 - -/* CXL 3.2 8.1.9: Register Locator DVSEC */ -#define CXL_DVSEC_REG_LOCATOR 8 -#define CXL_DVSEC_REG_LOCATOR_BLOCK1_OFFSET 0xC -#define CXL_DVSEC_REG_LOCATOR_BIR_MASK __GENMASK(2, 0) -#define CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK __GENMASK(15, 8) -#define CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK __GENMASK(31, 16) +/* CXL r4.0, 8.1.4: Non-CXL Function Map DVSEC */ +#define PCI_DVSEC_CXL_FUNCTION_MAP 2 + +/* CXL r4.0, 8.1.5: Extensions DVSEC for Ports */ +#define PCI_DVSEC_CXL_PORT 3 +#define PCI_DVSEC_CXL_PORT_CTL 0x0c +#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 + +/* CXL r4.0, 8.1.6: GPF DVSEC for CXL Port */ +#define PCI_DVSEC_CXL_PORT_GPF 4 +#define PCI_DVSEC_CXL_PORT_GPF_PHASE_1_CONTROL 0x0C +#define PCI_DVSEC_CXL_PORT_GPF_PHASE_1_TMO_BASE __GENMASK(3, 0) +#define PCI_DVSEC_CXL_PORT_GPF_PHASE_1_TMO_SCALE __GENMASK(11, 8) +#define PCI_DVSEC_CXL_PORT_GPF_PHASE_2_CONTROL 0xE +#define PCI_DVSEC_CXL_PORT_GPF_PHASE_2_TMO_BASE __GENMASK(3, 0) +#define PCI_DVSEC_CXL_PORT_GPF_PHASE_2_TMO_SCALE __GENMASK(11, 8) + +/* CXL r4.0, 8.1.7: GPF DVSEC for CXL Device */ +#define PCI_DVSEC_CXL_DEVICE_GPF 5 + +/* CXL r4.0, 8.1.9: Register Locator DVSEC */ +#define PCI_DVSEC_CXL_REG_LOCATOR 8 +#define PCI_DVSEC_CXL_REG_LOCATOR_BLOCK1 0xC +#define PCI_DVSEC_CXL_REG_LOCATOR_BIR __GENMASK(2, 0) +#define PCI_DVSEC_CXL_REG_LOCATOR_BLOCK_ID __GENMASK(15, 8) +#define PCI_DVSEC_CXL_REG_LOCATOR_BLOCK_OFF_LOW __GENMASK(31, 16) #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 7c29ba02210c6e4570cdce53813a1ae68fb6d049 Mon Sep 17 00:00:00 2001 From: Terry Bowman Date: Wed, 14 Jan 2026 12:20:24 -0600 Subject: PCI: Introduce pcie_is_cxl() CXL is a protocol that runs on top of PCIe electricals. Its error model also runs on top of the PCIe AER error model by standardizing "internal" errors as "CXL" errors. Linux has historically ignored internal errors. CXL protocol error handling is then a task of enhancing the PCIe AER core to understand that PCIe ports (upstream and downstream) and endpoints may throw internal errors that represent standard CXL protocol errors. The proposed method to make that determination is to teach 'struct pci_dev' to cache when its link has trained the CXL.mem and/or CXL.cache protocols and then treat all internal errors as CXL errors. A design goal is to not burden the PCIe AER core with CXL knowledge beyond just enough to forward error notifications to the CXL RAS core. The forwarded notification looks up a 'struct cxl_port' or 'struct cxl_dport' companion device to the PCI device. Introduce set_pcie_cxl() with logic checking for CXL.mem or CXL.cache status in the CXL Flex Bus DVSEC status register. The CXL Flex Bus DVSEC presence is used because it is required for all the CXL PCIe devices.[1] [1] CXL 3.1 Spec, 8.1.1 PCIe Designated Vendor-Specific Extended Capability (DVSEC) ID Assignment, Table 8-2 Signed-off-by: Terry Bowman Reviewed-by: Ira Weiny Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Dave Jiang Reviewed-by: Jonathan Cameron Reviewed-by: Alejandro Lucero Reviewed-by: Ben Cheatham Reviewed-by: Dan Williams Acked-by: Bjorn Helgaas Link: https://patch.msgid.link/20260114182055.46029-4-terry.bowman@amd.com Signed-off-by: Dan Williams Signed-off-by: Dave Jiang --- include/uapi/linux/pci_regs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 662582bdccf0..b6622fd60fd9 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1379,6 +1379,12 @@ /* CXL r4.0, 8.1.7: GPF DVSEC for CXL Device */ #define PCI_DVSEC_CXL_DEVICE_GPF 5 +/* CXL r4.0, 8.1.8: Flex Bus DVSEC */ +#define PCI_DVSEC_CXL_FLEXBUS_PORT 7 +#define PCI_DVSEC_CXL_FLEXBUS_PORT_STATUS 0xE +#define PCI_DVSEC_CXL_FLEXBUS_PORT_STATUS_CACHE _BITUL(0) +#define PCI_DVSEC_CXL_FLEXBUS_PORT_STATUS_MEM _BITUL(2) + /* CXL r4.0, 8.1.9: Register Locator DVSEC */ #define PCI_DVSEC_CXL_REG_LOCATOR 8 #define PCI_DVSEC_CXL_REG_LOCATOR_BLOCK1 0xC -- cgit v1.2.3 From 5247c034a67f5a93cc1faa15e9867eec5b22f38a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 20 Jan 2026 20:47:40 +0000 Subject: io_uring: introduce non-circular SQ Outside of SQPOLL, normally SQ entries are consumed by the time the submission syscall returns. For those cases we don't need a circular buffer and the head/tail tracking, instead the kernel can assume that entries always start from the beginning of the SQ at index 0. This patch introduces a setup flag doing exactly that. It's a simpler and helps to keeps SQEs hot in cache. The feature is optional and enabled by setting IORING_SETUP_SQ_REWIND. The flag is rejected if passed together with SQPOLL as it'd require waiting for SQ before each submission. It also requires IORING_SETUP_NO_SQARRAY, which can be supported but it's unlikely there will be users, so leave more space for future optimisations. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b5b23c0d5283..475094c7a668 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -237,6 +237,18 @@ enum io_uring_sqe_flags_bit { */ #define IORING_SETUP_SQE_MIXED (1U << 19) +/* + * When set, io_uring ignores SQ head and tail and fetches SQEs to submit + * starting from index 0 instead from the index stored in the head pointer. + * IOW, the user should place all SQE at the beginning of the SQ memory + * before issuing a submission syscall. + * + * It requires IORING_SETUP_NO_SQARRAY and is incompatible with + * IORING_SETUP_SQPOLL. The user must also never change the SQ head and tail + * values and keep it set to 0. Any other value is undefined behaviour. + */ +#define IORING_SETUP_SQ_REWIND (1U << 20) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, -- cgit v1.2.3 From e86f89ab24f5ec595879a01eebb5df84f5ed6d2b Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 16 Jan 2026 22:18:36 +0800 Subject: ublk: add new batch command UBLK_U_IO_PREP_IO_CMDS & UBLK_U_IO_COMMIT_IO_CMDS Add new command UBLK_U_IO_PREP_IO_CMDS, which is the batch version of UBLK_IO_FETCH_REQ. Add new command UBLK_U_IO_COMMIT_IO_CMDS, which is for committing io command result only, still the batch version. The new command header type is `struct ublk_batch_io`. This patch doesn't actually implement these commands yet, just validates the SQE fields. Reviewed-by: Caleb Sander Mateos Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 49 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 90f47da4f435..0cc58e19d401 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -103,6 +103,10 @@ _IOWR('u', 0x23, struct ublksrv_io_cmd) #define UBLK_U_IO_UNREGISTER_IO_BUF \ _IOWR('u', 0x24, struct ublksrv_io_cmd) +#define UBLK_U_IO_PREP_IO_CMDS \ + _IOWR('u', 0x25, struct ublk_batch_io) +#define UBLK_U_IO_COMMIT_IO_CMDS \ + _IOWR('u', 0x26, struct ublk_batch_io) /* only ABORT means that no re-fetch */ #define UBLK_IO_RES_OK 0 @@ -544,6 +548,51 @@ struct ublksrv_io_cmd { }; }; +struct ublk_elem_header { + __u16 tag; /* IO tag */ + + /* + * Buffer index for incoming io command, only valid iff + * UBLK_F_AUTO_BUF_REG is set + */ + __u16 buf_index; + __s32 result; /* I/O completion result (commit only) */ +}; + +/* + * uring_cmd buffer structure for batch commands + * + * buffer includes multiple elements, which number is specified by + * `nr_elem`. Each element buffer is organized in the following order: + * + * struct ublk_elem_buffer { + * // Mandatory fields (8 bytes) + * struct ublk_elem_header header; + * + * // Optional fields (8 bytes each, included based on flags) + * + * // Buffer address (if UBLK_BATCH_F_HAS_BUF_ADDR) for copying data + * // between ublk request and ublk server buffer + * __u64 buf_addr; + * + * // returned Zone append LBA (if UBLK_BATCH_F_HAS_ZONE_LBA) + * __u64 zone_lba; + * } + * + * Used for `UBLK_U_IO_PREP_IO_CMDS` and `UBLK_U_IO_COMMIT_IO_CMDS` + */ +struct ublk_batch_io { + __u16 q_id; +#define UBLK_BATCH_F_HAS_ZONE_LBA (1 << 0) +#define UBLK_BATCH_F_HAS_BUF_ADDR (1 << 1) +#define UBLK_BATCH_F_AUTO_BUF_REG_FALLBACK (1 << 2) + __u16 flags; + __u16 nr_elem; + __u8 elem_bytes; + __u8 reserved; + __u64 reserved2; +}; + struct ublk_param_basic { #define UBLK_ATTR_READ_ONLY (1 << 0) #define UBLK_ATTR_ROTATIONAL (1 << 1) -- cgit v1.2.3 From b256795b3606e9a67c725dde8eaae91dd9d21de4 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 16 Jan 2026 22:18:37 +0800 Subject: ublk: handle UBLK_U_IO_PREP_IO_CMDS This commit implements the handling of the UBLK_U_IO_PREP_IO_CMDS command, which allows userspace to prepare a batch of I/O requests. The core of this change is the `ublk_walk_cmd_buf` function, which iterates over the elements in the uring_cmd fixed buffer. For each element, it parses the I/O details, finds the corresponding `ublk_io` structure, and prepares it for future dispatch. Add per-io lock for protecting concurrent delivery and committing. Reviewed-by: Caleb Sander Mateos Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 0cc58e19d401..1a3d4d33c1d1 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -103,6 +103,11 @@ _IOWR('u', 0x23, struct ublksrv_io_cmd) #define UBLK_U_IO_UNREGISTER_IO_BUF \ _IOWR('u', 0x24, struct ublksrv_io_cmd) + +/* + * return 0 if the command is run successfully, otherwise failure code + * is returned + */ #define UBLK_U_IO_PREP_IO_CMDS \ _IOWR('u', 0x25, struct ublk_batch_io) #define UBLK_U_IO_COMMIT_IO_CMDS \ -- cgit v1.2.3 From 1e500e106d5a82280db59dba06f0108085beba65 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 16 Jan 2026 22:18:38 +0800 Subject: ublk: handle UBLK_U_IO_COMMIT_IO_CMDS Handle UBLK_U_IO_COMMIT_IO_CMDS by walking the uring_cmd fixed buffer: - read each element into one temp buffer in batch style - parse and apply each element for committing io result Reviewed-by: Caleb Sander Mateos Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 1a3d4d33c1d1..3894d676dd02 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -110,6 +110,14 @@ */ #define UBLK_U_IO_PREP_IO_CMDS \ _IOWR('u', 0x25, struct ublk_batch_io) +/* + * If failure code is returned, nothing in the command buffer is handled. + * Otherwise, the returned value means how many bytes in command buffer + * are handled actually, then number of handled IOs can be calculated with + * `elem_bytes` for each IO. IOs in the remained bytes are not committed, + * userspace has to check return value for dealing with partial committing + * correctly. + */ #define UBLK_U_IO_COMMIT_IO_CMDS \ _IOWR('u', 0x26, struct ublk_batch_io) -- cgit v1.2.3 From a4d88375539920b7401ead59d2f944ac23c668ea Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 16 Jan 2026 22:18:41 +0800 Subject: ublk: add UBLK_U_IO_FETCH_IO_CMDS for batch I/O processing Add UBLK_U_IO_FETCH_IO_CMDS command to enable efficient batch processing of I/O requests. This multishot uring_cmd allows the ublk server to fetch multiple I/O commands in a single operation, significantly reducing submission overhead compared to individual FETCH_REQ* commands. Key Design Features: 1. Multishot Operation: One UBLK_U_IO_FETCH_IO_CMDS can fetch many I/O commands, with the batch size limited by the provided buffer length. 2. Dynamic Load Balancing: Multiple fetch commands can be submitted simultaneously, but only one is active at any time. This enables efficient load distribution across multiple server task contexts. 3. Implicit State Management: The implementation uses three key variables to track state: - evts_fifo: Queue of request tags awaiting processing - fcmd_head: List of available fetch commands - active_fcmd: Currently active fetch command (NULL = none active) States are derived implicitly: - IDLE: No fetch commands available - READY: Fetch commands available, none active - ACTIVE: One fetch command processing events 4. Lockless Reader Optimization: The active fetch command can read from evts_fifo without locking (single reader guarantee), while writers (ublk_queue_rq/ublk_queue_rqs) use evts_lock protection. The memory barrier pairing plays key role for the single lockless reader optimization. Implementation Details: - ublk_queue_rq() and ublk_queue_rqs() save request tags to evts_fifo - __ublk_acquire_fcmd() selects an available fetch command when events arrive and no command is currently active - ublk_batch_dispatch() moves tags from evts_fifo to the fetch command's buffer and posts completion via io_uring_mshot_cmd_post_cqe() - State transitions are coordinated via evts_lock to maintain consistency Reviewed-by: Caleb Sander Mateos Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 3894d676dd02..70d8ebbf4326 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -121,6 +121,13 @@ #define UBLK_U_IO_COMMIT_IO_CMDS \ _IOWR('u', 0x26, struct ublk_batch_io) +/* + * Fetch io commands to provided buffer in multishot style, + * `IORING_URING_CMD_MULTISHOT` is required for this command. + */ +#define UBLK_U_IO_FETCH_IO_CMDS \ + _IOWR('u', 0x27, struct ublk_batch_io) + /* only ABORT means that no re-fetch */ #define UBLK_IO_RES_OK 0 #define UBLK_IO_RES_NEED_GET_DATA 1 -- cgit v1.2.3 From e2723e6ce6025026b6d79d9a00048386a69e00c3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 16 Jan 2026 22:18:44 +0800 Subject: ublk: add new feature UBLK_F_BATCH_IO Add new feature UBLK_F_BATCH_IO which replaces the following two per-io commands: - UBLK_U_IO_FETCH_REQ - UBLK_U_IO_COMMIT_AND_FETCH_REQ with three per-queue batch io uring_cmd: - UBLK_U_IO_PREP_IO_CMDS - UBLK_U_IO_COMMIT_IO_CMDS - UBLK_U_IO_FETCH_IO_CMDS Then ublk can deliver batch io commands to ublk server in single multishort uring_cmd, also allows to prepare & commit multiple commands in batch style via single uring_cmd, communication cost is reduced a lot. This feature also doesn't limit task context any more for all supported commands, so any allowed uring_cmd can be issued in any task context. ublk server implementation becomes much easier. Meantime load balance becomes much easier to support with this feature. The command `UBLK_U_IO_FETCH_IO_CMDS` can be issued from multiple task contexts, so each task can adjust this command's buffer length or number of inflight commands for controlling how much load is handled by current task. Later, priority parameter will be added to command `UBLK_U_IO_FETCH_IO_CMDS` for improving load balance support. UBLK_U_IO_NEED_GET_DATA isn't supported in batch io yet, but it may be enabled in future via its batch pair. Reviewed-by: Caleb Sander Mateos Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 70d8ebbf4326..743d31491387 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -340,6 +340,21 @@ */ #define UBLK_F_BUF_REG_OFF_DAEMON (1ULL << 14) +/* + * Support the following commands for delivering & committing io command + * in batch. + * + * - UBLK_U_IO_PREP_IO_CMDS + * - UBLK_U_IO_COMMIT_IO_CMDS + * - UBLK_U_IO_FETCH_IO_CMDS + * - UBLK_U_IO_REGISTER_IO_BUF + * - UBLK_U_IO_UNREGISTER_IO_BUF + * + * The existing UBLK_U_IO_FETCH_REQ, UBLK_U_IO_COMMIT_AND_FETCH_REQ and + * UBLK_U_IO_NEED_GET_DATA uring_cmd are not supported for this feature. + */ +#define UBLK_F_BATCH_IO (1ULL << 15) + /* * ublk device supports requests with integrity/metadata buffer. * Requires UBLK_F_USER_COPY. -- cgit v1.2.3 From fa9893fadbc245e179cb17f3c371c67471b5a8a8 Mon Sep 17 00:00:00 2001 From: Michael Roth Date: Fri, 9 Jan 2026 17:17:32 -0600 Subject: KVM: Introduce KVM_EXIT_SNP_REQ_CERTS for SNP certificate-fetching For SEV-SNP, the host can optionally provide a certificate table to the guest when it issues an attestation request to firmware (see GHCB 2.0 specification regarding "SNP Extended Guest Requests"). This certificate table can then be used to verify the endorsement key used by firmware to sign the attestation report. While it is possible for guests to obtain the certificates through other means, handling it via the host provides more flexibility in being able to keep the certificate data in sync with the endorsement key throughout host-side operations that might resulting in the endorsement key changing. In the case of KVM, userspace will be responsible for fetching the certificate table and keeping it in sync with any modifications to the endorsement key by other userspace management tools. Define a new KVM_EXIT_SNP_REQ_CERTS event where userspace is provided with the GPA of the buffer the guest has provided as part of the attestation request so that userspace can write the certificate data into it while relying on filesystem-based locking to keep the certificates up-to-date relative to the endorsement keys installed/utilized by firmware at the time the certificates are fetched. [Melody: Update the documentation scheme about how file locking is expected to happen.] Reviewed-by: Liam Merwick Tested-by: Liam Merwick Tested-by: Dionna Glaze Signed-off-by: Michael Roth Signed-off-by: Melody Wang Signed-off-by: Michael Roth Link: https://patch.msgid.link/20260109231732.1160759-2-michael.roth@amd.com Signed-off-by: Sean Christopherson --- include/uapi/linux/kvm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dddb781b0507..8cd107cdcf0b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -135,6 +135,12 @@ struct kvm_xen_exit { } u; }; +struct kvm_exit_snp_req_certs { + __u64 gpa; + __u64 npages; + __u64 ret; +}; + #define KVM_S390_GET_SKEYS_NONE 1 #define KVM_S390_SKEYS_MAX 1048576 @@ -180,6 +186,7 @@ struct kvm_xen_exit { #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 #define KVM_EXIT_ARM_SEA 41 +#define KVM_EXIT_SNP_REQ_CERTS 42 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -482,6 +489,8 @@ struct kvm_run { __u64 gva; __u64 gpa; } arm_sea; + /* KVM_EXIT_SNP_REQ_CERTS */ + struct kvm_exit_snp_req_certs snp_req_certs; /* Fix the size of the union. */ char padding[256]; }; -- cgit v1.2.3 From ba1b8c97b9a0414432382a11f144a8597f6f597e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 21 Jan 2026 17:11:30 +0100 Subject: geneve: add netlink support for GRO hint Allow configuring and dumping the new device option, and cache its value into the geneve socket itself. The new option is not tie to it any code yet. Signed-off-by: Paolo Abeni Link: https://patch.msgid.link/2295d4e4d1e919a3189425141bbc71c7850a2de0.1769011015.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3b491d96e52e..e9b5f79e1ee1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1443,6 +1443,7 @@ enum { IFLA_GENEVE_DF, IFLA_GENEVE_INNER_PROTO_INHERIT, IFLA_GENEVE_PORT_RANGE, + IFLA_GENEVE_GRO_HINT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) -- cgit v1.2.3 From 795663b4d160ba652959f1a46381c5e8b1342a53 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 24 Jan 2026 10:36:17 +0000 Subject: io_uring/zcrx: implement large rx buffer support There are network cards that support receive buffers larger than 4K, and that can be vastly beneficial for performance, and benchmarks for this patch showed up to 30% CPU util improvement for 32K vs 4K buffers. Allows zcrx users to specify the size in struct io_uring_zcrx_ifq_reg::rx_buf_len. If set to zero, zcrx will use a default value. zcrx will check and fail if the memory backing the area can't be split into physically contiguous chunks of the required size. It's more restrictive as it only needs dma addresses to be contig, but that's beyond this series. Signed-off-by: Pavel Begunkov [axboe: kill duplicate netdev_queues.h include] 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 b5b23c0d5283..3184f7e7f1f2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1082,7 +1082,7 @@ struct io_uring_zcrx_ifq_reg { struct io_uring_zcrx_offsets offsets; __u32 zcrx_id; - __u32 __resv2; + __u32 rx_buf_len; __u64 __resv[3]; }; -- cgit v1.2.3 From 2d419c44658f75e7655794341a95c0687830f3df Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 24 Jan 2026 14:19:56 +0800 Subject: bpf: add fsession support The fsession is something that similar to kprobe session. It allow to attach a single BPF program to both the entry and the exit of the target functions. Introduce the struct bpf_fsession_link, which allows to add the link to both the fentry and fexit progs_hlist of the trampoline. Signed-off-by: Menglong Dong Co-developed-by: Leon Hwang Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260124062008.8657-2-dongml2@chinatelecom.cn Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2a2ade4be60f..44e7dbc278e3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1145,6 +1145,7 @@ enum bpf_attach_type { BPF_NETKIT_PEER, BPF_TRACE_KPROBE_SESSION, BPF_TRACE_UPROBE_SESSION, + BPF_TRACE_FSESSION, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From 0ac903d1bfdce8ff40657c2b7d996947b72b6645 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 9 Dec 2025 19:28:50 -0500 Subject: NFS: NFSERR_INVAL is not defined by NFSv2 A documenting comment in include/uapi/linux/nfs.h claims incorrectly that NFSv2 defines NFSERR_INVAL. There is no such definition in either RFC 1094 or https://pubs.opengroup.org/onlinepubs/9629799/chap7.htm NFS3ERR_INVAL is introduced in RFC 1813. NFSD returns NFSERR_INVAL for PROC_GETACL, which has no specification (yet). However, nfsd_map_status() maps nfserr_symlink and nfserr_wrong_type to nfserr_inval, which does not align with RFC 1094. This logic was introduced only recently by commit 438f81e0e92a ("nfsd: move error choice for incorrect object types to version-specific code."). Given that we have no INVAL or SERVERFAULT status in NFSv2, probably the only choice is NFSERR_IO. Fixes: 438f81e0e92a ("nfsd: move error choice for incorrect object types to version-specific code.") Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/uapi/linux/nfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index 71c7196d3281..e629c4953534 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -55,7 +55,7 @@ NFSERR_NODEV = 19, /* v2 v3 v4 */ NFSERR_NOTDIR = 20, /* v2 v3 v4 */ NFSERR_ISDIR = 21, /* v2 v3 v4 */ - NFSERR_INVAL = 22, /* v2 v3 v4 */ + NFSERR_INVAL = 22, /* v3 v4 */ NFSERR_FBIG = 27, /* v2 v3 v4 */ NFSERR_NOSPC = 28, /* v2 v3 v4 */ NFSERR_ROFS = 30, /* v2 v3 v4 */ -- cgit v1.2.3 From 1965bbb8f3c72e5f1972b5eeb6f19a36664a676d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 22 Dec 2025 08:55:10 +0100 Subject: ipc/shm: uapi: remove dependency on libc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using libc types and headers from the UAPI headers is problematic as it introduces a dependency on a full C toolchain. shm.h does not even use any symbols from the libc header as the usage of getpagesize() was removed a decade ago in commit 060028bac94b ("ipc/shm.c: increase the defaults for SHMALL, SHMMAX") Drop the unnecessary inclusion. Link: https://lkml.kernel.org/r/20251222-uapi-shm-v1-1-270bb7f75d97@linutronix.de Signed-off-by: Thomas Weißschuh Cc: Arnd Bergmann Signed-off-by: Andrew Morton --- include/uapi/linux/shm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index 8d1f17a4e08e..7269f9f402e3 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -5,9 +5,6 @@ #include #include #include -#ifndef __KERNEL__ -#include -#endif /* * SHMMNI, SHMMAX and SHMALL are default upper limits which can be -- cgit v1.2.3 From 3d702678f57edc524f73a7865382ae304269f590 Mon Sep 17 00:00:00 2001 From: Jinjiang Tu Date: Tue, 23 Dec 2025 19:05:23 +0800 Subject: mm/mempolicy: fix mpol_rebind_nodemask() for MPOL_F_NUMA_BALANCING commit bda420b98505 ("numa balancing: migrate on fault among multiple bound nodes") adds new flag MPOL_F_NUMA_BALANCING to enable NUMA balancing for MPOL_BIND memory policy. When the cpuset of tasks changes, the mempolicy of the task is rebound by mpol_rebind_nodemask(). When MPOL_F_STATIC_NODES and MPOL_F_RELATIVE_NODES are both not set, the behaviour of rebinding should be same whenever MPOL_F_NUMA_BALANCING is set or not. So, when an application calls set_mempolicy() with MPOL_F_NUMA_BALANCING set but both MPOL_F_STATIC_NODES and MPOL_F_RELATIVE_NODES cleared, mempolicy.w.cpuset_mems_allowed should be set to cpuset_current_mems_allowed nodemask. However, in current implementation, mpol_store_user_nodemask() wrongly returns true, causing mempolicy->w.user_nodemask to be incorrectly set to the user-specified nodemask. Later, when the cpuset of the application changes, mpol_rebind_nodemask() ends up rebinding based on the user-specified nodemask rather than the cpuset_mems_allowed nodemask as intended. I can reproduce with the following steps in qemu with 4 NUMA nodes: 1. echo '+cpuset' > /sys/fs/cgroup/cgroup.subtree_control 2. mkdir /sys/fs/cgroup/test 3. ./reproducer & 4. cat /proc/$pid/numa_maps, the task is bound to NUMA 1 5. echo $pid > /sys/fs/cgroup/test/cgroup.procs 6. cat /proc/$pid/numa_maps, the task is bound to NUMA 0 now. The reproducer code: int main() { struct bitmask *bmp; int ret; bmp = numa_parse_nodestring("1"); ret = set_mempolicy(MPOL_BIND | MPOL_F_NUMA_BALANCING, bmp->maskp, bmp->size + 1); if (ret < 0) { perror("Failed to call set_mempolicy"); exit(-1); } while (1); return 0; } If I call set_mempolicy() without MPOL_F_NUMA_BALANCING in the reproducer code. After step 5, the task is still bound to NUMA 1. To fix this, only set mempolicy->w.user_nodemask to the user-specified nodemask if MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES is present. Link: https://lkml.kernel.org/r/20260120011018.1256654-1-tujinjiang@huawei.com Link: https://lkml.kernel.org/r/20251223110523.1161421-1-tujinjiang@huawei.com Fixes: bda420b98505 ("numa balancing: migrate on fault among multiple bound nodes") Signed-off-by: Jinjiang Tu Reviewed-by: Gregory Price Reviewed-by: Huang Ying Acked-by: David Hildenbrand (Red Hat) Cc: Alistair Popple Cc: Byungchul Park Cc: Joshua Hahn Cc: Kefeng Wang Cc: Mathew Brost Cc: Mel Gorman Cc: Rakie Kim Cc: Zi Yan Signed-off-by: Andrew Morton --- include/uapi/linux/mempolicy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 8fbbe613611a..6c962d866e86 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -39,6 +39,9 @@ enum { #define MPOL_MODE_FLAGS \ (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES | MPOL_F_NUMA_BALANCING) +/* Whether the nodemask is specified by users */ +#define MPOL_USER_NODEMASK_FLAGS (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) + /* Flags for get_mempolicy */ #define MPOL_F_NODE (1<<0) /* return next IL mode instead of node mask */ #define MPOL_F_ADDR (1<<1) /* look up vma using address */ -- cgit v1.2.3 From 86c6b6e4d187652d718915e15cf126f98e24e955 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Sun, 11 Jan 2026 19:03:48 +0200 Subject: wifi: nl80211/cfg80211: add new FTM capabilities Add new capabilities to the PMSR FTM capabilities list. The new capabilities include 6 GHz support, supported number of spatial streams and supported number of LTF repetitions. Signed-off-by: Avraham Stern Tested-by: Miriam Rachel Korenblit Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260111190221.bf43785c18f6.Ic98cf9790ddee84bf88e5720b93c46c23af3c96c@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index b0f050e36fa4..200703c8b2c1 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7790,6 +7790,28 @@ enum nl80211_peer_measurement_attrs { * trigger based ranging measurement is supported * @NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED: flag attribute indicating * if non-trigger-based ranging measurement is supported + * @NL80211_PMSR_FTM_CAPA_ATTR_6GHZ_SUPPORT: flag attribute indicating if + * ranging on the 6 GHz band is supported + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_TX_LTF_REP: u32 attribute indicating + * the maximum number of LTF repetitions the device can transmit in the + * preamble of the ranging NDP (zero means only one LTF, no repetitions) + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_RX_LTF_REP: u32 attribute indicating + * the maximum number of LTF repetitions the device can receive in the + * preamble of the ranging NDP (zero means only one LTF, no repetitions) + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_TX_STS: u32 attribute indicating + * the maximum number of space-time streams supported for ranging NDP TX + * (zero-based) + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_RX_STS: u32 attribute indicating + * the maximum number of space-time streams supported for ranging NDP RX + * (zero-based) + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_TX: u32 attribute indicating the + * maximum total number of LTFs the device can transmit. The total number + * of LTFs is (number of LTF repetitions) * (number of space-time streams). + * This limits the allowed combinations of LTF repetitions and STS. + * @NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_RX: u32 attribute indicating the + * maximum total number of LTFs the device can receive. The total number + * of LTFs is (number of LTF repetitions) * (number of space-time streams). + * This limits the allowed combinations of LTF repetitions and STS. * * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number @@ -7807,6 +7829,13 @@ enum nl80211_peer_measurement_ftm_capa { NL80211_PMSR_FTM_CAPA_ATTR_MAX_FTMS_PER_BURST, NL80211_PMSR_FTM_CAPA_ATTR_TRIGGER_BASED, NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED, + NL80211_PMSR_FTM_CAPA_ATTR_6GHZ_SUPPORT, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_TX_LTF_REP, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_RX_LTF_REP, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_TX_STS, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_RX_STS, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_TX, + NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_RX, /* keep last */ NUM_NL80211_PMSR_FTM_CAPA_ATTR, -- cgit v1.2.3 From 853ce6943c385be2f6cccf371080e592f2e08b0f Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Sun, 11 Jan 2026 19:03:49 +0200 Subject: wifi: nl80211/cfg80211: clarify periodic FTM parameters for non-EDCA based ranging Periodic FTM request attributes are defined based on the periodic parameters used in EDCA-based ranging negotiation. However, non-EDCA based ranging (trigger-based/non-trigger-based) does not include periodic parameters in the negotiation protocol, even though upper layers may still request periodic measurements. Clarify the semantics of periodic ranging attributes when used with non-EDCA based ranging. Signed-off-by: Avraham Stern Reviewed-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260111190221.b89cb3f68e1a.I7a9d8c6d1c66c77f1b43120a841101c96c3f19ad@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 200703c8b2c1..71219445f5c7 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7851,12 +7851,15 @@ enum nl80211_peer_measurement_ftm_capa { * &enum nl80211_preamble), optional for DMG (u32) * @NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP: number of bursts exponent as in * 802.11-2016 9.4.2.168 "Fine Timing Measurement Parameters element" - * (u8, 0-15, optional with default 15 i.e. "no preference") + * (u8, 0-15, optional with default 15 i.e. "no preference". No limit for + * non-EDCA ranging) * @NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD: interval between bursts in units * of 100ms (u16, optional with default 0) * @NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION: burst duration, as in 802.11-2016 * Table 9-257 "Burst Duration field encoding" (u8, 0-15, optional with - * default 15 i.e. "no preference") + * default 15 i.e. "no preference"). For non-EDCA ranging, this is the + * burst duration in milliseconds (optional with default 0, i.e. let the + * device decide). * @NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST: number of successful FTM frames * requested per burst * (u8, 0-31, optional with default 0 i.e. "no preference") -- cgit v1.2.3 From cfd46d1c6f4bf232c5630b1cf5c8b317d38101c5 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Sun, 11 Jan 2026 19:03:50 +0200 Subject: wifi: nl80211/cfg80211: add negotiated burst period to FTM result The FTM result includes some of the periodic measurement negotiated parameters (like the burst duration and number of bursts), but it doesn't include the burst period. Add it to the FTM result notification. Signed-off-by: Avraham Stern Reviewed-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260111190221.e0778f86edef.I3c98c1933eb639963bc3ffdef81a8788b59f2188@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 71219445f5c7..8910b709bfb1 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7992,6 +7992,8 @@ enum nl80211_peer_measurement_ftm_failure_reasons { * 9.4.2.22.1) starting with the Measurement Token, with Measurement * Type 11. * @NL80211_PMSR_FTM_RESP_ATTR_PAD: ignore, for u64/s64 padding only + * @NL80211_PMSR_FTM_RESP_ATTR_BURST_PERIOD: actual burst period used by + * the responder (similar to request, u16) * * @NUM_NL80211_PMSR_FTM_RESP_ATTR: internal * @NL80211_PMSR_FTM_RESP_ATTR_MAX: highest attribute number @@ -8020,6 +8022,7 @@ enum nl80211_peer_measurement_ftm_resp { NL80211_PMSR_FTM_RESP_ATTR_LCI, NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC, NL80211_PMSR_FTM_RESP_ATTR_PAD, + NL80211_PMSR_FTM_RESP_ATTR_BURST_PERIOD, /* keep last */ NUM_NL80211_PMSR_FTM_RESP_ATTR, -- cgit v1.2.3 From 853800c746d38486673ef67f461b660a01d52716 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Sun, 11 Jan 2026 19:03:51 +0200 Subject: wifi: nl80211/cfg80211: support operating as RSTA in PMSR FTM request Add an option to operate as the RSTA in an FTM measurement request. When requested, the device will dwell on the requested channel until the peer starts the FTM negotiation. This option is only valid for trigger-based/non trigger-based measurement with LMR feedback which will allow the RSTA to receive the results of the measurement. Signed-off-by: Avraham Stern Reviewed-by: Johannes Berg Signed-off-by: Miri Korenblit Link: https://patch.msgid.link/20260111190221.1f95fc0afab4.Iae2d32783b8e7c4a29089fec0f4c6bce94d303cc@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8910b709bfb1..54ddbd9a5459 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7812,6 +7812,8 @@ enum nl80211_peer_measurement_attrs { * maximum total number of LTFs the device can receive. The total number * of LTFs is (number of LTF repetitions) * (number of space-time streams). * This limits the allowed combinations of LTF repetitions and STS. + * @NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT: flag attribute indicating the + * device supports operating as the RSTA in PMSR FTM request * * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number @@ -7836,6 +7838,7 @@ enum nl80211_peer_measurement_ftm_capa { NL80211_PMSR_FTM_CAPA_ATTR_MAX_RX_STS, NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_TX, NL80211_PMSR_FTM_CAPA_ATTR_MAX_TOTAL_LTF_RX, + NL80211_PMSR_FTM_CAPA_ATTR_RSTA_SUPPORT, /* keep last */ NUM_NL80211_PMSR_FTM_CAPA_ATTR, @@ -7888,6 +7891,14 @@ enum nl80211_peer_measurement_ftm_capa { * @NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR: optional. The BSS color of the * responder. Only valid if %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED * or %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED is set. + * @NL80211_PMSR_FTM_REQ_ATTR_RSTA: optional. Request to perform the measurement + * as the RSTA (flag). When set, the device is expected to dwell on the + * channel specified in %NL80211_PMSR_PEER_ATTR_CHAN until it receives the + * FTM request from the peer or the timeout specified by + * %NL80211_ATTR_TIMEOUT has expired. + * Only valid if %NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK is set (so the + * RSTA will have the measurement results to report back in the FTM + * response). * * @NUM_NL80211_PMSR_FTM_REQ_ATTR: internal * @NL80211_PMSR_FTM_REQ_ATTR_MAX: highest attribute number @@ -7908,6 +7919,7 @@ enum nl80211_peer_measurement_ftm_req { NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED, NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK, NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR, + NL80211_PMSR_FTM_REQ_ATTR_RSTA, /* keep last */ NUM_NL80211_PMSR_FTM_REQ_ATTR, -- cgit v1.2.3 From 752b807028e63f1473b84eb1350e131eca5e5249 Mon Sep 17 00:00:00 2001 From: Matt Bobrowski Date: Tue, 27 Jan 2026 08:51:10 +0000 Subject: bpf: add new BPF_CGROUP_ITER_CHILDREN control option Currently, the BPF cgroup iterator supports walking descendants in either pre-order (BPF_CGROUP_ITER_DESCENDANTS_PRE) or post-order (BPF_CGROUP_ITER_DESCENDANTS_POST). These modes perform an exhaustive depth-first search (DFS) of the hierarchy. In scenarios where a BPF program may need to inspect only the direct children of a given parent cgroup, a full DFS is unnecessarily expensive. This patch introduces a new BPF cgroup iterator control option, BPF_CGROUP_ITER_CHILDREN. This control option restricts the traversal to the immediate children of a specified parent cgroup, allowing for more targeted and efficient iteration, particularly when exhaustive depth-first search (DFS) traversal is not required. Signed-off-by: Matt Bobrowski Link: https://lore.kernel.org/r/20260127085112.3608687-1-mattbobrowski@google.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 44e7dbc278e3..c8d400b7680a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -119,6 +119,14 @@ enum bpf_cgroup_iter_order { BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */ BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */ BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */ + /* + * Walks the immediate children of the specified parent + * cgroup_subsys_state. Unlike BPF_CGROUP_ITER_DESCENDANTS_PRE, + * BPF_CGROUP_ITER_DESCENDANTS_POST, and BPF_CGROUP_ITER_ANCESTORS_UP + * the iterator does not include the specified parent as one of the + * returned iterator elements. + */ + BPF_CGROUP_ITER_CHILDREN, }; union bpf_iter_link_info { -- cgit v1.2.3 From d42eb05e60fea31de49897d63a1d73f933303bd4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Jan 2026 08:24:02 -0700 Subject: io_uring: add support for BPF filtering for opcode restrictions Add support for loading classic BPF programs with io_uring to provide fine-grained filtering of SQE operations. Unlike IORING_REGISTER_RESTRICTIONS which only allows bitmap-based allow/deny of opcodes, BPF filters can inspect request attributes and make dynamic decisions. The filter is registered via IORING_REGISTER_BPF_FILTER with a struct io_uring_bpf: struct io_uring_bpf_filter { __u32 opcode; /* io_uring opcode to filter */ __u32 flags; __u32 filter_len; /* number of BPF instructions */ __u32 resv; __u64 filter_ptr; /* pointer to BPF filter */ __u64 resv2[5]; }; enum { IO_URING_BPF_CMD_FILTER = 1, }; struct io_uring_bpf { __u16 cmd_type; /* IO_URING_BPF_* values */ __u16 cmd_flags; /* none so far */ __u32 resv; union { struct io_uring_bpf_filter filter; }; }; and the filters get supplied a struct io_uring_bpf_ctx: struct io_uring_bpf_ctx { __u64 user_data; __u8 opcode; __u8 sqe_flags; __u8 pdu_size; __u8 pad[5]; }; where it's possible to filter on opcode and sqe_flags, with pdu_size indicating how much extra data is being passed in beyond the pad field. This will used for specific finer grained filtering inside an opcode. An example of that for sockets is in one of the following patches. Anything the opcode supports can end up in this struct, populated by the opcode itself, and hence can be filtered for. Filters have the following semantics: - Return 1 to allow the request - Return 0 to deny the request with -EACCES - Multiple filters can be stacked per opcode. All filters must return 1 for the opcode to be allowed. - Filters are evaluated in registration order (most recent first) The implementation uses classic BPF (cBPF) rather than eBPF for as that's required for containers, and since they can be used by any user in the system. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 ++ include/uapi/linux/io_uring/bpf_filter.h | 50 ++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 include/uapi/linux/io_uring/bpf_filter.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b5b23c0d5283..94669b77fee8 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -700,6 +700,9 @@ enum io_uring_register_op { /* auxiliary zcrx configuration, see enum zcrx_ctrl_op */ IORING_REGISTER_ZCRX_CTRL = 36, + /* register bpf filtering programs */ + IORING_REGISTER_BPF_FILTER = 37, + /* this goes last */ IORING_REGISTER_LAST, diff --git a/include/uapi/linux/io_uring/bpf_filter.h b/include/uapi/linux/io_uring/bpf_filter.h new file mode 100644 index 000000000000..2d4d0e5743e4 --- /dev/null +++ b/include/uapi/linux/io_uring/bpf_filter.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ +/* + * Header file for the io_uring BPF filters. + */ +#ifndef LINUX_IO_URING_BPF_FILTER_H +#define LINUX_IO_URING_BPF_FILTER_H + +#include + +/* + * Struct passed to filters. + */ +struct io_uring_bpf_ctx { + __u64 user_data; + __u8 opcode; + __u8 sqe_flags; + __u8 pdu_size; /* size of aux data for filter */ + __u8 pad[5]; +}; + +enum { + /* + * If set, any currently unset opcode will have a deny filter attached + */ + IO_URING_BPF_FILTER_DENY_REST = 1, +}; + +struct io_uring_bpf_filter { + __u32 opcode; /* io_uring opcode to filter */ + __u32 flags; + __u32 filter_len; /* number of BPF instructions */ + __u32 resv; + __u64 filter_ptr; /* pointer to BPF filter */ + __u64 resv2[5]; +}; + +enum { + IO_URING_BPF_CMD_FILTER = 1, +}; + +struct io_uring_bpf { + __u16 cmd_type; /* IO_URING_BPF_* values */ + __u16 cmd_flags; /* none so far */ + __u32 resv; + union { + struct io_uring_bpf_filter filter; + }; +}; + +#endif -- cgit v1.2.3 From cff1c26b4223820431129696b45525e5928e6409 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 16 Jan 2026 14:50:05 -0700 Subject: io_uring/net: allow filtering on IORING_OP_SOCKET data Example population method for the BPF based opcode filtering. This exposes the socket family, type, and protocol to a registered BPF filter. This in turn enables the filter to make decisions based on what was passed in to the IORING_OP_SOCKET request type. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/bpf_filter.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/bpf_filter.h b/include/uapi/linux/io_uring/bpf_filter.h index 2d4d0e5743e4..4dbc89bbbf10 100644 --- a/include/uapi/linux/io_uring/bpf_filter.h +++ b/include/uapi/linux/io_uring/bpf_filter.h @@ -16,6 +16,13 @@ struct io_uring_bpf_ctx { __u8 sqe_flags; __u8 pdu_size; /* size of aux data for filter */ __u8 pad[5]; + union { + struct { + __u32 family; + __u32 type; + __u32 protocol; + } socket; + }; }; enum { -- cgit v1.2.3 From 8768770cf5d76d177fa2200e6957a372e61e06b5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 19 Jan 2026 15:59:54 -0700 Subject: io_uring/bpf_filter: allow filtering on contents of struct open_how This adds custom filtering for IORING_OP_OPENAT and IORING_OP_OPENAT2, where the open_how flags, mode, and resolve can be checked by filters. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/bpf_filter.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/bpf_filter.h b/include/uapi/linux/io_uring/bpf_filter.h index 4dbc89bbbf10..220351b81bc0 100644 --- a/include/uapi/linux/io_uring/bpf_filter.h +++ b/include/uapi/linux/io_uring/bpf_filter.h @@ -22,6 +22,11 @@ struct io_uring_bpf_ctx { __u32 type; __u32 protocol; } socket; + struct { + __u64 flags; + __u64 mode; + __u64 resolve; + } open; }; }; -- cgit v1.2.3 From cad3337bb6c3a2ba2307d6a9061e752e15681d2b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 19 Dec 2025 19:40:33 +0200 Subject: PCI: Add dword #defines for Bus Number + Secondary Latency Timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit uapi/linux/pci_regs.h defines Primary/Secondary/Subordinate Bus Numbers and Secondary Latency Timer (PCIe r7.0, sec. 7.5.1.3) as byte register offsets, but in practice the code may read/write the entire dword. In the lack of #defines to handle the dword fields, the code ends up using literals which are not as easy to read. Add dword field masks for the Bus Number and Secondary Latency Timer fields and use them in probe.c. Signed-off-by: Ilpo Järvinen [bhelgaas: squash new #defines and uses together] Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20251219174036.16738-21-ilpo.jarvinen@linux.intel.com Link: https://patch.msgid.link/20251219174036.16738-22-ilpo.jarvinen@linux.intel.com --- include/uapi/linux/pci_regs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 3add74ae2594..8be55ece2a21 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -132,6 +132,11 @@ #define PCI_SECONDARY_BUS 0x19 /* Secondary bus number */ #define PCI_SUBORDINATE_BUS 0x1a /* Highest bus number behind the bridge */ #define PCI_SEC_LATENCY_TIMER 0x1b /* Latency timer for secondary interface */ +/* Masks for dword-sized processing of Bus Number and Sec Latency Timer fields */ +#define PCI_PRIMARY_BUS_MASK 0x000000ff +#define PCI_SECONDARY_BUS_MASK 0x0000ff00 +#define PCI_SUBORDINATE_BUS_MASK 0x00ff0000 +#define PCI_SEC_LATENCY_TIMER_MASK 0xff000000 #define PCI_IO_BASE 0x1c /* I/O range behind the bridge */ #define PCI_IO_LIMIT 0x1d #define PCI_IO_RANGE_TYPE_MASK 0x0fUL /* I/O bridging type */ -- cgit v1.2.3 From e698127eb7249d6c70fa8f2bdba469c0e54f2e2b Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Wed, 23 Jul 2025 10:07:28 -0400 Subject: drm/amdkfd: add extended capabilities to device snapshot Add additional capabilities reporting. Signed-off-by: Jonathan Kim Reviewed-by: James Zhu 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 047bcb1cc078..e72359370857 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -149,6 +149,8 @@ struct kfd_dbg_device_info_entry { __u32 num_xcc; __u32 capability; __u32 debug_prop; + __u32 capability2; + __u32 pad; }; /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ -- cgit v1.2.3 From d8316b837c2ca5f92e781fa1575095c0132ae3c1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 6 Jan 2026 13:59:50 -0500 Subject: nfsd: add controls to set the minimum number of threads per pool Add a new "min_threads" variable to the nfsd_net, along with the corresponding netlink interface, to set that value from userland. Pass that value to svc_set_pool_threads() and svc_set_num_threads(). Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/uapi/linux/nfsd_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index e157e2009ea8..e9efbc9e63d8 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -35,6 +35,7 @@ enum { NFSD_A_SERVER_GRACETIME, NFSD_A_SERVER_LEASETIME, NFSD_A_SERVER_SCOPE, + NFSD_A_SERVER_MIN_THREADS, __NFSD_A_SERVER_MAX, NFSD_A_SERVER_MAX = (__NFSD_A_SERVER_MAX - 1) -- cgit v1.2.3 From a006ed4ecd4905b69402980ad7d4e5f31bf44953 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= Date: Mon, 19 Jan 2026 15:32:55 +0100 Subject: vduse: add v1 API definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows the kernel to detect whether the userspace VDUSE device supports the VQ group and ASID features. VDUSE devices that don't set the V1 API will not receive the new messages, and vdpa device will be created with only one vq group and asid. The next patches implement the new feature incrementally, only enabling the VDUSE device to set the V1 API version by the end of the series. Acked-by: Jason Wang Reviewed-by: Xie Yongji Signed-off-by: Eugenio Pérez Signed-off-by: Michael S. Tsirkin Message-Id: <20260119143306.1818855-3-eperezma@redhat.com> --- include/uapi/linux/vduse.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index 10ad71aa00d6..ccb92a1efce0 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -10,6 +10,10 @@ #define VDUSE_API_VERSION 0 +/* VQ groups and ASID support */ + +#define VDUSE_API_VERSION_1 1 + /* * Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION). * This is used for future extension. -- cgit v1.2.3 From 9350a09afd086771b0612c7b7c9583e8a1568135 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= Date: Mon, 19 Jan 2026 15:32:56 +0100 Subject: vduse: add vq group support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows separate the different virtqueues in groups that shares the same address space. Asking the VDUSE device for the groups of the vq at the beginning as they're needed for the DMA API. Allocating 3 vq groups as net is the device that need the most groups: * Dataplane (guest passthrough) * CVQ * Shadowed vrings. Future versions of the series can include dynamic allocation of the groups array so VDUSE can declare more groups. Acked-by: Jason Wang Reviewed-by: Xie Yongji Signed-off-by: Eugenio Pérez Signed-off-by: Michael S. Tsirkin Message-Id: <20260119143306.1818855-4-eperezma@redhat.com> --- include/uapi/linux/vduse.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index ccb92a1efce0..a3d51cf6df3a 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -31,6 +31,7 @@ * @features: virtio features * @vq_num: the number of virtqueues * @vq_align: the allocation alignment of virtqueue's metadata + * @ngroups: number of vq groups that VDUSE device declares * @reserved: for future use, needs to be initialized to zero * @config_size: the size of the configuration space * @config: the buffer of the configuration space @@ -45,7 +46,8 @@ struct vduse_dev_config { __u64 features; __u32 vq_num; __u32 vq_align; - __u32 reserved[13]; + __u32 ngroups; /* if VDUSE_API_VERSION >= 1 */ + __u32 reserved[12]; __u32 config_size; __u8 config[]; }; @@ -122,14 +124,18 @@ struct vduse_config_data { * struct vduse_vq_config - basic configuration of a virtqueue * @index: virtqueue index * @max_size: the max size of virtqueue - * @reserved: for future use, needs to be initialized to zero + * @reserved1: for future use, needs to be initialized to zero + * @group: virtqueue group + * @reserved2: for future use, needs to be initialized to zero * * Structure used by VDUSE_VQ_SETUP ioctl to setup a virtqueue. */ struct vduse_vq_config { __u32 index; __u16 max_size; - __u16 reserved[13]; + __u16 reserved1; + __u32 group; + __u16 reserved2[10]; }; /* -- cgit v1.2.3 From 079212f6877e5d07308c8998a8fbc7539ca3f8f3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= Date: Mon, 19 Jan 2026 15:33:04 +0100 Subject: vduse: add vq group asid support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for assigning Address Space Identifiers (ASIDs) to each VQ group. This enables mapping each group into a distinct memory space. The vq group to ASID association is protected by a rwlock now. But the mutex domain_lock keeps protecting the domains of all ASIDs, as some operations like the one related with the bounce buffer size still requires to lock all the ASIDs. Acked-by: Jason Wang Signed-off-by: Eugenio Pérez Signed-off-by: Michael S. Tsirkin Message-Id: <20260119143306.1818855-12-eperezma@redhat.com> --- include/uapi/linux/vduse.h | 66 +++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 63 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index a3d51cf6df3a..68b4287f9fac 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -32,6 +32,7 @@ * @vq_num: the number of virtqueues * @vq_align: the allocation alignment of virtqueue's metadata * @ngroups: number of vq groups that VDUSE device declares + * @nas: number of address spaces that VDUSE device declares * @reserved: for future use, needs to be initialized to zero * @config_size: the size of the configuration space * @config: the buffer of the configuration space @@ -47,7 +48,8 @@ struct vduse_dev_config { __u32 vq_num; __u32 vq_align; __u32 ngroups; /* if VDUSE_API_VERSION >= 1 */ - __u32 reserved[12]; + __u32 nas; /* if VDUSE_API_VERSION >= 1 */ + __u32 reserved[11]; __u32 config_size; __u8 config[]; }; @@ -166,6 +168,16 @@ struct vduse_vq_state_packed { __u16 last_used_idx; }; +/** + * struct vduse_vq_group_asid - virtqueue group ASID + * @group: Index of the virtqueue group + * @asid: Address space ID of the group + */ +struct vduse_vq_group_asid { + __u32 group; + __u32 asid; +}; + /** * struct vduse_vq_info - information of a virtqueue * @index: virtqueue index @@ -225,6 +237,7 @@ struct vduse_vq_eventfd { * @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 + * @asid: Address space ID 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 @@ -234,7 +247,8 @@ struct vduse_iova_umem { __u64 uaddr; __u64 iova; __u64 size; - __u64 reserved[3]; + __u32 asid; + __u32 reserved[5]; }; /* Register userspace memory for IOVA regions */ @@ -248,6 +262,7 @@ struct vduse_iova_umem { * @start: start of the IOVA region * @last: last of the IOVA region * @capability: capability of the IOVA region + * @asid: Address space ID of the IOVA region, only if device API version >= 1 * @reserved: for future use, needs to be initialized to zero * * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of @@ -258,7 +273,8 @@ struct vduse_iova_info { __u64 last; #define VDUSE_IOVA_CAP_UMEM (1 << 0) __u64 capability; - __u64 reserved[3]; + __u32 asid; /* Only if device API version >= 1 */ + __u32 reserved[5]; }; /* @@ -267,6 +283,28 @@ struct vduse_iova_info { */ #define VDUSE_IOTLB_GET_INFO _IOWR(VDUSE_BASE, 0x1a, struct vduse_iova_info) +/** + * struct vduse_iotlb_entry_v2 - entry of IOTLB to describe one IOVA region + * + * @v1: the original vduse_iotlb_entry + * @asid: address space ID of the IOVA region + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_IOTLB_GET_FD2 ioctl to find an overlapped IOVA region. + */ +struct vduse_iotlb_entry_v2 { + struct vduse_iotlb_entry v1; + __u32 asid; + __u32 reserved[12]; +}; + +/* + * Same as VDUSE_IOTLB_GET_FD but with vduse_iotlb_entry_v2 argument that + * support extra fields. + */ +#define VDUSE_IOTLB_GET_FD2 _IOWR(VDUSE_BASE, 0x1b, struct vduse_iotlb_entry_v2) + + /* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ /** @@ -275,11 +313,14 @@ struct vduse_iova_info { * @VDUSE_SET_STATUS: set the device status * @VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for * specified IOVA range via VDUSE_IOTLB_GET_FD ioctl + * @VDUSE_SET_VQ_GROUP_ASID: Notify userspace to update the address space of a + * virtqueue group. */ enum vduse_req_type { VDUSE_GET_VQ_STATE, VDUSE_SET_STATUS, VDUSE_UPDATE_IOTLB, + VDUSE_SET_VQ_GROUP_ASID, }; /** @@ -314,6 +355,18 @@ struct vduse_iova_range { __u64 last; }; +/** + * struct vduse_iova_range_v2 - IOVA range [start, last] if API_VERSION >= 1 + * @start: start of the IOVA range + * @last: last of the IOVA range + * @asid: address space ID of the IOVA range + */ +struct vduse_iova_range_v2 { + __u64 start; + __u64 last; + __u32 asid; +}; + /** * struct vduse_dev_request - control request * @type: request type @@ -322,6 +375,8 @@ struct vduse_iova_range { * @vq_state: virtqueue state, only index field is available * @s: device status * @iova: IOVA range for updating + * @iova_v2: IOVA range for updating if API_VERSION >= 1 + * @vq_group_asid: ASID of a virtqueue group * @padding: padding * * Structure used by read(2) on /dev/vduse/$NAME. @@ -334,6 +389,11 @@ struct vduse_dev_request { struct vduse_vq_state vq_state; struct vduse_dev_status s; struct vduse_iova_range iova; + /* Following members but padding exist only if vduse api + * version >= 1 + */ + struct vduse_iova_range_v2 iova_v2; + struct vduse_vq_group_asid vq_group_asid; __u32 padding[32]; }; }; -- cgit v1.2.3 From 5ca243f6e3c30b979a54a96b96df355dda2b4d0f Mon Sep 17 00:00:00 2001 From: Deepak Gupta Date: Sun, 25 Jan 2026 21:09:54 -0700 Subject: prctl: add arch-agnostic prctl()s for indirect branch tracking Three architectures (x86, aarch64, riscv) have support for indirect branch tracking feature in a very similar fashion. On a very high level, indirect branch tracking is a CPU feature where CPU tracks branches which use a memory operand to transfer control. As part of this tracking, during an indirect branch, the CPU expects a landing pad instruction on the target PC, and if not found, the CPU raises some fault (architecture-dependent). x86 landing pad instr - 'ENDBRANCH' arch64 landing pad instr - 'BTI' riscv landing instr - 'lpad' Given that three major architectures have support for indirect branch tracking, this patch creates architecture-agnostic 'prctls' to allow userspace to control this feature. They are: - PR_GET_INDIR_BR_LP_STATUS: Get the current configured status for indirect branch tracking. - PR_SET_INDIR_BR_LP_STATUS: Set the configuration for indirect branch tracking. The following status options are allowed: - PR_INDIR_BR_LP_ENABLE: Enables indirect branch tracking on user thread. - PR_INDIR_BR_LP_DISABLE: Disables indirect branch tracking on user thread. - PR_LOCK_INDIR_BR_LP_STATUS: Locks configured status for indirect branch tracking for user thread. Reviewed-by: Mark Brown Reviewed-by: Zong Li Signed-off-by: Deepak Gupta Tested-by: Andreas Korb # QEMU, custom CVA6 Tested-by: Valentin Haudiquet Link: https://patch.msgid.link/20251112-v5_user_cfi_series-v23-13-b55691eacf4f@rivosinc.com [pjw@kernel.org: cleaned up patch description, code comments] Signed-off-by: Paul Walmsley --- include/uapi/linux/prctl.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 51c4e8c82b1e..f57098fb0ba8 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -386,4 +386,31 @@ struct prctl_mm_map { # define PR_FUTEX_HASH_SET_SLOTS 1 # define PR_FUTEX_HASH_GET_SLOTS 2 +/* + * Get the current indirect branch tracking configuration for the current + * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS. + */ +#define PR_GET_INDIR_BR_LP_STATUS 79 + +/* + * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will + * enable cpu feature for user thread, to track all indirect branches and ensure + * they land on arch defined landing pad instruction. + * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction. + * arch64 - If enabled, an indirect branch must land on a BTI instruction. + * riscv - If enabled, an indirect branch must land on an lpad instruction. + * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect + * branches will no more be tracked by cpu to land on arch defined landing pad + * instruction. + */ +#define PR_SET_INDIR_BR_LP_STATUS 80 +# define PR_INDIR_BR_LP_ENABLE (1UL << 0) + +/* + * Prevent further changes to the specified indirect branch tracking + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_INDIR_BR_LP_STATUS 81 + #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From 2af7c9cf021c5dabe880b68e5cc22c618060d954 Mon Sep 17 00:00:00 2001 From: Deepak Gupta Date: Sun, 25 Jan 2026 21:09:55 -0700 Subject: riscv/ptrace: expose riscv CFI status and state via ptrace and in core files Expose a new register type NT_RISCV_USER_CFI for risc-v CFI status and state. Intentionally, both landing pad and shadow stack status and state are rolled into the CFI state. Creating two different NT_RISCV_USER_XXX would not be useful and would waste a note type. Enabling, disabling and locking the CFI feature is not allowed via ptrace set interface. However, setting 'elp' state or setting shadow stack pointer are allowed via the ptrace set interface. It is expected that 'gdb' might need to fixup 'elp' state or 'shadow stack' pointer. Signed-off-by: Deepak Gupta Tested-by: Andreas Korb # QEMU, custom CVA6 Tested-by: Valentin Haudiquet Link: https://patch.msgid.link/20251112-v5_user_cfi_series-v23-19-b55691eacf4f@rivosinc.com [pjw@kernel.org: updated to apply; cleaned patch description and comments; addressed checkpatch issues] Signed-off-by: Paul Walmsley --- include/uapi/linux/elf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 819ded2d39de..ee30dcd80901 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -545,6 +545,8 @@ typedef struct elf64_shdr { #define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ #define NN_RISCV_TAGGED_ADDR_CTRL "LINUX" #define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NN_RISCV_USER_CFI "LINUX" +#define NT_RISCV_USER_CFI 0x903 /* RISC-V shadow stack state */ #define NN_LOONGARCH_CPUCFG "LINUX" #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NN_LOONGARCH_CSR "LINUX" -- cgit v1.2.3 From 0e6b7eae1fded85f94a357d6132f07d64c614cfa Mon Sep 17 00:00:00 2001 From: Andrey Albershteyn Date: Mon, 26 Jan 2026 12:56:57 +0100 Subject: fs: add FS_XFLAG_VERITY for fs-verity files fs-verity introduced inode flag for inodes with enabled fs-verity on them. This patch adds FS_XFLAG_VERITY file attribute which can be retrieved with FS_IOC_FSGETXATTR ioctl() and file_getattr() syscall. This flag is read-only and can not be set with corresponding set ioctl() and file_setattr(). The FS_IOC_SETFLAGS requires file to be opened for writing which is not allowed for verity files. The FS_IOC_FSSETXATTR and file_setattr() clears this flag from the user input. As this is now common flag for both flag interfaces (flags/xflags) add it to overlapping flags list to exclude it from overwrite. Signed-off-by: Andrey Albershteyn Link: https://patch.msgid.link/20260126115658.27656-2-aalbersh@kernel.org Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/uapi/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 66ca526cf786..70b2b661f42c 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -253,6 +253,7 @@ struct file_attr { #define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ #define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ #define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ +#define FS_XFLAG_VERITY 0x00020000 /* fs-verity enabled */ #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ /* the read-only stuff doesn't really belong here, but any other place is -- cgit v1.2.3 From 8cf82bb558517503a81f8e3c49914c0836360aa6 Mon Sep 17 00:00:00 2001 From: Koichiro Den Date: Sat, 24 Jan 2026 23:50:11 +0900 Subject: misc: pci_endpoint_test: Add BAR subrange mapping test case Add a new PCITEST_BAR_SUBRANGE ioctl to exercise EPC BAR subrange mapping end-to-end. The test programs a simple 2-subrange layout on the endpoint (via pci-epf-test) and verifies that: - the endpoint-provided per-subrange signature bytes are observed at the expected PCIe BAR offsets, and - writes to each subrange are routed to the correct backing region (i.e. the submap order is applied rather than accidentally working due to an identity mapping). Return -EOPNOTSUPP when the endpoint does not advertise subrange mapping, -ENODATA when the BAR is disabled, and -EBUSY when the BAR is reserved for the test register space. Signed-off-by: Koichiro Den Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20260124145012.2794108-8-den@valinux.co.jp --- include/uapi/linux/pcitest.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index d6023a45a9d0..710f8842223f 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -22,6 +22,7 @@ #define PCITEST_GET_IRQTYPE _IO('P', 0x9) #define PCITEST_BARS _IO('P', 0xa) #define PCITEST_DOORBELL _IO('P', 0xb) +#define PCITEST_BAR_SUBRANGE _IO('P', 0xc) #define PCITEST_CLEAR_IRQ _IO('P', 0x10) #define PCITEST_IRQ_TYPE_UNDEFINED -1 -- cgit v1.2.3 From bc443c253fcdd2636e2a29fde3f749d39d479cf0 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Mon, 26 Jan 2026 17:22:51 +0100 Subject: dpll: expose fractional frequency offset in ppt Currently, the dpll subsystem exports the fractional frequency offset (FFO) in parts per million (ppm). This granularity is insufficient for high-precision synchronization scenarios which often require parts per trillion (ppt) resolution. Add a new netlink attribute DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET_PPT to expose the FFO in ppt. Update the dpll netlink core to expect the driver-provided FFO value to be in ppt. To maintain backward compatibility with existing userspace tools, populate the legacy DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET attribute by dividing the new ppt value by 1,000,000. Update the zl3073x and mlx5 drivers to provide the FFO value in ppt: - zl3073x: adjust the fixed-point calculation to produce ppt (10^12) instead of ppm (10^6). - mlx5: scale the existing ppm value by 1,000,000. Signed-off-by: Ivan Vecera Reviewed-by: Arkadiusz Kubalewski Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20260126162253.27890-1-ivecera@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/dpll.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index b7ff9c44f9aa..de0005f28e5c 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -253,6 +253,7 @@ enum dpll_a_pin { DPLL_A_PIN_ESYNC_PULSE, DPLL_A_PIN_REFERENCE_SYNC, DPLL_A_PIN_PHASE_ADJUST_GRAN, + DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET_PPT, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) -- cgit v1.2.3 From 8443e2087e7002fa25984faad6bbf5f63b280645 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 30 Jan 2026 00:19:51 +0800 Subject: ublk: add UBLK_F_NO_AUTO_PART_SCAN feature flag Add a new feature flag UBLK_F_NO_AUTO_PART_SCAN to allow users to suppress automatic partition scanning when starting a ublk device. This is useful for some cases in which user don't want to scan partitions. Users still can manually trigger partition scanning later when appropriate using standard tools (e.g., partprobe, blockdev --rereadpt). Reported-by: Yoav Cohen Link: https://lore.kernel.org/linux-block/DM4PR12MB63280C5637917C071C2F0D65A9A8A@DM4PR12MB6328.namprd12.prod.outlook.com/ Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/uapi/linux/ublk_cmd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 743d31491387..a88876756805 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -367,6 +367,9 @@ */ #define UBLK_F_SAFE_STOP_DEV (1ULL << 17) +/* Disable automatic partition scanning when device is started */ +#define UBLK_F_NO_AUTO_PART_SCAN (1ULL << 18) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From 503efe850c7463a1e59df133b84461ef53c0361f Mon Sep 17 00:00:00 2001 From: Wang Yaxin Date: Mon, 19 Jan 2026 10:02:41 +0800 Subject: delayacct: add timestamp of delay max Problem ======= Commit 658eb5ab916d ("delayacct: add delay max to record delay peak") introduced the delay max for getdelays, which records abnormal latency peaks and helps us understand the magnitude of such delays. However, the peak latency value alone is insufficient for effective root cause analysis. Without the precise timestamp of when the peak occurred, we still lack the critical context needed to correlate it with other system events. Solution ======== To address this, we need to additionally record a precise timestamp when the maximum latency occurs. By correlating this timestamp with system logs and monitoring metrics, we can identify processes with abnormal resource usage at the same moment, which can help us to pinpoint root causes. Use Case ======== bash-4.4# ./getdelays -d -t 227 print delayacct stats ON TGID 227 CPU count real total virtual total delay total delay average delay max delay min delay max timestamp 46 188000000 192348334 4098012 0.089ms 0.429260ms 0.051205ms 2026-01-15T15:06:58 IO count delay total delay average delay max delay min delay max timestamp 0 0 0.000ms 0.000000ms 0.000000ms N/A SWAP count delay total delay average delay max delay min delay max timestamp 0 0 0.000ms 0.000000ms 0.000000ms N/A RECLAIM count delay total delay average delay max delay min delay max timestamp 0 0 0.000ms 0.000000ms 0.000000ms N/A THRAS HING count delay total delay average delay max delay min delay max timestamp 0 0 0.000ms 0.000000ms 0.000000ms N/A COMPACT count delay total delay average delay max delay min delay max timestamp 0 0 0.000ms 0.000000ms 0.000000ms N/A WPCOPY count delay total delay average delay max delay min delay max timestamp 182 19413338 0.107ms 0.547353ms 0.022462ms 2026-01-15T15:05:24 IRQ count delay total delay average delay max delay min delay max timestamp 0 0 0.000ms 0.000000ms 0.000000ms N/A Link: https://lkml.kernel.org/r/20260119100241520gWubW8-5QfhSf9gjqcc_E@zte.com.cn Signed-off-by: Wang Yaxin Cc: Fan Yu Cc: Jonathan Corbet Cc: xu xin Cc: Yang Yang Signed-off-by: Andrew Morton --- include/uapi/linux/taskstats.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 5929030d4e8b..1b31e8e14d2f 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -18,6 +18,16 @@ #define _LINUX_TASKSTATS_H #include +#ifdef __KERNEL__ +#include +#else +#ifndef _LINUX_TIME64_H +struct timespec64 { + __s64 tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ +}; +#endif +#endif /* Format for per-task data returned to userland when * - a task exits @@ -34,7 +44,7 @@ */ -#define TASKSTATS_VERSION 16 +#define TASKSTATS_VERSION 17 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -230,6 +240,16 @@ struct taskstats { __u64 irq_delay_max; __u64 irq_delay_min; + + /*v17: delay max timestamp record*/ + struct timespec64 cpu_delay_max_ts; + struct timespec64 blkio_delay_max_ts; + struct timespec64 swapin_delay_max_ts; + struct timespec64 freepages_delay_max_ts; + struct timespec64 thrashing_delay_max_ts; + struct timespec64 compact_delay_max_ts; + struct timespec64 wpcopy_delay_max_ts; + struct timespec64 irq_delay_max_ts; }; -- cgit v1.2.3 From 072e6f7f416f5d17be71000b31fb108651ad360d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 30 Jan 2026 16:21:06 +0100 Subject: wifi: cfg80211: add initial UHR support Add initial support for making UHR connections (or suppressing that), adding UHR capable stations on the AP side, encoding and decoding UHR MCSes (except rate calculation for the new MCSes 17, 19, 20 and 23) as well as regulatory support. Link: https://patch.msgid.link/20260130164259.54cc12fbb307.I26126bebd83c7ab17e99827489f946ceabb3521f@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 706a98686068..b63f71850906 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2977,6 +2977,13 @@ enum nl80211_commands { * @NL80211_ATTR_EPP_PEER: A flag attribute to indicate if the peer is an EPP * STA. Used with %NL80211_CMD_NEW_STA and %NL80211_CMD_ADD_LINK_STA * + * @NL80211_ATTR_UHR_CAPABILITY: UHR Capability information element (from + * association request when used with NL80211_CMD_NEW_STATION). Can be set + * only if HE/EHT are also available. + * @NL80211_ATTR_DISABLE_UHR: Force UHR capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3547,6 +3554,9 @@ enum nl80211_attrs { NL80211_ATTR_EPP_PEER, + NL80211_ATTR_UHR_CAPABILITY, + NL80211_ATTR_DISABLE_UHR, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3899,6 +3909,12 @@ enum nl80211_eht_ru_alloc { * @NL80211_RATE_INFO_4_MHZ_WIDTH: 4 MHz S1G rate * @NL80211_RATE_INFO_8_MHZ_WIDTH: 8 MHz S1G rate * @NL80211_RATE_INFO_16_MHZ_WIDTH: 16 MHz S1G rate + * @NL80211_RATE_INFO_UHR_MCS: UHR MCS index (u8, 0-15, 17, 19, 20, 23) + * Note that the other EHT attributes (such as @NL80211_RATE_INFO_EHT_NSS) + * are used in conjunction with this where applicable + * @NL80211_RATE_INFO_UHR_ELR: UHR ELR flag, which restricts NSS to 1, + * MCS to 0 or 1, and GI to %NL80211_RATE_INFO_EHT_GI_1_6. + * @NL80211_RATE_INFO_UHR_IM: UHR Interference Mitigation flag * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ enum nl80211_rate_info { @@ -3932,6 +3948,9 @@ enum nl80211_rate_info { NL80211_RATE_INFO_4_MHZ_WIDTH, NL80211_RATE_INFO_8_MHZ_WIDTH, NL80211_RATE_INFO_16_MHZ_WIDTH, + NL80211_RATE_INFO_UHR_MCS, + NL80211_RATE_INFO_UHR_ELR, + NL80211_RATE_INFO_UHR_IM, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, @@ -4254,6 +4273,10 @@ enum nl80211_mpath_info { * capabilities element * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE: EHT PPE thresholds information as * defined in EHT capabilities element + * @NL80211_BAND_IFTYPE_ATTR_UHR_CAP_MAC: UHR MAC capabilities as in UHR + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_UHR_CAP_PHY: UHR PHY capabilities as in UHR + * capabilities element * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band attribute currently defined */ @@ -4271,6 +4294,8 @@ enum nl80211_band_iftype_attr { NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PHY, NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MCS_SET, NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE, + NL80211_BAND_IFTYPE_ATTR_UHR_CAP_MAC, + NL80211_BAND_IFTYPE_ATTR_UHR_CAP_PHY, /* keep last */ __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, @@ -4453,6 +4478,8 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_S1G_NO_PRIMARY: Channel is not permitted for use * as a primary channel. Does not prevent the channel from existing * as a non-primary subchannel. Only applicable to S1G channels. + * @NL80211_FREQUENCY_ATTR_NO_UHR: UHR operation is not allowed on this channel + * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4502,6 +4529,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_8MHZ, NL80211_FREQUENCY_ATTR_NO_16MHZ, NL80211_FREQUENCY_ATTR_S1G_NO_PRIMARY, + NL80211_FREQUENCY_ATTR_NO_UHR, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4715,6 +4743,7 @@ enum nl80211_sched_scan_match_attr { * despite NO_IR configuration. * @NL80211_RRF_ALLOW_20MHZ_ACTIVITY: Allow activity in 20 MHz bandwidth, * despite NO_IR configuration. + * @NL80211_RRF_NO_UHR: UHR operation not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1 << 0, @@ -4741,6 +4770,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_6GHZ_AFC_CLIENT = 1 << 23, NL80211_RRF_ALLOW_6GHZ_VLP_AP = 1 << 24, NL80211_RRF_ALLOW_20MHZ_ACTIVITY = 1 << 25, + NL80211_RRF_NO_UHR = 1 << 26, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR -- cgit v1.2.3 From 3495064b6d65a669b409cfe1241db4f3c540251a Mon Sep 17 00:00:00 2001 From: Babis Chalios Date: Fri, 30 Jan 2026 17:36:00 +0000 Subject: ptp: vmclock: add vm generation counter Similar to live migration, loading a VM from some saved state (aka snapshot) is also an event that calls for clock adjustments in the guest. However, guests might want to take more actions as a response to such events, e.g. as discarding UUIDs, resetting network connections, reseeding entropy pools, etc. These are actions that guests don't typically take during live migration, so add a new field in the vmclock_abi called vm_generation_counter which informs the guest about such events. Hypervisor advertises support for vm_generation_counter through the VMCLOCK_FLAG_VM_GEN_COUNTER_PRESENT flag. Users need to check the presence of this bit in vmclock_abi flags field before using this flag. Signed-off-by: Babis Chalios Signed-off-by: David Woodhouse Reviewed-by: David Woodhouse Tested-by: Takahiro Itazur Link: https://patch.msgid.link/20260130173704.12575-2-itazur@amazon.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/vmclock-abi.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vmclock-abi.h b/include/uapi/linux/vmclock-abi.h index 2d99b29ac44a..937fe00e4f33 100644 --- a/include/uapi/linux/vmclock-abi.h +++ b/include/uapi/linux/vmclock-abi.h @@ -115,6 +115,12 @@ struct vmclock_abi { * bit again after the update, using the about-to-be-valid fields. */ #define VMCLOCK_FLAG_TIME_MONOTONIC (1 << 7) + /* + * If the VM_GEN_COUNTER_PRESENT flag is set, the hypervisor will + * bump the vm_generation_counter field every time the guest is + * loaded from some save state (restored from a snapshot). + */ +#define VMCLOCK_FLAG_VM_GEN_COUNTER_PRESENT (1 << 8) __u8 pad[2]; __u8 clock_status; @@ -177,6 +183,15 @@ struct vmclock_abi { __le64 time_frac_sec; /* Units of 1/2^64 of a second */ __le64 time_esterror_nanosec; __le64 time_maxerror_nanosec; + + /* + * This field changes to another non-repeating value when the guest + * has been loaded from a snapshot. In addition to handling a + * disruption in time (which will also be signalled through the + * disruption_marker field), a guest may wish to discard UUIDs, + * reset network connections, reseed entropy, etc. + */ + __le64 vm_generation_counter; }; #endif /* __VMCLOCK_ABI_H__ */ -- cgit v1.2.3 From 3b1526ddb25452385b52f2588b655f524a57070b Mon Sep 17 00:00:00 2001 From: Babis Chalios Date: Fri, 30 Jan 2026 17:36:01 +0000 Subject: ptp: vmclock: support device notifications Add optional support for device notifications in VMClock. When supported, the hypervisor will send a device notification every time it updates the seq_count to a new even value. Moreover, add support for poll() in VMClock as a means to propagate this notification to user space. poll() will return a POLLIN event to listeners every time seq_count changes to a value different than the one last seen (since open() or last read()/pread()). This means that when poll() returns a POLLIN event, listeners need to use read() to observe what has changed and update the reader's view of seq_count. In other words, after a poll() returned, all subsequent calls to poll() will immediately return with a POLLIN event until the listener calls read(). The device advertises support for the notification mechanism by setting flag VMCLOCK_FLAG_NOTIFICATION_PRESENT in vmclock_abi flags field. If the flag is not present the driver won't setup the ACPI notification handler and poll() will always immediately return POLLHUP. Signed-off-by: Babis Chalios Signed-off-by: David Woodhouse Signed-off-by: Takahiro Itazuri Reviewed-by: David Woodhouse Tested-by: Takahiro Itazuri Link: https://patch.msgid.link/20260130173704.12575-3-itazur@amazon.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/vmclock-abi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vmclock-abi.h b/include/uapi/linux/vmclock-abi.h index 937fe00e4f33..d320623b0118 100644 --- a/include/uapi/linux/vmclock-abi.h +++ b/include/uapi/linux/vmclock-abi.h @@ -121,6 +121,11 @@ struct vmclock_abi { * loaded from some save state (restored from a snapshot). */ #define VMCLOCK_FLAG_VM_GEN_COUNTER_PRESENT (1 << 8) + /* + * If the NOTIFICATION_PRESENT flag is set, the hypervisor will send + * a notification every time it updates seq_count to a new even number. + */ +#define VMCLOCK_FLAG_NOTIFICATION_PRESENT (1 << 9) __u8 pad[2]; __u8 clock_status; -- cgit v1.2.3 From ef6a31d035a1000071dc4846aebd02ad081db9e4 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Wed, 7 Jan 2026 14:09:01 +0000 Subject: btrfs: add definitions and constants for remap-tree Add an incompat flag for the new remap-tree feature, and the constants and definitions needed to support it. Reviewed-by: Boris Burkov Signed-off-by: Mark Harmstone Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 1 + include/uapi/linux/btrfs_tree.h | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index e8fd92789423..9165154a274d 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -336,6 +336,7 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2 (1ULL << 13) #define BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE (1ULL << 14) #define BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA (1ULL << 16) +#define BTRFS_FEATURE_INCOMPAT_REMAP_TREE (1ULL << 17) struct btrfs_ioctl_feature_flags { __u64 compat_flags; diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index fc29d273845d..f011d34cb699 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -76,6 +76,9 @@ /* Tracks RAID stripes in block groups. */ #define BTRFS_RAID_STRIPE_TREE_OBJECTID 12ULL +/* Holds details of remapped addresses after relocation. */ +#define BTRFS_REMAP_TREE_OBJECTID 13ULL + /* device stats in the device tree */ #define BTRFS_DEV_STATS_OBJECTID 0ULL @@ -282,6 +285,10 @@ #define BTRFS_RAID_STRIPE_KEY 230 +#define BTRFS_IDENTITY_REMAP_KEY 234 +#define BTRFS_REMAP_KEY 235 +#define BTRFS_REMAP_BACKREF_KEY 236 + /* * Records the overall state of the qgroups. * There's only one instance of this key present, @@ -1161,6 +1168,7 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) #define BTRFS_BLOCK_GROUP_RAID1C3 (1ULL << 9) #define BTRFS_BLOCK_GROUP_RAID1C4 (1ULL << 10) +#define BTRFS_BLOCK_GROUP_REMAPPED (1ULL << 11) #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) @@ -1323,4 +1331,13 @@ struct btrfs_verity_descriptor_item { __u8 encryption; } __attribute__ ((__packed__)); +/* + * For a range identified by a BTRFS_REMAP_KEY item in the remap tree, gives + * the address that the start of the range will get remapped to. This + * structure is also shared by BTRFS_REMAP_BACKREF_KEY. + */ +struct btrfs_remap_item { + __le64 address; +} __attribute__ ((__packed__)); + #endif /* _BTRFS_CTREE_H_ */ -- cgit v1.2.3 From 0b4d29fa98ca1a49c4498353253f857573871ba0 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Wed, 7 Jan 2026 14:09:02 +0000 Subject: btrfs: add METADATA_REMAP chunk type Add a new METADATA_REMAP chunk type, which is a metadata chunk that holds the remap tree. This is needed for bootstrapping purposes: the remap tree can't itself be remapped, and must be relocated the existing way, by COWing every leaf. The remap tree can't go in the SYSTEM chunk as space there is limited, because a copy of the chunk item gets placed in the superblock. The changes in fs/btrfs/volumes.h are because we're adding a new block group type bit after the profile bits, and so can no longer rely on the const_ilog2 trick. The sizing to 32MB per chunk, matching the SYSTEM chunk, is an estimate here, we can adjust it later if it proves to be too big or too small. This works out to be ~500,000 remap items, which for a 4KB block size covers ~2GB of remapped data in the worst case and ~500TB in the best case. Reviewed-by: Boris Burkov Signed-off-by: Mark Harmstone Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index f011d34cb699..76578426671c 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -1169,12 +1169,14 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RAID1C3 (1ULL << 9) #define BTRFS_BLOCK_GROUP_RAID1C4 (1ULL << 10) #define BTRFS_BLOCK_GROUP_REMAPPED (1ULL << 11) +#define BTRFS_BLOCK_GROUP_METADATA_REMAP (1ULL << 12) #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) #define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ BTRFS_BLOCK_GROUP_SYSTEM | \ - BTRFS_BLOCK_GROUP_METADATA) + BTRFS_BLOCK_GROUP_METADATA | \ + BTRFS_BLOCK_GROUP_METADATA_REMAP) #define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ BTRFS_BLOCK_GROUP_RAID1 | \ -- cgit v1.2.3 From 7977011460cffc6f5a0cd830584c832c4aa07076 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Wed, 7 Jan 2026 14:09:07 +0000 Subject: btrfs: add extended version of struct block_group_item Add a struct btrfs_block_group_item_v2, which is used in the block group tree if the remap-tree incompat flag is set. This adds two new fields to the block group item: `remap_bytes` and `identity_remap_count`. `remap_bytes` records the amount of data that's physically within this block group, but nominally in another, remapped block group. This is necessary because this data will need to be moved first if this block group is itself relocated. If `remap_bytes` > 0, this is an indicator to the relocation thread that it will need to search the remap-tree for backrefs. A block group must also have `remap_bytes` == 0 before it can be dropped. `identity_remap_count` records how many identity remap items are located in the remap tree for this block group. When relocation is begun for this block group, this is set to the number of holes in the free-space tree for this range. As identity remaps are converted into actual remaps by the relocation process, this number is decreased. Once it reaches 0, either because of relocation or because extents have been deleted, the block group has been fully remapped and its chunk's device extents are removed. Reviewed-by: Boris Burkov Signed-off-by: Mark Harmstone Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 76578426671c..86820a9644e8 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -1229,6 +1229,14 @@ struct btrfs_block_group_item { __le64 flags; } __attribute__ ((__packed__)); +struct btrfs_block_group_item_v2 { + __le64 used; + __le64 chunk_objectid; + __le64 flags; + __le64 remap_bytes; + __le32 identity_remap_count; +} __attribute__ ((__packed__)); + struct btrfs_free_space_info { __le32 extent_count; __le32 flags; -- cgit v1.2.3 From 8620da16fb6be1fd9906374fa1c763a10c6918df Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Wed, 7 Jan 2026 14:09:08 +0000 Subject: btrfs: allow mounting filesystems with remap-tree incompat flag If we encounter a filesystem with the remap-tree incompat flag set, validate its compatibility with the other flags, and load the remap tree using the values that have been added to the superblock. The remap-tree feature depends on the free-space-tree, but no-holes and block-group-tree have been made dependencies to reduce the testing matrix. Similarly I'm not aware of any reason why mixed-bg and zoned would be incompatible with remap-tree, but this is blocked for the time being until it can be fully tested. Reviewed-by: Boris Burkov Signed-off-by: Mark Harmstone Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 86820a9644e8..f7843e6bb978 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -721,9 +721,12 @@ struct btrfs_super_block { __u8 metadata_uuid[BTRFS_FSID_SIZE]; __u64 nr_global_roots; + __le64 remap_root; + __le64 remap_root_generation; + __u8 remap_root_level; /* Future expansion */ - __le64 reserved[27]; + __u8 reserved[199]; __u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; -- cgit v1.2.3 From 4fa4ac5e584841c0f9b01c2f7dd0c2e3caa8bca0 Mon Sep 17 00:00:00 2001 From: Chia-Yu Chang Date: Sat, 31 Jan 2026 23:25:13 +0100 Subject: tcp: accecn: add tcpi_ecn_mode and tcpi_option2 in tcp_info Add 2-bit tcpi_ecn_mode feild within tcp_info to indicate which ECN mode is negotiated: ECN_MODE_DISABLED, ECN_MODE_RFC3168, ECN_MODE_ACCECN, or ECN_MODE_PENDING. This is done by utilizing available bits from tcpi_accecn_opt_seen (reduced from 16 bits to 2 bits) and tcpi_accecn_fail_mode (reduced from 16 bits to 4 bits). Also, an extra 24-bit tcpi_options2 field is identified to represent newer options and connection features, as all 8 bits of tcpi_options field have been used. Signed-off-by: Chia-Yu Chang Co-developed-by: Neal Cardwell Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260131222515.8485-14-chia-yu.chang@nokia-bell-labs.com Signed-off-by: Paolo Abeni --- include/uapi/linux/tcp.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index dce3113787a7..03772dd4d399 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -226,6 +226,24 @@ enum tcp_ca_state { #define TCPF_CA_Loss (1< Date: Wed, 4 Feb 2026 16:02:57 +0100 Subject: KVM: s390: Storage key manipulation IOCTL Add a new IOCTL to allow userspace to manipulate storage keys directly. This will make it easier to write selftests related to storage keys. Acked-by: Heiko Carstens Signed-off-by: Claudio Imbrenda --- include/uapi/linux/kvm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dddb781b0507..ab3d3d96e75f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -974,6 +974,7 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD_FLAGS 244 #define KVM_CAP_ARM_SEA_TO_USER 245 #define KVM_CAP_S390_USER_OPEREXEC 246 +#define KVM_CAP_S390_KEYOP 247 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1219,6 +1220,15 @@ struct kvm_vfio_spapr_tce { __s32 tablefd; }; +#define KVM_S390_KEYOP_ISKE 0x01 +#define KVM_S390_KEYOP_RRBE 0x02 +#define KVM_S390_KEYOP_SSKE 0x03 +struct kvm_s390_keyop { + __u64 guest_addr; + __u8 key; + __u8 operation; +}; + /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. @@ -1238,6 +1248,7 @@ struct kvm_vfio_spapr_tce { #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) +#define KVM_S390_KEYOP _IOWR(KVMIO, 0x53, struct kvm_s390_keyop) /* Device model IOC */ #define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) -- cgit v1.2.3 From f7ab71f178d56447e5efb55b65436feb68662f8f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Feb 2026 10:17:30 +0100 Subject: KVM: s390: Add explicit padding to struct kvm_s390_keyop The newly added structure causes a warning about implied padding: ./usr/include/linux/kvm.h:1247:1: error: padding struct size to alignment boundary with 6 bytes [-Werror=padded] The padding can lead to leaking kernel data and ABI incompatibilies when used on x86. Neither of these is a problem in this specific patch, but it's best to avoid it and use explicit padding fields in general. Fixes: 0ee4ddc1647b ("KVM: s390: Storage key manipulation IOCTL") Signed-off-by: Arnd Bergmann Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ab3d3d96e75f..d4250ab662fe 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1227,6 +1227,7 @@ struct kvm_s390_keyop { __u64 guest_addr; __u8 key; __u8 operation; + __u8 pad[6]; }; /* -- cgit v1.2.3 From ed82f35b926b2e505c14b7006473614b8f58b4f4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 8 Jan 2026 10:18:31 -0700 Subject: io_uring: allow registration of per-task restrictions Currently io_uring supports restricting operations on a per-ring basis. To use those, the ring must be setup in a disabled state by setting IORING_SETUP_R_DISABLED. Then restrictions can be set for the ring, and the ring can then be enabled. This commit adds support for IORING_REGISTER_RESTRICTIONS with ring_fd == -1, like the other "blind" register opcodes which work on the task rather than a specific ring. This allows registration of the same kind of restrictions as can been done on a specific ring, but with the task itself. Once done, any ring created will inherit these restrictions. If a restriction filter is registered with a task, then it's inherited on fork for its children. Children may only further restrict operations, not extend them. Inheriting restrictions include both the classic IORING_REGISTER_RESTRICTIONS based restrictions, as well as the BPF filters that have been registered with the task via IORING_REGISTER_BPF_FILTER. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 94669b77fee8..aeeffcf27fee 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -808,6 +808,13 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_task_restriction { + __u16 flags; + __u16 nr_res; + __u32 resv[3]; + __DECLARE_FLEX_ARRAY(struct io_uring_restriction, restrictions); +}; + struct io_uring_clock_register { __u32 clockid; __u32 __resv[3]; -- cgit v1.2.3 From 42fc7e6543f6d17d2cf9ed3e5021f103a3d11182 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?G=C3=BCnther=20Noack?= Date: Thu, 27 Nov 2025 12:51:34 +0100 Subject: landlock: Multithreading support for landlock_restrict_self() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce the LANDLOCK_RESTRICT_SELF_TSYNC flag. With this flag, a given Landlock ruleset is applied to all threads of the calling process, instead of only the current one. Without this flag, multithreaded userspace programs currently resort to using the nptl(7)/libpsx hack for multithreaded policy enforcement, which is also used by libcap and for setuid(2). Using this userspace-based scheme, the threads of a process enforce the same Landlock policy, but the resulting Landlock domains are still separate. The domains being separate causes multiple problems: * When using Landlock's "scoped" access rights, the domain identity is used to determine whether an operation is permitted. As a result, when using LANLDOCK_SCOPE_SIGNAL, signaling between sibling threads stops working. This is a problem for programming languages and frameworks which are inherently multithreaded (e.g. Go). * In audit logging, the domains of separate threads in a process will get logged with different domain IDs, even when they are based on the same ruleset FD, which might confuse users. Cc: Andrew G. Morgan Cc: John Johansen Cc: Paul Moore Suggested-by: Jann Horn Signed-off-by: Günther Noack Link: https://lore.kernel.org/r/20251127115136.3064948-2-gnoack@google.com [mic: Fix restrict_self_flags test, clean up Makefile, allign comments, reduce local variable scope, add missing includes] Closes: https://github.com/landlock-lsm/linux/issues/2 Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 75fd7f5e6cc3..d5081ab4e5ef 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -117,11 +117,24 @@ struct landlock_ruleset_attr { * future nested domains, not the one being created. It can also be used * with a @ruleset_fd value of -1 to mute subdomain logs without creating a * domain. + * + * The following flag supports policy enforcement in multithreaded processes: + * + * %LANDLOCK_RESTRICT_SELF_TSYNC + * Applies the new Landlock configuration atomically to all threads of the + * current process, including the Landlock domain and logging + * configuration. This overrides the Landlock configuration of sibling + * threads, irrespective of previously established Landlock domains and + * logging configurations on these threads. + * + * If the calling thread is running with no_new_privs, this operation + * enables no_new_privs on the sibling threads as well. */ /* clang-format off */ #define LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF (1U << 0) #define LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON (1U << 1) #define LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF (1U << 2) +#define LANDLOCK_RESTRICT_SELF_TSYNC (1U << 3) /* clang-format on */ /** -- cgit v1.2.3 From bbb6f53e905ca119f99ccab8496f8921d9db9c50 Mon Sep 17 00:00:00 2001 From: Matthieu Buffet Date: Fri, 12 Dec 2025 17:36:57 +0100 Subject: landlock: Minor reword of docs for TCP access rights MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Move ABI requirement next to each access right to prepare adding more access rights; - Mention the possibility to remove the random component of a socket's ephemeral port choice within the netns-wide ephemeral port range, since it allows choosing the "random" ephemeral port. Signed-off-by: Matthieu Buffet Link: https://lore.kernel.org/r/20251212163704.142301-2-matthieu@buffet.re Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index d5081ab4e5ef..f88fa1f68b77 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -195,11 +195,13 @@ struct landlock_net_port_attr { * It should be noted that port 0 passed to :manpage:`bind(2)` will bind * to an available port from the ephemeral port range. This can be * configured with the ``/proc/sys/net/ipv4/ip_local_port_range`` sysctl - * (also used for IPv6). + * (also used for IPv6), and within that range, on a per-socket basis + * with ``setsockopt(IP_LOCAL_PORT_RANGE)``. * - * A Landlock rule with port 0 and the ``LANDLOCK_ACCESS_NET_BIND_TCP`` + * A Landlock rule with port 0 and the %LANDLOCK_ACCESS_NET_BIND_TCP * right means that requesting to bind on port 0 is allowed and it will - * automatically translate to binding on the related port range. + * automatically translate to binding on a kernel-assigned ephemeral + * port. */ __u64 port; }; @@ -342,13 +344,12 @@ struct landlock_net_port_attr { * These flags enable to restrict a sandboxed process to a set of network * actions. * - * This is supported since Landlock ABI version 4. - * * The following access rights apply to TCP port numbers: * - * - %LANDLOCK_ACCESS_NET_BIND_TCP: Bind a TCP socket to a local port. - * - %LANDLOCK_ACCESS_NET_CONNECT_TCP: Connect an active TCP socket to - * a remote port. + * - %LANDLOCK_ACCESS_NET_BIND_TCP: Bind TCP sockets to the given local + * port. Support added in Landlock ABI version 4. + * - %LANDLOCK_ACCESS_NET_CONNECT_TCP: Connect TCP sockets to the given + * remote port. Support added in Landlock ABI version 4. */ /* clang-format off */ #define LANDLOCK_ACCESS_NET_BIND_TCP (1ULL << 0) -- cgit v1.2.3 From 136f1e168f4941021565f8c10ff4bb81b1f13f2c Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Thu, 5 Feb 2026 18:34:23 +0100 Subject: mptcp: fix kdoc warnings The following warnings were visible: $ ./scripts/kernel-doc -Wall -none \ net/mptcp/ include/net/mptcp.h include/uapi/linux/mptcp*.h \ include/trace/events/mptcp.h Warning: net/mptcp/token.c:108 No description found for return value of 'mptcp_token_new_request' Warning: net/mptcp/token.c:151 No description found for return value of 'mptcp_token_new_connect' Warning: net/mptcp/token.c:246 No description found for return value of 'mptcp_token_get_sock' Warning: net/mptcp/token.c:298 No description found for return value of 'mptcp_token_iter_next' Warning: net/mptcp/protocol.c:4431 No description found for return value of 'mptcp_splice_read' Warning: include/uapi/linux/mptcp_pm.h:13 missing initial short description on line: * enum mptcp_event_type Address all of them: either by using the 'Return:' keyword, or by adding a missing initial short description. The MPTCP CI will soon report issues with kdoc to avoid introducing new issues and being flagged by the Netdev CI. Reviewed-by: Geliang Tang Reviewed-by: Randy Dunlap Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260205-net-mptcp-misc-fixes-6-19-rc8-v2-3-c2720ce75c34@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp_pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index c97d060ee90b..fe9863d75350 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -11,7 +11,7 @@ #define MPTCP_PM_VER 1 /** - * enum mptcp_event_type + * enum mptcp_event_type - Netlink MPTCP event types * @MPTCP_EVENT_UNSPEC: unused event * @MPTCP_EVENT_CREATED: A new MPTCP connection has been created. It is the * good time to allocate memory and send ADD_ADDR if needed. Depending on the -- cgit v1.2.3 From 90079798f1d748e97c74e23736491543577b8aee Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Feb 2026 10:59:00 +0100 Subject: delayacct: fix uapi timespec64 definition The custom definition of 'struct timespec64' is incompatible with both the kernel's internal definition and the glibc type, at least on big-endian targets that have the tv_nsec field in a different place, and the definition clashes with any userspace that also defines a timespec64 structure. Running the header check with -Wpadding enabled produces this output that warns about the incorrect padding: usr/include/linux/taskstats.h:25:1: error: padding struct size to alignment boundary with 4 bytes [-Werror=padded] Remove the hack and instead use the regular __kernel_timespec type that is meant to be used in uapi definitions. Link: https://lkml.kernel.org/r/20260202095906.1344100-1-arnd@kernel.org Fixes: 29b63f6eff0e ("delayacct: add timestamp of delay max") Signed-off-by: Arnd Bergmann Cc: Fan Yu Cc: Jonathan Corbet Cc: xu xin Cc: Yang Yang Cc: Balbir Singh Cc: Jiang Kun Signed-off-by: Andrew Morton --- include/uapi/linux/taskstats.h | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 1b31e8e14d2f..3ae25f3ce067 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -18,16 +18,7 @@ #define _LINUX_TASKSTATS_H #include -#ifdef __KERNEL__ -#include -#else -#ifndef _LINUX_TIME64_H -struct timespec64 { - __s64 tv_sec; /* seconds */ - long tv_nsec; /* nanoseconds */ -}; -#endif -#endif +#include /* Format for per-task data returned to userland when * - a task exits @@ -242,14 +233,14 @@ struct taskstats { __u64 irq_delay_min; /*v17: delay max timestamp record*/ - struct timespec64 cpu_delay_max_ts; - struct timespec64 blkio_delay_max_ts; - struct timespec64 swapin_delay_max_ts; - struct timespec64 freepages_delay_max_ts; - struct timespec64 thrashing_delay_max_ts; - struct timespec64 compact_delay_max_ts; - struct timespec64 wpcopy_delay_max_ts; - struct timespec64 irq_delay_max_ts; + struct __kernel_timespec cpu_delay_max_ts; + struct __kernel_timespec blkio_delay_max_ts; + struct __kernel_timespec swapin_delay_max_ts; + struct __kernel_timespec freepages_delay_max_ts; + struct __kernel_timespec thrashing_delay_max_ts; + struct __kernel_timespec compact_delay_max_ts; + struct __kernel_timespec wpcopy_delay_max_ts; + struct __kernel_timespec irq_delay_max_ts; }; -- cgit v1.2.3 From ebcff9dacaf2c1418f8bc927388186d7d3674603 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Feb 2026 23:48:07 +0100 Subject: vduse: avoid adding implicit padding The vduse_iova_range_v2 and vduse_iotlb_entry_v2 structures are both defined in a way that adds implicit padding and is incompatible between i386 and x86_64 userspace because of the different structure alignment requirements. Building the header with -Wpadded shows these new warnings: vduse.h:305:1: error: padding struct size to alignment boundary with 4 bytes [-Werror=padded] vduse.h:374:1: error: padding struct size to alignment boundary with 4 bytes [-Werror=padded] Change the amount of padding in these two structures to align them to 64 bit words and avoid those problems. Since the v1 vduse_iotlb_entry already has an inconsistent size, do not attempt to reuse the structure but rather list the members indiviudally, with a fixed amount of padding. Fixes: 079212f6877e ("vduse: add vq group asid support") Signed-off-by: Arnd Bergmann Signed-off-by: Michael S. Tsirkin Message-Id: <20260202224835.559538-1-arnd@kernel.org> --- include/uapi/linux/vduse.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h index 68b4287f9fac..361eea511c21 100644 --- a/include/uapi/linux/vduse.h +++ b/include/uapi/linux/vduse.h @@ -293,9 +293,13 @@ struct vduse_iova_info { * Structure used by VDUSE_IOTLB_GET_FD2 ioctl to find an overlapped IOVA region. */ struct vduse_iotlb_entry_v2 { - struct vduse_iotlb_entry v1; + __u64 offset; + __u64 start; + __u64 last; + __u8 perm; + __u8 padding[7]; __u32 asid; - __u32 reserved[12]; + __u32 reserved[11]; }; /* @@ -365,6 +369,7 @@ struct vduse_iova_range_v2 { __u64 start; __u64 last; __u32 asid; + __u32 padding; }; /** -- cgit v1.2.3 From c29214677a9fc1a3a4ee65e189afeb5fd10d676f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 15 Feb 2026 21:34:28 +0000 Subject: io_uring/query: return support for custom rx page size Add an ability to query if the zcrx rx page size setting is available. Note, even when the API is supported by io_uring, the registration can still get rejected for various reasons, e.g. when the NIC or the driver doesn't support it, when the particular specified size is unsupported, when the memory area doesn't satisfy all requirements, etc. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ include/uapi/linux/io_uring/query.h | 3 ++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index da5156954731..c462bdf3c42c 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -1090,6 +1090,14 @@ enum zcrx_reg_flags { ZCRX_REG_IMPORT = 1, }; +enum zcrx_features { + /* + * The user can ask for the desired rx page size by passing the + * value in struct io_uring_zcrx_ifq_reg::rx_buf_len. + */ + ZCRX_FEATURE_RX_PAGE_SIZE = 1 << 0, +}; + /* * Argument for IORING_REGISTER_ZCRX_IFQ */ diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 2456e6c5ebb5..0b6248175e26 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -50,7 +50,8 @@ struct io_uring_query_zcrx { __u64 area_flags; /* The number of supported ZCRX_CTRL_* opcodes */ __u32 nr_ctrl_opcodes; - __u32 __resv1; + /* Bitmask of ZCRX_FEATURE_* indicating which features are available */ + __u32 features; /* The refill ring header size */ __u32 rq_hdr_size; /* The alignment for the header */ -- cgit v1.2.3 From 6b34f8edf8b807b7f87901623aa52dfa1b29ef93 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 15 Feb 2026 21:38:09 +0000 Subject: io_uring/query: add query.h copyright notice Add a copyright notice to io_uring's query uapi header. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/query.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 0b6248175e26..95500759cc13 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -1,6 +1,9 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ /* * Header file for the io_uring query interface. + * + * Copyright (C) 2026 Pavel Begunkov + * Copyright (C) Meta Platforms, Inc. */ #ifndef LINUX_IO_URING_QUERY_H #define LINUX_IO_URING_QUERY_H -- cgit v1.2.3 From be3573124e630736d2d39650b12f5ef220b47ac1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 10 Feb 2026 10:00:44 -0700 Subject: io_uring/bpf_filter: pass in expected filter payload size It's quite possible that opcodes that have payloads attached to them, like IORING_OP_OPENAT/OPENAT2 or IORING_OP_SOCKET, that these paylods can change over time. For example, on the openat/openat2 side, the struct open_how argument is extensible, and could be extended in the future to allow further arguments to be passed in. Allow registration of a cBPF filter to give the size of the filter as seen by userspace. If that filter is for an opcode that takes extra payload data, allow it if the application payload expectation is the same size than the kernels. If that is the case, the kernel supports filtering on the payload that the application expects. If the size differs, the behavior depends on the IO_URING_BPF_FILTER_SZ_STRICT flag: 1) If IO_URING_BPF_FILTER_SZ_STRICT is set and the size expectation differs, fail the attempt to load the filter. 2) If IO_URING_BPF_FILTER_SZ_STRICT isn't set, allow the filter if the userspace pdu size is smaller than what the kernel offers. 3) Regardless if IO_URING_BPF_FILTER_SZ_STRICT, fail loading the filter if the userspace pdu size is bigger than what the kernel supports. An attempt to load a filter due to sizing will error with -EMSGSIZE. For that error, the registration struct will have filter->pdu_size populated with the pdu size that the kernel uses. Reported-by: Christian Brauner Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring/bpf_filter.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring/bpf_filter.h b/include/uapi/linux/io_uring/bpf_filter.h index 220351b81bc0..1b461d792a7b 100644 --- a/include/uapi/linux/io_uring/bpf_filter.h +++ b/include/uapi/linux/io_uring/bpf_filter.h @@ -35,13 +35,19 @@ enum { * If set, any currently unset opcode will have a deny filter attached */ IO_URING_BPF_FILTER_DENY_REST = 1, + /* + * If set, if kernel and application don't agree on pdu_size for + * the given opcode, fail the registration of the filter. + */ + IO_URING_BPF_FILTER_SZ_STRICT = 2, }; struct io_uring_bpf_filter { __u32 opcode; /* io_uring opcode to filter */ __u32 flags; __u32 filter_len; /* number of BPF instructions */ - __u32 resv; + __u8 pdu_size; /* expected pdu size for opcode */ + __u8 resv[3]; __u64 filter_ptr; /* pointer to BPF filter */ __u64 resv2[5]; }; -- cgit v1.2.3 From 4edd4ba71ce0df015303dba75ea9d20d1a217546 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Sat, 14 Feb 2026 15:54:06 +0100 Subject: include: uapi: netfilter_bridge.h: Cover for musl libc Musl defines its own struct ethhdr and thus defines __UAPI_DEF_ETHHDR to zero. To avoid struct redefinition errors, user space is therefore supposed to include netinet/if_ether.h before (or instead of) linux/if_ether.h. To relieve them from this burden, include the libc header here if not building for kernel space. Reported-by: Alyssa Ross Suggested-by: Florian Westphal Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter_bridge.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index f6e8d1e05c97..758de72b2764 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -5,6 +5,10 @@ /* bridge-specific defines for netfilter. */ +#ifndef __KERNEL__ +#include /* for __UAPI_DEF_ETHHDR if defined */ +#endif + #include #include #include -- cgit v1.2.3 From a284dbc96a47891a7a595a1c81b1e2da4d309cf6 Mon Sep 17 00:00:00 2001 From: Muminul Islam Date: Wed, 18 Feb 2026 14:47:59 +0000 Subject: mshv: Add nested virtualization creation flag Introduce HV_PARTITION_CREATION_FLAG_NESTED_VIRTUALIZATION_CAPABLE to indicate support for nested virtualization during partition creation. This enables clearer configuration and capability checks for nested virtualization scenarios. Signed-off-by: Stanislav Kinsburskii Signed-off-by: Muminul Islam Signed-off-by: Wei Liu --- include/uapi/linux/mshv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mshv.h b/include/uapi/linux/mshv.h index dee3ece28ce5..7ef5dd67a232 100644 --- a/include/uapi/linux/mshv.h +++ b/include/uapi/linux/mshv.h @@ -27,6 +27,7 @@ enum { MSHV_PT_BIT_X2APIC, MSHV_PT_BIT_GPA_SUPER_PAGES, MSHV_PT_BIT_CPU_AND_XSAVE_FEATURES, + MSHV_PT_BIT_NESTED_VIRTUALIZATION, MSHV_PT_BIT_COUNT, }; -- cgit v1.2.3 From 8927a108a7662eb83eb667bc0c5a0633397122b1 Mon Sep 17 00:00:00 2001 From: Anatol Belski Date: Wed, 18 Feb 2026 14:48:02 +0000 Subject: mshv: Add SMT_ENABLED_GUEST partition creation flag Add support for HV_PARTITION_CREATION_FLAG_SMT_ENABLED_GUEST to allow userspace VMMs to enable SMT for guest partitions. Expose this via new MSHV_PT_BIT_SMT_ENABLED_GUEST flag in the UAPI. Without this flag, the hypervisor schedules guest VPs incorrectly, causing SMT unusable. Signed-off-by: Anatol Belski Signed-off-by: Wei Liu --- include/uapi/linux/mshv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mshv.h b/include/uapi/linux/mshv.h index 7ef5dd67a232..e0645a34b55b 100644 --- a/include/uapi/linux/mshv.h +++ b/include/uapi/linux/mshv.h @@ -28,6 +28,7 @@ enum { MSHV_PT_BIT_GPA_SUPER_PAGES, MSHV_PT_BIT_CPU_AND_XSAVE_FEATURES, MSHV_PT_BIT_NESTED_VIRTUALIZATION, + MSHV_PT_BIT_SMT_ENABLED_GUEST, MSHV_PT_BIT_COUNT, }; -- cgit v1.2.3 From 3b68df978133ac3d46d570af065a73debbb68248 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 20 Feb 2026 15:06:41 -0500 Subject: rseq: slice ext: Ensure rseq feature size differs from original rseq size Before rseq became extensible, its original size was 32 bytes even though the active rseq area was only 20 bytes. This had the following impact in terms of userspace ecosystem evolution: * The GNU libc between 2.35 and 2.39 expose a __rseq_size symbol set to 32, even though the size of the active rseq area is really 20. * The GNU libc 2.40 changes this __rseq_size to 20, thus making it express the active rseq area. * Starting from glibc 2.41, __rseq_size corresponds to the AT_RSEQ_FEATURE_SIZE from getauxval(3). This means that users of __rseq_size can always expect it to correspond to the active rseq area, except for the value 32, for which the active rseq area is 20 bytes. Exposing a 32 bytes feature size would make life needlessly painful for userspace. Therefore, add a reserved field at the end of the rseq area to bump the feature size to 33 bytes. This reserved field is expected to be replaced with whatever field will come next, expecting that this field will be larger than 1 byte. The effect of this change is to increase the size from 32 to 64 bytes before we actually have fields using that memory. Clarify the allocation size and alignment requirements in the struct rseq uapi comment. Change the value returned by getauxval(AT_RSEQ_ALIGN) to return the value of the active rseq area size rounded up to next power of 2, which guarantees that the rseq structure will always be aligned on the nearest power of two large enough to contain it, even as it grows. Change the alignment check in the rseq registration accordingly. This will minimize the amount of ABI corner-cases we need to document and require userspace to play games with. The rule stays simple when __rseq_size != 32: #define rseq_field_available(field) (__rseq_size >= offsetofend(struct rseq_abi, field)) Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260220200642.1317826-3-mathieu.desnoyers@efficios.com --- include/uapi/linux/rseq.h | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 863c4a00a66b..f69344fe6c08 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -87,10 +87,17 @@ struct rseq_slice_ctrl { }; /* - * struct rseq is aligned on 4 * 8 bytes to ensure it is always - * contained within a single cache-line. + * The original size and alignment of the allocation for struct rseq is + * 32 bytes. * - * A single struct rseq per thread is allowed. + * The allocation size needs to be greater or equal to + * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to + * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32). + * + * As an alternative, userspace is allowed to use both the original size + * and alignment of 32 bytes for backward compatibility. + * + * A single active struct rseq registration per thread is allowed. */ struct rseq { /* @@ -180,10 +187,21 @@ struct rseq { */ struct rseq_slice_ctrl slice_ctrl; + /* + * Before rseq became extensible, its original size was 32 bytes even + * though the active rseq area was only 20 bytes. + * Exposing a 32 bytes feature size would make life needlessly painful + * for userspace. Therefore, add a reserved byte after byte 32 + * to bump the rseq feature size from 32 to 33. + * The next field to be added to the rseq area will be larger + * than one byte, and will replace this reserved byte. + */ + __u8 __reserved; + /* * Flexible array member at end of structure, after last feature field. */ char end[]; -} __attribute__((aligned(4 * sizeof(__u64)))); +} __attribute__((aligned(32))); #endif /* _UAPI_LINUX_RSEQ_H */ -- cgit v1.2.3 From 39195990e4c093c9eecf88f29811c6de29265214 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 27 Feb 2026 06:10:08 -0600 Subject: PCI: Correct PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fb82437fdd8c ("PCI: Change capability register offsets to hex") incorrectly converted the PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 value from decimal 52 to hex 0x32: -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32 /* end of v2 EPs w/ link */ This broke PCI capabilities in a VMM because subsequent ones weren't DWORD-aligned. Change PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 to the correct value of 0x34. fb82437fdd8c was from Baruch Siach , but this was not Baruch's fault; it's a mistake I made when applying the patch. Fixes: fb82437fdd8c ("PCI: Change capability register offsets to hex") Reported-by: David Woodhouse Closes: https://lore.kernel.org/all/3ae392a0158e9d9ab09a1d42150429dd8ca42791.camel@infradead.org Signed-off-by: Bjorn Helgaas Reviewed-by: Krzysztof Wilczyński --- include/uapi/linux/pci_regs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ec1c54b5a310..14f634ab9350 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -712,7 +712,7 @@ #define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ #define PCI_EXP_LNKSTA2 0x32 /* Link Status 2 */ #define PCI_EXP_LNKSTA2_FLIT 0x0400 /* Flit Mode Status */ -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32 /* end of v2 EPs w/ link */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x34 /* end of v2 EPs w/ link */ #define PCI_EXP_SLTCAP2 0x34 /* Slot Capabilities 2 */ #define PCI_EXP_SLTCAP2_IBPD 0x00000001 /* In-band PD Disable Supported */ #define PCI_EXP_SLTCTL2 0x38 /* Slot Control 2 */ -- cgit v1.2.3 From 0ed2e8bf61d6d5df1d78f4e24b682dff4c394e17 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 28 Feb 2026 04:56:20 -0700 Subject: io_uring: correct comment for IORING_SETUP_TASKRUN_FLAG Sync with a recent liburing fix, which corrects the comment explaining when the IORING_SETUP_TASKRUN_FLAG setup flag is valid to use. May be use with COOP_TASKRUN or DEFER_TASKRUN, not useful without either of this task_work mechanisms being used. Link: https://github.com/axboe/liburing/pull/1543 Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6750c383a2ab..1ff16141c8a5 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -188,7 +188,8 @@ enum io_uring_sqe_flags_bit { /* * If COOP_TASKRUN is set, get notified if task work is available for * running and a kernel transition would be needed to run it. This sets - * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + * IORING_SQ_TASKRUN in the sq ring flags. Not valid without COOP_TASKRUN + * or DEFER_TASKRUN. */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ -- cgit v1.2.3 From a116bac87118903925108e57781bbfc7a7eea27b Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Mon, 2 Mar 2026 16:23:09 -0800 Subject: dma-buf: Include ioctl.h in UAPI header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include/uapi/linux/dma-buf.h uses several macros from ioctl.h to define its ioctl commands. However, it does not include ioctl.h itself. So, if userspace source code tries to include the dma-buf.h file without including ioctl.h, it can result in build failures. Therefore, include ioctl.h in the dma-buf UAPI header. Signed-off-by: Isaac J. Manjarres Reviewed-by: T.J. Mercier Reviewed-by: Christian König Signed-off-by: Christian König Link: https://lore.kernel.org/r/20260303002309.1401849-1-isaacmanjarres@google.com --- include/uapi/linux/dma-buf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 5a6fda66d9ad..e827c9d20c5d 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -20,6 +20,7 @@ #ifndef _DMA_BUF_UAPI_H_ #define _DMA_BUF_UAPI_H_ +#include #include /** -- cgit v1.2.3