From e17d43b93e544f5016c0251d2074c15568d5d963 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 12 May 2020 15:19:08 +0300 Subject: perf: Add perf text poke event Record (single instruction) changes to the kernel text (i.e. self-modifying code) in order to support tracers like Intel PT and ARM CoreSight. A copy of the running kernel code is needed as a reference point (e.g. from /proc/kcore). The text poke event records the old bytes and the new bytes so that the event can be processed forwards or backwards. The basic problem is recording the modified instruction in an unambiguous manner given SMP instruction cache (in)coherence. That is, when modifying an instruction concurrently any solution with one or multiple timestamps is not sufficient: CPU0 CPU1 0 1 write insn A 2 execute insn A 3 sync-I$ 4 Due to I$, CPU1 might execute either the old or new A. No matter where we record tracepoints on CPU0, one simply cannot tell what CPU1 will have observed, except that at 0 it must be the old one and at 4 it must be the new one. To solve this, take inspiration from x86 text poking, which has to solve this exact problem due to variable length instruction encoding and I-fetch windows. 1) overwrite the instruction with a breakpoint and sync I$ This guarantees that that code flow will never hit the target instruction anymore, on any CPU (or rather, it will cause an exception). 2) issue the TEXT_POKE event 3) overwrite the breakpoint with the new instruction and sync I$ Now we know that any execution after the TEXT_POKE event will either observe the breakpoint (and hit the exception) or the new instruction. So by guarding the TEXT_POKE event with an exception on either side; we can now tell, without doubt, which instruction another CPU will have observed. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200512121922.8997-2-adrian.hunter@intel.com --- include/uapi/linux/perf_event.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..e5bee6c17b86 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -383,7 +383,8 @@ struct perf_event_attr { bpf_event : 1, /* include bpf events */ aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ - __reserved_1 : 31; + text_poke : 1, /* include text poke events */ + __reserved_1 : 30; union { __u32 wakeup_events; /* wakeup every n events */ @@ -1024,6 +1025,24 @@ enum perf_event_type { */ PERF_RECORD_CGROUP = 19, + /* + * Records changes to kernel text i.e. self-modified code. 'old_len' is + * the number of old bytes, 'new_len' is the number of new bytes. Either + * 'old_len' or 'new_len' may be zero to indicate, for example, the + * addition or removal of a trampoline. 'bytes' contains the old bytes + * followed immediately by the new bytes. + * + * struct { + * struct perf_event_header header; + * u64 addr; + * u16 old_len; + * u16 new_len; + * u8 bytes[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_TEXT_POKE = 20, + PERF_RECORD_MAX, /* non-ABI */ }; -- cgit v1.2.3 From 69e49088692899d25dedfa22f00dfb9761e86ed7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 12 May 2020 15:19:11 +0300 Subject: kprobes: Add perf ksymbol events for kprobe insn pages Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via perf ksymbol events. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200512121922.8997-5-adrian.hunter@intel.com --- include/uapi/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e5bee6c17b86..e1a4179144a1 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1049,6 +1049,11 @@ enum perf_event_type { enum perf_record_ksymbol_type { PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0, PERF_RECORD_KSYMBOL_TYPE_BPF = 1, + /* + * Out of line code such as kprobe-replaced instructions or optimized + * kprobes. + */ + PERF_RECORD_KSYMBOL_TYPE_OOL = 2, PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */ }; -- cgit v1.2.3 From dd9ddf466ad7a5d2e247925d81ebb0b878bf3b76 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 12 May 2020 15:19:14 +0300 Subject: ftrace: Add perf ksymbol events for ftrace trampolines Symbols are needed for tools to describe instruction addresses. Pages allocated for ftrace's purposes need symbols to be created for them. Add such symbols to be visible via perf ksymbol events. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20200512121922.8997-8-adrian.hunter@intel.com --- include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e1a4179144a1..52ca2093831c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1051,7 +1051,7 @@ enum perf_record_ksymbol_type { PERF_RECORD_KSYMBOL_TYPE_BPF = 1, /* * Out of line code such as kprobe-replaced instructions or optimized - * kprobes. + * kprobes or ftrace trampolines. */ PERF_RECORD_KSYMBOL_TYPE_OOL = 2, PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */ -- cgit v1.2.3 From 9b4feb630e8e9801603f3cab3a36369e3c1cf88d Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 24 May 2019 11:31:44 +0200 Subject: arch: wire-up close_range() This wires up the close_range() syscall into all arches at once. Suggested-by: Arnd Bergmann Signed-off-by: Christian Brauner Reviewed-by: Oleg Nesterov Acked-by: Arnd Bergmann Acked-by: Michael Ellerman (powerpc) Cc: Jann Horn Cc: David Howells Cc: Dmitry V. Levin Cc: Linus Torvalds Cc: Al Viro Cc: Florian Weimer Cc: linux-api@vger.kernel.org Cc: linux-alpha@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-ia64@vger.kernel.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-mips@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Cc: x86@kernel.org --- include/uapi/asm-generic/unistd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index f4a01305d9a6..31001e3323bc 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -850,6 +850,8 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open) #define __NR_clone3 435 __SYSCALL(__NR_clone3, sys_clone3) #endif +#define __NR_close_range 436 +__SYSCALL(__NR_close_range, sys_close_range) #define __NR_openat2 437 __SYSCALL(__NR_openat2, sys_openat2) -- cgit v1.2.3 From 60997c3d45d9a67daf01c56d805ae4fec37e0bd8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 3 Jun 2020 21:48:55 +0200 Subject: close_range: add CLOSE_RANGE_UNSHARE One of the use-cases of close_range() is to drop file descriptors just before execve(). This would usually be expressed in the sequence: unshare(CLONE_FILES); close_range(3, ~0U); as pointed out by Linus it might be desirable to have this be a part of close_range() itself under a new flag CLOSE_RANGE_UNSHARE. This expands {dup,unshare)_fd() to take a max_fds argument that indicates the maximum number of file descriptors to copy from the old struct files. When the user requests that all file descriptors are supposed to be closed via close_range(min, max) then we can cap via unshare_fd(min) and hence don't need to do any of the heavy fput() work for everything above min. The patch makes it so that if CLOSE_RANGE_UNSHARE is requested and we do in fact currently share our file descriptor table we create a new private copy. We then close all fds in the requested range and finally after we're done we install the new fd table. Suggested-by: Linus Torvalds Signed-off-by: Christian Brauner --- include/uapi/linux/close_range.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/uapi/linux/close_range.h (limited to 'include/uapi') diff --git a/include/uapi/linux/close_range.h b/include/uapi/linux/close_range.h new file mode 100644 index 000000000000..6928a9fdee3c --- /dev/null +++ b/include/uapi/linux/close_range.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_CLOSE_RANGE_H +#define _UAPI_LINUX_CLOSE_RANGE_H + +/* Unshare the file descriptor table before closing file descriptors. */ +#define CLOSE_RANGE_UNSHARE (1U << 1) + +#endif /* _UAPI_LINUX_CLOSE_RANGE_H */ + -- cgit v1.2.3 From 03cc8353c2244c8b790c3c81a0f1532d34a9d738 Mon Sep 17 00:00:00 2001 From: Rob Gill Date: Mon, 1 Jun 2020 21:17:56 +0000 Subject: USB: core: additional Device Classes to debug/usb/devices Several newer USB Device classes are not presently reported individually at /sys/kernel/debug/usb/devices, (reported as "unk."). This patch adds the following classes: 0fh (Personal Healthcare devices), 10h (USB Type-C combined Audio/Video devices) 11h (USB billboard), 12h (USB Type-C Bridge). As defined at [https://www.usb.org/defined-class-codes] Corresponding classes defined in include/linux/usb/ch9.h. Signed-off-by: Rob Gill Link: https://lore.kernel.org/r/20200601211749.6878-1-rrobgill@protonmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 2b623f36af6b..456ab0c2b586 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -326,6 +326,10 @@ struct usb_device_descriptor { #define USB_CLASS_CONTENT_SEC 0x0d /* content security */ #define USB_CLASS_VIDEO 0x0e #define USB_CLASS_WIRELESS_CONTROLLER 0xe0 +#define USB_CLASS_PERSONAL_HEALTHCARE 0x0f +#define USB_CLASS_AUDIO_VIDEO 0x10 +#define USB_CLASS_BILLBOARD 0x11 +#define USB_CLASS_USB_TYPE_C_BRIDGE 0x12 #define USB_CLASS_MISC 0xef #define USB_CLASS_APP_SPEC 0xfe #define USB_CLASS_VENDOR_SPEC 0xff -- cgit v1.2.3 From 81c7462883b0cc0a4eeef0687f80ad5b5baee5f6 Mon Sep 17 00:00:00 2001 From: Macpaul Lin Date: Thu, 18 Jun 2020 17:13:38 +0800 Subject: USB: replace hardcode maximum usb string length by definition Replace hardcoded maximum USB string length (126 bytes) by definition "USB_MAX_STRING_LEN". Signed-off-by: Macpaul Lin Acked-by: Alan Stern Link: https://lore.kernel.org/r/1592471618-29428-1-git-send-email-macpaul.lin@mediatek.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 456ab0c2b586..b1ed2ccfe9cf 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -368,6 +368,9 @@ struct usb_config_descriptor { /*-------------------------------------------------------------------------*/ +/* USB String descriptors can contain at most 126 characters. */ +#define USB_MAX_STRING_LEN 126 + /* USB_DT_STRING: String descriptor */ struct usb_string_descriptor { __u8 bLength; -- cgit v1.2.3 From 5769a351b89cd4d82016f18fa5f6c4077403564d Mon Sep 17 00:00:00 2001 From: Jiufei Xue Date: Wed, 17 Jun 2020 17:53:55 +0800 Subject: io_uring: change the poll type to be 32-bits poll events should be 32-bits to cover EPOLLEXCLUSIVE. Explicit word-swap the poll32_events for big endian to make sure the ABI is not changed. We call this feature IORING_FEAT_POLL_32BITS, applications who want to use EPOLLEXCLUSIVE should check the feature bit first. Signed-off-by: Jiufei Xue Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 92c22699a5a7..8d033961cb78 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -31,7 +31,8 @@ struct io_uring_sqe { union { __kernel_rwf_t rw_flags; __u32 fsync_flags; - __u16 poll_events; + __u16 poll_events; /* compatibility */ + __u32 poll32_events; /* word-reversed for BE */ __u32 sync_range_flags; __u32 msg_flags; __u32 timeout_flags; @@ -248,6 +249,7 @@ struct io_uring_params { #define IORING_FEAT_RW_CUR_POS (1U << 3) #define IORING_FEAT_CUR_PERSONALITY (1U << 4) #define IORING_FEAT_FAST_POLL (1U << 5) +#define IORING_FEAT_POLL_32BITS (1U << 6) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3 From 2a916ecc405686c1d86f632281bc06aa75ebae4e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 19 Jun 2020 03:32:48 +0000 Subject: net/devlink: Support querying hardware address of port function PCI PF and VF devlink port can manage the function represented by a devlink port. Enable users to query port function's hardware address. Example of a PCI VF port which supports a port function: $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:11:22:33:44:66 $ devlink port show pci/0000:06:00.0/2 -jp { "port": { "pci/0000:06:00.0/2": { "type": "eth", "netdev": "enp6s0pf0vf1", "flavour": "pcivf", "pfnum": 0, "vfnum": 1, "function": { "hw_addr": "00:11:22:33:44:66" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 08563e6a424d..07d0af8f5923 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -451,6 +451,8 @@ enum devlink_attr { DEVLINK_ATTR_TRAP_POLICER_RATE, /* u64 */ DEVLINK_ATTR_TRAP_POLICER_BURST, /* u64 */ + DEVLINK_ATTR_PORT_FUNCTION, /* nested */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, @@ -497,4 +499,12 @@ enum devlink_resource_unit { DEVLINK_RESOURCE_UNIT_ENTRY, }; +enum devlink_port_function_attr { + DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, + DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ + + __DEVLINK_PORT_FUNCTION_ATTR_MAX, + DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ -- cgit v1.2.3 From b5872cd0e823e4cb50b3a75cd9522167eeb676a2 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Sat, 20 Jun 2020 22:01:56 +0530 Subject: devlink: Add support for board.serial_number to info_get cb. Board serial number is a serial number, often available in PCI *Vital Product Data*. Also, update devlink-info.rst documentation file. Cc: Jiri Pirko Cc: Jakub Kicinski Signed-off-by: Vasundhara Volam Reviewed-by: Michael Chan Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 07d0af8f5923..87c83a82991b 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -453,6 +453,8 @@ enum devlink_attr { DEVLINK_ATTR_PORT_FUNCTION, /* nested */ + DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, /* string */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From 23a60f834406c8e3805328b630d09d5546b460c1 Mon Sep 17 00:00:00 2001 From: Collin Walling Date: Mon, 22 Jun 2020 11:46:36 -0400 Subject: s390/kvm: diagnose 0x318 sync and reset DIAGNOSE 0x318 (diag318) sets information regarding the environment the VM is running in (Linux, z/VM, etc) and is observed via firmware/service events. This is a privileged s390x instruction that must be intercepted by SIE. Userspace handles the instruction as well as migration. Data is communicated via VCPU register synchronization. The Control Program Name Code (CPNC) is stored in the SIE block. The CPNC along with the Control Program Version Code (CPVC) are stored in the kvm_vcpu_arch struct. This data is reset on load normal and clear resets. Signed-off-by: Collin Walling Reviewed-by: Janosch Frank Acked-by: Cornelia Huck Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/r/20200622154636.5499-3-walling@linux.ibm.com [borntraeger@de.ibm.com: fix sync_reg position] Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4fdf30316582..35cdb4307904 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1031,6 +1031,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_SECURE_GUEST 181 #define KVM_CAP_HALT_POLL 182 #define KVM_CAP_ASYNC_PF_INT 183 +#define KVM_CAP_S390_DIAG318 184 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From ac53503ee38a1ffbc47c7cca6cbfc48ba9c65c5e Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 14 May 2020 18:01:43 +0200 Subject: media: videobuf2: add V4L2_FLAG_MEMORY_NON_CONSISTENT flag By setting or clearing V4L2_FLAG_MEMORY_NON_CONSISTENT flag user-space should be able to set or clear queue's NON_CONSISTENT ->dma_attrs. Queue's ->dma_attrs are passed to the underlying allocator in __vb2_buf_mem_alloc(), so thus user-space is able to request vb2 buffer's memory to be either consistent (coherent) or non-consistent. The patch set also adds a corresponding capability flag: fill_buf_caps() reports V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS when queue supports user-space cache management hints. Note, however, that MMAP_CACHE_HINTS capability only valid when the queue is used for memory MMAP-ed streaming I/O. Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c3a1cf1c507f..34ba1017b89b 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -189,6 +189,8 @@ enum v4l2_memory { V4L2_MEMORY_DMABUF = 4, }; +#define V4L2_FLAG_MEMORY_NON_CONSISTENT (1 << 0) + /* see also http://vektor.theorem.ca/graphics/ycbcr/ */ enum v4l2_colorspace { /* @@ -954,6 +956,7 @@ struct v4l2_requestbuffers { #define V4L2_BUF_CAP_SUPPORTS_REQUESTS (1 << 3) #define V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS (1 << 4) #define V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF (1 << 5) +#define V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS (1 << 6) /** * struct v4l2_plane - plane info for multi-planar buffers -- cgit v1.2.3 From 1e0b2318fa75d186ee0d2be31843ce867385fcc4 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 14 May 2020 18:01:45 +0200 Subject: media: videobuf2: handle V4L2_FLAG_MEMORY_NON_CONSISTENT flag This patch lets user-space to request a non-consistent memory allocation during CREATE_BUFS and REQBUFS ioctl calls. = CREATE_BUFS struct v4l2_create_buffers has seven 4-byte reserved areas, so reserved[0] is renamed to ->flags. The struct, thus, now has six reserved 4-byte regions. = CREATE_BUFS32 struct v4l2_create_buffers32 has seven 4-byte reserved areas, so reserved[0] is renamed to ->flags. The struct, thus, now has six reserved 4-byte regions. = REQBUFS We use one bit of a ->reserved[1] member of struct v4l2_requestbuffers, which is now renamed to ->flags. Unlike v4l2_create_buffers, struct v4l2_requestbuffers does not have enough reserved room. Therefore for backward compatibility ->reserved and ->flags were put into anonymous union. Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 34ba1017b89b..fec2607a07e3 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -946,7 +946,10 @@ struct v4l2_requestbuffers { __u32 type; /* enum v4l2_buf_type */ __u32 memory; /* enum v4l2_memory */ __u32 capabilities; - __u32 reserved[1]; + union { + __u32 flags; + __u32 reserved[1]; + }; }; /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */ @@ -2450,6 +2453,9 @@ struct v4l2_dbg_chip_info { * @memory: enum v4l2_memory; buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. + * @flags: additional buffer management attributes (ignored unless the + * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability + * and configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2458,7 +2464,8 @@ struct v4l2_create_buffers { __u32 memory; struct v4l2_format format; __u32 capabilities; - __u32 reserved[7]; + __u32 flags; + __u32 reserved[6]; }; /* -- cgit v1.2.3 From 286cf7d3a99e1ca8c1d8e674b9a98f2dbe8520dc Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 26 May 2020 10:59:53 +0200 Subject: media: videodev2.h: add V4L2_FMT_FLAG_ENC_CAP_FRAME_INTERVAL flag Add the V4L2_FMT_FLAG_ENC_CAP_FRAME_INTERVAL flag to signal that the coded frame interval can be set separately from the raw frame interval for stateful encoders. Signed-off-by: Hans Verkuil Reviewed-by: Michael Tretter Acked-by: Tomasz Figa Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index fec2607a07e3..303805438814 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -794,6 +794,7 @@ struct v4l2_fmtdesc { #define V4L2_FMT_FLAG_EMULATED 0x0002 #define V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM 0x0004 #define V4L2_FMT_FLAG_DYN_RESOLUTION 0x0008 +#define V4L2_FMT_FLAG_ENC_CAP_FRAME_INTERVAL 0x0010 /* Frame Size and frame rate enumeration */ /* -- cgit v1.2.3 From 79a28ddd18e9c653f13f60dfabee15c024e64b9b Mon Sep 17 00:00:00 2001 From: Alexandre Cassen Date: Tue, 23 Jun 2020 10:33:45 +0200 Subject: rtnetlink: add keepalived rtm_protocol Keepalived can set global static ip routes or virtual ip routes dynamically following VRRP protocol states. Using a dedicated rtm_protocol will help keeping track of it. Changes in v2: - fix tab/space indenting Signed-off-by: Alexandre Cassen Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 45 +++++++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 073e71ef6bdd..879e64950a0a 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -257,12 +257,12 @@ enum { /* rtm_protocol */ -#define RTPROT_UNSPEC 0 -#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects; - not used by current IPv4 */ -#define RTPROT_KERNEL 2 /* Route installed by kernel */ -#define RTPROT_BOOT 3 /* Route installed during boot */ -#define RTPROT_STATIC 4 /* Route installed by administrator */ +#define RTPROT_UNSPEC 0 +#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects; + not used by current IPv4 */ +#define RTPROT_KERNEL 2 /* Route installed by kernel */ +#define RTPROT_BOOT 3 /* Route installed during boot */ +#define RTPROT_STATIC 4 /* Route installed by administrator */ /* Values of protocol >= RTPROT_STATIC are not interpreted by kernel; they are just passed from user and back as is. @@ -271,22 +271,23 @@ enum { avoid conflicts. */ -#define RTPROT_GATED 8 /* Apparently, GateD */ -#define RTPROT_RA 9 /* RDISC/ND router advertisements */ -#define RTPROT_MRT 10 /* Merit MRT */ -#define RTPROT_ZEBRA 11 /* Zebra */ -#define RTPROT_BIRD 12 /* BIRD */ -#define RTPROT_DNROUTED 13 /* DECnet routing daemon */ -#define RTPROT_XORP 14 /* XORP */ -#define RTPROT_NTK 15 /* Netsukuku */ -#define RTPROT_DHCP 16 /* DHCP client */ -#define RTPROT_MROUTED 17 /* Multicast daemon */ -#define RTPROT_BABEL 42 /* Babel daemon */ -#define RTPROT_BGP 186 /* BGP Routes */ -#define RTPROT_ISIS 187 /* ISIS Routes */ -#define RTPROT_OSPF 188 /* OSPF Routes */ -#define RTPROT_RIP 189 /* RIP Routes */ -#define RTPROT_EIGRP 192 /* EIGRP Routes */ +#define RTPROT_GATED 8 /* Apparently, GateD */ +#define RTPROT_RA 9 /* RDISC/ND router advertisements */ +#define RTPROT_MRT 10 /* Merit MRT */ +#define RTPROT_ZEBRA 11 /* Zebra */ +#define RTPROT_BIRD 12 /* BIRD */ +#define RTPROT_DNROUTED 13 /* DECnet routing daemon */ +#define RTPROT_XORP 14 /* XORP */ +#define RTPROT_NTK 15 /* Netsukuku */ +#define RTPROT_DHCP 16 /* DHCP client */ +#define RTPROT_MROUTED 17 /* Multicast daemon */ +#define RTPROT_KEEPALIVED 18 /* Keepalived daemon */ +#define RTPROT_BABEL 42 /* Babel daemon */ +#define RTPROT_BGP 186 /* BGP Routes */ +#define RTPROT_ISIS 187 /* ISIS Routes */ +#define RTPROT_OSPF 188 /* OSPF Routes */ +#define RTPROT_RIP 189 /* RIP Routes */ +#define RTPROT_EIGRP 192 /* EIGRP Routes */ /* rtm_scope -- cgit v1.2.3 From bdb7b79b4ce864a724250e1d35948c46f135de36 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 22 Jun 2020 20:22:21 -0700 Subject: bpf: Switch most helper return values from 32-bit int to 64-bit long Switch most of BPF helper definitions from returning int to long. These definitions are coming from comments in BPF UAPI header and are used to generate bpf_helper_defs.h (under libbpf) to be later included and used from BPF programs. In actual in-kernel implementation, all the helpers are defined as returning u64, but due to some historical reasons, most of them are actually defined as returning int in UAPI (usually, to return 0 on success, and negative value on error). This actually causes Clang to quite often generate sub-optimal code, because compiler believes that return value is 32-bit, and in a lot of cases has to be up-converted (usually with a pair of 32-bit bit shifts) to 64-bit values, before they can be used further in BPF code. Besides just "polluting" the code, these 32-bit shifts quite often cause problems for cases in which return value matters. This is especially the case for the family of bpf_probe_read_str() functions. There are few other similar helpers (e.g., bpf_read_branch_records()), in which return value is used by BPF program logic to record variable-length data and process it. For such cases, BPF program logic carefully manages offsets within some array or map to read variable-length data. For such uses, it's crucial for BPF verifier to track possible range of register values to prove that all the accesses happen within given memory bounds. Those extraneous zero-extending bit shifts, inserted by Clang (and quite often interleaved with other code, which makes the issues even more challenging and sometimes requires employing extra per-variable compiler barriers), throws off verifier logic and makes it mark registers as having unknown variable offset. We'll study this pattern a bit later below. Another common pattern is to check return of BPF helper for non-zero state to detect error conditions and attempt alternative actions in such case. Even in this simple and straightforward case, this 32-bit vs BPF's native 64-bit mode quite often leads to sub-optimal and unnecessary extra code. We'll look at this pattern as well. Clang's BPF target supports two modes of code generation: ALU32, in which it is capable of using lower 32-bit parts of registers, and no-ALU32, in which only full 64-bit registers are being used. ALU32 mode somewhat mitigates the above described problems, but not in all cases. This patch switches all the cases in which BPF helpers return 0 or negative error from returning int to returning long. It is shown below that such change in definition leads to equivalent or better code. No-ALU32 mode benefits more, but ALU32 mode doesn't degrade or still gets improved code generation. Another class of cases switched from int to long are bpf_probe_read_str()-like helpers, which encode successful case as non-negative values, while still returning negative value for errors. In all of such cases, correctness is preserved due to two's complement encoding of negative values and the fact that all helpers return values with 32-bit absolute value. Two's complement ensures that for negative values higher 32 bits are all ones and when truncated, leave valid negative 32-bit value with the same value. Non-negative values have upper 32 bits set to zero and similarly preserve value when high 32 bits are truncated. This means that just casting to int/u32 is correct and efficient (and in ALU32 mode doesn't require any extra shifts). To minimize the chances of regressions, two code patterns were investigated, as mentioned above. For both patterns, BPF assembly was analyzed in ALU32/NO-ALU32 compiler modes, both with current 32-bit int return type and new 64-bit long return type. Case 1. Variable-length data reading and concatenation. This is quite ubiquitous pattern in tracing/monitoring applications, reading data like process's environment variables, file path, etc. In such case, many pieces of string-like variable-length data are read into a single big buffer, and at the end of the process, only a part of array containing actual data is sent to user-space for further processing. This case is tested in test_varlen.c selftest (in the next patch). Code flow is roughly as follows: void *payload = &sample->payload; u64 len; len = bpf_probe_read_kernel_str(payload, MAX_SZ1, &source_data1); if (len <= MAX_SZ1) { payload += len; sample->len1 = len; } len = bpf_probe_read_kernel_str(payload, MAX_SZ2, &source_data2); if (len <= MAX_SZ2) { payload += len; sample->len2 = len; } /* and so on */ sample->total_len = payload - &sample->payload; /* send over, e.g., perf buffer */ There could be two variations with slightly different code generated: when len is 64-bit integer and when it is 32-bit integer. Both variations were analysed. BPF assembly instructions between two successive invocations of bpf_probe_read_kernel_str() were used to check code regressions. Results are below, followed by short analysis. Left side is using helpers with int return type, the right one is after the switch to long. ALU32 + INT ALU32 + LONG =========== ============ 64-BIT (13 insns): 64-BIT (10 insns): ------------------------------------ ------------------------------------ 17: call 115 17: call 115 18: if w0 > 256 goto +9 18: if r0 > 256 goto +6 19: w1 = w0 19: r1 = 0 ll 20: r1 <<= 32 21: *(u64 *)(r1 + 0) = r0 21: r1 s>>= 32 22: r6 = 0 ll 22: r2 = 0 ll 24: r6 += r0 24: *(u64 *)(r2 + 0) = r1 00000000000000c8 : 25: r6 = 0 ll 25: r1 = r6 27: r6 += r1 26: w2 = 256 00000000000000e0 : 27: r3 = 0 ll 28: r1 = r6 29: call 115 29: w2 = 256 30: r3 = 0 ll 32: call 115 32-BIT (11 insns): 32-BIT (12 insns): ------------------------------------ ------------------------------------ 17: call 115 17: call 115 18: if w0 > 256 goto +7 18: if w0 > 256 goto +8 19: r1 = 0 ll 19: r1 = 0 ll 21: *(u32 *)(r1 + 0) = r0 21: *(u32 *)(r1 + 0) = r0 22: w1 = w0 22: r0 <<= 32 23: r6 = 0 ll 23: r0 >>= 32 25: r6 += r1 24: r6 = 0 ll 00000000000000d0 : 26: r6 += r0 26: r1 = r6 00000000000000d8 : 27: w2 = 256 27: r1 = r6 28: r3 = 0 ll 28: w2 = 256 30: call 115 29: r3 = 0 ll 31: call 115 In ALU32 mode, the variant using 64-bit length variable clearly wins and avoids unnecessary zero-extension bit shifts. In practice, this is even more important and good, because BPF code won't need to do extra checks to "prove" that payload/len are within good bounds. 32-bit len is one instruction longer. Clang decided to do 64-to-32 casting with two bit shifts, instead of equivalent `w1 = w0` assignment. The former uses extra register. The latter might potentially lose some range information, but not for 32-bit value. So in this case, verifier infers that r0 is [0, 256] after check at 18:, and shifting 32 bits left/right keeps that range intact. We should probably look into Clang's logic and see why it chooses bitshifts over sub-register assignments for this. NO-ALU32 + INT NO-ALU32 + LONG ============== =============== 64-BIT (14 insns): 64-BIT (10 insns): ------------------------------------ ------------------------------------ 17: call 115 17: call 115 18: r0 <<= 32 18: if r0 > 256 goto +6 19: r1 = r0 19: r1 = 0 ll 20: r1 >>= 32 21: *(u64 *)(r1 + 0) = r0 21: if r1 > 256 goto +7 22: r6 = 0 ll 22: r0 s>>= 32 24: r6 += r0 23: r1 = 0 ll 00000000000000c8 : 25: *(u64 *)(r1 + 0) = r0 25: r1 = r6 26: r6 = 0 ll 26: r2 = 256 28: r6 += r0 27: r3 = 0 ll 00000000000000e8 : 29: call 115 29: r1 = r6 30: r2 = 256 31: r3 = 0 ll 33: call 115 32-BIT (13 insns): 32-BIT (13 insns): ------------------------------------ ------------------------------------ 17: call 115 17: call 115 18: r1 = r0 18: r1 = r0 19: r1 <<= 32 19: r1 <<= 32 20: r1 >>= 32 20: r1 >>= 32 21: if r1 > 256 goto +6 21: if r1 > 256 goto +6 22: r2 = 0 ll 22: r2 = 0 ll 24: *(u32 *)(r2 + 0) = r0 24: *(u32 *)(r2 + 0) = r0 25: r6 = 0 ll 25: r6 = 0 ll 27: r6 += r1 27: r6 += r1 00000000000000e0 : 00000000000000e0 : 28: r1 = r6 28: r1 = r6 29: r2 = 256 29: r2 = 256 30: r3 = 0 ll 30: r3 = 0 ll 32: call 115 32: call 115 In NO-ALU32 mode, for the case of 64-bit len variable, Clang generates much superior code, as expected, eliminating unnecessary bit shifts. For 32-bit len, code is identical. So overall, only ALU-32 32-bit len case is more-or-less equivalent and the difference stems from internal Clang decision, rather than compiler lacking enough information about types. Case 2. Let's look at the simpler case of checking return result of BPF helper for errors. The code is very simple: long bla; if (bpf_probe_read_kenerl(&bla, sizeof(bla), 0)) return 1; else return 0; ALU32 + CHECK (9 insns) ALU32 + CHECK (9 insns) ==================================== ==================================== 0: r1 = r10 0: r1 = r10 1: r1 += -8 1: r1 += -8 2: w2 = 8 2: w2 = 8 3: r3 = 0 3: r3 = 0 4: call 113 4: call 113 5: w1 = w0 5: r1 = r0 6: w0 = 1 6: w0 = 1 7: if w1 != 0 goto +1 7: if r1 != 0 goto +1 8: w0 = 0 8: w0 = 0 0000000000000048 : 0000000000000048 : 9: exit 9: exit Almost identical code, the only difference is the use of full register assignment (r1 = r0) vs half-registers (w1 = w0) in instruction #5. On 32-bit architectures, new BPF assembly might be slightly less optimal, in theory. But one can argue that's not a big issue, given that use of full registers is still prevalent (e.g., for parameter passing). NO-ALU32 + CHECK (11 insns) NO-ALU32 + CHECK (9 insns) ==================================== ==================================== 0: r1 = r10 0: r1 = r10 1: r1 += -8 1: r1 += -8 2: r2 = 8 2: r2 = 8 3: r3 = 0 3: r3 = 0 4: call 113 4: call 113 5: r1 = r0 5: r1 = r0 6: r1 <<= 32 6: r0 = 1 7: r1 >>= 32 7: if r1 != 0 goto +1 8: r0 = 1 8: r0 = 0 9: if r1 != 0 goto +1 0000000000000048 : 10: r0 = 0 9: exit 0000000000000058 : 11: exit NO-ALU32 is a clear improvement, getting rid of unnecessary zero-extension bit shifts. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200623032224.4020118-1-andriin@fb.com --- include/uapi/linux/bpf.h | 192 +++++++++++++++++++++++------------------------ 1 file changed, 96 insertions(+), 96 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 19684813faae..be0efee49093 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -653,7 +653,7 @@ union bpf_attr { * Map value associated to *key*, or **NULL** if no entry was * found. * - * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) * Description * Add or update the value of the entry associated to *key* in * *map* with *value*. *flags* is one of: @@ -671,13 +671,13 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * long bpf_map_delete_elem(struct bpf_map *map, const void *key) * Description * Delete entry with *key* from *map*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) * Description * For tracing programs, safely attempt to read *size* bytes from * kernel space address *unsafe_ptr* and store the data in *dst*. @@ -695,7 +695,7 @@ union bpf_attr { * Return * Current *ktime*. * - * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * long bpf_trace_printk(const char *fmt, u32 fmt_size, ...) * Description * This helper is a "printk()-like" facility for debugging. It * prints a message defined by format *fmt* (of size *fmt_size*) @@ -775,7 +775,7 @@ union bpf_attr { * Return * The SMP id of the processor running the program. * - * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description * Store *len* bytes from address *from* into the packet * associated to *skb*, at *offset*. *flags* are a combination of @@ -792,7 +792,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * long bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) * Description * Recompute the layer 3 (e.g. IP) checksum for the packet * associated to *skb*. Computation is incremental, so the helper @@ -817,7 +817,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * long bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) * Description * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the * packet associated to *skb*. Computation is incremental, so the @@ -849,7 +849,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * long bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) * Description * This special helper is used to trigger a "tail call", or in * other words, to jump into another eBPF program. The same stack @@ -880,7 +880,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * long bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) * Description * Clone and redirect the packet associated to *skb* to another * net device of index *ifindex*. Both ingress and egress @@ -916,7 +916,7 @@ union bpf_attr { * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. * - * int bpf_get_current_comm(void *buf, u32 size_of_buf) + * long bpf_get_current_comm(void *buf, u32 size_of_buf) * Description * Copy the **comm** attribute of the current task into *buf* of * *size_of_buf*. The **comm** attribute contains the name of @@ -953,7 +953,7 @@ union bpf_attr { * Return * The classid, or 0 for the default unconfigured classid. * - * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * long bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) * Description * Push a *vlan_tci* (VLAN tag control information) of protocol * *vlan_proto* to the packet associated to *skb*, then update @@ -969,7 +969,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_vlan_pop(struct sk_buff *skb) + * long bpf_skb_vlan_pop(struct sk_buff *skb) * Description * Pop a VLAN header from the packet associated to *skb*. * @@ -981,7 +981,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * long bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) * Description * Get tunnel metadata. This helper takes a pointer *key* to an * empty **struct bpf_tunnel_key** of **size**, that will be @@ -1032,7 +1032,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * long bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) * Description * Populate tunnel metadata for packet associated to *skb.* The * tunnel metadata is set to the contents of *key*, of *size*. The @@ -1098,7 +1098,7 @@ union bpf_attr { * The value of the perf event counter read from the map, or a * negative error code in case of failure. * - * int bpf_redirect(u32 ifindex, u64 flags) + * long bpf_redirect(u32 ifindex, u64 flags) * Description * Redirect the packet to another net device of index *ifindex*. * This helper is somewhat similar to **bpf_clone_redirect**\ @@ -1145,7 +1145,7 @@ union bpf_attr { * The realm of the route for the packet associated to *skb*, or 0 * if none was found. * - * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * long bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) * Description * Write raw *data* blob into a special BPF perf event held by * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf @@ -1190,7 +1190,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) + * long bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) * Description * This helper was provided as an easy way to load data from a * packet. It can be used to load *len* bytes from *offset* from @@ -1207,7 +1207,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) + * long bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) * Description * Walk a user or a kernel stack and return its id. To achieve * this, the helper needs *ctx*, which is a pointer to the context @@ -1276,7 +1276,7 @@ union bpf_attr { * The checksum result, or a negative error code in case of * failure. * - * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * long bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) * Description * Retrieve tunnel options metadata for the packet associated to * *skb*, and store the raw tunnel option data to the buffer *opt* @@ -1294,7 +1294,7 @@ union bpf_attr { * Return * The size of the option data retrieved. * - * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * long bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) * Description * Set tunnel options metadata for the packet associated to *skb* * to the option data contained in the raw buffer *opt* of *size*. @@ -1304,7 +1304,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * long bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) * Description * Change the protocol of the *skb* to *proto*. Currently * supported are transition from IPv4 to IPv6, and from IPv6 to @@ -1331,7 +1331,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * long bpf_skb_change_type(struct sk_buff *skb, u32 type) * Description * Change the packet type for the packet associated to *skb*. This * comes down to setting *skb*\ **->pkt_type** to *type*, except @@ -1358,7 +1358,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * long bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) * Description * Check whether *skb* is a descendant of the cgroup2 held by * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. @@ -1389,7 +1389,7 @@ union bpf_attr { * Return * A pointer to the current task struct. * - * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * long bpf_probe_write_user(void *dst, const void *src, u32 len) * Description * Attempt in a safe way to write *len* bytes from the buffer * *src* to *dst* in memory. It only works for threads that are in @@ -1408,7 +1408,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * long bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) * Description * Check whether the probe is being run is the context of a given * subset of the cgroup2 hierarchy. The cgroup2 to test is held by @@ -1420,7 +1420,7 @@ union bpf_attr { * * 1, if the *skb* task does not belong to the cgroup2. * * A negative error code, if an error occurred. * - * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) * Description * Resize (trim or grow) the packet associated to *skb* to the * new *len*. The *flags* are reserved for future usage, and must @@ -1444,7 +1444,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * long bpf_skb_pull_data(struct sk_buff *skb, u32 len) * Description * Pull in non-linear data in case the *skb* is non-linear and not * all of *len* are part of the linear section. Make *len* bytes @@ -1500,7 +1500,7 @@ union bpf_attr { * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. * - * int bpf_get_numa_node_id(void) + * long bpf_get_numa_node_id(void) * Description * Return the id of the current NUMA node. The primary use case * for this helper is the selection of sockets for the local NUMA @@ -1511,7 +1511,7 @@ union bpf_attr { * Return * The id of current NUMA node. * - * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * long bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) * Description * Grows headroom of packet associated to *skb* and adjusts the * offset of the MAC header accordingly, adding *len* bytes of @@ -1532,7 +1532,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * long bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) * Description * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that * it is possible to use a negative value for *delta*. This helper @@ -1547,7 +1547,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for @@ -1595,14 +1595,14 @@ union bpf_attr { * is returned (note that **overflowuid** might also be the actual * UID value for the socket). * - * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * long bpf_set_hash(struct sk_buff *skb, u32 hash) * Description * Set the full hash for *skb* (set the field *skb*\ **->hash**) * to value *hash*. * Return * 0 * - * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) + * long bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **setsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1630,7 +1630,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) + * long bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. @@ -1676,7 +1676,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain @@ -1697,7 +1697,7 @@ union bpf_attr { * **XDP_REDIRECT** on success, or the value of the two lower bits * of the *flags* argument on error. * - * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) + * long bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description * Redirect the packet to the socket referenced by *map* (of type * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and @@ -1708,7 +1708,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * long bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a *map* referencing sockets. The * *skops* is used as a new value for the entry associated to @@ -1727,7 +1727,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * long bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) * Description * Adjust the address pointed by *xdp_md*\ **->data_meta** by * *delta* (which can be positive or negative). Note that this @@ -1756,7 +1756,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * long bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) * Description * Read the value of a perf event counter, and store it into *buf* * of size *buf_size*. This helper relies on a *map* of type @@ -1806,7 +1806,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description * For en eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in @@ -1817,7 +1817,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) + * long bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) * Description * Emulate a call to **getsockopt()** on the socket associated to * *bpf_socket*, which must be a full socket. The *level* at @@ -1842,7 +1842,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_override_return(struct pt_regs *regs, u64 rc) + * long bpf_override_return(struct pt_regs *regs, u64 rc) * Description * Used for error injection, this helper uses kprobes to override * the return value of the probed function, and to set it to *rc*. @@ -1867,7 +1867,7 @@ union bpf_attr { * Return * 0 * - * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * long bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) * Description * Attempt to set the value of the **bpf_sock_ops_cb_flags** field * for the full TCP socket associated to *bpf_sock_ops* to @@ -1911,7 +1911,7 @@ union bpf_attr { * be set is returned (which comes down to 0 if all bits were set * as required). * - * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * long bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) * Description * This helper is used in programs implementing policies at the * socket level. If the message *msg* is allowed to pass (i.e. if @@ -1925,7 +1925,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * long bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) * Description * For socket policies, apply the verdict of the eBPF program to * the next *bytes* (number of bytes) of message *msg*. @@ -1959,7 +1959,7 @@ union bpf_attr { * Return * 0 * - * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * long bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) * Description * For socket policies, prevent the execution of the verdict eBPF * program for message *msg* until *bytes* (byte number) have been @@ -1977,7 +1977,7 @@ union bpf_attr { * Return * 0 * - * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * long bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) * Description * For socket policies, pull in non-linear data from user space * for *msg* and set pointers *msg*\ **->data** and *msg*\ @@ -2008,7 +2008,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * long bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) * Description * Bind the socket associated to *ctx* to the address pointed by * *addr*, of length *addr_len*. This allows for making outgoing @@ -2026,7 +2026,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * long bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) * Description * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is * possible to both shrink and grow the packet tail. @@ -2040,7 +2040,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * long bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) * Description * Retrieve the XFRM state (IP transform framework, see also * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. @@ -2056,7 +2056,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) + * long bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. * To achieve this, the helper needs *ctx*, which is a pointer @@ -2089,7 +2089,7 @@ union bpf_attr { * A non-negative value equal to or less than *size* on success, * or a negative error in case of failure. * - * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) + * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) * Description * This helper is similar to **bpf_skb_load_bytes**\ () in that * it provides an easy way to load *len* bytes from *offset* @@ -2111,7 +2111,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * long bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) * Description * Do FIB lookup in kernel tables using parameters in *params*. * If lookup is successful and result shows packet is to be @@ -2142,7 +2142,7 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * - * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. * The *skops* is used as a new value for the entry associated to @@ -2161,7 +2161,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * long bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) * Description * This helper is used in programs implementing policies at the * socket level. If the message *msg* is allowed to pass (i.e. if @@ -2175,7 +2175,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * long bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) * Description * This helper is used in programs implementing policies at the * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. @@ -2189,7 +2189,7 @@ union bpf_attr { * Return * **SK_PASS** on success, or **SK_DROP** on error. * - * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * long bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) * Description * Encapsulate the packet associated to *skb* within a Layer 3 * protocol header. This header is provided in the buffer at @@ -2226,7 +2226,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * long bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) * Description * Store *len* bytes from address *from* into the packet * associated to *skb*, at *offset*. Only the flags, tag and TLVs @@ -2241,7 +2241,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * long bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) * Description * Adjust the size allocated to TLVs in the outermost IPv6 * Segment Routing Header contained in the packet associated to @@ -2257,7 +2257,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * long bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) * Description * Apply an IPv6 Segment Routing action of type *action* to the * packet associated to *skb*. Each action takes a parameter @@ -2286,7 +2286,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_repeat(void *ctx) + * long bpf_rc_repeat(void *ctx) * Description * This helper is used in programs implementing IR decoding, to * report a successfully decoded repeat key message. This delays @@ -2305,7 +2305,7 @@ union bpf_attr { * Return * 0 * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * long bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) * Description * This helper is used in programs implementing IR decoding, to * report a successfully decoded key press with *scancode*, @@ -2370,7 +2370,7 @@ union bpf_attr { * Return * A pointer to the local storage area. * - * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) * Description * Select a **SO_REUSEPORT** socket from a * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. @@ -2471,7 +2471,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * int bpf_sk_release(struct bpf_sock *sock) + * long bpf_sk_release(struct bpf_sock *sock) * Description * Release the reference held by *sock*. *sock* must be a * non-**NULL** pointer that was returned from @@ -2479,7 +2479,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * long bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) * Description * Push an element *value* in *map*. *flags* is one of: * @@ -2489,19 +2489,19 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * long bpf_map_pop_elem(struct bpf_map *map, void *value) * Description * Pop an element from *map*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * long bpf_map_peek_elem(struct bpf_map *map, void *value) * Description * Get an element from *map* without removing it. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * long bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description * For socket policies, insert *len* bytes into *msg* at offset * *start*. @@ -2517,7 +2517,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * long bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description * Will remove *len* bytes from a *msg* starting at byte *start*. * This may result in **ENOMEM** errors under certain situations if @@ -2529,7 +2529,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * long bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) * Description * This helper is used in programs implementing IR decoding, to * report a successfully decoded pointer movement. @@ -2543,7 +2543,7 @@ union bpf_attr { * Return * 0 * - * int bpf_spin_lock(struct bpf_spin_lock *lock) + * long bpf_spin_lock(struct bpf_spin_lock *lock) * Description * Acquire a spinlock represented by the pointer *lock*, which is * stored as part of a value of a map. Taking the lock allows to @@ -2591,7 +2591,7 @@ union bpf_attr { * Return * 0 * - * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * long bpf_spin_unlock(struct bpf_spin_lock *lock) * Description * Release the *lock* previously locked by a call to * **bpf_spin_lock**\ (\ *lock*\ ). @@ -2614,7 +2614,7 @@ union bpf_attr { * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * - * int bpf_skb_ecn_set_ce(struct sk_buff *skb) + * long bpf_skb_ecn_set_ce(struct sk_buff *skb) * Description * Set ECN (Explicit Congestion Notification) field of IP header * to **CE** (Congestion Encountered) if current value is **ECT** @@ -2651,7 +2651,7 @@ union bpf_attr { * result is from *reuse*\ **->socks**\ [] using the hash of the * tuple. * - * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) * Description * Check whether *iph* and *th* contain a valid SYN cookie ACK for * the listening socket in *sk*. @@ -2666,7 +2666,7 @@ union bpf_attr { * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative * error otherwise. * - * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * long bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) * Description * Get name of sysctl in /proc/sys/ and copy it into provided by * program buffer *buf* of size *buf_len*. @@ -2682,7 +2682,7 @@ union bpf_attr { * **-E2BIG** if the buffer wasn't big enough (*buf* will contain * truncated name in this case). * - * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * long bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) * Description * Get current value of sysctl as it is presented in /proc/sys * (incl. newline, etc), and copy it as a string into provided @@ -2701,7 +2701,7 @@ union bpf_attr { * **-EINVAL** if current value was unavailable, e.g. because * sysctl is uninitialized and read returns -EIO for it. * - * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * long bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) * Description * Get new value being written by user space to sysctl (before * the actual write happens) and copy it as a string into @@ -2718,7 +2718,7 @@ union bpf_attr { * * **-EINVAL** if sysctl is being read. * - * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * long bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) * Description * Override new value being written by user space to sysctl with * value provided by program in buffer *buf* of size *buf_len*. @@ -2735,7 +2735,7 @@ union bpf_attr { * * **-EINVAL** if sysctl is being read. * - * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * long bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) * Description * Convert the initial part of the string from buffer *buf* of * size *buf_len* to a long integer according to the given base @@ -2759,7 +2759,7 @@ union bpf_attr { * * **-ERANGE** if resulting value was out of range. * - * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * long bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) * Description * Convert the initial part of the string from buffer *buf* of * size *buf_len* to an unsigned long integer according to the @@ -2810,7 +2810,7 @@ union bpf_attr { * **NULL** if not found or there was an error in adding * a new bpf-local-storage. * - * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) * Description * Delete a bpf-local-storage from a *sk*. * Return @@ -2818,7 +2818,7 @@ union bpf_attr { * * **-ENOENT** if the bpf-local-storage cannot be found. * - * int bpf_send_signal(u32 sig) + * long bpf_send_signal(u32 sig) * Description * Send signal *sig* to the process of the current task. * The signal may be delivered to any of this process's threads. @@ -2859,7 +2859,7 @@ union bpf_attr { * * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 * - * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * long bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) * Description * Write raw *data* blob into a special BPF perf event held by * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf @@ -2883,21 +2883,21 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) * Description * Safely attempt to read *size* bytes from user space address * *unsafe_ptr* and store the data in *dst*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) * Description * Safely attempt to read *size* bytes from kernel space address * *unsafe_ptr* and store the data in *dst*. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe user address * *unsafe_ptr* to *dst*. The *size* should include the @@ -2941,7 +2941,7 @@ union bpf_attr { * including the trailing NUL character. On error, a negative * value. * - * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * long bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) * Description * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. @@ -2949,14 +2949,14 @@ union bpf_attr { * On success, the strictly positive length of the string, including * the trailing NUL character. On error, a negative value. * - * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt) + * long bpf_tcp_send_ack(void *tp, u32 rcv_nxt) * Description * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**. * *rcv_nxt* is the ack_seq to be sent out. * Return * 0 on success, or a negative error in case of failure. * - * int bpf_send_signal_thread(u32 sig) + * long bpf_send_signal_thread(u32 sig) * Description * Send signal *sig* to the thread corresponding to the current task. * Return @@ -2976,7 +2976,7 @@ union bpf_attr { * Return * The 64 bit jiffies * - * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) + * long bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) * Description * For an eBPF program attached to a perf event, retrieve the * branch records (**struct perf_branch_entry**) associated to *ctx* @@ -2995,7 +2995,7 @@ union bpf_attr { * * **-ENOENT** if architecture does not support branch records. * - * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) + * long bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) * Description * Returns 0 on success, values for *pid* and *tgid* as seen from the current * *namespace* will be returned in *nsdata*. @@ -3007,7 +3007,7 @@ union bpf_attr { * * **-ENOENT** if pidns does not exists for the current task. * - * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * long bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) * Description * Write raw *data* blob into a special BPF perf event held by * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf @@ -3062,7 +3062,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) * Description * Assign the *sk* to the *skb*. When combined with appropriate * routing configuration to receive the packet towards the socket, @@ -3097,7 +3097,7 @@ union bpf_attr { * Return * Current *ktime*. * - * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * long bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) * Description * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print * out the format string. @@ -3126,7 +3126,7 @@ union bpf_attr { * * **-EOVERFLOW** if an overflow happened: The same object will be tried again. * - * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * long bpf_seq_write(struct seq_file *m, const void *data, u32 len) * Description * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. * The *m* represents the seq_file. The *data* and *len* represent the @@ -3221,7 +3221,7 @@ union bpf_attr { * Return * Requested value, or 0, if flags are not recognized. * - * int bpf_csum_level(struct sk_buff *skb, u64 level) + * long bpf_csum_level(struct sk_buff *skb, u64 level) * Description * Change the skbs checksum level by one layer up or down, or * reset it entirely to none in order to have the stack perform -- cgit v1.2.3 From 428d2459cceb77357b81c242ca22462a6a904817 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Petr=20Van=C4=9Bk?= Date: Sat, 30 May 2020 14:39:12 +0200 Subject: xfrm: introduce oseq-may-wrap flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RFC 4303 in section 3.3.3 suggests to disable anti-replay for manually distributed ICVs in which case the sender does not need to monitor or reset the counter. However, the sender still increments the counter and when it reaches the maximum value, the counter rolls over back to zero. This patch introduces new extra_flag XFRM_SA_XFLAG_OSEQ_MAY_WRAP which allows sequence number to cycle in outbound packets if set. This flag is used only in legacy and bmp code, because esn should not be negotiated if anti-replay is disabled (see note in 3.3.3 section). Signed-off-by: Petr Vaněk Acked-by: Christophe Gouault Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index ff7cfdc6cb44..ffc6a5391bb7 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -387,6 +387,7 @@ struct xfrm_usersa_info { }; #define XFRM_SA_XFLAG_DONT_ENCAP_DSCP 1 +#define XFRM_SA_XFLAG_OSEQ_MAY_WRAP 2 struct xfrm_usersa_id { xfrm_address_t daddr; -- cgit v1.2.3 From 65959522f8060659e308977f09f3eb7b7af5e43f Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 23 Jun 2020 14:30:40 +0300 Subject: RDMA: Add support to dump resource tracker in RAW format Add support to get resource dump in raw format. It enable drivers to return the entire device specific QP/CQ/MR context without a need from the driver to set each field separately. The raw query returns only the device specific data, general data is still returned by using the existing queries. Example: $ rdma res show mr dev mlx5_1 mrn 2 -r -j [{"ifindex":7,"ifname":"mlx5_1", "data":[0,4,255,254,0,0,0,0,0,0,0,0,16,28,0,216,...]}] Link: https://lore.kernel.org/r/20200623113043.1228482-9-leon@kernel.org Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/rdma_netlink.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 8e277783fa96..3826143d420d 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -287,6 +287,12 @@ enum rdma_nldev_command { RDMA_NLDEV_CMD_STAT_DEL, + RDMA_NLDEV_CMD_RES_QP_GET_RAW, + + RDMA_NLDEV_CMD_RES_CQ_GET_RAW, + + RDMA_NLDEV_CMD_RES_MR_GET_RAW, + RDMA_NLDEV_NUM_OPS }; @@ -525,6 +531,8 @@ enum rdma_nldev_attr { */ RDMA_NLDEV_ATTR_DEV_DIM, /* u8 */ + RDMA_NLDEV_ATTR_RES_RAW, /* binary */ + /* * Always the end */ -- cgit v1.2.3 From 62fb45d317c5fa08e4db093441835bb6f33acbd7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 18 Jun 2020 16:42:06 +0200 Subject: USB: ch9: add "USB_" prefix in front of TEST defines For some reason, the TEST_ defines in the usb/ch9.h files did not have the USB_ prefix on it, making it a bit confusing when reading the file, as well as not the nicest thing to do in a uapi file. So fix that up and add the USB_ prefix on to them, and fix up all in-kernel usages. This included deleting the duplicate copy in the net2272.h file. Cc: Felipe Balbi Cc: Michal Simek Cc: Mathias Nyman Cc: Pawel Laszczak Cc: YueHaibing Cc: Nathan Chancellor Cc: Jason Yan Cc: Jia-Ju Bai Cc: Stephen Boyd Cc: Christophe JAILLET Cc: Arnd Bergmann Cc: Jules Irenge Cc: Alan Stern Cc: Thinh Nguyen Cc: Rob Gill Cc: Macpaul Lin Acked-by: Minas Harutyunyan Acked-by: Bin Liu Acked-by: Chunfeng Yun Acked-by: Peter Chen Link: https://lore.kernel.org/r/20200618144206.2655890-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index b1ed2ccfe9cf..48766fdf6580 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -138,11 +138,11 @@ * Test Mode Selectors * See USB 2.0 spec Table 9-7 */ -#define TEST_J 1 -#define TEST_K 2 -#define TEST_SE0_NAK 3 -#define TEST_PACKET 4 -#define TEST_FORCE_EN 5 +#define USB_TEST_J 1 +#define USB_TEST_K 2 +#define USB_TEST_SE0_NAK 3 +#define USB_TEST_PACKET 4 +#define USB_TEST_FORCE_ENABLE 5 /* Status Type */ #define USB_STATUS_TYPE_STANDARD 0 -- cgit v1.2.3 From f9bcf96837f158db6ea982d15cd2c8161ca6bc23 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Sat, 20 Jun 2020 18:30:52 +0300 Subject: bpf: Add SO_KEEPALIVE and related options to bpf_setsockopt This patch adds support of SO_KEEPALIVE flag and TCP related options to bpf_setsockopt() routine. This is helpful if we want to enable or tune TCP keepalive for applications which don't do it in the userspace code. v3: - update kernel-doc in uapi (Nikita Vetoshkin ) v4: - update kernel-doc in tools too (Alexei Starovoitov) - add test to selftests (Alexei Starovoitov) Signed-off-by: Dmitry Yakunin Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200620153052.9439-3-zeil@yandex-team.ru --- include/uapi/linux/bpf.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9d3923e6b860..d9737d51dd19 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1621,10 +1621,13 @@ union bpf_attr { * * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, - * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**. + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return -- cgit v1.2.3 From 899426b3bdd947541ba4af8c767575889c8b842a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 23 Jun 2020 23:47:16 +0300 Subject: net: neighbor: add fdb extended attribute Add an attribute to NDA which will contain all future fdb-specific attributes in order to avoid polluting the NDA namespace with e.g. bridge or vxlan specific attributes. The attribute is called NDA_FDB_EXT_ATTRS and the structure would look like: [NDA_FDB_EXT_ATTRS] = { [NFEA_xxx] } Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/neighbour.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index eefcda8ca44e..540ff48402a1 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -30,6 +30,7 @@ enum { NDA_SRC_VNI, NDA_PROTOCOL, /* Originator of entry */ NDA_NH_ID, + NDA_FDB_EXT_ATTRS, __NDA_MAX }; @@ -172,4 +173,15 @@ enum { }; #define NDTA_MAX (__NDTA_MAX - 1) +/* embedded into NDA_FDB_EXT_ATTRS: + * [NDA_FDB_EXT_ATTRS] = { + * ... + * } + */ +enum { + NFEA_UNSPEC, + __NFEA_MAX +}; +#define NFEA_MAX (__NFEA_MAX - 1) + #endif -- cgit v1.2.3 From 31cbc39b6344916c20452e43a9171009214c409c Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 23 Jun 2020 23:47:17 +0300 Subject: net: bridge: add option to allow activity notifications for any fdb entries This patch adds the ability to notify about activity of any entries (static, permanent or ext_learn). EVPN multihoming peers need it to properly and efficiently handle mac sync (peer active/locally active). We add a new NFEA_ACTIVITY_NOTIFY attribute which is used to dump the current activity state and to control if static entries should be monitored at all. We use 2 bits - one to activate fdb entry tracking (disabled by default) and the second to denote that an entry is inactive. We need the second bit in order to avoid multiple notifications of inactivity. Obviously this makes no difference for dynamic entries since at the time of inactivity they get deleted, while the tracked non-dynamic entries get the inactive bit set and get a notification. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/neighbour.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 540ff48402a1..21e569297355 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -173,13 +173,24 @@ enum { }; #define NDTA_MAX (__NDTA_MAX - 1) + /* FDB activity notification bits used in NFEA_ACTIVITY_NOTIFY: + * - FDB_NOTIFY_BIT - notify on activity/expire for any entry + * - FDB_NOTIFY_INACTIVE_BIT - mark as inactive to avoid multiple notifications + */ +enum { + FDB_NOTIFY_BIT = (1 << 0), + FDB_NOTIFY_INACTIVE_BIT = (1 << 1) +}; + /* embedded into NDA_FDB_EXT_ATTRS: * [NDA_FDB_EXT_ATTRS] = { + * [NFEA_ACTIVITY_NOTIFY] * ... * } */ enum { NFEA_UNSPEC, + NFEA_ACTIVITY_NOTIFY, __NFEA_MAX }; #define NFEA_MAX (__NFEA_MAX - 1) -- cgit v1.2.3 From b5f1d9ec283bd28a452cf61d7e5c2f2b1a9cccda Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 23 Jun 2020 23:47:18 +0300 Subject: net: bridge: add a flag to avoid refreshing fdb when changing/adding When we modify or create a new fdb entry sometimes we want to avoid refreshing its activity in order to track it properly. One example is when a mac is received from EVPN multi-homing peer by FRR, which doesn't want to change local activity accounting. It makes it static and sets a flag to track its activity. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/neighbour.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 21e569297355..dc8b72201f6c 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -191,6 +191,7 @@ enum { enum { NFEA_UNSPEC, NFEA_ACTIVITY_NOTIFY, + NFEA_DONT_REFRESH, __NFEA_MAX }; #define NFEA_MAX (__NFEA_MAX - 1) -- cgit v1.2.3 From af7ec13833619e17f03aa73a785a2f871da6d66b Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:09 -0700 Subject: bpf: Add bpf_skc_to_tcp6_sock() helper The helper is used in tracing programs to cast a socket pointer to a tcp6_sock pointer. The return value could be NULL if the casting is illegal. A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added so the verifier is able to deduce proper return types for the helper. Different from the previous BTF_ID based helpers, the bpf_skc_to_tcp6_sock() argument can be several possible btf_ids. More specifically, all possible socket data structures with sock_common appearing in the first in the memory layout. This patch only added socket types related to tcp and udp. All possible argument btf_id and return value btf_id for helper bpf_skc_to_tcp6_sock() are pre-calculcated and cached. In the future, it is even possible to precompute these btf_id's at kernel build time. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com --- include/uapi/linux/bpf.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d9737d51dd19..e90ad07b291a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3255,6 +3255,12 @@ union bpf_attr { * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level * is returned or the error code -EACCES in case the skb is not * subject to CHECKSUM_UNNECESSARY. + * + * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3392,7 +3398,8 @@ union bpf_attr { FN(ringbuf_submit), \ FN(ringbuf_discard), \ FN(ringbuf_query), \ - FN(csum_level), + FN(csum_level), \ + FN(skc_to_tcp6_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From 478cfbdf5f13dfe09cfd0b1cbac821f5e27f6108 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:11 -0700 Subject: bpf: Add bpf_skc_to_{tcp, tcp_timewait, tcp_request}_sock() helpers Three more helpers are added to cast a sock_common pointer to an tcp_sock, tcp_timewait_sock or a tcp_request_sock for tracing programs. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230811.3988277-1-yhs@fb.com --- include/uapi/linux/bpf.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e90ad07b291a..b9412ab275f3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3261,6 +3261,24 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. * Return * *sk* if casting is valid, or NULL otherwise. + * + * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. + * + * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3399,7 +3417,10 @@ union bpf_attr { FN(ringbuf_discard), \ FN(ringbuf_query), \ FN(csum_level), \ - FN(skc_to_tcp6_sock), + FN(skc_to_tcp6_sock), \ + FN(skc_to_tcp_sock), \ + FN(skc_to_tcp_timewait_sock), \ + FN(skc_to_tcp_request_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From 0d4fad3e57df2bf61e8ffc8d12a34b1caf9b8835 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:15 -0700 Subject: bpf: Add bpf_skc_to_udp6_sock() helper The helper is used in tracing programs to cast a socket pointer to a udp6_sock pointer. The return value could be NULL if the casting is illegal. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Cc: Eric Dumazet Link: https://lore.kernel.org/bpf/20200623230815.3988481-1-yhs@fb.com --- include/uapi/linux/bpf.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b9412ab275f3..0cb8ec948816 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3279,6 +3279,12 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. * Return * *sk* if casting is valid, or NULL otherwise. + * + * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. + * Return + * *sk* if casting is valid, or NULL otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3420,7 +3426,8 @@ union bpf_attr { FN(skc_to_tcp6_sock), \ FN(skc_to_tcp_sock), \ FN(skc_to_tcp_timewait_sock), \ - FN(skc_to_tcp_request_sock), + FN(skc_to_tcp_request_sock), \ + FN(skc_to_udp6_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From bccb48c89fe3c09f1cbb7c8612e31f5daa1d4541 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Mon, 1 Jun 2020 20:13:21 +0200 Subject: batman-adv: Fix typos and grammar in documentation Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 50 +++++++++++++++++++------------------- include/uapi/linux/batman_adv.h | 4 +-- 2 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 0ae34c85ef9e..9c8604c5b5f6 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -72,8 +72,8 @@ enum batadv_subtype { /** * enum batadv_iv_flags - flags used in B.A.T.M.A.N. IV OGM packets - * @BATADV_NOT_BEST_NEXT_HOP: flag is set when ogm packet is forwarded and was - * previously received from someone else than the best neighbor. + * @BATADV_NOT_BEST_NEXT_HOP: flag is set when the ogm packet is forwarded and + * was previously received from someone other than the best neighbor. * @BATADV_PRIMARIES_FIRST_HOP: flag unused. * @BATADV_DIRECTLINK: flag is for the first hop or if rebroadcasted from a * one hop neighbor on the interface where it was originally received. @@ -195,8 +195,8 @@ struct batadv_bla_claim_dst { /** * struct batadv_ogm_packet - ogm (routing protocol) packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @flags: contains routing relevant flags - see enum batadv_iv_flags * @seqno: sequence identification * @orig: address of the source node @@ -247,7 +247,7 @@ struct batadv_ogm2_packet { /** * struct batadv_elp_packet - elp (neighbor discovery) packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header + * @version: batman-adv protocol version, part of the general header * @orig: originator mac address * @seqno: sequence number * @elp_interval: currently used ELP sending interval in ms @@ -265,15 +265,15 @@ struct batadv_elp_packet { /** * struct batadv_icmp_header - common members among all the ICMP packets * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @msg_type: ICMP packet type * @dst: address of the destination node * @orig: address of the source node * @uid: local ICMP socket identifier * @align: not used - useful for alignment purposes only * - * This structure is used for ICMP packets parsing only and it is never sent + * This structure is used for ICMP packet parsing only and it is never sent * over the wire. The alignment field at the end is there to ensure that * members are padded the same way as they are in real packets. */ @@ -291,8 +291,8 @@ struct batadv_icmp_header { /** * struct batadv_icmp_packet - ICMP packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @msg_type: ICMP packet type * @dst: address of the destination node * @orig: address of the source node @@ -315,8 +315,8 @@ struct batadv_icmp_packet { /** * struct batadv_icmp_tp_packet - ICMP TP Meter packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @msg_type: ICMP packet type * @dst: address of the destination node * @orig: address of the source node @@ -358,8 +358,8 @@ enum batadv_icmp_tp_subtype { /** * struct batadv_icmp_packet_rr - ICMP RouteRecord packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @msg_type: ICMP packet type * @dst: address of the destination node * @orig: address of the source node @@ -397,8 +397,8 @@ struct batadv_icmp_packet_rr { /** * struct batadv_unicast_packet - unicast packet for network payload * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @ttvn: translation table version number * @dest: originator destination of the unicast packet */ @@ -433,8 +433,8 @@ struct batadv_unicast_4addr_packet { /** * struct batadv_frag_packet - fragmented packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @dest: final destination used when routing fragments * @orig: originator of the fragment used when merging the packet * @no: fragment number within this sequence @@ -467,8 +467,8 @@ struct batadv_frag_packet { /** * struct batadv_bcast_packet - broadcast packet for network payload * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @reserved: reserved byte for alignment * @seqno: sequence identification * @orig: originator of the broadcast packet @@ -488,10 +488,10 @@ struct batadv_bcast_packet { /** * struct batadv_coded_packet - network coded packet * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @first_source: original source of first included packet - * @first_orig_dest: original destinal of first included packet + * @first_orig_dest: original destination of first included packet * @first_crc: checksum of first included packet * @first_ttvn: tt-version number of first included packet * @second_ttl: ttl of second packet @@ -523,8 +523,8 @@ struct batadv_coded_packet { /** * struct batadv_unicast_tvlv_packet - generic unicast packet with tvlv payload * @packet_type: batman-adv packet type, part of the general header - * @version: batman-adv protocol version, part of the genereal header - * @ttl: time to live for this packet, part of the genereal header + * @version: batman-adv protocol version, part of the general header + * @ttl: time to live for this packet, part of the general header * @reserved: reserved field (for packet alignment) * @src: address of the source * @dst: address of the destination diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 617c180ff0c8..8cf2ad11ead9 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -69,7 +69,7 @@ enum batadv_tt_client_flags { /** * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be - * part of the network but no nnode has already announced it + * part of the network but no node has already announced it */ BATADV_TT_CLIENT_TEMP = (1 << 11), }; @@ -131,7 +131,7 @@ enum batadv_gw_modes { /** @BATADV_GW_MODE_CLIENT: send DHCP requests to gw servers */ BATADV_GW_MODE_CLIENT, - /** @BATADV_GW_MODE_SERVER: announce itself as gatway server */ + /** @BATADV_GW_MODE_SERVER: announce itself as gateway server */ BATADV_GW_MODE_SERVER, }; -- cgit v1.2.3 From 3bda14d09dc5789a895ab02b7dcfcec19b0a65b3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Mon, 1 Jun 2020 22:35:22 +0200 Subject: batman-adv: Introduce a configurable per interface hop penalty MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In some setups multiple hard interfaces with similar link qualities or throughput values are available. But people have expressed the desire to consider one of them as a backup only. Some creative solutions are currently in use: Such people are configuring multiple batman-adv mesh/soft interfaces, wire them together with some veth pairs and then tune the hop penalty to achieve an effect similar to a tunable per interface hop penalty. This patch introduces a new, configurable, per hard interface hop penalty to simplify such setups. Signed-off-by: Linus Lüssing Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 8cf2ad11ead9..bb0ae945b36a 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -427,7 +427,8 @@ enum batadv_nl_attrs { /** * @BATADV_ATTR_HOP_PENALTY: defines the penalty which will be applied - * to an originator message's tq-field on every hop. + * to an originator message's tq-field on every hop and/or per + * hard interface */ BATADV_ATTR_HOP_PENALTY, -- cgit v1.2.3 From 322b598be4d9b9090cda560c4caab78704615ab4 Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Tue, 16 Jun 2020 12:08:44 +0800 Subject: fpga: dfl: introduce interrupt trigger setting API FPGA user applications may be interested in interrupts generated by DFL features. For example, users can implement their own FPGA logics with interrupts enabled in AFU (Accelerated Function Unit, dynamic region of DFL based FPGA). So user applications need to be notified to handle these interrupts. In order to allow userspace applications to monitor interrupts, driver requires userspace to provide eventfds as interrupt notification channels. Applications then poll/select on the eventfds to get notified. This patch introduces a generic helper functions to do eventfds binding with given interrupts. Sub feature drivers are expected to use XXX_GET_IRQ_NUM to query irq info, and XXX_SET_IRQ to set eventfds for interrupts. This patch also introduces helper functions for these 2 ioctls. Signed-off-by: Luwei Kang Signed-off-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Tom Rix Reviewed-by: Marcelo Tosatti Acked-by: Wu Hao Signed-off-by: Moritz Fischer --- include/uapi/linux/fpga-dfl.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/fpga-dfl.h b/include/uapi/linux/fpga-dfl.h index ec70a0746e59..7331350f3067 100644 --- a/include/uapi/linux/fpga-dfl.h +++ b/include/uapi/linux/fpga-dfl.h @@ -151,6 +151,19 @@ struct dfl_fpga_port_dma_unmap { #define DFL_FPGA_PORT_DMA_UNMAP _IO(DFL_FPGA_MAGIC, DFL_PORT_BASE + 4) +/** + * struct dfl_fpga_irq_set - the argument for DFL_FPGA_XXX_SET_IRQ ioctl. + * + * @start: Index of the first irq. + * @count: The number of eventfd handler. + * @evtfds: Eventfd handlers. + */ +struct dfl_fpga_irq_set { + __u32 start; + __u32 count; + __s32 evtfds[]; +}; + /* IOCTLs for FME file descriptor */ /** -- cgit v1.2.3 From fe80536acf8397827be77f9b8ada384b90e790d0 Mon Sep 17 00:00:00 2001 From: Martin Date: Sun, 28 Jun 2020 23:18:23 +0530 Subject: bareudp: Added attribute to enable & disable rx metadata collection Metadata need not be collected in receive if the packet from bareudp device is not targeted to openvswitch. Signed-off-by: Martin Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a009365ad67b..cc185a007ade 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -600,6 +600,7 @@ enum { IFLA_BAREUDP_ETHERTYPE, IFLA_BAREUDP_SRCPORT_MIN, IFLA_BAREUDP_MULTIPROTO_MODE, + IFLA_BAREUDP_RX_COLLECT_METADATA, __IFLA_BAREUDP_MAX }; -- cgit v1.2.3 From aee9caa03fc3c8b02f8f31824354d85f30e562e0 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sat, 27 Jun 2020 01:45:28 +0300 Subject: net: sched: sch_red: Add qevents "early_drop" and "mark" In order to allow acting on dropped and/or ECN-marked packets, add two new qevents to the RED qdisc: "early_drop" and "mark". Filters attached at "early_drop" block are executed as packets are early-dropped, those attached at the "mark" block are executed as packets are ECN-marked. Two new attributes are introduced: TCA_RED_EARLY_DROP_BLOCK with the block index for the "early_drop" qevent, and TCA_RED_MARK_BLOCK for the "mark" qevent. Absence of these attributes signifies "don't care": no block is allocated in that case, or the existing blocks are left intact in case of the change callback. For purposes of offloading, blocks attached to these qevents appear with newly-introduced binder types, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP and FLOW_BLOCK_BINDER_TYPE_RED_MARK. Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index a95f3ae7ab37..9e7c2c607845 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -257,6 +257,8 @@ enum { TCA_RED_STAB, TCA_RED_MAX_P, TCA_RED_FLAGS, /* bitfield32 */ + TCA_RED_EARLY_DROP_BLOCK, /* u32 */ + TCA_RED_MARK_BLOCK, /* u32 */ __TCA_RED_MAX, }; -- cgit v1.2.3 From ecc31c60240b9808a274befc5db6b8a249a6ade1 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 29 Jun 2020 23:46:16 +0300 Subject: ethtool: Add link extended state Currently, drivers can only tell whether the link is up/down using LINKSTATE_GET, but no additional information is given. Add attributes to LINKSTATE_GET command in order to allow drivers to expose the user more information in addition to link state to ease the debug process, for example, reason for link down state. Extended state consists of two attributes - link_ext_state and link_ext_substate. The idea is to avoid 'vendor specific' states in order to prevent drivers to use specific link_ext_state that can be in the future common link_ext_state. The substates allows drivers to add more information to the common link_ext_state. For example, vendor can expose 'Autoneg' as link_ext_state and add 'No partner detected during force mode' as link_ext_substate. If a driver cannot pinpoint the extended state with the substate accuracy, it is free to expose only the extended state and omit the substate attribute. Signed-off-by: Amit Cohen Reviewed-by: Jiri Pirko Reviewed-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 70 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 2 ++ 2 files changed, 72 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f4662b3a9e1e..d1413538ef30 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -579,6 +579,76 @@ struct ethtool_pauseparam { __u32 tx_pause; }; +/** + * enum ethtool_link_ext_state - link extended state + */ +enum ethtool_link_ext_state { + ETHTOOL_LINK_EXT_STATE_AUTONEG, + ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE, + ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH, + ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY, + ETHTOOL_LINK_EXT_STATE_NO_CABLE, + ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE, + ETHTOOL_LINK_EXT_STATE_EEPROM_ISSUE, + ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, + ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, + ETHTOOL_LINK_EXT_STATE_OVERHEAT, +}; + +/** + * enum ethtool_link_ext_substate_autoneg - more information in addition to + * ETHTOOL_LINK_EXT_STATE_AUTONEG. + */ +enum ethtool_link_ext_substate_autoneg { + ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1, + ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED, + ETHTOOL_LINK_EXT_SUBSTATE_AN_NEXT_PAGE_EXCHANGE_FAILED, + ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED_FORCE_MODE, + ETHTOOL_LINK_EXT_SUBSTATE_AN_FEC_MISMATCH_DURING_OVERRIDE, + ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD, +}; + +/** + * enum ethtool_link_ext_substate_link_training - more information in addition to + * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. + */ +enum ethtool_link_ext_substate_link_training { + ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1, + ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_INHIBIT_TIMEOUT, + ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_PARTNER_DID_NOT_SET_RECEIVER_READY, + ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT, +}; + +/** + * enum ethtool_link_ext_substate_logical_mismatch - more information in addition + * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. + */ +enum ethtool_link_ext_substate_link_logical_mismatch { + ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1, + ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_AM_LOCK, + ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_GET_ALIGN_STATUS, + ETHTOOL_LINK_EXT_SUBSTATE_LLM_FC_FEC_IS_NOT_LOCKED, + ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED, +}; + +/** + * enum ethtool_link_ext_substate_bad_signal_integrity - more information in + * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. + */ +enum ethtool_link_ext_substate_bad_signal_integrity { + ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, + ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, +}; + +/** + * enum ethtool_link_ext_substate_cable_issue - more information in + * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. + */ +enum ethtool_link_ext_substate_cable_issue { + ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1, + ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, +}; + #define ETH_GSTRING_LEN 32 /** diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 4dda5e4244a7..c12ce4df4b6b 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -236,6 +236,8 @@ enum { ETHTOOL_A_LINKSTATE_LINK, /* u8 */ ETHTOOL_A_LINKSTATE_SQI, /* u32 */ ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */ + ETHTOOL_A_LINKSTATE_EXT_STATE, /* u8 */ + ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, /* u8 */ /* add new constants above here */ __ETHTOOL_A_LINKSTATE_CNT, -- cgit v1.2.3 From 970471914c67b70df24def6b2a30cc42acbebded Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 16 Jun 2020 16:47:14 +0200 Subject: iommu: Allow page responses without PASID Some PCIe devices do not expect a PASID value in PRI Page Responses. If the "PRG Response PASID Required" bit in the PRI capability is zero, then the OS should not set the PASID field. Similarly on Arm SMMU, responses to stall events do not have a PASID. Currently iommu_page_response() systematically checks that the PASID in the page response corresponds to the one in the page request. This can't work with virtualization because a page response coming from a guest OS won't have a PASID if the passed-through device does not require one. Add a flag to page requests that declares whether the corresponding response needs to have a PASID. When this flag isn't set, allow page responses without PASID. Reported-by: Shameerali Kolothum Thodi Signed-off-by: Jean-Philippe Brucker Link: https://lore.kernel.org/r/20200616144712.748818-1-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/uapi/linux/iommu.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index e907b7091a46..c2b2caf9ed41 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -81,7 +81,10 @@ struct iommu_fault_unrecoverable { /** * struct iommu_fault_page_request - Page Request data * @flags: encodes whether the corresponding fields are valid and whether this - * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values) + * is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values). + * When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response + * must have the same PASID value as the page request. When it is clear, + * the page response should not have a PASID. * @pasid: Process Address Space ID * @grpid: Page Request Group Index * @perm: requested page permissions (IOMMU_FAULT_PERM_* values) @@ -92,6 +95,7 @@ struct iommu_fault_page_request { #define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) #define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) #define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) __u32 flags; __u32 pasid; __u32 grpid; -- cgit v1.2.3 From fa28dcb82a38f8e3993b0fae9106b1a80b59e4f0 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 29 Jun 2020 23:28:44 -0700 Subject: bpf: Introduce helper bpf_get_task_stack() Introduce helper bpf_get_task_stack(), which dumps stack trace of given task. This is different to bpf_get_stack(), which gets stack track of current task. One potential use case of bpf_get_task_stack() is to call it from bpf_iter__task and dump all /proc//stack to a seq_file. bpf_get_task_stack() uses stack_trace_save_tsk() instead of get_perf_callchain() for kernel stack. The benefit of this choice is that stack_trace_save_tsk() doesn't require changes in arch/. The downside of using stack_trace_save_tsk() is that stack_trace_save_tsk() dumps the stack trace to unsigned long array. For 32-bit systems, we need to translate it to u64 array. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200630062846.664389-3-songliubraving@fb.com --- include/uapi/linux/bpf.h | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0cb8ec948816..da9bf35a26f8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3285,6 +3285,39 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. * Return * *sk* if casting is valid, or NULL otherwise. + * + * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *task*, which is a valid + * pointer to struct task_struct. To store the stacktrace, the + * bpf program provides *buf* with a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_task_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3427,7 +3460,9 @@ union bpf_attr { FN(skc_to_tcp_sock), \ FN(skc_to_tcp_timewait_sock), \ FN(skc_to_tcp_request_sock), \ - FN(skc_to_udp6_sock), + FN(skc_to_udp6_sock), \ + FN(get_task_stack), \ + /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From 62e9dd177732843ae6c5b9d2ed61e7c9538fa276 Mon Sep 17 00:00:00 2001 From: Shyam Sundar Date: Tue, 30 Jun 2020 03:22:28 -0700 Subject: scsi: qla2xxx: Change in PUREX to handle FPIN ELS requests SAN Congestion Management generates ELS pkts whose size can vary and be > 64 bytes. Change the PUREX handling code to support non-standard ELS pkt size. Link: https://lore.kernel.org/r/20200630102229.29660-2-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Shyam Sundar Signed-off-by: Arun Easi Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen --- include/uapi/scsi/fc/fc_els.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/scsi/fc/fc_els.h b/include/uapi/scsi/fc/fc_els.h index 66318c44acd7..8c704e510e39 100644 --- a/include/uapi/scsi/fc/fc_els.h +++ b/include/uapi/scsi/fc/fc_els.h @@ -41,6 +41,7 @@ enum fc_els_cmd { ELS_REC = 0x13, /* read exchange concise */ ELS_SRR = 0x14, /* sequence retransmission request */ ELS_FPIN = 0x16, /* Fabric Performance Impact Notification */ + ELS_RDP = 0x18, /* Read Diagnostic Parameters */ ELS_RDF = 0x19, /* Register Diagnostic Functions */ ELS_PRLI = 0x20, /* process login */ ELS_PRLO = 0x21, /* process logout */ @@ -110,6 +111,7 @@ enum fc_els_cmd { [ELS_REC] = "REC", \ [ELS_SRR] = "SRR", \ [ELS_FPIN] = "FPIN", \ + [ELS_RDP] = "RDP", \ [ELS_RDF] = "RDF", \ [ELS_PRLI] = "PRLI", \ [ELS_PRLO] = "PRLO", \ -- cgit v1.2.3 From e4266b991fead8eb996688e82ff39f6cc59ef7dd Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Thu, 2 Jul 2020 10:13:05 +0200 Subject: bridge: uapi: mrp: Extend MRP attributes to get the status Add MRP attribute IFLA_BRIDGE_MRP_INFO to allow the userspace to get the current state of the MRP instances. This is a nested attribute that contains other attributes like, ring id, index of primary and secondary port, priority, ring state, ring role. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index caa6914a3e53..c114c1c2bd53 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -166,6 +166,7 @@ enum { IFLA_BRIDGE_MRP_RING_STATE, IFLA_BRIDGE_MRP_RING_ROLE, IFLA_BRIDGE_MRP_START_TEST, + IFLA_BRIDGE_MRP_INFO, __IFLA_BRIDGE_MRP_MAX, }; @@ -228,6 +229,22 @@ enum { #define IFLA_BRIDGE_MRP_START_TEST_MAX (__IFLA_BRIDGE_MRP_START_TEST_MAX - 1) +enum { + IFLA_BRIDGE_MRP_INFO_UNSPEC, + IFLA_BRIDGE_MRP_INFO_RING_ID, + IFLA_BRIDGE_MRP_INFO_P_IFINDEX, + IFLA_BRIDGE_MRP_INFO_S_IFINDEX, + IFLA_BRIDGE_MRP_INFO_PRIO, + IFLA_BRIDGE_MRP_INFO_RING_STATE, + IFLA_BRIDGE_MRP_INFO_RING_ROLE, + IFLA_BRIDGE_MRP_INFO_TEST_INTERVAL, + IFLA_BRIDGE_MRP_INFO_TEST_MAX_MISS, + IFLA_BRIDGE_MRP_INFO_TEST_MONITOR, + __IFLA_BRIDGE_MRP_INFO_MAX, +}; + +#define IFLA_BRIDGE_MRP_INFO_MAX (__IFLA_BRIDGE_MRP_INFO_MAX - 1) + struct br_mrp_instance { __u32 ring_id; __u32 p_ifindex; -- cgit v1.2.3 From 36a8e8e26542056bbd7eb5e047cadee30587d230 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Thu, 2 Jul 2020 10:13:07 +0200 Subject: bridge: Extend br_fill_ifinfo to return MPR status This patch extends the function br_fill_ifinfo to return also the MRP status for each instance on a bridge. It also adds a new filter RTEXT_FILTER_MRP to return the MRP status only when this is set, not to interfer with the vlans. The MRP status is return only on the bridge interfaces. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 879e64950a0a..9b814c92de12 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -778,6 +778,7 @@ enum { #define RTEXT_FILTER_BRVLAN (1 << 1) #define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) #define RTEXT_FILTER_SKIP_STATS (1 << 3) +#define RTEXT_FILTER_MRP (1 << 4) /* End of information exported to user level */ -- cgit v1.2.3 From 74cccc3d38438b346e40a4f8133cff3f0839ff84 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 30 Jun 2020 19:21:11 +0200 Subject: netfilter: nf_tables: add NFTA_CHAIN_ID attribute This netlink attribute allows you to refer to chains inside a transaction as an alternative to the name and the handle. The chain binding support requires this new chain ID approach. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 4565456c0ef4..477779595b78 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -196,6 +196,7 @@ enum nft_table_attributes { * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING) * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes) * @NFTA_CHAIN_FLAGS: chain flags + * @NFTA_CHAIN_ID: uniquely identifies a chain in a transaction (NLA_U32) */ enum nft_chain_attributes { NFTA_CHAIN_UNSPEC, @@ -209,6 +210,7 @@ enum nft_chain_attributes { NFTA_CHAIN_COUNTERS, NFTA_CHAIN_PAD, NFTA_CHAIN_FLAGS, + NFTA_CHAIN_ID, __NFTA_CHAIN_MAX }; #define NFTA_CHAIN_MAX (__NFTA_CHAIN_MAX - 1) -- cgit v1.2.3 From 837830a4b439bfeb86c70b0115c280377c84714b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 30 Jun 2020 19:21:16 +0200 Subject: netfilter: nf_tables: add NFTA_RULE_CHAIN_ID attribute This new netlink attribute allows you to add rules to chains by the chain ID. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 477779595b78..2304d1b7ba5e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -240,6 +240,7 @@ enum nft_rule_attributes { NFTA_RULE_PAD, NFTA_RULE_ID, NFTA_RULE_POSITION_ID, + NFTA_RULE_CHAIN_ID, __NFTA_RULE_MAX }; #define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1) -- cgit v1.2.3 From 51d70f181ff4e2c996ddf256af1efecd7d5864e5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 30 Jun 2020 19:21:21 +0200 Subject: netfilter: nf_tables: add NFTA_VERDICT_CHAIN_ID attribute This netlink attribute allows you to identify the chain to jump/goto by means of the chain ID. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 2304d1b7ba5e..683e75126d68 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -471,11 +471,13 @@ enum nft_data_attributes { * * @NFTA_VERDICT_CODE: nf_tables verdict (NLA_U32: enum nft_verdicts) * @NFTA_VERDICT_CHAIN: jump target chain name (NLA_STRING) + * @NFTA_VERDICT_CHAIN_ID: jump target chain ID (NLA_U32) */ enum nft_verdict_attributes { NFTA_VERDICT_UNSPEC, NFTA_VERDICT_CODE, NFTA_VERDICT_CHAIN, + NFTA_VERDICT_CHAIN_ID, __NFTA_VERDICT_MAX }; #define NFTA_VERDICT_MAX (__NFTA_VERDICT_MAX - 1) -- cgit v1.2.3 From 67c49de4ad862c567088c5119cf125e566f56e7f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 30 Jun 2020 19:21:25 +0200 Subject: netfilter: nf_tables: expose enum nft_chain_flags through UAPI This enum definition was never exposed through UAPI. Rename NFT_BASE_CHAIN to NFT_CHAIN_BASE for consistency. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 683e75126d68..2cf7cc3b50c1 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -184,6 +184,11 @@ enum nft_table_attributes { }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) +enum nft_chain_flags { + NFT_CHAIN_BASE = (1 << 0), + NFT_CHAIN_HW_OFFLOAD = (1 << 1), +}; + /** * enum nft_chain_attributes - nf_tables chain netlink attributes * -- cgit v1.2.3 From d0e2c7de92c7f2b3d355ad76b0bb9fc43d1beb87 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 30 Jun 2020 19:21:36 +0200 Subject: netfilter: nf_tables: add NFT_CHAIN_BINDING This new chain flag specifies that: * the kernel dynamically allocates the chain name, if no chain name is specified. * If the immediate expression that refers to this chain is removed, then this bound chain (and its content) is destroyed. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 2cf7cc3b50c1..e00b4ae6174e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -187,6 +187,7 @@ enum nft_table_attributes { enum nft_chain_flags { NFT_CHAIN_BASE = (1 << 0), NFT_CHAIN_HW_OFFLOAD = (1 << 1), + NFT_CHAIN_BINDING = (1 << 2), }; /** -- cgit v1.2.3 From c1f79a2eefdcc0aef5d7a911c27a3f75f1936ecd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 4 Jul 2020 02:51:28 +0200 Subject: netfilter: nf_tables: reject unsupported chain flags Bail out if userspace sends unsupported chain flags. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e00b4ae6174e..42f351c1f5c5 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -189,6 +189,9 @@ enum nft_chain_flags { NFT_CHAIN_HW_OFFLOAD = (1 << 1), NFT_CHAIN_BINDING = (1 << 2), }; +#define NFT_CHAIN_FLAGS (NFT_CHAIN_BASE | \ + NFT_CHAIN_HW_OFFLOAD | \ + NFT_CHAIN_BINDING) /** * enum nft_chain_attributes - nf_tables chain netlink attributes -- cgit v1.2.3 From ea1be1e59b19017e61aa357d524b743ba5602d3c Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 7 May 2020 20:03:35 +0800 Subject: serial: Remove duplicated macro definition of port type There exists the same macro definition of port type from 0 to 13 in include/uapi/linux/serial.h, remove these duplicated code in include/uapi/linux/serial_core.h which includes the former header. Acked-by: Jiri Slaby Signed-off-by: Tiezhu Yang Link: https://lore.kernel.org/r/1588853015-28392-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 8ec3dd742ea4..851b982f8c4b 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -26,20 +26,6 @@ /* * The type definitions. These are from Ted Ts'o's serial.h */ -#define PORT_UNKNOWN 0 -#define PORT_8250 1 -#define PORT_16450 2 -#define PORT_16550 3 -#define PORT_16550A 4 -#define PORT_CIRRUS 5 -#define PORT_16650 6 -#define PORT_16650V2 7 -#define PORT_16750 8 -#define PORT_STARTECH 9 -#define PORT_16C950 10 -#define PORT_16654 11 -#define PORT_16850 12 -#define PORT_RSA 13 #define PORT_NS16550A 14 #define PORT_XSCALE 15 #define PORT_RM9000 16 /* PMC-Sierra RM9xxx internal UART */ -- cgit v1.2.3 From 1c8fb1ea5a1dbd2159e78fa580aaffb001794cfa Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 30 Jun 2020 12:39:12 +0300 Subject: IB/uverbs: Expose UAPI to query ucontext Expose UAPI to query ucontext, this will let user space application that didn't allocate the ucontext but has access to by owning the matching command FD to retrieve the ucontext information. Link: https://lore.kernel.org/r/20200630093916.332097-4-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/ib_user_ioctl_cmds.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h index 4961d5e858eb..83b6e71ea216 100644 --- a/include/uapi/rdma/ib_user_ioctl_cmds.h +++ b/include/uapi/rdma/ib_user_ioctl_cmds.h @@ -69,6 +69,7 @@ enum uverbs_methods_device { UVERBS_METHOD_INFO_HANDLES, UVERBS_METHOD_QUERY_PORT, UVERBS_METHOD_GET_CONTEXT, + UVERBS_METHOD_QUERY_CONTEXT, }; enum uverbs_attrs_invoke_write_cmd_attr_ids { @@ -87,6 +88,11 @@ enum uverbs_attrs_get_context_attr_ids { UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT, }; +enum uverbs_attrs_query_context_attr_ids { + UVERBS_ATTR_QUERY_CONTEXT_NUM_COMP_VECTORS, + UVERBS_ATTR_QUERY_CONTEXT_CORE_SUPPORT, +}; + enum uverbs_attrs_create_cq_cmd_attr_ids { UVERBS_ATTR_CREATE_CQ_HANDLE, UVERBS_ATTR_CREATE_CQ_CQE, -- cgit v1.2.3 From 0fb556b2b58d6b8336c94379042bad2a8512af1a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 30 Jun 2020 12:39:14 +0300 Subject: RDMA/mlx5: Implement the query ucontext functionality Implement the query ucontext functionality by returning the original ucontext data as part of an extra mlx5 attribute that holds the driver UAPI response. Link: https://lore.kernel.org/r/20200630093916.332097-6-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index 8e316ef896b5..496309e8a856 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -228,6 +228,10 @@ enum mlx5_ib_flow_matcher_methods { MLX5_IB_METHOD_FLOW_MATCHER_DESTROY, }; +enum mlx5_ib_device_query_context_attrs { + MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT), +}; + #define MLX5_IB_DW_MATCH_PARAM 0x80 struct mlx5_ib_match_params { -- cgit v1.2.3 From 05f71ef9797454b9384c740b8acd0d02eca1d1bc Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 30 Jun 2020 12:39:15 +0300 Subject: RDMA/mlx5: Introduce UAPI to query PD attributes Introduce UAPI to query PD attributes, this can be used to retrieve PD attributes by having the PD handle of the created one and owning the command FD for the ucontxet. Link: https://lore.kernel.org/r/20200630093916.332097-7-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index 496309e8a856..b330e6eee626 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -290,4 +290,14 @@ enum mlx5_ib_create_flow_action_create_packet_reformat_attrs { MLX5_IB_ATTR_CREATE_PACKET_REFORMAT_DATA_BUF, }; +enum mlx5_ib_query_pd_attrs { + MLX5_IB_ATTR_QUERY_PD_HANDLE = (1U << UVERBS_ID_NS_SHIFT), + MLX5_IB_ATTR_QUERY_PD_RESP_PDN, +}; + +enum mlx5_ib_pd_methods { + MLX5_IB_METHOD_PD_QUERY = (1U << UVERBS_ID_NS_SHIFT), + +}; + #endif -- cgit v1.2.3 From 6c01e6b218aea09ec9947cbf88a4db97b4dd155c Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 30 Jun 2020 12:39:16 +0300 Subject: IB/uverbs: Expose UAPI to query MR Expose UAPI to query MR, this will let user space application that didn't allocate the MR but has access to by owning the matching command FD to retrieve its information. Link: https://lore.kernel.org/r/20200630093916.332097-8-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/ib_user_ioctl_cmds.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h index 83b6e71ea216..99dcabf61a71 100644 --- a/include/uapi/rdma/ib_user_ioctl_cmds.h +++ b/include/uapi/rdma/ib_user_ioctl_cmds.h @@ -248,6 +248,7 @@ enum uverbs_methods_mr { UVERBS_METHOD_DM_MR_REG, UVERBS_METHOD_MR_DESTROY, UVERBS_METHOD_ADVISE_MR, + UVERBS_METHOD_QUERY_MR, }; enum uverbs_attrs_mr_destroy_ids { @@ -261,6 +262,14 @@ enum uverbs_attrs_advise_mr_cmd_attr_ids { UVERBS_ATTR_ADVISE_MR_SGE_LIST, }; +enum uverbs_attrs_query_mr_cmd_attr_ids { + UVERBS_ATTR_QUERY_MR_HANDLE, + UVERBS_ATTR_QUERY_MR_RESP_LKEY, + UVERBS_ATTR_QUERY_MR_RESP_RKEY, + UVERBS_ATTR_QUERY_MR_RESP_LENGTH, + UVERBS_ATTR_QUERY_MR_RESP_IOVA, +}; + enum uverbs_attrs_create_counters_cmd_attr_ids { UVERBS_ATTR_CREATE_COUNTERS_HANDLE, }; -- cgit v1.2.3 From fe6a3d6521227e49857d0d6caabbdae3bd4aef89 Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Tue, 16 Jun 2020 12:08:45 +0800 Subject: fpga: dfl: afu: add interrupt support for port error reporting Error reporting interrupt is very useful to notify users that some errors are detected by the hardware. Once users are notified, they could query hardware logged error states, no need to continuously poll on these states. This patch adds interrupt support for port error reporting sub feature. It follows the common DFL interrupt notification and handling mechanism, implements two ioctl commands below for user to query number of irqs supported, and set/unset interrupt triggers. Ioctls: * DFL_FPGA_PORT_ERR_GET_IRQ_NUM get the number of irqs, which is used to determine whether/how many interrupts error reporting feature supports. * DFL_FPGA_PORT_ERR_SET_IRQ set/unset given eventfds as error interrupt triggers. Signed-off-by: Luwei Kang Signed-off-by: Wu Hao Signed-off-by: Xu Yilun Reviewed-by: Marcelo Tosatti Acked-by: Wu Hao Signed-off-by: Moritz Fischer --- include/uapi/linux/fpga-dfl.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/fpga-dfl.h b/include/uapi/linux/fpga-dfl.h index 7331350f3067..6c71c9d7e926 100644 --- a/include/uapi/linux/fpga-dfl.h +++ b/include/uapi/linux/fpga-dfl.h @@ -164,6 +164,29 @@ struct dfl_fpga_irq_set { __s32 evtfds[]; }; +/** + * DFL_FPGA_PORT_ERR_GET_IRQ_NUM - _IOR(DFL_FPGA_MAGIC, DFL_PORT_BASE + 5, + * __u32 num_irqs) + * + * Get the number of irqs supported by the fpga port error reporting private + * feature. Currently hardware supports up to 1 irq. + * Return: 0 on success, -errno on failure. + */ +#define DFL_FPGA_PORT_ERR_GET_IRQ_NUM _IOR(DFL_FPGA_MAGIC, \ + DFL_PORT_BASE + 5, __u32) + +/** + * DFL_FPGA_PORT_ERR_SET_IRQ - _IOW(DFL_FPGA_MAGIC, DFL_PORT_BASE + 6, + * struct dfl_fpga_irq_set) + * + * Set fpga port error reporting interrupt trigger if evtfds[n] is valid. + * Unset related interrupt trigger if evtfds[n] is a negative value. + * Return: 0 on success, -errno on failure. + */ +#define DFL_FPGA_PORT_ERR_SET_IRQ _IOW(DFL_FPGA_MAGIC, \ + DFL_PORT_BASE + 6, \ + struct dfl_fpga_irq_set) + /* IOCTLs for FME file descriptor */ /** -- cgit v1.2.3 From d43f20bae5173ba431526040c320c36fdd4f086d Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Tue, 16 Jun 2020 12:08:46 +0800 Subject: fpga: dfl: fme: add interrupt support for global error reporting Error reporting interrupt is very useful to notify users that some errors are detected by the hardware. Once users are notified, they could query hardware logged error states, no need to continuously poll on these states. This patch adds interrupt support for fme global error reporting sub feature. It follows the common DFL interrupt notification and handling mechanism. And it implements two ioctls below for user to query number of irqs supported, and set/unset interrupt triggers. Ioctls: * DFL_FPGA_FME_ERR_GET_IRQ_NUM get the number of irqs, which is used to determine whether/how many interrupts fme error reporting feature supports. * DFL_FPGA_FME_ERR_SET_IRQ set/unset given eventfds as fme error reporting interrupt triggers. Signed-off-by: Luwei Kang Signed-off-by: Wu Hao Signed-off-by: Xu Yilun Reviewed-by: Marcelo Tosatti Acked-by: Wu Hao Signed-off-by: Moritz Fischer --- include/uapi/linux/fpga-dfl.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/fpga-dfl.h b/include/uapi/linux/fpga-dfl.h index 6c71c9d7e926..b6495ea412ec 100644 --- a/include/uapi/linux/fpga-dfl.h +++ b/include/uapi/linux/fpga-dfl.h @@ -230,4 +230,27 @@ struct dfl_fpga_fme_port_pr { */ #define DFL_FPGA_FME_PORT_ASSIGN _IOW(DFL_FPGA_MAGIC, DFL_FME_BASE + 2, int) +/** + * DFL_FPGA_FME_ERR_GET_IRQ_NUM - _IOR(DFL_FPGA_MAGIC, DFL_FME_BASE + 3, + * __u32 num_irqs) + * + * Get the number of irqs supported by the fpga fme error reporting private + * feature. Currently hardware supports up to 1 irq. + * Return: 0 on success, -errno on failure. + */ +#define DFL_FPGA_FME_ERR_GET_IRQ_NUM _IOR(DFL_FPGA_MAGIC, \ + DFL_FME_BASE + 3, __u32) + +/** + * DFL_FPGA_FME_ERR_SET_IRQ - _IOW(DFL_FPGA_MAGIC, DFL_FME_BASE + 4, + * struct dfl_fpga_irq_set) + * + * Set fpga fme error reporting interrupt trigger if evtfds[n] is valid. + * Unset related interrupt trigger if evtfds[n] is a negative value. + * Return: 0 on success, -errno on failure. + */ +#define DFL_FPGA_FME_ERR_SET_IRQ _IOW(DFL_FPGA_MAGIC, \ + DFL_FME_BASE + 4, \ + struct dfl_fpga_irq_set) + #endif /* _UAPI_LINUX_FPGA_DFL_H */ -- cgit v1.2.3 From 09d86150141955ba1b3d7cbef23785f4996e4d6f Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Tue, 16 Jun 2020 12:08:47 +0800 Subject: fpga: dfl: afu: add AFU interrupt support AFU (Accelerated Function Unit) is dynamic region of the DFL based FPGA, and always defined by users. Some DFL based FPGA cards allow users to implement their own interrupts in AFU. In order to support this, hardware implements a new UINT (AFU Interrupt) private feature with related capability register which describes the number of supported AFU interrupts as well as the local index of the interrupts for software enumeration, and from software side, driver follows the common DFL interrupt notification and handling mechanism, and it implements two ioctls below for user to query number of irqs supported and set/unset interrupt triggers. Ioctls: * DFL_FPGA_PORT_UINT_GET_IRQ_NUM get the number of irqs, which is used to determine how many interrupts UINT feature supports. * DFL_FPGA_PORT_UINT_SET_IRQ set/unset eventfds as AFU interrupt triggers. Signed-off-by: Luwei Kang Signed-off-by: Wu Hao Signed-off-by: Xu Yilun Reviewed-by: Marcelo Tosatti Acked-by: Wu Hao Signed-off-by: Moritz Fischer --- include/uapi/linux/fpga-dfl.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/fpga-dfl.h b/include/uapi/linux/fpga-dfl.h index b6495ea412ec..1621b077bf21 100644 --- a/include/uapi/linux/fpga-dfl.h +++ b/include/uapi/linux/fpga-dfl.h @@ -187,6 +187,29 @@ struct dfl_fpga_irq_set { DFL_PORT_BASE + 6, \ struct dfl_fpga_irq_set) +/** + * DFL_FPGA_PORT_UINT_GET_IRQ_NUM - _IOR(DFL_FPGA_MAGIC, DFL_PORT_BASE + 7, + * __u32 num_irqs) + * + * Get the number of irqs supported by the fpga AFU interrupt private + * feature. + * Return: 0 on success, -errno on failure. + */ +#define DFL_FPGA_PORT_UINT_GET_IRQ_NUM _IOR(DFL_FPGA_MAGIC, \ + DFL_PORT_BASE + 7, __u32) + +/** + * DFL_FPGA_PORT_UINT_SET_IRQ - _IOW(DFL_FPGA_MAGIC, DFL_PORT_BASE + 8, + * struct dfl_fpga_irq_set) + * + * Set fpga AFU interrupt trigger if evtfds[n] is valid. + * Unset related interrupt trigger if evtfds[n] is a negative value. + * Return: 0 on success, -errno on failure. + */ +#define DFL_FPGA_PORT_UINT_SET_IRQ _IOW(DFL_FPGA_MAGIC, \ + DFL_PORT_BASE + 8, \ + struct dfl_fpga_irq_set) + /* IOCTLs for FME file descriptor */ /** -- cgit v1.2.3 From 1ce50e7d408ef2bdc8ca021363fd46d1b8bfad00 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 6 Jul 2020 12:55:37 +0200 Subject: thermal: core: genetlink support for events/cmd/sampling Initially the thermal framework had a very simple notification mechanism to send generic netlink messages to the userspace. The notification function was never called from anywhere and the corresponding dead code was removed. It was probably a first attempt to introduce the netlink notification. At LPC2018, the presentation "Linux thermal: User kernel interface", proposed to create the notifications to the userspace via a kfifo. The advantage of the kfifo is the performance. It is usually used from a 1:1 communication channel where a driver captures data and sends it as fast as possible to a userspace process. The drawback is that only one process uses the notification channel exclusively, thus no other process is allowed to use the channel to get temperature or notifications. This patch defines a generic netlink API to discover the current thermal setup and adds event notifications as well as temperature sampling. As any genetlink protocol, it can evolve and the versioning allows to keep the backward compatibility. In order to prevent the user from getting flooded with data on a single channel, there are two multicast channels, one for the temperature sampling when the thermal zone is updated and another one for the events, so the user can get the events only without the thermal zone temperature sampling. Also, a list of commands to discover the thermal setup is added and can be extended when needed. Reviewed-by: Amit Kucheria Signed-off-by: Daniel Lezcano Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20200706105538.2159-3-daniel.lezcano@linaro.org --- include/uapi/linux/thermal.h | 89 +++++++++++++++++++++++++++++++++++--------- 1 file changed, 72 insertions(+), 17 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index 96218378dda8..c105054cbb57 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -4,31 +4,86 @@ #define THERMAL_NAME_LENGTH 20 -/* Adding event notification support elements */ -#define THERMAL_GENL_FAMILY_NAME "thermal_event" -#define THERMAL_GENL_VERSION 0x01 -#define THERMAL_GENL_MCAST_GROUP_NAME "thermal_mc_grp" - -/* Events supported by Thermal Netlink */ -enum events { - THERMAL_AUX0, - THERMAL_AUX1, - THERMAL_CRITICAL, - THERMAL_DEV_FAULT, +enum thermal_device_mode { + THERMAL_DEVICE_DISABLED = 0, + THERMAL_DEVICE_ENABLED, +}; + +enum thermal_trip_type { + THERMAL_TRIP_ACTIVE = 0, + THERMAL_TRIP_PASSIVE, + THERMAL_TRIP_HOT, + THERMAL_TRIP_CRITICAL, }; -/* attributes of thermal_genl_family */ -enum { +/* Adding event notification support elements */ +#define THERMAL_GENL_FAMILY_NAME "thermal" +#define THERMAL_GENL_VERSION 0x01 +#define THERMAL_GENL_SAMPLING_GROUP_NAME "sampling" +#define THERMAL_GENL_EVENT_GROUP_NAME "event" + +/* Attributes of thermal_genl_family */ +enum thermal_genl_attr { THERMAL_GENL_ATTR_UNSPEC, - THERMAL_GENL_ATTR_EVENT, + THERMAL_GENL_ATTR_TZ, + THERMAL_GENL_ATTR_TZ_ID, + THERMAL_GENL_ATTR_TZ_TEMP, + THERMAL_GENL_ATTR_TZ_TRIP, + THERMAL_GENL_ATTR_TZ_TRIP_ID, + THERMAL_GENL_ATTR_TZ_TRIP_TYPE, + THERMAL_GENL_ATTR_TZ_TRIP_TEMP, + THERMAL_GENL_ATTR_TZ_TRIP_HYST, + THERMAL_GENL_ATTR_TZ_MODE, + THERMAL_GENL_ATTR_TZ_NAME, + THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT, + THERMAL_GENL_ATTR_TZ_GOV, + THERMAL_GENL_ATTR_TZ_GOV_NAME, + THERMAL_GENL_ATTR_CDEV, + THERMAL_GENL_ATTR_CDEV_ID, + THERMAL_GENL_ATTR_CDEV_CUR_STATE, + THERMAL_GENL_ATTR_CDEV_MAX_STATE, + THERMAL_GENL_ATTR_CDEV_NAME, + THERMAL_GENL_ATTR_GOV_NAME, + __THERMAL_GENL_ATTR_MAX, }; #define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1) -/* commands supported by the thermal_genl_family */ -enum { +enum thermal_genl_sampling { + THERMAL_GENL_SAMPLING_TEMP, + __THERMAL_GENL_SAMPLING_MAX, +}; +#define THERMAL_GENL_SAMPLING_MAX (__THERMAL_GENL_SAMPLING_MAX - 1) + +/* Events of thermal_genl_family */ +enum thermal_genl_event { + THERMAL_GENL_EVENT_UNSPEC, + THERMAL_GENL_EVENT_TZ_CREATE, /* Thermal zone creation */ + THERMAL_GENL_EVENT_TZ_DELETE, /* Thermal zone deletion */ + THERMAL_GENL_EVENT_TZ_DISABLE, /* Thermal zone disabed */ + THERMAL_GENL_EVENT_TZ_ENABLE, /* Thermal zone enabled */ + THERMAL_GENL_EVENT_TZ_TRIP_UP, /* Trip point crossed the way up */ + THERMAL_GENL_EVENT_TZ_TRIP_DOWN, /* Trip point crossed the way down */ + THERMAL_GENL_EVENT_TZ_TRIP_CHANGE, /* Trip point changed */ + THERMAL_GENL_EVENT_TZ_TRIP_ADD, /* Trip point added */ + THERMAL_GENL_EVENT_TZ_TRIP_DELETE, /* Trip point deleted */ + THERMAL_GENL_EVENT_CDEV_ADD, /* Cdev bound to the thermal zone */ + THERMAL_GENL_EVENT_CDEV_DELETE, /* Cdev unbound */ + THERMAL_GENL_EVENT_CDEV_STATE_UPDATE, /* Cdev state updated */ + THERMAL_GENL_EVENT_TZ_GOV_CHANGE, /* Governor policy changed */ + __THERMAL_GENL_EVENT_MAX, +}; +#define THERMAL_GENL_EVENT_MAX (__THERMAL_GENL_EVENT_MAX - 1) + +/* Commands supported by the thermal_genl_family */ +enum thermal_genl_cmd { THERMAL_GENL_CMD_UNSPEC, - THERMAL_GENL_CMD_EVENT, + THERMAL_GENL_CMD_TZ_GET_ID, /* List of thermal zones id */ + THERMAL_GENL_CMD_TZ_GET_TRIP, /* List of thermal trips */ + THERMAL_GENL_CMD_TZ_GET_TEMP, /* Get the thermal zone temperature */ + THERMAL_GENL_CMD_TZ_GET_GOV, /* Get the thermal zone governor */ + THERMAL_GENL_CMD_TZ_GET_MODE, /* Get the thermal zone mode */ + THERMAL_GENL_CMD_CDEV_GET, /* List of cdev id */ __THERMAL_GENL_CMD_MAX, }; #define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1) -- cgit v1.2.3 From f5836749c9c04a10decd2742845ad4870965fdef Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 6 Jul 2020 16:01:25 -0700 Subject: bpf: Add BPF_CGROUP_INET_SOCK_RELEASE hook Sometimes it's handy to know when the socket gets freed. In particular, we'd like to try to use a smarter allocation of ports for bpf_bind and explore the possibility of limiting the number of SOCK_DGRAM sockets the process can have. Implement BPF_CGROUP_INET_SOCK_RELEASE hook that triggers on inet socket release. It triggers only for userspace sockets (not in-kernel ones) and therefore has the same semantics as the existing BPF_CGROUP_INET_SOCK_CREATE. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200706230128.4073544-2-sdf@google.com --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index da9bf35a26f8..548a749aebb3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -226,6 +226,7 @@ enum bpf_attach_type { BPF_CGROUP_INET4_GETSOCKNAME, BPF_CGROUP_INET6_GETSOCKNAME, BPF_XDP_DEVMAP, + BPF_CGROUP_INET_SOCK_RELEASE, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From 82394db7383d33641f3f565bd79792fb41b1741f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Mon, 29 Jun 2020 12:06:37 -0700 Subject: block: add capacity field to zone descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the zoned storage model, the sectors within a zone are typically all writeable. With the introduction of the Zoned Namespace (ZNS) Command Set in the NVM Express organization, the model was extended to have a specific writeable capacity. Extend the zone descriptor data structure with a zone capacity field to indicate to the user how many sectors in a zone are writeable. Introduce backward compatibility in the zone report ioctl by extending the zone report header data structure with a flags field to indicate if the capacity field is available. Reviewed-by: Jens Axboe Reviewed-by: Javier González Reviewed-by: Chaitanya Kulkarni Reviewed-by: Himanshu Madhani Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Daniel Wagner Signed-off-by: Matias Bjørling Signed-off-by: Christoph Hellwig --- include/uapi/linux/blkzoned.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 0cdef67135f0..42c3366cc25f 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -73,6 +73,15 @@ enum blk_zone_cond { BLK_ZONE_COND_OFFLINE = 0xF, }; +/** + * enum blk_zone_report_flags - Feature flags of reported zone descriptors. + * + * @BLK_ZONE_REP_CAPACITY: Zone descriptor has capacity field. + */ +enum blk_zone_report_flags { + BLK_ZONE_REP_CAPACITY = (1 << 0), +}; + /** * struct blk_zone - Zone descriptor for BLKREPORTZONE ioctl. * @@ -99,7 +108,9 @@ struct blk_zone { __u8 cond; /* Zone condition */ __u8 non_seq; /* Non-sequential write resources active */ __u8 reset; /* Reset write pointer recommended */ - __u8 reserved[36]; + __u8 resv[4]; + __u64 capacity; /* Zone capacity in number of sectors */ + __u8 reserved[24]; }; /** @@ -115,7 +126,7 @@ struct blk_zone { struct blk_zone_report { __u64 sector; __u32 nr_zones; - __u8 reserved[4]; + __u32 flags; struct blk_zone zones[0]; }; -- cgit v1.2.3 From 1aa561b1a4c0ae2a9a9b9c21a84b5ca66b4775d8 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Wed, 3 Jun 2020 16:56:21 -0700 Subject: kvm: x86: Add "last CPU" to some KVM_EXIT information More often than not, a failed VM-entry in an x86 production environment is induced by a defective CPU. To help identify the bad hardware, include the id of the last logical CPU to run a vCPU in the information provided to userspace on a KVM exit for failed VM-entry or for KVM internal errors not associated with emulation. The presence of this additional information is indicated by a new capability, KVM_CAP_LAST_CPU. Signed-off-by: Jim Mattson Reviewed-by: Oliver Upton Reviewed-by: Peter Shier Message-Id: <20200603235623.245638-5-jmattson@google.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4fdf30316582..ff9b335620d0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -289,6 +289,7 @@ struct kvm_run { /* KVM_EXIT_FAIL_ENTRY */ struct { __u64 hardware_entry_failure_reason; + __u32 cpu; } fail_entry; /* KVM_EXIT_EXCEPTION */ struct { @@ -1031,6 +1032,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_SECURE_GUEST 181 #define KVM_CAP_HALT_POLL 182 #define KVM_CAP_ASYNC_PF_INT 183 +#define KVM_CAP_LAST_CPU 184 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 065e0d42a0a728d7f6c2aec7c9f3e5dc7b715394 Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Mon, 6 Jul 2020 20:42:32 -0700 Subject: ethtool: Add support for 100Gbps per lane link modes Define 100G, 200G and 400G link modes using 100Gbps per lane LR, ER and FR are defined as a single link mode because they are using same technology and by design are fully interoperable. EEPROM content indicates if the module is LR, ER, or FR, and the user space ethtool decoder is planned to support decoding these modes in the EEPROM. Signed-off-by: Meir Lichtinger CC: Andrew Lunn Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index d1413538ef30..60856e0f9618 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1600,6 +1600,21 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT = 72, ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT = 73, ETHTOOL_LINK_MODE_FEC_LLRS_BIT = 74, + ETHTOOL_LINK_MODE_100000baseKR_Full_BIT = 75, + ETHTOOL_LINK_MODE_100000baseSR_Full_BIT = 76, + ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT = 77, + ETHTOOL_LINK_MODE_100000baseCR_Full_BIT = 78, + ETHTOOL_LINK_MODE_100000baseDR_Full_BIT = 79, + ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT = 80, + ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT = 81, + ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT = 82, + ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT = 83, + ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT = 84, + ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT = 85, + ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT = 86, + ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87, + ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT = 88, + ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; -- cgit v1.2.3 From 3f935c75eb52dd968351dba824adf466fb9c9429 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Jul 2020 15:12:39 +0200 Subject: inet_diag: support for wider protocol numbers After commit bf9765145b85 ("sock: Make sk_protocol a 16-bit value") the current size of 'sdiag_protocol' is not sufficient to represent the possible protocol values. This change introduces a new inet diag request attribute to let user space specify the relevant protocol number using u32 values. The attribute is parsed by inet diag core on get/dump command and the extended protocol value, if available, is preferred to 'sdiag_protocol' to lookup the diag handler. The parse attributed are exposed to all the diag handlers via the cb->data. Note that inet_diag_dump_one_icsk() is left unmodified, as it will not be used by protocol using the extended attribute. Suggested-by: David S. Miller Co-developed-by: Christoph Paasch Signed-off-by: Christoph Paasch Acked-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index e6f183ee8417..5ba122c1949a 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -65,6 +65,7 @@ enum { INET_DIAG_REQ_NONE, INET_DIAG_REQ_BYTECODE, INET_DIAG_REQ_SK_BPF_STORAGES, + INET_DIAG_REQ_PROTOCOL, __INET_DIAG_REQ_MAX, }; -- cgit v1.2.3 From ac3b45f6095452a9731f8825be1513d326dbfa15 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 9 Jul 2020 15:12:41 +0200 Subject: mptcp: add MPTCP socket diag interface exposes basic inet socket attribute, plus some MPTCP socket fields comprising PM status and MPTCP-level sequence numbers. Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 5f2c77082d9e..9762660df741 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -86,4 +86,21 @@ enum { __MPTCP_PM_CMD_AFTER_LAST }; +#define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) +#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) + +struct mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; +}; + #endif /* _UAPI_MPTCP_H */ -- cgit v1.2.3 From a21cf0a8330bba60e44ca6c99e1591042f336ff5 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 9 Jul 2020 16:18:18 +0300 Subject: devlink: Add a new devlink port lanes attribute and pass to netlink Add a new devlink port attribute that indicates the port's number of lanes. Drivers are expected to set it via devlink_port_attrs_set(), before registering the port. The attribute is not passed to user space in case the number of lanes is invalid (0). Signed-off-by: Danielle Ratson Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 87c83a82991b..f741ab8d9cf0 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -455,6 +455,8 @@ enum devlink_attr { DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, /* string */ + DEVLINK_ATTR_PORT_LANES, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From a0f49b54865273c895be3826d6d59cbc5ad725c2 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 9 Jul 2020 16:18:20 +0300 Subject: devlink: Add a new devlink port split ability attribute and pass to netlink Add a new attribute that indicates the split ability of devlink port. Drivers are expected to set it via devlink_port_attrs_set(), before registering the port. Signed-off-by: Danielle Ratson Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index f741ab8d9cf0..cfef4245ea5a 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -456,6 +456,7 @@ enum devlink_attr { DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, /* string */ DEVLINK_ATTR_PORT_LANES, /* u32 */ + DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From 631beddc5466731b048263a4a9d3d67150e72f8d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 9 Jul 2020 14:08:55 +0200 Subject: virt: vbox: Add support for the new VBG_IOCTL_ACQUIRE_GUEST_CAPABILITIES ioctl Add support for the new VBG_IOCTL_ACQUIRE_GUEST_CAPABILITIES ioctl, this is necessary for automatic resizing of the guest resolution to match the VM-window size to work with the new VMSVGA virtual GPU which is now the new default in VirtualBox. BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1789545 Acked-by: Arnd Bergmann Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20200709120858.63928-6-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/vboxguest.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vboxguest.h b/include/uapi/linux/vboxguest.h index f79d7abe27db..15125f6ec60d 100644 --- a/include/uapi/linux/vboxguest.h +++ b/include/uapi/linux/vboxguest.h @@ -257,6 +257,30 @@ VMMDEV_ASSERT_SIZE(vbg_ioctl_change_filter, 24 + 8); _IOWR('V', 12, struct vbg_ioctl_change_filter) +/** VBG_IOCTL_ACQUIRE_GUEST_CAPABILITIES data structure. */ +struct vbg_ioctl_acquire_guest_caps { + /** The header. */ + struct vbg_ioctl_hdr hdr; + union { + struct { + /** Flags (VBGL_IOC_AGC_FLAGS_XXX). */ + __u32 flags; + /** Capabilities to set (VMMDEV_GUEST_SUPPORTS_XXX). */ + __u32 or_mask; + /** Capabilities to drop (VMMDEV_GUEST_SUPPORTS_XXX). */ + __u32 not_mask; + } in; + } u; +}; +VMMDEV_ASSERT_SIZE(vbg_ioctl_acquire_guest_caps, 24 + 12); + +#define VBGL_IOC_AGC_FLAGS_CONFIG_ACQUIRE_MODE 0x00000001 +#define VBGL_IOC_AGC_FLAGS_VALID_MASK 0x00000001 + +#define VBG_IOCTL_ACQUIRE_GUEST_CAPABILITIES \ + _IOWR('V', 13, struct vbg_ioctl_acquire_guest_caps) + + /** VBG_IOCTL_CHANGE_GUEST_CAPABILITIES data structure. */ struct vbg_ioctl_set_guest_caps { /** The header. */ -- cgit v1.2.3 From 316b0035402f05fe9e9e5334d1ff65dae285cb7c Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 9 Jul 2020 14:08:56 +0200 Subject: virt: vbox: Add a few new vmmdev request types to the userspace whitelist Upstream VirtualBox has defined and is using a few new request types for vmmdev requests passed through /dev/vboxguest to the hypervisor. Add the defines for these to vbox_vmmdev_types.h and add add them to the whitelists of vmmdev requests which userspace is allowed to make. BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1789545 Acked-by: Arnd Bergmann Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20200709120858.63928-7-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/vbox_vmmdev_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vbox_vmmdev_types.h b/include/uapi/linux/vbox_vmmdev_types.h index c27289fd619a..f8a8d6b3c521 100644 --- a/include/uapi/linux/vbox_vmmdev_types.h +++ b/include/uapi/linux/vbox_vmmdev_types.h @@ -63,6 +63,7 @@ enum vmmdev_request_type { VMMDEVREQ_SET_GUEST_CAPABILITIES = 56, VMMDEVREQ_VIDEMODE_SUPPORTED2 = 57, /* since version 3.2.0 */ VMMDEVREQ_GET_DISPLAY_CHANGE_REQEX = 80, /* since version 4.2.4 */ + VMMDEVREQ_GET_DISPLAY_CHANGE_REQ_MULTI = 81, VMMDEVREQ_HGCM_CONNECT = 60, VMMDEVREQ_HGCM_DISCONNECT = 61, VMMDEVREQ_HGCM_CALL32 = 62, @@ -92,6 +93,8 @@ enum vmmdev_request_type { VMMDEVREQ_WRITE_COREDUMP = 218, VMMDEVREQ_GUEST_HEARTBEAT = 219, VMMDEVREQ_HEARTBEAT_CONFIGURE = 220, + VMMDEVREQ_NT_BUG_CHECK = 221, + VMMDEVREQ_VIDEO_UPDATE_MONITOR_POSITIONS = 222, /* Ensure the enum is a 32 bit data-type */ VMMDEVREQ_SIZEHACK = 0x7fffffff }; -- cgit v1.2.3 From 04aaca197f16aff608e19ee98b1e55f535d746be Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 17 Jun 2020 17:33:13 +0900 Subject: char: raw: do not leak CONFIG_MAX_RAW_DEVS to userspace include/uapi/linux/raw.h leaks CONFIG_MAX_RAW_DEVS to userspace. Userspace programs cannot use MAX_RAW_MINORS since CONFIG_MAX_RAW_DEVS is not available anyway. Remove the MAX_RAW_MINORS definition from the exported header, and use CONFIG_MAX_RAW_DEVS in drivers/char/raw.c While I was here, I converted printk(KERN_WARNING ...) to pr_warn(...) and stretched the warning message. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20200617083313.183184-1-masahiroy@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/raw.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/raw.h b/include/uapi/linux/raw.h index dc96dda479d6..47874919d0b9 100644 --- a/include/uapi/linux/raw.h +++ b/include/uapi/linux/raw.h @@ -14,6 +14,4 @@ struct raw_config_request __u64 block_minor; }; -#define MAX_RAW_MINORS CONFIG_MAX_RAW_DEVS - #endif /* __LINUX_RAW_H */ -- cgit v1.2.3 From 7c97f3aded10aa86fc1944341288434117e9c926 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Thu, 2 Jul 2020 11:29:31 +0300 Subject: RDMA/counter: Add PID category support in auto mode With the "PID" category QPs have same PID will be bound to same counter; If this category is not set then QPs have different PIDs will be bound to same counter. This is implemented for 2 reasons: 1. The counter is a limited resource, while there may be dozens of applications, each of which creates several types of QPs, which means it may doesn't have enough counter. 2. The system administrator needs all QPs created by all applications with same type bound to one counter. The counter name and PID is only make sense when "PID" category are configured. This category can also be used in combine with others, e.g. QP type. Link: https://lore.kernel.org/r/20200702082933.424537-2-leon@kernel.org Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/rdma_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 3826143d420d..d2f5b8396243 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -569,5 +569,6 @@ enum rdma_nl_counter_mode { */ enum rdma_nl_counter_mask { RDMA_COUNTER_MASK_QP_TYPE = 1, + RDMA_COUNTER_MASK_PID = 1 << 1, }; #endif /* _UAPI_RDMA_NETLINK_H */ -- cgit v1.2.3 From c7d759eb7b12f91a25f4d3cd03ff5209046ddfc2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jul 2020 17:42:47 -0700 Subject: ethtool: add tunnel info interface Add an interface to report offloaded UDP ports via ethtool netlink. Now that core takes care of tracking which UDP tunnel ports the NICs are aware of we can quite easily export this information out to user space. The responsibility of writing the netlink dumps is split between ethtool code and udp_tunnel_nic.c - since udp_tunnel module may not always be loaded, yet we should always report the capabilities of the NIC. $ ethtool --show-tunnels eth0 Tunnel information for eth0: UDP port table 0: Size: 4 Types: vxlan No entries UDP port table 1: Size: 4 Types: geneve, vxlan-gpe Entries (1): port 1230, vxlan-gpe v4: - back to v2, build fix is now directly in udp_tunnel.h v3: - don't compile ETHTOOL_MSG_TUNNEL_INFO_GET in if CONFIG_INET not set. v2: - fix string set count, - reorder enums in the uAPI, - fix type of ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES to bitset in docs and comments. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 2 ++ include/uapi/linux/ethtool_netlink.h | 55 ++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 60856e0f9618..b4f2d134e713 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -669,6 +669,7 @@ enum ethtool_link_ext_substate_cable_issue { * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags * @ETH_SS_TS_TX_TYPES: timestamping Tx types * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters + * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -686,6 +687,7 @@ enum ethtool_stringset { ETH_SS_SOF_TIMESTAMPING, ETH_SS_TS_TX_TYPES, ETH_SS_TS_RX_FILTERS, + ETH_SS_UDP_TUNNEL_TYPES, /* add new constants above here */ ETH_SS_COUNT diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index c12ce4df4b6b..5dcd24cb33ea 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -41,6 +41,7 @@ enum { ETHTOOL_MSG_TSINFO_GET, ETHTOOL_MSG_CABLE_TEST_ACT, ETHTOOL_MSG_CABLE_TEST_TDR_ACT, + ETHTOOL_MSG_TUNNEL_INFO_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -556,6 +557,60 @@ enum { ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX = __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT - 1 }; +/* TUNNEL INFO */ + +enum { + ETHTOOL_UDP_TUNNEL_TYPE_VXLAN, + ETHTOOL_UDP_TUNNEL_TYPE_GENEVE, + ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE, + + __ETHTOOL_UDP_TUNNEL_TYPE_CNT +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_ENTRY_UNSPEC, + + ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, /* be16 */ + ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT, + ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX = (__ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_TABLE_UNSPEC, + + ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE, /* u32 */ + ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES, /* bitset */ + ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY, /* nest - _UDP_ENTRY_* */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_UDP_TABLE_CNT, + ETHTOOL_A_TUNNEL_UDP_TABLE_MAX = (__ETHTOOL_A_TUNNEL_UDP_TABLE_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_UNSPEC, + + ETHTOOL_A_TUNNEL_UDP_TABLE, /* nest - _UDP_TABLE_* */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_UDP_CNT, + ETHTOOL_A_TUNNEL_UDP_MAX = (__ETHTOOL_A_TUNNEL_UDP_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_INFO_UNSPEC, + ETHTOOL_A_TUNNEL_INFO_HEADER, /* nest - _A_HEADER_* */ + + ETHTOOL_A_TUNNEL_INFO_UDP_PORTS, /* nest - _UDP_TABLE */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_INFO_CNT, + ETHTOOL_A_TUNNEL_INFO_MAX = (__ETHTOOL_A_TUNNEL_INFO_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 -- cgit v1.2.3 From 3edd68399dc155b80335244c8c2673eaa652931a Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Fri, 10 Jul 2020 17:48:11 +0200 Subject: KVM: x86: Add a capability for GUEST_MAXPHYADDR < HOST_MAXPHYADDR support This patch adds a new capability KVM_CAP_SMALLER_MAXPHYADDR which allows userspace to query if the underlying architecture would support GUEST_MAXPHYADDR < HOST_MAXPHYADDR and hence act accordingly (e.g. qemu can decide if it should warn for -cpu ..,phys-bits=X) The complications in this patch are due to unexpected (but documented) behaviour we see with NPF vmexit handling in AMD processor. If SVM is modified to add guest physical address checks in the NPF and guest #PF paths, we see the followning error multiple times in the 'access' test in kvm-unit-tests: test pte.p pte.36 pde.p: FAIL: pte 2000021 expected 2000001 Dump mapping: address: 0x123400000000 ------L4: 24c3027 ------L3: 24c4027 ------L2: 24c5021 ------L1: 1002000021 This is because the PTE's accessed bit is set by the CPU hardware before the NPF vmexit. This is handled completely by hardware and cannot be fixed in software. Therefore, availability of the new capability depends on a boolean variable allow_smaller_maxphyaddr which is set individually by VMX and SVM init routines. On VMX it's always set to true, on SVM it's only set to true when NPT is not enabled. CC: Tom Lendacky CC: Babu Moger Signed-off-by: Mohammed Gamal Message-Id: <20200710154811.418214-10-mgamal@redhat.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ff9b335620d0..2c73dcfb3dbb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1033,6 +1033,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_HALT_POLL 182 #define KVM_CAP_ASYNC_PF_INT 183 #define KVM_CAP_LAST_CPU 184 +#define KVM_CAP_SMALLER_MAXPHYADDR 185 + #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 47e33c05f9f07cac3de833e531bcac9ae052c7ca Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 15 Jun 2020 15:42:46 -0700 Subject: seccomp: Fix ioctl number for SECCOMP_IOCTL_NOTIF_ID_VALID When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced it had the wrong direction flag set. While this isn't a big deal as nothing currently enforces these bits in the kernel, it should be defined correctly. Fix the define and provide support for the old command until it is no longer needed for backward compatibility. Fixes: 6a21cc50f0c7 ("seccomp: add a return code to trap to userspace") Signed-off-by: Kees Cook --- include/uapi/linux/seccomp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index c1735455bc53..965290f7dcc2 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -123,5 +123,6 @@ struct seccomp_notif_resp { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) + #endif /* _UAPI_LINUX_SECCOMP_H */ -- cgit v1.2.3 From 21249616f02dc3f4c5efc3b3e9ba48e428b0131c Mon Sep 17 00:00:00 2001 From: Kent Gibson Date: Wed, 8 Jul 2020 12:15:57 +0800 Subject: gpio: uapi: fix misplaced comment line The second line of the description for event_type is before the first. Move it to after the first line. Signed-off-by: Kent Gibson Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 0206383c0383..9c27cecf406f 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -71,8 +71,8 @@ enum { * of a GPIO line * @info: updated line information * @timestamp: estimate of time of status change occurrence, in nanoseconds - * and GPIOLINE_CHANGED_CONFIG * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED + * and GPIOLINE_CHANGED_CONFIG * * Note: struct gpioline_info embedded here has 32-bit alignment on its own, * but it works fine with 64-bit alignment too. With its 72 byte size, we can -- cgit v1.2.3 From c1326210477ecc06c53221f0005c64419aba30d6 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:20 +0000 Subject: nfs,nfsd: NFSv4.2 extended attribute protocol definitions Add definitions for the new operations, errors and flags as defined in RFC 8276 (File System Extended Attributes in NFSv4). Signed-off-by: Frank van der Linden Signed-off-by: Chuck Lever --- include/uapi/linux/nfs4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 8572930cf5b0..bf197e99b98f 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -33,6 +33,9 @@ #define NFS4_ACCESS_EXTEND 0x0008 #define NFS4_ACCESS_DELETE 0x0010 #define NFS4_ACCESS_EXECUTE 0x0020 +#define NFS4_ACCESS_XAREAD 0x0040 +#define NFS4_ACCESS_XAWRITE 0x0080 +#define NFS4_ACCESS_XALIST 0x0100 #define NFS4_FH_PERSISTENT 0x0000 #define NFS4_FH_NOEXPIRE_WITH_OPEN 0x0001 -- cgit v1.2.3 From 95ad37f90c338e3fd4abf61cecfe02b6f3e080f0 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Tue, 23 Jun 2020 22:39:04 +0000 Subject: NFSv4.2: add client side xattr caching. Implement client side caching for NFSv4.2 extended attributes. The cache is a per-inode hashtable, with name/value entries. There is one special entry for the listxattr cache. NFS inodes have a pointer to a cache structure. The cache structure is allocated on demand, freed when the cache is invalidated. Memory shrinkers keep the size in check. Large entries (> PAGE_SIZE) are collected by a separate shrinker, and freed more aggressively than others. Signed-off-by: Frank van der Linden Signed-off-by: Trond Myklebust --- include/uapi/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nfs_fs.h b/include/uapi/linux/nfs_fs.h index 7bcc8cd6831d..3afe3767c55d 100644 --- a/include/uapi/linux/nfs_fs.h +++ b/include/uapi/linux/nfs_fs.h @@ -56,6 +56,7 @@ #define NFSDBG_PNFS 0x1000 #define NFSDBG_PNFS_LD 0x2000 #define NFSDBG_STATE 0x4000 +#define NFSDBG_XATTRCACHE 0x8000 #define NFSDBG_ALL 0xFFFF -- cgit v1.2.3 From 8aa5a33578e9685d06020bd10d1637557423e945 Mon Sep 17 00:00:00 2001 From: Ciara Loftus Date: Wed, 8 Jul 2020 07:28:33 +0000 Subject: xsk: Add new statistics It can be useful for the user to know the reason behind a dropped packet. Introduce new counters which track drops on the receive path caused by: 1. rx ring being full 2. fill ring being empty Also, on the tx path introduce a counter which tracks the number of times we attempt pull from the tx ring when it is empty. Signed-off-by: Ciara Loftus Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200708072835.4427-2-ciara.loftus@intel.com --- include/uapi/linux/if_xdp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index be328c59389d..a78a8096f4ce 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -73,9 +73,12 @@ struct xdp_umem_reg { }; struct xdp_statistics { - __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_dropped; /* Dropped for other reasons */ __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 rx_ring_full; /* Dropped due to rx ring being full */ + __u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */ + __u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */ }; struct xdp_options { -- cgit v1.2.3 From 0d80cb4612aa32dc0faa17fa3ab6f96f33e2b4a7 Mon Sep 17 00:00:00 2001 From: Ciara Loftus Date: Wed, 8 Jul 2020 07:28:35 +0000 Subject: xsk: Add xdp statistics to xsk_diag Add xdp statistics to the information dumped through the xsk_diag interface Signed-off-by: Ciara Loftus Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200708072835.4427-4-ciara.loftus@intel.com --- include/uapi/linux/xdp_diag.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/xdp_diag.h b/include/uapi/linux/xdp_diag.h index 78b2591a7782..66b9973b4f4c 100644 --- a/include/uapi/linux/xdp_diag.h +++ b/include/uapi/linux/xdp_diag.h @@ -30,6 +30,7 @@ struct xdp_diag_msg { #define XDP_SHOW_RING_CFG (1 << 1) #define XDP_SHOW_UMEM (1 << 2) #define XDP_SHOW_MEMINFO (1 << 3) +#define XDP_SHOW_STATS (1 << 4) enum { XDP_DIAG_NONE, @@ -41,6 +42,7 @@ enum { XDP_DIAG_UMEM_FILL_RING, XDP_DIAG_UMEM_COMPLETION_RING, XDP_DIAG_MEMINFO, + XDP_DIAG_STATS, __XDP_DIAG_MAX, }; @@ -69,4 +71,13 @@ struct xdp_diag_umem { __u32 refs; }; +struct xdp_diag_stats { + __u64 n_rx_dropped; + __u64 n_rx_invalid; + __u64 n_rx_full; + __u64 n_fill_ring_empty; + __u64 n_tx_invalid; + __u64 n_tx_ring_empty; +}; + #endif /* _LINUX_XDP_DIAG_H */ -- cgit v1.2.3 From ed757328c34015be4ec51861a90bb3bcc807ad58 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Mon, 13 Jul 2020 12:24:18 +0200 Subject: atm: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Signed-off-by: David S. Miller --- include/uapi/linux/atmioc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/atmioc.h b/include/uapi/linux/atmioc.h index cd7655e40c77..a9030bcc8d56 100644 --- a/include/uapi/linux/atmioc.h +++ b/include/uapi/linux/atmioc.h @@ -5,7 +5,7 @@ /* - * See http://icawww1.epfl.ch/linux-atm/magic.html for the complete list of + * See https://icawww1.epfl.ch/linux-atm/magic.html for the complete list of * "magic" ioctl numbers. */ -- cgit v1.2.3 From 2801758391ba6b0c20e253b956355e1b15ad85a2 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 14 Jul 2020 09:34:48 +0200 Subject: bridge: uapi: mrp: Extend MRP attributes for MRP interconnect Extend the existing MRP netlink attributes to allow to configure MRP Interconnect: IFLA_BRIDGE_MRP_IN_ROLE - the parameter type is br_mrp_in_role which contains the interconnect id, the ring id, the interconnect role(MIM or MIC) and the port ifindex that represents the interconnect port. IFLA_BRIDGE_MRP_IN_STATE - the parameter type is br_mrp_in_state which contains the interconnect id and the interconnect state. IFLA_BRIDGE_MRP_IN_TEST - the parameter type is br_mrp_start_in_test which contains the interconnect id, the interval at which to send MRP_InTest frames, how many test frames can be missed before declaring the interconnect ring open and the period which represents for how long to send MRP_InTest frames. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 53 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/mrp_bridge.h | 38 +++++++++++++++++++++++++++++ 2 files changed, 91 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index c114c1c2bd53..d840a3e37a37 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -167,6 +167,9 @@ enum { IFLA_BRIDGE_MRP_RING_ROLE, IFLA_BRIDGE_MRP_START_TEST, IFLA_BRIDGE_MRP_INFO, + IFLA_BRIDGE_MRP_IN_ROLE, + IFLA_BRIDGE_MRP_IN_STATE, + IFLA_BRIDGE_MRP_START_IN_TEST, __IFLA_BRIDGE_MRP_MAX, }; @@ -245,6 +248,37 @@ enum { #define IFLA_BRIDGE_MRP_INFO_MAX (__IFLA_BRIDGE_MRP_INFO_MAX - 1) +enum { + IFLA_BRIDGE_MRP_IN_STATE_UNSPEC, + IFLA_BRIDGE_MRP_IN_STATE_IN_ID, + IFLA_BRIDGE_MRP_IN_STATE_STATE, + __IFLA_BRIDGE_MRP_IN_STATE_MAX, +}; + +#define IFLA_BRIDGE_MRP_IN_STATE_MAX (__IFLA_BRIDGE_MRP_IN_STATE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_IN_ROLE_UNSPEC, + IFLA_BRIDGE_MRP_IN_ROLE_RING_ID, + IFLA_BRIDGE_MRP_IN_ROLE_IN_ID, + IFLA_BRIDGE_MRP_IN_ROLE_ROLE, + IFLA_BRIDGE_MRP_IN_ROLE_I_IFINDEX, + __IFLA_BRIDGE_MRP_IN_ROLE_MAX, +}; + +#define IFLA_BRIDGE_MRP_IN_ROLE_MAX (__IFLA_BRIDGE_MRP_IN_ROLE_MAX - 1) + +enum { + IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC, + IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID, + IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, + IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS, + IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD, + __IFLA_BRIDGE_MRP_START_IN_TEST_MAX, +}; + +#define IFLA_BRIDGE_MRP_START_IN_TEST_MAX (__IFLA_BRIDGE_MRP_START_IN_TEST_MAX - 1) + struct br_mrp_instance { __u32 ring_id; __u32 p_ifindex; @@ -270,6 +304,25 @@ struct br_mrp_start_test { __u32 monitor; }; +struct br_mrp_in_state { + __u32 in_state; + __u16 in_id; +}; + +struct br_mrp_in_role { + __u32 ring_id; + __u32 in_role; + __u32 i_ifindex; + __u16 in_id; +}; + +struct br_mrp_start_in_test { + __u32 interval; + __u32 max_miss; + __u32 period; + __u16 in_id; +}; + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index bee366540212..6aeb13ef0b1e 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -21,11 +21,22 @@ enum br_mrp_ring_role_type { BR_MRP_RING_ROLE_MRA, }; +enum br_mrp_in_role_type { + BR_MRP_IN_ROLE_DISABLED, + BR_MRP_IN_ROLE_MIC, + BR_MRP_IN_ROLE_MIM, +}; + enum br_mrp_ring_state_type { BR_MRP_RING_STATE_OPEN, BR_MRP_RING_STATE_CLOSED, }; +enum br_mrp_in_state_type { + BR_MRP_IN_STATE_OPEN, + BR_MRP_IN_STATE_CLOSED, +}; + enum br_mrp_port_state_type { BR_MRP_PORT_STATE_DISABLED, BR_MRP_PORT_STATE_BLOCKED, @@ -36,6 +47,7 @@ enum br_mrp_port_state_type { enum br_mrp_port_role_type { BR_MRP_PORT_ROLE_PRIMARY, BR_MRP_PORT_ROLE_SECONDARY, + BR_MRP_PORT_ROLE_INTER, }; enum br_mrp_tlv_header_type { @@ -45,6 +57,10 @@ enum br_mrp_tlv_header_type { BR_MRP_TLV_HEADER_RING_TOPO = 0x3, BR_MRP_TLV_HEADER_RING_LINK_DOWN = 0x4, BR_MRP_TLV_HEADER_RING_LINK_UP = 0x5, + BR_MRP_TLV_HEADER_IN_TEST = 0x6, + BR_MRP_TLV_HEADER_IN_TOPO = 0x7, + BR_MRP_TLV_HEADER_IN_LINK_DOWN = 0x8, + BR_MRP_TLV_HEADER_IN_LINK_UP = 0x9, BR_MRP_TLV_HEADER_OPTION = 0x7f, }; @@ -118,4 +134,26 @@ struct br_mrp_oui_hdr { __u8 oui[MRP_OUI_LENGTH]; }; +struct br_mrp_in_test_hdr { + __be16 id; + __u8 sa[ETH_ALEN]; + __be16 port_role; + __be16 state; + __be16 transitions; + __be32 timestamp; +}; + +struct br_mrp_in_topo_hdr { + __u8 sa[ETH_ALEN]; + __be16 id; + __be16 interval; +}; + +struct br_mrp_in_link_hdr { + __u8 sa[ETH_ALEN]; + __be16 port_role; + __be16 id; + __be16 interval; +}; + #endif -- cgit v1.2.3 From 559139cb0405d38816e5e725adee9000db993235 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 14 Jul 2020 09:34:56 +0200 Subject: bridge: uapi: mrp: Extend MRP_INFO attributes for interconnect status Extend the existing MRP_INFO to return status of MRP interconnect. In case there is no MRP interconnect on the node then the role will be disabled so the other attributes can be ignored. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index d840a3e37a37..c1227aecd38f 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -243,6 +243,11 @@ enum { IFLA_BRIDGE_MRP_INFO_TEST_INTERVAL, IFLA_BRIDGE_MRP_INFO_TEST_MAX_MISS, IFLA_BRIDGE_MRP_INFO_TEST_MONITOR, + IFLA_BRIDGE_MRP_INFO_I_IFINDEX, + IFLA_BRIDGE_MRP_INFO_IN_STATE, + IFLA_BRIDGE_MRP_INFO_IN_ROLE, + IFLA_BRIDGE_MRP_INFO_IN_TEST_INTERVAL, + IFLA_BRIDGE_MRP_INFO_IN_TEST_MAX_MISS, __IFLA_BRIDGE_MRP_INFO_MAX, }; -- cgit v1.2.3 From ffb3adba64801f70c472303c9e386eb5eaec193d Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 14 Jul 2020 09:34:58 +0200 Subject: net: bridge: Add port attribute IFLA_BRPORT_MRP_IN_OPEN This patch adds a new port attribute, IFLA_BRPORT_MRP_IN_OPEN, which allows to notify the userspace when the node lost the contiuity of MRP_InTest frames. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cc185a007ade..26842ffd0501 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -344,6 +344,7 @@ enum { IFLA_BRPORT_ISOLATED, IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, + IFLA_BRPORT_MRP_IN_OPEN, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 7cf97b12545503992020796c74bd84078eb39299 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Tue, 2 Jun 2020 18:10:43 -0700 Subject: seccomp: Introduce addfd ioctl to seccomp user notifier The current SECCOMP_RET_USER_NOTIF API allows for syscall supervision over an fd. It is often used in settings where a supervising task emulates syscalls on behalf of a supervised task in userspace, either to further restrict the supervisee's syscall abilities or to circumvent kernel enforced restrictions the supervisor deems safe to lift (e.g. actually performing a mount(2) for an unprivileged container). While SECCOMP_RET_USER_NOTIF allows for the interception of any syscall, only a certain subset of syscalls could be correctly emulated. Over the last few development cycles, the set of syscalls which can't be emulated has been reduced due to the addition of pidfd_getfd(2). With this we are now able to, for example, intercept syscalls that require the supervisor to operate on file descriptors of the supervisee such as connect(2). However, syscalls that cause new file descriptors to be installed can not currently be correctly emulated since there is no way for the supervisor to inject file descriptors into the supervisee. This patch adds a new addfd ioctl to remove this restriction by allowing the supervisor to install file descriptors into the intercepted task. By implementing this feature via seccomp the supervisor effectively instructs the supervisee to install a set of file descriptors into its own file descriptor table during the intercepted syscall. This way it is possible to intercept syscalls such as open() or accept(), and install (or replace, like dup2(2)) the supervisor's resulting fd into the supervisee. One replacement use-case would be to redirect the stdout and stderr of a supervisee into log file descriptors opened by the supervisor. The ioctl handling is based on the discussions[1] of how Extensible Arguments should interact with ioctls. Instead of building size into the addfd structure, make it a function of the ioctl command (which is how sizes are normally passed to ioctls). To support forward and backward compatibility, just mask out the direction and size, and match everything. The size (and any future direction) checks are done along with copy_struct_from_user() logic. As a note, the seccomp_notif_addfd structure is laid out based on 8-byte alignment without requiring packing as there have been packing issues with uapi highlighted before[2][3]. Although we could overload the newfd field and use -1 to indicate that it is not to be used, doing so requires changing the size of the fd field, and introduces struct packing complexity. [1]: https://lore.kernel.org/lkml/87o8w9bcaf.fsf@mid.deneb.enyo.de/ [2]: https://lore.kernel.org/lkml/a328b91d-fd8f-4f27-b3c2-91a9c45f18c0@rasmusvillemoes.dk/ [3]: https://lore.kernel.org/lkml/20200612104629.GA15814@ircssh-2.c.rugged-nimbus-611.internal Cc: Christoph Hellwig Cc: Christian Brauner Cc: Tycho Andersen Cc: Jann Horn Cc: Robert Sesek Cc: Chris Palmer Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-api@vger.kernel.org Suggested-by: Matt Denton Link: https://lore.kernel.org/r/20200603011044.7972-4-sargun@sargun.me Signed-off-by: Sargun Dhillon Reviewed-by: Will Drewry Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/uapi/linux/seccomp.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 965290f7dcc2..6ba18b82a02e 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -113,6 +113,25 @@ struct seccomp_notif_resp { __u32 flags; }; +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ + +/** + * struct seccomp_notif_addfd + * @id: The ID of the seccomp notification + * @flags: SECCOMP_ADDFD_FLAG_* + * @srcfd: The local fd number + * @newfd: Optional remote FD number if SETFD option is set, otherwise 0. + * @newfd_flags: The O_* flags the remote FD should have applied + */ +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; + #define SECCOMP_IOC_MAGIC '!' #define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) #define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) @@ -124,5 +143,8 @@ struct seccomp_notif_resp { #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) #define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) #endif /* _UAPI_LINUX_SECCOMP_H */ -- cgit v1.2.3 From c201324b54553aebb32845193680f21eb493c6e5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:42 -0700 Subject: net: caif: drop duplicate words in comments Drop doubled words "or" and "the" in several comments. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/caif/caif_socket.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/caif/caif_socket.h b/include/uapi/linux/caif/caif_socket.h index 10ec1d1cf68e..d9970bbaa156 100644 --- a/include/uapi/linux/caif/caif_socket.h +++ b/include/uapi/linux/caif/caif_socket.h @@ -169,7 +169,7 @@ struct sockaddr_caif { * @CAIFSO_LINK_SELECT: Selector used if multiple CAIF Link layers are * available. Either a high bandwidth * link can be selected (CAIF_LINK_HIGH_BANDW) or - * or a low latency link (CAIF_LINK_LOW_LATENCY). + * a low latency link (CAIF_LINK_LOW_LATENCY). * This option is of type __u32. * Alternatively SO_BINDTODEVICE can be used. * -- cgit v1.2.3 From 644bfe51fa49c22244d24e896cd3fe3ee2f2cfd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:37 +0200 Subject: cpumap: Formalize map value as a named struct As it has been already done for devmap, introduce 'struct bpf_cpumap_val' to formalize the expected values that can be passed in for a CPUMAP. Update cpumap code to use the struct. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/754f950674665dae6139c061d28c1d982aaf4170.1594734381.git.lorenzo@kernel.org --- include/uapi/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5e386389913a..109623527358 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3849,6 +3849,15 @@ struct bpf_devmap_val { } bpf_prog; }; +/* CPUMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_cpumap_val { + __u32 qsize; /* queue size to remote target CPU */ +}; + enum sk_action { SK_DROP = 0, SK_PASS, -- cgit v1.2.3 From 9216477449f33cdbc9c9a99d49f500b7fbb81702 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:38 +0200 Subject: bpf: cpumap: Add the possibility to attach an eBPF program to cpumap Introduce the capability to attach an eBPF program to cpumap entries. The idea behind this feature is to add the possibility to define on which CPU run the eBPF program if the underlying hw does not support RSS. Current supported verdicts are XDP_DROP and XDP_PASS. This patch has been tested on Marvell ESPRESSObin using xdp_redirect_cpu sample available in the kernel tree to identify possible performance regressions. Results show there are no observable differences in packet-per-second: $./xdp_redirect_cpu --progname xdp_cpu_map0 --dev eth0 --cpu 1 rx: 354.8 Kpps rx: 356.0 Kpps rx: 356.8 Kpps rx: 356.3 Kpps rx: 356.6 Kpps rx: 356.6 Kpps rx: 356.7 Kpps rx: 355.8 Kpps rx: 356.8 Kpps rx: 356.8 Kpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/5c9febdf903d810b3415732e5cd98491d7d9067a.1594734381.git.lorenzo@kernel.org --- include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 109623527358..c010b57fce3f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -227,6 +227,7 @@ enum bpf_attach_type { BPF_CGROUP_INET6_GETSOCKNAME, BPF_XDP_DEVMAP, BPF_CGROUP_INET_SOCK_RELEASE, + BPF_XDP_CPUMAP, __MAX_BPF_ATTACH_TYPE }; @@ -3856,6 +3857,10 @@ struct bpf_devmap_val { */ struct bpf_cpumap_val { __u32 qsize; /* queue size to remote target CPU */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; }; enum sk_action { -- cgit v1.2.3 From bfdfa51702dec67e9fcd52568b4cf3c7f799db8b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:29:11 -0700 Subject: bpf: Drop duplicated words in uapi helper comments Drop doubled words "will" and "attach". Signed-off-by: Randy Dunlap Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/6b9f71ae-4f8e-0259-2c5d-187ddaefe6eb@infradead.org --- include/uapi/linux/bpf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c010b57fce3f..7ac3992dacfe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2420,7 +2420,7 @@ union bpf_attr { * Look for an IPv6 socket. * * If the *netns* is a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* will + * socket lookup table in the netns associated with the *ctx* * will be used. For the TC hooks, this is the netns of the device * in the skb. For socket hooks, this is the netns of the socket. * If *netns* is any other signed 32-bit value greater than or @@ -2457,7 +2457,7 @@ union bpf_attr { * Look for an IPv6 socket. * * If the *netns* is a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* will + * socket lookup table in the netns associated with the *ctx* * will be used. For the TC hooks, this is the netns of the device * in the skb. For socket hooks, this is the netns of the socket. * If *netns* is any other signed 32-bit value greater than or @@ -4000,7 +4000,7 @@ struct bpf_link_info { /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed * by user and intended to be used by socket (e.g. to bind to, depends on - * attach attach type). + * attach type). */ struct bpf_sock_addr { __u32 user_family; /* Allows 4-byte read, but no write. */ -- cgit v1.2.3 From bbe4f4245271bd0f21bf826996c0c5d87a3529c9 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Tue, 7 Jul 2020 09:30:59 +0300 Subject: RDMA/qedr: Add EDPM mode type for user-fw compatibility In older FW versions the completion flag was treated as the ack flag in edpm messages. commit ff937b916eb6 ("qed: Add EDPM mode type for user-fw compatibility") exposed the FW option of setting which mode the QP is in by adding a flag to the qedr <-> qed API. This patch adds the qedr <-> libqedr interface so that the libqedr can set the flag appropriately and qedr can pass it down to FW. Flag is added for backward compatibility with libqedr. For older libs, this flag didn't exist and therefore set to zero. Fixes: ac1b36e55a51 ("qedr: Add support for user context verbs") Link: https://lore.kernel.org/r/20200707063100.3811-2-michal.kalderon@marvell.com Signed-off-by: Yuval Bason Signed-off-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/qedr-abi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h index a0b83c9d4498..b261c9fca07b 100644 --- a/include/uapi/rdma/qedr-abi.h +++ b/include/uapi/rdma/qedr-abi.h @@ -39,7 +39,7 @@ /* user kernel communication data structures. */ enum qedr_alloc_ucontext_flags { - QEDR_ALLOC_UCTX_RESERVED = 1 << 0, + QEDR_ALLOC_UCTX_EDPM_MODE = 1 << 0, QEDR_ALLOC_UCTX_DB_REC = 1 << 1 }; @@ -56,7 +56,7 @@ enum qedr_rdma_dpm_type { QEDR_DPM_TYPE_ROCE_ENHANCED = 1 << 0, QEDR_DPM_TYPE_ROCE_LEGACY = 1 << 1, QEDR_DPM_TYPE_IWARP_LEGACY = 1 << 2, - QEDR_DPM_TYPE_RESERVED = 1 << 3, + QEDR_DPM_TYPE_ROCE_EDPM_MODE = 1 << 3, QEDR_DPM_SIZES_SET = 1 << 4, }; -- cgit v1.2.3 From eb7f84e379daad69b4c92538baeaf93bbf493c14 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Tue, 7 Jul 2020 09:31:00 +0300 Subject: RDMA/qedr: Add EDPM max size to alloc ucontext response User space should receive the maximum edpm size from kernel driver, similar to other edpm/ldpm related limits. Add an additional parameter to the alloc_ucontext_resp structure for the edpm maximum size. In addition, pass an indication from user-space to kernel (and not just kernel to user) that the DPM sizes are supported. This is for supporting backward-forward compatibility between driver and lib for everything related to DPM transaction and limit sizes. This should have been part of commit mentioned in Fixes tag. Link: https://lore.kernel.org/r/20200707063100.3811-3-michal.kalderon@marvell.com Fixes: 93a3d05f9d68 ("RDMA/qedr: Add kernel capability flags for dpm enabled mode") Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/qedr-abi.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h index b261c9fca07b..bf7333b2b5d7 100644 --- a/include/uapi/rdma/qedr-abi.h +++ b/include/uapi/rdma/qedr-abi.h @@ -40,7 +40,8 @@ /* user kernel communication data structures. */ enum qedr_alloc_ucontext_flags { QEDR_ALLOC_UCTX_EDPM_MODE = 1 << 0, - QEDR_ALLOC_UCTX_DB_REC = 1 << 1 + QEDR_ALLOC_UCTX_DB_REC = 1 << 1, + QEDR_SUPPORT_DPM_SIZES = 1 << 2, }; struct qedr_alloc_ucontext_req { @@ -50,6 +51,7 @@ struct qedr_alloc_ucontext_req { #define QEDR_LDPM_MAX_SIZE (8192) #define QEDR_EDPM_TRANS_SIZE (64) +#define QEDR_EDPM_MAX_SIZE (ROCE_REQ_MAX_INLINE_DATA_SIZE) enum qedr_rdma_dpm_type { QEDR_DPM_TYPE_NONE = 0, @@ -77,6 +79,8 @@ struct qedr_alloc_ucontext_resp { __u16 ldpm_limit_size; __u8 edpm_trans_size; __u8 reserved; + __u16 edpm_limit_size; + __u8 padding[6]; }; struct qedr_alloc_pd_ureq { -- cgit v1.2.3 From e3a5a1e8b6548f5d37328e2d3571edc5c9e6d7c0 Mon Sep 17 00:00:00 2001 From: Priyaranjan Jha Date: Thu, 16 Jul 2020 12:12:35 -0700 Subject: tcp: add SNMP counter for no. of duplicate segments reported by DSACK There are two existing SNMP counters, TCPDSACKRecv and TCPDSACKOfoRecv, which are incremented depending on whether the DSACKed range is below the cumulative ACK sequence number or not. Unfortunately, these both implicitly assume each DSACK covers only one segment. This makes these counters unusable for estimating spurious retransmit rates, or real/non-spurious loss rate. This patch introduces a new SNMP counter, TCPDSACKRecvSegs, which tracks the estimated number of duplicate segments based on: (DSACKed sequence range) / MSS. This counter is usable for estimating spurious retransmit rates, or real/non-spurious loss rate. Signed-off-by: Priyaranjan Jha Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 7d91f4debc48..cee9f8e6fce3 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -287,6 +287,7 @@ enum LINUX_MIB_TCPFASTOPENPASSIVEALTKEY, /* TCPFastOpenPassiveAltKey */ LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */ LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */ + LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */ __LINUX_MIB_MAX }; -- cgit v1.2.3 From e9ddbb7707ff5891616240026062b8c1e29864ca Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:23 +0200 Subject: bpf: Introduce SK_LOOKUP program type with a dedicated attach point Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer when looking up a listening socket for a new connection request for connection oriented protocols, or when looking up an unconnected socket for a packet for connection-less protocols. When called, SK_LOOKUP BPF program can select a socket that will receive the packet. This serves as a mechanism to overcome the limits of what bind() API allows to express. Two use-cases driving this work are: (1) steer packets destined to an IP range, on fixed port to a socket 192.0.2.0/24, port 80 -> NGINX socket (2) steer packets destined to an IP address, on any port to a socket 198.51.100.1, any port -> L7 proxy socket In its run-time context program receives information about the packet that triggered the socket lookup. Namely IP version, L4 protocol identifier, and address 4-tuple. Context can be further extended to include ingress interface identifier. To select a socket BPF program fetches it from a map holding socket references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...) helper to record the selection. Transport layer then uses the selected socket as a result of socket lookup. In its basic form, SK_LOOKUP acts as a filter and hence must return either SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should look for a socket to receive the packet, or use the one selected by the program if available, while SK_DROP informs the transport layer that the lookup should fail. This patch only enables the user to attach an SK_LOOKUP program to a network namespace. Subsequent patches hook it up to run on local delivery path in ipv4 and ipv6 stacks. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com --- include/uapi/linux/bpf.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7ac3992dacfe..54d0c886e3ba 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -189,6 +189,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_STRUCT_OPS, BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, + BPF_PROG_TYPE_SK_LOOKUP, }; enum bpf_attach_type { @@ -228,6 +229,7 @@ enum bpf_attach_type { BPF_XDP_DEVMAP, BPF_CGROUP_INET_SOCK_RELEASE, BPF_XDP_CPUMAP, + BPF_SK_LOOKUP, __MAX_BPF_ATTACH_TYPE }; @@ -3069,6 +3071,10 @@ union bpf_attr { * * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SCHED_CLS** and + * **BPF_PROG_TYPE_SCHED_ACT** programs. + * * Assign the *sk* to the *skb*. When combined with appropriate * routing configuration to receive the packet towards the socket, * will cause *skb* to be delivered to the specified socket. @@ -3094,6 +3100,56 @@ union bpf_attr { * **-ESOCKTNOSUPPORT** if the socket type is not supported * (reuseport). * + * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) + * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs. + * + * Select the *sk* as a result of a socket lookup. + * + * For the operation to succeed passed socket must be compatible + * with the packet description provided by the *ctx* object. + * + * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must + * be an exact match. While IP family (**AF_INET** or + * **AF_INET6**) must be compatible, that is IPv6 sockets + * that are not v6-only can be selected for IPv4 packets. + * + * Only TCP listeners and UDP unconnected sockets can be + * selected. *sk* can also be NULL to reset any previous + * selection. + * + * *flags* argument can combination of following values: + * + * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous + * socket selection, potentially done by a BPF program + * that ran before us. + * + * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip + * load-balancing within reuseport group for the socket + * being selected. + * + * On success *ctx->sk* will point to the selected socket. + * + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EAFNOSUPPORT** if socket family (*sk->family*) is + * not compatible with packet family (*ctx->family*). + * + * * **-EEXIST** if socket has been already selected, + * potentially by another program, and + * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified. + * + * * **-EINVAL** if unsupported flags were specified. + * + * * **-EPROTOTYPE** if socket L4 protocol + * (*sk->protocol*) doesn't match packet protocol + * (*ctx->protocol*). + * + * * **-ESOCKTNOSUPPORT** if socket is not in allowed + * state (TCP listening or UDP unconnected). + * * u64 bpf_ktime_get_boot_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. @@ -3607,6 +3663,12 @@ enum { BPF_RINGBUF_HDR_SZ = 8, }; +/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */ +enum { + BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0), + BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1), +}; + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, @@ -4349,4 +4411,19 @@ struct bpf_pidns_info { __u32 pid; __u32 tgid; }; + +/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */ +struct bpf_sk_lookup { + __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + + __u32 family; /* Protocol family (AF_INET, AF_INET6) */ + __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ + __u32 remote_ip4; /* Network byte order */ + __u32 remote_ip6[4]; /* Network byte order */ + __u32 remote_port; /* Network byte order */ + __u32 local_ip4; /* Network byte order */ + __u32 local_ip6[4]; /* Network byte order */ + __u32 local_port; /* Host byte order */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From b3ab1c6058fad8cd5726f24e9ed9053e43bb2af4 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Wed, 24 Jun 2020 21:28:00 +0200 Subject: media: Add V4L2_TYPE_IS_CAPTURE helper It's all too easy to get confused by the V4L2_TYPE_IS_OUTPUT macro, when it's used as !V4L2_TYPE_IS_OUTPUT. Reduce the risk of confusion with macro to explicitly check for the CAPTURE queue type case. This change does not affect functionality, and it's only intended to make the code more readable. Suggested-by: Nicolas Dufresne Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil [hverkuil-cisco@xs4all.nl: checkpatch: align with parenthesis] Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 303805438814..c7b70ff53bc1 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -171,6 +171,8 @@ enum v4l2_buf_type { || (type) == V4L2_BUF_TYPE_SDR_OUTPUT \ || (type) == V4L2_BUF_TYPE_META_OUTPUT) +#define V4L2_TYPE_IS_CAPTURE(type) (!V4L2_TYPE_IS_OUTPUT(type)) + enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, V4L2_TUNER_ANALOG_TV = 2, -- cgit v1.2.3 From 124ea650d3072b005457faed69909221c2905a1f Mon Sep 17 00:00:00 2001 From: Adrian Reber Date: Sun, 19 Jul 2020 12:04:11 +0200 Subject: capabilities: Introduce CAP_CHECKPOINT_RESTORE This patch introduces CAP_CHECKPOINT_RESTORE, a new capability facilitating checkpoint/restore for non-root users. Over the last years, The CRIU (Checkpoint/Restore In Userspace) team has been asked numerous times if it is possible to checkpoint/restore a process as non-root. The answer usually was: 'almost'. The main blocker to restore a process as non-root was to control the PID of the restored process. This feature available via the clone3 system call, or via /proc/sys/kernel/ns_last_pid is unfortunately guarded by CAP_SYS_ADMIN. In the past two years, requests for non-root checkpoint/restore have increased due to the following use cases: * Checkpoint/Restore in an HPC environment in combination with a resource manager distributing jobs where users are always running as non-root. There is a desire to provide a way to checkpoint and restore long running jobs. * Container migration as non-root * We have been in contact with JVM developers who are integrating CRIU into a Java VM to decrease the startup time. These checkpoint/restore applications are not meant to be running with CAP_SYS_ADMIN. We have seen the following workarounds: * Use a setuid wrapper around CRIU: See https://github.com/FredHutch/slurm-examples/blob/master/checkpointer/lib/checkpointer/checkpointer-suid.c * Use a setuid helper that writes to ns_last_pid. Unfortunately, this helper delegation technique is impossible to use with clone3, and is thus prone to races. See https://github.com/twosigma/set_ns_last_pid * Cycle through PIDs with fork() until the desired PID is reached: This has been demonstrated to work with cycling rates of 100,000 PIDs/s See https://github.com/twosigma/set_ns_last_pid * Patch out the CAP_SYS_ADMIN check from the kernel * Run the desired application in a new user and PID namespace to provide a local CAP_SYS_ADMIN for controlling PIDs. This technique has limited use in typical container environments (e.g., Kubernetes) as /proc is typically protected with read-only layers (e.g., /proc/sys) for hardening purposes. Read-only layers prevent additional /proc mounts (due to proc's SB_I_USERNS_VISIBLE property), making the use of new PID namespaces limited as certain applications need access to /proc matching their PID namespace. The introduced capability allows to: * Control PIDs when the current user is CAP_CHECKPOINT_RESTORE capable for the corresponding PID namespace via ns_last_pid/clone3. * Open files in /proc/pid/map_files when the current user is CAP_CHECKPOINT_RESTORE capable in the root namespace, useful for recovering files that are unreachable via the file system such as deleted files, or memfd files. See corresponding selftest for an example with clone3(). Signed-off-by: Adrian Reber Signed-off-by: Nicolas Viennot Reviewed-by: Serge Hallyn Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20200719100418.2112740-2-areber@redhat.com Signed-off-by: Christian Brauner --- include/uapi/linux/capability.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 48ff0757ae5e..395dd0df8d08 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -408,7 +408,14 @@ struct vfs_ns_cap_data { */ #define CAP_BPF 39 -#define CAP_LAST_CAP CAP_BPF + +/* Allow checkpoint/restore related operations */ +/* Allow PID selection during clone3() */ +/* Allow writing to ns_last_pid */ + +#define CAP_CHECKPOINT_RESTORE 40 + +#define CAP_LAST_CAP CAP_CHECKPOINT_RESTORE #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP) -- cgit v1.2.3 From c4471ad9a50d5548e66ae4511acfb1dc23a48744 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 20 Jul 2020 00:03:33 +0200 Subject: net: phy: add USXGMII link partner ability constants The constants are taken from the USXGMII Singleport Copper Interface specification. The naming are based on the SGMII ones, but with an MDIO_ prefix. Signed-off-by: Michael Walle Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 4bcb41c71b8c..3f302e2523b2 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -324,4 +324,30 @@ static inline __u16 mdio_phy_id_c45(int prtad, int devad) return MDIO_PHY_ID_C45 | (prtad << 5) | devad; } +/* UsxgmiiChannelInfo[15:0] for USXGMII in-band auto-negotiation.*/ +#define MDIO_USXGMII_EEE_CLK_STP 0x0080 /* EEE clock stop supported */ +#define MDIO_USXGMII_EEE 0x0100 /* EEE supported */ +#define MDIO_USXGMII_SPD_MASK 0x0e00 /* USXGMII speed mask */ +#define MDIO_USXGMII_FULL_DUPLEX 0x1000 /* USXGMII full duplex */ +#define MDIO_USXGMII_DPX_SPD_MASK 0x1e00 /* USXGMII duplex and speed bits */ +#define MDIO_USXGMII_10 0x0000 /* 10Mbps */ +#define MDIO_USXGMII_10HALF 0x0000 /* 10Mbps half-duplex */ +#define MDIO_USXGMII_10FULL 0x1000 /* 10Mbps full-duplex */ +#define MDIO_USXGMII_100 0x0200 /* 100Mbps */ +#define MDIO_USXGMII_100HALF 0x0200 /* 100Mbps half-duplex */ +#define MDIO_USXGMII_100FULL 0x1200 /* 100Mbps full-duplex */ +#define MDIO_USXGMII_1000 0x0400 /* 1000Mbps */ +#define MDIO_USXGMII_1000HALF 0x0400 /* 1000Mbps half-duplex */ +#define MDIO_USXGMII_1000FULL 0x1400 /* 1000Mbps full-duplex */ +#define MDIO_USXGMII_10G 0x0600 /* 10Gbps */ +#define MDIO_USXGMII_10GHALF 0x0600 /* 10Gbps half-duplex */ +#define MDIO_USXGMII_10GFULL 0x1600 /* 10Gbps full-duplex */ +#define MDIO_USXGMII_2500 0x0800 /* 2500Mbps */ +#define MDIO_USXGMII_2500HALF 0x0800 /* 2500Mbps half-duplex */ +#define MDIO_USXGMII_2500FULL 0x1800 /* 2500Mbps full-duplex */ +#define MDIO_USXGMII_5000 0x0a00 /* 5000Mbps */ +#define MDIO_USXGMII_5000HALF 0x0a00 /* 5000Mbps half-duplex */ +#define MDIO_USXGMII_5000FULL 0x1a00 /* 5000Mbps full-duplex */ +#define MDIO_USXGMII_LINK 0x8000 /* PHY link with copper-side partner */ + #endif /* _UAPI__LINUX_MDIO_H__ */ -- cgit v1.2.3 From 55db9c0e853421fa71cac5e6855898601f78a1f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:15 +0200 Subject: net: remove compat_sys_{get,set}sockopt Now that the ->compat_{get,set}sockopt proto_ops methods are gone there is no good reason left to keep the compat syscalls separate. This fixes the odd use of unsigned int for the compat_setsockopt optlen and the missing sock_use_custom_sol_socket. It would also easily allow running the eBPF hooks for the compat syscalls, but such a large change in behavior does not belong into a consolidation patch like this one. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/uapi/asm-generic/unistd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index f4a01305d9a6..c8c189a5f0a6 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -606,9 +606,9 @@ __SYSCALL(__NR_sendto, sys_sendto) #define __NR_recvfrom 207 __SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom) #define __NR_setsockopt 208 -__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt) +__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt) #define __NR_getsockopt 209 -__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt) +__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt) #define __NR_shutdown 210 __SYSCALL(__NR_shutdown, sys_shutdown) #define __NR_sendmsg 211 -- cgit v1.2.3 From eba75c587e811d3249c8bd50d22bb2266ccd3c0f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 10 Jul 2020 09:29:02 -0400 Subject: icmp: support rfc 4884 Add setsockopt SOL_IP/IP_RECVERR_4884 to return the offset to an extension struct if present. ICMP messages may include an extension structure after the original datagram. RFC 4884 standardized this behavior. It stores the offset in words to the extension header in u8 icmphdr.un.reserved[1]. The field is valid only for ICMP types destination unreachable, time exceeded and parameter problem, if length is at least 128 bytes and entire packet does not exceed 576 bytes. Return the offset to the start of the extension struct when reading an ICMP error from the error queue, if it matches the above constraints. Do not return the raw u8 field. Return the offset from the start of the user buffer, in bytes. The kernel does not return the network and transport headers, so subtract those. Also validate the headers. Return the offset regardless of validation, as an invalid extension must still not be misinterpreted as part of the original datagram. Note that !invalid does not imply valid. If the extension version does not match, no validation can take place, for instance. For backward compatibility, make this optional, set by setsockopt SOL_IP/IP_RECVERR_RFC4884. For API example and feature test, see github.com/wdebruij/kerneltools/blob/master/tests/recv_icmp_v2.c For forward compatibility, reserve only setsockopt value 1, leaving other bits for additional icmp extensions. Changes v1->v2: - convert word offset to byte offset from start of user buffer - return in ee_data as u8 may be insufficient - define extension struct and object header structs - return len only if constraints met - if returning len, also validate Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/errqueue.h | 14 +++++++++++++- include/uapi/linux/icmp.h | 22 ++++++++++++++++++++++ include/uapi/linux/in.h | 1 + 3 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index ca5cb3e3c6df..3c70e8ac14b8 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -5,6 +5,13 @@ #include #include +/* RFC 4884: return offset to extension struct + validation */ +struct sock_ee_data_rfc4884 { + __u16 len; + __u8 flags; + __u8 reserved; +}; + struct sock_extended_err { __u32 ee_errno; __u8 ee_origin; @@ -12,7 +19,10 @@ struct sock_extended_err { __u8 ee_code; __u8 ee_pad; __u32 ee_info; - __u32 ee_data; + union { + __u32 ee_data; + struct sock_ee_data_rfc4884 ee_rfc4884; + }; }; #define SO_EE_ORIGIN_NONE 0 @@ -31,6 +41,8 @@ struct sock_extended_err { #define SO_EE_CODE_TXTIME_INVALID_PARAM 1 #define SO_EE_CODE_TXTIME_MISSED 2 +#define SO_EE_RFC4884_FLAG_INVALID 1 + /** * struct scm_timestamping - timestamps exposed through cmsg * diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h index 5589eeb791ca..fb169a50895e 100644 --- a/include/uapi/linux/icmp.h +++ b/include/uapi/linux/icmp.h @@ -19,6 +19,7 @@ #define _UAPI_LINUX_ICMP_H #include +#include #define ICMP_ECHOREPLY 0 /* Echo Reply */ #define ICMP_DEST_UNREACH 3 /* Destination Unreachable */ @@ -95,5 +96,26 @@ struct icmp_filter { __u32 data; }; +/* RFC 4884 extension struct: one per message */ +struct icmp_ext_hdr { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 reserved1:4, + version:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 version:4, + reserved1:4; +#else +#error "Please fix " +#endif + __u8 reserved2; + __sum16 checksum; +}; + +/* RFC 4884 extension object header: one for each object */ +struct icmp_extobj_hdr { + __be16 length; + __u8 class_num; + __u8 class_type; +}; #endif /* _UAPI_LINUX_ICMP_H */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 8533bf07450f..3d0d8231dc19 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -123,6 +123,7 @@ struct in_addr { #define IP_CHECKSUM 23 #define IP_BIND_ADDRESS_NO_PORT 24 #define IP_RECVFRAGSIZE 25 +#define IP_RECVERR_RFC4884 26 /* IP_MTU_DISCOVER values */ #define IP_PMTUDISC_DONT 0 /* Never send DF frames */ -- cgit v1.2.3 From f65b71aa25a65e13cf3d10445a48c63d3eeb942e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Jul 2020 01:45:29 +0300 Subject: ptp: add ability to configure duty cycle for periodic output There are external event timestampers (PHCs with support for PTP_EXTTS_REQUEST) that timestamp both event edges. When those edges are very close (such as in the case of a short pulse), there is a chance that the collected timestamp might be of the rising, or of the falling edge, we never know. There are also PHCs capable of generating periodic output with a configurable duty cycle. This is good news, because we can space the rising and falling edge out enough in time, that the risks to overrun the 1-entry timestamp FIFO of the extts PHC are lower (example: the perout PHC can be configured for a period of 1 second, and an "on" time of 0.5 seconds, resulting in a duty cycle of 50%). A flag is introduced for signaling that an on time is present in the perout request structure, for preserving compatibility. Logically speaking, the duty cycle cannot exceed 100% and the PTP core checks for this. PHC drivers that don't support this flag emit a periodic output of an unspecified duty cycle, same as before. The duty cycle is encoded as an "on" time, similar to the "start" and "period" times, and reuses the reserved space while preserving overall binary layout. Pahole reported before: struct ptp_perout_request { struct ptp_clock_time start; /* 0 16 */ struct ptp_clock_time period; /* 16 16 */ unsigned int index; /* 32 4 */ unsigned int flags; /* 36 4 */ unsigned int rsv[4]; /* 40 16 */ /* size: 56, cachelines: 1, members: 5 */ /* last cacheline: 56 bytes */ }; And now: struct ptp_perout_request { struct ptp_clock_time start; /* 0 16 */ struct ptp_clock_time period; /* 16 16 */ unsigned int index; /* 32 4 */ unsigned int flags; /* 36 4 */ union { struct ptp_clock_time on; /* 40 16 */ unsigned int rsv[4]; /* 40 16 */ }; /* 40 16 */ /* size: 56, cachelines: 1, members: 5 */ /* last cacheline: 56 bytes */ }; Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/uapi/linux/ptp_clock.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index ff070aa64278..1d2841155f7d 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -53,12 +53,14 @@ /* * Bits of the ptp_perout_request.flags field: */ -#define PTP_PEROUT_ONE_SHOT (1<<0) +#define PTP_PEROUT_ONE_SHOT (1<<0) +#define PTP_PEROUT_DUTY_CYCLE (1<<1) /* * flag fields valid for the new PTP_PEROUT_REQUEST2 ioctl. */ -#define PTP_PEROUT_VALID_FLAGS (PTP_PEROUT_ONE_SHOT) +#define PTP_PEROUT_VALID_FLAGS (PTP_PEROUT_ONE_SHOT | \ + PTP_PEROUT_DUTY_CYCLE) /* * No flags are valid for the original PTP_PEROUT_REQUEST ioctl @@ -105,7 +107,16 @@ struct ptp_perout_request { struct ptp_clock_time period; /* Desired period, zero means disable. */ unsigned int index; /* Which channel to configure. */ unsigned int flags; - unsigned int rsv[4]; /* Reserved for future use. */ + union { + /* + * The "on" time of the signal. + * Must be lower than the period. + * Valid only if (flags & PTP_PEROUT_DUTY_CYCLE) is set. + */ + struct ptp_clock_time on; + /* Reserved for future use. */ + unsigned int rsv[4]; + }; }; #define PTP_MAX_SAMPLES 25 /* Maximum allowed offset measurement samples. */ -- cgit v1.2.3 From b6bd41363a1ca39282496803cc32f7515ed917fe Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Jul 2020 01:45:30 +0300 Subject: ptp: introduce a phase offset in the periodic output request Some PHCs like the ocelot/felix switch cannot emit generic periodic output, but just PPS (pulse per second) signals, which: - don't start from arbitrary absolute times, but are rather phase-aligned to the beginning of [the closest next] second. - have an optional phase offset relative to that beginning of the second. For those, it was initially established that they should reject any other absolute time for the PTP_PEROUT_REQUEST than 0.000000000 [1]. But when it actually came to writing an application [2] that makes use of this functionality, we realized that we can't really deal generically with PHCs that support absolute start time, and with PHCs that don't, without an explicit interface. Namely, in an ideal world, PHC drivers would ensure that the "perout.start" value written to hardware will result in a functional output. This means that if the PTP time has become in the past of this PHC's current time, it should be automatically fast-forwarded by the driver into a close enough future time that is known to work (note: this is necessary only if the hardware doesn't do this fast-forward by itself). But we don't really know what is the status for PHC drivers in use today, so in the general sense, user space would be risking to have a non-functional periodic output if it simply asked for a start time of 0.000000000. So let's introduce a flag for this type of reduced-functionality hardware, named PTP_PEROUT_PHASE. The start time is just "soon", the only thing we know for sure about this signal is that its rising edge events, Rn, occur at: Rn = perout.phase + n * perout.period The "phase" in the periodic output structure is simply an alias to the "start" time, since both cannot logically be specified at the same time. Therefore, the binary layout of the structure is not affected. [1]: https://patchwork.ozlabs.org/project/netdev/patch/20200320103726.32559-7-yangbo.lu@nxp.com/ [2]: https://www.mail-archive.com/linuxptp-devel@lists.sourceforge.net/msg04142.html Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/uapi/linux/ptp_clock.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 1d2841155f7d..1d108d597f66 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -55,12 +55,14 @@ */ #define PTP_PEROUT_ONE_SHOT (1<<0) #define PTP_PEROUT_DUTY_CYCLE (1<<1) +#define PTP_PEROUT_PHASE (1<<2) /* * flag fields valid for the new PTP_PEROUT_REQUEST2 ioctl. */ #define PTP_PEROUT_VALID_FLAGS (PTP_PEROUT_ONE_SHOT | \ - PTP_PEROUT_DUTY_CYCLE) + PTP_PEROUT_DUTY_CYCLE | \ + PTP_PEROUT_PHASE) /* * No flags are valid for the original PTP_PEROUT_REQUEST ioctl @@ -103,7 +105,20 @@ struct ptp_extts_request { }; struct ptp_perout_request { - struct ptp_clock_time start; /* Absolute start time. */ + union { + /* + * Absolute start time. + * Valid only if (flags & PTP_PEROUT_PHASE) is unset. + */ + struct ptp_clock_time start; + /* + * Phase offset. The signal should start toggling at an + * unspecified integer multiple of the period, plus this value. + * The start time should be "as soon as possible". + * Valid only if (flags & PTP_PEROUT_PHASE) is set. + */ + struct ptp_clock_time phase; + }; struct ptp_clock_time period; /* Desired period, zero means disable. */ unsigned int index; /* Which channel to configure. */ unsigned int flags; -- cgit v1.2.3 From 6c0246a4588d418f72acd40a7b7601be403d80a9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Jul 2020 13:11:28 +0800 Subject: perf: Add perf_event_mmap_page::cap_user_time_short ABI In order to support short clock counters, provide an ABI extension. As a whole: u64 time, delta, cyc = read_cycle_counter(); + if (cap_user_time_short) + cyc = time_cycle + ((cyc - time_cycle) & time_mask); delta = mul_u64_u32_shr(cyc, time_mult, time_shift); if (cap_user_time_zero) time = time_zero + delta; delta += time_offset; Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Leo Yan Link: https://lore.kernel.org/r/20200716051130.4359-6-leo.yan@linaro.org Signed-off-by: Will Deacon --- include/uapi/linux/perf_event.h | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..21a1edd08cbe 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -532,9 +532,10 @@ struct perf_event_mmap_page { cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ - cap_user_time : 1, /* The time_* fields are used */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - cap_____res : 59; + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; }; }; @@ -593,13 +594,29 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; /* * Hole for extension of the self monitor capabilities */ - __u8 __reserved[118*8+4]; /* align to 1k. */ + __u8 __reserved[116*8]; /* align to 1k. */ /* * Control data for the mmap() data buffer. -- cgit v1.2.3 From 8e7eafb816ab7e5047b74cb8eb1db2f8f14f7d7a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:32:20 -0700 Subject: RDMA: rdma_user_ioctl.h: fix a duplicated word + clarify Change the repeated word "it" in a comment to "it to". Also insert a dash in the sentence to add clarity. Link: https://lore.kernel.org/r/20200719003220.21250-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/rdma_user_ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h index d92d2721b28c..53c55188dd2a 100644 --- a/include/uapi/rdma/rdma_user_ioctl.h +++ b/include/uapi/rdma/rdma_user_ioctl.h @@ -43,7 +43,7 @@ /* * General blocks assignments - * It is closed on purpose do not expose it it user space + * It is closed on purpose - do not expose it to user space * #define MAD_CMD_BASE 0x00 * #define HFI1_CMD_BAS 0xE0 */ -- cgit v1.2.3 From b43870c74f3fdf0cd06bf5f1b7a5ed70a2cd4ed2 Mon Sep 17 00:00:00 2001 From: Max Englander Date: Sat, 4 Jul 2020 15:15:28 +0000 Subject: audit: report audit wait metric in audit status reply In environments where the preservation of audit events and predictable usage of system memory are prioritized, admins may use a combination of --backlog_wait_time and -b options at the risk of degraded performance resulting from backlog waiting. In some cases, this risk may be preferred to lost events or unbounded memory usage. Ideally, this risk can be mitigated by making adjustments when backlog waiting is detected. However, detection can be difficult using the currently available metrics. For example, an admin attempting to debug degraded performance may falsely believe a full backlog indicates backlog waiting. It may turn out the backlog frequently fills up but drains quickly. To make it easier to reliably track degraded performance to backlog waiting, this patch makes the following changes: Add a new field backlog_wait_time_total to the audit status reply. Initialize this field to zero. Add to this field the total time spent by the current task on scheduled timeouts while the backlog limit is exceeded. Reset field to zero upon request via AUDIT_SET. Tested on Ubuntu 18.04 using complementary changes to the audit-userspace and audit-testsuite: - https://github.com/linux-audit/audit-userspace/pull/134 - https://github.com/linux-audit/audit-testsuite/pull/97 Signed-off-by: Max Englander Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 9b6a973f4cc3..cd2d8279a5e4 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -333,14 +333,15 @@ enum { }; /* Status symbols */ - /* Mask values */ -#define AUDIT_STATUS_ENABLED 0x0001 -#define AUDIT_STATUS_FAILURE 0x0002 -#define AUDIT_STATUS_PID 0x0004 + /* Mask values */ +#define AUDIT_STATUS_ENABLED 0x0001 +#define AUDIT_STATUS_FAILURE 0x0002 +#define AUDIT_STATUS_PID 0x0004 #define AUDIT_STATUS_RATE_LIMIT 0x0008 -#define AUDIT_STATUS_BACKLOG_LIMIT 0x0010 -#define AUDIT_STATUS_BACKLOG_WAIT_TIME 0x0020 -#define AUDIT_STATUS_LOST 0x0040 +#define AUDIT_STATUS_BACKLOG_LIMIT 0x0010 +#define AUDIT_STATUS_BACKLOG_WAIT_TIME 0x0020 +#define AUDIT_STATUS_LOST 0x0040 +#define AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL 0x0080 #define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT 0x00000001 #define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME 0x00000002 @@ -467,6 +468,9 @@ struct audit_status { __u32 feature_bitmap; /* bitmap of kernel audit features */ }; __u32 backlog_wait_time;/* message queue wait timeout */ + __u32 backlog_wait_time_actual;/* time spent waiting while + * message limit exceeded + */ }; struct audit_features { -- cgit v1.2.3 From 4787dd582dbde0b7f29eb3dbe59df3da1b350925 Mon Sep 17 00:00:00 2001 From: Martin Varghese Date: Fri, 17 Jul 2020 08:05:12 +0530 Subject: bareudp: Reverted support to enable & disable rx metadata collection The commit fe80536acf83 ("bareudp: Added attribute to enable & disable rx metadata collection") breaks the the original(5.7) default behavior of bareudp module to collect RX metadadata at the receive. It was added to avoid the crash at the kernel neighbour subsytem when packet with metadata from bareudp is processed. But it is no more needed as the commit 394de110a733 ("net: Added pointer check for dst->ops->neigh_lookup in dst_neigh_lookup_skb") solves this crash. Fixes: fe80536acf83 ("bareudp: Added attribute to enable & disable rx metadata collection") Signed-off-by: Martin Varghese Acked-by: Guillaume Nault Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 26842ffd0501..af8f31987526 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -601,7 +601,6 @@ enum { IFLA_BAREUDP_ETHERTYPE, IFLA_BAREUDP_SRCPORT_MIN, IFLA_BAREUDP_MULTIPROTO_MODE, - IFLA_BAREUDP_RX_COLLECT_METADATA, __IFLA_BAREUDP_MAX }; -- cgit v1.2.3 From c333f9495c451d958c6f4a41e5de2d8f80f79496 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Jul 2020 16:37:13 -0700 Subject: raid: md_p.h: drop duplicated word in a comment Drop the doubled word "the" in a comment. Signed-off-by: Randy Dunlap Cc: Song Liu Cc: linux-raid@vger.kernel.org Signed-off-by: Song Liu --- include/uapi/linux/raid/md_p.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index 1f2d8c81f0e0..e5a98a16f9b0 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -123,7 +123,7 @@ typedef struct mdp_device_descriptor_s { /* * Notes: - * - if an array is being reshaped (restriped) in order to change the + * - if an array is being reshaped (restriped) in order to change * the number of active devices in the array, 'raid_disks' will be * the larger of the old and new numbers. 'delta_disks' will * be the "new - old". So if +ve, raid_disks is the new value, and -- cgit v1.2.3 From 1859f4ebcf2dfe2e878a3805700036fdc4e01e2c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:27:38 -0700 Subject: android: binder.h: drop a duplicated word MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop the repeated word "the" in a comment. Cc: Arve Hjønnevåg Cc: Todd Kjos Cc: Martijn Coenen Cc: Joel Fernandes Cc: Hridya Valsaraju Cc: Suren Baghdasaryan Cc: devel@driverdev.osuosl.org Acked-by: Christian Brauner Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20200719002738.20210-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 2832134e5397..f1ce2c4c077e 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -404,7 +404,7 @@ enum binder_driver_return_protocol { BR_FAILED_REPLY = _IO('r', 17), /* - * The the last transaction (either a bcTRANSACTION or + * The last transaction (either a bcTRANSACTION or * a bcATTEMPT_ACQUIRE) failed (e.g. out of memory). No parameters. */ }; -- cgit v1.2.3 From 7deff7b5b4395784b194bae3631b8333d3423938 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:28:41 -0700 Subject: hyperv: hyperv.h: drop a duplicated word Drop the repeated word "the" in a comment. Signed-off-by: Randy Dunlap Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Wei Liu Cc: linux-hyperv@vger.kernel.org Link: https://lore.kernel.org/r/20200719002841.20369-1-rdunlap@infradead.org Signed-off-by: Wei Liu --- include/uapi/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index 8f24404ad04f..6135d92e0d47 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -219,7 +219,7 @@ struct hv_do_fcopy { * kernel and user-level daemon communicate using a connector channel. * * The user mode component first registers with the - * the kernel component. Subsequently, the kernel component requests, data + * kernel component. Subsequently, the kernel component requests, data * for the specified keys. In response to this message the user mode component * fills in the value corresponding to the specified key. We overload the * sequence field in the cn_msg header to define our KVP message types. -- cgit v1.2.3 From 3bf1c021e36e7269c71dceafec713b0181f413a9 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 9 Jun 2020 16:14:55 +0300 Subject: uapi/habanalabs: fix some comments MAP/UNMAP are done also for device memory. Reviewed-by: Omer Shpigelman Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index f6267a8d7416..f218d1c62c62 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -530,13 +530,13 @@ union hl_wait_cs_args { struct hl_wait_cs_out out; }; -/* Opcode to alloc device memory */ +/* Opcode to allocate device memory */ #define HL_MEM_OP_ALLOC 0 /* Opcode to free previously allocated device memory */ #define HL_MEM_OP_FREE 1 -/* Opcode to map host memory */ +/* Opcode to map host and device memory */ #define HL_MEM_OP_MAP 2 -/* Opcode to unmap previously mapped host memory */ +/* Opcode to unmap previously mapped host and device memory */ #define HL_MEM_OP_UNMAP 3 /* Memory flags */ -- cgit v1.2.3 From db491e4f08a9fd84ebb1ebd22a6b0b988a81a0d8 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 18 Jun 2020 09:51:16 +0300 Subject: habanalabs: Add dropped cs statistics info struct Add command submission statistics structure which can be obtained through the info ioctl. Each drop counter describes the reason for which the command submission was dropped. This information is needed for the user to be aware of the specific reason for which the submitted work was dropped. The user can then utilize the driver more efficiently. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index f218d1c62c62..d5c4f983b7a8 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -263,6 +263,7 @@ enum hl_device_status { * time the driver was loaded. * HL_INFO_TIME_SYNC - Retrieve the device's time alongside the host's time * for synchronization. + * HL_INFO_CS_COUNTERS - Retrieve command submission counters */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -274,6 +275,7 @@ enum hl_device_status { #define HL_INFO_CLK_RATE 8 #define HL_INFO_RESET_COUNT 9 #define HL_INFO_TIME_SYNC 10 +#define HL_INFO_CS_COUNTERS 11 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -338,6 +340,25 @@ struct hl_info_time_sync { __u64 host_time; }; +/** + * struct hl_info_cs_counters - command submission counters + * @out_of_mem_drop_cnt: dropped due to memory allocation issue + * @parsing_drop_cnt: dropped due to error in packet parsing + * @queue_full_drop_cnt: dropped due to queue full + * @device_in_reset_drop_cnt: dropped due to device in reset + */ +struct hl_cs_counters { + __u64 out_of_mem_drop_cnt; + __u64 parsing_drop_cnt; + __u64 queue_full_drop_cnt; + __u64 device_in_reset_drop_cnt; +}; + +struct hl_info_cs_counters { + struct hl_cs_counters cs_counters; + struct hl_cs_counters ctx_cs_counters; +}; + struct hl_info_args { /* Location of relevant struct in userspace */ __u64 return_pointer; -- cgit v1.2.3 From 8b603d0715a372f5827d3a6b19d9568bf854b687 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Fri, 24 Jul 2020 10:41:12 +0200 Subject: RDMA/mlx5: Fix typo in enum name Nnothing uses the enum name, so this is harmless. Fixes: 322694412400 ("IB/mlx5: Introduce driver create and destroy flow methods") Link: https://lore.kernel.org/r/20200724084112.GC31930@amd Signed-off-by: Pavel Machek (CIP) Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index b330e6eee626..e24d66d278cf 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -263,7 +263,7 @@ enum mlx5_ib_create_flow_attrs { MLX5_IB_ATTR_CREATE_FLOW_FLAGS, }; -enum mlx5_ib_destoy_flow_attrs { +enum mlx5_ib_destroy_flow_attrs { MLX5_IB_ATTR_DESTROY_FLOW_HANDLE = (1U << UVERBS_ID_NS_SHIFT), }; -- cgit v1.2.3 From 5923b8f7fa218a9bccd730c0a9692635eb2fc740 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Thu, 23 Jul 2020 01:03:01 +0300 Subject: net/sched: cls_flower: Add hash info to flow classification Adding new cls flower keys for hash value and hash mask and dissect the hash info from the skb into the flow key towards flow classication. Signed-off-by: Ariel Levkovich Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 7576209d96f9..ee95f42fb0ec 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -578,6 +578,9 @@ enum { TCA_FLOWER_KEY_MPLS_OPTS, + TCA_FLOWER_KEY_HASH, /* u32 */ + TCA_FLOWER_KEY_HASH_MASK, /* u32 */ + __TCA_FLOWER_MAX, }; -- cgit v1.2.3 From 01370434df85eb76ecb1527a4466013c4aca2436 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 24 Jul 2020 09:03:10 -0400 Subject: icmp6: support rfc 4884 Extend the rfc 4884 read interface introduced for ipv4 in commit eba75c587e81 ("icmp: support rfc 4884") to ipv6. Add socket option SOL_IPV6/IPV6_RECVERR_RFC4884. Changes v1->v2: - make ipv6_icmp_error_rfc4884 static (file scope) Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/icmpv6.h | 1 + include/uapi/linux/in6.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index 2622b5a3e616..c1661febc2dc 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -68,6 +68,7 @@ struct icmp6hdr { #define icmp6_mtu icmp6_dataun.un_data32[0] #define icmp6_unused icmp6_dataun.un_data32[0] #define icmp6_maxdelay icmp6_dataun.un_data16[0] +#define icmp6_datagram_len icmp6_dataun.un_data8[0] #define icmp6_router icmp6_dataun.u_nd_advt.router #define icmp6_solicited icmp6_dataun.u_nd_advt.solicited #define icmp6_override icmp6_dataun.u_nd_advt.override diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 9f2273a08356..5ad396a57eb3 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -179,6 +179,7 @@ struct in6_flowlabel_req { #define IPV6_LEAVE_ANYCAST 28 #define IPV6_MULTICAST_ALL 29 #define IPV6_ROUTER_ALERT_ISOLATE 30 +#define IPV6_RECVERR_RFC4884 31 /* IPV6_MTU_DISCOVER values */ #define IPV6_PMTUDISC_DONT 0 -- cgit v1.2.3 From d721a43ff69cd473019c3b77aacb76b09102aca3 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Sat, 25 Jul 2020 20:00:27 +0800 Subject: bcache: increase super block version for cache device and backing device The new added super block version BCACHE_SB_VERSION_BDEV_WITH_FEATURES (5) BCACHE_SB_VERSION_CDEV_WITH_FEATURES value (6), is for the feature set bits. Devices have super block version equal to the new version will have three new members for feature set bits in the on-disk super block, __le64 feature_compat; __le64 feature_incompat; __le64 feature_ro_compat; They are used for further new features which may introduce on-disk format change, and avoid unncessary super block version increase. The very basic features handling code skeleton is also initialized in this patch. Signed-off-by: Coly Li Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/uapi/linux/bcache.h | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 9a1965c6c3d0..47df2db2e727 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -141,11 +141,13 @@ static inline struct bkey *bkey_idx(const struct bkey *k, unsigned int nr_keys) * Version 3: Cache device with new UUID format * Version 4: Backing device with data offset */ -#define BCACHE_SB_VERSION_CDEV 0 -#define BCACHE_SB_VERSION_BDEV 1 -#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 -#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 -#define BCACHE_SB_MAX_VERSION 4 +#define BCACHE_SB_VERSION_CDEV 0 +#define BCACHE_SB_VERSION_BDEV 1 +#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 +#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 +#define BCACHE_SB_VERSION_CDEV_WITH_FEATURES 5 +#define BCACHE_SB_VERSION_BDEV_WITH_FEATURES 6 +#define BCACHE_SB_MAX_VERSION 6 #define SB_SECTOR 8 #define SB_OFFSET (SB_SECTOR << SECTOR_SHIFT) @@ -173,7 +175,12 @@ struct cache_sb_disk { __le64 flags; __le64 seq; - __le64 pad[8]; + + __le64 feature_compat; + __le64 feature_incompat; + __le64 feature_ro_compat; + + __le64 pad[5]; union { struct { @@ -224,7 +231,12 @@ struct cache_sb { __u64 flags; __u64 seq; - __u64 pad[8]; + + __u64 feature_compat; + __u64 feature_incompat; + __u64 feature_ro_compat; + + __u64 pad[5]; union { struct { @@ -262,7 +274,8 @@ struct cache_sb { static inline _Bool SB_IS_BDEV(const struct cache_sb *sb) { return sb->version == BCACHE_SB_VERSION_BDEV - || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET; + || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET + || sb->version == BCACHE_SB_VERSION_BDEV_WITH_FEATURES; } BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1); -- cgit v1.2.3 From 4c1ccd0896d6a45f2159280d957afd441a7aeaba Mon Sep 17 00:00:00 2001 From: Coly Li Date: Sat, 25 Jul 2020 20:00:29 +0800 Subject: bcache: struct cache_sb is only for in-memory super block now We have struct cache_sb_disk for on-disk super block already, it is unnecessary to keep the in-memory super block format exactly mapping to the on-disk struct layout. This patch adds code comments to notice that struct cache_sb is not exactly mapping to cache_sb_disk, and removes the useless member csum and pad[5]. Although struct cache_sb does not belong to uapi, but there are still some on-disk format related macros reference it and it is unncessary to get rid of such dependency now. So struct cache_sb will continue to stay in include/uapi/linux/bache.h for now. Signed-off-by: Coly Li Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/uapi/linux/bcache.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 47df2db2e727..0ef984ea515a 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -215,8 +215,13 @@ struct cache_sb_disk { __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ }; +/* + * This is for in-memory bcache super block. + * NOTE: cache_sb is NOT exactly mapping to cache_sb_disk, the member + * size, ordering and even whole struct size may be different + * from cache_sb_disk. + */ struct cache_sb { - __u64 csum; __u64 offset; /* sector where this sb was written */ __u64 version; @@ -236,8 +241,6 @@ struct cache_sb { __u64 feature_incompat; __u64 feature_ro_compat; - __u64 pad[5]; - union { struct { /* Cache devices */ @@ -245,7 +248,6 @@ struct cache_sb { __u16 block_size; /* sectors */ __u16 bucket_size; /* sectors */ - __u16 nr_in_set; __u16 nr_this_dev; }; -- cgit v1.2.3 From ffa470327572b8f85dceda48fd0676d9658cb8c5 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Sat, 25 Jul 2020 20:00:35 +0800 Subject: bcache: add bucket_size_hi into struct cache_sb_disk for large bucket The large bucket feature is to extend bucket_size from 16bit to 32bit. When create cache device on zoned device (e.g. zoned NVMe SSD), making a single bucket cover one or more zones of the zoned device is the simplest way to support zoned device as cache by bcache. But current maximum bucket size is 16MB and a typical zone size of zoned device is 256MB, this is the major motiviation to extend bucket size to a larger bit width. This patch is the basic and first change to support large bucket size, the major changes it makes are, - Add BCH_FEATURE_INCOMPAT_LARGE_BUCKET for the large bucket feature, INCOMPAT means it introduces incompatible on-disk format change. - Add BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET) routines. - Adds __le16 bucket_size_hi into struct cache_sb_disk at offset 0x8d0 for the on-disk super block format. - For the in-memory super block struct cache_sb, member bucket_size is extended from __u16 to __32. - Add get_bucket_size() to combine the bucket_size and bucket_size_hi from struct cache_sb_disk into an unsigned int value. Since we already have large bucket size helpers meta_bucket_pages(), meta_bucket_bytes() and alloc_meta_bucket_pages(), they make sure when bucket size > 8MB, the memory allocation for bcache meta data bucket won't fail no matter how large the bucket size extended. So these meta data buckets are handled properly when the bucket size width increase from 16bit to 32bit, we don't need to worry about them. Signed-off-by: Coly Li Signed-off-by: Jens Axboe --- include/uapi/linux/bcache.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 0ef984ea515a..52e8bcb33981 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -213,6 +213,7 @@ struct cache_sb_disk { __le16 keys; }; __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ + __le16 bucket_size_hi; }; /* @@ -247,9 +248,9 @@ struct cache_sb { __u64 nbuckets; /* device size */ __u16 block_size; /* sectors */ - __u16 bucket_size; /* sectors */ __u16 nr_in_set; __u16 nr_this_dev; + __u32 bucket_size; /* sectors */ }; struct { /* Backing devices */ -- cgit v1.2.3 From 92fe2aa859f52ce6aa595ca97fec110dc7100e63 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:30 -0700 Subject: libnvdimm: Validate command family indices The ND_CMD_CALL format allows for a general passthrough of passlisted commands targeting a given command set. However there is no validation of the family index relative to what the bus supports. - Update the NFIT bus implementation (the only one that supports ND_CMD_CALL passthrough) to also passlist the valid set of command family indices. - Update the generic __nd_ioctl() path to validate that field on behalf of all implementations. Fixes: 31eca76ba2fc ("nfit, libnvdimm: limited/whitelisted dimm command marshaling mechanism") Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/uapi/linux/ndctl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 0e09dc5cec19..e9468b9332bd 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -245,6 +245,10 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_MSFT 3 #define NVDIMM_FAMILY_HYPERV 4 #define NVDIMM_FAMILY_PAPR 5 +#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_PAPR + +#define NVDIMM_BUS_FAMILY_NFIT 0 +#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_NFIT #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) -- cgit v1.2.3 From 6450ddbd5d8e83ea9927c7f9076a21f829699e0f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 20 Jul 2020 15:07:40 -0700 Subject: ACPI: NFIT: Define runtime firmware activation commands Platform reboots are expensive. Towards reducing downtime to apply firmware updates the Intel NVDIMM command definition is growing support for applying live firmware updates that only require temporarily suspending memory traffic instead of a full reboot. Follow-on commits add support for triggering firmware activation, this patch only defines the commands, adds probe support, and validates that they are blocked via the ioctl path. The ioctl-path block ensures that the OS is in charge since these commands have side effects only the OS can handle. Specifically firmware activation may cause the memory controller to be quiesced on the order of 100s of milliseconds. In that case Linux ensure the activation only takes place while the OS is in a suspend state. Link: https://pmem.io/documents/IntelOptanePMem_DSM_Interface-V2.0.pdf Cc: Vishal Verma Cc: Dave Jiang Cc: Ira Weiny Cc: "Rafael J. Wysocki" Cc: Len Brown Signed-off-by: Dan Williams Signed-off-by: Vishal Verma --- include/uapi/linux/ndctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index e9468b9332bd..8cf1e4884fd5 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -248,7 +248,8 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_PAPR #define NVDIMM_BUS_FAMILY_NFIT 0 -#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_NFIT +#define NVDIMM_BUS_FAMILY_INTEL 1 +#define NVDIMM_BUS_FAMILY_MAX NVDIMM_BUS_FAMILY_INTEL #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) -- cgit v1.2.3 From a5cbe05a6673b85bed2a63ffcfea6a96c6410cff Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:12 -0700 Subject: bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com --- include/uapi/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 54d0c886e3ba..828c2f6438f2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -246,6 +246,13 @@ enum bpf_link_type { MAX_BPF_LINK_TYPE, }; +enum bpf_iter_link_info { + BPF_ITER_LINK_UNSPEC = 0, + BPF_ITER_LINK_MAP_FD = 1, + + MAX_BPF_ITER_LINK_INFO, +}; + /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. -- cgit v1.2.3 From aa8d3a716b59db6c1ad6c68fb8aa05e31980da60 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:57 -0700 Subject: bpf, xdp: Add bpf_link-based XDP attachment API Add bpf_link-based API (bpf_xdp_link) to attach BPF XDP program through BPF_LINK_CREATE command. bpf_xdp_link is mutually exclusive with direct BPF program attachment, previous BPF program should be detached prior to attempting to create a new bpf_xdp_link attachment (for a given XDP mode). Once BPF link is attached, it can't be replaced by other BPF program attachment or link attachment. It will be detached only when the last BPF link FD is closed. bpf_xdp_link will be auto-detached when net_device is shutdown, similarly to how other BPF links behave (cgroup, flow_dissector). At that point bpf_link will become defunct, but won't be destroyed until last FD is closed. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-5-andriin@fb.com --- include/uapi/linux/bpf.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 828c2f6438f2..87823fb9c123 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -230,6 +230,7 @@ enum bpf_attach_type { BPF_CGROUP_INET_SOCK_RELEASE, BPF_XDP_CPUMAP, BPF_SK_LOOKUP, + BPF_XDP, __MAX_BPF_ATTACH_TYPE }; @@ -242,6 +243,7 @@ enum bpf_link_type { BPF_LINK_TYPE_CGROUP = 3, BPF_LINK_TYPE_ITER = 4, BPF_LINK_TYPE_NETNS = 5, + BPF_LINK_TYPE_XDP = 6, MAX_BPF_LINK_TYPE, }; @@ -614,7 +616,10 @@ union bpf_attr { struct { /* struct used by BPF_LINK_CREATE command */ __u32 prog_fd; /* eBPF program to attach */ - __u32 target_fd; /* object to attach to */ + union { + __u32 target_fd; /* object to attach to */ + __u32 target_ifindex; /* target ifindex */ + }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ } link_create; -- cgit v1.2.3 From c1931c9784ebb5787c0784c112fb8baa5e8455b3 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:59 -0700 Subject: bpf: Implement BPF XDP link-specific introspection APIs Implement XDP link-specific show_fdinfo and link_info to emit ifindex. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-7-andriin@fb.com --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 87823fb9c123..e1ba4ae6a916 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4069,6 +4069,9 @@ struct bpf_link_info { __u32 netns_ino; __u32 attach_type; } netns; + struct { + __u32 ifindex; + } xdp; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From 1a0c02ba643ed05c07ddf14d87c3bec640666836 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Mon, 20 Jul 2020 08:50:58 -0700 Subject: dmaengine: idxd: add missing invalid flags field to completion Add missing "invalid flags" field to completion record struct. Reported-by: Nikhil Rao Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/159526025819.49266.13176787210106133664.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 1f412fbf561b..5d07a3ff9e96 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -178,6 +178,12 @@ struct dsa_completion_record { uint32_t bytes_completed; uint64_t fault_addr; union { + /* common record */ + struct { + uint32_t invalid_flags:24; + uint32_t rsvd2:8; + }; + uint16_t delta_rec_size; uint16_t crc_val; -- cgit v1.2.3 From 06f67c47076e5c3ee65276171596479dcc3a3941 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sun, 28 Jun 2020 13:07:14 +0800 Subject: btrfs: use __u16 for the return value of btrfs_qgroup_level() The qgroup level is limited to u16, so no need to use u64 for it. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index a3f3975df0de..9ba64ca6b4ac 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -913,9 +913,9 @@ struct btrfs_free_space_info { #define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0) #define BTRFS_QGROUP_LEVEL_SHIFT 48 -static inline __u64 btrfs_qgroup_level(__u64 qgroupid) +static inline __u16 btrfs_qgroup_level(__u64 qgroupid) { - return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT; + return (__u16)(qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT); } /* -- cgit v1.2.3 From 137c541821a83debb63b3fa8abdd1cbc41bdf3a1 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Mon, 13 Jul 2020 21:28:58 +0900 Subject: btrfs: pass checksum type via BTRFS_IOC_FS_INFO ioctl With the recent addition of filesystem checksum types other than CRC32c, it is not anymore hard-coded which checksum type a btrfs filesystem uses. Up to now there is no good way to read the filesystem checksum, apart from reading the filesystem UUID and then query sysfs for the checksum type. Add a new csum_type and csum_size fields to the BTRFS_IOC_FS_INFO ioctl command which usually is used to query filesystem features. Also add a flags member indicating that the kernel responded with a set csum_type and csum_size field. For compatibility reasons, only return the csum_type and csum_size if the BTRFS_FS_INFO_FLAG_CSUM_INFO flag was passed to the kernel. Also clear any unknown flags so we don't pass false positives to user-space newer than the kernel. To simplify further additions to the ioctl, also switch the padding to a u8 array. Pahole was used to verify the result of this switch: The csum members are added before flags, which might look odd, but this is to keep the alignment requirements and not to introduce holes in the structure. $ pahole -C btrfs_ioctl_fs_info_args fs/btrfs/btrfs.ko struct btrfs_ioctl_fs_info_args { __u64 max_id; /* 0 8 */ __u64 num_devices; /* 8 8 */ __u8 fsid[16]; /* 16 16 */ __u32 nodesize; /* 32 4 */ __u32 sectorsize; /* 36 4 */ __u32 clone_alignment; /* 40 4 */ __u16 csum_type; /* 44 2 */ __u16 csum_size; /* 46 2 */ __u64 flags; /* 48 8 */ __u8 reserved[968]; /* 56 968 */ /* size: 1024, cachelines: 16, members: 10 */ }; Fixes: 3951e7f050ac ("btrfs: add xxhash64 to checksumming algorithms") Fixes: 3831bf0094ab ("btrfs: add sha256 to checksumming algorithm") CC: stable@vger.kernel.org # 5.5+ Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index e6b6cb0f8bc6..24f6848ad78e 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -243,6 +243,13 @@ struct btrfs_ioctl_dev_info_args { __u8 path[BTRFS_DEVICE_PATH_NAME_MAX]; /* out */ }; +/* + * Retrieve information about the filesystem + */ + +/* Request information about checksum type and size */ +#define BTRFS_FS_INFO_FLAG_CSUM_INFO (1 << 0) + struct btrfs_ioctl_fs_info_args { __u64 max_id; /* out */ __u64 num_devices; /* out */ @@ -250,8 +257,11 @@ struct btrfs_ioctl_fs_info_args { __u32 nodesize; /* out */ __u32 sectorsize; /* out */ __u32 clone_alignment; /* out */ - __u32 reserved32; - __u64 reserved[122]; /* pad to 1k */ + /* See BTRFS_FS_INFO_FLAG_* */ + __u16 csum_type; /* out */ + __u16 csum_size; /* out */ + __u64 flags; /* in/out */ + __u8 reserved[968]; /* pad to 1k */ }; /* -- cgit v1.2.3 From 0fb408a558aadbaa58beb75b02c95741e1fbb514 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Mon, 13 Jul 2020 21:28:59 +0900 Subject: btrfs: add filesystem generation to FS_INFO ioctl Add retrieval of the filesystem's generation to the fsinfo ioctl. This is driven by setting the BTRFS_FS_INFO_FLAG_GENERATION flag in btrfs_ioctl_fs_info_args::flags. Reviewed-by: Nikolay Borisov Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 24f6848ad78e..9b82e01c191d 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -250,6 +250,9 @@ struct btrfs_ioctl_dev_info_args { /* Request information about checksum type and size */ #define BTRFS_FS_INFO_FLAG_CSUM_INFO (1 << 0) +/* Request information about filesystem generation */ +#define BTRFS_FS_INFO_FLAG_GENERATION (1 << 1) + struct btrfs_ioctl_fs_info_args { __u64 max_id; /* out */ __u64 num_devices; /* out */ @@ -261,7 +264,8 @@ struct btrfs_ioctl_fs_info_args { __u16 csum_type; /* out */ __u16 csum_size; /* out */ __u64 flags; /* in/out */ - __u8 reserved[968]; /* pad to 1k */ + __u64 generation; /* out */ + __u8 reserved[960]; /* pad to 1k */ }; /* -- cgit v1.2.3 From 49bac897683340457a0ab1f76b924a1220bdb604 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Mon, 13 Jul 2020 21:29:00 +0900 Subject: btrfs: add metadata_uuid to FS_INFO ioctl Add retrieval of the filesystem's metadata UUID to the fsinfo ioctl. This is driven by setting the BTRFS_FS_INFO_FLAG_METADATA_UUID flag in btrfs_ioctl_fs_info_args::flags. Reviewed-by: Nikolay Borisov Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 9b82e01c191d..2c39d15a2beb 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -252,6 +252,8 @@ struct btrfs_ioctl_dev_info_args { /* Request information about filesystem generation */ #define BTRFS_FS_INFO_FLAG_GENERATION (1 << 1) +/* Request information about filesystem metadata UUID */ +#define BTRFS_FS_INFO_FLAG_METADATA_UUID (1 << 2) struct btrfs_ioctl_fs_info_args { __u64 max_id; /* out */ @@ -265,7 +267,8 @@ struct btrfs_ioctl_fs_info_args { __u16 csum_size; /* out */ __u64 flags; /* in/out */ __u64 generation; /* out */ - __u8 reserved[960]; /* pad to 1k */ + __u8 metadata_uuid[BTRFS_FSID_SIZE]; /* out */ + __u8 reserved[944]; /* pad to 1k */ }; /* -- cgit v1.2.3 From 50c8a002bfd43798768ad07833b2b9d4b4d5274f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:29:03 -0700 Subject: platform/x86: ISST: drop a duplicated word in isst_if.h Drop the repeated word "for" in a comment. Signed-off-by: Randy Dunlap Cc: Srinivas Pandruvada Cc: platform-driver-x86@vger.kernel.org Cc: Darren Hart Cc: Andy Shevchenko Acked-by: Srinivas Pandruvada Signed-off-by: Andy Shevchenko --- include/uapi/linux/isst_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index 0a52b7b093d3..ba078f8e9add 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -69,7 +69,7 @@ struct isst_if_cpu_maps { * @logical_cpu: Logical CPU number to get target PCI device. * @reg: PUNIT register offset * @value: For write operation value to write and for - * for read placeholder read value + * read placeholder read value * * Structure to specify read/write data to PUNIT registers. */ -- cgit v1.2.3 From 1e6b57d6421f0343dd11619612e5ff8930cddf38 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 11 Jun 2020 11:11:32 -0400 Subject: unexport linux/elfcore.h It's unusable from userland - it uses elf_gregset_t, which is not provided by exported headers. glibc has it in sys/procfs.h, but the same file defines struct elf_prstatus, so linux/elfcore.h can't be included once sys/procfs.h has been pulled. Same goes for uclibc and dietlibc simply doesn't have elf_gregset_t defined anywhere. IOW, no userland source is including that thing. Signed-off-by: Al Viro --- include/uapi/linux/elfcore.h | 101 ------------------------------------------- 1 file changed, 101 deletions(-) delete mode 100644 include/uapi/linux/elfcore.h (limited to 'include/uapi') diff --git a/include/uapi/linux/elfcore.h b/include/uapi/linux/elfcore.h deleted file mode 100644 index baf03562306d..000000000000 --- a/include/uapi/linux/elfcore.h +++ /dev/null @@ -1,101 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI_LINUX_ELFCORE_H -#define _UAPI_LINUX_ELFCORE_H - -#include -#include -#include -#include -#include -#include - -struct elf_siginfo -{ - int si_signo; /* signal number */ - int si_code; /* extra code */ - int si_errno; /* errno */ -}; - - -#ifndef __KERNEL__ -typedef elf_greg_t greg_t; -typedef elf_gregset_t gregset_t; -typedef elf_fpregset_t fpregset_t; -typedef elf_fpxregset_t fpxregset_t; -#define NGREG ELF_NGREG -#endif - -/* - * Definitions to generate Intel SVR4-like core files. - * These mostly have the same names as the SVR4 types with "elf_" - * tacked on the front to prevent clashes with linux definitions, - * and the typedef forms have been avoided. This is mostly like - * the SVR4 structure, but more Linuxy, with things that Linux does - * not support and which gdb doesn't really use excluded. - * Fields present but not used are marked with "XXX". - */ -struct elf_prstatus -{ -#if 0 - long pr_flags; /* XXX Process flags */ - short pr_why; /* XXX Reason for process halt */ - short pr_what; /* XXX More detailed reason */ -#endif - struct elf_siginfo pr_info; /* Info associated with signal */ - short pr_cursig; /* Current signal */ - unsigned long pr_sigpend; /* Set of pending signals */ - unsigned long pr_sighold; /* Set of held signals */ -#if 0 - struct sigaltstack pr_altstack; /* Alternate stack info */ - struct sigaction pr_action; /* Signal action for current sig */ -#endif - pid_t pr_pid; - pid_t pr_ppid; - pid_t pr_pgrp; - pid_t pr_sid; - struct __kernel_old_timeval pr_utime; /* User time */ - struct __kernel_old_timeval pr_stime; /* System time */ - struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ - struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ -#if 0 - long pr_instr; /* Current instruction */ -#endif - elf_gregset_t pr_reg; /* GP registers */ -#ifdef CONFIG_BINFMT_ELF_FDPIC - /* When using FDPIC, the loadmap addresses need to be communicated - * to GDB in order for GDB to do the necessary relocations. The - * fields (below) used to communicate this information are placed - * immediately after ``pr_reg'', so that the loadmap addresses may - * be viewed as part of the register set if so desired. - */ - unsigned long pr_exec_fdpic_loadmap; - unsigned long pr_interp_fdpic_loadmap; -#endif - int pr_fpvalid; /* True if math co-processor being used. */ -}; - -#define ELF_PRARGSZ (80) /* Number of chars for args */ - -struct elf_prpsinfo -{ - char pr_state; /* numeric process state */ - char pr_sname; /* char for pr_state */ - char pr_zomb; /* zombie */ - char pr_nice; /* nice val */ - unsigned long pr_flag; /* flags */ - __kernel_uid_t pr_uid; - __kernel_gid_t pr_gid; - pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; - /* Lots missing */ - char pr_fname[16]; /* filename of executable */ - char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ -}; - -#ifndef __KERNEL__ -typedef struct elf_prstatus prstatus_t; -typedef struct elf_prpsinfo prpsinfo_t; -#define PRARGSZ ELF_PRARGSZ -#endif - - -#endif /* _UAPI_LINUX_ELFCORE_H */ -- cgit v1.2.3 From 8f4c0e01789c18674acdf17cae3822b3dc3db715 Mon Sep 17 00:00:00 2001 From: Murali Karicheri Date: Wed, 22 Jul 2020 10:40:16 -0400 Subject: hsr: enhance netlink socket interface to support PRP Parallel Redundancy Protocol (PRP) is another redundancy protocol introduced by IEC 63439 standard. It is similar to HSR in many aspects:- - Use a pair of Ethernet interfaces to created the PRP device - Use a 6 byte redundancy protocol part (RCT, Redundancy Check Trailer) similar to HSR Tag. - Has Link Redundancy Entity (LRE) that works with RCT to implement redundancy. Key difference is that the protocol unit is a trailer instead of a prefix as in HSR. That makes it inter-operable with tradition network components such as bridges/switches which treat it as pad bytes, whereas HSR nodes requires some kind of translators (Called redbox) to talk to regular network devices. This features allows regular linux box to be converted to a DAN-P box. DAN-P stands for Dual Attached Node - PRP similar to DAN-H (Dual Attached Node - HSR). Add a comment at the header/source code to explicitly state that the driver files also handles PRP protocol as well. Signed-off-by: Murali Karicheri Signed-off-by: David S. Miller --- include/uapi/linux/hsr_netlink.h | 2 +- include/uapi/linux/if_link.h | 12 +++++++++++- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/hsr_netlink.h b/include/uapi/linux/hsr_netlink.h index c218ef9c35dd..d540ea9bbef4 100644 --- a/include/uapi/linux/hsr_netlink.h +++ b/include/uapi/linux/hsr_netlink.h @@ -17,7 +17,7 @@ /* Generic Netlink HSR family definition */ -/* attributes */ +/* attributes for HSR or PRP node */ enum { HSR_A_UNSPEC, HSR_A_NODE_ADDR, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index af8f31987526..63af64646358 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -907,7 +907,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -917,6 +924,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; -- cgit v1.2.3 From 08b95c338e0c5a96e47f4ca314ea1e7580ecb5d7 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 8 Jul 2020 14:11:52 +0300 Subject: fanotify: remove event FAN_DIR_MODIFY It was never enabled in uapi and its functionality is about to be superseded by events FAN_CREATE, FAN_DELETE, FAN_MOVE with group flag FAN_REPORT_NAME. Keep a place holder variable name_event instead of removing the name recording code since it will be used by the new events. Link: https://lore.kernel.org/r/20200708111156.24659-17-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/uapi/linux/fanotify.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index a88c7c6d0692..7f2f17eacbf9 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -24,7 +24,6 @@ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ #define FAN_OPEN_EXEC_PERM 0x00040000 /* File open/exec in perm check */ -#define FAN_DIR_MODIFY 0x00080000 /* Directory entry was modified */ #define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ -- cgit v1.2.3 From 83b7a59896dd24015a34b7f00027f0ff3747972f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:26 +0300 Subject: fanotify: add basic support for FAN_REPORT_DIR_FID For now, the flag is mutually exclusive with FAN_REPORT_FID. Events include a single info record of type FAN_EVENT_INFO_TYPE_DFID with a directory file handle. For now, events are only reported for: - Directory modification events - Events on children of a watching directory - Events on directory objects Soon, we will add support for reporting the parent directory fid for events on non-directories with filesystem/mount mark and support for reporting both parent directory fid and child fid. Link: https://lore.kernel.org/r/20200716084230.30611-19-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/uapi/linux/fanotify.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 7f2f17eacbf9..21afebf77fd7 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -53,6 +53,7 @@ /* Flags to determine fanotify event format */ #define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ #define FAN_REPORT_FID 0x00000200 /* Report unique file id */ +#define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ @@ -117,6 +118,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_FID 1 #define FAN_EVENT_INFO_TYPE_DFID_NAME 2 +#define FAN_EVENT_INFO_TYPE_DFID 3 /* Variable length info record following event metadata */ struct fanotify_event_info_header { @@ -126,10 +128,11 @@ struct fanotify_event_info_header { }; /* - * Unique file identifier info record. This is used both for - * FAN_EVENT_INFO_TYPE_FID records and for FAN_EVENT_INFO_TYPE_DFID_NAME - * records. For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null - * terminated name immediately after the file handle. + * Unique file identifier info record. + * This structure is used for records of types FAN_EVENT_INFO_TYPE_FID, + * FAN_EVENT_INFO_TYPE_DFID and FAN_EVENT_INFO_TYPE_DFID_NAME. + * For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null terminated + * name immediately after the file handle. */ struct fanotify_event_info_fid { struct fanotify_event_info_header hdr; -- cgit v1.2.3 From 929943b38daf817f2e6d303ea04401651fc3bc05 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 16 Jul 2020 11:42:28 +0300 Subject: fanotify: add support for FAN_REPORT_NAME Introduce a new fanotify_init() flag FAN_REPORT_NAME. It requires the flag FAN_REPORT_DIR_FID and there is a constant for setting both flags named FAN_REPORT_DFID_NAME. For a group with flag FAN_REPORT_NAME, the parent fid and name are reported for directory entry modification events (create/detete/move) and for events on non-directory objects. Events on directories themselves are reported with their own fid and "." as the name. The parent fid and name are reported with an info record of type FAN_EVENT_INFO_TYPE_DFID_NAME, similar to the way that parent fid is reported with into type FAN_EVENT_INFO_TYPE_DFID, but with an appended null terminated name string. Link: https://lore.kernel.org/r/20200716084230.30611-21-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/uapi/linux/fanotify.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 21afebf77fd7..fbf9c5c7dd59 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -54,6 +54,10 @@ #define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ #define FAN_REPORT_FID 0x00000200 /* Report unique file id */ #define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ +#define FAN_REPORT_NAME 0x00000800 /* Report events with name */ + +/* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ +#define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ -- cgit v1.2.3 From e1613b5714ee6c186c9628e9958edf65e9d9cddd Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 27 Jul 2020 15:47:15 -0700 Subject: bpf: Fix bpf_ringbuf_output() signature to return long Due to bpf tree fix merge, bpf_ringbuf_output() signature ended up with int as a return type, while all other helpers got converted to returning long. So fix it in bpf-next now. Fixes: b0659d8a950d ("bpf: Fix definition of bpf_ringbuf_output() helper in UAPI comments") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20200727224715.652037-1-andriin@fb.com --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e1ba4ae6a916..eb5e0c38eb2c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3241,7 +3241,7 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * long bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification -- cgit v1.2.3 From bc2d214af5dbcf1e53be9a23d95905a585657ff4 Mon Sep 17 00:00:00 2001 From: Bodo Stroesser Date: Sun, 26 Jul 2020 17:35:09 +0200 Subject: scsi: target: tcmu: Implement tmr_notify callback This patch implements the tmr_notify callback for tcmu. When the callback is called, tcmu checks the list of aborted commands it received as parameter: - aborted commands in the qfull_queue are removed from the queue and target_complete_command is called - from the cmd_ids of aborted commands currently uncompleted in cmd ring it creates a list of aborted cmd_ids. Finally a TMR notification is written to cmd ring containing TMR type and cmd_id list. If there is no space in ring, the TMR notification is queued on a TMR specific queue. The TMR specific queue 'tmr_queue' can be seen as a extension of the cmd ring. At the end of each iexecution of tcmu_complete_commands() we check whether tmr_queue contains TMRs and try to move them onto the ring. If tmr_queue is not empty after that, we don't call run_qfull_queue() because commands must not overtake TMRs. This way we guarantee that cmd_ids in TMR notification received by userspace either match an active, not yet completed command or are no longer valid due to userspace having complete some cmd_ids meanwhile. New commands that were assigned to an aborted cmd_id will always appear on the cmd ring _after_ the TMR. Link: https://lore.kernel.org/r/20200726153510.13077-8-bstroesser@ts.fujitsu.com Reviewed-by: Mike Christie Signed-off-by: Bodo Stroesser Signed-off-by: Martin K. Petersen --- include/uapi/linux/target_core_user.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index b7b57967d90f..95b1597f16ae 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -45,6 +45,7 @@ #define ALIGN_SIZE 64 /* Should be enough for most CPUs */ #define TCMU_MAILBOX_FLAG_CAP_OOOC (1 << 0) /* Out-of-order completions */ #define TCMU_MAILBOX_FLAG_CAP_READ_LEN (1 << 1) /* Read data length */ +#define TCMU_MAILBOX_FLAG_CAP_TMR (1 << 2) /* TMR notifications */ struct tcmu_mailbox { __u16 version; @@ -62,6 +63,7 @@ struct tcmu_mailbox { enum tcmu_opcode { TCMU_OP_PAD = 0, TCMU_OP_CMD, + TCMU_OP_TMR, }; /* @@ -128,6 +130,29 @@ struct tcmu_cmd_entry { } __packed; +struct tcmu_tmr_entry { + struct tcmu_cmd_entry_hdr hdr; + +#define TCMU_TMR_UNKNOWN 0 +#define TCMU_TMR_ABORT_TASK 1 +#define TCMU_TMR_ABORT_TASK_SET 2 +#define TCMU_TMR_CLEAR_ACA 3 +#define TCMU_TMR_CLEAR_TASK_SET 4 +#define TCMU_TMR_LUN_RESET 5 +#define TCMU_TMR_TARGET_WARM_RESET 6 +#define TCMU_TMR_TARGET_COLD_RESET 7 +/* Pseudo reset due to received PR OUT */ +#define TCMU_TMR_LUN_RESET_PRO 128 + __u8 tmr_type; + + __u8 __pad1; + __u16 __pad2; + __u32 cmd_cnt; + __u64 __pad3; + __u64 __pad4; + __u16 cmd_ids[0]; +} __packed; + #define TCMU_OP_ALIGN_SIZE sizeof(__u64) enum tcmu_genl_cmd { -- cgit v1.2.3 From 556c811f24b30cc883733a2eaf9e939817589231 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 22 Jul 2020 17:03:09 +0300 Subject: RDMA/efa: Expose maximum TX doorbell batch The device reports the maximum number of bytes to be written before ringing the doorbell (zero means unlimited). This patch queries the max batch size and reports it back to the userspace library. Link: https://lore.kernel.org/r/20200722140312.3651-2-galpress@amazon.com Reviewed-by: Daniel Kranzdorf Reviewed-by: Firas JahJah Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/efa-abi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index 53b6e2036a9b..10781763da37 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* - * Copyright 2018-2019 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef EFA_ABI_USER_H @@ -31,6 +31,8 @@ struct efa_ibv_alloc_ucontext_resp { __u16 sub_cqs_per_cq; __u16 inline_buf_size; __u32 max_llq_size; /* bytes */ + __u16 max_tx_batch; /* units of 64 bytes */ + __u8 reserved_90[6]; }; struct efa_ibv_alloc_pd_resp { -- cgit v1.2.3 From da2924bdca99768442c5e0ed0a9024ae79d62765 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 22 Jul 2020 17:03:10 +0300 Subject: RDMA/efa: Expose minimum SQ size The device reports the minimum SQ size required for creation. This patch queries the min SQ size and reports it back to the userspace library. Link: https://lore.kernel.org/r/20200722140312.3651-3-galpress@amazon.com Reviewed-by: Firas JahJah Reviewed-by: Shadi Ammouri Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/efa-abi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index 10781763da37..7ef2306f8dd4 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -32,7 +32,8 @@ struct efa_ibv_alloc_ucontext_resp { __u16 inline_buf_size; __u32 max_llq_size; /* bytes */ __u16 max_tx_batch; /* units of 64 bytes */ - __u8 reserved_90[6]; + __u16 min_sq_wr; + __u8 reserved_a0[4]; }; struct efa_ibv_alloc_pd_resp { -- cgit v1.2.3 From a5d87b698547233321466b2dc91271f5855a4df6 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 22 Jul 2020 17:03:11 +0300 Subject: RDMA/efa: User/kernel compatibility handshake mechanism Introduce a mechanism that performs an handshake between the userspace provider and kernel driver which verifies that the user supports all required features in order to operate correctly. The handshake verifies the needed functionality by comparing the reported device caps and the provider caps. If the device reports a non-zero capability the appropriate comp mask is required from the userspace provider in order to allocate the context. Link: https://lore.kernel.org/r/20200722140312.3651-4-galpress@amazon.com Reviewed-by: Shadi Ammouri Reviewed-by: Yossi Leybovich Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/efa-abi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index 7ef2306f8dd4..507a2862bedb 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -20,6 +20,16 @@ * hex bit offset of the field. */ +enum { + EFA_ALLOC_UCONTEXT_CMD_COMP_TX_BATCH = 1 << 0, + EFA_ALLOC_UCONTEXT_CMD_COMP_MIN_SQ_WR = 1 << 1, +}; + +struct efa_ibv_alloc_ucontext_cmd { + __u32 comp_mask; + __u8 reserved_20[4]; +}; + enum efa_ibv_user_cmds_supp_udata { EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE = 1 << 0, EFA_USER_CMDS_SUPP_UDATA_CREATE_AH = 1 << 1, -- cgit v1.2.3 From 50935339c394adfb3d7253055e3bc10ee70264b0 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Sat, 25 Jul 2020 19:02:25 +0200 Subject: netfilter: Replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: Alexander A. Klimov Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_connmark.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/xt_connmark.h b/include/uapi/linux/netfilter/xt_connmark.h index 1aa5c955ee1e..f01c19b83a2b 100644 --- a/include/uapi/linux/netfilter/xt_connmark.h +++ b/include/uapi/linux/netfilter/xt_connmark.h @@ -4,7 +4,7 @@ #include -/* Copyright (C) 2002,2004 MARA Systems AB +/* Copyright (C) 2002,2004 MARA Systems AB * by Henrik Nordstrom * * This program is free software; you can redistribute it and/or modify -- cgit v1.2.3 From df78a0c0b67de58934877aad61e0431a2bd0caf1 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Mon, 1 Jun 2020 23:22:47 -0700 Subject: nl80211: S1G band and channel definitions Gives drivers the definitions needed to advertise support for S1G bands. Signed-off-by: Thomas Pedersen Link: https://lore.kernel.org/r/20200602062247.23212-1-thomas@adapt-ip.com Link: https://lore.kernel.org/r/20200731055636.795173-1-thomas@adapt-ip.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 4e6339ab1fce..ad183469f9af 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4437,6 +4437,11 @@ enum nl80211_key_mode { * attribute must be provided as well * @NL80211_CHAN_WIDTH_5: 5 MHz OFDM channel * @NL80211_CHAN_WIDTH_10: 10 MHz OFDM channel + * @NL80211_CHAN_WIDTH_1: 1 MHz OFDM channel + * @NL80211_CHAN_WIDTH_2: 2 MHz OFDM channel + * @NL80211_CHAN_WIDTH_4: 4 MHz OFDM channel + * @NL80211_CHAN_WIDTH_8: 8 MHz OFDM channel + * @NL80211_CHAN_WIDTH_16: 16 MHz OFDM channel */ enum nl80211_chan_width { NL80211_CHAN_WIDTH_20_NOHT, @@ -4447,6 +4452,11 @@ enum nl80211_chan_width { NL80211_CHAN_WIDTH_160, NL80211_CHAN_WIDTH_5, NL80211_CHAN_WIDTH_10, + NL80211_CHAN_WIDTH_1, + NL80211_CHAN_WIDTH_2, + NL80211_CHAN_WIDTH_4, + NL80211_CHAN_WIDTH_8, + NL80211_CHAN_WIDTH_16, }; /** @@ -4457,11 +4467,15 @@ enum nl80211_chan_width { * @NL80211_BSS_CHAN_WIDTH_20: control channel is 20 MHz wide or compatible * @NL80211_BSS_CHAN_WIDTH_10: control channel is 10 MHz wide * @NL80211_BSS_CHAN_WIDTH_5: control channel is 5 MHz wide + * @NL80211_BSS_CHAN_WIDTH_1: control channel is 1 MHz wide + * @NL80211_BSS_CHAN_WIDTH_2: control channel is 2 MHz wide */ enum nl80211_bss_scan_width { NL80211_BSS_CHAN_WIDTH_20, NL80211_BSS_CHAN_WIDTH_10, NL80211_BSS_CHAN_WIDTH_5, + NL80211_BSS_CHAN_WIDTH_1, + NL80211_BSS_CHAN_WIDTH_2, }; /** @@ -4740,6 +4754,7 @@ enum nl80211_txrate_gi { * @NL80211_BAND_5GHZ: around 5 GHz band (4.9 - 5.7 GHz) * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 69.12 GHz) * @NL80211_BAND_6GHZ: around 6 GHz band (5.9 - 7.2 GHz) + * @NL80211_BAND_S1GHZ: around 900MHz, supported by S1G PHYs * @NUM_NL80211_BANDS: number of bands, avoid using this in userspace * since newer kernel versions may support more bands */ @@ -4748,6 +4763,7 @@ enum nl80211_band { NL80211_BAND_5GHZ, NL80211_BAND_60GHZ, NL80211_BAND_6GHZ, + NL80211_BAND_S1GHZ, NUM_NL80211_BANDS, }; -- cgit v1.2.3 From 987021726f9f41a1daf335c57cd7b6261109cdb2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:43:21 -0700 Subject: net/wireless: nl80211.h: drop duplicate words in comments Drop doubled words in several comments. Signed-off-by: Randy Dunlap Cc: netdev@vger.kernel.org Cc: Kalle Valo Cc: linux-wireless@vger.kernel.org Cc: Johannes Berg Link: https://lore.kernel.org/r/20200715164325.9109-1-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ad183469f9af..f47a7a8d0216 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -363,7 +363,7 @@ * @NL80211_CMD_SET_STATION: Set station attributes for station identified by * %NL80211_ATTR_MAC on the interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_NEW_STATION: Add a station with given attributes to the - * the interface identified by %NL80211_ATTR_IFINDEX. + * interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_DEL_STATION: Remove a station identified by %NL80211_ATTR_MAC * or, if no MAC address given, all stations, on the interface identified * by %NL80211_ATTR_IFINDEX. %NL80211_ATTR_MGMT_SUBTYPE and @@ -383,7 +383,7 @@ * @NL80211_CMD_DEL_MPATH: Delete a mesh path to the destination given by * %NL80211_ATTR_MAC. * @NL80211_CMD_NEW_PATH: Add a mesh path with given attributes to the - * the interface identified by %NL80211_ATTR_IFINDEX. + * interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_DEL_PATH: Remove a mesh path identified by %NL80211_ATTR_MAC * or, if no MAC address given, all mesh paths, on the interface identified * by %NL80211_ATTR_IFINDEX. @@ -934,7 +934,7 @@ * @NL80211_CMD_SET_COALESCE: Configure coalesce rules or clear existing rules. * * @NL80211_CMD_CHANNEL_SWITCH: Perform a channel switch by announcing the - * the new channel information (Channel Switch Announcement - CSA) + * new channel information (Channel Switch Announcement - CSA) * in the beacon for some time (as defined in the * %NL80211_ATTR_CH_SWITCH_COUNT parameter) and then change to the * new channel. Userspace provides the new channel information (using @@ -1113,7 +1113,7 @@ * randomization may be enabled and configured by specifying the * %NL80211_ATTR_MAC and %NL80211_ATTR_MAC_MASK attributes. * If a timeout is requested, use the %NL80211_ATTR_TIMEOUT attribute. - * A u64 cookie for further %NL80211_ATTR_COOKIE use is is returned in + * A u64 cookie for further %NL80211_ATTR_COOKIE use is returned in * the netlink extended ack message. * * To cancel a measurement, close the socket that requested it. @@ -1511,7 +1511,7 @@ enum nl80211_commands { * rates as defined by IEEE 802.11 7.3.2.2 but without the length * restriction (at most %NL80211_MAX_SUPP_RATES). * @NL80211_ATTR_STA_VLAN: interface index of VLAN interface to move station - * to, or the AP interface the station was originally added to to. + * to, or the AP interface the station was originally added to. * @NL80211_ATTR_STA_INFO: information about a station, part of station info * given for %NL80211_CMD_GET_STATION, nested attribute containing * info as possible, see &enum nl80211_sta_info. @@ -2084,7 +2084,7 @@ enum nl80211_commands { * @NL80211_ATTR_STA_SUPPORTED_CHANNELS: array of supported channels. * * @NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES: array of supported - * supported operating classes. + * operating classes. * * @NL80211_ATTR_HANDLE_DFS: A flag indicating whether user space * controls DFS operation in IBSS mode. If the flag is included in @@ -2395,7 +2395,7 @@ enum nl80211_commands { * nl80211_txq_stats) * @NL80211_ATTR_TXQ_LIMIT: Total packet limit for the TXQ queues for this phy. * The smaller of this and the memory limit is enforced. - * @NL80211_ATTR_TXQ_MEMORY_LIMIT: Total memory memory limit (in bytes) for the + * @NL80211_ATTR_TXQ_MEMORY_LIMIT: Total memory limit (in bytes) for the * TXQ queues for this phy. The smaller of this and the packet limit is * enforced. * @NL80211_ATTR_TXQ_QUANTUM: TXQ scheduler quantum (bytes). Number of bytes @@ -5652,7 +5652,7 @@ enum nl80211_feature_flags { * enum nl80211_ext_feature_index - bit index of extended features. * @NL80211_EXT_FEATURE_VHT_IBSS: This driver supports IBSS with VHT datarates. * @NL80211_EXT_FEATURE_RRM: This driver supports RRM. When featured, user can - * can request to use RRM (see %NL80211_ATTR_USE_RRM) with + * request to use RRM (see %NL80211_ATTR_USE_RRM) with * %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set * the ASSOC_REQ_USE_RRM flag in the association request even if * NL80211_FEATURE_QUIET is not advertized. @@ -6061,7 +6061,7 @@ enum nl80211_dfs_state { }; /** - * enum enum nl80211_protocol_features - nl80211 protocol features + * enum nl80211_protocol_features - nl80211 protocol features * @NL80211_PROTOCOL_FEATURE_SPLIT_WIPHY_DUMP: nl80211 supports splitting * wiphy dumps (if requested by the application with the attribute * %NL80211_ATTR_SPLIT_WIPHY_DUMP. Also supported is filtering the -- cgit v1.2.3 From 0f55c0c500f2bbfc5cc5590cdf6973b3f64dc195 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:43:22 -0700 Subject: net/wireless: wireless.h: drop duplicate word in comments Drop doubled word "threshold" in a comment. Signed-off-by: Randy Dunlap Cc: netdev@vger.kernel.org Cc: Kalle Valo Cc: linux-wireless@vger.kernel.org Cc: Johannes Berg Link: https://lore.kernel.org/r/20200715164325.9109-2-rdunlap@infradead.org Signed-off-by: Johannes Berg --- include/uapi/linux/wireless.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index 24f3371ad826..08967b3f19c8 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -914,7 +914,7 @@ union iwreq_data { struct iw_param sens; /* signal level threshold */ struct iw_param bitrate; /* default bit rate */ struct iw_param txpower; /* default transmit power */ - struct iw_param rts; /* RTS threshold threshold */ + struct iw_param rts; /* RTS threshold */ struct iw_param frag; /* Fragmentation threshold */ __u32 mode; /* Operation mode */ struct iw_param retry; /* Retry limits & lifetime */ -- cgit v1.2.3 From e3718a611470d311a92c60d4eb535270b49a7108 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Wed, 17 Jun 2020 09:30:33 +0200 Subject: cfg80211/mac80211: add mesh_param "mesh_nolearn" to skip path discovery MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, before being able to forward a packet between two 802.11s nodes, both a PLINK handshake is performed upon receiving a beacon and then later a PREQ/PREP exchange for path discovery is performed on demand upon receiving a data frame to forward. When running a mesh protocol on top of an 802.11s interface, like batman-adv, we do not need the multi-hop mesh routing capabilities of 802.11s and usually set mesh_fwding=0. However, even with mesh_fwding=0 the PREQ/PREP path discovery is still performed on demand. Even though in this scenario the next hop PREQ/PREP will determine is always the direct 11s neighbor node. The new mesh_nolearn parameter allows to skip the PREQ/PREP exchange in this scenario, leading to a reduced delay, reduced packet buffering and simplifies HWMP in general. mesh_nolearn is still rather conservative in that if the packet destination is not a direct 11s neighbor, it will fall back to PREQ/PREP path discovery. For normal, multi-hop 802.11s mesh routing it is usually not advisable to enable mesh_nolearn as a transmission to a direct but distant neighbor might be worse than reaching that same node via a more robust / higher throughput etc. multi-hop path. Cc: Sven Eckelmann Cc: Simon Wunderlich Signed-off-by: Linus Lüssing Link: https://lore.kernel.org/r/20200617073034.26149-1-linus.luessing@c0d3.blue [fix nl80211 policy to range 0/1 only] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f47a7a8d0216..a83d8faf88ac 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4236,6 +4236,12 @@ enum nl80211_mesh_power_mode { * field. If left unset then the mesh formation field will only * advertise such if there is an active root mesh path. * + * @NL80211_MESHCONF_NOLEARN: Try to avoid multi-hop path discovery (e.g. + * PREQ/PREP for HWMP) if the destination is a direct neighbor. Note that + * this might not be the optimal decision as a multi-hop route might be + * better. So if using this setting you will likely also want to disable + * dot11MeshForwarding and use another mesh routing protocol on top. + * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ enum nl80211_meshconf_params { @@ -4269,6 +4275,7 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_AWAKE_WINDOW, NL80211_MESHCONF_PLINK_TIMEOUT, NL80211_MESHCONF_CONNECTED_TO_GATE, + NL80211_MESHCONF_NOLEARN, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, -- cgit v1.2.3 From 184eebe664f0e11c485f6d309fe56297b3f75e9e Mon Sep 17 00:00:00 2001 From: Markus Theil Date: Thu, 11 Jun 2020 16:02:37 +0200 Subject: cfg80211/mac80211: add connected to auth server to meshconf Besides information about num of peerings and gate connectivity, the mesh formation byte also contains a flag for authentication server connectivity, that currently cannot be set in the mesh conf. This patch adds this capability, which is necessary to implement 802.1X authentication in mesh mode. Signed-off-by: Markus Theil Link: https://lore.kernel.org/r/20200611140238.427461-1-markus.theil@tu-ilmenau.de Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a83d8faf88ac..f1770e3756f4 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4242,6 +4242,10 @@ enum nl80211_mesh_power_mode { * better. So if using this setting you will likely also want to disable * dot11MeshForwarding and use another mesh routing protocol on top. * + * @NL80211_MESHCONF_CONNECTED_TO_AS: If set to true then this mesh STA + * will advertise that it is connected to a authentication server + * in the mesh formation field. + * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ enum nl80211_meshconf_params { @@ -4276,6 +4280,7 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_PLINK_TIMEOUT, NL80211_MESHCONF_CONNECTED_TO_GATE, NL80211_MESHCONF_NOLEARN, + NL80211_MESHCONF_CONNECTED_TO_AS, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, -- cgit v1.2.3 From 1303a51c24100b3b1915d6f9072fe5ae5bb4c5f6 Mon Sep 17 00:00:00 2001 From: Markus Theil Date: Thu, 11 Jun 2020 16:02:38 +0200 Subject: cfg80211/mac80211: add connected to auth server to station info This patch adds the necessary bits to later query the auth server flag for every peer from iw. Signed-off-by: Markus Theil Link: https://lore.kernel.org/r/20200611140238.427461-2-markus.theil@tu-ilmenau.de Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f1770e3756f4..d6b6599a6001 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3370,6 +3370,8 @@ enum nl80211_sta_bss_param { * @NL80211_STA_INFO_AIRTIME_LINK_METRIC: airtime link metric for mesh station * @NL80211_STA_INFO_ASSOC_AT_BOOTTIME: Timestamp (CLOCK_BOOTTIME, nanoseconds) * of STA's association + * @NL80211_STA_INFO_CONNECTED_TO_AS: set to true if STA has a path to a + * authentication server (u8, 0 or 1) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -3417,6 +3419,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_AIRTIME_WEIGHT, NL80211_STA_INFO_AIRTIME_LINK_METRIC, NL80211_STA_INFO_ASSOC_AT_BOOTTIME, + NL80211_STA_INFO_CONNECTED_TO_AS, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, -- cgit v1.2.3 From fd17dba1c860d39f655a3a08387c21e3ceca8c55 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Mon, 20 Jul 2020 13:12:25 +0530 Subject: cfg80211: Add support to advertize OCV support Add a new feature flag that drivers can use to advertize support for Operating Channel Validation (OCV) when using driver's SME for RSNA handshakes. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20200720074225.8990-1-vjakkam@codeaurora.org Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d6b6599a6001..a3ae2b060a55 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5804,6 +5804,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS: The driver * can report tx status for control port over nl80211 tx operations. * + * @NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION: Driver supports Operating + * Channel Validation (OCV) when using driver's SME for RSNA handshakes. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5859,6 +5862,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT, NL80211_EXT_FEATURE_SCAN_FREQ_KHZ, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, + NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From f96622749a67d40ad5efe8a58d5fc95313097aa0 Mon Sep 17 00:00:00 2001 From: Chung-Hsien Hsu Date: Tue, 23 Jun 2020 08:49:35 -0500 Subject: nl80211: support 4-way handshake offloading for WPA/WPA2-PSK in AP mode Let drivers advertise support for AP-mode WPA/WPA2-PSK 4-way handshake offloading with a new NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK flag. Extend use of NL80211_ATTR_PMK attribute indicating it might be passed as part of NL80211_CMD_START_AP command, and contain the PSK (which is the PMK, hence the name). The driver is assumed to handle the 4-way handshake by itself in this case, instead of relying on userspace. Signed-off-by: Chung-Hsien Hsu Signed-off-by: Chi-Hsien Lin Link: https://lore.kernel.org/r/20200623134938.39997-2-chi-hsien.lin@cypress.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 41 ++++++++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a3ae2b060a55..631f3a997b3c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -183,18 +183,27 @@ * * By setting @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK flag drivers * can indicate they support offloading EAPOL handshakes for WPA/WPA2 - * preshared key authentication. In %NL80211_CMD_CONNECT the preshared - * key should be specified using %NL80211_ATTR_PMK. Drivers supporting - * this offload may reject the %NL80211_CMD_CONNECT when no preshared - * key material is provided, for example when that driver does not - * support setting the temporal keys through %CMD_NEW_KEY. + * preshared key authentication in station mode. In %NL80211_CMD_CONNECT + * the preshared key should be specified using %NL80211_ATTR_PMK. Drivers + * supporting this offload may reject the %NL80211_CMD_CONNECT when no + * preshared key material is provided, for example when that driver does + * not support setting the temporal keys through %NL80211_CMD_NEW_KEY. * * Similarly @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X flag can be * set by drivers indicating offload support of the PTK/GTK EAPOL - * handshakes during 802.1X authentication. In order to use the offload - * the %NL80211_CMD_CONNECT should have %NL80211_ATTR_WANT_1X_4WAY_HS - * attribute flag. Drivers supporting this offload may reject the - * %NL80211_CMD_CONNECT when the attribute flag is not present. + * handshakes during 802.1X authentication in station mode. In order to + * use the offload the %NL80211_CMD_CONNECT should have + * %NL80211_ATTR_WANT_1X_4WAY_HS attribute flag. Drivers supporting this + * offload may reject the %NL80211_CMD_CONNECT when the attribute flag is + * not present. + * + * By setting @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK flag drivers + * can indicate they support offloading EAPOL handshakes for WPA/WPA2 + * preshared key authentication in AP mode. In %NL80211_CMD_START_AP + * the preshared key should be specified using %NL80211_ATTR_PMK. Drivers + * supporting this offload may reject the %NL80211_CMD_START_AP when no + * preshared key material is provided, for example when that driver does + * not support setting the temporal keys through %NL80211_CMD_NEW_KEY. * * For 802.1X the PMK or PMK-R0 are set by providing %NL80211_ATTR_PMK * using %NL80211_CMD_SET_PMK. For offloaded FT support also @@ -2362,10 +2371,11 @@ enum nl80211_commands { * * @NL80211_ATTR_PMK: attribute for passing PMK key material. Used with * %NL80211_CMD_SET_PMKSA for the PMKSA identified by %NL80211_ATTR_PMKID. - * For %NL80211_CMD_CONNECT it is used to provide PSK for offloading 4-way - * handshake for WPA/WPA2-PSK networks. For 802.1X authentication it is - * used with %NL80211_CMD_SET_PMK. For offloaded FT support this attribute - * specifies the PMK-R0 if NL80211_ATTR_PMKR0_NAME is included as well. + * For %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP it is used to provide + * PSK for offloading 4-way handshake for WPA/WPA2-PSK networks. For 802.1X + * authentication it is used with %NL80211_CMD_SET_PMK. For offloaded FT + * support this attribute specifies the PMK-R0 if NL80211_ATTR_PMKR0_NAME + * is included as well. * * @NL80211_ATTR_SCHED_SCAN_MULTI: flag attribute which user-space shall use to * indicate that it supports multiple active scheduled scan requests. @@ -5807,6 +5817,10 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION: Driver supports Operating * Channel Validation (OCV) when using driver's SME for RSNA handshakes. * + * @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK: Device wants to do 4-way + * handshake with PSK in AP mode (PSK is passed as part of the start AP + * command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5863,6 +5877,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCAN_FREQ_KHZ, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 48040793fa6003d211f021c6ad273477bcd90d91 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Thu, 30 Jul 2020 15:44:40 -0700 Subject: tcp: add earliest departure time to SCM_TIMESTAMPING_OPT_STATS This change adds TCP_NLA_EDT to SCM_TIMESTAMPING_OPT_STATS that reports the earliest departure time(EDT) of the timestamped skb. By tracking EDT values of the skb from different timestamps, we can observe when and how much the value changed. This allows to measure the precise delay injected on the sender host e.g. by a bpf-base throttler. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index f2acb2566333..cfcb10b75483 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -313,6 +313,7 @@ enum { TCP_NLA_SRTT, /* smoothed RTT in usecs */ TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ + TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ }; /* for TCP_MD5SIG socket option */ -- cgit v1.2.3 From 829eb208e80d6db95c0201cb8fa00c2f9ad87faf Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 31 Jul 2020 17:34:01 -0700 Subject: rtnetlink: add support for protodown reason netdev protodown is a mechanism that allows protocols to hold an interface down. It was initially introduced in the kernel to hold links down by a multihoming protocol. There was also an attempt to introduce protodown reason at the time but was rejected. protodown and protodown reason is supported by almost every switching and routing platform. It was ok for a while to live without a protodown reason. But, its become more critical now given more than one protocol may need to keep a link down on a system at the same time. eg: vrrp peer node, port security, multihoming protocol. Its common for Network operators and protocol developers to look for such a reason on a networking box (Its also known as errDisable by most networking operators) This patch adds support for link protodown reason attribute. There are two ways to maintain protodown reasons. (a) enumerate every possible reason code in kernel - A protocol developer has to make a request and have that appear in a certain kernel version (b) provide the bits in the kernel, and allow user-space (sysadmin or NOS distributions) to manage the bit-to-reasonname map. - This makes extending reason codes easier (kind of like the iproute2 table to vrf-name map /etc/iproute2/rt_tables.d/) This patch takes approach (b). a few things about the patch: - It treats the protodown reason bits as counter to indicate active protodown users - Since protodown attribute is already an exposed UAPI, the reason is not enforced on a protodown set. Its a no-op if not used. the patch follows the below algorithm: - presence of reason bits set indicates protodown is in use - user can set protodown and protodown reason in a single or multiple setlink operations - setlink operation to clear protodown, will return -EBUSY if there are active protodown reason bits - reason is not included in link dumps if not used example with patched iproute2: $cat /etc/iproute2/protodown_reasons.d/r.conf 0 mlag 1 evpn 2 vrrp 3 psecurity $ip link set dev vxlan0 protodown on protodown_reason vrrp on $ip link set dev vxlan0 protodown_reason mlag on $ip link show 14: vxlan0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether f6:06:be:17:91:e7 brd ff:ff:ff:ff:ff:ff protodown on $ip link set dev vxlan0 protodown_reason mlag off $ip link set dev vxlan0 protodown off protodown_reason vrrp off Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 63af64646358..7fba4de511de 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -170,12 +170,22 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) -- cgit v1.2.3 From 73b11c2ab072d5b0599d1e12cc126f55ee306daf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 31 Jul 2020 11:28:26 -0700 Subject: bpf: Add support for forced LINK_DETACH command Add LINK_DETACH command to force-detach bpf_link without destroying it. It has the same behavior as auto-detaching of bpf_link due to cgroup dying for bpf_cgroup_link or net_device being destroyed for bpf_xdp_link. In such case, bpf_link is still a valid kernel object, but is defuncts and doesn't hold BPF program attached to corresponding BPF hook. This functionality allows users with enough access rights to manually force-detach attached bpf_link without killing respective owner process. This patch implements LINK_DETACH for cgroup, xdp, and netns links, mostly re-using existing link release handling code. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200731182830.286260-2-andriin@fb.com --- include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index eb5e0c38eb2c..b134e679e9db 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -117,6 +117,7 @@ enum bpf_cmd { BPF_LINK_GET_NEXT_ID, BPF_ENABLE_STATS, BPF_ITER_CREATE, + BPF_LINK_DETACH, }; enum bpf_map_type { @@ -634,6 +635,10 @@ union bpf_attr { __u32 old_prog_fd; } link_update; + struct { + __u32 link_fd; + } link_detach; + struct { /* struct used by BPF_ENABLE_STATS command */ __u32 type; } enable_stats; -- cgit v1.2.3 From f8951902b9daa65ba240ce8a054c727748df2147 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:32:08 -0700 Subject: MTD: mtd-abi.h: drop a duplicated word Drop the repeated word "mode" in a comment. Signed-off-by: Randy Dunlap Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Cc: linux-mtd@lists.infradead.org Signed-off-by: Richard Weinberger --- include/uapi/mtd/mtd-abi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h index 4b48fbf7d343..65b9db936557 100644 --- a/include/uapi/mtd/mtd-abi.h +++ b/include/uapi/mtd/mtd-abi.h @@ -262,7 +262,7 @@ struct mtd_ecc_stats { * @MTD_FILE_MODE_OTP_USER: OTP enabled in user mode * @MTD_FILE_MODE_RAW: OTP disabled, ECC disabled * - * These modes can be set via ioctl(MTDFILEMODE). The mode mode will be retained + * These modes can be set via ioctl(MTDFILEMODE). The mode will be retained * separately for each open file descriptor. * * Note: %MTD_FILE_MODE_RAW provides the same functionality as %MTD_OPS_RAW - -- cgit v1.2.3 From e5a52fd2b8cdb700b3c07b030e050a49ef3156b9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 18 Jul 2020 17:33:17 -0700 Subject: xen/gntdev: gntdev.h: drop a duplicated word Drop the repeated word "of" in a comment. Signed-off-by: Randy Dunlap Reviewed-by: Juergen Gross Cc: Boris Ostrovsky Cc: Juergen Gross Cc: xen-devel@lists.xenproject.org Link: https://lore.kernel.org/r/20200719003317.21454-1-rdunlap@infradead.org Signed-off-by: Juergen Gross --- include/uapi/xen/gntdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index fe4423e518c6..9ac5515b9bc2 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -66,7 +66,7 @@ struct ioctl_gntdev_map_grant_ref { /* * Removes the grant references from the mapping table of an instance of - * of gntdev. N.B. munmap() must be called on the relevant virtual address(es) + * gntdev. N.B. munmap() must be called on the relevant virtual address(es) * before this ioctl is called, or an error will result. */ #define IOCTL_GNTDEV_UNMAP_GRANT_REF \ -- cgit v1.2.3 From 321bd212619a7269308696e4ddc446930ea73fad Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Jun 2020 18:24:33 -0400 Subject: virtio: VIRTIO_F_IOMMU_PLATFORM -> VIRTIO_F_ACCESS_PLATFORM Rename the bit to match latest virtio spec. Add a compat macro to avoid breaking existing userspace. Signed-off-by: Michael S. Tsirkin Reviewed-by: David Hildenbrand --- include/uapi/linux/virtio_config.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index ff8e7dc9d4dd..b5eda06f0d57 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -67,13 +67,17 @@ #define VIRTIO_F_VERSION_1 32 /* - * If clear - device has the IOMMU bypass quirk feature. - * If set - use platform tools to detect the IOMMU. + * If clear - device has the platform DMA (e.g. IOMMU) bypass quirk feature. + * If set - use platform DMA tools to access the memory. * * Note the reverse polarity (compared to most other features), * this is for compatibility with legacy systems. */ -#define VIRTIO_F_IOMMU_PLATFORM 33 +#define VIRTIO_F_ACCESS_PLATFORM 33 +#ifndef __KERNEL__ +/* Legacy name for VIRTIO_F_ACCESS_PLATFORM (for compatibility with old userspace) */ +#define VIRTIO_F_IOMMU_PLATFORM VIRTIO_F_ACCESS_PLATFORM +#endif /* __KERNEL__ */ /* This feature indicates support for the packed virtqueue layout. */ #define VIRTIO_F_RING_PACKED 34 -- cgit v1.2.3 From 9d2f627b7ec9d5d3246b6cec17f290ee6778c83b Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Fri, 31 Jul 2020 14:20:56 +0200 Subject: net: openvswitch: add masks cache hit counter Add a counter that counts the number of masks cache hits, and export it through the megaflow netlink statistics. Reviewed-by: Paolo Abeni Reviewed-by: Tonghao Zhang Signed-off-by: Eelco Chaudron Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 9b14519e74d9..7cb76e5ca7cf 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -102,8 +102,8 @@ struct ovs_dp_megaflow_stats { __u64 n_mask_hit; /* Number of masks used for flow lookups. */ __u32 n_masks; /* Number of masks for the datapath. */ __u32 pad0; /* Pad for future expension. */ + __u64 n_cache_hit; /* Number of cache matches for flow lookups. */ __u64 pad1; /* Pad for future expension. */ - __u64 pad2; /* Pad for future expension. */ }; struct ovs_vport_stats { -- cgit v1.2.3 From 9bf24f594c6acf676fb8c229f152c21bfb915ddb Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Fri, 31 Jul 2020 14:21:34 +0200 Subject: net: openvswitch: make masks cache size configurable This patch makes the masks cache size configurable, or with a size of 0, disable it. Reviewed-by: Paolo Abeni Reviewed-by: Tonghao Zhang Signed-off-by: Eelco Chaudron Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 7cb76e5ca7cf..8300cc29dec8 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -86,6 +86,7 @@ enum ovs_datapath_attr { OVS_DP_ATTR_MEGAFLOW_STATS, /* struct ovs_dp_megaflow_stats */ OVS_DP_ATTR_USER_FEATURES, /* OVS_DP_F_* */ OVS_DP_ATTR_PAD, + OVS_DP_ATTR_MASKS_CACHE_SIZE, __OVS_DP_ATTR_MAX }; -- cgit v1.2.3 From 88fab21c691bb1ff164e540735237a385e3afeaf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ioana-Ruxandra=20St=C4=83ncioi?= Date: Mon, 3 Aug 2020 07:33:33 +0000 Subject: seg6_iptunnel: Refactor seg6_lwt_headroom out of uapi header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Refactor the function seg6_lwt_headroom out of the seg6_iptunnel.h uapi header, because it is only used in seg6_iptunnel.c. Moreover, it is only used in the kernel code, as indicated by the "#ifdef __KERNEL__". Suggested-by: David Miller Signed-off-by: Ioana-Ruxandra Stăncioi Signed-off-by: David S. Miller --- include/uapi/linux/seg6_iptunnel.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index 09fb608a35ec..eb815e0d0ac3 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -37,25 +37,4 @@ enum { SEG6_IPTUN_MODE_L2ENCAP, }; -#ifdef __KERNEL__ - -static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) -{ - int head = 0; - - switch (tuninfo->mode) { - case SEG6_IPTUN_MODE_INLINE: - break; - case SEG6_IPTUN_MODE_ENCAP: - head = sizeof(struct ipv6hdr); - break; - case SEG6_IPTUN_MODE_L2ENCAP: - return 0; - } - - return ((tuninfo->srh->hdrlen + 1) << 3) + head; -} - -#endif - #endif -- cgit v1.2.3 From 4476770881d7ac647e3bcae0943f37e00b9c3f3c Mon Sep 17 00:00:00 2001 From: Siddharth Gupta Date: Wed, 29 Jul 2020 10:40:00 -0700 Subject: remoteproc: Add remoteproc character device interface Add the character device interface into remoteproc framework. This interface can be used in order to boot/shutdown remote subsystems and provides a basic ioctl based interface to implement supplementary functionality. An ioctl call is implemented to enable the shutdown on release feature which will allow remote processors to be shutdown when the controlling userspace application crashes or hangs. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Rishabh Bhatnagar Signed-off-by: Siddharth Gupta Link: https://lore.kernel.org/r/1596044401-22083-2-git-send-email-sidgup@codeaurora.org [bjorn: s/int32_t/s32/ per checkpatch] Signed-off-by: Bjorn Andersson --- include/uapi/linux/remoteproc_cdev.h | 37 ++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/uapi/linux/remoteproc_cdev.h (limited to 'include/uapi') diff --git a/include/uapi/linux/remoteproc_cdev.h b/include/uapi/linux/remoteproc_cdev.h new file mode 100644 index 000000000000..c43768e4b0dc --- /dev/null +++ b/include/uapi/linux/remoteproc_cdev.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * IOCTLs for Remoteproc's character device interface. + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _UAPI_REMOTEPROC_CDEV_H_ +#define _UAPI_REMOTEPROC_CDEV_H_ + +#include +#include + +#define RPROC_MAGIC 0xB7 + +/* + * The RPROC_SET_SHUTDOWN_ON_RELEASE ioctl allows to enable/disable the shutdown of a remote + * processor automatically when the controlling userpsace closes the char device interface. + * + * input parameter: integer + * 0 : disable automatic shutdown + * other : enable automatic shutdown + */ +#define RPROC_SET_SHUTDOWN_ON_RELEASE _IOW(RPROC_MAGIC, 1, __s32) + +/* + * The RPROC_GET_SHUTDOWN_ON_RELEASE ioctl gets information about whether the automatic shutdown of + * a remote processor is enabled or disabled when the controlling userspace closes the char device + * interface. + * + * output parameter: integer + * 0 : automatic shutdown disable + * other : automatic shutdown enable + */ +#define RPROC_GET_SHUTDOWN_ON_RELEASE _IOR(RPROC_MAGIC, 2, __s32) + +#endif -- cgit v1.2.3 From cae19a6386c86dec8ec2810a96d7497a2eec8d38 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_9p: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_9p.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_9p.h b/include/uapi/linux/virtio_9p.h index 277c4ad44e84..441047432258 100644 --- a/include/uapi/linux/virtio_9p.h +++ b/include/uapi/linux/virtio_9p.h @@ -25,7 +25,7 @@ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ -#include +#include #include #include @@ -36,7 +36,7 @@ struct virtio_9p_config { /* length of the tag name */ - __u16 tag_len; + __virtio16 tag_len; /* non-NULL terminated tag name */ __u8 tag[0]; } __attribute__((packed)); -- cgit v1.2.3 From c73cb10cc4421baa669c1edd8211086280273216 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_balloon: correct tags for config space fields Tag config space fields as having little endian-ness. Note that balloon is special: LE even when using the legacy interface. Signed-off-by: Michael S. Tsirkin Acked-by: David Hildenbrand Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_balloon.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index dc3e656470dd..ddaa45e723c4 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -45,20 +45,20 @@ #define VIRTIO_BALLOON_CMD_ID_DONE 1 struct virtio_balloon_config { /* Number of pages host wants Guest to give up. */ - __u32 num_pages; + __le32 num_pages; /* Number of pages we've actually got in balloon. */ - __u32 actual; + __le32 actual; /* * Free page hint command id, readonly by guest. * Was previously named free_page_report_cmd_id so we * need to carry that name for legacy support. */ union { - __u32 free_page_hint_cmd_id; - __u32 free_page_report_cmd_id; /* deprecated */ + __le32 free_page_hint_cmd_id; + __le32 free_page_report_cmd_id; /* deprecated */ }; /* Stores PAGE_POISON if page poisoning is in use */ - __u32 poison_val; + __le32 poison_val; }; #define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */ -- cgit v1.2.3 From 40e04c488bd6ab1859778d40bf9bb3ca294ab97b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_blk: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck Reviewed-by: Stefano Garzarella Reviewed-by: Stefano Garzarella --- include/uapi/linux/virtio_blk.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 0f99d7b49ede..d888f013d9ff 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -57,20 +57,20 @@ struct virtio_blk_config { /* The capacity (in 512-byte sectors). */ - __u64 capacity; + __virtio64 capacity; /* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */ - __u32 size_max; + __virtio32 size_max; /* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */ - __u32 seg_max; + __virtio32 seg_max; /* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */ struct virtio_blk_geometry { - __u16 cylinders; + __virtio16 cylinders; __u8 heads; __u8 sectors; } geometry; /* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */ - __u32 blk_size; + __virtio32 blk_size; /* the next 4 entries are guarded by VIRTIO_BLK_F_TOPOLOGY */ /* exponent for physical block per logical block. */ @@ -78,42 +78,42 @@ struct virtio_blk_config { /* alignment offset in logical blocks. */ __u8 alignment_offset; /* minimum I/O size without performance penalty in logical blocks. */ - __u16 min_io_size; + __virtio16 min_io_size; /* optimal sustained I/O size in logical blocks. */ - __u32 opt_io_size; + __virtio32 opt_io_size; /* writeback mode (if VIRTIO_BLK_F_CONFIG_WCE) */ __u8 wce; __u8 unused; /* number of vqs, only available when VIRTIO_BLK_F_MQ is set */ - __u16 num_queues; + __virtio16 num_queues; /* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */ /* * The maximum discard sectors (in 512-byte sectors) for * one segment. */ - __u32 max_discard_sectors; + __virtio32 max_discard_sectors; /* * The maximum number of discard segments in a * discard command. */ - __u32 max_discard_seg; + __virtio32 max_discard_seg; /* Discard commands must be aligned to this number of sectors. */ - __u32 discard_sector_alignment; + __virtio32 discard_sector_alignment; /* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */ /* * The maximum number of write zeroes sectors (in 512-byte sectors) in * one segment. */ - __u32 max_write_zeroes_sectors; + __virtio32 max_write_zeroes_sectors; /* * The maximum number of segments in a write zeroes * command. */ - __u32 max_write_zeroes_seg; + __virtio32 max_write_zeroes_seg; /* * Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the * deallocation of one or more of the sectors. -- cgit v1.2.3 From dbe2dc8c5838ef415620a4fe691570b062ab046f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_console: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_console.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_console.h b/include/uapi/linux/virtio_console.h index b7fb108c9310..7e6ec2ff0560 100644 --- a/include/uapi/linux/virtio_console.h +++ b/include/uapi/linux/virtio_console.h @@ -45,13 +45,13 @@ struct virtio_console_config { /* colums of the screens */ - __u16 cols; + __virtio16 cols; /* rows of the screens */ - __u16 rows; + __virtio16 rows; /* max. number of ports this device can hold */ - __u32 max_nr_ports; + __virtio32 max_nr_ports; /* emergency write register */ - __u32 emerg_wr; + __virtio32 emerg_wr; } __attribute__((packed)); /* -- cgit v1.2.3 From 24bcf35b695ef5228f3035eb979cc2de571d560b Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_crypto: correct tags for config space fields Since crypto is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_crypto.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h index 50cdc8aebfcf..a03932f10565 100644 --- a/include/uapi/linux/virtio_crypto.h +++ b/include/uapi/linux/virtio_crypto.h @@ -414,33 +414,33 @@ struct virtio_crypto_op_data_req { struct virtio_crypto_config { /* See VIRTIO_CRYPTO_OP_* above */ - __u32 status; + __le32 status; /* * Maximum number of data queue */ - __u32 max_dataqueues; + __le32 max_dataqueues; /* * Specifies the services mask which the device support, * see VIRTIO_CRYPTO_SERVICE_* above */ - __u32 crypto_services; + __le32 crypto_services; /* Detailed algorithms mask */ - __u32 cipher_algo_l; - __u32 cipher_algo_h; - __u32 hash_algo; - __u32 mac_algo_l; - __u32 mac_algo_h; - __u32 aead_algo; + __le32 cipher_algo_l; + __le32 cipher_algo_h; + __le32 hash_algo; + __le32 mac_algo_l; + __le32 mac_algo_h; + __le32 aead_algo; /* Maximum length of cipher key */ - __u32 max_cipher_key_len; + __le32 max_cipher_key_len; /* Maximum length of authenticated key */ - __u32 max_auth_key_len; - __u32 reserve; + __le32 max_auth_key_len; + __le32 reserve; /* Maximum size of each crypto request's content */ - __u64 max_size; + __le64 max_size; }; struct virtio_crypto_inhdr { -- cgit v1.2.3 From fc4a1accbb4ef372bb55b7ab161cf88e3b631935 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_fs: correct tags for config space fields Since fs is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Acked-by: Vivek Goyal Acked-by: Vivek Goyal Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h index b02eb2ac3d99..3056b6e9f8ce 100644 --- a/include/uapi/linux/virtio_fs.h +++ b/include/uapi/linux/virtio_fs.h @@ -13,7 +13,7 @@ struct virtio_fs_config { __u8 tag[36]; /* Number of request queues */ - __u32 num_request_queues; + __le32 num_request_queues; } __attribute__((packed)); #endif /* _UAPI_LINUX_VIRTIO_FS_H */ -- cgit v1.2.3 From f378444b7c97e39358de5d50d01fb0e92f259073 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_gpu: correct tags for config space fields Since gpu is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_gpu.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 0c85914d9369..ccbd174ef321 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -320,10 +320,10 @@ struct virtio_gpu_resp_edid { #define VIRTIO_GPU_EVENT_DISPLAY (1 << 0) struct virtio_gpu_config { - __u32 events_read; - __u32 events_clear; - __u32 num_scanouts; - __u32 num_capsets; + __le32 events_read; + __le32 events_clear; + __le32 num_scanouts; + __le32 num_capsets; }; /* simple formats for fbcon/X use */ -- cgit v1.2.3 From 924b59a6dfa85dc9eac4c7f2fe1857bba2cb2510 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_input: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Gerd Hoffmann Reviewed-by: Gerd Hoffmann Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_input.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_input.h b/include/uapi/linux/virtio_input.h index a7fe5c8fb135..52084b1fb965 100644 --- a/include/uapi/linux/virtio_input.h +++ b/include/uapi/linux/virtio_input.h @@ -40,18 +40,18 @@ enum virtio_input_config_select { }; struct virtio_input_absinfo { - __u32 min; - __u32 max; - __u32 fuzz; - __u32 flat; - __u32 res; + __le32 min; + __le32 max; + __le32 fuzz; + __le32 flat; + __le32 res; }; struct virtio_input_devids { - __u16 bustype; - __u16 vendor; - __u16 product; - __u16 version; + __le16 bustype; + __le16 vendor; + __le16 product; + __le16 version; }; struct virtio_input_config { -- cgit v1.2.3 From 0ebcffcc2731682777bab19b51a512d8f31e1bdd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_iommu: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_iommu.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index 48e3c29223b5..237e36a280cb 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -18,24 +18,24 @@ #define VIRTIO_IOMMU_F_MMIO 5 struct virtio_iommu_range_64 { - __u64 start; - __u64 end; + __le64 start; + __le64 end; }; struct virtio_iommu_range_32 { - __u32 start; - __u32 end; + __le32 start; + __le32 end; }; struct virtio_iommu_config { /* Supported page sizes */ - __u64 page_size_mask; + __le64 page_size_mask; /* Supported IOVA range */ struct virtio_iommu_range_64 input_range; /* Max domain ID size */ struct virtio_iommu_range_32 domain_range; /* Probe buffer size */ - __u32 probe_size; + __le32 probe_size; }; /* Request types */ -- cgit v1.2.3 From 79268954424771185fb4ca304786dd561a272246 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_mem: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. TODO: check other uses of __virtioXX types in this header, should probably be __leXX. Signed-off-by: Michael S. Tsirkin Acked-by: David Hildenbrand Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_mem.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index a9ffe041843c..70e01c687d5e 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -185,27 +185,27 @@ struct virtio_mem_resp { struct virtio_mem_config { /* Block size and alignment. Cannot change. */ - __u64 block_size; + __le64 block_size; /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ - __u16 node_id; + __le16 node_id; __u8 padding[6]; /* Start address of the memory region. Cannot change. */ - __u64 addr; + __le64 addr; /* Region size (maximum). Cannot change. */ - __u64 region_size; + __le64 region_size; /* * Currently usable region size. Can grow up to region_size. Can * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config * update will be sent). */ - __u64 usable_region_size; + __le64 usable_region_size; /* * Currently used size. Changes due to plug/unplug requests, but no * config updates will be sent. */ - __u64 plugged_size; + __le64 plugged_size; /* Requested size. New plug requests cannot exceed it. Can change. */ - __u64 requested_size; + __le64 requested_size; }; #endif /* _LINUX_VIRTIO_MEM_H */ -- cgit v1.2.3 From 577e677a785357542311a645eeb1756cd83988be Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_net: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_net.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 19d23e5baa4e..27d996f29dd1 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -87,19 +87,19 @@ struct virtio_net_config { /* The config defining mac address (if VIRTIO_NET_F_MAC) */ __u8 mac[ETH_ALEN]; /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */ - __u16 status; + __virtio16 status; /* Maximum number of each of transmit and receive queues; * see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ. * Legal values are between 1 and 0x8000 */ - __u16 max_virtqueue_pairs; + __virtio16 max_virtqueue_pairs; /* Default maximum transmit unit advice */ - __u16 mtu; + __virtio16 mtu; /* * speed, in units of 1Mb. All values 0 to INT_MAX are legal. * Any other value stands for unknown. */ - __u32 speed; + __virtio32 speed; /* * 0x00 - half duplex * 0x01 - full duplex -- cgit v1.2.3 From a28feb855cc0ad452acd3dfe2b8f2841927da5f1 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_pmem: correct tags for config space fields Since this is a modern-only device, tag config space fields as having little endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_pmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index b022787ffb94..d676b3620383 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -15,8 +15,8 @@ #include struct virtio_pmem_config { - __u64 start; - __u64 size; + __le64 start; + __le64 size; }; #define VIRTIO_PMEM_REQ_TYPE_FLUSH 0 -- cgit v1.2.3 From 965b5350514b597dc6347b733127e180844aeb43 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 10 Jul 2020 07:17:13 -0400 Subject: virtio_scsi: correct tags for config space fields Tag config space fields as having virtio endian-ness. Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/uapi/linux/virtio_scsi.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h index cc18ef8825c0..0abaae4027c0 100644 --- a/include/uapi/linux/virtio_scsi.h +++ b/include/uapi/linux/virtio_scsi.h @@ -103,16 +103,16 @@ struct virtio_scsi_event { } __attribute__((packed)); struct virtio_scsi_config { - __u32 num_queues; - __u32 seg_max; - __u32 max_sectors; - __u32 cmd_per_lun; - __u32 event_info_size; - __u32 sense_size; - __u32 cdb_size; - __u16 max_channel; - __u16 max_target; - __u32 max_lun; + __virtio32 num_queues; + __virtio32 seg_max; + __virtio32 max_sectors; + __virtio32 cmd_per_lun; + __virtio32 event_info_size; + __virtio32 sense_size; + __virtio32 cdb_size; + __virtio16 max_channel; + __virtio16 max_target; + __virtio32 max_lun; } __attribute__((packed)); /* Feature Bits */ -- cgit v1.2.3 From 64ffa39dc860fb9772225c694353f73eca5801c6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 5 Aug 2020 05:39:36 -0400 Subject: virtio_net: use LE accessors for speed/duplex Speed and duplex config fields depend on VIRTIO_NET_F_SPEED_DUPLEX which being 63>31 depends on VIRTIO_F_VERSION_1. Accordingly, use LE accessors for these fields. Reported-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 27d996f29dd1..3f55a4215f11 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -99,7 +99,7 @@ struct virtio_net_config { * speed, in units of 1Mb. All values 0 to INT_MAX are legal. * Any other value stands for unknown. */ - __virtio32 speed; + __le32 speed; /* * 0x00 - half duplex * 0x01 - full duplex -- cgit v1.2.3 From 25abc060d282132ea5c945392f900dca0a7e9bbb Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 4 Aug 2020 19:20:40 +0300 Subject: vhost-vdpa: support IOTLB batching hints This patches extend the vhost IOTLB API to accept batch updating hints form userspace. When userspace wants update the device IOTLB in a batch, it may do: 1) Write vhost_iotlb_msg with VHOST_IOTLB_BATCH_BEGIN flag 2) Perform a batch of IOTLB updating via VHOST_IOTLB_UPDATE/INVALIDATE 3) Write vhost_iotlb_msg with VHOST_IOTLB_BATCH_END flag Vhost-vdpa may decide to batch the IOMMU/IOTLB updating in step 3 when vDPA device support set_map() ops. This is useful for the vDPA device that want to know all the mappings to tweak their own DMA translation logic. For vDPA device that doesn't require set_map(), no behavior changes. This capability is advertised via VHOST_BACKEND_F_IOTLB_BATCH capability. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20200804162048.22587-5-eli@mellanox.com Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 2 ++ include/uapi/linux/vhost_types.h | 11 +++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 0c2349612e77..75232185324a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -91,6 +91,8 @@ /* Use message type V2 */ #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 669457ce5c48..9a269a88a6ff 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -60,6 +60,17 @@ struct vhost_iotlb_msg { #define VHOST_IOTLB_UPDATE 2 #define VHOST_IOTLB_INVALIDATE 3 #define VHOST_IOTLB_ACCESS_FAIL 4 +/* + * VHOST_IOTLB_BATCH_BEGIN and VHOST_IOTLB_BATCH_END allow modifying + * multiple mappings in one go: beginning with + * VHOST_IOTLB_BATCH_BEGIN, followed by any number of + * VHOST_IOTLB_UPDATE messages, and ending with VHOST_IOTLB_BATCH_END. + * When one of these two values is used as the message type, the rest + * of the fields in the message are ignored. There's no guarantee that + * these changes take place automatically in the device. + */ +#define VHOST_IOTLB_BATCH_BEGIN 5 +#define VHOST_IOTLB_BATCH_END 6 __u8 type; }; -- cgit v1.2.3 From 5e7b30205cef80f6bb922e61834437ca7bff5837 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 4 Aug 2020 22:50:56 -0700 Subject: bpf: Change uapi for bpf iterator map elements Commit a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") added bpf iterator support for map elements. The map element bpf iterator requires info to identify a particular map. In the above commit, the attr->link_create.target_fd is used to carry map_fd and an enum bpf_iter_link_info is added to uapi to specify the target_fd actually representing a map_fd: enum bpf_iter_link_info { BPF_ITER_LINK_UNSPEC = 0, BPF_ITER_LINK_MAP_FD = 1, MAX_BPF_ITER_LINK_INFO, }; This is an extensible approach as we can grow enumerator for pid, cgroup_id, etc. and we can unionize target_fd for pid, cgroup_id, etc. But in the future, there are chances that more complex customization may happen, e.g., for tasks, it could be filtered based on both cgroup_id and user_id. This patch changed the uapi to have fields __aligned_u64 iter_info; __u32 iter_info_len; for additional iter_info for link_create. The iter_info is defined as union bpf_iter_link_info { struct { __u32 map_fd; } map; }; So future extension for additional customization will be easier. The bpf_iter_link_info will be passed to target callback to validate and generic bpf_iter framework does not need to deal it any more. Note that map_fd = 0 will be considered invalid and -EBADF will be returned to user space. Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com --- include/uapi/linux/bpf.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b134e679e9db..0480f893facd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -81,6 +81,12 @@ struct bpf_cgroup_storage_key { __u32 attach_type; /* program attach type */ }; +union bpf_iter_link_info { + struct { + __u32 map_fd; + } map; +}; + /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { BPF_MAP_CREATE, @@ -249,13 +255,6 @@ enum bpf_link_type { MAX_BPF_LINK_TYPE, }; -enum bpf_iter_link_info { - BPF_ITER_LINK_UNSPEC = 0, - BPF_ITER_LINK_MAP_FD = 1, - - MAX_BPF_ITER_LINK_INFO, -}; - /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. @@ -623,6 +622,8 @@ union bpf_attr { }; __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ + __aligned_u64 iter_info; /* extra bpf_iter_link_info */ + __u32 iter_info_len; /* iter_info length */ } link_create; struct { /* struct used by BPF_LINK_UPDATE command */ -- cgit v1.2.3 From 7f317d34906c1033f0752fc137dda04e43979bb8 Mon Sep 17 00:00:00 2001 From: "Alexander A. Klimov" Date: Tue, 11 Aug 2020 18:34:19 -0700 Subject: include/: replace HTTP links with HTTPS ones Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Signed-off-by: Alexander A. Klimov Signed-off-by: Andrew Morton Reviewed-by: Kees Cook Link: http://lkml.kernel.org/r/20200726110117.16346-1-grandmaster@al2klimov.de Signed-off-by: Linus Torvalds --- include/uapi/linux/elf.h | 2 +- include/uapi/linux/map_to_7segment.h | 2 +- include/uapi/linux/types.h | 2 +- include/uapi/linux/usb/ch9.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c6dd0215482e..22220945a5fd 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -53,7 +53,7 @@ typedef __s64 Elf64_Sxword; * * - Oracle: Linker and Libraries. * Part No: 817–1984–19, August 2011. - * http://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf + * https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf * * - System V ABI AMD64 Architecture Processor Supplement * Draft Version 0.99.4, diff --git a/include/uapi/linux/map_to_7segment.h b/include/uapi/linux/map_to_7segment.h index f9ed18134b83..13a06e5e966e 100644 --- a/include/uapi/linux/map_to_7segment.h +++ b/include/uapi/linux/map_to_7segment.h @@ -24,7 +24,7 @@ * of (ASCII) characters to a 7-segments notation. * * The 7 segment's wikipedia notation below is used as standard. - * See: http://en.wikipedia.org/wiki/Seven_segment_display + * See: https://en.wikipedia.org/wiki/Seven_segment_display * * Notation: +-a-+ * f b diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index 2fce8b6876e9..f6d2f83cbe29 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -7,7 +7,7 @@ #ifndef __ASSEMBLY__ #ifndef __KERNEL__ #ifndef __EXPORTED_HEADERS__ -#warning "Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders" +#warning "Attempt to use kernel headers from user space, see https://kernelnewbies.org/KernelHeaders" #endif /* __EXPORTED_HEADERS__ */ #endif diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 48766fdf6580..0f865ae4ba89 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -1229,7 +1229,7 @@ struct usb_set_sel_req { * As per USB compliance update, a device that is actively drawing * more than 100mA from USB must report itself as bus-powered in * the GetStatus(DEVICE) call. - * http://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34 + * https://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34 */ #define USB_SELF_POWER_VBUS_MAX_DRAW 100 -- cgit v1.2.3 From 2fb3244f0a58ceb3d866ac63f644dfa31cae430f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 11 Aug 2020 18:35:21 -0700 Subject: autofs: fix doubled word Change doubled word "is" to "it is". Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Acked-by: Ian Kent Link: http://lkml.kernel.org/r/5a82befd-40f8-8dc0-3498-cbc0436cad9b@infradead.org Signed-off-by: Linus Torvalds --- include/uapi/linux/auto_dev-ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h index 374742651c30..62e625356dc8 100644 --- a/include/uapi/linux/auto_dev-ioctl.h +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -82,7 +82,7 @@ struct args_ismountpoint { /* * All the ioctls use this structure. * When sending a path size must account for the total length - * of the chunk of memory otherwise is is the size of the + * of the chunk of memory otherwise it is the size of the * structure. */ -- cgit v1.2.3