mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
b2197755b2
This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
81 lines
2.9 KiB
C
81 lines
2.9 KiB
C
#ifndef __LINUX_MAGIC_H__
|
|
#define __LINUX_MAGIC_H__
|
|
|
|
#define ADFS_SUPER_MAGIC 0xadf5
|
|
#define AFFS_SUPER_MAGIC 0xadff
|
|
#define AFS_SUPER_MAGIC 0x5346414F
|
|
#define AUTOFS_SUPER_MAGIC 0x0187
|
|
#define CODA_SUPER_MAGIC 0x73757245
|
|
#define CRAMFS_MAGIC 0x28cd3d45 /* some random number */
|
|
#define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */
|
|
#define DEBUGFS_MAGIC 0x64626720
|
|
#define SECURITYFS_MAGIC 0x73636673
|
|
#define SELINUX_MAGIC 0xf97cff8c
|
|
#define SMACK_MAGIC 0x43415d53 /* "SMAC" */
|
|
#define RAMFS_MAGIC 0x858458f6 /* some random number */
|
|
#define TMPFS_MAGIC 0x01021994
|
|
#define HUGETLBFS_MAGIC 0x958458f6 /* some random number */
|
|
#define SQUASHFS_MAGIC 0x73717368
|
|
#define ECRYPTFS_SUPER_MAGIC 0xf15f
|
|
#define EFS_SUPER_MAGIC 0x414A53
|
|
#define EXT2_SUPER_MAGIC 0xEF53
|
|
#define EXT3_SUPER_MAGIC 0xEF53
|
|
#define XENFS_SUPER_MAGIC 0xabba1974
|
|
#define EXT4_SUPER_MAGIC 0xEF53
|
|
#define BTRFS_SUPER_MAGIC 0x9123683E
|
|
#define NILFS_SUPER_MAGIC 0x3434
|
|
#define F2FS_SUPER_MAGIC 0xF2F52010
|
|
#define HPFS_SUPER_MAGIC 0xf995e849
|
|
#define ISOFS_SUPER_MAGIC 0x9660
|
|
#define JFFS2_SUPER_MAGIC 0x72b6
|
|
#define PSTOREFS_MAGIC 0x6165676C
|
|
#define EFIVARFS_MAGIC 0xde5e81e4
|
|
#define HOSTFS_SUPER_MAGIC 0x00c0ffee
|
|
|
|
#define MINIX_SUPER_MAGIC 0x137F /* minix v1 fs, 14 char names */
|
|
#define MINIX_SUPER_MAGIC2 0x138F /* minix v1 fs, 30 char names */
|
|
#define MINIX2_SUPER_MAGIC 0x2468 /* minix v2 fs, 14 char names */
|
|
#define MINIX2_SUPER_MAGIC2 0x2478 /* minix v2 fs, 30 char names */
|
|
#define MINIX3_SUPER_MAGIC 0x4d5a /* minix v3 fs, 60 char names */
|
|
|
|
#define MSDOS_SUPER_MAGIC 0x4d44 /* MD */
|
|
#define NCP_SUPER_MAGIC 0x564c /* Guess, what 0x564c is :-) */
|
|
#define NFS_SUPER_MAGIC 0x6969
|
|
#define OPENPROM_SUPER_MAGIC 0x9fa1
|
|
#define QNX4_SUPER_MAGIC 0x002f /* qnx4 fs detection */
|
|
#define QNX6_SUPER_MAGIC 0x68191122 /* qnx6 fs detection */
|
|
|
|
#define REISERFS_SUPER_MAGIC 0x52654973 /* used by gcc */
|
|
/* used by file system utilities that
|
|
look at the superblock, etc. */
|
|
#define REISERFS_SUPER_MAGIC_STRING "ReIsErFs"
|
|
#define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs"
|
|
#define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs"
|
|
|
|
#define SMB_SUPER_MAGIC 0x517B
|
|
#define CGROUP_SUPER_MAGIC 0x27e0eb
|
|
|
|
|
|
#define STACK_END_MAGIC 0x57AC6E9D
|
|
|
|
#define TRACEFS_MAGIC 0x74726163
|
|
|
|
#define V9FS_MAGIC 0x01021997
|
|
|
|
#define BDEVFS_MAGIC 0x62646576
|
|
#define BINFMTFS_MAGIC 0x42494e4d
|
|
#define DEVPTS_SUPER_MAGIC 0x1cd1
|
|
#define FUTEXFS_SUPER_MAGIC 0xBAD1DEA
|
|
#define PIPEFS_MAGIC 0x50495045
|
|
#define PROC_SUPER_MAGIC 0x9fa0
|
|
#define SOCKFS_MAGIC 0x534F434B
|
|
#define SYSFS_MAGIC 0x62656572
|
|
#define USBDEVICE_SUPER_MAGIC 0x9fa2
|
|
#define MTD_INODE_FS_MAGIC 0x11307854
|
|
#define ANON_INODE_FS_MAGIC 0x09041934
|
|
#define BTRFS_TEST_MAGIC 0x73727279
|
|
#define NSFS_MAGIC 0x6e736673
|
|
#define BPF_FS_MAGIC 0xcafe4a11
|
|
|
|
#endif /* __LINUX_MAGIC_H__ */
|