diff --git a/.clang-format b/.clang-format index 252820d9c80a..fe1aa1a30d40 100644 --- a/.clang-format +++ b/.clang-format @@ -141,11 +141,13 @@ ForEachMacros: - 'damon_for_each_target_safe' - 'damos_for_each_filter' - 'damos_for_each_filter_safe' + - 'damos_for_each_quota_goal' + - 'damos_for_each_quota_goal_safe' - 'data__for_each_file' - 'data__for_each_file_new' - 'data__for_each_file_start' - 'device_for_each_child_node' - - 'displayid_iter_for_each' + - 'device_for_each_child_node_scoped' - 'dma_fence_array_for_each' - 'dma_fence_chain_for_each' - 'dma_fence_unwrap_for_each' @@ -172,11 +174,14 @@ ForEachMacros: - 'drm_for_each_plane' - 'drm_for_each_plane_mask' - 'drm_for_each_privobj' - - 'drm_gem_for_each_gpuva' - - 'drm_gem_for_each_gpuva_safe' + - 'drm_gem_for_each_gpuvm_bo' + - 'drm_gem_for_each_gpuvm_bo_safe' - 'drm_gpuva_for_each_op' - 'drm_gpuva_for_each_op_from_reverse' + - 'drm_gpuva_for_each_op_reverse' - 'drm_gpuva_for_each_op_safe' + - 'drm_gpuvm_bo_for_each_va' + - 'drm_gpuvm_bo_for_each_va_safe' - 'drm_gpuvm_for_each_va' - 'drm_gpuvm_for_each_va_range' - 'drm_gpuvm_for_each_va_range_safe' @@ -192,11 +197,11 @@ ForEachMacros: - 'dsa_switch_for_each_port_continue_reverse' - 'dsa_switch_for_each_port_safe' - 'dsa_switch_for_each_user_port' + - 'dsa_switch_for_each_user_port_continue_reverse' - 'dsa_tree_for_each_cpu_port' - 'dsa_tree_for_each_user_port' - 'dsa_tree_for_each_user_port_continue_reverse' - 'dso__for_each_symbol' - - 'dsos__for_each_with_build_id' - 'elf_hash_for_each_possible' - 'elf_symtab__for_each_symbol' - 'evlist__for_each_cpu' @@ -216,6 +221,7 @@ ForEachMacros: - 'for_each_and_bit' - 'for_each_andnot_bit' - 'for_each_available_child_of_node' + - 'for_each_available_child_of_node_scoped' - 'for_each_bench' - 'for_each_bio' - 'for_each_board_func_rsrc' @@ -234,6 +240,7 @@ ForEachMacros: - 'for_each_card_widgets_safe' - 'for_each_cgroup_storage_type' - 'for_each_child_of_node' + - 'for_each_child_of_node_scoped' - 'for_each_clear_bit' - 'for_each_clear_bit_from' - 'for_each_clear_bitrange' @@ -251,6 +258,7 @@ ForEachMacros: - 'for_each_cpu' - 'for_each_cpu_and' - 'for_each_cpu_andnot' + - 'for_each_cpu_from' - 'for_each_cpu_or' - 'for_each_cpu_wrap' - 'for_each_dapm_widgets' @@ -269,13 +277,14 @@ ForEachMacros: - 'for_each_element' - 'for_each_element_extid' - 'for_each_element_id' + - 'for_each_enabled_cpu' - 'for_each_endpoint_of_node' - 'for_each_event' - 'for_each_event_tps' - 'for_each_evictable_lru' - 'for_each_fib6_node_rt_rcu' - 'for_each_fib6_walker_rt' - - 'for_each_free_mem_pfn_range_in_zone' + - 'for_each_file_lock' - 'for_each_free_mem_pfn_range_in_zone_from' - 'for_each_free_mem_range' - 'for_each_free_mem_range_reverse' @@ -286,15 +295,18 @@ ForEachMacros: - 'for_each_group_member' - 'for_each_group_member_head' - 'for_each_hstate' + - 'for_each_hwgpio' - 'for_each_if' - 'for_each_inject_fn' - 'for_each_insn' + - 'for_each_insn_op_loc' - 'for_each_insn_prefix' - 'for_each_intid' - 'for_each_iommu' - 'for_each_ip_tunnel_rcu' - 'for_each_irq_nr' - 'for_each_lang' + - 'for_each_link_ch_maps' - 'for_each_link_codecs' - 'for_each_link_cpus' - 'for_each_link_platforms' @@ -332,6 +344,9 @@ ForEachMacros: - 'for_each_new_plane_in_state_reverse' - 'for_each_new_private_obj_in_state' - 'for_each_new_reg' + - 'for_each_nhlt_endpoint' + - 'for_each_nhlt_endpoint_fmtcfg' + - 'for_each_nhlt_fmtcfg' - 'for_each_node' - 'for_each_node_by_name' - 'for_each_node_by_type' @@ -387,12 +402,15 @@ ForEachMacros: - 'for_each_reloc_from' - 'for_each_requested_gpio' - 'for_each_requested_gpio_in_range' + - 'for_each_reserved_child_of_node' - 'for_each_reserved_mem_range' - 'for_each_reserved_mem_region' + - 'for_each_rtd_ch_maps' - 'for_each_rtd_codec_dais' - 'for_each_rtd_components' - 'for_each_rtd_cpu_dais' - 'for_each_rtd_dais' + - 'for_each_rtd_dais_reverse' - 'for_each_sband_iftype_data' - 'for_each_script' - 'for_each_sec' @@ -533,8 +551,6 @@ ForEachMacros: - 'lwq_for_each_safe' - 'map__for_each_symbol' - 'map__for_each_symbol_by_name' - - 'maps__for_each_entry' - - 'maps__for_each_entry_safe' - 'mas_for_each' - 'mci_for_each_dimm' - 'media_device_for_each_entity' @@ -560,7 +576,9 @@ ForEachMacros: - 'netdev_hw_addr_list_for_each' - 'nft_rule_for_each_expr' - 'nla_for_each_attr' + - 'nla_for_each_attr_type' - 'nla_for_each_nested' + - 'nla_for_each_nested_type' - 'nlmsg_for_each_attr' - 'nlmsg_for_each_msg' - 'nr_neigh_for_each' @@ -579,6 +597,7 @@ ForEachMacros: - 'perf_config_sections__for_each_entry' - 'perf_config_set__for_each_entry' - 'perf_cpu_map__for_each_cpu' + - 'perf_cpu_map__for_each_cpu_skip_any' - 'perf_cpu_map__for_each_idx' - 'perf_evlist__for_each_entry' - 'perf_evlist__for_each_entry_reverse' @@ -639,7 +658,6 @@ ForEachMacros: - 'shost_for_each_device' - 'sk_for_each' - 'sk_for_each_bound' - - 'sk_for_each_bound_bhash2' - 'sk_for_each_entry_offset_rcu' - 'sk_for_each_from' - 'sk_for_each_rcu' @@ -653,6 +671,7 @@ ForEachMacros: - 'snd_soc_dapm_widget_for_each_path_safe' - 'snd_soc_dapm_widget_for_each_sink_path' - 'snd_soc_dapm_widget_for_each_source_path' + - 'sparsebit_for_each_set_range' - 'strlist__for_each_entry' - 'strlist__for_each_entry_safe' - 'sym_for_each_insn' @@ -662,7 +681,6 @@ ForEachMacros: - 'tcf_act_for_each_action' - 'tcf_exts_for_each_action' - 'ttm_resource_manager_for_each_res' - - 'twsk_for_each_bound_bhash2' - 'udp_portaddr_for_each_entry' - 'udp_portaddr_for_each_entry_rcu' - 'usb_hub_for_each_child' @@ -686,6 +704,9 @@ ForEachMacros: - 'xbc_node_for_each_child' - 'xbc_node_for_each_key_value' - 'xbc_node_for_each_subkey' + - 'ynl_attr_for_each' + - 'ynl_attr_for_each_nested' + - 'ynl_attr_for_each_payload' - 'zorro_for_each_dev' IncludeBlocks: Preserve diff --git a/Documentation/filesystems/nfs/index.rst b/Documentation/filesystems/nfs/index.rst index 8536134f31fd..95c2c009874c 100644 --- a/Documentation/filesystems/nfs/index.rst +++ b/Documentation/filesystems/nfs/index.rst @@ -8,6 +8,7 @@ NFS client-identifier exporting + localio pnfs rpc-cache rpc-server-gss diff --git a/Documentation/filesystems/nfs/localio.rst b/Documentation/filesystems/nfs/localio.rst new file mode 100644 index 000000000000..bd1967e2eab3 --- /dev/null +++ b/Documentation/filesystems/nfs/localio.rst @@ -0,0 +1,357 @@ +=========== +NFS LOCALIO +=========== + +Overview +======== + +The LOCALIO auxiliary RPC protocol allows the Linux NFS client and +server to reliably handshake to determine if they are on the same +host. Select "NFS client and server support for LOCALIO auxiliary +protocol" in menuconfig to enable CONFIG_NFS_LOCALIO in the kernel +config (both CONFIG_NFS_FS and CONFIG_NFSD must also be enabled). + +Once an NFS client and server handshake as "local", the client will +bypass the network RPC protocol for read, write and commit operations. +Due to this XDR and RPC bypass, these operations will operate faster. + +The LOCALIO auxiliary protocol's implementation, which uses the same +connection as NFS traffic, follows the pattern established by the NFS +ACL protocol extension. + +The LOCALIO auxiliary protocol is needed to allow robust discovery of +clients local to their servers. In a private implementation that +preceded use of this LOCALIO protocol, a fragile sockaddr network +address based match against all local network interfaces was attempted. +But unlike the LOCALIO protocol, the sockaddr-based matching didn't +handle use of iptables or containers. + +The robust handshake between local client and server is just the +beginning, the ultimate use case this locality makes possible is the +client is able to open files and issue reads, writes and commits +directly to the server without having to go over the network. The +requirement is to perform these loopback NFS operations as efficiently +as possible, this is particularly useful for container use cases +(e.g. kubernetes) where it is possible to run an IO job local to the +server. + +The performance advantage realized from LOCALIO's ability to bypass +using XDR and RPC for reads, writes and commits can be extreme, e.g.: + +fio for 20 secs with directio, qd of 8, 16 libaio threads: + - With LOCALIO: + 4K read: IOPS=979k, BW=3825MiB/s (4011MB/s)(74.7GiB/20002msec) + 4K write: IOPS=165k, BW=646MiB/s (678MB/s)(12.6GiB/20002msec) + 128K read: IOPS=402k, BW=49.1GiB/s (52.7GB/s)(982GiB/20002msec) + 128K write: IOPS=11.5k, BW=1433MiB/s (1503MB/s)(28.0GiB/20004msec) + + - Without LOCALIO: + 4K read: IOPS=79.2k, BW=309MiB/s (324MB/s)(6188MiB/20003msec) + 4K write: IOPS=59.8k, BW=234MiB/s (245MB/s)(4671MiB/20002msec) + 128K read: IOPS=33.9k, BW=4234MiB/s (4440MB/s)(82.7GiB/20004msec) + 128K write: IOPS=11.5k, BW=1434MiB/s (1504MB/s)(28.0GiB/20011msec) + +fio for 20 secs with directio, qd of 8, 1 libaio thread: + - With LOCALIO: + 4K read: IOPS=230k, BW=898MiB/s (941MB/s)(17.5GiB/20001msec) + 4K write: IOPS=22.6k, BW=88.3MiB/s (92.6MB/s)(1766MiB/20001msec) + 128K read: IOPS=38.8k, BW=4855MiB/s (5091MB/s)(94.8GiB/20001msec) + 128K write: IOPS=11.4k, BW=1428MiB/s (1497MB/s)(27.9GiB/20001msec) + + - Without LOCALIO: + 4K read: IOPS=77.1k, BW=301MiB/s (316MB/s)(6022MiB/20001msec) + 4K write: IOPS=32.8k, BW=128MiB/s (135MB/s)(2566MiB/20001msec) + 128K read: IOPS=24.4k, BW=3050MiB/s (3198MB/s)(59.6GiB/20001msec) + 128K write: IOPS=11.4k, BW=1430MiB/s (1500MB/s)(27.9GiB/20001msec) + +FAQ +=== + +1. What are the use cases for LOCALIO? + + a. Workloads where the NFS client and server are on the same host + realize improved IO performance. In particular, it is common when + running containerised workloads for jobs to find themselves + running on the same host as the knfsd server being used for + storage. + +2. What are the requirements for LOCALIO? + + a. Bypass use of the network RPC protocol as much as possible. This + includes bypassing XDR and RPC for open, read, write and commit + operations. + b. Allow client and server to autonomously discover if they are + running local to each other without making any assumptions about + the local network topology. + c. Support the use of containers by being compatible with relevant + namespaces (e.g. network, user, mount). + d. Support all versions of NFS. NFSv3 is of particular importance + because it has wide enterprise usage and pNFS flexfiles makes use + of it for the data path. + +3. Why doesn’t LOCALIO just compare IP addresses or hostnames when + deciding if the NFS client and server are co-located on the same + host? + + Since one of the main use cases is containerised workloads, we cannot + assume that IP addresses will be shared between the client and + server. This sets up a requirement for a handshake protocol that + needs to go over the same connection as the NFS traffic in order to + identify that the client and the server really are running on the + same host. The handshake uses a secret that is sent over the wire, + and can be verified by both parties by comparing with a value stored + in shared kernel memory if they are truly co-located. + +4. Does LOCALIO improve pNFS flexfiles? + + Yes, LOCALIO complements pNFS flexfiles by allowing it to take + advantage of NFS client and server locality. Policy that initiates + client IO as closely to the server where the data is stored naturally + benefits from the data path optimization LOCALIO provides. + +5. Why not develop a new pNFS layout to enable LOCALIO? + + A new pNFS layout could be developed, but doing so would put the + onus on the server to somehow discover that the client is co-located + when deciding to hand out the layout. + There is value in a simpler approach (as provided by LOCALIO) that + allows the NFS client to negotiate and leverage locality without + requiring more elaborate modeling and discovery of such locality in a + more centralized manner. + +6. Why is having the client perform a server-side file OPEN, without + using RPC, beneficial? Is the benefit pNFS specific? + + Avoiding the use of XDR and RPC for file opens is beneficial to + performance regardless of whether pNFS is used. Especially when + dealing with small files its best to avoid going over the wire + whenever possible, otherwise it could reduce or even negate the + benefits of avoiding the wire for doing the small file I/O itself. + Given LOCALIO's requirements the current approach of having the + client perform a server-side file open, without using RPC, is ideal. + If in the future requirements change then we can adapt accordingly. + +7. Why is LOCALIO only supported with UNIX Authentication (AUTH_UNIX)? + + Strong authentication is usually tied to the connection itself. It + works by establishing a context that is cached by the server, and + that acts as the key for discovering the authorisation token, which + can then be passed to rpc.mountd to complete the authentication + process. On the other hand, in the case of AUTH_UNIX, the credential + that was passed over the wire is used directly as the key in the + upcall to rpc.mountd. This simplifies the authentication process, and + so makes AUTH_UNIX easier to support. + +8. How do export options that translate RPC user IDs behave for LOCALIO + operations (eg. root_squash, all_squash)? + + Export options that translate user IDs are managed by nfsd_setuser() + which is called by nfsd_setuser_and_check_port() which is called by + __fh_verify(). So they get handled exactly the same way for LOCALIO + as they do for non-LOCALIO. + +9. How does LOCALIO make certain that object lifetimes are managed + properly given NFSD and NFS operate in different contexts? + + See the detailed "NFS Client and Server Interlock" section below. + +RPC +=== + +The LOCALIO auxiliary RPC protocol consists of a single "UUID_IS_LOCAL" +RPC method that allows the Linux NFS client to verify the local Linux +NFS server can see the nonce (single-use UUID) the client generated and +made available in nfs_common. This protocol isn't part of an IETF +standard, nor does it need to be considering it is Linux-to-Linux +auxiliary RPC protocol that amounts to an implementation detail. + +The UUID_IS_LOCAL method encodes the client generated uuid_t in terms of +the fixed UUID_SIZE (16 bytes). The fixed size opaque encode and decode +XDR methods are used instead of the less efficient variable sized +methods. + +The RPC program number for the NFS_LOCALIO_PROGRAM is 400122 (as assigned +by IANA, see https://www.iana.org/assignments/rpc-program-numbers/ ): +Linux Kernel Organization 400122 nfslocalio + +The LOCALIO protocol spec in rpcgen syntax is:: + + /* raw RFC 9562 UUID */ + #define UUID_SIZE 16 + typedef u8 uuid_t; + + program NFS_LOCALIO_PROGRAM { + version LOCALIO_V1 { + void + NULL(void) = 0; + + void + UUID_IS_LOCAL(uuid_t) = 1; + } = 1; + } = 400122; + +LOCALIO uses the same transport connection as NFS traffic. As such, +LOCALIO is not registered with rpcbind. + +NFS Common and Client/Server Handshake +====================================== + +fs/nfs_common/nfslocalio.c provides interfaces that enable an NFS client +to generate a nonce (single-use UUID) and associated short-lived +nfs_uuid_t struct, register it with nfs_common for subsequent lookup and +verification by the NFS server and if matched the NFS server populates +members in the nfs_uuid_t struct. The NFS client then uses nfs_common to +transfer the nfs_uuid_t from its nfs_uuids to the nn->nfsd_serv +clients_list from the nfs_common's uuids_list. See: +fs/nfs/localio.c:nfs_local_probe() + +nfs_common's nfs_uuids list is the basis for LOCALIO enablement, as such +it has members that point to nfsd memory for direct use by the client +(e.g. 'net' is the server's network namespace, through it the client can +access nn->nfsd_serv with proper rcu read access). It is this client +and server synchronization that enables advanced usage and lifetime of +objects to span from the host kernel's nfsd to per-container knfsd +instances that are connected to nfs client's running on the same local +host. + +NFS Client and Server Interlock +=============================== + +LOCALIO provides the nfs_uuid_t object and associated interfaces to +allow proper network namespace (net-ns) and NFSD object refcounting: + + We don't want to keep a long-term counted reference on each NFSD's + net-ns in the client because that prevents a server container from + completely shutting down. + + So we avoid taking a reference at all and rely on the per-cpu + reference to the server (detailed below) being sufficient to keep + the net-ns active. This involves allowing the NFSD's net-ns exit + code to iterate all active clients and clear their ->net pointers + (which are needed to find the per-cpu-refcount for the nfsd_serv). + + Details: + + - Embed nfs_uuid_t in nfs_client. nfs_uuid_t provides a list_head + that can be used to find the client. It does add the 16-byte + uuid_t to nfs_client so it is bigger than needed (given that + uuid_t is only used during the initial NFS client and server + LOCALIO handshake to determine if they are local to each other). + If that is really a problem we can find a fix. + + - When the nfs server confirms that the uuid_t is local, it moves + the nfs_uuid_t onto a per-net-ns list in NFSD's nfsd_net. + + - When each server's net-ns is shutting down - in a "pre_exit" + handler, all these nfs_uuid_t have their ->net cleared. There is + an rcu_synchronize() call between pre_exit() handlers and exit() + handlers so any caller that sees nfs_uuid_t ->net as not NULL can + safely manage the per-cpu-refcount for nfsd_serv. + + - The client's nfs_uuid_t is passed to nfsd_open_local_fh() so it + can safely dereference ->net in a private rcu_read_lock() section + to allow safe access to the associated nfsd_net and nfsd_serv. + +So LOCALIO required the introduction and use of NFSD's percpu_ref to +interlock nfsd_destroy_serv() and nfsd_open_local_fh(), to ensure each +nn->nfsd_serv is not destroyed while in use by nfsd_open_local_fh(), and +warrants a more detailed explanation: + + nfsd_open_local_fh() uses nfsd_serv_try_get() before opening its + nfsd_file handle and then the caller (NFS client) must drop the + reference for the nfsd_file and associated nn->nfsd_serv using + nfs_file_put_local() once it has completed its IO. + + This interlock working relies heavily on nfsd_open_local_fh() being + afforded the ability to safely deal with the possibility that the + NFSD's net-ns (and nfsd_net by association) may have been destroyed + by nfsd_destroy_serv() via nfsd_shutdown_net() -- which is only + possible given the nfs_uuid_t ->net pointer managemenet detailed + above. + +All told, this elaborate interlock of the NFS client and server has been +verified to fix an easy to hit crash that would occur if an NFSD +instance running in a container, with a LOCALIO client mounted, is +shutdown. Upon restart of the container and associated NFSD the client +would go on to crash due to NULL pointer dereference that occurred due +to the LOCALIO client's attempting to nfsd_open_local_fh(), using +nn->nfsd_serv, without having a proper reference on nn->nfsd_serv. + +NFS Client issues IO instead of Server +====================================== + +Because LOCALIO is focused on protocol bypass to achieve improved IO +performance, alternatives to the traditional NFS wire protocol (SUNRPC +with XDR) must be provided to access the backing filesystem. + +See fs/nfs/localio.c:nfs_local_open_fh() and +fs/nfsd/localio.c:nfsd_open_local_fh() for the interface that makes +focused use of select nfs server objects to allow a client local to a +server to open a file pointer without needing to go over the network. + +The client's fs/nfs/localio.c:nfs_local_open_fh() will call into the +server's fs/nfsd/localio.c:nfsd_open_local_fh() and carefully access +both the associated nfsd network namespace and nn->nfsd_serv in terms of +RCU. If nfsd_open_local_fh() finds that the client no longer sees valid +nfsd objects (be it struct net or nn->nfsd_serv) it returns -ENXIO +to nfs_local_open_fh() and the client will try to reestablish the +LOCALIO resources needed by calling nfs_local_probe() again. This +recovery is needed if/when an nfsd instance running in a container were +to reboot while a LOCALIO client is connected to it. + +Once the client has an open nfsd_file pointer it will issue reads, +writes and commits directly to the underlying local filesystem (normally +done by the nfs server). As such, for these operations, the NFS client +is issuing IO to the underlying local filesystem that it is sharing with +the NFS server. See: fs/nfs/localio.c:nfs_local_doio() and +fs/nfs/localio.c:nfs_local_commit(). + +Security +======== + +Localio is only supported when UNIX-style authentication (AUTH_UNIX, aka +AUTH_SYS) is used. + +Care is taken to ensure the same NFS security mechanisms are used +(authentication, etc) regardless of whether LOCALIO or regular NFS +access is used. The auth_domain established as part of the traditional +NFS client access to the NFS server is also used for LOCALIO. + +Relative to containers, LOCALIO gives the client access to the network +namespace the server has. This is required to allow the client to access +the server's per-namespace nfsd_net struct. With traditional NFS, the +client is afforded this same level of access (albeit in terms of the NFS +protocol via SUNRPC). No other namespaces (user, mount, etc) have been +altered or purposely extended from the server to the client. + +Testing +======= + +The LOCALIO auxiliary protocol and associated NFS LOCALIO read, write +and commit access have proven stable against various test scenarios: + +- Client and server both on the same host. + +- All permutations of client and server support enablement for both + local and remote client and server. + +- Testing against NFS storage products that don't support the LOCALIO + protocol was also performed. + +- Client on host, server within a container (for both v3 and v4.2). + The container testing was in terms of podman managed containers and + includes successful container stop/restart scenario. + +- Formalizing these test scenarios in terms of existing test + infrastructure is on-going. Initial regular coverage is provided in + terms of ktest running xfstests against a LOCALIO-enabled NFS loopback + mount configuration, and includes lockdep and KASAN coverage, see: + https://evilpiepirate.org/~testdashboard/ci?user=snitzer&branch=snitm-nfs-next + https://github.com/koverstreet/ktest + +- Various kdevops testing (in terms of "Chuck's BuildBot") has been + performed to regularly verify the LOCALIO changes haven't caused any + regressions to non-LOCALIO NFS use cases. + +- All of Hammerspace's various sanity tests pass with LOCALIO enabled + (this includes numerous pNFS and flexfiles tests). diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst index e3f388ef4ee4..6146b49b6a98 100644 --- a/Documentation/rust/general-information.rst +++ b/Documentation/rust/general-information.rst @@ -15,6 +15,8 @@ but not `std `_. Crates for use in the kernel must opt into this behavior using the ``#![no_std]`` attribute. +.. _rust_code_documentation: + Code documentation ------------------ @@ -22,10 +24,17 @@ Rust kernel code is documented using ``rustdoc``, its built-in documentation generator. The generated HTML docs include integrated search, linked items (e.g. types, -functions, constants), source code, etc. They may be read at (TODO: link when -in mainline and generated alongside the rest of the documentation): +functions, constants), source code, etc. They may be read at: - http://kernel.org/ + https://rust.docs.kernel.org + +For linux-next, please see: + + https://rust.docs.kernel.org/next/ + +There are also tags for each main release, e.g.: + + https://rust.docs.kernel.org/6.10/ The docs can also be easily generated and read locally. This is quite fast (same order as compiling the code itself) and no special tools or environment @@ -75,7 +84,7 @@ should provide as-safe-as-possible abstractions as needed. .. code-block:: rust/bindings/ - (rust/helpers.c) + (rust/helpers/) include/ -----+ <-+ | | @@ -112,7 +121,7 @@ output files in the ``rust/bindings/`` directory. For parts of the C header that ``bindgen`` does not auto generate, e.g. C ``inline`` functions or non-trivial macros, it is acceptable to add a small -wrapper function to ``rust/helpers.c`` to make it available for the Rust side as +wrapper function to ``rust/helpers/`` to make it available for the Rust side as well. Abstractions @@ -142,3 +151,11 @@ configuration: #[cfg(CONFIG_X="y")] // Enabled as a built-in (`y`) #[cfg(CONFIG_X="m")] // Enabled as a module (`m`) #[cfg(not(CONFIG_X))] // Disabled + +For other predicates that Rust's ``cfg`` does not support, e.g. expressions with +numerical comparisons, one may define a new Kconfig symbol: + +.. code-block:: kconfig + + config RUSTC_VERSION_MIN_107900 + def_bool y if RUSTC_VERSION >= 107900 diff --git a/Documentation/rust/index.rst b/Documentation/rust/index.rst index 46d35bd395cf..55dcde9e9e7e 100644 --- a/Documentation/rust/index.rst +++ b/Documentation/rust/index.rst @@ -25,13 +25,27 @@ support is still in development/experimental, especially for certain kernel configurations. +Code documentation +------------------ + +Given a kernel configuration, the kernel may generate Rust code documentation, +i.e. HTML rendered by the ``rustdoc`` tool. + .. only:: rustdoc and html - You can also browse `rustdoc documentation `_. + This kernel documentation was built with `Rust code documentation + `_. .. only:: not rustdoc and html - This documentation does not include rustdoc generated information. + This kernel documentation was not built with Rust code documentation. + +A pregenerated version is provided at: + + https://rust.docs.kernel.org + +Please see the :ref:`Code documentation ` section for +more details. .. toctree:: :maxdepth: 1 diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst index 8e3ad9678719..2d107982c87b 100644 --- a/Documentation/rust/quick-start.rst +++ b/Documentation/rust/quick-start.rst @@ -39,8 +39,8 @@ of the box, e.g.:: Debian ****** -Debian Unstable (Sid), outside of the freeze period, provides recent Rust -releases and thus it should generally work out of the box, e.g.:: +Debian Testing and Debian Unstable (Sid), outside of the freeze period, provide +recent Rust releases and thus they should generally work out of the box, e.g.:: apt install rustc rust-src bindgen rustfmt rust-clippy diff --git a/MAINTAINERS b/MAINTAINERS index f15f705f030a..9f622c921893 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20151,6 +20151,7 @@ R: Björn Roy Baron R: Benno Lossin R: Andreas Hindborg R: Alice Ryhl +R: Trevor Gross L: rust-for-linux@vger.kernel.org S: Supported W: https://rust-for-linux.com diff --git a/Makefile b/Makefile index 57a1e05c6130..2b13400e885d 100644 --- a/Makefile +++ b/Makefile @@ -663,9 +663,11 @@ endif # The expansion should be delayed until arch/$(SRCARCH)/Makefile is included. # Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile. -# CC_VERSION_TEXT is referenced from Kconfig (so it needs export), -# and from include/config/auto.conf.cmd to detect the compiler upgrade. +# CC_VERSION_TEXT and RUSTC_VERSION_TEXT are referenced from Kconfig (so they +# need export), and from include/config/auto.conf.cmd to detect the compiler +# upgrade. CC_VERSION_TEXT = $(subst $(pound),,$(shell LC_ALL=C $(CC) --version 2>/dev/null | head -n 1)) +RUSTC_VERSION_TEXT = $(subst $(pound),,$(shell $(RUSTC) --version 2>/dev/null)) ifneq ($(findstring clang,$(CC_VERSION_TEXT)),) include $(srctree)/scripts/Makefile.clang @@ -686,7 +688,7 @@ ifdef config-build # KBUILD_DEFCONFIG may point out an alternative default configuration # used for 'make defconfig' include $(srctree)/arch/$(SRCARCH)/Makefile -export KBUILD_DEFCONFIG KBUILD_KCONFIG CC_VERSION_TEXT +export KBUILD_DEFCONFIG KBUILD_KCONFIG CC_VERSION_TEXT RUSTC_VERSION_TEXT config: outputmakefile scripts_basic FORCE $(Q)$(MAKE) $(build)=scripts/kconfig $@ @@ -944,6 +946,7 @@ ifdef CONFIG_SHADOW_CALL_STACK ifndef CONFIG_DYNAMIC_SCS CC_FLAGS_SCS := -fsanitize=shadow-call-stack KBUILD_CFLAGS += $(CC_FLAGS_SCS) +KBUILD_RUSTFLAGS += -Zsanitizer=shadow-call-stack endif export CC_FLAGS_SCS endif @@ -977,6 +980,13 @@ CC_FLAGS_CFI := -fsanitize=kcfi ifdef CONFIG_CFI_ICALL_NORMALIZE_INTEGERS CC_FLAGS_CFI += -fsanitize-cfi-icall-experimental-normalize-integers endif +ifdef CONFIG_RUST + # Always pass -Zsanitizer-cfi-normalize-integers as CONFIG_RUST selects + # CONFIG_CFI_ICALL_NORMALIZE_INTEGERS. + RUSTC_FLAGS_CFI := -Zsanitizer=kcfi -Zsanitizer-cfi-normalize-integers + KBUILD_RUSTFLAGS += $(RUSTC_FLAGS_CFI) + export RUSTC_FLAGS_CFI +endif KBUILD_CFLAGS += $(CC_FLAGS_CFI) export CC_FLAGS_CFI endif diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 66cb9da44e8c..f8b8ea9d9cf2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -235,7 +235,7 @@ config ARM64 select HAVE_FUNCTION_ARG_ACCESS_API select MMU_GATHER_RCU_TABLE_FREE select HAVE_RSEQ - select HAVE_RUST if CPU_LITTLE_ENDIAN + select HAVE_RUST if RUSTC_SUPPORTS_ARM64 select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_KPROBES @@ -270,6 +270,18 @@ config ARM64 help ARM 64-bit (AArch64) Linux support. +config RUSTC_SUPPORTS_ARM64 + def_bool y + depends on CPU_LITTLE_ENDIAN + # Shadow call stack is only supported on certain rustc versions. + # + # When using the UNWIND_PATCH_PAC_INTO_SCS option, rustc version 1.80+ is + # required due to use of the -Zfixed-x18 flag. + # + # Otherwise, rustc version 1.82+ is required due to use of the + # -Zsanitizer=shadow-call-stack flag. + depends on !SHADOW_CALL_STACK || RUSTC_VERSION >= 108200 || RUSTC_VERSION >= 108000 && UNWIND_PATCH_PAC_INTO_SCS + config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_CLANG # https://github.com/ClangBuiltLinux/linux/issues/1507 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index ec659634eb1e..ce5e793dac8c 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -57,9 +57,11 @@ KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) ifneq ($(CONFIG_UNWIND_TABLES),y) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables KBUILD_AFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables +KBUILD_RUSTFLAGS += -Cforce-unwind-tables=n else KBUILD_CFLAGS += -fasynchronous-unwind-tables KBUILD_AFLAGS += -fasynchronous-unwind-tables +KBUILD_RUSTFLAGS += -Cforce-unwind-tables=y -Zuse-sync-unwind=n endif ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) @@ -114,6 +116,7 @@ endif ifeq ($(CONFIG_SHADOW_CALL_STACK), y) KBUILD_CFLAGS += -ffixed-x18 +KBUILD_RUSTFLAGS += -Zfixed-x18 endif ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 0e59b8fd9bc6..83fe99861eb1 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1574,6 +1574,104 @@ static int proc_eeh_show(struct seq_file *m, void *v) } #endif /* CONFIG_PROC_FS */ +static int eeh_break_device(struct pci_dev *pdev) +{ + struct resource *bar = NULL; + void __iomem *mapped; + u16 old, bit; + int i, pos; + + /* Do we have an MMIO BAR to disable? */ + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + struct resource *r = &pdev->resource[i]; + + if (!r->flags || !r->start) + continue; + if (r->flags & IORESOURCE_IO) + continue; + if (r->flags & IORESOURCE_UNSET) + continue; + + bar = r; + break; + } + + if (!bar) { + pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n"); + return -ENXIO; + } + + pci_err(pdev, "Going to break: %pR\n", bar); + + if (pdev->is_virtfn) { +#ifndef CONFIG_PCI_IOV + return -ENXIO; +#else + /* + * VFs don't have a per-function COMMAND register, so the best + * we can do is clear the Memory Space Enable bit in the PF's + * SRIOV control reg. + * + * Unfortunately, this requires that we have a PF (i.e doesn't + * work for a passed-through VF) and it has the potential side + * effect of also causing an EEH on every other VF under the + * PF. Oh well. + */ + pdev = pdev->physfn; + if (!pdev) + return -ENXIO; /* passed through VFs have no PF */ + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pos += PCI_SRIOV_CTRL; + bit = PCI_SRIOV_CTRL_MSE; +#endif /* !CONFIG_PCI_IOV */ + } else { + bit = PCI_COMMAND_MEMORY; + pos = PCI_COMMAND; + } + + /* + * Process here is: + * + * 1. Disable Memory space. + * + * 2. Perform an MMIO to the device. This should result in an error + * (CA / UR) being raised by the device which results in an EEH + * PE freeze. Using the in_8() accessor skips the eeh detection hook + * so the freeze hook so the EEH Detection machinery won't be + * triggered here. This is to match the usual behaviour of EEH + * where the HW will asynchronously freeze a PE and it's up to + * the kernel to notice and deal with it. + * + * 3. Turn Memory space back on. This is more important for VFs + * since recovery will probably fail if we don't. For normal + * the COMMAND register is reset as a part of re-initialising + * the device. + * + * Breaking stuff is the point so who cares if it's racy ;) + */ + pci_read_config_word(pdev, pos, &old); + + mapped = ioremap(bar->start, PAGE_SIZE); + if (!mapped) { + pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar); + return -ENXIO; + } + + pci_write_config_word(pdev, pos, old & ~bit); + in_8(mapped); + pci_write_config_word(pdev, pos, old); + + iounmap(mapped); + + return 0; +} + +int eeh_pe_inject_mmio_error(struct pci_dev *pdev) +{ + return eeh_break_device(pdev); +} + #ifdef CONFIG_DEBUG_FS @@ -1725,99 +1823,6 @@ static const struct file_operations eeh_dev_check_fops = { .read = eeh_debugfs_dev_usage, }; -static int eeh_debugfs_break_device(struct pci_dev *pdev) -{ - struct resource *bar = NULL; - void __iomem *mapped; - u16 old, bit; - int i, pos; - - /* Do we have an MMIO BAR to disable? */ - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { - struct resource *r = &pdev->resource[i]; - - if (!r->flags || !r->start) - continue; - if (r->flags & IORESOURCE_IO) - continue; - if (r->flags & IORESOURCE_UNSET) - continue; - - bar = r; - break; - } - - if (!bar) { - pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n"); - return -ENXIO; - } - - pci_err(pdev, "Going to break: %pR\n", bar); - - if (pdev->is_virtfn) { -#ifndef CONFIG_PCI_IOV - return -ENXIO; -#else - /* - * VFs don't have a per-function COMMAND register, so the best - * we can do is clear the Memory Space Enable bit in the PF's - * SRIOV control reg. - * - * Unfortunately, this requires that we have a PF (i.e doesn't - * work for a passed-through VF) and it has the potential side - * effect of also causing an EEH on every other VF under the - * PF. Oh well. - */ - pdev = pdev->physfn; - if (!pdev) - return -ENXIO; /* passed through VFs have no PF */ - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); - pos += PCI_SRIOV_CTRL; - bit = PCI_SRIOV_CTRL_MSE; -#endif /* !CONFIG_PCI_IOV */ - } else { - bit = PCI_COMMAND_MEMORY; - pos = PCI_COMMAND; - } - - /* - * Process here is: - * - * 1. Disable Memory space. - * - * 2. Perform an MMIO to the device. This should result in an error - * (CA / UR) being raised by the device which results in an EEH - * PE freeze. Using the in_8() accessor skips the eeh detection hook - * so the freeze hook so the EEH Detection machinery won't be - * triggered here. This is to match the usual behaviour of EEH - * where the HW will asynchronously freeze a PE and it's up to - * the kernel to notice and deal with it. - * - * 3. Turn Memory space back on. This is more important for VFs - * since recovery will probably fail if we don't. For normal - * the COMMAND register is reset as a part of re-initialising - * the device. - * - * Breaking stuff is the point so who cares if it's racy ;) - */ - pci_read_config_word(pdev, pos, &old); - - mapped = ioremap(bar->start, PAGE_SIZE); - if (!mapped) { - pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar); - return -ENXIO; - } - - pci_write_config_word(pdev, pos, old & ~bit); - in_8(mapped); - pci_write_config_word(pdev, pos, old); - - iounmap(mapped); - - return 0; -} - static ssize_t eeh_dev_break_write(struct file *filp, const char __user *user_buf, size_t count, loff_t *ppos) @@ -1829,7 +1834,7 @@ static ssize_t eeh_dev_break_write(struct file *filp, if (IS_ERR(pdev)) return PTR_ERR(pdev); - ret = eeh_debugfs_break_device(pdev); + ret = eeh_break_device(pdev); pci_dev_put(pdev); if (ret < 0) @@ -1844,11 +1849,6 @@ static const struct file_operations eeh_dev_break_fops = { .read = eeh_debugfs_dev_usage, }; -int eeh_pe_inject_mmio_error(struct pci_dev *pdev) -{ - return eeh_debugfs_break_device(pdev); -} - static ssize_t eeh_dev_can_recover(struct file *filp, const char __user *user_buf, size_t count, loff_t *ppos) diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S index 7e5e1c28e56a..8967903c15e9 100644 --- a/arch/powerpc/lib/crtsavres.S +++ b/arch/powerpc/lib/crtsavres.S @@ -46,7 +46,7 @@ .section ".text" -#ifndef CONFIG_PPC64 +#ifndef __powerpc64__ /* Routines for saving integer registers, called by the compiler. */ /* Called with r11 pointing to the stack header word of the caller of the */ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b6d515db869b..22dc5ea4196c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -177,7 +177,7 @@ config RISCV select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RETHOOK if !XIP_KERNEL select HAVE_RSEQ - select HAVE_RUST if 64BIT + select HAVE_RUST if RUSTC_SUPPORTS_RISCV select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_STACKPROTECTOR @@ -209,6 +209,13 @@ config RISCV select USER_STACKTRACE_SUPPORT select ZONE_DMA32 if 64BIT +config RUSTC_SUPPORTS_RISCV + def_bool y + depends on 64BIT + # Shadow call stack requires rustc version 1.82+ due to use of the + # -Zsanitizer=shadow-call-stack flag. + depends on !SHADOW_CALL_STACK || RUSTC_VERSION >= 108200 + config CLANG_SUPPORTS_DYNAMIC_FTRACE def_bool CC_IS_CLANG # https://github.com/ClangBuiltLinux/linux/issues/1817 diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 688abc65c79e..7a96623a9d2e 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -62,7 +62,7 @@ EXPORT_SYMBOL(zero_page_mask); static void __init setup_zero_pages(void) { - unsigned long total_pages = PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); + unsigned long total_pages = memblock_estimated_nr_free_pages(); unsigned int order; struct page *page; int i; diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c index ec61ff1f96b7..1dc9b3d70eda 100644 --- a/arch/sparc/mm/leon_mm.c +++ b/arch/sparc/mm/leon_mm.c @@ -39,12 +39,10 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr) unsigned int ctxtbl; unsigned int pgd, pmd, ped; unsigned int ptr; - unsigned int lvl, pte, paddrbase; + unsigned int lvl, pte; unsigned int ctx; unsigned int paddr_calc; - paddrbase = 0; - if (srmmu_swprobe_trace) printk(KERN_INFO "swprobe: trace on\n"); @@ -73,7 +71,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr) printk(KERN_INFO "swprobe: pgd is entry level 3\n"); lvl = 3; pte = pgd; - paddrbase = pgd & _SRMMU_PTE_PMASK_LEON; goto ready; } if (((pgd & SRMMU_ET_MASK) != SRMMU_ET_PTD)) { @@ -96,7 +93,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr) printk(KERN_INFO "swprobe: pmd is entry level 2\n"); lvl = 2; pte = pmd; - paddrbase = pmd & _SRMMU_PTE_PMASK_LEON; goto ready; } if (((pmd & SRMMU_ET_MASK) != SRMMU_ET_PTD)) { @@ -124,7 +120,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr) printk(KERN_INFO "swprobe: ped is entry level 1\n"); lvl = 1; pte = ped; - paddrbase = ped & _SRMMU_PTE_PMASK_LEON; goto ready; } if (((ped & SRMMU_ET_MASK) != SRMMU_ET_PTD)) { @@ -147,7 +142,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr) printk(KERN_INFO "swprobe: ptr is entry level 0\n"); lvl = 0; pte = ptr; - paddrbase = ptr & _SRMMU_PTE_PMASK_LEON; goto ready; } if (srmmu_swprobe_trace) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index fe9717f562d2..971fe11b05a2 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -24,11 +24,15 @@ RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) ifdef CONFIG_MITIGATION_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern +RETHUNK_RUSTFLAGS := -Zfunction-return=thunk-extern RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) +RETPOLINE_RUSTFLAGS += $(RETHUNK_RUSTFLAGS) endif export RETHUNK_CFLAGS +export RETHUNK_RUSTFLAGS export RETPOLINE_CFLAGS +export RETPOLINE_RUSTFLAGS export RETPOLINE_VDSO_CFLAGS # For gcc stack alignment is specified with -mpreferred-stack-boundary, @@ -218,9 +222,10 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_MITIGATION_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) + KBUILD_RUSTFLAGS += $(RETPOLINE_RUSTFLAGS) # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. - # clang turns off jump table generation by default when under + # LLVM turns off jump table generation by default when under # retpoline builds, however, gcc does not for x86. This has # only been fixed starting from gcc stable version 8.4.0 and # onwards, but not for older ones. See gcc bug #86952. @@ -237,6 +242,10 @@ ifdef CONFIG_CALL_PADDING PADDING_CFLAGS := -fpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES) KBUILD_CFLAGS += $(PADDING_CFLAGS) export PADDING_CFLAGS + +PADDING_RUSTFLAGS := -Zpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES) +KBUILD_RUSTFLAGS += $(PADDING_RUSTFLAGS) +export PADDING_RUSTFLAGS endif KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE) diff --git a/fs/Kconfig b/fs/Kconfig index 7024a1976170..8395d0a7b1d6 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -387,6 +387,29 @@ config NFS_COMMON depends on NFSD || NFS_FS || LOCKD default y +config NFS_COMMON_LOCALIO_SUPPORT + tristate + default n + default y if NFSD=y || NFS_FS=y + default m if NFSD=m && NFS_FS=m + select SUNRPC + +config NFS_LOCALIO + bool "NFS client and server support for LOCALIO auxiliary protocol" + depends on NFSD && NFS_FS + select NFS_COMMON_LOCALIO_SUPPORT + default n + help + Some NFS servers support an auxiliary NFS LOCALIO protocol + that is not an official part of the NFS protocol. + + This option enables support for the LOCALIO protocol in the + kernel's NFS server and client. Enable this to permit local + NFS clients to bypass the network when issuing reads and + writes to the local NFS server. + + If unsure, say N. + config NFS_V4_2_SSC_HELPER bool default y if NFS_V4_2 diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 57249f040dfc..0eb20012792f 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,6 +4,7 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC + select NFS_COMMON select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 5f6db37f461e..9fb2f2cac87e 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -13,6 +13,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o +nfs-$(CONFIG_NFS_LOCALIO) += localio.o obj-$(CONFIG_NFS_V2) += nfsv2.o nfsv2-y := nfs2super.o proc.o nfs2xdr.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8286edd6062d..a1d21c4be0ac 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -178,6 +178,14 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1; clp->cl_net = get_net(cl_init->net); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + seqlock_init(&clp->cl_boot_lock); + ktime_get_real_ts64(&clp->cl_nfssvc_boot); + clp->cl_uuid.net = NULL; + clp->cl_uuid.dom = NULL; + spin_lock_init(&clp->cl_localio_lock); +#endif /* CONFIG_NFS_LOCALIO */ + clp->cl_principal = "*"; clp->cl_xprtsec = cl_init->xprtsec; return clp; @@ -233,6 +241,8 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { + nfs_local_disable(clp); + /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); @@ -424,7 +434,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) list_add_tail(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); - return rpc_ops->init_client(new, cl_init); + new = rpc_ops->init_client(new, cl_init); + if (!IS_ERR(new)) + nfs_local_probe(new); + return new; } spin_unlock(&nn->nfs_client_lock); @@ -997,8 +1010,8 @@ struct nfs_server *nfs_alloc_server(void) init_waitqueue_head(&server->write_congestion_wait); atomic_long_set(&server->writeback, 0); - ida_init(&server->openowner_id); - ida_init(&server->lockowner_id); + atomic64_set(&server->owner_ctr, 0); + pnfs_init_server(server); rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); @@ -1037,8 +1050,6 @@ void nfs_free_server(struct nfs_server *server) } ida_free(&s_sysfs_ids, server->s_sysfs_id); - ida_destroy(&server->lockowner_id); - ida_destroy(&server->openowner_id); put_cred(server->cred); nfs_release_automount_timer(); call_rcu(&server->rcu, delayed_free); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 4cb97ef41350..492cffd9d3d8 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -151,7 +151,7 @@ struct nfs_cache_array { unsigned char folio_full : 1, folio_is_eof : 1, cookies_are_ordered : 1; - struct nfs_cache_array_entry array[]; + struct nfs_cache_array_entry array[] __counted_by(size); }; struct nfs_readdir_descriptor { @@ -328,7 +328,8 @@ static int nfs_readdir_folio_array_append(struct folio *folio, goto out; } - cache_entry = &array->array[array->size]; + array->size++; + cache_entry = &array->array[array->size - 1]; cache_entry->cookie = array->last_cookie; cache_entry->ino = entry->ino; cache_entry->d_type = entry->d_type; @@ -337,7 +338,6 @@ static int nfs_readdir_folio_array_append(struct folio *folio, array->last_cookie = entry->cookie; if (array->last_cookie <= cache_entry->cookie) array->cookies_are_ordered = 0; - array->size++; if (entry->eof != 0) nfs_readdir_array_set_eof(array); out: diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index b6e9aeaf4ce2..d39a1f58e18d 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -488,7 +488,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) /* Perform an asynchronous read to ds */ nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, NFS_PROTO(hdr->inode), &filelayout_read_call_ops, - 0, RPC_TASK_SOFTCONN); + 0, RPC_TASK_SOFTCONN, NULL); return PNFS_ATTEMPTED; } @@ -530,7 +530,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) /* Perform an asynchronous write */ nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, NFS_PROTO(hdr->inode), &filelayout_write_call_ops, - sync, RPC_TASK_SOFTCONN); + sync, RPC_TASK_SOFTCONN, NULL); return PNFS_ATTEMPTED; } @@ -1011,7 +1011,7 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) data->args.fh = fh; return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode), &filelayout_commit_call_ops, how, - RPC_TASK_SOFTCONN); + RPC_TASK_SOFTCONN, NULL); out_err: pnfs_generic_prepare_to_resend_writes(data); pnfs_generic_commit_release(data); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 39ba9f4208aa..f78115c6c2c1 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -162,6 +163,21 @@ decode_name(struct xdr_stream *xdr, u32 *id) return 0; } +static struct nfsd_file * +ff_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, fmode_t mode) +{ + if (mode & FMODE_WRITE) { + /* + * Always request read and write access since this corresponds + * to a rw layout. + */ + mode |= FMODE_READ; + } + + return nfs_local_open_fh(clp, cred, fh, mode); +} + static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, const struct nfs4_ff_layout_mirror *m2) { @@ -237,7 +253,7 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags) static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror) { - const struct cred *cred; + const struct cred *cred; ff_layout_remove_mirror(mirror); kfree(mirror->fh_versions); @@ -1756,6 +1772,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; struct rpc_clnt *ds_clnt; + struct nfsd_file *localio; struct nfs4_ff_layout_mirror *mirror; const struct cred *ds_cred; loff_t offset = hdr->args.offset; @@ -1802,11 +1819,18 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) hdr->args.offset = offset; hdr->mds_offset = offset; + /* Start IO accounting for local read */ + localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, FMODE_READ); + if (localio) { + hdr->task.tk_start = ktime_get(); + ff_layout_read_record_layoutstats_start(&hdr->task, hdr); + } + /* Perform an asynchronous read to ds */ nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, vers == 3 ? &ff_layout_read_call_ops_v3 : &ff_layout_read_call_ops_v4, - 0, RPC_TASK_SOFTCONN); + 0, RPC_TASK_SOFTCONN, localio); put_cred(ds_cred); return PNFS_ATTEMPTED; @@ -1826,6 +1850,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; struct rpc_clnt *ds_clnt; + struct nfsd_file *localio; struct nfs4_ff_layout_mirror *mirror; const struct cred *ds_cred; loff_t offset = hdr->args.offset; @@ -1870,11 +1895,19 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) */ hdr->args.offset = offset; + /* Start IO accounting for local write */ + localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, + FMODE_READ|FMODE_WRITE); + if (localio) { + hdr->task.tk_start = ktime_get(); + ff_layout_write_record_layoutstats_start(&hdr->task, hdr); + } + /* Perform an asynchronous write */ nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, vers == 3 ? &ff_layout_write_call_ops_v3 : &ff_layout_write_call_ops_v4, - sync, RPC_TASK_SOFTCONN); + sync, RPC_TASK_SOFTCONN, localio); put_cred(ds_cred); return PNFS_ATTEMPTED; @@ -1908,6 +1941,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) struct pnfs_layout_segment *lseg = data->lseg; struct nfs4_pnfs_ds *ds; struct rpc_clnt *ds_clnt; + struct nfsd_file *localio; struct nfs4_ff_layout_mirror *mirror; const struct cred *ds_cred; u32 idx; @@ -1946,10 +1980,18 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) if (fh) data->args.fh = fh; + /* Start IO accounting for local commit */ + localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, + FMODE_READ|FMODE_WRITE); + if (localio) { + data->task.tk_start = ktime_get(); + ff_layout_commit_record_layoutstats_start(&data->task, data); + } + ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops, vers == 3 ? &ff_layout_commit_call_ops_v3 : &ff_layout_commit_call_ops_v4, - how, RPC_TASK_SOFTCONN); + how, RPC_TASK_SOFTCONN, localio); put_cred(ds_cred); return ret; out_err: @@ -2086,12 +2128,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr, return ff_layout_encode_ds_ioerr(xdr, &ff_args->errors); } -static void -encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len) -{ - WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); -} - static void ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr, const nfs4_stateid *stateid, diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e028f5a0ef5f..e58bedfb1dcc 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -395,6 +395,12 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, /* connect success, check rsize/wsize limit */ if (!status) { + /* + * ds_clp is put in destroy_ds(). + * keep ds_clp even if DS is local, so that if local IO cannot + * proceed somehow, we can fall back to NFS whenever we want. + */ + nfs_local_probe(ds->ds_clp); max_payload = nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient), NULL); diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 6c9f3f6645dd..7e000d782e28 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -49,6 +49,7 @@ enum nfs_param { Opt_bsize, Opt_clientaddr, Opt_cto, + Opt_alignwrite, Opt_fg, Opt_fscache, Opt_fscache_flag, @@ -149,6 +150,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_u32 ("bsize", Opt_bsize), fsparam_string("clientaddr", Opt_clientaddr), fsparam_flag_no("cto", Opt_cto), + fsparam_flag_no("alignwrite", Opt_alignwrite), fsparam_flag ("fg", Opt_fg), fsparam_flag_no("fsc", Opt_fscache_flag), fsparam_string("fsc", Opt_fscache), @@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, else ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; break; + case Opt_alignwrite: + if (result.negated) + ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE; + else + ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE; + break; case Opt_ac: if (result.negated) ctx->flags |= NFS_MOUNT_NOAC; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 11ff2b2e060f..f13d25d95b85 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -62,7 +62,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i } /* - * get an NFS2/NFS3 root dentry from the root filehandle + * get a root dentry from the root filehandle */ int nfs_get_root(struct super_block *s, struct fs_context *fc) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b4914a11c3c2..542c7d97b235 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2461,35 +2461,54 @@ static void nfs_destroy_inodecache(void) kmem_cache_destroy(nfs_inode_cachep); } +struct workqueue_struct *nfslocaliod_workqueue; struct workqueue_struct *nfsiod_workqueue; EXPORT_SYMBOL_GPL(nfsiod_workqueue); /* - * start up the nfsiod workqueue - */ -static int nfsiod_start(void) -{ - struct workqueue_struct *wq; - dprintk("RPC: creating workqueue nfsiod\n"); - wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); - if (wq == NULL) - return -ENOMEM; - nfsiod_workqueue = wq; - return 0; -} - -/* - * Destroy the nfsiod workqueue + * Destroy the nfsiod workqueues */ static void nfsiod_stop(void) { struct workqueue_struct *wq; wq = nfsiod_workqueue; - if (wq == NULL) - return; - nfsiod_workqueue = NULL; - destroy_workqueue(wq); + if (wq != NULL) { + nfsiod_workqueue = NULL; + destroy_workqueue(wq); + } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + wq = nfslocaliod_workqueue; + if (wq != NULL) { + nfslocaliod_workqueue = NULL; + destroy_workqueue(wq); + } +#endif /* CONFIG_NFS_LOCALIO */ +} + +/* + * Start the nfsiod workqueues + */ +static int nfsiod_start(void) +{ + dprintk("RPC: creating workqueue nfsiod\n"); + nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + if (nfsiod_workqueue == NULL) + return -ENOMEM; +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + /* + * localio writes need to use a normal (non-memreclaim) workqueue. + * When we start getting low on space, XFS goes and calls flush_work() on + * a non-memreclaim work queue, which causes a priority inversion problem. + */ + dprintk("RPC: creating workqueue nfslocaliod\n"); + nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0); + if (unlikely(nfslocaliod_workqueue == NULL)) { + nfsiod_stop(); + return -ENOMEM; + } +#endif /* CONFIG_NFS_LOCALIO */ + return 0; } unsigned int nfs_net_id; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5902a9beca1f..430733e3eff2 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) @@ -308,7 +309,8 @@ void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, - const struct rpc_call_ops *call_ops, int how, int flags); + const struct rpc_call_ops *call_ops, int how, int flags, + struct nfsd_file *localio); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); @@ -438,6 +440,7 @@ int nfs_check_flags(int); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; +extern struct workqueue_struct *nfslocaliod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); @@ -449,6 +452,51 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +/* localio.c */ +extern void nfs_local_disable(struct nfs_client *); +extern void nfs_local_probe(struct nfs_client *); +extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, + const struct cred *, + struct nfs_fh *, + const fmode_t); +extern int nfs_local_doio(struct nfs_client *, + struct nfsd_file *, + struct nfs_pgio_header *, + const struct rpc_call_ops *); +extern int nfs_local_commit(struct nfsd_file *, + struct nfs_commit_data *, + const struct rpc_call_ops *, int); +extern bool nfs_server_is_local(const struct nfs_client *clp); + +#else /* CONFIG_NFS_LOCALIO */ +static inline void nfs_local_disable(struct nfs_client *clp) {} +static inline void nfs_local_probe(struct nfs_client *clp) {} +static inline struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, const fmode_t mode) +{ + return NULL; +} +static inline int nfs_local_doio(struct nfs_client *clp, + struct nfsd_file *localio, + struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + return -EINVAL; +} +static inline int nfs_local_commit(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops, int how) +{ + return -EINVAL; +} +static inline bool nfs_server_is_local(const struct nfs_client *clp) +{ + return false; +} +#endif /* CONFIG_NFS_LOCALIO */ + /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); @@ -505,7 +553,6 @@ extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); -extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ @@ -528,7 +575,8 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, - int how, int flags); + int how, int flags, + struct nfsd_file *localio); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c new file mode 100644 index 000000000000..c29cdf51c458 --- /dev/null +++ b/fs/nfs/localio.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * NFS client support for local clients to bypass network stack + * + * Copyright (C) 2014 Weston Andros Adamson + * Copyright (C) 2019 Trond Myklebust + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "internal.h" +#include "pnfs.h" +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +struct nfs_local_kiocb { + struct kiocb kiocb; + struct bio_vec *bvec; + struct nfs_pgio_header *hdr; + struct work_struct work; + struct nfsd_file *localio; +}; + +struct nfs_local_fsync_ctx { + struct nfsd_file *localio; + struct nfs_commit_data *data; + struct work_struct work; + struct kref kref; + struct completion *done; +}; +static void nfs_local_fsync_work(struct work_struct *work); + +static bool localio_enabled __read_mostly = true; +module_param(localio_enabled, bool, 0644); + +static inline bool nfs_client_is_local(const struct nfs_client *clp) +{ + return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); +} + +bool nfs_server_is_local(const struct nfs_client *clp) +{ + return nfs_client_is_local(clp) && localio_enabled; +} +EXPORT_SYMBOL_GPL(nfs_server_is_local); + +/* + * UUID_IS_LOCAL XDR functions + */ + +static void localio_xdr_enc_uuidargs(struct rpc_rqst *req, + struct xdr_stream *xdr, + const void *data) +{ + const u8 *uuid = data; + + encode_opaque_fixed(xdr, uuid, UUID_SIZE); +} + +static int localio_xdr_dec_uuidres(struct rpc_rqst *req, + struct xdr_stream *xdr, + void *result) +{ + /* void return */ + return 0; +} + +static const struct rpc_procinfo nfs_localio_procedures[] = { + [LOCALIOPROC_UUID_IS_LOCAL] = { + .p_proc = LOCALIOPROC_UUID_IS_LOCAL, + .p_encode = localio_xdr_enc_uuidargs, + .p_decode = localio_xdr_dec_uuidres, + .p_arglen = XDR_QUADLEN(UUID_SIZE), + .p_replen = 0, + .p_statidx = LOCALIOPROC_UUID_IS_LOCAL, + .p_name = "UUID_IS_LOCAL", + }, +}; + +static unsigned int nfs_localio_counts[ARRAY_SIZE(nfs_localio_procedures)]; +static const struct rpc_version nfslocalio_version1 = { + .number = 1, + .nrprocs = ARRAY_SIZE(nfs_localio_procedures), + .procs = nfs_localio_procedures, + .counts = nfs_localio_counts, +}; + +static const struct rpc_version *nfslocalio_version[] = { + [1] = &nfslocalio_version1, +}; + +extern const struct rpc_program nfslocalio_program; +static struct rpc_stat nfslocalio_rpcstat = { &nfslocalio_program }; + +const struct rpc_program nfslocalio_program = { + .name = "nfslocalio", + .number = NFS_LOCALIO_PROGRAM, + .nrvers = ARRAY_SIZE(nfslocalio_version), + .version = nfslocalio_version, + .stats = &nfslocalio_rpcstat, +}; + +/* + * nfs_local_enable - enable local i/o for an nfs_client + */ +static void nfs_local_enable(struct nfs_client *clp) +{ + spin_lock(&clp->cl_localio_lock); + set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags); + trace_nfs_local_enable(clp); + spin_unlock(&clp->cl_localio_lock); +} + +/* + * nfs_local_disable - disable local i/o for an nfs_client + */ +void nfs_local_disable(struct nfs_client *clp) +{ + spin_lock(&clp->cl_localio_lock); + if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) { + trace_nfs_local_disable(clp); + nfs_uuid_invalidate_one_client(&clp->cl_uuid); + } + spin_unlock(&clp->cl_localio_lock); +} + +/* + * nfs_init_localioclient - Initialise an NFS localio client connection + */ +static struct rpc_clnt *nfs_init_localioclient(struct nfs_client *clp) +{ + struct rpc_clnt *rpcclient_localio; + + rpcclient_localio = rpc_bind_new_program(clp->cl_rpcclient, + &nfslocalio_program, 1); + + dprintk_rcu("%s: server (%s) %s NFS LOCALIO.\n", + __func__, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR), + (IS_ERR(rpcclient_localio) ? "does not support" : "supports")); + + return rpcclient_localio; +} + +static bool nfs_server_uuid_is_local(struct nfs_client *clp) +{ + u8 uuid[UUID_SIZE]; + struct rpc_message msg = { + .rpc_argp = &uuid, + }; + struct rpc_clnt *rpcclient_localio; + int status; + + rpcclient_localio = nfs_init_localioclient(clp); + if (IS_ERR(rpcclient_localio)) + return false; + + export_uuid(uuid, &clp->cl_uuid.uuid); + + msg.rpc_proc = &nfs_localio_procedures[LOCALIOPROC_UUID_IS_LOCAL]; + status = rpc_call_sync(rpcclient_localio, &msg, 0); + dprintk("%s: NFS reply UUID_IS_LOCAL: status=%d\n", + __func__, status); + rpc_shutdown_client(rpcclient_localio); + + /* Server is only local if it initialized required struct members */ + if (status || !clp->cl_uuid.net || !clp->cl_uuid.dom) + return false; + + return true; +} + +/* + * nfs_local_probe - probe local i/o support for an nfs_server and nfs_client + * - called after alloc_client and init_client (so cl_rpcclient exists) + * - this function is idempotent, it can be called for old or new clients + */ +void nfs_local_probe(struct nfs_client *clp) +{ + /* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */ + if (!localio_enabled || + clp->cl_rpcclient->cl_auth->au_flavor != RPC_AUTH_UNIX) { + nfs_local_disable(clp); + return; + } + + if (nfs_client_is_local(clp)) { + /* If already enabled, disable and re-enable */ + nfs_local_disable(clp); + } + + nfs_uuid_begin(&clp->cl_uuid); + if (nfs_server_uuid_is_local(clp)) + nfs_local_enable(clp); + nfs_uuid_end(&clp->cl_uuid); +} +EXPORT_SYMBOL_GPL(nfs_local_probe); + +/* + * nfs_local_open_fh - open a local filehandle in terms of nfsd_file + * + * Returns a pointer to a struct nfsd_file or NULL + */ +struct nfsd_file * +nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, + struct nfs_fh *fh, const fmode_t mode) +{ + struct nfsd_file *localio; + int status; + + if (!nfs_server_is_local(clp)) + return NULL; + if (mode & ~(FMODE_READ | FMODE_WRITE)) + return NULL; + + localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient, + cred, fh, mode); + if (IS_ERR(localio)) { + status = PTR_ERR(localio); + trace_nfs_local_open_fh(fh, mode, status); + switch (status) { + case -ENOMEM: + case -ENXIO: + case -ENOENT: + /* Revalidate localio, will disable if unsupported */ + nfs_local_probe(clp); + } + return NULL; + } + return localio; +} +EXPORT_SYMBOL_GPL(nfs_local_open_fh); + +static struct bio_vec * +nfs_bvec_alloc_and_import_pagevec(struct page **pagevec, + unsigned int npages, gfp_t flags) +{ + struct bio_vec *bvec, *p; + + bvec = kmalloc_array(npages, sizeof(*bvec), flags); + if (bvec != NULL) { + for (p = bvec; npages > 0; p++, pagevec++, npages--) { + p->bv_page = *pagevec; + p->bv_len = PAGE_SIZE; + p->bv_offset = 0; + } + } + return bvec; +} + +static void +nfs_local_iocb_free(struct nfs_local_kiocb *iocb) +{ + kfree(iocb->bvec); + kfree(iocb); +} + +static struct nfs_local_kiocb * +nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, + struct nfsd_file *localio, gfp_t flags) +{ + struct nfs_local_kiocb *iocb; + + iocb = kmalloc(sizeof(*iocb), flags); + if (iocb == NULL) + return NULL; + iocb->bvec = nfs_bvec_alloc_and_import_pagevec(hdr->page_array.pagevec, + hdr->page_array.npages, flags); + if (iocb->bvec == NULL) { + kfree(iocb); + return NULL; + } + init_sync_kiocb(&iocb->kiocb, nfs_to->nfsd_file_file(localio)); + iocb->kiocb.ki_pos = hdr->args.offset; + iocb->localio = localio; + iocb->hdr = hdr; + iocb->kiocb.ki_flags &= ~IOCB_APPEND; + return iocb; +} + +static void +nfs_local_iter_init(struct iov_iter *i, struct nfs_local_kiocb *iocb, int dir) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + + iov_iter_bvec(i, dir, iocb->bvec, hdr->page_array.npages, + hdr->args.count + hdr->args.pgbase); + if (hdr->args.pgbase != 0) + iov_iter_advance(i, hdr->args.pgbase); +} + +static void +nfs_local_hdr_release(struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + call_ops->rpc_call_done(&hdr->task, hdr); + call_ops->rpc_release(hdr); +} + +static void +nfs_local_pgio_init(struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + hdr->task.tk_ops = call_ops; + if (!hdr->task.tk_start) + hdr->task.tk_start = ktime_get(); +} + +static void +nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) +{ + if (status >= 0) { + hdr->res.count = status; + hdr->res.op_status = NFS4_OK; + hdr->task.tk_status = 0; + } else { + hdr->res.op_status = nfs4_stat_to_errno(status); + hdr->task.tk_status = status; + } +} + +static void +nfs_local_pgio_release(struct nfs_local_kiocb *iocb) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + + nfs_to->nfsd_file_put_local(iocb->localio); + nfs_local_iocb_free(iocb); + nfs_local_hdr_release(hdr, hdr->task.tk_ops); +} + +static void +nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + struct file *filp = iocb->kiocb.ki_filp; + + nfs_local_pgio_done(hdr, status); + + if (hdr->res.count != hdr->args.count || + hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp))) + hdr->res.eof = true; + + dprintk("%s: read %ld bytes eof %d.\n", __func__, + status > 0 ? status : 0, hdr->res.eof); +} + +static void nfs_local_call_read(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + struct file *filp = iocb->kiocb.ki_filp; + const struct cred *save_cred; + struct iov_iter iter; + ssize_t status; + + save_cred = override_creds(filp->f_cred); + + nfs_local_iter_init(&iter, iocb, READ); + + status = filp->f_op->read_iter(&iocb->kiocb, &iter); + WARN_ON_ONCE(status == -EIOCBQUEUED); + + nfs_local_read_done(iocb, status); + nfs_local_pgio_release(iocb); + + revert_creds(save_cred); +} + +static int +nfs_do_local_read(struct nfs_pgio_header *hdr, + struct nfsd_file *localio, + const struct rpc_call_ops *call_ops) +{ + struct nfs_local_kiocb *iocb; + + dprintk("%s: vfs_read count=%u pos=%llu\n", + __func__, hdr->args.count, hdr->args.offset); + + iocb = nfs_local_iocb_alloc(hdr, localio, GFP_KERNEL); + if (iocb == NULL) + return -ENOMEM; + + nfs_local_pgio_init(hdr, call_ops); + hdr->res.eof = false; + + INIT_WORK(&iocb->work, nfs_local_call_read); + queue_work(nfslocaliod_workqueue, &iocb->work); + + return 0; +} + +static void +nfs_copy_boot_verifier(struct nfs_write_verifier *verifier, struct inode *inode) +{ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + u32 *verf = (u32 *)verifier->data; + int seq = 0; + + do { + read_seqbegin_or_lock(&clp->cl_boot_lock, &seq); + verf[0] = (u32)clp->cl_nfssvc_boot.tv_sec; + verf[1] = (u32)clp->cl_nfssvc_boot.tv_nsec; + } while (need_seqretry(&clp->cl_boot_lock, seq)); + done_seqretry(&clp->cl_boot_lock, seq); +} + +static void +nfs_reset_boot_verifier(struct inode *inode) +{ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + + write_seqlock(&clp->cl_boot_lock); + ktime_get_real_ts64(&clp->cl_nfssvc_boot); + write_sequnlock(&clp->cl_boot_lock); +} + +static void +nfs_set_local_verifier(struct inode *inode, + struct nfs_writeverf *verf, + enum nfs3_stable_how how) +{ + nfs_copy_boot_verifier(&verf->verifier, inode); + verf->committed = how; +} + +/* Factored out from fs/nfsd/vfs.h:fh_getattr() */ +static int __vfs_getattr(struct path *p, struct kstat *stat, int version) +{ + u32 request_mask = STATX_BASIC_STATS; + + if (version == 4) + request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); + return vfs_getattr(p, stat, request_mask, AT_STATX_SYNC_AS_STAT); +} + +/* Copied from fs/nfsd/nfsfh.c:nfsd4_change_attribute() */ +static u64 __nfsd4_change_attribute(const struct kstat *stat, + const struct inode *inode) +{ + u64 chattr; + + if (stat->result_mask & STATX_CHANGE_COOKIE) { + chattr = stat->change_cookie; + if (S_ISREG(inode->i_mode) && + !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) { + chattr += (u64)stat->ctime.tv_sec << 30; + chattr += stat->ctime.tv_nsec; + } + } else { + chattr = time_to_chattr(&stat->ctime); + } + return chattr; +} + +static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb) +{ + struct kstat stat; + struct file *filp = iocb->kiocb.ki_filp; + struct nfs_pgio_header *hdr = iocb->hdr; + struct nfs_fattr *fattr = hdr->res.fattr; + int version = NFS_PROTO(hdr->inode)->version; + + if (unlikely(!fattr) || __vfs_getattr(&filp->f_path, &stat, version)) + return; + + fattr->valid = (NFS_ATTR_FATTR_FILEID | + NFS_ATTR_FATTR_CHANGE | + NFS_ATTR_FATTR_SIZE | + NFS_ATTR_FATTR_ATIME | + NFS_ATTR_FATTR_MTIME | + NFS_ATTR_FATTR_CTIME | + NFS_ATTR_FATTR_SPACE_USED); + + fattr->fileid = stat.ino; + fattr->size = stat.size; + fattr->atime = stat.atime; + fattr->mtime = stat.mtime; + fattr->ctime = stat.ctime; + if (version == 4) { + fattr->change_attr = + __nfsd4_change_attribute(&stat, file_inode(filp)); + } else + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + fattr->du.nfs3.used = stat.blocks << 9; +} + +static void +nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) +{ + struct nfs_pgio_header *hdr = iocb->hdr; + struct inode *inode = hdr->inode; + + dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0); + + /* Handle short writes as if they are ENOSPC */ + if (status > 0 && status < hdr->args.count) { + hdr->mds_offset += status; + hdr->args.offset += status; + hdr->args.pgbase += status; + hdr->args.count -= status; + nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset); + status = -ENOSPC; + } + if (status < 0) + nfs_reset_boot_verifier(inode); + else if (nfs_should_remove_suid(inode)) { + /* Deal with the suid/sgid bit corner case */ + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + spin_unlock(&inode->i_lock); + } + nfs_local_pgio_done(hdr, status); +} + +static void nfs_local_call_write(struct work_struct *work) +{ + struct nfs_local_kiocb *iocb = + container_of(work, struct nfs_local_kiocb, work); + struct file *filp = iocb->kiocb.ki_filp; + unsigned long old_flags = current->flags; + const struct cred *save_cred; + struct iov_iter iter; + ssize_t status; + + current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; + save_cred = override_creds(filp->f_cred); + + nfs_local_iter_init(&iter, iocb, WRITE); + + file_start_write(filp); + status = filp->f_op->write_iter(&iocb->kiocb, &iter); + file_end_write(filp); + WARN_ON_ONCE(status == -EIOCBQUEUED); + + nfs_local_write_done(iocb, status); + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); + + revert_creds(save_cred); + current->flags = old_flags; +} + +static int +nfs_do_local_write(struct nfs_pgio_header *hdr, + struct nfsd_file *localio, + const struct rpc_call_ops *call_ops) +{ + struct nfs_local_kiocb *iocb; + + dprintk("%s: vfs_write count=%u pos=%llu %s\n", + __func__, hdr->args.count, hdr->args.offset, + (hdr->args.stable == NFS_UNSTABLE) ? "unstable" : "stable"); + + iocb = nfs_local_iocb_alloc(hdr, localio, GFP_NOIO); + if (iocb == NULL) + return -ENOMEM; + + switch (hdr->args.stable) { + default: + break; + case NFS_DATA_SYNC: + iocb->kiocb.ki_flags |= IOCB_DSYNC; + break; + case NFS_FILE_SYNC: + iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC; + } + nfs_local_pgio_init(hdr, call_ops); + + nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable); + + INIT_WORK(&iocb->work, nfs_local_call_write); + queue_work(nfslocaliod_workqueue, &iocb->work); + + return 0; +} + +int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, + struct nfs_pgio_header *hdr, + const struct rpc_call_ops *call_ops) +{ + int status = 0; + struct file *filp = nfs_to->nfsd_file_file(localio); + + if (!hdr->args.count) + return 0; + /* Don't support filesystems without read_iter/write_iter */ + if (!filp->f_op->read_iter || !filp->f_op->write_iter) { + nfs_local_disable(clp); + status = -EAGAIN; + goto out; + } + + switch (hdr->rw_mode) { + case FMODE_READ: + status = nfs_do_local_read(hdr, localio, call_ops); + break; + case FMODE_WRITE: + status = nfs_do_local_write(hdr, localio, call_ops); + break; + default: + dprintk("%s: invalid mode: %d\n", __func__, + hdr->rw_mode); + status = -EINVAL; + } +out: + if (status != 0) { + nfs_to->nfsd_file_put_local(localio); + hdr->task.tk_status = status; + nfs_local_hdr_release(hdr, call_ops); + } + return status; +} + +static void +nfs_local_init_commit(struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops) +{ + data->task.tk_ops = call_ops; +} + +static int +nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data) +{ + loff_t start = data->args.offset; + loff_t end = LLONG_MAX; + + if (data->args.count > 0) { + end = start + data->args.count - 1; + if (end < start) + end = LLONG_MAX; + } + + dprintk("%s: commit %llu - %llu\n", __func__, start, end); + return vfs_fsync_range(filp, start, end, 0); +} + +static void +nfs_local_commit_done(struct nfs_commit_data *data, int status) +{ + if (status >= 0) { + nfs_set_local_verifier(data->inode, + data->res.verf, + NFS_FILE_SYNC); + data->res.op_status = NFS4_OK; + data->task.tk_status = 0; + } else { + nfs_reset_boot_verifier(data->inode); + data->res.op_status = nfs4_stat_to_errno(status); + data->task.tk_status = status; + } +} + +static void +nfs_local_release_commit_data(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops) +{ + nfs_to->nfsd_file_put_local(localio); + call_ops->rpc_call_done(&data->task, data); + call_ops->rpc_release(data); +} + +static struct nfs_local_fsync_ctx * +nfs_local_fsync_ctx_alloc(struct nfs_commit_data *data, + struct nfsd_file *localio, gfp_t flags) +{ + struct nfs_local_fsync_ctx *ctx = kmalloc(sizeof(*ctx), flags); + + if (ctx != NULL) { + ctx->localio = localio; + ctx->data = data; + INIT_WORK(&ctx->work, nfs_local_fsync_work); + kref_init(&ctx->kref); + ctx->done = NULL; + } + return ctx; +} + +static void +nfs_local_fsync_ctx_kref_free(struct kref *kref) +{ + kfree(container_of(kref, struct nfs_local_fsync_ctx, kref)); +} + +static void +nfs_local_fsync_ctx_put(struct nfs_local_fsync_ctx *ctx) +{ + kref_put(&ctx->kref, nfs_local_fsync_ctx_kref_free); +} + +static void +nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx) +{ + nfs_local_release_commit_data(ctx->localio, ctx->data, + ctx->data->task.tk_ops); + nfs_local_fsync_ctx_put(ctx); +} + +static void +nfs_local_fsync_work(struct work_struct *work) +{ + struct nfs_local_fsync_ctx *ctx; + int status; + + ctx = container_of(work, struct nfs_local_fsync_ctx, work); + + status = nfs_local_run_commit(nfs_to->nfsd_file_file(ctx->localio), + ctx->data); + nfs_local_commit_done(ctx->data, status); + if (ctx->done != NULL) + complete(ctx->done); + nfs_local_fsync_ctx_free(ctx); +} + +int nfs_local_commit(struct nfsd_file *localio, + struct nfs_commit_data *data, + const struct rpc_call_ops *call_ops, int how) +{ + struct nfs_local_fsync_ctx *ctx; + + ctx = nfs_local_fsync_ctx_alloc(data, localio, GFP_KERNEL); + if (!ctx) { + nfs_local_commit_done(data, -ENOMEM); + nfs_local_release_commit_data(localio, data, call_ops); + return -ENOMEM; + } + + nfs_local_init_commit(data, call_ops); + kref_get(&ctx->kref); + if (how & FLUSH_SYNC) { + DECLARE_COMPLETION_ONSTACK(done); + ctx->done = &done; + queue_work(nfsiod_workqueue, &ctx->work); + wait_for_completion(&done); + } else + queue_work(nfsiod_workqueue, &ctx->work); + nfs_local_fsync_ctx_put(ctx); + return 0; +} diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index c19093814296..6e75c6c2d234 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -22,14 +22,12 @@ #include #include #include +#include #include "nfstrace.h" #include "internal.h" #define NFSDBG_FACILITY NFSDBG_XDR -/* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO - /* * Declare the space requirements for NFS arguments and replies as * number of 32bit-words @@ -64,8 +62,6 @@ #define NFS_readdirres_sz (1+NFS_pagepad_sz) #define NFS_statfsres_sz (1+NFS_info_sz) -static int nfs_stat_to_errno(enum nfs_stat); - /* * Encode/decode NFSv2 basic data types * @@ -1054,70 +1050,6 @@ out_default: return nfs_stat_to_errno(status); } - -/* - * We need to translate between nfs status return values and - * the local errno values which may not be the same. - */ -static const struct { - int stat; - int errno; -} nfs_errtbl[] = { - { NFS_OK, 0 }, - { NFSERR_PERM, -EPERM }, - { NFSERR_NOENT, -ENOENT }, - { NFSERR_IO, -errno_NFSERR_IO}, - { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ - { NFSERR_ACCES, -EACCES }, - { NFSERR_EXIST, -EEXIST }, - { NFSERR_XDEV, -EXDEV }, - { NFSERR_NODEV, -ENODEV }, - { NFSERR_NOTDIR, -ENOTDIR }, - { NFSERR_ISDIR, -EISDIR }, - { NFSERR_INVAL, -EINVAL }, - { NFSERR_FBIG, -EFBIG }, - { NFSERR_NOSPC, -ENOSPC }, - { NFSERR_ROFS, -EROFS }, - { NFSERR_MLINK, -EMLINK }, - { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, - { NFSERR_NOTEMPTY, -ENOTEMPTY }, - { NFSERR_DQUOT, -EDQUOT }, - { NFSERR_STALE, -ESTALE }, - { NFSERR_REMOTE, -EREMOTE }, -#ifdef EWFLUSH - { NFSERR_WFLUSH, -EWFLUSH }, -#endif - { NFSERR_BADHANDLE, -EBADHANDLE }, - { NFSERR_NOT_SYNC, -ENOTSYNC }, - { NFSERR_BAD_COOKIE, -EBADCOOKIE }, - { NFSERR_NOTSUPP, -ENOTSUPP }, - { NFSERR_TOOSMALL, -ETOOSMALL }, - { NFSERR_SERVERFAULT, -EREMOTEIO }, - { NFSERR_BADTYPE, -EBADTYPE }, - { NFSERR_JUKEBOX, -EJUKEBOX }, - { -1, -EIO } -}; - -/** - * nfs_stat_to_errno - convert an NFS status code to a local errno - * @status: NFS status code to convert - * - * Returns a local errno value, or -EIO if the NFS status code is - * not recognized. This function is used jointly by NFSv2 and NFSv3. - */ -static int nfs_stat_to_errno(enum nfs_stat status) -{ - int i; - - for (i = 0; nfs_errtbl[i].stat != -1; i++) { - if (nfs_errtbl[i].stat == (int)status) - return nfs_errtbl[i].errno; - } - dprintk("NFS: Unrecognized nfs status value: %u\n", status); - return nfs_errtbl[i].errno; -} - #define PROC(proc, argtype, restype, timer) \ [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 60f032be805a..4ae01c10b7e2 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -21,14 +21,13 @@ #include #include #include +#include + #include "nfstrace.h" #include "internal.h" #define NFSDBG_FACILITY NFSDBG_XDR -/* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO - /* * Declare the space requirements for NFS arguments and replies as * number of 32bit-words @@ -91,8 +90,6 @@ NFS3_pagepad_sz) #define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz) -static int nfs3_stat_to_errno(enum nfs_stat); - /* * Map file type to S_IFMT bits */ @@ -1406,7 +1403,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1445,7 +1442,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1495,7 +1492,7 @@ out_default: error = decode_post_op_attr(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1537,7 +1534,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1578,7 +1575,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1658,7 +1655,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1728,7 +1725,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1795,7 +1792,7 @@ out_default: error = decode_wcc_data(xdr, result->dir_attr, userns); if (unlikely(error)) goto out; - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1835,7 +1832,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1881,7 +1878,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -1926,7 +1923,7 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /** @@ -2101,7 +2098,7 @@ out_default: error = decode_post_op_attr(xdr, result->dir_attr, rpc_rqst_userns(req)); if (unlikely(error)) goto out; - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2167,7 +2164,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2243,7 +2240,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2304,7 +2301,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } /* @@ -2350,7 +2347,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, out: return error; out_status: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } #ifdef CONFIG_NFS_V3_ACL @@ -2416,7 +2413,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, @@ -2435,76 +2432,11 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, out: return error; out_default: - return nfs3_stat_to_errno(status); + return nfs_stat_to_errno(status); } #endif /* CONFIG_NFS_V3_ACL */ - -/* - * We need to translate between nfs status return values and - * the local errno values which may not be the same. - */ -static const struct { - int stat; - int errno; -} nfs_errtbl[] = { - { NFS_OK, 0 }, - { NFSERR_PERM, -EPERM }, - { NFSERR_NOENT, -ENOENT }, - { NFSERR_IO, -errno_NFSERR_IO}, - { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ - { NFSERR_ACCES, -EACCES }, - { NFSERR_EXIST, -EEXIST }, - { NFSERR_XDEV, -EXDEV }, - { NFSERR_NODEV, -ENODEV }, - { NFSERR_NOTDIR, -ENOTDIR }, - { NFSERR_ISDIR, -EISDIR }, - { NFSERR_INVAL, -EINVAL }, - { NFSERR_FBIG, -EFBIG }, - { NFSERR_NOSPC, -ENOSPC }, - { NFSERR_ROFS, -EROFS }, - { NFSERR_MLINK, -EMLINK }, - { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, - { NFSERR_NOTEMPTY, -ENOTEMPTY }, - { NFSERR_DQUOT, -EDQUOT }, - { NFSERR_STALE, -ESTALE }, - { NFSERR_REMOTE, -EREMOTE }, -#ifdef EWFLUSH - { NFSERR_WFLUSH, -EWFLUSH }, -#endif - { NFSERR_BADHANDLE, -EBADHANDLE }, - { NFSERR_NOT_SYNC, -ENOTSYNC }, - { NFSERR_BAD_COOKIE, -EBADCOOKIE }, - { NFSERR_NOTSUPP, -ENOTSUPP }, - { NFSERR_TOOSMALL, -ETOOSMALL }, - { NFSERR_SERVERFAULT, -EREMOTEIO }, - { NFSERR_BADTYPE, -EBADTYPE }, - { NFSERR_JUKEBOX, -EJUKEBOX }, - { -1, -EIO } -}; - -/** - * nfs3_stat_to_errno - convert an NFS status code to a local errno - * @status: NFS status code to convert - * - * Returns a local errno value, or -EIO if the NFS status code is - * not recognized. This function is used jointly by NFSv2 and NFSv3. - */ -static int nfs3_stat_to_errno(enum nfs_stat status) -{ - int i; - - for (i = 0; nfs_errtbl[i].stat != -1; i++) { - if (nfs_errtbl[i].stat == (int)status) - return nfs_errtbl[i].errno; - } - dprintk("NFS: Unrecognized nfs status value: %u\n", status); - return nfs_errtbl[i].errno; -} - - #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index c2045a2a9d0f..7d383d29a995 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -83,7 +83,7 @@ struct nfs4_minor_version_ops { #define NFS_SEQID_CONFIRMED 1 struct nfs_seqid_counter { ktime_t create_time; - int owner_id; + u64 owner_id; int flags; u32 counter; spinlock_t lock; /* Protects the list */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b8ffbe52ba15..cd2fbde2e6d7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3904,6 +3904,18 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL) #define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_OPEN_ARGUMENTS - 1UL) +#define FATTR4_WORD2_NFS42_TIME_DELEG_MASK \ + (FATTR4_WORD2_TIME_DELEG_MODIFY|FATTR4_WORD2_TIME_DELEG_ACCESS) +static bool nfs4_server_delegtime_capable(struct nfs4_server_caps_res *res) +{ + u32 share_access_want = res->open_caps.oa_share_access_want[0]; + u32 attr_bitmask = res->attr_bitmask[2]; + + return (share_access_want & NFS4_SHARE_WANT_DELEG_TIMESTAMPS) && + ((attr_bitmask & FATTR4_WORD2_NFS42_TIME_DELEG_MASK) == + FATTR4_WORD2_NFS42_TIME_DELEG_MASK); +} + static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { u32 minorversion = server->nfs_client->cl_minorversion; @@ -3982,8 +3994,6 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f #endif if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS) server->caps |= NFS_CAP_FS_LOCATIONS; - if (res.attr_bitmask[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) - server->caps |= NFS_CAP_DELEGTIME; if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID)) server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID; if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE)) @@ -4011,6 +4021,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f if (res.open_caps.oa_share_access_want[0] & NFS4_SHARE_WANT_OPEN_XOR_DELEGATION) server->caps |= NFS_CAP_OPEN_XOR; + if (nfs4_server_delegtime_capable(&res)) + server->caps |= NFS_CAP_DELEGTIME; memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask)); server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 877f682b45f2..581864a15888 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -501,11 +501,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, sp = kzalloc(sizeof(*sp), gfp_flags); if (!sp) return NULL; - sp->so_seqid.owner_id = ida_alloc(&server->openowner_id, gfp_flags); - if (sp->so_seqid.owner_id < 0) { - kfree(sp); - return NULL; - } + sp->so_seqid.owner_id = atomic64_inc_return(&server->owner_ctr); sp->so_server = server; sp->so_cred = get_cred(cred); spin_lock_init(&sp->so_lock); @@ -536,7 +532,6 @@ static void nfs4_free_state_owner(struct nfs4_state_owner *sp) { nfs4_destroy_seqid_counter(&sp->so_seqid); put_cred(sp->so_cred); - ida_free(&sp->so_server->openowner_id, sp->so_seqid.owner_id); kfree(sp); } @@ -879,19 +874,13 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f refcount_set(&lsp->ls_count, 1); lsp->ls_state = state; lsp->ls_owner = owner; - lsp->ls_seqid.owner_id = ida_alloc(&server->lockowner_id, GFP_KERNEL_ACCOUNT); - if (lsp->ls_seqid.owner_id < 0) - goto out_free; + lsp->ls_seqid.owner_id = atomic64_inc_return(&server->owner_ctr); INIT_LIST_HEAD(&lsp->ls_locks); return lsp; -out_free: - kfree(lsp); - return NULL; } void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp) { - ida_free(&server->lockowner_id, lsp->ls_seqid.owner_id); nfs4_destroy_seqid_counter(&lsp->ls_seqid); kfree(lsp); } @@ -1957,6 +1946,7 @@ restart: set_bit(ops->owner_flag_bit, &sp->so_flags); nfs4_put_state_owner(sp); status = nfs4_recovery_handle_error(clp, status); + nfs4_free_state_owners(&freeme); return (status != 0) ? status : -EAGAIN; } @@ -2023,6 +2013,12 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) nfs_mark_client_ready(clp, -EPERM); clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); return -EPERM; + case -ETIMEDOUT: + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) { + nfs_mark_client_ready(clp, -EIO); + return -EIO; + } + fallthrough; case -EACCES: case -NFS4ERR_DELAY: case -EAGAIN: diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 61190d6a5a77..e8ac3f615f93 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -52,6 +52,7 @@ #include #include #include +#include #include "nfs4_fs.h" #include "nfs4trace.h" @@ -63,11 +64,7 @@ #define NFSDBG_FACILITY NFSDBG_XDR -/* Mapping from NFS error code to "errno" error code. */ -#define errno_NFSERR_IO EIO - struct compound_hdr; -static int nfs4_stat_to_errno(int); static void encode_layoutget(struct xdr_stream *xdr, const struct nfs4_layoutget_args *args, struct compound_hdr *hdr); @@ -975,11 +972,6 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes) return p; } -static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len) -{ - WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); -} - static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) { WARN_ON_ONCE(xdr_stream_encode_opaque(xdr, str, len) < 0); @@ -1424,12 +1416,12 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena */ encode_nfs4_seqid(xdr, arg->seqid); encode_share_access(xdr, arg->share_access); - p = reserve_space(xdr, 36); + p = reserve_space(xdr, 40); p = xdr_encode_hyper(p, arg->clientid); - *p++ = cpu_to_be32(24); + *p++ = cpu_to_be32(28); p = xdr_encode_opaque_fixed(p, "open id:", 8); *p++ = cpu_to_be32(arg->server->s_dev); - *p++ = cpu_to_be32(arg->id.uniquifier); + p = xdr_encode_hyper(p, arg->id.uniquifier); xdr_encode_hyper(p, arg->id.create_time); } @@ -4408,14 +4400,6 @@ static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access) return 0; } -static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len) -{ - ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len); - if (unlikely(ret < 0)) - return -EIO; - return 0; -} - static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) { return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE); @@ -7620,72 +7604,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, return 0; } -/* - * We need to translate between nfs status return values and - * the local errno values which may not be the same. - */ -static struct { - int stat; - int errno; -} nfs_errtbl[] = { - { NFS4_OK, 0 }, - { NFS4ERR_PERM, -EPERM }, - { NFS4ERR_NOENT, -ENOENT }, - { NFS4ERR_IO, -errno_NFSERR_IO}, - { NFS4ERR_NXIO, -ENXIO }, - { NFS4ERR_ACCESS, -EACCES }, - { NFS4ERR_EXIST, -EEXIST }, - { NFS4ERR_XDEV, -EXDEV }, - { NFS4ERR_NOTDIR, -ENOTDIR }, - { NFS4ERR_ISDIR, -EISDIR }, - { NFS4ERR_INVAL, -EINVAL }, - { NFS4ERR_FBIG, -EFBIG }, - { NFS4ERR_NOSPC, -ENOSPC }, - { NFS4ERR_ROFS, -EROFS }, - { NFS4ERR_MLINK, -EMLINK }, - { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG }, - { NFS4ERR_NOTEMPTY, -ENOTEMPTY }, - { NFS4ERR_DQUOT, -EDQUOT }, - { NFS4ERR_STALE, -ESTALE }, - { NFS4ERR_BADHANDLE, -EBADHANDLE }, - { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, - { NFS4ERR_NOTSUPP, -ENOTSUPP }, - { NFS4ERR_TOOSMALL, -ETOOSMALL }, - { NFS4ERR_SERVERFAULT, -EREMOTEIO }, - { NFS4ERR_BADTYPE, -EBADTYPE }, - { NFS4ERR_LOCKED, -EAGAIN }, - { NFS4ERR_SYMLINK, -ELOOP }, - { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, - { NFS4ERR_DEADLOCK, -EDEADLK }, - { NFS4ERR_NOXATTR, -ENODATA }, - { NFS4ERR_XATTR2BIG, -E2BIG }, - { -1, -EIO } -}; - -/* - * Convert an NFS error code to a local one. - * This one is used jointly by NFSv2 and NFSv3. - */ -static int -nfs4_stat_to_errno(int stat) -{ - int i; - for (i = 0; nfs_errtbl[i].stat != -1; i++) { - if (nfs_errtbl[i].stat == stat) - return nfs_errtbl[i].errno; - } - if (stat <= 10000 || stat > 10100) { - /* The server is looney tunes. */ - return -EREMOTEIO; - } - /* If we cannot translate the error, the recovery routines should - * handle it. - * Note: remaining NFSv4 error codes have values > 10000, so should - * not conflict with native Linux error codes. - */ - return -stat; -} - #ifdef CONFIG_NFS_V4_2 #include "nfs42xdr.c" #endif /* CONFIG_NFS_V4_2 */ diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 352fdaed4075..1eab98c277fa 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1685,6 +1685,67 @@ TRACE_EVENT(nfs_mount_path, TP_printk("path='%s'", __get_str(path)) ); +TRACE_EVENT(nfs_local_open_fh, + TP_PROTO( + const struct nfs_fh *fh, + fmode_t fmode, + int error + ), + + TP_ARGS(fh, fmode, error), + + TP_STRUCT__entry( + __field(int, error) + __field(u32, fhandle) + __field(unsigned int, fmode) + ), + + TP_fast_assign( + __entry->error = error; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->fmode = (__force unsigned int)fmode; + ), + + TP_printk( + "error=%d fhandle=0x%08x mode=%s", + __entry->error, + __entry->fhandle, + show_fs_fmode_flags(__entry->fmode) + ) +); + +DECLARE_EVENT_CLASS(nfs_local_client_event, + TP_PROTO( + const struct nfs_client *clp + ), + + TP_ARGS(clp), + + TP_STRUCT__entry( + __field(unsigned int, protocol) + __string(server, clp->cl_hostname) + ), + + TP_fast_assign( + __entry->protocol = clp->rpc_ops->version; + __assign_str(server); + ), + + TP_printk( + "server=%s NFSv%u", __get_str(server), __entry->protocol + ) +); + +#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \ + DEFINE_EVENT(nfs_local_client_event, name, \ + TP_PROTO( \ + const struct nfs_client *clp \ + ), \ + TP_ARGS(clp)) + +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable); +DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable); + DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 04124f226665..e27c07bd8929 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -731,7 +731,8 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, - const struct rpc_call_ops *call_ops, int how, int flags) + const struct rpc_call_ops *call_ops, int how, int flags, + struct nfsd_file *localio) { struct rpc_task *task; struct rpc_message msg = { @@ -761,6 +762,10 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, hdr->args.count, (unsigned long long)hdr->args.offset); + if (localio) + return nfs_local_doio(NFS_SERVER(hdr->inode)->nfs_client, + localio, hdr, call_ops); + task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -953,6 +958,12 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) nfs_pgheader_init(desc, hdr, nfs_pgio_header_free); ret = nfs_generic_pgio(desc, hdr); if (ret == 0) { + struct nfs_client *clp = NFS_SERVER(hdr->inode)->nfs_client; + + struct nfsd_file *localio = + nfs_local_open_fh(clp, hdr->cred, + hdr->args.fh, hdr->args.context->mode); + if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion) task_flags = RPC_TASK_MOVEABLE; ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode), @@ -961,7 +972,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) NFS_PROTO(hdr->inode), desc->pg_rpc_callops, desc->pg_ioflags, - RPC_TASK_CRED_NOREF | task_flags); + RPC_TASK_CRED_NOREF | task_flags, + localio); } return ret; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index a74ee69a2fa6..dbef837e871a 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -490,7 +490,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(data->inode), data->mds_ops, how, - RPC_TASK_CRED_NOREF); + RPC_TASK_CRED_NOREF, NULL); } else { nfs_init_commit(data, NULL, data->lseg, cinfo); initiate_commit(data, how); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index a6103333b666..81bd1b9aba17 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -48,8 +48,7 @@ static struct nfs_pgio_header *nfs_readhdr_alloc(void) static void nfs_readhdr_free(struct nfs_pgio_header *rhdr) { - if (rhdr->res.scratch != NULL) - kfree(rhdr->res.scratch); + kfree(rhdr->res.scratch); kmem_cache_free(nfs_rdata_cachep, rhdr); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 97b386032b71..9723b6c53397 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -551,6 +551,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, else seq_puts(m, ",local_lock=posix"); + if (nfss->flags & NFS_MOUNT_NO_ALIGNWRITE) + seq_puts(m, ",noalignwrite"); + if (nfss->flags & NFS_MOUNT_WRITE_EAGER) { if (nfss->flags & NFS_MOUNT_WRITE_WAIT) seq_puts(m, ",write=wait"); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d074d0ceb4f0..ead2dc55952d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -772,8 +772,7 @@ static void nfs_inode_add_request(struct nfs_page *req) nfs_lock_request(req); spin_lock(&mapping->i_private_lock); set_bit(PG_MAPPED, &req->wb_flags); - folio_set_private(folio); - folio->private = req; + folio_attach_private(folio, req); spin_unlock(&mapping->i_private_lock); atomic_long_inc(&nfsi->nrequests); /* this a head request for a page group - mark it as having an @@ -797,8 +796,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) spin_lock(&mapping->i_private_lock); if (likely(folio)) { - folio->private = NULL; - folio_clear_private(folio); + folio_detach_private(folio); clear_bit(PG_MAPPED, &req->wb_head->wb_flags); } spin_unlock(&mapping->i_private_lock); @@ -1297,7 +1295,10 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio, struct file_lock_context *flctx = locks_inode_context(inode); struct file_lock *fl; int ret; + unsigned int mntflags = NFS_SERVER(inode)->flags; + if (mntflags & NFS_MOUNT_NO_ALIGNWRITE) + return 0; if (file->f_flags & O_DSYNC) return 0; if (!nfs_folio_write_uptodate(folio, pagelen)) @@ -1663,7 +1664,8 @@ EXPORT_SYMBOL_GPL(nfs_commitdata_release); int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, - int how, int flags) + int how, int flags, + struct nfsd_file *localio) { struct rpc_task *task; int priority = flush_task_priority(how); @@ -1692,6 +1694,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, dprintk("NFS: initiated commit call\n"); + if (localio) + return nfs_local_commit(localio, data, call_ops, how); + task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -1791,6 +1796,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo) { struct nfs_commit_data *data; + struct nfsd_file *localio; unsigned short task_flags = 0; /* another commit raced with us */ @@ -1807,9 +1813,12 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, nfs_init_commit(data, head, NULL, cinfo); if (NFS_SERVER(inode)->nfs_client->cl_minorversion) task_flags = RPC_TASK_MOVEABLE; + + localio = nfs_local_open_fh(NFS_SERVER(inode)->nfs_client, data->cred, + data->args.fh, data->context->mode); return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), data->mds_ops, how, - RPC_TASK_CRED_NOREF | task_flags); + RPC_TASK_CRED_NOREF | task_flags, localio); } /* diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index 119c75ab9fd0..a5e54809701e 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -6,5 +6,10 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o nfs_acl-objs := nfsacl.o +obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o +nfs_localio-objs := nfslocalio.o + obj-$(CONFIG_GRACE_PERIOD) += grace.o obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o + +obj-$(CONFIG_NFS_COMMON) += common.o diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c new file mode 100644 index 000000000000..34a115176f97 --- /dev/null +++ b/fs/nfs_common/common.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +/* + * We need to translate between nfs status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs_errtbl[] = { + { NFS_OK, 0 }, + { NFSERR_PERM, -EPERM }, + { NFSERR_NOENT, -ENOENT }, + { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_NXIO, -ENXIO }, +/* { NFSERR_EAGAIN, -EAGAIN }, */ + { NFSERR_ACCES, -EACCES }, + { NFSERR_EXIST, -EEXIST }, + { NFSERR_XDEV, -EXDEV }, + { NFSERR_NODEV, -ENODEV }, + { NFSERR_NOTDIR, -ENOTDIR }, + { NFSERR_ISDIR, -EISDIR }, + { NFSERR_INVAL, -EINVAL }, + { NFSERR_FBIG, -EFBIG }, + { NFSERR_NOSPC, -ENOSPC }, + { NFSERR_ROFS, -EROFS }, + { NFSERR_MLINK, -EMLINK }, + { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFSERR_NOTEMPTY, -ENOTEMPTY }, + { NFSERR_DQUOT, -EDQUOT }, + { NFSERR_STALE, -ESTALE }, + { NFSERR_REMOTE, -EREMOTE }, +#ifdef EWFLUSH + { NFSERR_WFLUSH, -EWFLUSH }, +#endif + { NFSERR_BADHANDLE, -EBADHANDLE }, + { NFSERR_NOT_SYNC, -ENOTSYNC }, + { NFSERR_BAD_COOKIE, -EBADCOOKIE }, + { NFSERR_NOTSUPP, -ENOTSUPP }, + { NFSERR_TOOSMALL, -ETOOSMALL }, + { NFSERR_SERVERFAULT, -EREMOTEIO }, + { NFSERR_BADTYPE, -EBADTYPE }, + { NFSERR_JUKEBOX, -EJUKEBOX }, + { -1, -EIO } +}; + +/** + * nfs_stat_to_errno - convert an NFS status code to a local errno + * @status: NFS status code to convert + * + * Returns a local errno value, or -EIO if the NFS status code is + * not recognized. This function is used jointly by NFSv2 and NFSv3. + */ +int nfs_stat_to_errno(enum nfs_stat status) +{ + int i; + + for (i = 0; nfs_errtbl[i].stat != -1; i++) { + if (nfs_errtbl[i].stat == (int)status) + return nfs_errtbl[i].errno; + } + return nfs_errtbl[i].errno; +} +EXPORT_SYMBOL_GPL(nfs_stat_to_errno); + +/* + * We need to translate between nfs v4 status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs4_errtbl[] = { + { NFS4_OK, 0 }, + { NFS4ERR_PERM, -EPERM }, + { NFS4ERR_NOENT, -ENOENT }, + { NFS4ERR_IO, -errno_NFSERR_IO}, + { NFS4ERR_NXIO, -ENXIO }, + { NFS4ERR_ACCESS, -EACCES }, + { NFS4ERR_EXIST, -EEXIST }, + { NFS4ERR_XDEV, -EXDEV }, + { NFS4ERR_NOTDIR, -ENOTDIR }, + { NFS4ERR_ISDIR, -EISDIR }, + { NFS4ERR_INVAL, -EINVAL }, + { NFS4ERR_FBIG, -EFBIG }, + { NFS4ERR_NOSPC, -ENOSPC }, + { NFS4ERR_ROFS, -EROFS }, + { NFS4ERR_MLINK, -EMLINK }, + { NFS4ERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFS4ERR_NOTEMPTY, -ENOTEMPTY }, + { NFS4ERR_DQUOT, -EDQUOT }, + { NFS4ERR_STALE, -ESTALE }, + { NFS4ERR_BADHANDLE, -EBADHANDLE }, + { NFS4ERR_BAD_COOKIE, -EBADCOOKIE }, + { NFS4ERR_NOTSUPP, -ENOTSUPP }, + { NFS4ERR_TOOSMALL, -ETOOSMALL }, + { NFS4ERR_SERVERFAULT, -EREMOTEIO }, + { NFS4ERR_BADTYPE, -EBADTYPE }, + { NFS4ERR_LOCKED, -EAGAIN }, + { NFS4ERR_SYMLINK, -ELOOP }, + { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, + { NFS4ERR_DEADLOCK, -EDEADLK }, + { NFS4ERR_NOXATTR, -ENODATA }, + { NFS4ERR_XATTR2BIG, -E2BIG }, + { -1, -EIO } +}; + +/* + * Convert an NFS error code to a local one. + * This one is used by NFSv4. + */ +int nfs4_stat_to_errno(int stat) +{ + int i; + for (i = 0; nfs4_errtbl[i].stat != -1; i++) { + if (nfs4_errtbl[i].stat == stat) + return nfs4_errtbl[i].errno; + } + if (stat <= 10000 || stat > 10100) { + /* The server is looney tunes. */ + return -EREMOTEIO; + } + /* If we cannot translate the error, the recovery routines should + * handle it. + * Note: remaining NFSv4 error codes have values > 10000, so should + * not conflict with native Linux error codes. + */ + return -stat; +} +EXPORT_SYMBOL_GPL(nfs4_stat_to_errno); diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c new file mode 100644 index 000000000000..42b479b9191f --- /dev/null +++ b/fs/nfs_common/nfslocalio.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ + +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("NFS localio protocol bypass support"); + +static DEFINE_SPINLOCK(nfs_uuid_lock); + +/* + * Global list of nfs_uuid_t instances + * that is protected by nfs_uuid_lock. + */ +static LIST_HEAD(nfs_uuids); + +void nfs_uuid_begin(nfs_uuid_t *nfs_uuid) +{ + nfs_uuid->net = NULL; + nfs_uuid->dom = NULL; + uuid_gen(&nfs_uuid->uuid); + + spin_lock(&nfs_uuid_lock); + list_add_tail_rcu(&nfs_uuid->list, &nfs_uuids); + spin_unlock(&nfs_uuid_lock); +} +EXPORT_SYMBOL_GPL(nfs_uuid_begin); + +void nfs_uuid_end(nfs_uuid_t *nfs_uuid) +{ + if (nfs_uuid->net == NULL) { + spin_lock(&nfs_uuid_lock); + list_del_init(&nfs_uuid->list); + spin_unlock(&nfs_uuid_lock); + } +} +EXPORT_SYMBOL_GPL(nfs_uuid_end); + +static nfs_uuid_t * nfs_uuid_lookup_locked(const uuid_t *uuid) +{ + nfs_uuid_t *nfs_uuid; + + list_for_each_entry(nfs_uuid, &nfs_uuids, list) + if (uuid_equal(&nfs_uuid->uuid, uuid)) + return nfs_uuid; + + return NULL; +} + +static struct module *nfsd_mod; + +void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list, + struct net *net, struct auth_domain *dom, + struct module *mod) +{ + nfs_uuid_t *nfs_uuid; + + spin_lock(&nfs_uuid_lock); + nfs_uuid = nfs_uuid_lookup_locked(uuid); + if (nfs_uuid) { + kref_get(&dom->ref); + nfs_uuid->dom = dom; + /* + * We don't hold a ref on the net, but instead put + * ourselves on a list so the net pointer can be + * invalidated. + */ + list_move(&nfs_uuid->list, list); + rcu_assign_pointer(nfs_uuid->net, net); + + __module_get(mod); + nfsd_mod = mod; + } + spin_unlock(&nfs_uuid_lock); +} +EXPORT_SYMBOL_GPL(nfs_uuid_is_local); + +static void nfs_uuid_put_locked(nfs_uuid_t *nfs_uuid) +{ + if (nfs_uuid->net) { + module_put(nfsd_mod); + nfs_uuid->net = NULL; + } + if (nfs_uuid->dom) { + auth_domain_put(nfs_uuid->dom); + nfs_uuid->dom = NULL; + } + list_del_init(&nfs_uuid->list); +} + +void nfs_uuid_invalidate_clients(struct list_head *list) +{ + nfs_uuid_t *nfs_uuid, *tmp; + + spin_lock(&nfs_uuid_lock); + list_for_each_entry_safe(nfs_uuid, tmp, list, list) + nfs_uuid_put_locked(nfs_uuid); + spin_unlock(&nfs_uuid_lock); +} +EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_clients); + +void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid) +{ + if (nfs_uuid->net) { + spin_lock(&nfs_uuid_lock); + nfs_uuid_put_locked(nfs_uuid); + spin_unlock(&nfs_uuid_lock); + } +} +EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client); + +struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, + struct rpc_clnt *rpc_clnt, const struct cred *cred, + const struct nfs_fh *nfs_fh, const fmode_t fmode) +{ + struct net *net; + struct nfsd_file *localio; + + /* + * Not running in nfsd context, so must safely get reference on nfsd_serv. + * But the server may already be shutting down, if so disallow new localio. + * uuid->net is NOT a counted reference, but rcu_read_lock() ensures that + * if uuid->net is not NULL, then calling nfsd_serv_try_get() is safe + * and if it succeeds we will have an implied reference to the net. + * + * Otherwise NFS may not have ref on NFSD and therefore cannot safely + * make 'nfs_to' calls. + */ + rcu_read_lock(); + net = rcu_dereference(uuid->net); + if (!net || !nfs_to->nfsd_serv_try_get(net)) { + rcu_read_unlock(); + return ERR_PTR(-ENXIO); + } + rcu_read_unlock(); + /* We have an implied reference to net thanks to nfsd_serv_try_get */ + localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, + cred, nfs_fh, fmode); + if (IS_ERR(localio)) + nfs_to->nfsd_serv_put(net); + return localio; +} +EXPORT_SYMBOL_GPL(nfs_open_local_fh); + +/* + * The NFS LOCALIO code needs to call into NFSD using various symbols, + * but cannot be statically linked, because that will make the NFS + * module always depend on the NFSD module. + * + * 'nfs_to' provides NFS access to NFSD functions needed for LOCALIO, + * its lifetime is tightly coupled to the NFSD module and will always + * be available to NFS LOCALIO because any successful client<->server + * LOCALIO handshake results in a reference on the NFSD module (above), + * so NFS implicitly holds a reference to the NFSD module and its + * functions in the 'nfs_to' nfsd_localio_operations cannot disappear. + * + * If the last NFS client using LOCALIO disconnects (and its reference + * on NFSD dropped) then NFSD could be unloaded, resulting in 'nfs_to' + * functions being invalid pointers. But if NFSD isn't loaded then NFS + * will not be able to handshake with NFSD and will have no cause to + * try to call 'nfs_to' function pointers. If/when NFSD is reloaded it + * will reinitialize the 'nfs_to' function pointers and make LOCALIO + * possible. + */ +const struct nfsd_localio_operations *nfs_to; +EXPORT_SYMBOL_GPL(nfs_to); diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index ec2ab6429e00..c0bd1509ccd4 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -7,6 +7,7 @@ config NFSD select LOCKD select SUNRPC select EXPORTFS + select NFS_COMMON select NFS_ACL_SUPPORT if NFSD_V2_ACL select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index b8736a82e57c..18cbd3fa7691 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -23,3 +23,4 @@ nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o +nfsd-$(CONFIG_NFS_LOCALIO) += localio.o diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 7bb4f2075ac5..c82d8e3e0d4f 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1074,10 +1074,30 @@ static struct svc_export *exp_find(struct cache_detail *cd, return exp; } +/** + * check_nfsd_access - check if access to export is allowed. + * @exp: svc_export that is being accessed. + * @rqstp: svc_rqst attempting to access @exp (will be NULL for LOCALIO). + * + * Return values: + * %nfs_ok if access is granted, or + * %nfserr_wrongsec if access is denied + */ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) { struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors; - struct svc_xprt *xprt = rqstp->rq_xprt; + struct svc_xprt *xprt; + + /* + * If rqstp is NULL, this is a LOCALIO request which will only + * ever use a filehandle/credential pair for which access has + * been affirmed (by ACCESS or OPEN NFS requests) over the + * wire. So there is no need for further checks here. + */ + if (!rqstp) + return nfs_ok; + + xprt = rqstp->rq_xprt; if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) { if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) @@ -1098,17 +1118,17 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) ok: /* legacy gss-only clients are always OK: */ if (exp->ex_client == rqstp->rq_gssclient) - return 0; + return nfs_ok; /* ip-address based client; check sec= export option: */ for (f = exp->ex_flavors; f < end; f++) { if (f->pseudoflavor == rqstp->rq_cred.cr_flavor) - return 0; + return nfs_ok; } /* defaults in absence of sec= options: */ if (exp->ex_nflavors == 0) { if (rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL || rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX) - return 0; + return nfs_ok; } /* If the compound op contains a spo_must_allowed op, @@ -1118,7 +1138,7 @@ ok: */ if (nfsd4_spo_must_allow(rqstp)) - return 0; + return nfs_ok; denied: return nfserr_wrongsec; diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 24e8f1fbcebb..19bb88c7eebd 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -52,7 +52,7 @@ #define NFSD_FILE_CACHE_UP (0) /* We only care about NFSD_MAY_READ/WRITE for this cache */ -#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE) +#define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO) static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions); @@ -390,6 +390,34 @@ nfsd_file_put(struct nfsd_file *nf) nfsd_file_free(nf); } +/** + * nfsd_file_put_local - put the reference to nfsd_file and local nfsd_serv + * @nf: nfsd_file of which to put the references + * + * First put the reference of the nfsd_file and then put the + * reference to the associated nn->nfsd_serv. + */ +void +nfsd_file_put_local(struct nfsd_file *nf) +{ + struct net *net = nf->nf_net; + + nfsd_file_put(nf); + nfsd_serv_put(net); +} + +/** + * nfsd_file_file - get the backing file of an nfsd_file + * @nf: nfsd_file of which to access the backing file. + * + * Return backing file for @nf. + */ +struct file * +nfsd_file_file(struct nfsd_file *nf) +{ + return nf->nf_file; +} + static void nfsd_file_dispose_list(struct list_head *dispose) { @@ -982,12 +1010,14 @@ nfsd_file_is_cached(struct inode *inode) } static __be32 -nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, +nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, + struct svc_cred *cred, + struct auth_domain *client, + struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf, bool want_gc) { unsigned char need = may_flags & NFSD_FILE_MAY_MASK; - struct net *net = SVC_NET(rqstp); struct nfsd_file *new, *nf; bool stale_retry = true; bool open_retry = true; @@ -996,8 +1026,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, int ret; retry: - status = fh_verify(rqstp, fhp, S_IFREG, - may_flags|NFSD_MAY_OWNER_OVERRIDE); + if (rqstp) { + status = fh_verify(rqstp, fhp, S_IFREG, + may_flags|NFSD_MAY_OWNER_OVERRIDE); + } else { + status = fh_verify_local(net, cred, client, fhp, S_IFREG, + may_flags|NFSD_MAY_OWNER_OVERRIDE); + } if (status != nfs_ok) return status; inode = d_inode(fhp->fh_dentry); @@ -1143,7 +1178,8 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true); + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, + fhp, may_flags, NULL, pnf, true); } /** @@ -1167,7 +1203,55 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false); + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, + fhp, may_flags, NULL, pnf, false); +} + +/** + * nfsd_file_acquire_local - Get a struct nfsd_file with an open file for localio + * @net: The network namespace in which to perform a lookup + * @cred: the user credential with which to validate access + * @client: the auth_domain for LOCALIO lookup + * @fhp: the NFS filehandle of the file to be opened + * @may_flags: NFSD_MAY_ settings for the file + * @pnf: OUT: new or found "struct nfsd_file" object + * + * This file lookup interface provide access to a file given the + * filehandle and credential. No connection-based authorisation + * is performed and in that way it is quite different to other + * file access mediated by nfsd. It allows a kernel module such as the NFS + * client to reach across network and filesystem namespaces to access + * a file. The security implications of this should be carefully + * considered before use. + * + * The nfsd_file object returned by this API is reference-counted + * and garbage-collected. The object is retained for a few + * seconds after the final nfsd_file_put() in case the caller + * wants to re-use it. + * + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. + */ +__be32 +nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, + struct auth_domain *client, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf) +{ + /* + * Save creds before calling nfsd_file_do_acquire() (which calls + * nfsd_setuser). Important because caller (LOCALIO) is from + * client context. + */ + const struct cred *save_cred = get_current_cred(); + __be32 beres; + + beres = nfsd_file_do_acquire(NULL, net, cred, client, + fhp, may_flags, NULL, pnf, true); + revert_creds(save_cred); + return beres; } /** @@ -1193,7 +1277,8 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false); + return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, + fhp, may_flags, file, pnf, false); } /* diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 3fbec24eea6c..cadf3c2689c4 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -55,7 +55,9 @@ void nfsd_file_cache_shutdown(void); int nfsd_file_cache_start_net(struct net *net); void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); +void nfsd_file_put_local(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); +struct file *nfsd_file_file(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); void nfsd_file_net_dispose(struct nfsd_net *nn); bool nfsd_file_is_cached(struct inode *inode); @@ -66,5 +68,8 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **nfp); +__be32 nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, + struct auth_domain *client, struct svc_fh *fhp, + unsigned int may_flags, struct nfsd_file **pnf); int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c new file mode 100644 index 000000000000..291e9c69cae4 --- /dev/null +++ b/fs/nfsd/localio.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * NFS server support for local clients to bypass network stack + * + * Copyright (C) 2014 Weston Andros Adamson + * Copyright (C) 2019 Trond Myklebust + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "nfsd.h" +#include "vfs.h" +#include "netns.h" +#include "filecache.h" +#include "cache.h" + +static const struct nfsd_localio_operations nfsd_localio_ops = { + .nfsd_serv_try_get = nfsd_serv_try_get, + .nfsd_serv_put = nfsd_serv_put, + .nfsd_open_local_fh = nfsd_open_local_fh, + .nfsd_file_put_local = nfsd_file_put_local, + .nfsd_file_file = nfsd_file_file, +}; + +void nfsd_localio_ops_init(void) +{ + nfs_to = &nfsd_localio_ops; +} + +/** + * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file + * + * @net: 'struct net' to get the proper nfsd_net required for LOCALIO access + * @dom: 'struct auth_domain' required for LOCALIO access + * @rpc_clnt: rpc_clnt that the client established + * @cred: cred that the client established + * @nfs_fh: filehandle to lookup + * @fmode: fmode_t to use for open + * + * This function maps a local fh to a path on a local filesystem. + * This is useful when the nfs client has the local server mounted - it can + * avoid all the NFS overhead with reads, writes and commits. + * + * On successful return, returned nfsd_file will have its nf_net member + * set. Caller (NFS client) is responsible for calling nfsd_serv_put and + * nfsd_file_put (via nfs_to->nfsd_file_put_local). + */ +struct nfsd_file * +nfsd_open_local_fh(struct net *net, struct auth_domain *dom, + struct rpc_clnt *rpc_clnt, const struct cred *cred, + const struct nfs_fh *nfs_fh, const fmode_t fmode) +{ + int mayflags = NFSD_MAY_LOCALIO; + struct svc_cred rq_cred; + struct svc_fh fh; + struct nfsd_file *localio; + __be32 beres; + + if (nfs_fh->size > NFS4_FHSIZE) + return ERR_PTR(-EINVAL); + + /* nfs_fh -> svc_fh */ + fh_init(&fh, NFS4_FHSIZE); + fh.fh_handle.fh_size = nfs_fh->size; + memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size); + + if (fmode & FMODE_READ) + mayflags |= NFSD_MAY_READ; + if (fmode & FMODE_WRITE) + mayflags |= NFSD_MAY_WRITE; + + svcauth_map_clnt_to_svc_cred_local(rpc_clnt, cred, &rq_cred); + + beres = nfsd_file_acquire_local(net, &rq_cred, dom, + &fh, mayflags, &localio); + if (beres) + localio = ERR_PTR(nfs_stat_to_errno(be32_to_cpu(beres))); + + fh_put(&fh); + if (rq_cred.cr_group_info) + put_group_info(rq_cred.cr_group_info); + + return localio; +} +EXPORT_SYMBOL_GPL(nfsd_open_local_fh); + +/* + * UUID_IS_LOCAL XDR functions + */ + +static __be32 localio_proc_null(struct svc_rqst *rqstp) +{ + return rpc_success; +} + +struct localio_uuidarg { + uuid_t uuid; +}; + +static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp) +{ + struct localio_uuidarg *argp = rqstp->rq_argp; + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs_uuid_is_local(&argp->uuid, &nn->local_clients, + net, rqstp->rq_client, THIS_MODULE); + + return rpc_success; +} + +static bool localio_decode_uuidarg(struct svc_rqst *rqstp, + struct xdr_stream *xdr) +{ + struct localio_uuidarg *argp = rqstp->rq_argp; + u8 uuid[UUID_SIZE]; + + if (decode_opaque_fixed(xdr, uuid, UUID_SIZE)) + return false; + import_uuid(&argp->uuid, uuid); + + return true; +} + +static const struct svc_procedure localio_procedures1[] = { + [LOCALIOPROC_NULL] = { + .pc_func = localio_proc_null, + .pc_decode = nfssvc_decode_voidarg, + .pc_encode = nfssvc_encode_voidres, + .pc_argsize = sizeof(struct nfsd_voidargs), + .pc_ressize = sizeof(struct nfsd_voidres), + .pc_cachetype = RC_NOCACHE, + .pc_xdrressize = 0, + .pc_name = "NULL", + }, + [LOCALIOPROC_UUID_IS_LOCAL] = { + .pc_func = localio_proc_uuid_is_local, + .pc_decode = localio_decode_uuidarg, + .pc_encode = nfssvc_encode_voidres, + .pc_argsize = sizeof(struct localio_uuidarg), + .pc_argzero = sizeof(struct localio_uuidarg), + .pc_ressize = sizeof(struct nfsd_voidres), + .pc_cachetype = RC_NOCACHE, + .pc_name = "UUID_IS_LOCAL", + }, +}; + +#define LOCALIO_NR_PROCEDURES ARRAY_SIZE(localio_procedures1) +static DEFINE_PER_CPU_ALIGNED(unsigned long, + localio_count[LOCALIO_NR_PROCEDURES]); +const struct svc_version localio_version1 = { + .vs_vers = 1, + .vs_nproc = LOCALIO_NR_PROCEDURES, + .vs_proc = localio_procedures1, + .vs_dispatch = nfsd_dispatch, + .vs_count = localio_count, + .vs_xdrsize = XDR_QUADLEN(UUID_SIZE), + .vs_hidden = true, +}; diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 37b8bfdcfeea..26f7b34d1a03 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -139,7 +140,9 @@ struct nfsd_net { struct svc_info nfsd_info; #define nfsd_serv nfsd_info.serv - + struct percpu_ref nfsd_serv_ref; + struct completion nfsd_serv_confirm_done; + struct completion nfsd_serv_free_done; /* * clientid and stateid data for construction of net unique COPY @@ -214,6 +217,10 @@ struct nfsd_net { /* last time an admin-revoke happened for NFSv4.0 */ time64_t nfs40_last_revoke; +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + /* Local clients to be invalidated when net is shut down */ + struct list_head local_clients; +#endif }; /* Simple check to find out if a given net was properly initialized */ @@ -222,6 +229,9 @@ struct nfsd_net { extern bool nfsd_support_version(int vers); extern unsigned int nfsd_net_id; +bool nfsd_serv_try_get(struct net *net); +void nfsd_serv_put(struct net *net); + void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn); void nfsd_reset_write_verifier(struct nfsd_net *nn); #endif /* __NFSD_NETNS_H__ */ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 1c9e5b4bcb0a..3adbc05ebaac 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "idmap.h" #include "nfsd.h" @@ -2246,7 +2247,7 @@ static __net_init int nfsd_net_init(struct net *net) if (retval) goto out_repcache_error; memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats)); - nn->nfsd_svcstats.program = &nfsd_program; + nn->nfsd_svcstats.program = &nfsd_programs[0]; for (i = 0; i < sizeof(nn->nfsd_versions); i++) nn->nfsd_versions[i] = nfsd_support_version(i); for (i = 0; i < sizeof(nn->nfsd4_minorversions); i++) @@ -2257,7 +2258,9 @@ static __net_init int nfsd_net_init(struct net *net) get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); nfsd_proc_stat_init(net); - +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + INIT_LIST_HEAD(&nn->local_clients); +#endif return 0; out_repcache_error: @@ -2268,6 +2271,22 @@ out_export_error: return retval; } +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +/** + * nfsd_net_pre_exit - Disconnect localio clients from net namespace + * @net: a network namespace that is about to be destroyed + * + * This invalidated ->net pointers held by localio clients + * while they can still safely access nn->counter. + */ +static __net_exit void nfsd_net_pre_exit(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs_uuid_invalidate_clients(&nn->local_clients); +} +#endif + /** * nfsd_net_exit - Release the nfsd_net portion of a net namespace * @net: a network namespace that is about to be destroyed @@ -2285,6 +2304,9 @@ static __net_exit void nfsd_net_exit(struct net *net) static struct pernet_operations nfsd_net_ops = { .init = nfsd_net_init, +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + .pre_exit = nfsd_net_pre_exit, +#endif .exit = nfsd_net_exit, .id = &nfsd_net_id, .size = sizeof(struct nfsd_net), @@ -2322,6 +2344,7 @@ static int __init init_nfsd(void) retval = genl_register_family(&nfsd_nl_family); if (retval) goto out_free_all; + nfsd_localio_ops_init(); return 0; out_free_all: diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 4ccbf014a2c7..4b56ba1e8e48 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -85,7 +85,7 @@ struct nfsd_genl_rqstp { u32 rq_opnum[NFSD_MAX_OPS_PER_COMPOUND]; }; -extern struct svc_program nfsd_program; +extern struct svc_program nfsd_programs[]; extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; @@ -146,6 +146,10 @@ extern const struct svc_version nfsd_acl_version3; #endif #endif +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +extern const struct svc_version localio_version1; +#endif + struct nfsd_net; enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 50d23d56f403..40ad58a6a036 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -87,23 +87,24 @@ nfsd_mode_check(struct dentry *dentry, umode_t requested) return nfserr_wrong_type; } -static bool nfsd_originating_port_ok(struct svc_rqst *rqstp, int flags) +static bool nfsd_originating_port_ok(struct svc_rqst *rqstp, + struct svc_cred *cred, + struct svc_export *exp) { - if (flags & NFSEXP_INSECURE_PORT) + if (nfsexp_flags(cred, exp) & NFSEXP_INSECURE_PORT) return true; /* We don't require gss requests to use low ports: */ - if (rqstp->rq_cred.cr_flavor >= RPC_AUTH_GSS) + if (cred->cr_flavor >= RPC_AUTH_GSS) return true; return test_bit(RQ_SECURE, &rqstp->rq_flags); } static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, + struct svc_cred *cred, struct svc_export *exp) { - int flags = nfsexp_flags(&rqstp->rq_cred, exp); - /* Check if the request originated from a secure port. */ - if (!nfsd_originating_port_ok(rqstp, flags)) { + if (rqstp && !nfsd_originating_port_ok(rqstp, cred, exp)) { RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk("nfsd: request from insecure port %s!\n", svc_print_addr(rqstp, buf, sizeof(buf))); @@ -111,7 +112,7 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, } /* Set user creds for this exportpoint */ - return nfserrno(nfsd_setuser(&rqstp->rq_cred, exp)); + return nfserrno(nfsd_setuser(cred, exp)); } static inline __be32 check_pseudo_root(struct dentry *dentry, @@ -141,7 +142,11 @@ static inline __be32 check_pseudo_root(struct dentry *dentry, * dentry. On success, the results are used to set fh_export and * fh_dentry. */ -static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) +static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, + struct svc_cred *cred, + struct auth_domain *client, + struct auth_domain *gssclient, + struct svc_fh *fhp) { struct knfsd_fh *fh = &fhp->fh_handle; struct fid *fid = NULL; @@ -183,8 +188,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) data_left -= len; if (data_left < 0) return error; - exp = rqst_exp_find(&rqstp->rq_chandle, SVC_NET(rqstp), - rqstp->rq_client, rqstp->rq_gssclient, + exp = rqst_exp_find(rqstp ? &rqstp->rq_chandle : NULL, + net, client, gssclient, fh->fh_fsid_type, fh->fh_fsid); fid = (struct fid *)(fh->fh_fsid + len); @@ -219,7 +224,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) put_cred(override_creds(new)); put_cred(new); } else { - error = nfsd_setuser_and_check_port(rqstp, exp); + error = nfsd_setuser_and_check_port(rqstp, cred, exp); if (error) goto out; } @@ -266,20 +271,20 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) fhp->fh_dentry = dentry; fhp->fh_export = exp; - switch (rqstp->rq_vers) { - case 4: + switch (fhp->fh_maxsize) { + case NFS4_FHSIZE: if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR) fhp->fh_no_atomic_attr = true; fhp->fh_64bit_cookies = true; break; - case 3: + case NFS3_FHSIZE: if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC) fhp->fh_no_wcc = true; fhp->fh_64bit_cookies = true; if (exp->ex_flags & NFSEXP_V4ROOT) goto out; break; - case 2: + case NFS_FHSIZE: fhp->fh_no_wcc = true; if (EX_WGATHER(exp)) fhp->fh_use_wgather = true; @@ -293,6 +298,123 @@ out: return error; } +/** + * __fh_verify - filehandle lookup and access checking + * @rqstp: RPC transaction context, or NULL + * @net: net namespace in which to perform the export lookup + * @cred: RPC user credential + * @client: RPC auth domain + * @gssclient: RPC GSS auth domain, or NULL + * @fhp: filehandle to be verified + * @type: expected type of object pointed to by filehandle + * @access: type of access needed to object + * + * See fh_verify() for further descriptions of @fhp, @type, and @access. + */ +static __be32 +__fh_verify(struct svc_rqst *rqstp, + struct net *net, struct svc_cred *cred, + struct auth_domain *client, + struct auth_domain *gssclient, + struct svc_fh *fhp, umode_t type, int access) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_export *exp = NULL; + struct dentry *dentry; + __be32 error; + + if (!fhp->fh_dentry) { + error = nfsd_set_fh_dentry(rqstp, net, cred, client, + gssclient, fhp); + if (error) + goto out; + } + dentry = fhp->fh_dentry; + exp = fhp->fh_export; + + trace_nfsd_fh_verify(rqstp, fhp, type, access); + + /* + * We still have to do all these permission checks, even when + * fh_dentry is already set: + * - fh_verify may be called multiple times with different + * "access" arguments (e.g. nfsd_proc_create calls + * fh_verify(...,NFSD_MAY_EXEC) first, then later (in + * nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE). + * - in the NFSv4 case, the filehandle may have been filled + * in by fh_compose, and given a dentry, but further + * compound operations performed with that filehandle + * still need permissions checks. In the worst case, a + * mountpoint crossing may have changed the export + * options, and we may now need to use a different uid + * (for example, if different id-squashing options are in + * effect on the new filesystem). + */ + error = check_pseudo_root(dentry, exp); + if (error) + goto out; + + error = nfsd_setuser_and_check_port(rqstp, cred, exp); + if (error) + goto out; + + error = nfsd_mode_check(dentry, type); + if (error) + goto out; + + /* + * pseudoflavor restrictions are not enforced on NLM, + * which clients virtually always use auth_sys for, + * even while using RPCSEC_GSS for NFS. + */ + if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS) + goto skip_pseudoflavor_check; + /* + * Clients may expect to be able to use auth_sys during mount, + * even if they use gss for everything else; see section 2.3.2 + * of rfc 2623. + */ + if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT + && exp->ex_path.dentry == dentry) + goto skip_pseudoflavor_check; + + error = check_nfsd_access(exp, rqstp); + if (error) + goto out; + +skip_pseudoflavor_check: + /* Finally, check access permissions. */ + error = nfsd_permission(cred, exp, dentry, access); +out: + trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error); + if (error == nfserr_stale) + nfsd_stats_fh_stale_inc(nn, exp); + return error; +} + +/** + * fh_verify_local - filehandle lookup and access checking + * @net: net namespace in which to perform the export lookup + * @cred: RPC user credential + * @client: RPC auth domain + * @fhp: filehandle to be verified + * @type: expected type of object pointed to by filehandle + * @access: type of access needed to object + * + * This API can be used by callers who do not have an RPC + * transaction context (ie are not running in an nfsd thread). + * + * See fh_verify() for further descriptions of @fhp, @type, and @access. + */ +__be32 +fh_verify_local(struct net *net, struct svc_cred *cred, + struct auth_domain *client, struct svc_fh *fhp, + umode_t type, int access) +{ + return __fh_verify(NULL, net, cred, client, NULL, + fhp, type, access); +} + /** * fh_verify - filehandle lookup and access checking * @rqstp: pointer to current rpc request @@ -323,80 +445,11 @@ out: __be32 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) { - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - struct svc_export *exp = NULL; - struct dentry *dentry; - __be32 error; - - if (!fhp->fh_dentry) { - error = nfsd_set_fh_dentry(rqstp, fhp); - if (error) - goto out; - } - dentry = fhp->fh_dentry; - exp = fhp->fh_export; - - trace_nfsd_fh_verify(rqstp, fhp, type, access); - - /* - * We still have to do all these permission checks, even when - * fh_dentry is already set: - * - fh_verify may be called multiple times with different - * "access" arguments (e.g. nfsd_proc_create calls - * fh_verify(...,NFSD_MAY_EXEC) first, then later (in - * nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE). - * - in the NFSv4 case, the filehandle may have been filled - * in by fh_compose, and given a dentry, but further - * compound operations performed with that filehandle - * still need permissions checks. In the worst case, a - * mountpoint crossing may have changed the export - * options, and we may now need to use a different uid - * (for example, if different id-squashing options are in - * effect on the new filesystem). - */ - error = check_pseudo_root(dentry, exp); - if (error) - goto out; - - error = nfsd_setuser_and_check_port(rqstp, exp); - if (error) - goto out; - - error = nfsd_mode_check(dentry, type); - if (error) - goto out; - - /* - * pseudoflavor restrictions are not enforced on NLM, - * which clients virtually always use auth_sys for, - * even while using RPCSEC_GSS for NFS. - */ - if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS) - goto skip_pseudoflavor_check; - /* - * Clients may expect to be able to use auth_sys during mount, - * even if they use gss for everything else; see section 2.3.2 - * of rfc 2623. - */ - if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT - && exp->ex_path.dentry == dentry) - goto skip_pseudoflavor_check; - - error = check_nfsd_access(exp, rqstp); - if (error) - goto out; - -skip_pseudoflavor_check: - /* Finally, check access permissions. */ - error = nfsd_permission(&rqstp->rq_cred, exp, dentry, access); -out: - trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error); - if (error == nfserr_stale) - nfsd_stats_fh_stale_inc(nn, exp); - return error; + return __fh_verify(rqstp, SVC_NET(rqstp), &rqstp->rq_cred, + rqstp->rq_client, rqstp->rq_gssclient, + fhp, type, access); } - /* * Compose a file handle for an NFS reply. * diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 8d46e203d139..5b7394801dc4 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -217,6 +217,8 @@ extern char * SVCFH_fmt(struct svc_fh *fhp); * Function prototypes */ __be32 fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int); +__be32 fh_verify_local(struct net *, struct svc_cred *, struct auth_domain *, + struct svc_fh *, umode_t, int); __be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index defc430f912f..e236135ddc63 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -35,7 +36,6 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC atomic_t nfsd_th_cnt = ATOMIC_INIT(0); -extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static int nfsd_acl_rpcbind_set(struct net *, @@ -80,6 +80,15 @@ DEFINE_SPINLOCK(nfsd_drc_lock); unsigned long nfsd_drc_max_mem; unsigned long nfsd_drc_mem_used; +#if IS_ENABLED(CONFIG_NFS_LOCALIO) +static const struct svc_version *localio_versions[] = { + [1] = &localio_version1, +}; + +#define NFSD_LOCALIO_NRVERS ARRAY_SIZE(localio_versions) + +#endif /* CONFIG_NFS_LOCALIO */ + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static const struct svc_version *nfsd_acl_version[] = { # if defined(CONFIG_NFSD_V2_ACL) @@ -90,20 +99,9 @@ static const struct svc_version *nfsd_acl_version[] = { # endif }; -#define NFSD_ACL_MINVERS 2 +#define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static struct svc_program nfsd_acl_program = { - .pg_prog = NFS_ACL_PROGRAM, - .pg_nvers = NFSD_ACL_NRVERS, - .pg_vers = nfsd_acl_version, - .pg_name = "nfsacl", - .pg_class = "nfsd", - .pg_authenticate = &svc_set_client, - .pg_init_request = nfsd_acl_init_request, - .pg_rpcbind_set = nfsd_acl_rpcbind_set, -}; - #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { @@ -116,18 +114,41 @@ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { #endif }; -struct svc_program nfsd_program = { -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - .pg_next = &nfsd_acl_program, -#endif +struct svc_program nfsd_programs[] = { + { .pg_prog = NFS_PROGRAM, /* program number */ .pg_nvers = NFSD_MAXVERS+1, /* nr of entries in nfsd_version */ .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ - .pg_authenticate = &svc_set_client, /* export authentication */ + .pg_authenticate = svc_set_client, /* export authentication */ .pg_init_request = nfsd_init_request, .pg_rpcbind_set = nfsd_rpcbind_set, + }, +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) + { + .pg_prog = NFS_ACL_PROGRAM, + .pg_nvers = NFSD_ACL_NRVERS, + .pg_vers = nfsd_acl_version, + .pg_name = "nfsacl", + .pg_class = "nfsd", + .pg_authenticate = svc_set_client, + .pg_init_request = nfsd_acl_init_request, + .pg_rpcbind_set = nfsd_acl_rpcbind_set, + }, +#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + { + .pg_prog = NFS_LOCALIO_PROGRAM, + .pg_nvers = NFSD_LOCALIO_NRVERS, + .pg_vers = localio_versions, + .pg_name = "nfslocalio", + .pg_class = "nfsd", + .pg_authenticate = svc_set_client, + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, + } +#endif /* CONFIG_NFS_LOCALIO */ }; bool nfsd_support_version(int vers) @@ -193,6 +214,34 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change return 0; } +bool nfsd_serv_try_get(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + return (nn && percpu_ref_tryget_live(&nn->nfsd_serv_ref)); +} + +void nfsd_serv_put(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + percpu_ref_put(&nn->nfsd_serv_ref); +} + +static void nfsd_serv_done(struct percpu_ref *ref) +{ + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); + + complete(&nn->nfsd_serv_confirm_done); +} + +static void nfsd_serv_free(struct percpu_ref *ref) +{ + struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); + + complete(&nn->nfsd_serv_free_done); +} + /* * Maximum number of nfsd processes */ @@ -392,6 +441,7 @@ static void nfsd_shutdown_net(struct net *net) lockd_down(net); nn->lockd_up = false; } + percpu_ref_exit(&nn->nfsd_serv_ref); nn->nfsd_net_up = false; nfsd_shutdown_generic(); } @@ -471,6 +521,13 @@ void nfsd_destroy_serv(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; + lockdep_assert_held(&nfsd_mutex); + + percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done); + wait_for_completion(&nn->nfsd_serv_confirm_done); + wait_for_completion(&nn->nfsd_serv_free_done); + /* percpu_ref_exit is called in nfsd_shutdown_net */ + spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = NULL; spin_unlock(&nfsd_notifier_lock); @@ -595,10 +652,18 @@ int nfsd_create_serv(struct net *net) if (nn->nfsd_serv) return 0; + error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free, + 0, GFP_KERNEL); + if (error) + return error; + init_completion(&nn->nfsd_serv_free_done); + init_completion(&nn->nfsd_serv_confirm_done); + if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); - serv = svc_create_pooled(&nfsd_program, &nn->nfsd_svcstats, + serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), + &nn->nfsd_svcstats, nfsd_max_blksize, nfsd); if (serv == NULL) return -ENOMEM; @@ -905,7 +970,7 @@ nfsd(void *vrqstp) } /** - * nfsd_dispatch - Process an NFS or NFSACL Request + * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request * @rqstp: incoming request * * This RPC dispatcher integrates the NFS server's duplicate reply cache. diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 7ab66497e261..c625966cfcf3 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -86,7 +86,8 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode); { NFSD_MAY_NOT_BREAK_LEASE, "NOT_BREAK_LEASE" }, \ { NFSD_MAY_BYPASS_GSS, "BYPASS_GSS" }, \ { NFSD_MAY_READ_IF_EXEC, "READ_IF_EXEC" }, \ - { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }) + { NFSD_MAY_64BIT_COOKIE, "64BIT_COOKIE" }, \ + { NFSD_MAY_LOCALIO, "LOCALIO" }) TRACE_EVENT(nfsd_compound, TP_PROTO( @@ -193,7 +194,7 @@ TRACE_EVENT(nfsd_compound_encode_err, { S_IFIFO, "FIFO" }, \ { S_IFSOCK, "SOCK" }) -TRACE_EVENT(nfsd_fh_verify, +TRACE_EVENT_CONDITION(nfsd_fh_verify, TP_PROTO( const struct svc_rqst *rqstp, const struct svc_fh *fhp, @@ -201,6 +202,7 @@ TRACE_EVENT(nfsd_fh_verify, int access ), TP_ARGS(rqstp, fhp, type, access), + TP_CONDITION(rqstp != NULL), TP_STRUCT__entry( __field(unsigned int, netns_ino) __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) @@ -239,7 +241,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify_err, __be32 error ), TP_ARGS(rqstp, fhp, type, access, error), - TP_CONDITION(error), + TP_CONDITION(rqstp != NULL && error), TP_STRUCT__entry( __field(unsigned int, netns_ino) __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) @@ -295,12 +297,13 @@ DECLARE_EVENT_CLASS(nfsd_fh_err_class, __entry->status) ) -#define DEFINE_NFSD_FH_ERR_EVENT(name) \ -DEFINE_EVENT(nfsd_fh_err_class, nfsd_##name, \ - TP_PROTO(struct svc_rqst *rqstp, \ - struct svc_fh *fhp, \ - int status), \ - TP_ARGS(rqstp, fhp, status)) +#define DEFINE_NFSD_FH_ERR_EVENT(name) \ +DEFINE_EVENT_CONDITION(nfsd_fh_err_class, nfsd_##name, \ + TP_PROTO(struct svc_rqst *rqstp, \ + struct svc_fh *fhp, \ + int status), \ + TP_ARGS(rqstp, fhp, status), \ + TP_CONDITION(rqstp != NULL)) DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badexport); DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badhandle); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 01947561d375..3ff146522556 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -33,6 +33,8 @@ #define NFSD_MAY_64BIT_COOKIE 0x1000 /* 64 bit readdir cookies for >= NFSv3 */ +#define NFSD_MAY_LOCALIO 0x2000 /* for tracing, reflects when localio used */ + #define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) #define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fc4d75c6cec3..673d5cae7c81 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -467,6 +467,7 @@ static inline __init_memblock bool memblock_bottom_up(void) phys_addr_t memblock_phys_mem_size(void); phys_addr_t memblock_reserved_size(void); +unsigned long memblock_estimated_nr_free_pages(void); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); diff --git a/include/linux/nfs.h b/include/linux/nfs.h index ceb70a926b95..9ad727ddfedb 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -8,11 +8,20 @@ #ifndef _LINUX_NFS_H #define _LINUX_NFS_H +#include +#include #include #include #include #include +/* The LOCALIO program is entirely private to Linux and is + * NOT part of the uapi. + */ +#define NFS_LOCALIO_PROGRAM 400122 +#define LOCALIOPROC_NULL 0 +#define LOCALIOPROC_UUID_IS_LOCAL 1 + /* * This is the kernel NFS client file handle representation */ diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h new file mode 100644 index 000000000000..5fc02df88252 --- /dev/null +++ b/include/linux/nfs_common.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains constants and methods used by both NFS client and server. + */ +#ifndef _LINUX_NFS_COMMON_H +#define _LINUX_NFS_COMMON_H + +#include +#include + +/* Mapping from NFS error code to "errno" error code. */ +#define errno_NFSERR_IO EIO + +int nfs_stat_to_errno(enum nfs_stat status); +int nfs4_stat_to_errno(int stat); + +#endif /* _LINUX_NFS_COMMON_H */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1df86ab98c77..853df3fcd4c2 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -49,6 +50,7 @@ struct nfs_client { #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ #define NFS_CS_PNFS 9 /* - Server used for pnfs */ +#define NFS_CS_LOCAL_IO 10 /* - client is local */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -125,6 +127,13 @@ struct nfs_client { struct net *cl_net; struct list_head pending_cb_stateids; struct rcu_head rcu; + +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + struct timespec64 cl_nfssvc_boot; + seqlock_t cl_boot_lock; + nfs_uuid_t cl_uuid; + spinlock_t cl_localio_lock; +#endif /* CONFIG_NFS_LOCALIO */ }; /* @@ -158,6 +167,7 @@ struct nfs_server { #define NFS_MOUNT_WRITE_WAIT 0x02000000 #define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 #define NFS_MOUNT_SHUTDOWN 0x08000000 +#define NFS_MOUNT_NO_ALIGNWRITE 0x10000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ @@ -234,8 +244,7 @@ struct nfs_server { /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; #endif - struct ida openowner_id; - struct ida lockowner_id; + atomic64_t owner_ctr; struct list_head state_owners_lru; struct list_head layouts; struct list_head delegations; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 45623af3e7b8..12d8e47bc5a3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -446,7 +446,7 @@ struct nfs42_clone_res { struct stateowner_id { __u64 create_time; - __u32 uniquifier; + __u64 uniquifier; }; struct nfs4_open_delegation { @@ -1853,6 +1853,24 @@ struct nfs_rpc_ops { void (*disable_swap)(struct inode *inode); }; +/* + * Helper functions used by NFS client and/or server + */ +static inline void encode_opaque_fixed(struct xdr_stream *xdr, + const void *buf, size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); +} + +static inline int decode_opaque_fixed(struct xdr_stream *xdr, + void *buf, size_t len) +{ + ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len); + if (unlikely(ret < 0)) + return -EIO; + return 0; +} + /* * Function vectors etc. for the NFS client */ @@ -1866,4 +1884,4 @@ extern const struct rpc_version nfs_version4; extern const struct rpc_version nfsacl_version3; extern const struct rpc_program nfsacl_program; -#endif +#endif /* _LINUX_NFS_XDR_H */ diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h new file mode 100644 index 000000000000..b353abe00357 --- /dev/null +++ b/include/linux/nfslocalio.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Mike Snitzer + * Copyright (C) 2024 NeilBrown + */ +#ifndef __LINUX_NFSLOCALIO_H +#define __LINUX_NFSLOCALIO_H + +/* nfsd_file structure is purposely kept opaque to NFS client */ +struct nfsd_file; + +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + +#include +#include +#include +#include +#include +#include +#include + +/* + * Useful to allow a client to negotiate if localio + * possible with its server. + * + * See Documentation/filesystems/nfs/localio.rst for more detail. + */ +typedef struct { + uuid_t uuid; + struct list_head list; + struct net __rcu *net; /* nfsd's network namespace */ + struct auth_domain *dom; /* auth_domain for localio */ +} nfs_uuid_t; + +void nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_end(nfs_uuid_t *); +void nfs_uuid_is_local(const uuid_t *, struct list_head *, + struct net *, struct auth_domain *, struct module *); +void nfs_uuid_invalidate_clients(struct list_head *list); +void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid); + +/* localio needs to map filehandle -> struct nfsd_file */ +extern struct nfsd_file * +nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, + const struct cred *, const struct nfs_fh *, + const fmode_t) __must_hold(rcu); + +struct nfsd_localio_operations { + bool (*nfsd_serv_try_get)(struct net *); + void (*nfsd_serv_put)(struct net *); + struct nfsd_file *(*nfsd_open_local_fh)(struct net *, + struct auth_domain *, + struct rpc_clnt *, + const struct cred *, + const struct nfs_fh *, + const fmode_t); + void (*nfsd_file_put_local)(struct nfsd_file *); + struct file *(*nfsd_file_file)(struct nfsd_file *); +} ____cacheline_aligned; + +extern void nfsd_localio_ops_init(void); +extern const struct nfsd_localio_operations *nfs_to; + +struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, + struct rpc_clnt *, const struct cred *, + const struct nfs_fh *, const fmode_t); + +#else /* CONFIG_NFS_LOCALIO */ +static inline void nfsd_localio_ops_init(void) +{ +} +#endif /* CONFIG_NFS_LOCALIO */ + +#endif /* __LINUX_NFSLOCALIO_H */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 0c77ba488bba..fec1e8a1570c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -151,13 +151,15 @@ struct rpc_task_setup { #define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT) #define RPC_IS_MOVEABLE(t) ((t)->tk_flags & RPC_TASK_MOVEABLE) -#define RPC_TASK_RUNNING 0 -#define RPC_TASK_QUEUED 1 -#define RPC_TASK_ACTIVE 2 -#define RPC_TASK_NEED_XMIT 3 -#define RPC_TASK_NEED_RECV 4 -#define RPC_TASK_MSG_PIN_WAIT 5 -#define RPC_TASK_SIGNALLED 6 +enum { + RPC_TASK_RUNNING, + RPC_TASK_QUEUED, + RPC_TASK_ACTIVE, + RPC_TASK_NEED_XMIT, + RPC_TASK_NEED_RECV, + RPC_TASK_MSG_PIN_WAIT, + RPC_TASK_SIGNALLED, +}; #define rpc_test_and_set_running(t) \ test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index c419a61f60e5..e68fecf6eab5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -67,9 +67,10 @@ enum { * We currently do not support more than one RPC program per daemon. */ struct svc_serv { - struct svc_program * sv_program; /* RPC program */ + struct svc_program * sv_programs; /* RPC programs */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + unsigned int sv_nprogs; /* Number of sv_programs */ unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -360,10 +361,9 @@ struct svc_process_info { }; /* - * List of RPC programs on the same transport endpoint + * RPC program - an array of these can use the same transport endpoint */ struct svc_program { - struct svc_program * pg_next; /* other programs (same xprt) */ u32 pg_prog; /* program number */ unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ @@ -441,6 +441,7 @@ bool svc_rqst_replace_page(struct svc_rqst *rqstp, void svc_rqst_release_pages(struct svc_rqst *rqstp); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *prog, + unsigned int nprog, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)); diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 63cf6fb26dcc..2e111153f7cd 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -157,6 +158,10 @@ extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp); extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops); extern void svc_auth_unregister(rpc_authflavor_t flavor); +extern void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt, + const struct cred *, + struct svc_cred *); + extern struct auth_domain *unix_domain_find(char *name); extern void auth_domain_put(struct auth_domain *item); extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new); diff --git a/init/Kconfig b/init/Kconfig index 2e0427453c39..18b5708f9d9f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -60,6 +60,13 @@ config LLD_VERSION default $(ld-version) if LD_IS_LLD default 0 +config RUSTC_VERSION + int + default $(shell,$(srctree)/scripts/rustc-version.sh $(RUSTC)) + help + It does not depend on `RUST` since that one may need to use the version + in a `depends on`. + config RUST_IS_AVAILABLE def_bool $(success,$(srctree)/scripts/rust_is_available.sh) help @@ -1935,12 +1942,14 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE - depends on !CFI_CLANG depends on !MODVERSIONS - depends on !GCC_PLUGINS + depends on !GCC_PLUGIN_RANDSTRUCT depends on !RANDSTRUCT - depends on !SHADOW_CALL_STACK depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE + depends on !CFI_CLANG || RUSTC_VERSION >= 107900 && $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers) + select CFI_ICALL_NORMALIZE_INTEGERS if CFI_CLANG + depends on !CALL_PADDING || RUSTC_VERSION >= 108000 + depends on !KASAN_SW_TAGS help Enables Rust support in the kernel. @@ -1957,7 +1966,9 @@ config RUST config RUSTC_VERSION_TEXT string depends on RUST - default "$(shell,$(RUSTC) --version 2>/dev/null)" + default "$(RUSTC_VERSION_TEXT)" + help + See `CC_VERSION_TEXT`. config BINDGEN_VERSION_TEXT string diff --git a/kernel/fork.c b/kernel/fork.c index d748c5f01167..daea0649cb86 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1013,7 +1013,7 @@ void __init __weak arch_task_cache_init(void) { } static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; - unsigned long nr_pages = PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); + unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 80f6baff73e0..e34f84e6ce28 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -160,6 +160,7 @@ config MODULE_UNLOAD_TAINT_TRACKING config MODVERSIONS bool "Module versioning support" + depends on !COMPILE_TEST help Usually, you have to use modules compiled with your kernel. Saying Y here makes it sometimes possible to use modules diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 7634dd2a6128..b88543e5c0cc 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -44,7 +44,8 @@ ifndef CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX CFLAGS_KASAN_TEST += -fno-builtin endif -CFLAGS_kasan_test.o := $(CFLAGS_KASAN_TEST) +CFLAGS_kasan_test_c.o := $(CFLAGS_KASAN_TEST) +RUSTFLAGS_kasan_test_rust.o := $(RUSTFLAGS_KASAN) CFLAGS_kasan_test_module.o := $(CFLAGS_KASAN_TEST) obj-y := common.o report.o @@ -52,5 +53,10 @@ obj-$(CONFIG_KASAN_GENERIC) += init.o generic.o report_generic.o shadow.o quaran obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o tags.o report_tags.o obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o tags.o report_tags.o +kasan_test-objs := kasan_test_c.o +ifdef CONFIG_RUST + kasan_test-objs += kasan_test_rust.o +endif + obj-$(CONFIG_KASAN_KUNIT_TEST) += kasan_test.o obj-$(CONFIG_KASAN_MODULE_TEST) += kasan_test_module.o diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index fb2b9ac0659a..f438a6cdc964 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -555,6 +555,12 @@ static inline bool kasan_arch_is_ready(void) { return true; } void kasan_kunit_test_suite_start(void); void kasan_kunit_test_suite_end(void); +#ifdef CONFIG_RUST +char kasan_test_rust_uaf(void); +#else +static inline char kasan_test_rust_uaf(void) { return '\0'; } +#endif + #else /* CONFIG_KASAN_KUNIT_TEST */ static inline void kasan_kunit_test_suite_start(void) { } diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test_c.c similarity index 99% rename from mm/kasan/kasan_test.c rename to mm/kasan/kasan_test_c.c index 567d33b493e2..a181e4780d9d 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test_c.c @@ -1944,6 +1944,16 @@ static void match_all_mem_tag(struct kunit *test) kfree(ptr); } +/* + * Check that Rust performing a use-after-free using `unsafe` is detected. + * This is a smoke test to make sure that Rust is being sanitized properly. + */ +static void rust_uaf(struct kunit *test) +{ + KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_RUST); + KUNIT_EXPECT_KASAN_FAIL(test, kasan_test_rust_uaf()); +} + static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kmalloc_oob_right), KUNIT_CASE(kmalloc_oob_left), @@ -2017,6 +2027,7 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(match_all_not_assigned), KUNIT_CASE(match_all_ptr_tag), KUNIT_CASE(match_all_mem_tag), + KUNIT_CASE(rust_uaf), {} }; diff --git a/mm/kasan/kasan_test_rust.rs b/mm/kasan/kasan_test_rust.rs new file mode 100644 index 000000000000..caa7175964ef --- /dev/null +++ b/mm/kasan/kasan_test_rust.rs @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Helper crate for KASAN testing. +//! +//! Provides behavior to check the sanitization of Rust code. + +use core::ptr::addr_of_mut; +use kernel::prelude::*; + +/// Trivial UAF - allocate a big vector, grab a pointer partway through, +/// drop the vector, and touch it. +#[no_mangle] +pub extern "C" fn kasan_test_rust_uaf() -> u8 { + let mut v: Vec = Vec::new(); + for _ in 0..4096 { + v.push(0x42, GFP_KERNEL).unwrap(); + } + let ptr: *mut u8 = addr_of_mut!(v[2048]); + drop(v); + unsafe { *ptr } +} diff --git a/mm/memblock.c b/mm/memblock.c index 0a77a748a8eb..0389ce5cd281 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1731,6 +1731,23 @@ phys_addr_t __init_memblock memblock_reserved_size(void) return memblock.reserved.total_size; } +/** + * memblock_estimated_nr_free_pages - return estimated number of free pages + * from memblock point of view + * + * During bootup, subsystems might need a rough estimate of the number of free + * pages in the whole system, before precise numbers are available from the + * buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers + * obtained from the buddy might be very imprecise during bootup. + * + * Return: + * An estimated number of free pages from memblock point of view. + */ +unsigned long __init memblock_estimated_nr_free_pages(void) +{ + return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); +} + /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 95ff74706104..4f31e73dc34d 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -731,11 +731,10 @@ static bool cache_defer_req(struct cache_req *req, struct cache_head *item) static void cache_revisit_request(struct cache_head *item) { struct cache_deferred_req *dreq; - struct list_head pending; struct hlist_node *tmp; int hash = DFR_HASH(item); + LIST_HEAD(pending); - INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash) @@ -756,10 +755,8 @@ static void cache_revisit_request(struct cache_head *item) void cache_clean_deferred(void *owner) { struct cache_deferred_req *dreq, *tmp; - struct list_head pending; + LIST_HEAD(pending); - - INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) { @@ -1085,9 +1082,8 @@ static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq, *tmp; struct cache_request *cr; - struct list_head dequeued; + LIST_HEAD(dequeued); - INIT_LIST_HEAD(&dequeued); spin_lock(&queue_lock); list_for_each_entry_safe(cq, tmp, &detail->queue, list) if (!cq->reader) { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 09f29a95f2bc..0090162ee8c3 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -48,13 +48,8 @@ # define RPCDBG_FACILITY RPCDBG_CALL #endif -/* - * All RPC clients are linked into this list - */ - static DECLARE_WAIT_QUEUE_HEAD(destroy_wait); - static void call_start(struct rpc_task *task); static void call_reserve(struct rpc_task *task); static void call_reserveresult(struct rpc_task *task); @@ -546,7 +541,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .connect_timeout = args->connect_timeout, .reconnect_timeout = args->reconnect_timeout, }; - char servername[48]; + char servername[RPC_MAXNETNAMELEN]; struct rpc_clnt *clnt; int i; @@ -1893,12 +1888,6 @@ call_allocate(struct rpc_task *task) if (req->rq_buffer) return; - if (proc->p_proc != 0) { - BUG_ON(proc->p_arglen == 0); - if (proc->p_decode != NULL) - BUG_ON(proc->p_replen == 0); - } - /* * Calculate the size (in quads) of the RPC call * and reply headers, and convert both values diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 9aff845196ce..7e7f4e0390c7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -440,10 +440,11 @@ EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); static int svc_uses_rpcbind(struct svc_serv *serv) { - struct svc_program *progp; - unsigned int i; + unsigned int p, i; + + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; - for (progp = serv->sv_program; progp; progp = progp->pg_next) { for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; @@ -480,7 +481,7 @@ __svc_init_bc(struct svc_serv *serv) * Create an RPC service */ static struct svc_serv * -__svc_create(struct svc_program *prog, struct svc_stat *stats, +__svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats, unsigned int bufsize, int npools, int (*threadfn)(void *data)) { struct svc_serv *serv; @@ -491,7 +492,8 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; serv->sv_name = prog->pg_name; - serv->sv_program = prog; + serv->sv_programs = prog; + serv->sv_nprogs = nprogs; serv->sv_stats = stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; @@ -499,17 +501,18 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); serv->sv_threadfn = threadfn; xdrsize = 0; - while (prog) { - prog->pg_lovers = prog->pg_nvers-1; - for (vers=0; verspg_nvers ; vers++) - if (prog->pg_vers[vers]) { - prog->pg_hivers = vers; - if (prog->pg_lovers > vers) - prog->pg_lovers = vers; - if (prog->pg_vers[vers]->vs_xdrsize > xdrsize) - xdrsize = prog->pg_vers[vers]->vs_xdrsize; + for (i = 0; i < nprogs; i++) { + struct svc_program *progp = &prog[i]; + + progp->pg_lovers = progp->pg_nvers-1; + for (vers = 0; vers < progp->pg_nvers ; vers++) + if (progp->pg_vers[vers]) { + progp->pg_hivers = vers; + if (progp->pg_lovers > vers) + progp->pg_lovers = vers; + if (progp->pg_vers[vers]->vs_xdrsize > xdrsize) + xdrsize = progp->pg_vers[vers]->vs_xdrsize; } - prog = prog->pg_next; } serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); @@ -558,13 +561,14 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize, int (*threadfn)(void *data)) { - return __svc_create(prog, NULL, bufsize, 1, threadfn); + return __svc_create(prog, 1, NULL, bufsize, 1, threadfn); } EXPORT_SYMBOL_GPL(svc_create); /** * svc_create_pooled - Create an RPC service with pooled threads - * @prog: the RPC program the new service will handle + * @prog: Array of RPC programs the new service will handle + * @nprogs: Number of programs in the array * @stats: the stats struct if desired * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog @@ -572,6 +576,7 @@ EXPORT_SYMBOL_GPL(svc_create); * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create_pooled(struct svc_program *prog, + unsigned int nprogs, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)) @@ -579,7 +584,7 @@ struct svc_serv *svc_create_pooled(struct svc_program *prog, struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, stats, bufsize, npools, threadfn); + serv = __svc_create(prog, nprogs, stats, bufsize, npools, threadfn); if (!serv) goto out_err; serv->sv_is_pooled = true; @@ -602,16 +607,16 @@ svc_destroy(struct svc_serv **servp) *servp = NULL; - dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); + dprintk("svc: svc_destroy(%s)\n", serv->sv_programs->pg_name); timer_shutdown_sync(&serv->sv_temptimer); /* * Remaining transports at this point are not expected. */ WARN_ONCE(!list_empty(&serv->sv_permsocks), - "SVC: permsocks remain for %s\n", serv->sv_program->pg_name); + "SVC: permsocks remain for %s\n", serv->sv_programs->pg_name); WARN_ONCE(!list_empty(&serv->sv_tempsocks), - "SVC: tempsocks remain for %s\n", serv->sv_program->pg_name); + "SVC: tempsocks remain for %s\n", serv->sv_programs->pg_name); cache_clean_deferred(serv); @@ -1148,15 +1153,16 @@ int svc_register(const struct svc_serv *serv, struct net *net, const int family, const unsigned short proto, const unsigned short port) { - struct svc_program *progp; - unsigned int i; + unsigned int p, i; int error = 0; WARN_ON_ONCE(proto == 0 && port == 0); if (proto == 0 && port == 0) return -EINVAL; - for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; + for (i = 0; i < progp->pg_nvers; i++) { error = progp->pg_rpcbind_set(net, progp, i, @@ -1208,13 +1214,14 @@ static void __svc_unregister(struct net *net, const u32 program, const u32 versi static void svc_unregister(const struct svc_serv *serv, struct net *net) { struct sighand_struct *sighand; - struct svc_program *progp; unsigned long flags; - unsigned int i; + unsigned int p, i; clear_thread_flag(TIF_SIGPENDING); - for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; + for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; @@ -1320,7 +1327,7 @@ svc_process_common(struct svc_rqst *rqstp) struct svc_process_info process; enum svc_auth_status auth_res; unsigned int aoffset; - int rc; + int pr, rc; __be32 *p; /* Will be turned off only when NFSv4 Sessions are used */ @@ -1344,9 +1351,12 @@ svc_process_common(struct svc_rqst *rqstp) rqstp->rq_vers = be32_to_cpup(p++); rqstp->rq_proc = be32_to_cpup(p); - for (progp = serv->sv_program; progp; progp = progp->pg_next) + for (pr = 0; pr < serv->sv_nprogs; pr++) { + progp = &serv->sv_programs[pr]; + if (rqstp->rq_prog == progp->pg_prog) break; + } /* * Decode auth data, and add verifier to reply buffer. diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 53ebc719ff5a..43c57124de52 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -268,7 +268,7 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, spin_unlock(&svc_xprt_class_lock); newxprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); if (IS_ERR(newxprt)) { - trace_svc_xprt_create_err(serv->sv_program->pg_name, + trace_svc_xprt_create_err(serv->sv_programs->pg_name, xcl->xcl_name, sap, len, newxprt); module_put(xcl->xcl_owner); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 93d9e949e265..55b4d2874188 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -175,6 +176,33 @@ rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_auth_flavor); +/** + * svcauth_map_clnt_to_svc_cred_local - maps a generic cred + * to a svc_cred suitable for use in nfsd. + * @clnt: rpc_clnt associated with nfs client + * @cred: generic cred associated with nfs client + * @svc: returned svc_cred that is suitable for use in nfsd + */ +void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt, + const struct cred *cred, + struct svc_cred *svc) +{ + struct user_namespace *userns = clnt->cl_cred ? + clnt->cl_cred->user_ns : &init_user_ns; + + memset(svc, 0, sizeof(struct svc_cred)); + + svc->cr_uid = KUIDT_INIT(from_kuid_munged(userns, cred->fsuid)); + svc->cr_gid = KGIDT_INIT(from_kgid_munged(userns, cred->fsgid)); + svc->cr_flavor = clnt->cl_auth->au_flavor; + if (cred->group_info) + svc->cr_group_info = get_group_info(cred->group_info); + /* These aren't relevant for local (network is bypassed) */ + svc->cr_principal = NULL; + svc->cr_gss_mech = NULL; +} +EXPORT_SYMBOL_GPL(svcauth_map_clnt_to_svc_cred_local); + /************************************************** * 'auth_domains' are stored in a hash table indexed by name. * When the last reference to an 'auth_domain' is dropped, diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 04b45588ae6f..8ca98b146ec8 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -697,7 +697,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) rqstp->rq_auth_stat = rpc_autherr_badcred; ipm = ip_map_cached_get(xprt); if (ipm == NULL) - ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class, + ipm = __ip_map_lookup(sn->ip_map_cache, + rqstp->rq_server->sv_programs->pg_class, &sin6->sin6_addr); if (ipm == NULL) diff --git a/rust/Makefile b/rust/Makefile index f168d2c98a15..b5e0a73b78f3 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -8,16 +8,16 @@ always-$(CONFIG_RUST) += exports_core_generated.h # Missing prototypes are expected in the helpers since these are exported # for Rust only, thus there is no header nor prototypes. -obj-$(CONFIG_RUST) += helpers.o -CFLAGS_REMOVE_helpers.o = -Wmissing-prototypes -Wmissing-declarations +obj-$(CONFIG_RUST) += helpers/helpers.o +CFLAGS_REMOVE_helpers/helpers.o = -Wmissing-prototypes -Wmissing-declarations always-$(CONFIG_RUST) += libmacros.so no-clean-files += libmacros.so always-$(CONFIG_RUST) += bindings/bindings_generated.rs bindings/bindings_helpers_generated.rs obj-$(CONFIG_RUST) += alloc.o bindings.o kernel.o -always-$(CONFIG_RUST) += exports_alloc_generated.h exports_bindings_generated.h \ - exports_kernel_generated.h +always-$(CONFIG_RUST) += exports_alloc_generated.h exports_helpers_generated.h \ + exports_bindings_generated.h exports_kernel_generated.h always-$(CONFIG_RUST) += uapi/uapi_generated.rs obj-$(CONFIG_RUST) += uapi.o @@ -63,6 +63,7 @@ quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< OBJTREE=$(abspath $(objtree)) \ $(RUSTDOC) $(if $(rustdoc_host),$(rust_common_flags),$(rust_flags)) \ $(rustc_target_flags) -L$(objtree)/$(obj) \ + -Zunstable-options --generate-link-to-definition \ --output $(rustdoc_output) \ --crate-name $(subst rustdoc-,,$@) \ $(if $(rustdoc_host),,--sysroot=/dev/null) \ @@ -270,7 +271,7 @@ quiet_cmd_bindgen = BINDGEN $@ cmd_bindgen = \ $(BINDGEN) $< $(bindgen_target_flags) \ --use-core --with-derive-default --ctypes-prefix core::ffi --no-layout-tests \ - --no-debug '.*' \ + --no-debug '.*' --enable-function-attribute-detection \ -o $@ -- $(bindgen_c_flags_final) -DMODULE \ $(bindgen_target_cflags) $(bindgen_target_extra) @@ -299,13 +300,13 @@ $(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_cflags = \ -I$(objtree)/$(obj) -Wno-missing-prototypes -Wno-missing-declarations $(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ; \ sed -Ei 's/pub fn rust_helper_([a-zA-Z0-9_]*)/#[link_name="rust_helper_\1"]\n pub fn \1/g' $@ -$(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers.c FORCE +$(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers/helpers.c FORCE $(call if_changed_dep,bindgen) quiet_cmd_exports = EXPORTS $@ cmd_exports = \ $(NM) -p --defined-only $< \ - | awk '/ (T|R|D|B) / {printf "EXPORT_SYMBOL_RUST_GPL(%s);\n",$$3}' > $@ + | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ {printf "EXPORT_SYMBOL_RUST_GPL(%s);\n",$$3}' > $@ $(obj)/exports_core_generated.h: $(obj)/core.o FORCE $(call if_changed,exports) @@ -313,6 +314,18 @@ $(obj)/exports_core_generated.h: $(obj)/core.o FORCE $(obj)/exports_alloc_generated.h: $(obj)/alloc.o FORCE $(call if_changed,exports) +# Even though Rust kernel modules should never use the bindings directly, +# symbols from the `bindings` crate and the C helpers need to be exported +# because Rust generics and inlined functions may not get their code generated +# in the crate where they are defined. Other helpers, called from non-inline +# functions, may not be exported, in principle. However, in general, the Rust +# compiler does not guarantee codegen will be performed for a non-inline +# function either. Therefore, we export all symbols from helpers and bindings. +# In the future, this may be revisited to reduce the number of exports after +# the compiler is informed about the places codegen is required. +$(obj)/exports_helpers_generated.h: $(obj)/helpers/helpers.o FORCE + $(call if_changed,exports) + $(obj)/exports_bindings_generated.h: $(obj)/bindings.o FORCE $(call if_changed,exports) @@ -329,9 +342,7 @@ quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@ --crate-name $(patsubst lib%.so,%,$(notdir $@)) $< # Procedural macros can only be used with the `rustc` that compiled it. -# Therefore, to get `libmacros.so` automatically recompiled when the compiler -# version changes, we add `core.o` as a dependency (even if it is not needed). -$(obj)/libmacros.so: $(src)/macros/lib.rs $(obj)/core.o FORCE +$(obj)/libmacros.so: $(src)/macros/lib.rs FORCE +$(call if_changed_dep,rustc_procmacro) quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@ @@ -344,7 +355,8 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L --crate-type rlib -L$(objtree)/$(obj) \ --crate-name $(patsubst %.o,%,$(notdir $@)) $< \ --sysroot=/dev/null \ - $(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@) + $(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@) \ + $(cmd_objtool) rust-analyzer: $(Q)$(srctree)/scripts/generate_rust_analyzer.py \ @@ -366,44 +378,50 @@ ifneq ($(or $(CONFIG_ARM64),$(and $(CONFIG_RISCV),$(CONFIG_64BIT))),) __ashlti3 __lshrti3 endif +define rule_rustc_library + $(call cmd_and_fixdep,rustc_library) + $(call cmd,gen_objtooldep) +endef + $(obj)/core.o: private skip_clippy = 1 $(obj)/core.o: private skip_flags = -Wunreachable_pub $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) $(obj)/core.o: private rustc_target_flags = $(core-cfgs) -$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs FORCE - +$(call if_changed_dep,rustc_library) +$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs \ + $(wildcard $(objtree)/include/config/RUSTC_VERSION_TEXT) FORCE + +$(call if_changed_rule,rustc_library) ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),) $(obj)/core.o: scripts/target.json endif $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*' $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE - +$(call if_changed_dep,rustc_library) + +$(call if_changed_rule,rustc_library) $(obj)/alloc.o: private skip_clippy = 1 $(obj)/alloc.o: private skip_flags = -Wunreachable_pub $(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs) $(obj)/alloc.o: $(RUST_LIB_SRC)/alloc/src/lib.rs $(obj)/compiler_builtins.o FORCE - +$(call if_changed_dep,rustc_library) + +$(call if_changed_rule,rustc_library) $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE - +$(call if_changed_dep,rustc_library) + +$(call if_changed_rule,rustc_library) $(obj)/bindings.o: $(src)/bindings/lib.rs \ $(obj)/compiler_builtins.o \ $(obj)/bindings/bindings_generated.rs \ $(obj)/bindings/bindings_helpers_generated.rs FORCE - +$(call if_changed_dep,rustc_library) + +$(call if_changed_rule,rustc_library) $(obj)/uapi.o: $(src)/uapi/lib.rs \ $(obj)/compiler_builtins.o \ $(obj)/uapi/uapi_generated.rs FORCE - +$(call if_changed_dep,rustc_library) + +$(call if_changed_rule,rustc_library) $(obj)/kernel.o: private rustc_target_flags = --extern alloc \ --extern build_error --extern macros --extern bindings --extern uapi $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \ $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE - +$(call if_changed_dep,rustc_library) + +$(call if_changed_rule,rustc_library) endif # CONFIG_RUST diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index b940a5777330..ae82e9c941af 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -7,8 +7,8 @@ */ #include -#include #include +#include #include #include #include diff --git a/rust/exports.c b/rust/exports.c index 3803c21d1403..e5695f3b45b7 100644 --- a/rust/exports.c +++ b/rust/exports.c @@ -17,6 +17,7 @@ #include "exports_core_generated.h" #include "exports_alloc_generated.h" +#include "exports_helpers_generated.h" #include "exports_bindings_generated.h" #include "exports_kernel_generated.h" diff --git a/rust/helpers.c b/rust/helpers.c deleted file mode 100644 index 92d3c03ae1bd..000000000000 --- a/rust/helpers.c +++ /dev/null @@ -1,239 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Non-trivial C macros cannot be used in Rust. Similarly, inlined C functions - * cannot be called either. This file explicitly creates functions ("helpers") - * that wrap those so that they can be called from Rust. - * - * Even though Rust kernel modules should never use the bindings directly, some - * of these helpers need to be exported because Rust generics and inlined - * functions may not get their code generated in the crate where they are - * defined. Other helpers, called from non-inline functions, may not be - * exported, in principle. However, in general, the Rust compiler does not - * guarantee codegen will be performed for a non-inline function either. - * Therefore, this file exports all the helpers. In the future, this may be - * revisited to reduce the number of exports after the compiler is informed - * about the places codegen is required. - * - * All symbols are exported as GPL-only to guarantee no GPL-only feature is - * accidentally exposed. - * - * Sorted alphabetically. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -__noreturn void rust_helper_BUG(void) -{ - BUG(); -} -EXPORT_SYMBOL_GPL(rust_helper_BUG); - -unsigned long rust_helper_copy_from_user(void *to, const void __user *from, - unsigned long n) -{ - return copy_from_user(to, from, n); -} -EXPORT_SYMBOL_GPL(rust_helper_copy_from_user); - -unsigned long rust_helper_copy_to_user(void __user *to, const void *from, - unsigned long n) -{ - return copy_to_user(to, from, n); -} -EXPORT_SYMBOL_GPL(rust_helper_copy_to_user); - -void rust_helper_mutex_lock(struct mutex *lock) -{ - mutex_lock(lock); -} -EXPORT_SYMBOL_GPL(rust_helper_mutex_lock); - -void rust_helper___spin_lock_init(spinlock_t *lock, const char *name, - struct lock_class_key *key) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - __raw_spin_lock_init(spinlock_check(lock), name, key, LD_WAIT_CONFIG); -#else - spin_lock_init(lock); -#endif -} -EXPORT_SYMBOL_GPL(rust_helper___spin_lock_init); - -void rust_helper_spin_lock(spinlock_t *lock) -{ - spin_lock(lock); -} -EXPORT_SYMBOL_GPL(rust_helper_spin_lock); - -void rust_helper_spin_unlock(spinlock_t *lock) -{ - spin_unlock(lock); -} -EXPORT_SYMBOL_GPL(rust_helper_spin_unlock); - -void rust_helper_init_wait(struct wait_queue_entry *wq_entry) -{ - init_wait(wq_entry); -} -EXPORT_SYMBOL_GPL(rust_helper_init_wait); - -int rust_helper_signal_pending(struct task_struct *t) -{ - return signal_pending(t); -} -EXPORT_SYMBOL_GPL(rust_helper_signal_pending); - -struct page *rust_helper_alloc_pages(gfp_t gfp_mask, unsigned int order) -{ - return alloc_pages(gfp_mask, order); -} -EXPORT_SYMBOL_GPL(rust_helper_alloc_pages); - -void *rust_helper_kmap_local_page(struct page *page) -{ - return kmap_local_page(page); -} -EXPORT_SYMBOL_GPL(rust_helper_kmap_local_page); - -void rust_helper_kunmap_local(const void *addr) -{ - kunmap_local(addr); -} -EXPORT_SYMBOL_GPL(rust_helper_kunmap_local); - -refcount_t rust_helper_REFCOUNT_INIT(int n) -{ - return (refcount_t)REFCOUNT_INIT(n); -} -EXPORT_SYMBOL_GPL(rust_helper_REFCOUNT_INIT); - -void rust_helper_refcount_inc(refcount_t *r) -{ - refcount_inc(r); -} -EXPORT_SYMBOL_GPL(rust_helper_refcount_inc); - -bool rust_helper_refcount_dec_and_test(refcount_t *r) -{ - return refcount_dec_and_test(r); -} -EXPORT_SYMBOL_GPL(rust_helper_refcount_dec_and_test); - -__force void *rust_helper_ERR_PTR(long err) -{ - return ERR_PTR(err); -} -EXPORT_SYMBOL_GPL(rust_helper_ERR_PTR); - -bool rust_helper_IS_ERR(__force const void *ptr) -{ - return IS_ERR(ptr); -} -EXPORT_SYMBOL_GPL(rust_helper_IS_ERR); - -long rust_helper_PTR_ERR(__force const void *ptr) -{ - return PTR_ERR(ptr); -} -EXPORT_SYMBOL_GPL(rust_helper_PTR_ERR); - -const char *rust_helper_errname(int err) -{ - return errname(err); -} -EXPORT_SYMBOL_GPL(rust_helper_errname); - -struct task_struct *rust_helper_get_current(void) -{ - return current; -} -EXPORT_SYMBOL_GPL(rust_helper_get_current); - -void rust_helper_get_task_struct(struct task_struct *t) -{ - get_task_struct(t); -} -EXPORT_SYMBOL_GPL(rust_helper_get_task_struct); - -void rust_helper_put_task_struct(struct task_struct *t) -{ - put_task_struct(t); -} -EXPORT_SYMBOL_GPL(rust_helper_put_task_struct); - -struct kunit *rust_helper_kunit_get_current_test(void) -{ - return kunit_get_current_test(); -} -EXPORT_SYMBOL_GPL(rust_helper_kunit_get_current_test); - -void rust_helper_init_work_with_key(struct work_struct *work, work_func_t func, - bool onstack, const char *name, - struct lock_class_key *key) -{ - __init_work(work, onstack); - work->data = (atomic_long_t)WORK_DATA_INIT(); - lockdep_init_map(&work->lockdep_map, name, key, 0); - INIT_LIST_HEAD(&work->entry); - work->func = func; -} -EXPORT_SYMBOL_GPL(rust_helper_init_work_with_key); - -void * __must_check __realloc_size(2) -rust_helper_krealloc(const void *objp, size_t new_size, gfp_t flags) -{ - return krealloc(objp, new_size, flags); -} -EXPORT_SYMBOL_GPL(rust_helper_krealloc); - -/* - * `bindgen` binds the C `size_t` type as the Rust `usize` type, so we can - * use it in contexts where Rust expects a `usize` like slice (array) indices. - * `usize` is defined to be the same as C's `uintptr_t` type (can hold any - * pointer) but not necessarily the same as `size_t` (can hold the size of any - * single object). Most modern platforms use the same concrete integer type for - * both of them, but in case we find ourselves on a platform where - * that's not true, fail early instead of risking ABI or - * integer-overflow issues. - * - * If your platform fails this assertion, it means that you are in - * danger of integer-overflow bugs (even if you attempt to add - * `--no-size_t-is-usize`). It may be easiest to change the kernel ABI on - * your platform such that `size_t` matches `uintptr_t` (i.e., to increase - * `size_t`, because `uintptr_t` has to be at least as big as `size_t`). - */ -static_assert( - sizeof(size_t) == sizeof(uintptr_t) && - __alignof__(size_t) == __alignof__(uintptr_t), - "Rust code expects C `size_t` to match Rust `usize`" -); - -// This will soon be moved to a separate file, so no need to merge with above. -#include -#include - -void *rust_helper_blk_mq_rq_to_pdu(struct request *rq) -{ - return blk_mq_rq_to_pdu(rq); -} -EXPORT_SYMBOL_GPL(rust_helper_blk_mq_rq_to_pdu); - -struct request *rust_helper_blk_mq_rq_from_pdu(void *pdu) -{ - return blk_mq_rq_from_pdu(pdu); -} -EXPORT_SYMBOL_GPL(rust_helper_blk_mq_rq_from_pdu); diff --git a/rust/helpers/blk.c b/rust/helpers/blk.c new file mode 100644 index 000000000000..cc9f4e6a2d23 --- /dev/null +++ b/rust/helpers/blk.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void *rust_helper_blk_mq_rq_to_pdu(struct request *rq) +{ + return blk_mq_rq_to_pdu(rq); +} + +struct request *rust_helper_blk_mq_rq_from_pdu(void *pdu) +{ + return blk_mq_rq_from_pdu(pdu); +} diff --git a/rust/helpers/bug.c b/rust/helpers/bug.c new file mode 100644 index 000000000000..e2d13babc737 --- /dev/null +++ b/rust/helpers/bug.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +__noreturn void rust_helper_BUG(void) +{ + BUG(); +} diff --git a/rust/helpers/build_assert.c b/rust/helpers/build_assert.c new file mode 100644 index 000000000000..6a54b2680b14 --- /dev/null +++ b/rust/helpers/build_assert.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +/* + * `bindgen` binds the C `size_t` type as the Rust `usize` type, so we can + * use it in contexts where Rust expects a `usize` like slice (array) indices. + * `usize` is defined to be the same as C's `uintptr_t` type (can hold any + * pointer) but not necessarily the same as `size_t` (can hold the size of any + * single object). Most modern platforms use the same concrete integer type for + * both of them, but in case we find ourselves on a platform where + * that's not true, fail early instead of risking ABI or + * integer-overflow issues. + * + * If your platform fails this assertion, it means that you are in + * danger of integer-overflow bugs (even if you attempt to add + * `--no-size_t-is-usize`). It may be easiest to change the kernel ABI on + * your platform such that `size_t` matches `uintptr_t` (i.e., to increase + * `size_t`, because `uintptr_t` has to be at least as big as `size_t`). + */ +static_assert( + sizeof(size_t) == sizeof(uintptr_t) && + __alignof__(size_t) == __alignof__(uintptr_t), + "Rust code expects C `size_t` to match Rust `usize`" +); diff --git a/rust/helpers/build_bug.c b/rust/helpers/build_bug.c new file mode 100644 index 000000000000..e994f7b5928c --- /dev/null +++ b/rust/helpers/build_bug.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +const char *rust_helper_errname(int err) +{ + return errname(err); +} diff --git a/rust/helpers/err.c b/rust/helpers/err.c new file mode 100644 index 000000000000..be3d45ef78a2 --- /dev/null +++ b/rust/helpers/err.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +__force void *rust_helper_ERR_PTR(long err) +{ + return ERR_PTR(err); +} + +bool rust_helper_IS_ERR(__force const void *ptr) +{ + return IS_ERR(ptr); +} + +long rust_helper_PTR_ERR(__force const void *ptr) +{ + return PTR_ERR(ptr); +} diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c new file mode 100644 index 000000000000..30f40149f3a9 --- /dev/null +++ b/rust/helpers/helpers.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Non-trivial C macros cannot be used in Rust. Similarly, inlined C functions + * cannot be called either. This file explicitly creates functions ("helpers") + * that wrap those so that they can be called from Rust. + * + * Sorted alphabetically. + */ + +#include "blk.c" +#include "bug.c" +#include "build_assert.c" +#include "build_bug.c" +#include "err.c" +#include "kunit.c" +#include "mutex.c" +#include "page.c" +#include "rbtree.c" +#include "refcount.c" +#include "signal.c" +#include "slab.c" +#include "spinlock.c" +#include "task.c" +#include "uaccess.c" +#include "wait.c" +#include "workqueue.c" diff --git a/rust/helpers/kunit.c b/rust/helpers/kunit.c new file mode 100644 index 000000000000..9d725067eb3b --- /dev/null +++ b/rust/helpers/kunit.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +struct kunit *rust_helper_kunit_get_current_test(void) +{ + return kunit_get_current_test(); +} diff --git a/rust/helpers/mutex.c b/rust/helpers/mutex.c new file mode 100644 index 000000000000..200db7e6279f --- /dev/null +++ b/rust/helpers/mutex.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void rust_helper_mutex_lock(struct mutex *lock) +{ + mutex_lock(lock); +} diff --git a/rust/helpers/page.c b/rust/helpers/page.c new file mode 100644 index 000000000000..b3f2b8fbf87f --- /dev/null +++ b/rust/helpers/page.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +struct page *rust_helper_alloc_pages(gfp_t gfp_mask, unsigned int order) +{ + return alloc_pages(gfp_mask, order); +} + +void *rust_helper_kmap_local_page(struct page *page) +{ + return kmap_local_page(page); +} + +void rust_helper_kunmap_local(const void *addr) +{ + kunmap_local(addr); +} diff --git a/rust/helpers/rbtree.c b/rust/helpers/rbtree.c new file mode 100644 index 000000000000..6d404b84a9b5 --- /dev/null +++ b/rust/helpers/rbtree.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void rust_helper_rb_link_node(struct rb_node *node, struct rb_node *parent, + struct rb_node **rb_link) +{ + rb_link_node(node, parent, rb_link); +} diff --git a/rust/helpers/refcount.c b/rust/helpers/refcount.c new file mode 100644 index 000000000000..f47afc148ec3 --- /dev/null +++ b/rust/helpers/refcount.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +refcount_t rust_helper_REFCOUNT_INIT(int n) +{ + return (refcount_t)REFCOUNT_INIT(n); +} + +void rust_helper_refcount_inc(refcount_t *r) +{ + refcount_inc(r); +} + +bool rust_helper_refcount_dec_and_test(refcount_t *r) +{ + return refcount_dec_and_test(r); +} diff --git a/rust/helpers/signal.c b/rust/helpers/signal.c new file mode 100644 index 000000000000..63c407f80c26 --- /dev/null +++ b/rust/helpers/signal.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +int rust_helper_signal_pending(struct task_struct *t) +{ + return signal_pending(t); +} diff --git a/rust/helpers/slab.c b/rust/helpers/slab.c new file mode 100644 index 000000000000..f043e087f9d6 --- /dev/null +++ b/rust/helpers/slab.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void * __must_check __realloc_size(2) +rust_helper_krealloc(const void *objp, size_t new_size, gfp_t flags) +{ + return krealloc(objp, new_size, flags); +} diff --git a/rust/helpers/spinlock.c b/rust/helpers/spinlock.c new file mode 100644 index 000000000000..acc1376b833c --- /dev/null +++ b/rust/helpers/spinlock.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void rust_helper___spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + __raw_spin_lock_init(spinlock_check(lock), name, key, LD_WAIT_CONFIG); +#else + spin_lock_init(lock); +#endif +} + +void rust_helper_spin_lock(spinlock_t *lock) +{ + spin_lock(lock); +} + +void rust_helper_spin_unlock(spinlock_t *lock) +{ + spin_unlock(lock); +} diff --git a/rust/helpers/task.c b/rust/helpers/task.c new file mode 100644 index 000000000000..7ac789232d11 --- /dev/null +++ b/rust/helpers/task.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +struct task_struct *rust_helper_get_current(void) +{ + return current; +} + +void rust_helper_get_task_struct(struct task_struct *t) +{ + get_task_struct(t); +} + +void rust_helper_put_task_struct(struct task_struct *t) +{ + put_task_struct(t); +} diff --git a/rust/helpers/uaccess.c b/rust/helpers/uaccess.c new file mode 100644 index 000000000000..f49076f813cd --- /dev/null +++ b/rust/helpers/uaccess.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +unsigned long rust_helper_copy_from_user(void *to, const void __user *from, + unsigned long n) +{ + return copy_from_user(to, from, n); +} + +unsigned long rust_helper_copy_to_user(void __user *to, const void *from, + unsigned long n) +{ + return copy_to_user(to, from, n); +} diff --git a/rust/helpers/wait.c b/rust/helpers/wait.c new file mode 100644 index 000000000000..c7336bbf2750 --- /dev/null +++ b/rust/helpers/wait.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void rust_helper_init_wait(struct wait_queue_entry *wq_entry) +{ + init_wait(wq_entry); +} diff --git a/rust/helpers/workqueue.c b/rust/helpers/workqueue.c new file mode 100644 index 000000000000..f59427acc323 --- /dev/null +++ b/rust/helpers/workqueue.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void rust_helper_init_work_with_key(struct work_struct *work, work_func_t func, + bool onstack, const char *name, + struct lock_class_key *key) +{ + __init_work(work, onstack); + work->data = (atomic_long_t)WORK_DATA_INIT(); + lockdep_init_map(&work->lockdep_map, name, key, 0); + INIT_LIST_HEAD(&work->entry); + work->func = func; +} diff --git a/rust/kernel/alloc/box_ext.rs b/rust/kernel/alloc/box_ext.rs index 9f1c1c489189..7009ad78d4e0 100644 --- a/rust/kernel/alloc/box_ext.rs +++ b/rust/kernel/alloc/box_ext.rs @@ -4,7 +4,7 @@ use super::{AllocError, Flags}; use alloc::boxed::Box; -use core::mem::MaybeUninit; +use core::{mem::MaybeUninit, ptr, result::Result}; /// Extensions to [`Box`]. pub trait BoxExt: Sized { @@ -17,6 +17,24 @@ pub trait BoxExt: Sized { /// /// The allocation may fail, in which case an error is returned. fn new_uninit(flags: Flags) -> Result>, AllocError>; + + /// Drops the contents, but keeps the allocation. + /// + /// # Examples + /// + /// ``` + /// use kernel::alloc::{flags, box_ext::BoxExt}; + /// let value = Box::new([0; 32], flags::GFP_KERNEL)?; + /// assert_eq!(*value, [0; 32]); + /// let mut value = Box::drop_contents(value); + /// // Now we can re-use `value`: + /// value.write([1; 32]); + /// // SAFETY: We just wrote to it. + /// let value = unsafe { value.assume_init() }; + /// assert_eq!(*value, [1; 32]); + /// # Ok::<(), Error>(()) + /// ``` + fn drop_contents(this: Self) -> Box>; } impl BoxExt for Box { @@ -55,4 +73,17 @@ impl BoxExt for Box { // zero-sized types, we use `NonNull::dangling`. Ok(unsafe { Box::from_raw(ptr) }) } + + fn drop_contents(this: Self) -> Box> { + let ptr = Box::into_raw(this); + // SAFETY: `ptr` is valid, because it came from `Box::into_raw`. + unsafe { ptr::drop_in_place(ptr) }; + + // CAST: `MaybeUninit` is a transparent wrapper of `T`. + let ptr = ptr.cast::>(); + + // SAFETY: `ptr` is valid for writes, because it came from `Box::into_raw` and it is valid for + // reads, since the pointer came from `Box::into_raw` and the type is `MaybeUninit`. + unsafe { Box::from_raw(ptr) } + } } diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 145f5c397009..6f1587a2524e 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -135,8 +135,11 @@ impl Error { /// Returns the error encoded as a pointer. #[allow(dead_code)] pub(crate) fn to_ptr(self) -> *mut T { + #[cfg_attr(target_pointer_width = "32", allow(clippy::useless_conversion))] // SAFETY: `self.0` is a valid error due to its invariant. - unsafe { bindings::ERR_PTR(self.0.into()) as *mut _ } + unsafe { + bindings::ERR_PTR(self.0.into()) as *mut _ + } } /// Returns a string representing the error, if one exists. diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 495c09ebe3a3..a17ac8762d8f 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -213,6 +213,7 @@ use crate::{ alloc::{box_ext::BoxExt, AllocError, Flags}, error::{self, Error}, + sync::Arc, sync::UniqueArc, types::{Opaque, ScopeGuard}, }; @@ -742,6 +743,74 @@ macro_rules! try_init { }; } +/// Asserts that a field on a struct using `#[pin_data]` is marked with `#[pin]` ie. that it is +/// structurally pinned. +/// +/// # Example +/// +/// This will succeed: +/// ``` +/// use kernel::assert_pinned; +/// #[pin_data] +/// struct MyStruct { +/// #[pin] +/// some_field: u64, +/// } +/// +/// assert_pinned!(MyStruct, some_field, u64); +/// ``` +/// +/// This will fail: +// TODO: replace with `compile_fail` when supported. +/// ```ignore +/// use kernel::assert_pinned; +/// #[pin_data] +/// struct MyStruct { +/// some_field: u64, +/// } +/// +/// assert_pinned!(MyStruct, some_field, u64); +/// ``` +/// +/// Some uses of the macro may trigger the `can't use generic parameters from outer item` error. To +/// work around this, you may pass the `inline` parameter to the macro. The `inline` parameter can +/// only be used when the macro is invoked from a function body. +/// ``` +/// use kernel::assert_pinned; +/// #[pin_data] +/// struct Foo { +/// #[pin] +/// elem: T, +/// } +/// +/// impl Foo { +/// fn project(self: Pin<&mut Self>) -> Pin<&mut T> { +/// assert_pinned!(Foo, elem, T, inline); +/// +/// // SAFETY: The field is structurally pinned. +/// unsafe { self.map_unchecked_mut(|me| &mut me.elem) } +/// } +/// } +/// ``` +#[macro_export] +macro_rules! assert_pinned { + ($ty:ty, $field:ident, $field_ty:ty, inline) => { + let _ = move |ptr: *mut $field_ty| { + // SAFETY: This code is unreachable. + let data = unsafe { <$ty as $crate::init::__internal::HasPinData>::__pin_data() }; + let init = $crate::init::__internal::AlwaysFail::<$field_ty>::new(); + // SAFETY: This code is unreachable. + unsafe { data.$field(ptr, init) }.ok(); + }; + }; + + ($ty:ty, $field:ident, $field_ty:ty) => { + const _: () = { + $crate::assert_pinned!($ty, $field, $field_ty, inline); + }; + }; +} + /// A pin-initializer for the type `T`. /// /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can @@ -1107,11 +1176,17 @@ unsafe impl PinInit for T { /// Smart pointer that can initialize memory in-place. pub trait InPlaceInit: Sized { + /// Pinned version of `Self`. + /// + /// If a type already implicitly pins its pointee, `Pin` is unnecessary. In this case use + /// `Self`, otherwise just use `Pin`. + type PinnedSelf; + /// Use the given pin-initializer to pin-initialize a `T` inside of a new smart pointer of this /// type. /// /// If `T: !Unpin` it will not be able to move afterwards. - fn try_pin_init(init: impl PinInit, flags: Flags) -> Result, E> + fn try_pin_init(init: impl PinInit, flags: Flags) -> Result where E: From; @@ -1119,7 +1194,7 @@ pub trait InPlaceInit: Sized { /// type. /// /// If `T: !Unpin` it will not be able to move afterwards. - fn pin_init(init: impl PinInit, flags: Flags) -> error::Result> + fn pin_init(init: impl PinInit, flags: Flags) -> error::Result where Error: From, { @@ -1148,19 +1223,15 @@ pub trait InPlaceInit: Sized { } } -impl InPlaceInit for Box { +impl InPlaceInit for Arc { + type PinnedSelf = Self; + #[inline] - fn try_pin_init(init: impl PinInit, flags: Flags) -> Result, E> + fn try_pin_init(init: impl PinInit, flags: Flags) -> Result where E: From, { - let mut this = as BoxExt<_>>::new_uninit(flags)?; - let slot = this.as_mut_ptr(); - // SAFETY: When init errors/panics, slot will get deallocated but not dropped, - // slot is valid and will not be moved, because we pin it later. - unsafe { init.__pinned_init(slot)? }; - // SAFETY: All fields have been initialized. - Ok(unsafe { this.assume_init() }.into()) + UniqueArc::try_pin_init(init, flags).map(|u| u.into()) } #[inline] @@ -1168,29 +1239,39 @@ impl InPlaceInit for Box { where E: From, { - let mut this = as BoxExt<_>>::new_uninit(flags)?; - let slot = this.as_mut_ptr(); - // SAFETY: When init errors/panics, slot will get deallocated but not dropped, - // slot is valid. - unsafe { init.__init(slot)? }; - // SAFETY: All fields have been initialized. - Ok(unsafe { this.assume_init() }) + UniqueArc::try_init(init, flags).map(|u| u.into()) + } +} + +impl InPlaceInit for Box { + type PinnedSelf = Pin; + + #[inline] + fn try_pin_init(init: impl PinInit, flags: Flags) -> Result + where + E: From, + { + as BoxExt<_>>::new_uninit(flags)?.write_pin_init(init) + } + + #[inline] + fn try_init(init: impl Init, flags: Flags) -> Result + where + E: From, + { + as BoxExt<_>>::new_uninit(flags)?.write_init(init) } } impl InPlaceInit for UniqueArc { + type PinnedSelf = Pin; + #[inline] - fn try_pin_init(init: impl PinInit, flags: Flags) -> Result, E> + fn try_pin_init(init: impl PinInit, flags: Flags) -> Result where E: From, { - let mut this = UniqueArc::new_uninit(flags)?; - let slot = this.as_mut_ptr(); - // SAFETY: When init errors/panics, slot will get deallocated but not dropped, - // slot is valid and will not be moved, because we pin it later. - unsafe { init.__pinned_init(slot)? }; - // SAFETY: All fields have been initialized. - Ok(unsafe { this.assume_init() }.into()) + UniqueArc::new_uninit(flags)?.write_pin_init(init) } #[inline] @@ -1198,13 +1279,67 @@ impl InPlaceInit for UniqueArc { where E: From, { - let mut this = UniqueArc::new_uninit(flags)?; - let slot = this.as_mut_ptr(); + UniqueArc::new_uninit(flags)?.write_init(init) + } +} + +/// Smart pointer containing uninitialized memory and that can write a value. +pub trait InPlaceWrite { + /// The type `Self` turns into when the contents are initialized. + type Initialized; + + /// Use the given initializer to write a value into `self`. + /// + /// Does not drop the current value and considers it as uninitialized memory. + fn write_init(self, init: impl Init) -> Result; + + /// Use the given pin-initializer to write a value into `self`. + /// + /// Does not drop the current value and considers it as uninitialized memory. + fn write_pin_init(self, init: impl PinInit) -> Result, E>; +} + +impl InPlaceWrite for Box> { + type Initialized = Box; + + fn write_init(mut self, init: impl Init) -> Result { + let slot = self.as_mut_ptr(); // SAFETY: When init errors/panics, slot will get deallocated but not dropped, // slot is valid. unsafe { init.__init(slot)? }; // SAFETY: All fields have been initialized. - Ok(unsafe { this.assume_init() }) + Ok(unsafe { self.assume_init() }) + } + + fn write_pin_init(mut self, init: impl PinInit) -> Result, E> { + let slot = self.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid and will not be moved, because we pin it later. + unsafe { init.__pinned_init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { self.assume_init() }.into()) + } +} + +impl InPlaceWrite for UniqueArc> { + type Initialized = UniqueArc; + + fn write_init(mut self, init: impl Init) -> Result { + let slot = self.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid. + unsafe { init.__init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { self.assume_init() }) + } + + fn write_pin_init(mut self, init: impl PinInit) -> Result, E> { + let slot = self.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid and will not be moved, because we pin it later. + unsafe { init.__pinned_init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { self.assume_init() }.into()) } } diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs index db3372619ecd..13cefd37512f 100644 --- a/rust/kernel/init/__internal.rs +++ b/rust/kernel/init/__internal.rs @@ -228,3 +228,32 @@ impl OnlyCallFromDrop { Self(()) } } + +/// Initializer that always fails. +/// +/// Used by [`assert_pinned!`]. +/// +/// [`assert_pinned!`]: crate::assert_pinned +pub struct AlwaysFail { + _t: PhantomData, +} + +impl AlwaysFail { + /// Creates a new initializer that always fails. + pub fn new() -> Self { + Self { _t: PhantomData } + } +} + +impl Default for AlwaysFail { + fn default() -> Self { + Self::new() + } +} + +// SAFETY: `__pinned_init` always fails, which is always okay. +unsafe impl PinInit for AlwaysFail { + unsafe fn __pinned_init(self, _slot: *mut T) -> Result<(), ()> { + Err(()) + } +} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 58ed400198bf..22a3bfa5a9e9 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -38,12 +38,14 @@ pub mod init; pub mod ioctl; #[cfg(CONFIG_KUNIT)] pub mod kunit; +pub mod list; #[cfg(CONFIG_NET)] pub mod net; pub mod page; pub mod prelude; pub mod print; pub mod sizes; +pub mod rbtree; mod static_assert; #[doc(hidden)] pub mod std_vendor; diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs new file mode 100644 index 000000000000..5b4aec29eb67 --- /dev/null +++ b/rust/kernel/list.rs @@ -0,0 +1,686 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2024 Google LLC. + +//! A linked list implementation. + +use crate::init::PinInit; +use crate::sync::ArcBorrow; +use crate::types::Opaque; +use core::iter::{DoubleEndedIterator, FusedIterator}; +use core::marker::PhantomData; +use core::ptr; + +mod impl_list_item_mod; +pub use self::impl_list_item_mod::{ + impl_has_list_links, impl_has_list_links_self_ptr, impl_list_item, HasListLinks, HasSelfPtr, +}; + +mod arc; +pub use self::arc::{impl_list_arc_safe, AtomicTracker, ListArc, ListArcSafe, TryNewListArc}; + +mod arc_field; +pub use self::arc_field::{define_list_arc_field_getter, ListArcField}; + +/// A linked list. +/// +/// All elements in this linked list will be [`ListArc`] references to the value. Since a value can +/// only have one `ListArc` (for each pair of prev/next pointers), this ensures that the same +/// prev/next pointers are not used for several linked lists. +/// +/// # Invariants +/// +/// * If the list is empty, then `first` is null. Otherwise, `first` points at the `ListLinks` +/// field of the first element in the list. +/// * All prev/next pointers in `ListLinks` fields of items in the list are valid and form a cycle. +/// * For every item in the list, the list owns the associated [`ListArc`] reference and has +/// exclusive access to the `ListLinks` field. +pub struct List, const ID: u64 = 0> { + first: *mut ListLinksFields, + _ty: PhantomData>, +} + +// SAFETY: This is a container of `ListArc`, and access to the container allows the same +// type of access to the `ListArc` elements. +unsafe impl Send for List +where + ListArc: Send, + T: ?Sized + ListItem, +{ +} +// SAFETY: This is a container of `ListArc`, and access to the container allows the same +// type of access to the `ListArc` elements. +unsafe impl Sync for List +where + ListArc: Sync, + T: ?Sized + ListItem, +{ +} + +/// Implemented by types where a [`ListArc`] can be inserted into a [`List`]. +/// +/// # Safety +/// +/// Implementers must ensure that they provide the guarantees documented on methods provided by +/// this trait. +/// +/// [`ListArc`]: ListArc +pub unsafe trait ListItem: ListArcSafe { + /// Views the [`ListLinks`] for this value. + /// + /// # Guarantees + /// + /// If there is a previous call to `prepare_to_insert` and there is no call to `post_remove` + /// since the most recent such call, then this returns the same pointer as the one returned by + /// the most recent call to `prepare_to_insert`. + /// + /// Otherwise, the returned pointer points at a read-only [`ListLinks`] with two null pointers. + /// + /// # Safety + /// + /// The provided pointer must point at a valid value. (It need not be in an `Arc`.) + unsafe fn view_links(me: *const Self) -> *mut ListLinks; + + /// View the full value given its [`ListLinks`] field. + /// + /// Can only be used when the value is in a list. + /// + /// # Guarantees + /// + /// * Returns the same pointer as the one passed to the most recent call to `prepare_to_insert`. + /// * The returned pointer is valid until the next call to `post_remove`. + /// + /// # Safety + /// + /// * The provided pointer must originate from the most recent call to `prepare_to_insert`, or + /// from a call to `view_links` that happened after the most recent call to + /// `prepare_to_insert`. + /// * Since the most recent call to `prepare_to_insert`, the `post_remove` method must not have + /// been called. + unsafe fn view_value(me: *mut ListLinks) -> *const Self; + + /// This is called when an item is inserted into a [`List`]. + /// + /// # Guarantees + /// + /// The caller is granted exclusive access to the returned [`ListLinks`] until `post_remove` is + /// called. + /// + /// # Safety + /// + /// * The provided pointer must point at a valid value in an [`Arc`]. + /// * Calls to `prepare_to_insert` and `post_remove` on the same value must alternate. + /// * The caller must own the [`ListArc`] for this value. + /// * The caller must not give up ownership of the [`ListArc`] unless `post_remove` has been + /// called after this call to `prepare_to_insert`. + /// + /// [`Arc`]: crate::sync::Arc + unsafe fn prepare_to_insert(me: *const Self) -> *mut ListLinks; + + /// This undoes a previous call to `prepare_to_insert`. + /// + /// # Guarantees + /// + /// The returned pointer is the pointer that was originally passed to `prepare_to_insert`. + /// + /// # Safety + /// + /// The provided pointer must be the pointer returned by the most recent call to + /// `prepare_to_insert`. + unsafe fn post_remove(me: *mut ListLinks) -> *const Self; +} + +#[repr(C)] +#[derive(Copy, Clone)] +struct ListLinksFields { + next: *mut ListLinksFields, + prev: *mut ListLinksFields, +} + +/// The prev/next pointers for an item in a linked list. +/// +/// # Invariants +/// +/// The fields are null if and only if this item is not in a list. +#[repr(transparent)] +pub struct ListLinks { + // This type is `!Unpin` for aliasing reasons as the pointers are part of an intrusive linked + // list. + inner: Opaque, +} + +// SAFETY: The only way to access/modify the pointers inside of `ListLinks` is via holding the +// associated `ListArc`. Since that type correctly implements `Send`, it is impossible to +// move this an instance of this type to a different thread if the pointees are `!Send`. +unsafe impl Send for ListLinks {} +// SAFETY: The type is opaque so immutable references to a ListLinks are useless. Therefore, it's +// okay to have immutable access to a ListLinks from several threads at once. +unsafe impl Sync for ListLinks {} + +impl ListLinks { + /// Creates a new initializer for this type. + pub fn new() -> impl PinInit { + // INVARIANT: Pin-init initializers can't be used on an existing `Arc`, so this value will + // not be constructed in an `Arc` that already has a `ListArc`. + ListLinks { + inner: Opaque::new(ListLinksFields { + prev: ptr::null_mut(), + next: ptr::null_mut(), + }), + } + } + + /// # Safety + /// + /// `me` must be dereferenceable. + #[inline] + unsafe fn fields(me: *mut Self) -> *mut ListLinksFields { + // SAFETY: The caller promises that the pointer is valid. + unsafe { Opaque::raw_get(ptr::addr_of!((*me).inner)) } + } + + /// # Safety + /// + /// `me` must be dereferenceable. + #[inline] + unsafe fn from_fields(me: *mut ListLinksFields) -> *mut Self { + me.cast() + } +} + +/// Similar to [`ListLinks`], but also contains a pointer to the full value. +/// +/// This type can be used instead of [`ListLinks`] to support lists with trait objects. +#[repr(C)] +pub struct ListLinksSelfPtr { + /// The `ListLinks` field inside this value. + /// + /// This is public so that it can be used with `impl_has_list_links!`. + pub inner: ListLinks, + // UnsafeCell is not enough here because we use `Opaque::uninit` as a dummy value, and + // `ptr::null()` doesn't work for `T: ?Sized`. + self_ptr: Opaque<*const T>, +} + +// SAFETY: The fields of a ListLinksSelfPtr can be moved across thread boundaries. +unsafe impl Send for ListLinksSelfPtr {} +// SAFETY: The type is opaque so immutable references to a ListLinksSelfPtr are useless. Therefore, +// it's okay to have immutable access to a ListLinks from several threads at once. +// +// Note that `inner` being a public field does not prevent this type from being opaque, since +// `inner` is a opaque type. +unsafe impl Sync for ListLinksSelfPtr {} + +impl ListLinksSelfPtr { + /// The offset from the [`ListLinks`] to the self pointer field. + pub const LIST_LINKS_SELF_PTR_OFFSET: usize = core::mem::offset_of!(Self, self_ptr); + + /// Creates a new initializer for this type. + pub fn new() -> impl PinInit { + // INVARIANT: Pin-init initializers can't be used on an existing `Arc`, so this value will + // not be constructed in an `Arc` that already has a `ListArc`. + Self { + inner: ListLinks { + inner: Opaque::new(ListLinksFields { + prev: ptr::null_mut(), + next: ptr::null_mut(), + }), + }, + self_ptr: Opaque::uninit(), + } + } +} + +impl, const ID: u64> List { + /// Creates a new empty list. + pub const fn new() -> Self { + Self { + first: ptr::null_mut(), + _ty: PhantomData, + } + } + + /// Returns whether this list is empty. + pub fn is_empty(&self) -> bool { + self.first.is_null() + } + + /// Add the provided item to the back of the list. + pub fn push_back(&mut self, item: ListArc) { + let raw_item = ListArc::into_raw(item); + // SAFETY: + // * We just got `raw_item` from a `ListArc`, so it's in an `Arc`. + // * Since we have ownership of the `ListArc`, `post_remove` must have been called after + // the most recent call to `prepare_to_insert`, if any. + // * We own the `ListArc`. + // * Removing items from this list is always done using `remove_internal_inner`, which + // calls `post_remove` before giving up ownership. + let list_links = unsafe { T::prepare_to_insert(raw_item) }; + // SAFETY: We have not yet called `post_remove`, so `list_links` is still valid. + let item = unsafe { ListLinks::fields(list_links) }; + + if self.first.is_null() { + self.first = item; + // SAFETY: The caller just gave us ownership of these fields. + // INVARIANT: A linked list with one item should be cyclic. + unsafe { + (*item).next = item; + (*item).prev = item; + } + } else { + let next = self.first; + // SAFETY: By the type invariant, this pointer is valid or null. We just checked that + // it's not null, so it must be valid. + let prev = unsafe { (*next).prev }; + // SAFETY: Pointers in a linked list are never dangling, and the caller just gave us + // ownership of the fields on `item`. + // INVARIANT: This correctly inserts `item` between `prev` and `next`. + unsafe { + (*item).next = next; + (*item).prev = prev; + (*prev).next = item; + (*next).prev = item; + } + } + } + + /// Add the provided item to the front of the list. + pub fn push_front(&mut self, item: ListArc) { + let raw_item = ListArc::into_raw(item); + // SAFETY: + // * We just got `raw_item` from a `ListArc`, so it's in an `Arc`. + // * If this requirement is violated, then the previous caller of `prepare_to_insert` + // violated the safety requirement that they can't give up ownership of the `ListArc` + // until they call `post_remove`. + // * We own the `ListArc`. + // * Removing items] from this list is always done using `remove_internal_inner`, which + // calls `post_remove` before giving up ownership. + let list_links = unsafe { T::prepare_to_insert(raw_item) }; + // SAFETY: We have not yet called `post_remove`, so `list_links` is still valid. + let item = unsafe { ListLinks::fields(list_links) }; + + if self.first.is_null() { + // SAFETY: The caller just gave us ownership of these fields. + // INVARIANT: A linked list with one item should be cyclic. + unsafe { + (*item).next = item; + (*item).prev = item; + } + } else { + let next = self.first; + // SAFETY: We just checked that `next` is non-null. + let prev = unsafe { (*next).prev }; + // SAFETY: Pointers in a linked list are never dangling, and the caller just gave us + // ownership of the fields on `item`. + // INVARIANT: This correctly inserts `item` between `prev` and `next`. + unsafe { + (*item).next = next; + (*item).prev = prev; + (*prev).next = item; + (*next).prev = item; + } + } + self.first = item; + } + + /// Removes the last item from this list. + pub fn pop_back(&mut self) -> Option> { + if self.first.is_null() { + return None; + } + + // SAFETY: We just checked that the list is not empty. + let last = unsafe { (*self.first).prev }; + // SAFETY: The last item of this list is in this list. + Some(unsafe { self.remove_internal(last) }) + } + + /// Removes the first item from this list. + pub fn pop_front(&mut self) -> Option> { + if self.first.is_null() { + return None; + } + + // SAFETY: The first item of this list is in this list. + Some(unsafe { self.remove_internal(self.first) }) + } + + /// Removes the provided item from this list and returns it. + /// + /// This returns `None` if the item is not in the list. (Note that by the safety requirements, + /// this means that the item is not in any list.) + /// + /// # Safety + /// + /// `item` must not be in a different linked list (with the same id). + pub unsafe fn remove(&mut self, item: &T) -> Option> { + let mut item = unsafe { ListLinks::fields(T::view_links(item)) }; + // SAFETY: The user provided a reference, and reference are never dangling. + // + // As for why this is not a data race, there are two cases: + // + // * If `item` is not in any list, then these fields are read-only and null. + // * If `item` is in this list, then we have exclusive access to these fields since we + // have a mutable reference to the list. + // + // In either case, there's no race. + let ListLinksFields { next, prev } = unsafe { *item }; + + debug_assert_eq!(next.is_null(), prev.is_null()); + if !next.is_null() { + // This is really a no-op, but this ensures that `item` is a raw pointer that was + // obtained without going through a pointer->reference->pointer conversion roundtrip. + // This ensures that the list is valid under the more restrictive strict provenance + // ruleset. + // + // SAFETY: We just checked that `next` is not null, and it's not dangling by the + // list invariants. + unsafe { + debug_assert_eq!(item, (*next).prev); + item = (*next).prev; + } + + // SAFETY: We just checked that `item` is in a list, so the caller guarantees that it + // is in this list. The pointers are in the right order. + Some(unsafe { self.remove_internal_inner(item, next, prev) }) + } else { + None + } + } + + /// Removes the provided item from the list. + /// + /// # Safety + /// + /// `item` must point at an item in this list. + unsafe fn remove_internal(&mut self, item: *mut ListLinksFields) -> ListArc { + // SAFETY: The caller promises that this pointer is not dangling, and there's no data race + // since we have a mutable reference to the list containing `item`. + let ListLinksFields { next, prev } = unsafe { *item }; + // SAFETY: The pointers are ok and in the right order. + unsafe { self.remove_internal_inner(item, next, prev) } + } + + /// Removes the provided item from the list. + /// + /// # Safety + /// + /// The `item` pointer must point at an item in this list, and we must have `(*item).next == + /// next` and `(*item).prev == prev`. + unsafe fn remove_internal_inner( + &mut self, + item: *mut ListLinksFields, + next: *mut ListLinksFields, + prev: *mut ListLinksFields, + ) -> ListArc { + // SAFETY: We have exclusive access to the pointers of items in the list, and the prev/next + // pointers are always valid for items in a list. + // + // INVARIANT: There are three cases: + // * If the list has at least three items, then after removing the item, `prev` and `next` + // will be next to each other. + // * If the list has two items, then the remaining item will point at itself. + // * If the list has one item, then `next == prev == item`, so these writes have no + // effect. The list remains unchanged and `item` is still in the list for now. + unsafe { + (*next).prev = prev; + (*prev).next = next; + } + // SAFETY: We have exclusive access to items in the list. + // INVARIANT: `item` is being removed, so the pointers should be null. + unsafe { + (*item).prev = ptr::null_mut(); + (*item).next = ptr::null_mut(); + } + // INVARIANT: There are three cases: + // * If `item` was not the first item, then `self.first` should remain unchanged. + // * If `item` was the first item and there is another item, then we just updated + // `prev->next` to `next`, which is the new first item, and setting `item->next` to null + // did not modify `prev->next`. + // * If `item` was the only item in the list, then `prev == item`, and we just set + // `item->next` to null, so this correctly sets `first` to null now that the list is + // empty. + if self.first == item { + // SAFETY: The `prev` pointer is the value that `item->prev` had when it was in this + // list, so it must be valid. There is no race since `prev` is still in the list and we + // still have exclusive access to the list. + self.first = unsafe { (*prev).next }; + } + + // SAFETY: `item` used to be in the list, so it is dereferenceable by the type invariants + // of `List`. + let list_links = unsafe { ListLinks::from_fields(item) }; + // SAFETY: Any pointer in the list originates from a `prepare_to_insert` call. + let raw_item = unsafe { T::post_remove(list_links) }; + // SAFETY: The above call to `post_remove` guarantees that we can recreate the `ListArc`. + unsafe { ListArc::from_raw(raw_item) } + } + + /// Moves all items from `other` into `self`. + /// + /// The items of `other` are added to the back of `self`, so the last item of `other` becomes + /// the last item of `self`. + pub fn push_all_back(&mut self, other: &mut List) { + // First, we insert the elements into `self`. At the end, we make `other` empty. + if self.is_empty() { + // INVARIANT: All of the elements in `other` become elements of `self`. + self.first = other.first; + } else if !other.is_empty() { + let other_first = other.first; + // SAFETY: The other list is not empty, so this pointer is valid. + let other_last = unsafe { (*other_first).prev }; + let self_first = self.first; + // SAFETY: The self list is not empty, so this pointer is valid. + let self_last = unsafe { (*self_first).prev }; + + // SAFETY: We have exclusive access to both lists, so we can update the pointers. + // INVARIANT: This correctly sets the pointers to merge both lists. We do not need to + // update `self.first` because the first element of `self` does not change. + unsafe { + (*self_first).prev = other_last; + (*other_last).next = self_first; + (*self_last).next = other_first; + (*other_first).prev = self_last; + } + } + + // INVARIANT: The other list is now empty, so update its pointer. + other.first = ptr::null_mut(); + } + + /// Returns a cursor to the first element of the list. + /// + /// If the list is empty, this returns `None`. + pub fn cursor_front(&mut self) -> Option> { + if self.first.is_null() { + None + } else { + Some(Cursor { + current: self.first, + list: self, + }) + } + } + + /// Creates an iterator over the list. + pub fn iter(&self) -> Iter<'_, T, ID> { + // INVARIANT: If the list is empty, both pointers are null. Otherwise, both pointers point + // at the first element of the same list. + Iter { + current: self.first, + stop: self.first, + _ty: PhantomData, + } + } +} + +impl, const ID: u64> Default for List { + fn default() -> Self { + List::new() + } +} + +impl, const ID: u64> Drop for List { + fn drop(&mut self) { + while let Some(item) = self.pop_front() { + drop(item); + } + } +} + +/// An iterator over a [`List`]. +/// +/// # Invariants +/// +/// * There must be a [`List`] that is immutably borrowed for the duration of `'a`. +/// * The `current` pointer is null or points at a value in that [`List`]. +/// * The `stop` pointer is equal to the `first` field of that [`List`]. +#[derive(Clone)] +pub struct Iter<'a, T: ?Sized + ListItem, const ID: u64 = 0> { + current: *mut ListLinksFields, + stop: *mut ListLinksFields, + _ty: PhantomData<&'a ListArc>, +} + +impl<'a, T: ?Sized + ListItem, const ID: u64> Iterator for Iter<'a, T, ID> { + type Item = ArcBorrow<'a, T>; + + fn next(&mut self) -> Option> { + if self.current.is_null() { + return None; + } + + let current = self.current; + + // SAFETY: We just checked that `current` is not null, so it is in a list, and hence not + // dangling. There's no race because the iterator holds an immutable borrow to the list. + let next = unsafe { (*current).next }; + // INVARIANT: If `current` was the last element of the list, then this updates it to null. + // Otherwise, we update it to the next element. + self.current = if next != self.stop { + next + } else { + ptr::null_mut() + }; + + // SAFETY: The `current` pointer points at a value in the list. + let item = unsafe { T::view_value(ListLinks::from_fields(current)) }; + // SAFETY: + // * All values in a list are stored in an `Arc`. + // * The value cannot be removed from the list for the duration of the lifetime annotated + // on the returned `ArcBorrow`, because removing it from the list would require mutable + // access to the list. However, the `ArcBorrow` is annotated with the iterator's + // lifetime, and the list is immutably borrowed for that lifetime. + // * Values in a list never have a `UniqueArc` reference. + Some(unsafe { ArcBorrow::from_raw(item) }) + } +} + +/// A cursor into a [`List`]. +/// +/// # Invariants +/// +/// The `current` pointer points a value in `list`. +pub struct Cursor<'a, T: ?Sized + ListItem, const ID: u64 = 0> { + current: *mut ListLinksFields, + list: &'a mut List, +} + +impl<'a, T: ?Sized + ListItem, const ID: u64> Cursor<'a, T, ID> { + /// Access the current element of this cursor. + pub fn current(&self) -> ArcBorrow<'_, T> { + // SAFETY: The `current` pointer points a value in the list. + let me = unsafe { T::view_value(ListLinks::from_fields(self.current)) }; + // SAFETY: + // * All values in a list are stored in an `Arc`. + // * The value cannot be removed from the list for the duration of the lifetime annotated + // on the returned `ArcBorrow`, because removing it from the list would require mutable + // access to the cursor or the list. However, the `ArcBorrow` holds an immutable borrow + // on the cursor, which in turn holds a mutable borrow on the list, so any such + // mutable access requires first releasing the immutable borrow on the cursor. + // * Values in a list never have a `UniqueArc` reference, because the list has a `ListArc` + // reference, and `UniqueArc` references must be unique. + unsafe { ArcBorrow::from_raw(me) } + } + + /// Move the cursor to the next element. + pub fn next(self) -> Option> { + // SAFETY: The `current` field is always in a list. + let next = unsafe { (*self.current).next }; + + if next == self.list.first { + None + } else { + // INVARIANT: Since `self.current` is in the `list`, its `next` pointer is also in the + // `list`. + Some(Cursor { + current: next, + list: self.list, + }) + } + } + + /// Move the cursor to the previous element. + pub fn prev(self) -> Option> { + // SAFETY: The `current` field is always in a list. + let prev = unsafe { (*self.current).prev }; + + if self.current == self.list.first { + None + } else { + // INVARIANT: Since `self.current` is in the `list`, its `prev` pointer is also in the + // `list`. + Some(Cursor { + current: prev, + list: self.list, + }) + } + } + + /// Remove the current element from the list. + pub fn remove(self) -> ListArc { + // SAFETY: The `current` pointer always points at a member of the list. + unsafe { self.list.remove_internal(self.current) } + } +} + +impl<'a, T: ?Sized + ListItem, const ID: u64> FusedIterator for Iter<'a, T, ID> {} + +impl<'a, T: ?Sized + ListItem, const ID: u64> IntoIterator for &'a List { + type IntoIter = Iter<'a, T, ID>; + type Item = ArcBorrow<'a, T>; + + fn into_iter(self) -> Iter<'a, T, ID> { + self.iter() + } +} + +/// An owning iterator into a [`List`]. +pub struct IntoIter, const ID: u64 = 0> { + list: List, +} + +impl, const ID: u64> Iterator for IntoIter { + type Item = ListArc; + + fn next(&mut self) -> Option> { + self.list.pop_front() + } +} + +impl, const ID: u64> FusedIterator for IntoIter {} + +impl, const ID: u64> DoubleEndedIterator for IntoIter { + fn next_back(&mut self) -> Option> { + self.list.pop_back() + } +} + +impl, const ID: u64> IntoIterator for List { + type IntoIter = IntoIter; + type Item = ListArc; + + fn into_iter(self) -> IntoIter { + IntoIter { list: self } + } +} diff --git a/rust/kernel/list/arc.rs b/rust/kernel/list/arc.rs new file mode 100644 index 000000000000..d801b9dc6291 --- /dev/null +++ b/rust/kernel/list/arc.rs @@ -0,0 +1,521 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2024 Google LLC. + +//! A wrapper around `Arc` for linked lists. + +use crate::alloc::{AllocError, Flags}; +use crate::prelude::*; +use crate::sync::{Arc, ArcBorrow, UniqueArc}; +use core::marker::{PhantomPinned, Unsize}; +use core::ops::Deref; +use core::pin::Pin; +use core::sync::atomic::{AtomicBool, Ordering}; + +/// Declares that this type has some way to ensure that there is exactly one `ListArc` instance for +/// this id. +/// +/// Types that implement this trait should include some kind of logic for keeping track of whether +/// a [`ListArc`] exists or not. We refer to this logic as "the tracking inside `T`". +/// +/// We allow the case where the tracking inside `T` thinks that a [`ListArc`] exists, but actually, +/// there isn't a [`ListArc`]. However, we do not allow the opposite situation where a [`ListArc`] +/// exists, but the tracking thinks it doesn't. This is because the former can at most result in us +/// failing to create a [`ListArc`] when the operation could succeed, whereas the latter can result +/// in the creation of two [`ListArc`] references. Only the latter situation can lead to memory +/// safety issues. +/// +/// A consequence of the above is that you may implement the tracking inside `T` by not actually +/// keeping track of anything. To do this, you always claim that a [`ListArc`] exists, even if +/// there isn't one. This implementation is allowed by the above rule, but it means that +/// [`ListArc`] references can only be created if you have ownership of *all* references to the +/// refcounted object, as you otherwise have no way of knowing whether a [`ListArc`] exists. +pub trait ListArcSafe { + /// Informs the tracking inside this type that it now has a [`ListArc`] reference. + /// + /// This method may be called even if the tracking inside this type thinks that a `ListArc` + /// reference exists. (But only if that's not actually the case.) + /// + /// # Safety + /// + /// Must not be called if a [`ListArc`] already exist for this value. + unsafe fn on_create_list_arc_from_unique(self: Pin<&mut Self>); + + /// Informs the tracking inside this type that there is no [`ListArc`] reference anymore. + /// + /// # Safety + /// + /// Must only be called if there is no [`ListArc`] reference, but the tracking thinks there is. + unsafe fn on_drop_list_arc(&self); +} + +/// Declares that this type is able to safely attempt to create `ListArc`s at any time. +/// +/// # Safety +/// +/// The guarantees of `try_new_list_arc` must be upheld. +pub unsafe trait TryNewListArc: ListArcSafe { + /// Attempts to convert an `Arc` into an `ListArc`. Returns `true` if the + /// conversion was successful. + /// + /// This method should not be called directly. Use [`ListArc::try_from_arc`] instead. + /// + /// # Guarantees + /// + /// If this call returns `true`, then there is no [`ListArc`] pointing to this value. + /// Additionally, this call will have transitioned the tracking inside `Self` from not thinking + /// that a [`ListArc`] exists, to thinking that a [`ListArc`] exists. + fn try_new_list_arc(&self) -> bool; +} + +/// Declares that this type supports [`ListArc`]. +/// +/// This macro supports a few different strategies for implementing the tracking inside the type: +/// +/// * The `untracked` strategy does not actually keep track of whether a [`ListArc`] exists. When +/// using this strategy, the only way to create a [`ListArc`] is using a [`UniqueArc`]. +/// * The `tracked_by` strategy defers the tracking to a field of the struct. The user much specify +/// which field to defer the tracking to. The field must implement [`ListArcSafe`]. If the field +/// implements [`TryNewListArc`], then the type will also implement [`TryNewListArc`]. +/// +/// The `tracked_by` strategy is usually used by deferring to a field of type +/// [`AtomicTracker`]. However, it is also possible to defer the tracking to another struct +/// using also using this macro. +#[macro_export] +macro_rules! impl_list_arc_safe { + (impl$({$($generics:tt)*})? ListArcSafe<$num:tt> for $t:ty { untracked; } $($rest:tt)*) => { + impl$(<$($generics)*>)? $crate::list::ListArcSafe<$num> for $t { + unsafe fn on_create_list_arc_from_unique(self: ::core::pin::Pin<&mut Self>) {} + unsafe fn on_drop_list_arc(&self) {} + } + $crate::list::impl_list_arc_safe! { $($rest)* } + }; + + (impl$({$($generics:tt)*})? ListArcSafe<$num:tt> for $t:ty { + tracked_by $field:ident : $fty:ty; + } $($rest:tt)*) => { + impl$(<$($generics)*>)? $crate::list::ListArcSafe<$num> for $t { + unsafe fn on_create_list_arc_from_unique(self: ::core::pin::Pin<&mut Self>) { + $crate::assert_pinned!($t, $field, $fty, inline); + + // SAFETY: This field is structurally pinned as per the above assertion. + let field = unsafe { + ::core::pin::Pin::map_unchecked_mut(self, |me| &mut me.$field) + }; + // SAFETY: The caller promises that there is no `ListArc`. + unsafe { + <$fty as $crate::list::ListArcSafe<$num>>::on_create_list_arc_from_unique(field) + }; + } + unsafe fn on_drop_list_arc(&self) { + // SAFETY: The caller promises that there is no `ListArc` reference, and also + // promises that the tracking thinks there is a `ListArc` reference. + unsafe { <$fty as $crate::list::ListArcSafe<$num>>::on_drop_list_arc(&self.$field) }; + } + } + unsafe impl$(<$($generics)*>)? $crate::list::TryNewListArc<$num> for $t + where + $fty: TryNewListArc<$num>, + { + fn try_new_list_arc(&self) -> bool { + <$fty as $crate::list::TryNewListArc<$num>>::try_new_list_arc(&self.$field) + } + } + $crate::list::impl_list_arc_safe! { $($rest)* } + }; + + () => {}; +} +pub use impl_list_arc_safe; + +/// A wrapper around [`Arc`] that's guaranteed unique for the given id. +/// +/// The `ListArc` type can be thought of as a special reference to a refcounted object that owns the +/// permission to manipulate the `next`/`prev` pointers stored in the refcounted object. By ensuring +/// that each object has only one `ListArc` reference, the owner of that reference is assured +/// exclusive access to the `next`/`prev` pointers. When a `ListArc` is inserted into a [`List`], +/// the [`List`] takes ownership of the `ListArc` reference. +/// +/// There are various strategies to ensuring that a value has only one `ListArc` reference. The +/// simplest is to convert a [`UniqueArc`] into a `ListArc`. However, the refcounted object could +/// also keep track of whether a `ListArc` exists using a boolean, which could allow for the +/// creation of new `ListArc` references from an [`Arc`] reference. Whatever strategy is used, the +/// relevant tracking is referred to as "the tracking inside `T`", and the [`ListArcSafe`] trait +/// (and its subtraits) are used to update the tracking when a `ListArc` is created or destroyed. +/// +/// Note that we allow the case where the tracking inside `T` thinks that a `ListArc` exists, but +/// actually, there isn't a `ListArc`. However, we do not allow the opposite situation where a +/// `ListArc` exists, but the tracking thinks it doesn't. This is because the former can at most +/// result in us failing to create a `ListArc` when the operation could succeed, whereas the latter +/// can result in the creation of two `ListArc` references. +/// +/// While this `ListArc` is unique for the given id, there still might exist normal `Arc` +/// references to the object. +/// +/// # Invariants +/// +/// * Each reference counted object has at most one `ListArc` for each value of `ID`. +/// * The tracking inside `T` is aware that a `ListArc` reference exists. +/// +/// [`List`]: crate::list::List +#[repr(transparent)] +pub struct ListArc +where + T: ListArcSafe + ?Sized, +{ + arc: Arc, +} + +impl, const ID: u64> ListArc { + /// Constructs a new reference counted instance of `T`. + #[inline] + pub fn new(contents: T, flags: Flags) -> Result { + Ok(Self::from(UniqueArc::new(contents, flags)?)) + } + + /// Use the given initializer to in-place initialize a `T`. + /// + /// If `T: !Unpin` it will not be able to move afterwards. + // We don't implement `InPlaceInit` because `ListArc` is implicitly pinned. This is similar to + // what we do for `Arc`. + #[inline] + pub fn pin_init(init: impl PinInit, flags: Flags) -> Result + where + E: From, + { + Ok(Self::from(UniqueArc::try_pin_init(init, flags)?)) + } + + /// Use the given initializer to in-place initialize a `T`. + /// + /// This is equivalent to [`ListArc::pin_init`], since a [`ListArc`] is always pinned. + #[inline] + pub fn init(init: impl Init, flags: Flags) -> Result + where + E: From, + { + Ok(Self::from(UniqueArc::try_init(init, flags)?)) + } +} + +impl From> for ListArc +where + T: ListArcSafe + ?Sized, +{ + /// Convert a [`UniqueArc`] into a [`ListArc`]. + #[inline] + fn from(unique: UniqueArc) -> Self { + Self::from(Pin::from(unique)) + } +} + +impl From>> for ListArc +where + T: ListArcSafe + ?Sized, +{ + /// Convert a pinned [`UniqueArc`] into a [`ListArc`]. + #[inline] + fn from(mut unique: Pin>) -> Self { + // SAFETY: We have a `UniqueArc`, so there is no `ListArc`. + unsafe { T::on_create_list_arc_from_unique(unique.as_mut()) }; + let arc = Arc::from(unique); + // SAFETY: We just called `on_create_list_arc_from_unique` on an arc without a `ListArc`, + // so we can create a `ListArc`. + unsafe { Self::transmute_from_arc(arc) } + } +} + +impl ListArc +where + T: ListArcSafe + ?Sized, +{ + /// Creates two `ListArc`s from a [`UniqueArc`]. + /// + /// The two ids must be different. + #[inline] + pub fn pair_from_unique(unique: UniqueArc) -> (Self, ListArc) + where + T: ListArcSafe, + { + Self::pair_from_pin_unique(Pin::from(unique)) + } + + /// Creates two `ListArc`s from a pinned [`UniqueArc`]. + /// + /// The two ids must be different. + #[inline] + pub fn pair_from_pin_unique( + mut unique: Pin>, + ) -> (Self, ListArc) + where + T: ListArcSafe, + { + build_assert!(ID != ID2); + + // SAFETY: We have a `UniqueArc`, so there is no `ListArc`. + unsafe { >::on_create_list_arc_from_unique(unique.as_mut()) }; + // SAFETY: We have a `UniqueArc`, so there is no `ListArc`. + unsafe { >::on_create_list_arc_from_unique(unique.as_mut()) }; + + let arc1 = Arc::from(unique); + let arc2 = Arc::clone(&arc1); + + // SAFETY: We just called `on_create_list_arc_from_unique` on an arc without a `ListArc` + // for both IDs (which are different), so we can create two `ListArc`s. + unsafe { + ( + Self::transmute_from_arc(arc1), + ListArc::transmute_from_arc(arc2), + ) + } + } + + /// Try to create a new `ListArc`. + /// + /// This fails if this value already has a `ListArc`. + pub fn try_from_arc(arc: Arc) -> Result> + where + T: TryNewListArc, + { + if arc.try_new_list_arc() { + // SAFETY: The `try_new_list_arc` method returned true, so we made the tracking think + // that a `ListArc` exists. This lets us create a `ListArc`. + Ok(unsafe { Self::transmute_from_arc(arc) }) + } else { + Err(arc) + } + } + + /// Try to create a new `ListArc`. + /// + /// This fails if this value already has a `ListArc`. + pub fn try_from_arc_borrow(arc: ArcBorrow<'_, T>) -> Option + where + T: TryNewListArc, + { + if arc.try_new_list_arc() { + // SAFETY: The `try_new_list_arc` method returned true, so we made the tracking think + // that a `ListArc` exists. This lets us create a `ListArc`. + Some(unsafe { Self::transmute_from_arc(Arc::from(arc)) }) + } else { + None + } + } + + /// Try to create a new `ListArc`. + /// + /// If it's not possible to create a new `ListArc`, then the `Arc` is dropped. This will never + /// run the destructor of the value. + pub fn try_from_arc_or_drop(arc: Arc) -> Option + where + T: TryNewListArc, + { + match Self::try_from_arc(arc) { + Ok(list_arc) => Some(list_arc), + Err(arc) => Arc::into_unique_or_drop(arc).map(Self::from), + } + } + + /// Transmutes an [`Arc`] into a `ListArc` without updating the tracking inside `T`. + /// + /// # Safety + /// + /// * The value must not already have a `ListArc` reference. + /// * The tracking inside `T` must think that there is a `ListArc` reference. + #[inline] + unsafe fn transmute_from_arc(arc: Arc) -> Self { + // INVARIANT: By the safety requirements, the invariants on `ListArc` are satisfied. + Self { arc } + } + + /// Transmutes a `ListArc` into an [`Arc`] without updating the tracking inside `T`. + /// + /// After this call, the tracking inside `T` will still think that there is a `ListArc` + /// reference. + #[inline] + fn transmute_to_arc(self) -> Arc { + // Use a transmute to skip destructor. + // + // SAFETY: ListArc is repr(transparent). + unsafe { core::mem::transmute(self) } + } + + /// Convert ownership of this `ListArc` into a raw pointer. + /// + /// The returned pointer is indistinguishable from pointers returned by [`Arc::into_raw`]. The + /// tracking inside `T` will still think that a `ListArc` exists after this call. + #[inline] + pub fn into_raw(self) -> *const T { + Arc::into_raw(Self::transmute_to_arc(self)) + } + + /// Take ownership of the `ListArc` from a raw pointer. + /// + /// # Safety + /// + /// * `ptr` must satisfy the safety requirements of [`Arc::from_raw`]. + /// * The value must not already have a `ListArc` reference. + /// * The tracking inside `T` must think that there is a `ListArc` reference. + #[inline] + pub unsafe fn from_raw(ptr: *const T) -> Self { + // SAFETY: The pointer satisfies the safety requirements for `Arc::from_raw`. + let arc = unsafe { Arc::from_raw(ptr) }; + // SAFETY: The value doesn't already have a `ListArc` reference, but the tracking thinks it + // does. + unsafe { Self::transmute_from_arc(arc) } + } + + /// Converts the `ListArc` into an [`Arc`]. + #[inline] + pub fn into_arc(self) -> Arc { + let arc = Self::transmute_to_arc(self); + // SAFETY: There is no longer a `ListArc`, but the tracking thinks there is. + unsafe { T::on_drop_list_arc(&arc) }; + arc + } + + /// Clone a `ListArc` into an [`Arc`]. + #[inline] + pub fn clone_arc(&self) -> Arc { + self.arc.clone() + } + + /// Returns a reference to an [`Arc`] from the given [`ListArc`]. + /// + /// This is useful when the argument of a function call is an [`&Arc`] (e.g., in a method + /// receiver), but we have a [`ListArc`] instead. + /// + /// [`&Arc`]: Arc + #[inline] + pub fn as_arc(&self) -> &Arc { + &self.arc + } + + /// Returns an [`ArcBorrow`] from the given [`ListArc`]. + /// + /// This is useful when the argument of a function call is an [`ArcBorrow`] (e.g., in a method + /// receiver), but we have an [`Arc`] instead. Getting an [`ArcBorrow`] is free when optimised. + #[inline] + pub fn as_arc_borrow(&self) -> ArcBorrow<'_, T> { + self.arc.as_arc_borrow() + } + + /// Compare whether two [`ListArc`] pointers reference the same underlying object. + #[inline] + pub fn ptr_eq(this: &Self, other: &Self) -> bool { + Arc::ptr_eq(&this.arc, &other.arc) + } +} + +impl Deref for ListArc +where + T: ListArcSafe + ?Sized, +{ + type Target = T; + + #[inline] + fn deref(&self) -> &Self::Target { + self.arc.deref() + } +} + +impl Drop for ListArc +where + T: ListArcSafe + ?Sized, +{ + #[inline] + fn drop(&mut self) { + // SAFETY: There is no longer a `ListArc`, but the tracking thinks there is by the type + // invariants on `Self`. + unsafe { T::on_drop_list_arc(&self.arc) }; + } +} + +impl AsRef> for ListArc +where + T: ListArcSafe + ?Sized, +{ + #[inline] + fn as_ref(&self) -> &Arc { + self.as_arc() + } +} + +// This is to allow [`ListArc`] (and variants) to be used as the type of `self`. +impl core::ops::Receiver for ListArc where T: ListArcSafe + ?Sized {} + +// This is to allow coercion from `ListArc` to `ListArc` if `T` can be converted to the +// dynamically-sized type (DST) `U`. +impl core::ops::CoerceUnsized> for ListArc +where + T: ListArcSafe + Unsize + ?Sized, + U: ListArcSafe + ?Sized, +{ +} + +// This is to allow `ListArc` to be dispatched on when `ListArc` can be coerced into +// `ListArc`. +impl core::ops::DispatchFromDyn> for ListArc +where + T: ListArcSafe + Unsize + ?Sized, + U: ListArcSafe + ?Sized, +{ +} + +/// A utility for tracking whether a [`ListArc`] exists using an atomic. +/// +/// # Invariant +/// +/// If the boolean is `false`, then there is no [`ListArc`] for this value. +#[repr(transparent)] +pub struct AtomicTracker { + inner: AtomicBool, + // This value needs to be pinned to justify the INVARIANT: comment in `AtomicTracker::new`. + _pin: PhantomPinned, +} + +impl AtomicTracker { + /// Creates a new initializer for this type. + pub fn new() -> impl PinInit { + // INVARIANT: Pin-init initializers can't be used on an existing `Arc`, so this value will + // not be constructed in an `Arc` that already has a `ListArc`. + Self { + inner: AtomicBool::new(false), + _pin: PhantomPinned, + } + } + + fn project_inner(self: Pin<&mut Self>) -> &mut AtomicBool { + // SAFETY: The `inner` field is not structurally pinned, so we may obtain a mutable + // reference to it even if we only have a pinned reference to `self`. + unsafe { &mut Pin::into_inner_unchecked(self).inner } + } +} + +impl ListArcSafe for AtomicTracker { + unsafe fn on_create_list_arc_from_unique(self: Pin<&mut Self>) { + // INVARIANT: We just created a ListArc, so the boolean should be true. + *self.project_inner().get_mut() = true; + } + + unsafe fn on_drop_list_arc(&self) { + // INVARIANT: We just dropped a ListArc, so the boolean should be false. + self.inner.store(false, Ordering::Release); + } +} + +// SAFETY: If this method returns `true`, then by the type invariant there is no `ListArc` before +// this call, so it is okay to create a new `ListArc`. +// +// The acquire ordering will synchronize with the release store from the destruction of any +// previous `ListArc`, so if there was a previous `ListArc`, then the destruction of the previous +// `ListArc` happens-before the creation of the new `ListArc`. +unsafe impl TryNewListArc for AtomicTracker { + fn try_new_list_arc(&self) -> bool { + // INVARIANT: If this method returns true, then the boolean used to be false, and is no + // longer false, so it is okay for the caller to create a new [`ListArc`]. + self.inner + .compare_exchange(false, true, Ordering::Acquire, Ordering::Relaxed) + .is_ok() + } +} diff --git a/rust/kernel/list/arc_field.rs b/rust/kernel/list/arc_field.rs new file mode 100644 index 000000000000..2330f673427a --- /dev/null +++ b/rust/kernel/list/arc_field.rs @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2024 Google LLC. + +//! A field that is exclusively owned by a [`ListArc`]. +//! +//! This can be used to have reference counted struct where one of the reference counted pointers +//! has exclusive access to a field of the struct. +//! +//! [`ListArc`]: crate::list::ListArc + +use core::cell::UnsafeCell; + +/// A field owned by a specific [`ListArc`]. +/// +/// [`ListArc`]: crate::list::ListArc +pub struct ListArcField { + value: UnsafeCell, +} + +// SAFETY: If the inner type is thread-safe, then it's also okay for `ListArc` to be thread-safe. +unsafe impl Send for ListArcField {} +// SAFETY: If the inner type is thread-safe, then it's also okay for `ListArc` to be thread-safe. +unsafe impl Sync for ListArcField {} + +impl ListArcField { + /// Creates a new `ListArcField`. + pub fn new(value: T) -> Self { + Self { + value: UnsafeCell::new(value), + } + } + + /// Access the value when we have exclusive access to the `ListArcField`. + /// + /// This allows access to the field using an `UniqueArc` instead of a `ListArc`. + pub fn get_mut(&mut self) -> &mut T { + self.value.get_mut() + } + + /// Unsafely assert that you have shared access to the `ListArc` for this field. + /// + /// # Safety + /// + /// The caller must have shared access to the `ListArc` containing the struct with this + /// field for the duration of the returned reference. + pub unsafe fn assert_ref(&self) -> &T { + // SAFETY: The caller has shared access to the `ListArc`, so they also have shared access + // to this field. + unsafe { &*self.value.get() } + } + + /// Unsafely assert that you have mutable access to the `ListArc` for this field. + /// + /// # Safety + /// + /// The caller must have mutable access to the `ListArc` containing the struct with this + /// field for the duration of the returned reference. + #[allow(clippy::mut_from_ref)] + pub unsafe fn assert_mut(&self) -> &mut T { + // SAFETY: The caller has exclusive access to the `ListArc`, so they also have exclusive + // access to this field. + unsafe { &mut *self.value.get() } + } +} + +/// Defines getters for a [`ListArcField`]. +#[macro_export] +macro_rules! define_list_arc_field_getter { + ($pub:vis fn $name:ident(&self $(<$id:tt>)?) -> &$typ:ty { $field:ident } + $($rest:tt)* + ) => { + $pub fn $name<'a>(self: &'a $crate::list::ListArc) -> &'a $typ { + let field = &(&**self).$field; + // SAFETY: We have a shared reference to the `ListArc`. + unsafe { $crate::list::ListArcField::<$typ $(, $id)?>::assert_ref(field) } + } + + $crate::list::define_list_arc_field_getter!($($rest)*); + }; + + ($pub:vis fn $name:ident(&mut self $(<$id:tt>)?) -> &mut $typ:ty { $field:ident } + $($rest:tt)* + ) => { + $pub fn $name<'a>(self: &'a mut $crate::list::ListArc) -> &'a mut $typ { + let field = &(&**self).$field; + // SAFETY: We have a mutable reference to the `ListArc`. + unsafe { $crate::list::ListArcField::<$typ $(, $id)?>::assert_mut(field) } + } + + $crate::list::define_list_arc_field_getter!($($rest)*); + }; + + () => {}; +} +pub use define_list_arc_field_getter; diff --git a/rust/kernel/list/impl_list_item_mod.rs b/rust/kernel/list/impl_list_item_mod.rs new file mode 100644 index 000000000000..a0438537cee1 --- /dev/null +++ b/rust/kernel/list/impl_list_item_mod.rs @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Copyright (C) 2024 Google LLC. + +//! Helpers for implementing list traits safely. + +use crate::list::ListLinks; + +/// Declares that this type has a `ListLinks` field at a fixed offset. +/// +/// This trait is only used to help implement `ListItem` safely. If `ListItem` is implemented +/// manually, then this trait is not needed. Use the [`impl_has_list_links!`] macro to implement +/// this trait. +/// +/// # Safety +/// +/// All values of this type must have a `ListLinks` field at the given offset. +/// +/// The behavior of `raw_get_list_links` must not be changed. +pub unsafe trait HasListLinks { + /// The offset of the `ListLinks` field. + const OFFSET: usize; + + /// Returns a pointer to the [`ListLinks`] field. + /// + /// # Safety + /// + /// The provided pointer must point at a valid struct of type `Self`. + /// + /// [`ListLinks`]: ListLinks + // We don't really need this method, but it's necessary for the implementation of + // `impl_has_list_links!` to be correct. + #[inline] + unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut ListLinks { + // SAFETY: The caller promises that the pointer is valid. The implementer promises that the + // `OFFSET` constant is correct. + unsafe { (ptr as *mut u8).add(Self::OFFSET) as *mut ListLinks } + } +} + +/// Implements the [`HasListLinks`] trait for the given type. +#[macro_export] +macro_rules! impl_has_list_links { + ($(impl$(<$($implarg:ident),*>)? + HasListLinks$(<$id:tt>)? + for $self:ident $(<$($selfarg:ty),*>)? + { self$(.$field:ident)* } + )*) => {$( + // SAFETY: The implementation of `raw_get_list_links` only compiles if the field has the + // right type. + // + // The behavior of `raw_get_list_links` is not changed since the `addr_of_mut!` macro is + // equivalent to the pointer offset operation in the trait definition. + unsafe impl$(<$($implarg),*>)? $crate::list::HasListLinks$(<$id>)? for + $self $(<$($selfarg),*>)? + { + const OFFSET: usize = ::core::mem::offset_of!(Self, $($field).*) as usize; + + #[inline] + unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut $crate::list::ListLinks$(<$id>)? { + // SAFETY: The caller promises that the pointer is not dangling. We know that this + // expression doesn't follow any pointers, as the `offset_of!` invocation above + // would otherwise not compile. + unsafe { ::core::ptr::addr_of_mut!((*ptr)$(.$field)*) } + } + } + )*}; +} +pub use impl_has_list_links; + +/// Declares that the `ListLinks` field in this struct is inside a `ListLinksSelfPtr`. +/// +/// # Safety +/// +/// The `ListLinks` field of this struct at the offset `HasListLinks::OFFSET` must be +/// inside a `ListLinksSelfPtr`. +pub unsafe trait HasSelfPtr +where + Self: HasListLinks, +{ +} + +/// Implements the [`HasListLinks`] and [`HasSelfPtr`] traits for the given type. +#[macro_export] +macro_rules! impl_has_list_links_self_ptr { + ($(impl$({$($implarg:tt)*})? + HasSelfPtr<$item_type:ty $(, $id:tt)?> + for $self:ident $(<$($selfarg:ty),*>)? + { self.$field:ident } + )*) => {$( + // SAFETY: The implementation of `raw_get_list_links` only compiles if the field has the + // right type. + unsafe impl$(<$($implarg)*>)? $crate::list::HasSelfPtr<$item_type $(, $id)?> for + $self $(<$($selfarg),*>)? + {} + + unsafe impl$(<$($implarg)*>)? $crate::list::HasListLinks$(<$id>)? for + $self $(<$($selfarg),*>)? + { + const OFFSET: usize = ::core::mem::offset_of!(Self, $field) as usize; + + #[inline] + unsafe fn raw_get_list_links(ptr: *mut Self) -> *mut $crate::list::ListLinks$(<$id>)? { + // SAFETY: The caller promises that the pointer is not dangling. + let ptr: *mut $crate::list::ListLinksSelfPtr<$item_type $(, $id)?> = + unsafe { ::core::ptr::addr_of_mut!((*ptr).$field) }; + ptr.cast() + } + } + )*}; +} +pub use impl_has_list_links_self_ptr; + +/// Implements the [`ListItem`] trait for the given type. +/// +/// Requires that the type implements [`HasListLinks`]. Use the [`impl_has_list_links!`] macro to +/// implement that trait. +/// +/// [`ListItem`]: crate::list::ListItem +#[macro_export] +macro_rules! impl_list_item { + ( + $(impl$({$($generics:tt)*})? ListItem<$num:tt> for $t:ty { + using ListLinks; + })* + ) => {$( + // SAFETY: See GUARANTEES comment on each method. + unsafe impl$(<$($generics)*>)? $crate::list::ListItem<$num> for $t { + // GUARANTEES: + // * This returns the same pointer as `prepare_to_insert` because `prepare_to_insert` + // is implemented in terms of `view_links`. + // * By the type invariants of `ListLinks`, the `ListLinks` has two null pointers when + // this value is not in a list. + unsafe fn view_links(me: *const Self) -> *mut $crate::list::ListLinks<$num> { + // SAFETY: The caller guarantees that `me` points at a valid value of type `Self`. + unsafe { + >::raw_get_list_links(me.cast_mut()) + } + } + + // GUARANTEES: + // * `me` originates from the most recent call to `prepare_to_insert`, which just added + // `offset` to the pointer passed to `prepare_to_insert`. This method subtracts + // `offset` from `me` so it returns the pointer originally passed to + // `prepare_to_insert`. + // * The pointer remains valid until the next call to `post_remove` because the caller + // of the most recent call to `prepare_to_insert` promised to retain ownership of the + // `ListArc` containing `Self` until the next call to `post_remove`. The value cannot + // be destroyed while a `ListArc` reference exists. + unsafe fn view_value(me: *mut $crate::list::ListLinks<$num>) -> *const Self { + let offset = >::OFFSET; + // SAFETY: `me` originates from the most recent call to `prepare_to_insert`, so it + // points at the field at offset `offset` in a value of type `Self`. Thus, + // subtracting `offset` from `me` is still in-bounds of the allocation. + unsafe { (me as *const u8).sub(offset) as *const Self } + } + + // GUARANTEES: + // This implementation of `ListItem` will not give out exclusive access to the same + // `ListLinks` several times because calls to `prepare_to_insert` and `post_remove` + // must alternate and exclusive access is given up when `post_remove` is called. + // + // Other invocations of `impl_list_item!` also cannot give out exclusive access to the + // same `ListLinks` because you can only implement `ListItem` once for each value of + // `ID`, and the `ListLinks` fields only work with the specified `ID`. + unsafe fn prepare_to_insert(me: *const Self) -> *mut $crate::list::ListLinks<$num> { + // SAFETY: The caller promises that `me` points at a valid value. + unsafe { >::view_links(me) } + } + + // GUARANTEES: + // * `me` originates from the most recent call to `prepare_to_insert`, which just added + // `offset` to the pointer passed to `prepare_to_insert`. This method subtracts + // `offset` from `me` so it returns the pointer originally passed to + // `prepare_to_insert`. + unsafe fn post_remove(me: *mut $crate::list::ListLinks<$num>) -> *const Self { + let offset = >::OFFSET; + // SAFETY: `me` originates from the most recent call to `prepare_to_insert`, so it + // points at the field at offset `offset` in a value of type `Self`. Thus, + // subtracting `offset` from `me` is still in-bounds of the allocation. + unsafe { (me as *const u8).sub(offset) as *const Self } + } + } + )*}; + + ( + $(impl$({$($generics:tt)*})? ListItem<$num:tt> for $t:ty { + using ListLinksSelfPtr; + })* + ) => {$( + // SAFETY: See GUARANTEES comment on each method. + unsafe impl$(<$($generics)*>)? $crate::list::ListItem<$num> for $t { + // GUARANTEES: + // This implementation of `ListItem` will not give out exclusive access to the same + // `ListLinks` several times because calls to `prepare_to_insert` and `post_remove` + // must alternate and exclusive access is given up when `post_remove` is called. + // + // Other invocations of `impl_list_item!` also cannot give out exclusive access to the + // same `ListLinks` because you can only implement `ListItem` once for each value of + // `ID`, and the `ListLinks` fields only work with the specified `ID`. + unsafe fn prepare_to_insert(me: *const Self) -> *mut $crate::list::ListLinks<$num> { + // SAFETY: The caller promises that `me` points at a valid value of type `Self`. + let links_field = unsafe { >::view_links(me) }; + + let spoff = $crate::list::ListLinksSelfPtr::::LIST_LINKS_SELF_PTR_OFFSET; + // Goes via the offset as the field is private. + // + // SAFETY: The constant is equal to `offset_of!(ListLinksSelfPtr, self_ptr)`, so + // the pointer stays in bounds of the allocation. + let self_ptr = unsafe { (links_field as *const u8).add(spoff) } + as *const $crate::types::Opaque<*const Self>; + let cell_inner = $crate::types::Opaque::raw_get(self_ptr); + + // SAFETY: This value is not accessed in any other places than `prepare_to_insert`, + // `post_remove`, or `view_value`. By the safety requirements of those methods, + // none of these three methods may be called in parallel with this call to + // `prepare_to_insert`, so this write will not race with any other access to the + // value. + unsafe { ::core::ptr::write(cell_inner, me) }; + + links_field + } + + // GUARANTEES: + // * This returns the same pointer as `prepare_to_insert` because `prepare_to_insert` + // returns the return value of `view_links`. + // * By the type invariants of `ListLinks`, the `ListLinks` has two null pointers when + // this value is not in a list. + unsafe fn view_links(me: *const Self) -> *mut $crate::list::ListLinks<$num> { + // SAFETY: The caller promises that `me` points at a valid value of type `Self`. + unsafe { >::raw_get_list_links(me.cast_mut()) } + } + + // This function is also used as the implementation of `post_remove`, so the caller + // may choose to satisfy the safety requirements of `post_remove` instead of the safety + // requirements for `view_value`. + // + // GUARANTEES: (always) + // * This returns the same pointer as the one passed to the most recent call to + // `prepare_to_insert` since that call wrote that pointer to this location. The value + // is only modified in `prepare_to_insert`, so it has not been modified since the + // most recent call. + // + // GUARANTEES: (only when using the `view_value` safety requirements) + // * The pointer remains valid until the next call to `post_remove` because the caller + // of the most recent call to `prepare_to_insert` promised to retain ownership of the + // `ListArc` containing `Self` until the next call to `post_remove`. The value cannot + // be destroyed while a `ListArc` reference exists. + unsafe fn view_value(links_field: *mut $crate::list::ListLinks<$num>) -> *const Self { + let spoff = $crate::list::ListLinksSelfPtr::::LIST_LINKS_SELF_PTR_OFFSET; + // SAFETY: The constant is equal to `offset_of!(ListLinksSelfPtr, self_ptr)`, so + // the pointer stays in bounds of the allocation. + let self_ptr = unsafe { (links_field as *const u8).add(spoff) } + as *const ::core::cell::UnsafeCell<*const Self>; + let cell_inner = ::core::cell::UnsafeCell::raw_get(self_ptr); + // SAFETY: This is not a data race, because the only function that writes to this + // value is `prepare_to_insert`, but by the safety requirements the + // `prepare_to_insert` method may not be called in parallel with `view_value` or + // `post_remove`. + unsafe { ::core::ptr::read(cell_inner) } + } + + // GUARANTEES: + // The first guarantee of `view_value` is exactly what `post_remove` guarantees. + unsafe fn post_remove(me: *mut $crate::list::ListLinks<$num>) -> *const Self { + // SAFETY: This specific implementation of `view_value` allows the caller to + // promise the safety requirements of `post_remove` instead of the safety + // requirements for `view_value`. + unsafe { >::view_value(me) } + } + } + )*}; +} +pub use impl_list_item; diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index b37a0b3180fb..4571daec0961 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -37,6 +37,6 @@ pub use super::error::{code::*, Error, Result}; pub use super::{str::CStr, ThisModule}; -pub use super::init::{InPlaceInit, Init, PinInit}; +pub use super::init::{InPlaceInit, InPlaceWrite, Init, PinInit}; pub use super::current; diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs index a78aa3514a0a..508b0221256c 100644 --- a/rust/kernel/print.rs +++ b/rust/kernel/print.rs @@ -4,7 +4,7 @@ //! //! C header: [`include/linux/printk.h`](srctree/include/linux/printk.h) //! -//! Reference: +//! Reference: use core::{ ffi::{c_char, c_void}, @@ -197,7 +197,7 @@ macro_rules! print_macro ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_emerg`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_emerg +/// [`pr_emerg`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_emerg /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -221,7 +221,7 @@ macro_rules! pr_emerg ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_alert`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_alert +/// [`pr_alert`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_alert /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -245,7 +245,7 @@ macro_rules! pr_alert ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_crit`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_crit +/// [`pr_crit`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_crit /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -269,7 +269,7 @@ macro_rules! pr_crit ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_err`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_err +/// [`pr_err`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_err /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -293,7 +293,7 @@ macro_rules! pr_err ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_warn`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_warn +/// [`pr_warn`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_warn /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -317,7 +317,7 @@ macro_rules! pr_warn ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_notice`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_notice +/// [`pr_notice`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_notice /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -341,7 +341,7 @@ macro_rules! pr_notice ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_info`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_info +/// [`pr_info`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_info /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -367,7 +367,7 @@ macro_rules! pr_info ( /// Mimics the interface of [`std::print!`]. See [`core::fmt`] and /// `alloc::format!` for information about the formatting syntax. /// -/// [`pr_debug`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_debug +/// [`pr_debug`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_debug /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples @@ -395,7 +395,7 @@ macro_rules! pr_debug ( /// `alloc::format!` for information about the formatting syntax. /// /// [`pr_info!`]: crate::pr_info! -/// [`pr_cont`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_cont +/// [`pr_cont`]: https://docs.kernel.org/core-api/printk-basics.html#c.pr_cont /// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html /// /// # Examples diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs new file mode 100644 index 000000000000..25eb36fd1cdc --- /dev/null +++ b/rust/kernel/rbtree.rs @@ -0,0 +1,1278 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Red-black trees. +//! +//! C header: [`include/linux/rbtree.h`](srctree/include/linux/rbtree.h) +//! +//! Reference: + +use crate::{alloc::Flags, bindings, container_of, error::Result, prelude::*}; +use alloc::boxed::Box; +use core::{ + cmp::{Ord, Ordering}, + marker::PhantomData, + mem::MaybeUninit, + ptr::{addr_of_mut, from_mut, NonNull}, +}; + +/// A red-black tree with owned nodes. +/// +/// It is backed by the kernel C red-black trees. +/// +/// # Examples +/// +/// In the example below we do several operations on a tree. We note that insertions may fail if +/// the system is out of memory. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::{RBTree, RBTreeNode, RBTreeNodeReservation}}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// // Check the nodes we just inserted. +/// { +/// assert_eq!(tree.get(&10).unwrap(), &100); +/// assert_eq!(tree.get(&20).unwrap(), &200); +/// assert_eq!(tree.get(&30).unwrap(), &300); +/// } +/// +/// // Iterate over the nodes we just inserted. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&10, &100)); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next().unwrap(), (&30, &300)); +/// assert!(iter.next().is_none()); +/// } +/// +/// // Print all elements. +/// for (key, value) in &tree { +/// pr_info!("{} = {}\n", key, value); +/// } +/// +/// // Replace one of the elements. +/// tree.try_create_and_insert(10, 1000, flags::GFP_KERNEL)?; +/// +/// // Check that the tree reflects the replacement. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&10, &1000)); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next().unwrap(), (&30, &300)); +/// assert!(iter.next().is_none()); +/// } +/// +/// // Change the value of one of the elements. +/// *tree.get_mut(&30).unwrap() = 3000; +/// +/// // Check that the tree reflects the update. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&10, &1000)); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next().unwrap(), (&30, &3000)); +/// assert!(iter.next().is_none()); +/// } +/// +/// // Remove an element. +/// tree.remove(&10); +/// +/// // Check that the tree reflects the removal. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next().unwrap(), (&30, &3000)); +/// assert!(iter.next().is_none()); +/// } +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// In the example below, we first allocate a node, acquire a spinlock, then insert the node into +/// the tree. This is useful when the insertion context does not allow sleeping, for example, when +/// holding a spinlock. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::{RBTree, RBTreeNode}, sync::SpinLock}; +/// +/// fn insert_test(tree: &SpinLock>) -> Result { +/// // Pre-allocate node. This may fail (as it allocates memory). +/// let node = RBTreeNode::new(10, 100, flags::GFP_KERNEL)?; +/// +/// // Insert node while holding the lock. It is guaranteed to succeed with no allocation +/// // attempts. +/// let mut guard = tree.lock(); +/// guard.insert(node); +/// Ok(()) +/// } +/// ``` +/// +/// In the example below, we reuse an existing node allocation from an element we removed. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::{RBTree, RBTreeNodeReservation}}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// // Check the nodes we just inserted. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&10, &100)); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert_eq!(iter.next().unwrap(), (&30, &300)); +/// assert!(iter.next().is_none()); +/// } +/// +/// // Remove a node, getting back ownership of it. +/// let existing = tree.remove(&30).unwrap(); +/// +/// // Check that the tree reflects the removal. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&10, &100)); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert!(iter.next().is_none()); +/// } +/// +/// // Create a preallocated reservation that we can re-use later. +/// let reservation = RBTreeNodeReservation::new(flags::GFP_KERNEL)?; +/// +/// // Insert a new node into the tree, reusing the previous allocation. This is guaranteed to +/// // succeed (no memory allocations). +/// tree.insert(reservation.into_node(15, 150)); +/// +/// // Check that the tree reflect the new insertion. +/// { +/// let mut iter = tree.iter(); +/// assert_eq!(iter.next().unwrap(), (&10, &100)); +/// assert_eq!(iter.next().unwrap(), (&15, &150)); +/// assert_eq!(iter.next().unwrap(), (&20, &200)); +/// assert!(iter.next().is_none()); +/// } +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// # Invariants +/// +/// Non-null parent/children pointers stored in instances of the `rb_node` C struct are always +/// valid, and pointing to a field of our internal representation of a node. +pub struct RBTree { + root: bindings::rb_root, + _p: PhantomData>, +} + +// SAFETY: An [`RBTree`] allows the same kinds of access to its values that a struct allows to its +// fields, so we use the same Send condition as would be used for a struct with K and V fields. +unsafe impl Send for RBTree {} + +// SAFETY: An [`RBTree`] allows the same kinds of access to its values that a struct allows to its +// fields, so we use the same Sync condition as would be used for a struct with K and V fields. +unsafe impl Sync for RBTree {} + +impl RBTree { + /// Creates a new and empty tree. + pub fn new() -> Self { + Self { + // INVARIANT: There are no nodes in the tree, so the invariant holds vacuously. + root: bindings::rb_root::default(), + _p: PhantomData, + } + } + + /// Returns an iterator over the tree nodes, sorted by key. + pub fn iter(&self) -> Iter<'_, K, V> { + Iter { + _tree: PhantomData, + // INVARIANT: + // - `self.root` is a valid pointer to a tree root. + // - `bindings::rb_first` produces a valid pointer to a node given `root` is valid. + iter_raw: IterRaw { + // SAFETY: by the invariants, all pointers are valid. + next: unsafe { bindings::rb_first(&self.root) }, + _phantom: PhantomData, + }, + } + } + + /// Returns a mutable iterator over the tree nodes, sorted by key. + pub fn iter_mut(&mut self) -> IterMut<'_, K, V> { + IterMut { + _tree: PhantomData, + // INVARIANT: + // - `self.root` is a valid pointer to a tree root. + // - `bindings::rb_first` produces a valid pointer to a node given `root` is valid. + iter_raw: IterRaw { + // SAFETY: by the invariants, all pointers are valid. + next: unsafe { bindings::rb_first(from_mut(&mut self.root)) }, + _phantom: PhantomData, + }, + } + } + + /// Returns an iterator over the keys of the nodes in the tree, in sorted order. + pub fn keys(&self) -> impl Iterator { + self.iter().map(|(k, _)| k) + } + + /// Returns an iterator over the values of the nodes in the tree, sorted by key. + pub fn values(&self) -> impl Iterator { + self.iter().map(|(_, v)| v) + } + + /// Returns a mutable iterator over the values of the nodes in the tree, sorted by key. + pub fn values_mut(&mut self) -> impl Iterator { + self.iter_mut().map(|(_, v)| v) + } + + /// Returns a cursor over the tree nodes, starting with the smallest key. + pub fn cursor_front(&mut self) -> Option> { + let root = addr_of_mut!(self.root); + // SAFETY: `self.root` is always a valid root node + let current = unsafe { bindings::rb_first(root) }; + NonNull::new(current).map(|current| { + // INVARIANT: + // - `current` is a valid node in the [`RBTree`] pointed to by `self`. + Cursor { + current, + tree: self, + } + }) + } + + /// Returns a cursor over the tree nodes, starting with the largest key. + pub fn cursor_back(&mut self) -> Option> { + let root = addr_of_mut!(self.root); + // SAFETY: `self.root` is always a valid root node + let current = unsafe { bindings::rb_last(root) }; + NonNull::new(current).map(|current| { + // INVARIANT: + // - `current` is a valid node in the [`RBTree`] pointed to by `self`. + Cursor { + current, + tree: self, + } + }) + } +} + +impl RBTree +where + K: Ord, +{ + /// Tries to insert a new value into the tree. + /// + /// It overwrites a node if one already exists with the same key and returns it (containing the + /// key/value pair). Returns [`None`] if a node with the same key didn't already exist. + /// + /// Returns an error if it cannot allocate memory for the new node. + pub fn try_create_and_insert( + &mut self, + key: K, + value: V, + flags: Flags, + ) -> Result>> { + Ok(self.insert(RBTreeNode::new(key, value, flags)?)) + } + + /// Inserts a new node into the tree. + /// + /// It overwrites a node if one already exists with the same key and returns it (containing the + /// key/value pair). Returns [`None`] if a node with the same key didn't already exist. + /// + /// This function always succeeds. + pub fn insert(&mut self, node: RBTreeNode) -> Option> { + match self.raw_entry(&node.node.key) { + RawEntry::Occupied(entry) => Some(entry.replace(node)), + RawEntry::Vacant(entry) => { + entry.insert(node); + None + } + } + } + + fn raw_entry(&mut self, key: &K) -> RawEntry<'_, K, V> { + let raw_self: *mut RBTree = self; + // The returned `RawEntry` is used to call either `rb_link_node` or `rb_replace_node`. + // The parameters of `bindings::rb_link_node` are as follows: + // - `node`: A pointer to an uninitialized node being inserted. + // - `parent`: A pointer to an existing node in the tree. One of its child pointers must be + // null, and `node` will become a child of `parent` by replacing that child pointer + // with a pointer to `node`. + // - `rb_link`: A pointer to either the left-child or right-child field of `parent`. This + // specifies which child of `parent` should hold `node` after this call. The + // value of `*rb_link` must be null before the call to `rb_link_node`. If the + // red/black tree is empty, then it’s also possible for `parent` to be null. In + // this case, `rb_link` is a pointer to the `root` field of the red/black tree. + // + // We will traverse the tree looking for a node that has a null pointer as its child, + // representing an empty subtree where we can insert our new node. We need to make sure + // that we preserve the ordering of the nodes in the tree. In each iteration of the loop + // we store `parent` and `child_field_of_parent`, and the new `node` will go somewhere + // in the subtree of `parent` that `child_field_of_parent` points at. Once + // we find an empty subtree, we can insert the new node using `rb_link_node`. + let mut parent = core::ptr::null_mut(); + let mut child_field_of_parent: &mut *mut bindings::rb_node = + // SAFETY: `raw_self` is a valid pointer to the `RBTree` (created from `self` above). + unsafe { &mut (*raw_self).root.rb_node }; + while !(*child_field_of_parent).is_null() { + let curr = *child_field_of_parent; + // SAFETY: All links fields we create are in a `Node`. + let node = unsafe { container_of!(curr, Node, links) }; + + // SAFETY: `node` is a non-null node so it is valid by the type invariants. + match key.cmp(unsafe { &(*node).key }) { + // SAFETY: `curr` is a non-null node so it is valid by the type invariants. + Ordering::Less => child_field_of_parent = unsafe { &mut (*curr).rb_left }, + // SAFETY: `curr` is a non-null node so it is valid by the type invariants. + Ordering::Greater => child_field_of_parent = unsafe { &mut (*curr).rb_right }, + Ordering::Equal => { + return RawEntry::Occupied(OccupiedEntry { + rbtree: self, + node_links: curr, + }) + } + } + parent = curr; + } + + RawEntry::Vacant(RawVacantEntry { + rbtree: raw_self, + parent, + child_field_of_parent, + _phantom: PhantomData, + }) + } + + /// Gets the given key's corresponding entry in the map for in-place manipulation. + pub fn entry(&mut self, key: K) -> Entry<'_, K, V> { + match self.raw_entry(&key) { + RawEntry::Occupied(entry) => Entry::Occupied(entry), + RawEntry::Vacant(entry) => Entry::Vacant(VacantEntry { raw: entry, key }), + } + } + + /// Used for accessing the given node, if it exists. + pub fn find_mut(&mut self, key: &K) -> Option> { + match self.raw_entry(key) { + RawEntry::Occupied(entry) => Some(entry), + RawEntry::Vacant(_entry) => None, + } + } + + /// Returns a reference to the value corresponding to the key. + pub fn get(&self, key: &K) -> Option<&V> { + let mut node = self.root.rb_node; + while !node.is_null() { + // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` + // point to the links field of `Node` objects. + let this = unsafe { container_of!(node, Node, links) }; + // SAFETY: `this` is a non-null node so it is valid by the type invariants. + node = match key.cmp(unsafe { &(*this).key }) { + // SAFETY: `node` is a non-null node so it is valid by the type invariants. + Ordering::Less => unsafe { (*node).rb_left }, + // SAFETY: `node` is a non-null node so it is valid by the type invariants. + Ordering::Greater => unsafe { (*node).rb_right }, + // SAFETY: `node` is a non-null node so it is valid by the type invariants. + Ordering::Equal => return Some(unsafe { &(*this).value }), + } + } + None + } + + /// Returns a mutable reference to the value corresponding to the key. + pub fn get_mut(&mut self, key: &K) -> Option<&mut V> { + self.find_mut(key).map(|node| node.into_mut()) + } + + /// Removes the node with the given key from the tree. + /// + /// It returns the node that was removed if one exists, or [`None`] otherwise. + pub fn remove_node(&mut self, key: &K) -> Option> { + self.find_mut(key).map(OccupiedEntry::remove_node) + } + + /// Removes the node with the given key from the tree. + /// + /// It returns the value that was removed if one exists, or [`None`] otherwise. + pub fn remove(&mut self, key: &K) -> Option { + self.find_mut(key).map(OccupiedEntry::remove) + } + + /// Returns a cursor over the tree nodes based on the given key. + /// + /// If the given key exists, the cursor starts there. + /// Otherwise it starts with the first larger key in sort order. + /// If there is no larger key, it returns [`None`]. + pub fn cursor_lower_bound(&mut self, key: &K) -> Option> + where + K: Ord, + { + let mut node = self.root.rb_node; + let mut best_match: Option>> = None; + while !node.is_null() { + // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` + // point to the links field of `Node` objects. + let this = unsafe { container_of!(node, Node, links) }.cast_mut(); + // SAFETY: `this` is a non-null node so it is valid by the type invariants. + let this_key = unsafe { &(*this).key }; + // SAFETY: `node` is a non-null node so it is valid by the type invariants. + let left_child = unsafe { (*node).rb_left }; + // SAFETY: `node` is a non-null node so it is valid by the type invariants. + let right_child = unsafe { (*node).rb_right }; + match key.cmp(this_key) { + Ordering::Equal => { + best_match = NonNull::new(this); + break; + } + Ordering::Greater => { + node = right_child; + } + Ordering::Less => { + let is_better_match = match best_match { + None => true, + Some(best) => { + // SAFETY: `best` is a non-null node so it is valid by the type invariants. + let best_key = unsafe { &(*best.as_ptr()).key }; + best_key > this_key + } + }; + if is_better_match { + best_match = NonNull::new(this); + } + node = left_child; + } + }; + } + + let best = best_match?; + + // SAFETY: `best` is a non-null node so it is valid by the type invariants. + let links = unsafe { addr_of_mut!((*best.as_ptr()).links) }; + + NonNull::new(links).map(|current| { + // INVARIANT: + // - `current` is a valid node in the [`RBTree`] pointed to by `self`. + Cursor { + current, + tree: self, + } + }) + } +} + +impl Default for RBTree { + fn default() -> Self { + Self::new() + } +} + +impl Drop for RBTree { + fn drop(&mut self) { + // SAFETY: `root` is valid as it's embedded in `self` and we have a valid `self`. + let mut next = unsafe { bindings::rb_first_postorder(&self.root) }; + + // INVARIANT: The loop invariant is that all tree nodes from `next` in postorder are valid. + while !next.is_null() { + // SAFETY: All links fields we create are in a `Node`. + let this = unsafe { container_of!(next, Node, links) }; + + // Find out what the next node is before disposing of the current one. + // SAFETY: `next` and all nodes in postorder are still valid. + next = unsafe { bindings::rb_next_postorder(next) }; + + // INVARIANT: This is the destructor, so we break the type invariant during clean-up, + // but it is not observable. The loop invariant is still maintained. + + // SAFETY: `this` is valid per the loop invariant. + unsafe { drop(Box::from_raw(this.cast_mut())) }; + } + } +} + +/// A bidirectional cursor over the tree nodes, sorted by key. +/// +/// # Examples +/// +/// In the following example, we obtain a cursor to the first element in the tree. +/// The cursor allows us to iterate bidirectionally over key/value pairs in the tree. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::RBTree}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// // Get a cursor to the first element. +/// let mut cursor = tree.cursor_front().unwrap(); +/// let mut current = cursor.current(); +/// assert_eq!(current, (&10, &100)); +/// +/// // Move the cursor, updating it to the 2nd element. +/// cursor = cursor.move_next().unwrap(); +/// current = cursor.current(); +/// assert_eq!(current, (&20, &200)); +/// +/// // Peek at the next element without impacting the cursor. +/// let next = cursor.peek_next().unwrap(); +/// assert_eq!(next, (&30, &300)); +/// current = cursor.current(); +/// assert_eq!(current, (&20, &200)); +/// +/// // Moving past the last element causes the cursor to return [`None`]. +/// cursor = cursor.move_next().unwrap(); +/// current = cursor.current(); +/// assert_eq!(current, (&30, &300)); +/// let cursor = cursor.move_next(); +/// assert!(cursor.is_none()); +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// A cursor can also be obtained at the last element in the tree. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::RBTree}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// let mut cursor = tree.cursor_back().unwrap(); +/// let current = cursor.current(); +/// assert_eq!(current, (&30, &300)); +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// Obtaining a cursor returns [`None`] if the tree is empty. +/// +/// ``` +/// use kernel::rbtree::RBTree; +/// +/// let mut tree: RBTree = RBTree::new(); +/// assert!(tree.cursor_front().is_none()); +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// [`RBTree::cursor_lower_bound`] can be used to start at an arbitrary node in the tree. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::RBTree}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert five elements. +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(40, 400, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(50, 500, flags::GFP_KERNEL)?; +/// +/// // If the provided key exists, a cursor to that key is returned. +/// let cursor = tree.cursor_lower_bound(&20).unwrap(); +/// let current = cursor.current(); +/// assert_eq!(current, (&20, &200)); +/// +/// // If the provided key doesn't exist, a cursor to the first larger element in sort order is returned. +/// let cursor = tree.cursor_lower_bound(&25).unwrap(); +/// let current = cursor.current(); +/// assert_eq!(current, (&30, &300)); +/// +/// // If there is no larger key, [`None`] is returned. +/// let cursor = tree.cursor_lower_bound(&55); +/// assert!(cursor.is_none()); +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// The cursor allows mutation of values in the tree. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::RBTree}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// // Retrieve a cursor. +/// let mut cursor = tree.cursor_front().unwrap(); +/// +/// // Get a mutable reference to the current value. +/// let (k, v) = cursor.current_mut(); +/// *v = 1000; +/// +/// // The updated value is reflected in the tree. +/// let updated = tree.get(&10).unwrap(); +/// assert_eq!(updated, &1000); +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// It also allows node removal. The following examples demonstrate the behavior of removing the current node. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::RBTree}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// // Remove the first element. +/// let mut cursor = tree.cursor_front().unwrap(); +/// let mut current = cursor.current(); +/// assert_eq!(current, (&10, &100)); +/// cursor = cursor.remove_current().0.unwrap(); +/// +/// // If a node exists after the current element, it is returned. +/// current = cursor.current(); +/// assert_eq!(current, (&20, &200)); +/// +/// // Get a cursor to the last element, and remove it. +/// cursor = tree.cursor_back().unwrap(); +/// current = cursor.current(); +/// assert_eq!(current, (&30, &300)); +/// +/// // Since there is no next node, the previous node is returned. +/// cursor = cursor.remove_current().0.unwrap(); +/// current = cursor.current(); +/// assert_eq!(current, (&20, &200)); +/// +/// // Removing the last element in the tree returns [`None`]. +/// assert!(cursor.remove_current().0.is_none()); +/// +/// # Ok::<(), Error>(()) +/// ``` +/// +/// Nodes adjacent to the current node can also be removed. +/// +/// ``` +/// use kernel::{alloc::flags, rbtree::RBTree}; +/// +/// // Create a new tree. +/// let mut tree = RBTree::new(); +/// +/// // Insert three elements. +/// tree.try_create_and_insert(10, 100, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(20, 200, flags::GFP_KERNEL)?; +/// tree.try_create_and_insert(30, 300, flags::GFP_KERNEL)?; +/// +/// // Get a cursor to the first element. +/// let mut cursor = tree.cursor_front().unwrap(); +/// let mut current = cursor.current(); +/// assert_eq!(current, (&10, &100)); +/// +/// // Calling `remove_prev` from the first element returns [`None`]. +/// assert!(cursor.remove_prev().is_none()); +/// +/// // Get a cursor to the last element. +/// cursor = tree.cursor_back().unwrap(); +/// current = cursor.current(); +/// assert_eq!(current, (&30, &300)); +/// +/// // Calling `remove_prev` removes and returns the middle element. +/// assert_eq!(cursor.remove_prev().unwrap().to_key_value(), (20, 200)); +/// +/// // Calling `remove_next` from the last element returns [`None`]. +/// assert!(cursor.remove_next().is_none()); +/// +/// // Move to the first element +/// cursor = cursor.move_prev().unwrap(); +/// current = cursor.current(); +/// assert_eq!(current, (&10, &100)); +/// +/// // Calling `remove_next` removes and returns the last element. +/// assert_eq!(cursor.remove_next().unwrap().to_key_value(), (30, 300)); +/// +/// # Ok::<(), Error>(()) +/// +/// ``` +/// +/// # Invariants +/// - `current` points to a node that is in the same [`RBTree`] as `tree`. +pub struct Cursor<'a, K, V> { + tree: &'a mut RBTree, + current: NonNull, +} + +// SAFETY: The [`Cursor`] has exclusive access to both `K` and `V`, so it is sufficient to require them to be `Send`. +// The cursor only gives out immutable references to the keys, but since it has excusive access to those same +// keys, `Send` is sufficient. `Sync` would be okay, but it is more restrictive to the user. +unsafe impl<'a, K: Send, V: Send> Send for Cursor<'a, K, V> {} + +// SAFETY: The [`Cursor`] gives out immutable references to K and mutable references to V, +// so it has the same thread safety requirements as mutable references. +unsafe impl<'a, K: Sync, V: Sync> Sync for Cursor<'a, K, V> {} + +impl<'a, K, V> Cursor<'a, K, V> { + /// The current node + pub fn current(&self) -> (&K, &V) { + // SAFETY: + // - `self.current` is a valid node by the type invariants. + // - We have an immutable reference by the function signature. + unsafe { Self::to_key_value(self.current) } + } + + /// The current node, with a mutable value + pub fn current_mut(&mut self) -> (&K, &mut V) { + // SAFETY: + // - `self.current` is a valid node by the type invariants. + // - We have an mutable reference by the function signature. + unsafe { Self::to_key_value_mut(self.current) } + } + + /// Remove the current node from the tree. + /// + /// Returns a tuple where the first element is a cursor to the next node, if it exists, + /// else the previous node, else [`None`] (if the tree becomes empty). The second element + /// is the removed node. + pub fn remove_current(self) -> (Option, RBTreeNode) { + let prev = self.get_neighbor_raw(Direction::Prev); + let next = self.get_neighbor_raw(Direction::Next); + // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` + // point to the links field of `Node` objects. + let this = unsafe { container_of!(self.current.as_ptr(), Node, links) }.cast_mut(); + // SAFETY: `this` is valid by the type invariants as described above. + let node = unsafe { Box::from_raw(this) }; + let node = RBTreeNode { node }; + // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so + // the tree cannot change. By the tree invariant, all nodes are valid. + unsafe { bindings::rb_erase(&mut (*this).links, addr_of_mut!(self.tree.root)) }; + + let current = match (prev, next) { + (_, Some(next)) => next, + (Some(prev), None) => prev, + (None, None) => { + return (None, node); + } + }; + + ( + // INVARIANT: + // - `current` is a valid node in the [`RBTree`] pointed to by `self.tree`. + Some(Self { + current, + tree: self.tree, + }), + node, + ) + } + + /// Remove the previous node, returning it if it exists. + pub fn remove_prev(&mut self) -> Option> { + self.remove_neighbor(Direction::Prev) + } + + /// Remove the next node, returning it if it exists. + pub fn remove_next(&mut self) -> Option> { + self.remove_neighbor(Direction::Next) + } + + fn remove_neighbor(&mut self, direction: Direction) -> Option> { + if let Some(neighbor) = self.get_neighbor_raw(direction) { + let neighbor = neighbor.as_ptr(); + // SAFETY: The reference to the tree used to create the cursor outlives the cursor, so + // the tree cannot change. By the tree invariant, all nodes are valid. + unsafe { bindings::rb_erase(neighbor, addr_of_mut!(self.tree.root)) }; + // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` + // point to the links field of `Node` objects. + let this = unsafe { container_of!(neighbor, Node, links) }.cast_mut(); + // SAFETY: `this` is valid by the type invariants as described above. + let node = unsafe { Box::from_raw(this) }; + return Some(RBTreeNode { node }); + } + None + } + + /// Move the cursor to the previous node, returning [`None`] if it doesn't exist. + pub fn move_prev(self) -> Option { + self.mv(Direction::Prev) + } + + /// Move the cursor to the next node, returning [`None`] if it doesn't exist. + pub fn move_next(self) -> Option { + self.mv(Direction::Next) + } + + fn mv(self, direction: Direction) -> Option { + // INVARIANT: + // - `neighbor` is a valid node in the [`RBTree`] pointed to by `self.tree`. + self.get_neighbor_raw(direction).map(|neighbor| Self { + tree: self.tree, + current: neighbor, + }) + } + + /// Access the previous node without moving the cursor. + pub fn peek_prev(&self) -> Option<(&K, &V)> { + self.peek(Direction::Prev) + } + + /// Access the previous node without moving the cursor. + pub fn peek_next(&self) -> Option<(&K, &V)> { + self.peek(Direction::Next) + } + + fn peek(&self, direction: Direction) -> Option<(&K, &V)> { + self.get_neighbor_raw(direction).map(|neighbor| { + // SAFETY: + // - `neighbor` is a valid tree node. + // - By the function signature, we have an immutable reference to `self`. + unsafe { Self::to_key_value(neighbor) } + }) + } + + /// Access the previous node mutably without moving the cursor. + pub fn peek_prev_mut(&mut self) -> Option<(&K, &mut V)> { + self.peek_mut(Direction::Prev) + } + + /// Access the next node mutably without moving the cursor. + pub fn peek_next_mut(&mut self) -> Option<(&K, &mut V)> { + self.peek_mut(Direction::Next) + } + + fn peek_mut(&mut self, direction: Direction) -> Option<(&K, &mut V)> { + self.get_neighbor_raw(direction).map(|neighbor| { + // SAFETY: + // - `neighbor` is a valid tree node. + // - By the function signature, we have a mutable reference to `self`. + unsafe { Self::to_key_value_mut(neighbor) } + }) + } + + fn get_neighbor_raw(&self, direction: Direction) -> Option> { + // SAFETY: `self.current` is valid by the type invariants. + let neighbor = unsafe { + match direction { + Direction::Prev => bindings::rb_prev(self.current.as_ptr()), + Direction::Next => bindings::rb_next(self.current.as_ptr()), + } + }; + + NonNull::new(neighbor) + } + + /// SAFETY: + /// - `node` must be a valid pointer to a node in an [`RBTree`]. + /// - The caller has immutable access to `node` for the duration of 'b. + unsafe fn to_key_value<'b>(node: NonNull) -> (&'b K, &'b V) { + // SAFETY: the caller guarantees that `node` is a valid pointer in an `RBTree`. + let (k, v) = unsafe { Self::to_key_value_raw(node) }; + // SAFETY: the caller guarantees immutable access to `node`. + (k, unsafe { &*v }) + } + + /// SAFETY: + /// - `node` must be a valid pointer to a node in an [`RBTree`]. + /// - The caller has mutable access to `node` for the duration of 'b. + unsafe fn to_key_value_mut<'b>(node: NonNull) -> (&'b K, &'b mut V) { + // SAFETY: the caller guarantees that `node` is a valid pointer in an `RBTree`. + let (k, v) = unsafe { Self::to_key_value_raw(node) }; + // SAFETY: the caller guarantees mutable access to `node`. + (k, unsafe { &mut *v }) + } + + /// SAFETY: + /// - `node` must be a valid pointer to a node in an [`RBTree`]. + /// - The caller has immutable access to the key for the duration of 'b. + unsafe fn to_key_value_raw<'b>(node: NonNull) -> (&'b K, *mut V) { + // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self` + // point to the links field of `Node` objects. + let this = unsafe { container_of!(node.as_ptr(), Node, links) }.cast_mut(); + // SAFETY: The passed `node` is the current node or a non-null neighbor, + // thus `this` is valid by the type invariants. + let k = unsafe { &(*this).key }; + // SAFETY: The passed `node` is the current node or a non-null neighbor, + // thus `this` is valid by the type invariants. + let v = unsafe { addr_of_mut!((*this).value) }; + (k, v) + } +} + +/// Direction for [`Cursor`] operations. +enum Direction { + /// the node immediately before, in sort order + Prev, + /// the node immediately after, in sort order + Next, +} + +impl<'a, K, V> IntoIterator for &'a RBTree { + type Item = (&'a K, &'a V); + type IntoIter = Iter<'a, K, V>; + + fn into_iter(self) -> Self::IntoIter { + self.iter() + } +} + +/// An iterator over the nodes of a [`RBTree`]. +/// +/// Instances are created by calling [`RBTree::iter`]. +pub struct Iter<'a, K, V> { + _tree: PhantomData<&'a RBTree>, + iter_raw: IterRaw, +} + +// SAFETY: The [`Iter`] gives out immutable references to K and V, so it has the same +// thread safety requirements as immutable references. +unsafe impl<'a, K: Sync, V: Sync> Send for Iter<'a, K, V> {} + +// SAFETY: The [`Iter`] gives out immutable references to K and V, so it has the same +// thread safety requirements as immutable references. +unsafe impl<'a, K: Sync, V: Sync> Sync for Iter<'a, K, V> {} + +impl<'a, K, V> Iterator for Iter<'a, K, V> { + type Item = (&'a K, &'a V); + + fn next(&mut self) -> Option { + // SAFETY: Due to `self._tree`, `k` and `v` are valid for the lifetime of `'a`. + self.iter_raw.next().map(|(k, v)| unsafe { (&*k, &*v) }) + } +} + +impl<'a, K, V> IntoIterator for &'a mut RBTree { + type Item = (&'a K, &'a mut V); + type IntoIter = IterMut<'a, K, V>; + + fn into_iter(self) -> Self::IntoIter { + self.iter_mut() + } +} + +/// A mutable iterator over the nodes of a [`RBTree`]. +/// +/// Instances are created by calling [`RBTree::iter_mut`]. +pub struct IterMut<'a, K, V> { + _tree: PhantomData<&'a mut RBTree>, + iter_raw: IterRaw, +} + +// SAFETY: The [`IterMut`] has exclusive access to both `K` and `V`, so it is sufficient to require them to be `Send`. +// The iterator only gives out immutable references to the keys, but since the iterator has excusive access to those same +// keys, `Send` is sufficient. `Sync` would be okay, but it is more restrictive to the user. +unsafe impl<'a, K: Send, V: Send> Send for IterMut<'a, K, V> {} + +// SAFETY: The [`IterMut`] gives out immutable references to K and mutable references to V, so it has the same +// thread safety requirements as mutable references. +unsafe impl<'a, K: Sync, V: Sync> Sync for IterMut<'a, K, V> {} + +impl<'a, K, V> Iterator for IterMut<'a, K, V> { + type Item = (&'a K, &'a mut V); + + fn next(&mut self) -> Option { + self.iter_raw.next().map(|(k, v)| + // SAFETY: Due to `&mut self`, we have exclusive access to `k` and `v`, for the lifetime of `'a`. + unsafe { (&*k, &mut *v) }) + } +} + +/// A raw iterator over the nodes of a [`RBTree`]. +/// +/// # Invariants +/// - `self.next` is a valid pointer. +/// - `self.next` points to a node stored inside of a valid `RBTree`. +struct IterRaw { + next: *mut bindings::rb_node, + _phantom: PhantomData (K, V)>, +} + +impl Iterator for IterRaw { + type Item = (*mut K, *mut V); + + fn next(&mut self) -> Option { + if self.next.is_null() { + return None; + } + + // SAFETY: By the type invariant of `IterRaw`, `self.next` is a valid node in an `RBTree`, + // and by the type invariant of `RBTree`, all nodes point to the links field of `Node` objects. + let cur = unsafe { container_of!(self.next, Node, links) }.cast_mut(); + + // SAFETY: `self.next` is a valid tree node by the type invariants. + self.next = unsafe { bindings::rb_next(self.next) }; + + // SAFETY: By the same reasoning above, it is safe to dereference the node. + Some(unsafe { (addr_of_mut!((*cur).key), addr_of_mut!((*cur).value)) }) + } +} + +/// A memory reservation for a red-black tree node. +/// +/// +/// It contains the memory needed to hold a node that can be inserted into a red-black tree. One +/// can be obtained by directly allocating it ([`RBTreeNodeReservation::new`]). +pub struct RBTreeNodeReservation { + node: Box>>, +} + +impl RBTreeNodeReservation { + /// Allocates memory for a node to be eventually initialised and inserted into the tree via a + /// call to [`RBTree::insert`]. + pub fn new(flags: Flags) -> Result> { + Ok(RBTreeNodeReservation { + node: as BoxExt<_>>::new_uninit(flags)?, + }) + } +} + +// SAFETY: This doesn't actually contain K or V, and is just a memory allocation. Those can always +// be moved across threads. +unsafe impl Send for RBTreeNodeReservation {} + +// SAFETY: This doesn't actually contain K or V, and is just a memory allocation. +unsafe impl Sync for RBTreeNodeReservation {} + +impl RBTreeNodeReservation { + /// Initialises a node reservation. + /// + /// It then becomes an [`RBTreeNode`] that can be inserted into a tree. + pub fn into_node(mut self, key: K, value: V) -> RBTreeNode { + self.node.write(Node { + key, + value, + links: bindings::rb_node::default(), + }); + // SAFETY: We just wrote to it. + let node = unsafe { self.node.assume_init() }; + RBTreeNode { node } + } +} + +/// A red-black tree node. +/// +/// The node is fully initialised (with key and value) and can be inserted into a tree without any +/// extra allocations or failure paths. +pub struct RBTreeNode { + node: Box>, +} + +impl RBTreeNode { + /// Allocates and initialises a node that can be inserted into the tree via + /// [`RBTree::insert`]. + pub fn new(key: K, value: V, flags: Flags) -> Result> { + Ok(RBTreeNodeReservation::new(flags)?.into_node(key, value)) + } + + /// Get the key and value from inside the node. + pub fn to_key_value(self) -> (K, V) { + (self.node.key, self.node.value) + } +} + +// SAFETY: If K and V can be sent across threads, then it's also okay to send [`RBTreeNode`] across +// threads. +unsafe impl Send for RBTreeNode {} + +// SAFETY: If K and V can be accessed without synchronization, then it's also okay to access +// [`RBTreeNode`] without synchronization. +unsafe impl Sync for RBTreeNode {} + +impl RBTreeNode { + /// Drop the key and value, but keep the allocation. + /// + /// It then becomes a reservation that can be re-initialised into a different node (i.e., with + /// a different key and/or value). + /// + /// The existing key and value are dropped in-place as part of this operation, that is, memory + /// may be freed (but only for the key/value; memory for the node itself is kept for reuse). + pub fn into_reservation(self) -> RBTreeNodeReservation { + RBTreeNodeReservation { + node: Box::drop_contents(self.node), + } + } +} + +/// A view into a single entry in a map, which may either be vacant or occupied. +/// +/// This enum is constructed from the [`RBTree::entry`]. +/// +/// [`entry`]: fn@RBTree::entry +pub enum Entry<'a, K, V> { + /// This [`RBTree`] does not have a node with this key. + Vacant(VacantEntry<'a, K, V>), + /// This [`RBTree`] already has a node with this key. + Occupied(OccupiedEntry<'a, K, V>), +} + +/// Like [`Entry`], except that it doesn't have ownership of the key. +enum RawEntry<'a, K, V> { + Vacant(RawVacantEntry<'a, K, V>), + Occupied(OccupiedEntry<'a, K, V>), +} + +/// A view into a vacant entry in a [`RBTree`]. It is part of the [`Entry`] enum. +pub struct VacantEntry<'a, K, V> { + key: K, + raw: RawVacantEntry<'a, K, V>, +} + +/// Like [`VacantEntry`], but doesn't hold on to the key. +/// +/// # Invariants +/// - `parent` may be null if the new node becomes the root. +/// - `child_field_of_parent` is a valid pointer to the left-child or right-child of `parent`. If `parent` is +/// null, it is a pointer to the root of the [`RBTree`]. +struct RawVacantEntry<'a, K, V> { + rbtree: *mut RBTree, + /// The node that will become the parent of the new node if we insert one. + parent: *mut bindings::rb_node, + /// This points to the left-child or right-child field of `parent`, or `root` if `parent` is + /// null. + child_field_of_parent: *mut *mut bindings::rb_node, + _phantom: PhantomData<&'a mut RBTree>, +} + +impl<'a, K, V> RawVacantEntry<'a, K, V> { + /// Inserts the given node into the [`RBTree`] at this entry. + /// + /// The `node` must have a key such that inserting it here does not break the ordering of this + /// [`RBTree`]. + fn insert(self, node: RBTreeNode) -> &'a mut V { + let node = Box::into_raw(node.node); + + // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when + // the node is removed or replaced. + let node_links = unsafe { addr_of_mut!((*node).links) }; + + // INVARIANT: We are linking in a new node, which is valid. It remains valid because we + // "forgot" it with `Box::into_raw`. + // SAFETY: The type invariants of `RawVacantEntry` are exactly the safety requirements of `rb_link_node`. + unsafe { bindings::rb_link_node(node_links, self.parent, self.child_field_of_parent) }; + + // SAFETY: All pointers are valid. `node` has just been inserted into the tree. + unsafe { bindings::rb_insert_color(node_links, addr_of_mut!((*self.rbtree).root)) }; + + // SAFETY: The node is valid until we remove it from the tree. + unsafe { &mut (*node).value } + } +} + +impl<'a, K, V> VacantEntry<'a, K, V> { + /// Inserts the given node into the [`RBTree`] at this entry. + pub fn insert(self, value: V, reservation: RBTreeNodeReservation) -> &'a mut V { + self.raw.insert(reservation.into_node(self.key, value)) + } +} + +/// A view into an occupied entry in a [`RBTree`]. It is part of the [`Entry`] enum. +/// +/// # Invariants +/// - `node_links` is a valid, non-null pointer to a tree node in `self.rbtree` +pub struct OccupiedEntry<'a, K, V> { + rbtree: &'a mut RBTree, + /// The node that this entry corresponds to. + node_links: *mut bindings::rb_node, +} + +impl<'a, K, V> OccupiedEntry<'a, K, V> { + /// Gets a reference to the value in the entry. + pub fn get(&self) -> &V { + // SAFETY: + // - `self.node_links` is a valid pointer to a node in the tree. + // - We have shared access to the underlying tree, and can thus give out a shared reference. + unsafe { &(*container_of!(self.node_links, Node, links)).value } + } + + /// Gets a mutable reference to the value in the entry. + pub fn get_mut(&mut self) -> &mut V { + // SAFETY: + // - `self.node_links` is a valid pointer to a node in the tree. + // - We have exclusive access to the underlying tree, and can thus give out a mutable reference. + unsafe { &mut (*(container_of!(self.node_links, Node, links).cast_mut())).value } + } + + /// Converts the entry into a mutable reference to its value. + /// + /// If you need multiple references to the `OccupiedEntry`, see [`self#get_mut`]. + pub fn into_mut(self) -> &'a mut V { + // SAFETY: + // - `self.node_links` is a valid pointer to a node in the tree. + // - This consumes the `&'a mut RBTree`, therefore it can give out a mutable reference that lives for `'a`. + unsafe { &mut (*(container_of!(self.node_links, Node, links).cast_mut())).value } + } + + /// Remove this entry from the [`RBTree`]. + pub fn remove_node(self) -> RBTreeNode { + // SAFETY: The node is a node in the tree, so it is valid. + unsafe { bindings::rb_erase(self.node_links, &mut self.rbtree.root) }; + + // INVARIANT: The node is being returned and the caller may free it, however, it was + // removed from the tree. So the invariants still hold. + RBTreeNode { + // SAFETY: The node was a node in the tree, but we removed it, so we can convert it + // back into a box. + node: unsafe { + Box::from_raw(container_of!(self.node_links, Node, links).cast_mut()) + }, + } + } + + /// Takes the value of the entry out of the map, and returns it. + pub fn remove(self) -> V { + self.remove_node().node.value + } + + /// Swap the current node for the provided node. + /// + /// The key of both nodes must be equal. + fn replace(self, node: RBTreeNode) -> RBTreeNode { + let node = Box::into_raw(node.node); + + // SAFETY: `node` is valid at least until we call `Box::from_raw`, which only happens when + // the node is removed or replaced. + let new_node_links = unsafe { addr_of_mut!((*node).links) }; + + // SAFETY: This updates the pointers so that `new_node_links` is in the tree where + // `self.node_links` used to be. + unsafe { + bindings::rb_replace_node(self.node_links, new_node_links, &mut self.rbtree.root) + }; + + // SAFETY: + // - `self.node_ptr` produces a valid pointer to a node in the tree. + // - Now that we removed this entry from the tree, we can convert the node to a box. + let old_node = + unsafe { Box::from_raw(container_of!(self.node_links, Node, links).cast_mut()) }; + + RBTreeNode { node: old_node } + } +} + +struct Node { + links: bindings::rb_node, + key: K, + value: V, +} diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs index 39679a960c1a..67bf9d37ddb5 100644 --- a/rust/kernel/std_vendor.rs +++ b/rust/kernel/std_vendor.rs @@ -136,7 +136,7 @@ /// /// [`std::dbg`]: https://doc.rust-lang.org/std/macro.dbg.html /// [`eprintln`]: https://doc.rust-lang.org/std/macro.eprintln.html -/// [`printk`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html +/// [`printk`]: https://docs.kernel.org/core-api/printk-basics.html /// [`pr_info`]: crate::pr_info! /// [`pr_debug`]: crate::pr_debug! #[macro_export] diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index 3673496c2363..3021f30fd822 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -12,12 +12,13 @@ //! 2. It does not support weak references, which allows it to be half the size. //! 3. It saturates the reference count instead of aborting when it goes over a threshold. //! 4. It does not provide a `get_mut` method, so the ref counted object is pinned. +//! 5. The object in [`Arc`] is pinned implicitly. //! //! [`Arc`]: https://doc.rust-lang.org/std/sync/struct.Arc.html use crate::{ alloc::{box_ext::BoxExt, AllocError, Flags}, - error::{self, Error}, + bindings, init::{self, InPlaceInit, Init, PinInit}, try_init, types::{ForeignOwnable, Opaque}, @@ -209,28 +210,6 @@ impl Arc { // `Arc` object. Ok(unsafe { Self::from_inner(Box::leak(inner).into()) }) } - - /// Use the given initializer to in-place initialize a `T`. - /// - /// If `T: !Unpin` it will not be able to move afterwards. - #[inline] - pub fn pin_init(init: impl PinInit, flags: Flags) -> error::Result - where - Error: From, - { - UniqueArc::pin_init(init, flags).map(|u| u.into()) - } - - /// Use the given initializer to in-place initialize a `T`. - /// - /// This is equivalent to [`Arc::pin_init`], since an [`Arc`] is always pinned. - #[inline] - pub fn init(init: impl Init, flags: Flags) -> error::Result - where - Error: From, - { - UniqueArc::init(init, flags).map(|u| u.into()) - } } impl Arc { diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index bd189d646adb..9e7ca066355c 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -7,8 +7,9 @@ use alloc::boxed::Box; use core::{ cell::UnsafeCell, marker::{PhantomData, PhantomPinned}, - mem::MaybeUninit, + mem::{ManuallyDrop, MaybeUninit}, ops::{Deref, DerefMut}, + pin::Pin, ptr::NonNull, }; @@ -26,7 +27,10 @@ pub trait ForeignOwnable: Sized { /// Converts a Rust-owned object to a foreign-owned one. /// - /// The foreign representation is a pointer to void. + /// The foreign representation is a pointer to void. There are no guarantees for this pointer. + /// For example, it might be invalid, dangling or pointing to uninitialized memory. Using it in + /// any way except for [`ForeignOwnable::from_foreign`], [`ForeignOwnable::borrow`], + /// [`ForeignOwnable::try_from_foreign`] can result in undefined behavior. fn into_foreign(self) -> *const core::ffi::c_void; /// Borrows a foreign-owned object. @@ -89,6 +93,32 @@ impl ForeignOwnable for Box { } } +impl ForeignOwnable for Pin> { + type Borrowed<'a> = Pin<&'a T>; + + fn into_foreign(self) -> *const core::ffi::c_void { + // SAFETY: We are still treating the box as pinned. + Box::into_raw(unsafe { Pin::into_inner_unchecked(self) }) as _ + } + + unsafe fn borrow<'a>(ptr: *const core::ffi::c_void) -> Pin<&'a T> { + // SAFETY: The safety requirements for this function ensure that the object is still alive, + // so it is safe to dereference the raw pointer. + // The safety requirements of `from_foreign` also ensure that the object remains alive for + // the lifetime of the returned value. + let r = unsafe { &*ptr.cast() }; + + // SAFETY: This pointer originates from a `Pin>`. + unsafe { Pin::new_unchecked(r) } + } + + unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self { + // SAFETY: The safety requirements of this function ensure that `ptr` comes from a previous + // call to `Self::into_foreign`. + unsafe { Pin::new_unchecked(Box::from_raw(ptr as _)) } + } +} + impl ForeignOwnable for () { type Borrowed<'a> = (); @@ -366,6 +396,35 @@ impl ARef { _p: PhantomData, } } + + /// Consumes the `ARef`, returning a raw pointer. + /// + /// This function does not change the refcount. After calling this function, the caller is + /// responsible for the refcount previously managed by the `ARef`. + /// + /// # Examples + /// + /// ``` + /// use core::ptr::NonNull; + /// use kernel::types::{ARef, AlwaysRefCounted}; + /// + /// struct Empty {} + /// + /// unsafe impl AlwaysRefCounted for Empty { + /// fn inc_ref(&self) {} + /// unsafe fn dec_ref(_obj: NonNull) {} + /// } + /// + /// let mut data = Empty {}; + /// let ptr = NonNull::::new(&mut data as *mut _).unwrap(); + /// let data_ref: ARef = unsafe { ARef::from_raw(ptr) }; + /// let raw_ptr: NonNull = ARef::into_raw(data_ref); + /// + /// assert_eq!(ptr, raw_ptr); + /// ``` + pub fn into_raw(me: Self) -> NonNull { + ManuallyDrop::new(me).ptr + } } impl Clone for ARef { diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index 5be0cb9db3ee..a626b1145e5c 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -2,6 +2,10 @@ //! Crate for all kernel procedural macros. +// When fixdep scans this, it will find this string `CONFIG_RUSTC_VERSION_TEXT` +// and thus add a dependency on `include/config/RUSTC_VERSION_TEXT`, which is +// touched by Kconfig when the version string from the compiler changes. + #[macro_use] mod quote; mod concat_idents; diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 7a5b899e47b7..aef3b132f32b 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -260,6 +260,12 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { unsafe {{ __init() }} }} + #[cfg(MODULE)] + #[doc(hidden)] + #[used] + #[link_section = \".init.data\"] + static __UNIQUE_ID___addressable_init_module: unsafe extern \"C\" fn() -> i32 = init_module; + #[cfg(MODULE)] #[doc(hidden)] #[no_mangle] @@ -273,6 +279,12 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { unsafe {{ __exit() }} }} + #[cfg(MODULE)] + #[doc(hidden)] + #[used] + #[link_section = \".exit.data\"] + static __UNIQUE_ID___addressable_cleanup_module: extern \"C\" fn() = cleanup_module; + // Built-in modules are initialized through an initcall pointer // and the identifiers need to be unique. #[cfg(not(MODULE))] diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 3500a3d62f0d..785a491e5996 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -64,3 +64,11 @@ ld-version := $(shell,set -- $(ld-info) && echo $2) cc-option-bit = $(if-success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null,$(1)) m32-flag := $(cc-option-bit,-m32) m64-flag := $(cc-option-bit,-m64) + +# $(rustc-option,) +# Return y if the Rust compiler supports , n otherwise +# Calls to this should be guarded so that they are not evaluated if +# CONFIG_RUST_IS_AVAILABLE is not set. +# If you are testing for unstable features, consider testing RUSTC_VERSION +# instead, as features may have different completeness while available. +rustc-option = $(success,trap "rm -rf .tmp_$$" EXIT; mkdir .tmp_$$; $(RUSTC) $(1) --crate-type=rlib /dev/null --out-dir=.tmp_$$ -o .tmp_$$/tmp.rlib) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 4b6942653093..1413dd7c8ff7 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -274,10 +274,15 @@ rust_common_cmd = \ # would not match each other. quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ - cmd_rustc_o_rs = $(rust_common_cmd) --emit=obj=$@ $< + cmd_rustc_o_rs = $(rust_common_cmd) --emit=obj=$@ $< $(cmd_objtool) + +define rule_rustc_o_rs + $(call cmd_and_fixdep,rustc_o_rs) + $(call cmd,gen_objtooldep) +endef $(obj)/%.o: $(obj)/%.rs FORCE - +$(call if_changed_dep,rustc_o_rs) + +$(call if_changed_rule,rustc_o_rs) quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_rsi_rs = \ diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler index 92be0c9a13ee..057305eae85c 100644 --- a/scripts/Makefile.compiler +++ b/scripts/Makefile.compiler @@ -72,3 +72,18 @@ clang-min-version = $(call test-ge, $(CONFIG_CLANG_VERSION), $1) # ld-option # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y) ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) + +# __rustc-option +# Usage: MY_RUSTFLAGS += $(call __rustc-option,$(RUSTC),$(MY_RUSTFLAGS),-Cinstrument-coverage,-Zinstrument-coverage) +__rustc-option = $(call try-run,\ + $(1) $(2) $(3) --crate-type=rlib /dev/null --out-dir=$$TMPOUT -o "$$TMP",$(3),$(4)) + +# rustc-option +# Usage: rustflags-y += $(call rustc-option,-Cinstrument-coverage,-Zinstrument-coverage) +rustc-option = $(call __rustc-option, $(RUSTC),\ + $(KBUILD_RUSTFLAGS),$(1),$(2)) + +# rustc-option-yn +# Usage: flag := $(call rustc-option-yn,-Cinstrument-coverage) +rustc-option-yn = $(call try-run,\ + $(RUSTC) $(KBUILD_RUSTFLAGS) $(1) --crate-type=rlib /dev/null --out-dir=$$TMPOUT -o "$$TMP",y,n) diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index aab4154af00a..693dbbebebba 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -12,6 +12,11 @@ endif KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET) cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1))) +rustc-param = $(call rustc-option, -Cllvm-args=-$(1),) + +check-args = $(foreach arg,$(2),$(call $(1),$(arg))) + +kasan_params := ifdef CONFIG_KASAN_STACK stack_enable := 1 @@ -41,39 +46,59 @@ CFLAGS_KASAN := $(call cc-option, -fsanitize=kernel-address \ $(call cc-option, -fsanitize=kernel-address \ -mllvm -asan-mapping-offset=$(KASAN_SHADOW_OFFSET))) -# Now, add other parameters enabled similarly in both GCC and Clang. -# As some of them are not supported by older compilers, use cc-param. -CFLAGS_KASAN += $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \ - $(call cc-param,asan-stack=$(stack_enable)) \ - $(call cc-param,asan-instrument-allocas=1) \ - $(call cc-param,asan-globals=1) +# The minimum supported `rustc` version has a minimum supported LLVM +# version late enough that we can assume support for -asan-mapping-offset. +RUSTFLAGS_KASAN := -Zsanitizer=kernel-address \ + -Zsanitizer-recover=kernel-address \ + -Cllvm-args=-asan-mapping-offset=$(KASAN_SHADOW_OFFSET) + +# Now, add other parameters enabled similarly in GCC, Clang, and rustc. +# As some of them are not supported by older compilers, these will be filtered +# through `cc-param` or `rust-param` as applicable. +kasan_params += asan-instrumentation-with-call-threshold=$(call_threshold) \ + asan-stack=$(stack_enable) \ + asan-instrument-allocas=1 \ + asan-globals=1 # Instrument memcpy/memset/memmove calls by using instrumented __asan_mem*() # instead. With compilers that don't support this option, compiler-inserted # memintrinsics won't be checked by KASAN on GENERIC_ENTRY architectures. -CFLAGS_KASAN += $(call cc-param,asan-kernel-mem-intrinsic-prefix=1) +kasan_params += asan-kernel-mem-intrinsic-prefix=1 endif # CONFIG_KASAN_GENERIC ifdef CONFIG_KASAN_SW_TAGS +CFLAGS_KASAN := -fsanitize=kernel-hwaddress + +# This sets flags that will enable SW_TAGS KASAN once enabled in Rust. These +# will not work today, and is guarded against in dependencies for CONFIG_RUST. +RUSTFLAGS_KASAN := -Zsanitizer=kernel-hwaddress \ + -Zsanitizer-recover=kernel-hwaddress + ifdef CONFIG_KASAN_INLINE - instrumentation_flags := $(call cc-param,hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET)) + kasan_params += hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET) else - instrumentation_flags := $(call cc-param,hwasan-instrument-with-calls=1) + kasan_params += hwasan-instrument-with-calls=1 endif -CFLAGS_KASAN := -fsanitize=kernel-hwaddress \ - $(call cc-param,hwasan-instrument-stack=$(stack_enable)) \ - $(call cc-param,hwasan-use-short-granules=0) \ - $(call cc-param,hwasan-inline-all-checks=0) \ - $(instrumentation_flags) +kasan_params += hwasan-instrument-stack=$(stack_enable) \ + hwasan-use-short-granules=0 \ + hwasan-inline-all-checks=0 # Instrument memcpy/memset/memmove calls by using instrumented __hwasan_mem*(). ifeq ($(call clang-min-version, 150000)$(call gcc-min-version, 130000),y) - CFLAGS_KASAN += $(call cc-param,hwasan-kernel-mem-intrinsic-prefix=1) + kasan_params += hwasan-kernel-mem-intrinsic-prefix=1 endif endif # CONFIG_KASAN_SW_TAGS -export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE +# Add all as-supported KASAN LLVM parameters requested by the configuration. +CFLAGS_KASAN += $(call check-args, cc-param, $(kasan_params)) + +ifdef CONFIG_RUST + # Avoid calling `rustc-param` unless Rust is enabled. + RUSTFLAGS_KASAN += $(call check-args, rustc-param, $(kasan_params)) +endif # CONFIG_RUST + +export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE RUSTFLAGS_KASAN diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index bc56c68bc8fe..426cdcd3180e 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -167,6 +167,9 @@ ifneq ($(CONFIG_KASAN_HW_TAGS),y) _c_flags += $(if $(patsubst n%,, \ $(KASAN_SANITIZE_$(target-stem).o)$(KASAN_SANITIZE)$(is-kernel-object)), \ $(CFLAGS_KASAN), $(CFLAGS_KASAN_NOSANITIZE)) +_rust_flags += $(if $(patsubst n%,, \ + $(KASAN_SANITIZE_$(target-stem).o)$(KASAN_SANITIZE)$(is-kernel-object)), \ + $(RUSTFLAGS_KASAN)) endif endif diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 404edf7587e0..0d00ac3723b5 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -20,12 +20,28 @@ enum Value { Boolean(bool), Number(i32), String(String), + Array(Vec), Object(Object), } type Object = Vec<(String, Value)>; -/// Minimal "almost JSON" generator (e.g. no `null`s, no arrays, no escaping), +fn comma_sep( + seq: &[T], + formatter: &mut Formatter<'_>, + f: impl Fn(&mut Formatter<'_>, &T) -> Result, +) -> Result { + if let [ref rest @ .., ref last] = seq[..] { + for v in rest { + f(formatter, v)?; + formatter.write_str(",")?; + } + f(formatter, last)?; + } + Ok(()) +} + +/// Minimal "almost JSON" generator (e.g. no `null`s, no escaping), /// enough for this purpose. impl Display for Value { fn fmt(&self, formatter: &mut Formatter<'_>) -> Result { @@ -33,59 +49,67 @@ impl Display for Value { Value::Boolean(boolean) => write!(formatter, "{}", boolean), Value::Number(number) => write!(formatter, "{}", number), Value::String(string) => write!(formatter, "\"{}\"", string), + Value::Array(values) => { + formatter.write_str("[")?; + comma_sep(&values[..], formatter, |formatter, v| v.fmt(formatter))?; + formatter.write_str("]") + } Value::Object(object) => { formatter.write_str("{")?; - if let [ref rest @ .., ref last] = object[..] { - for (key, value) in rest { - write!(formatter, "\"{}\": {},", key, value)?; - } - write!(formatter, "\"{}\": {}", last.0, last.1)?; - } + comma_sep(&object[..], formatter, |formatter, v| { + write!(formatter, "\"{}\": {}", v.0, v.1) + })?; formatter.write_str("}") } } } } +impl From for Value { + fn from(value: bool) -> Self { + Self::Boolean(value) + } +} + +impl From for Value { + fn from(value: i32) -> Self { + Self::Number(value) + } +} + +impl From for Value { + fn from(value: String) -> Self { + Self::String(value) + } +} + +impl From<&str> for Value { + fn from(value: &str) -> Self { + Self::String(value.to_string()) + } +} + +impl From for Value { + fn from(object: Object) -> Self { + Self::Object(object) + } +} + +impl, const N: usize> From<[T; N]> for Value { + fn from(i: [T; N]) -> Self { + Self::Array(i.into_iter().map(|v| v.into()).collect()) + } +} + struct TargetSpec(Object); impl TargetSpec { fn new() -> TargetSpec { TargetSpec(Vec::new()) } -} -trait Push { - fn push(&mut self, key: &str, value: T); -} - -impl Push for TargetSpec { - fn push(&mut self, key: &str, value: bool) { - self.0.push((key.to_string(), Value::Boolean(value))); - } -} - -impl Push for TargetSpec { - fn push(&mut self, key: &str, value: i32) { - self.0.push((key.to_string(), Value::Number(value))); - } -} - -impl Push for TargetSpec { - fn push(&mut self, key: &str, value: String) { - self.0.push((key.to_string(), Value::String(value))); - } -} - -impl Push<&str> for TargetSpec { - fn push(&mut self, key: &str, value: &str) { - self.push(key, value.to_string()); - } -} - -impl Push for TargetSpec { - fn push(&mut self, key: &str, value: Object) { - self.0.push((key.to_string(), Value::Object(value))); + fn push(&mut self, key: &str, value: impl Into) { + self.0.push((key.to_string(), value.into())); } } @@ -164,10 +188,26 @@ fn main() { ); let mut features = "-mmx,+soft-float".to_string(); if cfg.has("MITIGATION_RETPOLINE") { + // The kernel uses `-mretpoline-external-thunk` (for Clang), which Clang maps to the + // target feature of the same name plus the other two target features in + // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via + // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated + // flag); see https://github.com/rust-lang/rust/issues/116852. features += ",+retpoline-external-thunk"; + features += ",+retpoline-indirect-branches"; + features += ",+retpoline-indirect-calls"; + } + if cfg.has("MITIGATION_SLS") { + // The kernel uses `-mharden-sls=all`, which Clang maps to both these target features in + // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via + // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated + // flag); see https://github.com/rust-lang/rust/issues/116851. + features += ",+harden-sls-ijmp"; + features += ",+harden-sls-ret"; } ts.push("features", features); ts.push("llvm-target", "x86_64-linux-gnu"); + ts.push("supported-sanitizers", ["kcfi", "kernel-address"]); ts.push("target-pointer-width", "64"); } else if cfg.has("X86_32") { // This only works on UML, as i386 otherwise needs regparm support in rustc diff --git a/scripts/rustc-version.sh b/scripts/rustc-version.sh new file mode 100755 index 000000000000..4e22593e2eab --- /dev/null +++ b/scripts/rustc-version.sh @@ -0,0 +1,26 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Usage: $ ./rustc-version.sh rustc +# +# Print the Rust compiler version in a 6 or 7-digit form. + +# Convert the version string x.y.z to a canonical up-to-7-digits form. +# +# Note that this function uses one more digit (compared to other +# instances in other version scripts) to give a bit more space to +# `rustc` since it will reach 1.100.0 in late 2026. +get_canonical_version() +{ + IFS=. + set -- $1 + echo $((100000 * $1 + 100 * $2 + $3)) +} + +if output=$("$@" --version 2>/dev/null); then + set -- $output + get_canonical_version $2 +else + echo 0 + exit 1 +fi diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 4366da278033..9c05a59f0184 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -128,10 +128,6 @@ # define unlikely(x) __builtin_expect(!!(x), 0) #endif -#ifndef __init -# define __init -#endif - #include /* diff --git a/tools/testing/memblock/linux/init.h b/tools/include/linux/init.h similarity index 76% rename from tools/testing/memblock/linux/init.h rename to tools/include/linux/init.h index 828e0ee0bc6c..51b5cde28639 100644 --- a/tools/testing/memblock/linux/init.h +++ b/tools/include/linux/init.h @@ -1,10 +1,16 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_INIT_H -#define _LINUX_INIT_H +#ifndef _TOOLS_LINUX_INIT_H_ +#define _TOOLS_LINUX_INIT_H_ #include -#include -#include + +#ifndef __init +# define __init +#endif + +#ifndef __exit +# define __exit +#endif #define __section(section) __attribute__((__section__(section))) @@ -28,7 +34,10 @@ struct obs_kernel_param { __aligned(__alignof__(struct obs_kernel_param)) = \ { __setup_str_##unique_id, fn, early } +#define __setup(str, fn) \ + __setup_param(str, fn, fn, 0) + #define early_param(str, fn) \ __setup_param(str, fn, fn, 1) -#endif +#endif /* _TOOLS_LINUX_INIT_H_ */ diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h index a48ff086899c..b7183576d8eb 100644 --- a/tools/include/linux/linkage.h +++ b/tools/include/linux/linkage.h @@ -1,6 +1,8 @@ #ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H #define _TOOLS_INCLUDE_LINUX_LINKAGE_H +#include + #define SYM_FUNC_START(x) .globl x; x: #define SYM_FUNC_END(x) diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index cad4f2927983..677c37e4a18c 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -25,6 +25,12 @@ static inline void *phys_to_virt(unsigned long address) return __va(address); } +#define virt_to_phys virt_to_phys +static inline phys_addr_t virt_to_phys(volatile void *address) +{ + return (phys_addr_t)address; +} + void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); static inline void totalram_pages_inc(void) diff --git a/tools/include/linux/pfn.h b/tools/include/linux/pfn.h index 7512a58189eb..f77a30d70152 100644 --- a/tools/include/linux/pfn.h +++ b/tools/include/linux/pfn.h @@ -7,4 +7,5 @@ #define PFN_UP(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) #define PFN_DOWN(x) ((x) >> PAGE_SHIFT) #define PFN_PHYS(x) ((phys_addr_t)(x) << PAGE_SHIFT) +#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) #endif diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index 0acb1fc14e19..8499f509f03e 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -12,6 +12,8 @@ void argv_free(char **argv); int strtobool(const char *s, bool *res); +#define strscpy strcpy + /* * glibc based builds needs the extern while uClibc doesn't. * However uClibc headers also define __GLIBC__ hence the hack below @@ -49,4 +51,5 @@ extern char *strim(char *); extern void remove_spaces(char *s); extern void *memchr_inv(const void *start, int c, size_t bytes); +extern unsigned long long memparse(const char *ptr, char **retptr); #endif /* _TOOLS_LINUX_STRING_H_ */ diff --git a/tools/lib/cmdline.c b/tools/lib/cmdline.c new file mode 100644 index 000000000000..c85f00f43c5e --- /dev/null +++ b/tools/lib/cmdline.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * From lib/cmdline.c + */ +#include + +#if __has_attribute(__fallthrough__) +# define fallthrough __attribute__((__fallthrough__)) +#else +# define fallthrough do {} while (0) /* fallthrough */ +#endif + +unsigned long long memparse(const char *ptr, char **retptr) +{ + char *endptr; /* local pointer to end of parsed string */ + + unsigned long long ret = strtoll(ptr, &endptr, 0); + + switch (*endptr) { + case 'E': + case 'e': + ret <<= 10; + fallthrough; + case 'P': + case 'p': + ret <<= 10; + fallthrough; + case 'T': + case 't': + ret <<= 10; + fallthrough; + case 'G': + case 'g': + ret <<= 10; + fallthrough; + case 'M': + case 'm': + ret <<= 10; + fallthrough; + case 'K': + case 'k': + ret <<= 10; + endptr++; + fallthrough; + default: + break; + } + + if (retptr) + *retptr = endptr; + + return ret; +} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 01237d167223..d086f207a3d3 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -177,6 +177,52 @@ static bool is_sibling_call(struct instruction *insn) return (is_static_jump(insn) && insn_call_dest(insn)); } +/* + * Checks if a string ends with another. + */ +static bool str_ends_with(const char *s, const char *sub) +{ + const int slen = strlen(s); + const int sublen = strlen(sub); + + if (sublen > slen) + return 0; + + return !memcmp(s + slen - sublen, sub, sublen); +} + +/* + * Checks if a function is a Rust "noreturn" one. + */ +static bool is_rust_noreturn(const struct symbol *func) +{ + /* + * If it does not start with "_R", then it is not a Rust symbol. + */ + if (strncmp(func->name, "_R", 2)) + return false; + + /* + * These are just heuristics -- we do not control the precise symbol + * name, due to the crate disambiguators (which depend on the compiler) + * as well as changes to the source code itself between versions (since + * these come from the Rust standard library). + */ + return str_ends_with(func->name, "_4core5sliceSp15copy_from_slice17len_mismatch_fail") || + str_ends_with(func->name, "_4core6option13unwrap_failed") || + str_ends_with(func->name, "_4core6result13unwrap_failed") || + str_ends_with(func->name, "_4core9panicking5panic") || + str_ends_with(func->name, "_4core9panicking9panic_fmt") || + str_ends_with(func->name, "_4core9panicking14panic_explicit") || + str_ends_with(func->name, "_4core9panicking14panic_nounwind") || + str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || + str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || + str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || + strstr(func->name, "_4core9panicking11panic_const24panic_const_") || + (strstr(func->name, "_4core5slice5index24slice_") && + str_ends_with(func->name, "_fail")); +} + /* * This checks to see if the given function is a "noreturn" function. * @@ -202,10 +248,14 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, if (!func) return false; - if (func->bind == STB_GLOBAL || func->bind == STB_WEAK) + if (func->bind == STB_GLOBAL || func->bind == STB_WEAK) { + if (is_rust_noreturn(func)) + return true; + for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) if (!strcmp(func->name, global_noreturns[i])) return true; + } if (func->bind == STB_WEAK) return false; diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index 1e8141ef1b15..e7da92489167 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -39,6 +39,8 @@ NORETURN(panic) NORETURN(panic_smp_self_stop) NORETURN(rest_init) NORETURN(rewind_stack_and_make_dead) +NORETURN(rust_begin_unwind) +NORETURN(rust_helper_BUG) NORETURN(sev_es_terminate) NORETURN(snp_abort) NORETURN(start_kernel) diff --git a/tools/testing/memblock/Makefile b/tools/testing/memblock/Makefile index 7a1ca694a982..d80982ccdc20 100644 --- a/tools/testing/memblock/Makefile +++ b/tools/testing/memblock/Makefile @@ -8,7 +8,7 @@ LDFLAGS += -fsanitize=address -fsanitize=undefined TARGETS = main TEST_OFILES = tests/alloc_nid_api.o tests/alloc_helpers_api.o tests/alloc_api.o \ tests/basic_api.o tests/common.o tests/alloc_exact_nid_api.o -DEP_OFILES = memblock.o lib/slab.o mmzone.o slab.o +DEP_OFILES = memblock.o lib/slab.o mmzone.o slab.o cmdline.o OFILES = main.o $(DEP_OFILES) $(TEST_OFILES) EXTR_SRC = ../../../mm/memblock.c diff --git a/tools/testing/memblock/linux/kernel.h b/tools/testing/memblock/linux/kernel.h index d2f148bd8902..4d1012d5be6e 100644 --- a/tools/testing/memblock/linux/kernel.h +++ b/tools/testing/memblock/linux/kernel.h @@ -8,5 +8,7 @@ #include #include #include +#include +#include #endif diff --git a/tools/testing/memblock/linux/mmzone.h b/tools/testing/memblock/linux/mmzone.h index 71546e15bdd3..bb682659a12d 100644 --- a/tools/testing/memblock/linux/mmzone.h +++ b/tools/testing/memblock/linux/mmzone.h @@ -3,6 +3,7 @@ #define _TOOLS_MMZONE_H #include +#include struct pglist_data *first_online_pgdat(void); struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index c5b00aca9def..1873ddbe16cc 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -14,7 +14,7 @@ #include "test.h" #include #include -#include "linux/init.h" +#include #define module_init(x) #define module_exit(x) diff --git a/tools/testing/shared/linux/init.h b/tools/testing/shared/linux/init.h deleted file mode 100644 index 81563c3dfce7..000000000000 --- a/tools/testing/shared/linux/init.h +++ /dev/null @@ -1,2 +0,0 @@ -#define __init -#define __exit