From 5f9ae91f7c0dbbc4195e2a6c8eedcaeb5b9e4cbb Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 9 Nov 2020 17:19:30 -0800 Subject: kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it Detect if pahole supports split BTF generation, and generate BTF for each selected kernel module, if it does. This is exposed to Makefiles and C code as CONFIG_DEBUG_INFO_BTF_MODULES flag. Kernel module BTF has to be re-generated if either vmlinux's BTF changes or module's .ko changes. To achieve that, I needed a helper similar to if_changed, but that would allow to filter out vmlinux from the list of updated dependencies for .ko building. I've put it next to the only place that uses and needs it, but it might be a better idea to just add it along the other if_changed variants into scripts/Kbuild.include. Each kernel module's BTF deduplication is pretty fast, as it does only incremental BTF deduplication on top of already deduplicated vmlinux BTF. To show the added build time, I've first ran make only just built kernel (to establish the baseline) and then forced only BTF re-generation, without regenerating .ko files. The build was performed with -j60 parallelization on 56-core machine. The final time also includes bzImage building, so it's not a pure BTF overhead. $ time make -j60 ... make -j60 27.65s user 10.96s system 782% cpu 4.933 total $ touch ~/linux-build/default/vmlinux && time make -j60 ... make -j60 123.69s user 27.85s system 1566% cpu 9.675 total So 4.6 seconds real time, with noticeable part spent in compressed vmlinux and bzImage building. To show size savings, I've built my kernel configuration with about 700 kernel modules with full BTF per each kernel module (without deduplicating against vmlinux) and with split BTF against deduplicated vmlinux (approach in this patch). Below are top 10 modules with biggest BTF sizes. And total size of BTF data across all kernel modules. It shows that split BTF "compresses" 115MB down to 5MB total. And the biggest kernel modules get a downsize from 500-570KB down to 200-300KB. FULL BTF ======== $ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }' 115710691 $ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10 ./drivers/gpu/drm/i915/i915.ko 570570 ./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 520240 ./drivers/gpu/drm/radeon/radeon.ko 503849 ./drivers/infiniband/hw/mlx5/mlx5_ib.ko 491777 ./fs/xfs/xfs.ko 411544 ./drivers/net/ethernet/intel/i40e/i40e.ko 403904 ./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 398754 ./drivers/infiniband/core/ib_core.ko 397224 ./fs/cifs/cifs.ko 386249 ./fs/nfsd/nfsd.ko 379738 SPLIT BTF ========= $ for f in $(find . -name '*.ko'); do size -A -d $f | grep BTF | awk '{print $2}'; done | awk '{ s += $1 } END { print s }' 5194047 $ for f in $(find . -name '*.ko'); do printf "%s %d\n" $f $(size -A -d $f | grep BTF | awk '{print $2}'); done | sort -nr -k2 | head -n10 ./drivers/gpu/drm/i915/i915.ko 293206 ./drivers/gpu/drm/radeon/radeon.ko 282103 ./fs/xfs/xfs.ko 222150 ./drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko 198503 ./drivers/infiniband/hw/mlx5/mlx5_ib.ko 198356 ./drivers/net/ethernet/broadcom/bnx2x/bnx2x.ko 113444 ./fs/cifs/cifs.ko 109379 ./arch/x86/kvm/kvm.ko 100225 ./drivers/gpu/drm/drm.ko 94827 ./drivers/infiniband/core/ib_core.ko 91188 Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201110011932.3201430-4-andrii@kernel.org --- scripts/Makefile.modfinal | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index ae01baf96f4e..02b892421f7a 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -6,6 +6,7 @@ PHONY := __modfinal __modfinal: +include include/config/auto.conf include $(srctree)/scripts/Kbuild.include # for c_flags @@ -36,8 +37,23 @@ quiet_cmd_ld_ko_o = LD [M] $@ -T scripts/module.lds -o $@ $(filter %.o, $^); \ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) -$(modules): %.ko: %.o %.mod.o scripts/module.lds FORCE - +$(call if_changed,ld_ko_o) +quiet_cmd_btf_ko = BTF [M] $@ + cmd_btf_ko = LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@ + +# Same as newer-prereqs, but allows to exclude specified extra dependencies +newer_prereqs_except = $(filter-out $(PHONY) $(1),$?) + +# Same as if_changed, but allows to exclude specified extra dependencies +if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check), \ + $(cmd); \ + printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:) + +# Re-generate module BTFs if either module's .ko or vmlinux changed +$(modules): %.ko: %.o %.mod.o scripts/module.lds vmlinux FORCE + +$(call if_changed_except,ld_ko_o,vmlinux) +ifdef CONFIG_DEBUG_INFO_BTF_MODULES + +$(if $(newer-prereqs),$(call cmd,btf_ko)) +endif targets += $(modules) $(modules:.ko=.mod.o) -- cgit v1.2.3-58-ga151 From 3f6719c7b62f0327c9091e26d0da10e65668229e Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 17 Nov 2020 23:29:28 +0000 Subject: bpf: Add bpf_bprm_opts_set helper The helper allows modification of certain bits on the linux_binprm struct starting with the secureexec bit which can be updated using the BPF_F_BPRM_SECUREEXEC flag. secureexec can be set by the LSM for privilege gaining executions to set the AT_SECURE auxv for glibc. When set, the dynamic linker disables the use of certain environment variables (like LD_PRELOAD). Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201117232929.2156341-1-kpsingh@chromium.org --- include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/bpf/bpf_lsm.c | 26 ++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 60 insertions(+) (limited to 'scripts') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 162999b12790..a52299b80b9d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3787,6 +3787,16 @@ union bpf_attr { * *ARG_PTR_TO_BTF_ID* of type *task_struct*. * Return * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3948,6 +3958,7 @@ union bpf_attr { FN(task_storage_get), \ FN(task_storage_delete), \ FN(get_current_task_btf), \ + FN(bprm_opts_set), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4119,6 +4130,11 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 553107f4706a..b4f27a874092 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,29 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return 0; } +/* Mask for all the currently supported BPRM option flags */ +#define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC + +BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) +{ + if (flags & ~BPF_F_BRPM_OPTS_MASK) + return -EINVAL; + + bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) + +const static struct bpf_func_proto bpf_bprm_opts_set_proto = { + .func = bpf_bprm_opts_set, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], + .arg2_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -71,6 +95,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: return &bpf_task_storage_delete_proto; + case BPF_FUNC_bprm_opts_set: + return &bpf_bprm_opts_set_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 31484377b8b1..c5bc947a70ad 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -418,6 +418,7 @@ class PrinterHelpers(Printer): 'struct bpf_tcp_sock', 'struct bpf_tunnel_key', 'struct bpf_xfrm_state', + 'struct linux_binprm', 'struct pt_regs', 'struct sk_reuseport_md', 'struct sockaddr', @@ -465,6 +466,7 @@ class PrinterHelpers(Printer): 'struct bpf_tcp_sock', 'struct bpf_tunnel_key', 'struct bpf_xfrm_state', + 'struct linux_binprm', 'struct pt_regs', 'struct sk_reuseport_md', 'struct sockaddr', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 162999b12790..a52299b80b9d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3787,6 +3787,16 @@ union bpf_attr { * *ARG_PTR_TO_BTF_ID* of type *task_struct*. * Return * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3948,6 +3958,7 @@ union bpf_attr { FN(task_storage_get), \ FN(task_storage_delete), \ FN(get_current_task_btf), \ + FN(bprm_opts_set), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4119,6 +4130,11 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ -- cgit v1.2.3-58-ga151 From e732b538f4557cd0a856bbce3cde55d2dfef3b03 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 20 Nov 2020 23:08:28 -0800 Subject: kbuild: Skip module BTF generation for out-of-tree external modules In some modes of operation, Kbuild allows to build modules without having vmlinux image around. In such case, generation of module BTF is impossible. This patch changes the behavior to emit a warning about impossibility of generating kernel module BTF, instead of breaking the build. This is especially important for out-of-tree external module builds. In vmlinux-less mode: $ make clean $ make modules_prepare $ touch drivers/acpi/button.c $ make M=drivers/acpi ... CC [M] drivers/acpi/button.o MODPOST drivers/acpi/Module.symvers LD [M] drivers/acpi/button.ko BTF [M] drivers/acpi/button.ko Skipping BTF generation for drivers/acpi/button.ko due to unavailability of vmlinux ... $ readelf -S ~/linux-build/default/drivers/acpi/button.ko | grep BTF -A1 ... empty ... Now with normal build: $ make all ... LD [M] drivers/acpi/button.ko BTF [M] drivers/acpi/button.ko ... $ readelf -S ~/linux-build/default/drivers/acpi/button.ko | grep BTF -A1 [60] .BTF PROGBITS 0000000000000000 00029310 000000000000ab3f 0000000000000000 0 0 1 Fixes: 5f9ae91f7c0d ("kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it") Reported-by: Bruce Allan Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Cc: Jessica Yu Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Link: https://lore.kernel.org/bpf/20201121070829.2612884-1-andrii@kernel.org --- scripts/Makefile.modfinal | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 02b892421f7a..d49ec001825d 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -38,7 +38,12 @@ quiet_cmd_ld_ko_o = LD [M] $@ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) quiet_cmd_btf_ko = BTF [M] $@ - cmd_btf_ko = LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@ + cmd_btf_ko = \ + if [ -f vmlinux ]; then \ + LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@; \ + else \ + printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ + fi; # Same as newer-prereqs, but allows to exclude specified extra dependencies newer_prereqs_except = $(filter-out $(PHONY) $(1),$?) @@ -49,7 +54,7 @@ if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check), \ printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:) # Re-generate module BTFs if either module's .ko or vmlinux changed -$(modules): %.ko: %.o %.mod.o scripts/module.lds vmlinux FORCE +$(modules): %.ko: %.o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE +$(call if_changed_except,ld_ko_o,vmlinux) ifdef CONFIG_DEBUG_INFO_BTF_MODULES +$(if $(newer-prereqs),$(call cmd,btf_ko)) -- cgit v1.2.3-58-ga151 From 27672f0d280a3f286a410a8db2004f46ace72a17 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Tue, 24 Nov 2020 15:12:09 +0000 Subject: bpf: Add a BPF helper for getting the IMA hash of an inode Provide a wrapper function to get the IMA hash of an inode. This helper is useful in fingerprinting files (e.g executables on execution) and using these fingerprints in detections like an executable unlinking itself. Since the ima_inode_hash can sleep, it's only allowed for sleepable LSM hooks. Signed-off-by: KP Singh Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20201124151210.1081188-3-kpsingh@chromium.org --- include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/bpf_lsm.c | 26 ++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 4 files changed, 50 insertions(+) (limited to 'scripts') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3ca6146f001a..c3458ec1f30a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3807,6 +3807,16 @@ union bpf_attr { * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) * Return * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3970,6 +3980,7 @@ union bpf_attr { FN(get_current_task_btf), \ FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index b4f27a874092..70e5e0b6d69d 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -15,6 +15,7 @@ #include #include #include +#include /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -75,6 +76,29 @@ const static struct bpf_func_proto bpf_bprm_opts_set_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) +{ + return ima_inode_hash(inode, dst, size); +} + +static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) +{ + return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); +} + +BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) + +const static struct bpf_func_proto bpf_ima_inode_hash_proto = { + .func = bpf_ima_inode_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -97,6 +121,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_delete_proto; case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; + case BPF_FUNC_ima_inode_hash: + return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index c5bc947a70ad..8b829748d488 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -436,6 +436,7 @@ class PrinterHelpers(Printer): 'struct xdp_md', 'struct path', 'struct btf_ptr', + 'struct inode', ] known_types = { '...', @@ -480,6 +481,7 @@ class PrinterHelpers(Printer): 'struct task_struct', 'struct path', 'struct btf_ptr', + 'struct inode', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3ca6146f001a..c3458ec1f30a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3807,6 +3807,16 @@ union bpf_attr { * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) * Return * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3970,6 +3980,7 @@ union bpf_attr { FN(get_current_task_btf), \ FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3-58-ga151 From 7de3697e9cbd4bd3d62bafa249d57990e1b8f294 Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Wed, 2 Dec 2020 16:54:24 -0800 Subject: Add auxiliary bus support Add support for the Auxiliary Bus, auxiliary_device and auxiliary_driver. It enables drivers to create an auxiliary_device and bind an auxiliary_driver to it. The bus supports probe/remove shutdown and suspend/resume callbacks. Each auxiliary_device has a unique string based id; driver binds to an auxiliary_device based on this id through the bus. Co-developed-by: Kiran Patil Co-developed-by: Ranjani Sridharan Co-developed-by: Fred Oh Co-developed-by: Leon Romanovsky Signed-off-by: Kiran Patil Signed-off-by: Ranjani Sridharan Signed-off-by: Fred Oh Signed-off-by: Leon Romanovsky Signed-off-by: Dave Ertman Reviewed-by: Pierre-Louis Bossart Reviewed-by: Shiraz Saleem Reviewed-by: Parav Pandit Reviewed-by: Dan Williams Reviewed-by: Martin Habets Link: https://lore.kernel.org/r/20201113161859.1775473-2-david.m.ertman@intel.com Signed-off-by: Dan Williams Link: https://lore.kernel.org/r/160695681289.505290.8978295443574440604.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/auxiliary_bus.rst | 234 +++++++++++++++++++++++++ Documentation/driver-api/index.rst | 1 + drivers/base/Kconfig | 3 + drivers/base/Makefile | 1 + drivers/base/auxiliary.c | 268 +++++++++++++++++++++++++++++ include/linux/auxiliary_bus.h | 78 +++++++++ include/linux/mod_devicetable.h | 8 + scripts/mod/devicetable-offsets.c | 3 + scripts/mod/file2alias.c | 8 + 9 files changed, 604 insertions(+) create mode 100644 Documentation/driver-api/auxiliary_bus.rst create mode 100644 drivers/base/auxiliary.c create mode 100644 include/linux/auxiliary_bus.h (limited to 'scripts') diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst new file mode 100644 index 000000000000..5dd7804631ef --- /dev/null +++ b/Documentation/driver-api/auxiliary_bus.rst @@ -0,0 +1,234 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +============= +Auxiliary Bus +============= + +In some subsystems, the functionality of the core device (PCI/ACPI/other) is +too complex for a single device to be managed by a monolithic driver +(e.g. Sound Open Firmware), multiple devices might implement a common +intersection of functionality (e.g. NICs + RDMA), or a driver may want to +export an interface for another subsystem to drive (e.g. SIOV Physical Function +export Virtual Function management). A split of the functinoality into child- +devices representing sub-domains of functionality makes it possible to +compartmentalize, layer, and distribute domain-specific concerns via a Linux +device-driver model. + +An example for this kind of requirement is the audio subsystem where a single +IP is handling multiple entities such as HDMI, Soundwire, local devices such as +mics/speakers etc. The split for the core's functionality can be arbitrary or +be defined by the DSP firmware topology and include hooks for test/debug. This +allows for the audio core device to be minimal and focused on hardware-specific +control and communication. + +Each auxiliary_device represents a part of its parent functionality. The +generic behavior can be extended and specialized as needed by encapsulating an +auxiliary_device within other domain-specific structures and the use of .ops +callbacks. Devices on the auxiliary bus do not share any structures and the use +of a communication channel with the parent is domain-specific. + +Note that ops are intended as a way to augment instance behavior within a class +of auxiliary devices, it is not the mechanism for exporting common +infrastructure from the parent. Consider EXPORT_SYMBOL_NS() to convey +infrastructure from the parent module to the auxiliary module(s). + + +When Should the Auxiliary Bus Be Used +===================================== + +The auxiliary bus is to be used when a driver and one or more kernel modules, +who share a common header file with the driver, need a mechanism to connect and +provide access to a shared object allocated by the auxiliary_device's +registering driver. The registering driver for the auxiliary_device(s) and the +kernel module(s) registering auxiliary_drivers can be from the same subsystem, +or from multiple subsystems. + +The emphasis here is on a common generic interface that keeps subsystem +customization out of the bus infrastructure. + +One example is a PCI network device that is RDMA-capable and exports a child +device to be driven by an auxiliary_driver in the RDMA subsystem. The PCI +driver allocates and registers an auxiliary_device for each physical +function on the NIC. The RDMA driver registers an auxiliary_driver that claims +each of these auxiliary_devices. This conveys data/ops published by the parent +PCI device/driver to the RDMA auxiliary_driver. + +Another use case is for the PCI device to be split out into multiple sub +functions. For each sub function an auxiliary_device is created. A PCI sub +function driver binds to such devices that creates its own one or more class +devices. A PCI sub function auxiliary device is likely to be contained in a +struct with additional attributes such as user defined sub function number and +optional attributes such as resources and a link to the parent device. These +attributes could be used by systemd/udev; and hence should be initialized +before a driver binds to an auxiliary_device. + +A key requirement for utilizing the auxiliary bus is that there is no +dependency on a physical bus, device, register accesses or regmap support. +These individual devices split from the core cannot live on the platform bus as +they are not physical devices that are controlled by DT/ACPI. The same +argument applies for not using MFD in this scenario as MFD relies on individual +function devices being physical devices. + +Auxiliary Device +================ + +An auxiliary_device represents a part of its parent device's functionality. It +is given a name that, combined with the registering drivers KBUILD_MODNAME, +creates a match_name that is used for driver binding, and an id that combined +with the match_name provide a unique name to register with the bus subsystem. + +Registering an auxiliary_device is a two-step process. First call +auxiliary_device_init(), which checks several aspects of the auxiliary_device +struct and performs a device_initialize(). After this step completes, any +error state must have a call to auxiliary_device_uninit() in its resolution path. +The second step in registering an auxiliary_device is to perform a call to +auxiliary_device_add(), which sets the name of the device and add the device to +the bus. + +Unregistering an auxiliary_device is also a two-step process to mirror the +register process. First call auxiliary_device_delete(), then call +auxiliary_device_uninit(). + +.. code-block:: c + + struct auxiliary_device { + struct device dev; + const char *name; + u32 id; + }; + +If two auxiliary_devices both with a match_name "mod.foo" are registered onto +the bus, they must have unique id values (e.g. "x" and "y") so that the +registered devices names are "mod.foo.x" and "mod.foo.y". If match_name + id +are not unique, then the device_add fails and generates an error message. + +The auxiliary_device.dev.type.release or auxiliary_device.dev.release must be +populated with a non-NULL pointer to successfully register the auxiliary_device. + +The auxiliary_device.dev.parent must also be populated. + +Auxiliary Device Memory Model and Lifespan +------------------------------------------ + +The registering driver is the entity that allocates memory for the +auxiliary_device and register it on the auxiliary bus. It is important to note +that, as opposed to the platform bus, the registering driver is wholly +responsible for the management for the memory used for the driver object. + +A parent object, defined in the shared header file, contains the +auxiliary_device. It also contains a pointer to the shared object(s), which +also is defined in the shared header. Both the parent object and the shared +object(s) are allocated by the registering driver. This layout allows the +auxiliary_driver's registering module to perform a container_of() call to go +from the pointer to the auxiliary_device, that is passed during the call to the +auxiliary_driver's probe function, up to the parent object, and then have +access to the shared object(s). + +The memory for the auxiliary_device is freed only in its release() callback +flow as defined by its registering driver. + +The memory for the shared object(s) must have a lifespan equal to, or greater +than, the lifespan of the memory for the auxiliary_device. The auxiliary_driver +should only consider that this shared object is valid as long as the +auxiliary_device is still registered on the auxiliary bus. It is up to the +registering driver to manage (e.g. free or keep available) the memory for the +shared object beyond the life of the auxiliary_device. + +The registering driver must unregister all auxiliary devices before its own +driver.remove() is completed. + +Auxiliary Drivers +================= + +Auxiliary drivers follow the standard driver model convention, where +discovery/enumeration is handled by the core, and drivers +provide probe() and remove() methods. They support power management +and shutdown notifications using the standard conventions. + +.. code-block:: c + + struct auxiliary_driver { + int (*probe)(struct auxiliary_device *, + const struct auxiliary_device_id *id); + int (*remove)(struct auxiliary_device *); + void (*shutdown)(struct auxiliary_device *); + int (*suspend)(struct auxiliary_device *, pm_message_t); + int (*resume)(struct auxiliary_device *); + struct device_driver driver; + const struct auxiliary_device_id *id_table; + }; + +Auxiliary drivers register themselves with the bus by calling +auxiliary_driver_register(). The id_table contains the match_names of auxiliary +devices that a driver can bind with. + +Example Usage +============= + +Auxiliary devices are created and registered by a subsystem-level core device +that needs to break up its functionality into smaller fragments. One way to +extend the scope of an auxiliary_device is to encapsulate it within a domain- +pecific structure defined by the parent device. This structure contains the +auxiliary_device and any associated shared data/callbacks needed to establish +the connection with the parent. + +An example is: + +.. code-block:: c + + struct foo { + struct auxiliary_device auxdev; + void (*connect)(struct auxiliary_device *auxdev); + void (*disconnect)(struct auxiliary_device *auxdev); + void *data; + }; + +The parent device then registers the auxiliary_device by calling +auxiliary_device_init(), and then auxiliary_device_add(), with the pointer to +the auxdev member of the above structure. The parent provides a name for the +auxiliary_device that, combined with the parent's KBUILD_MODNAME, creates a +match_name that is be used for matching and binding with a driver. + +Whenever an auxiliary_driver is registered, based on the match_name, the +auxiliary_driver's probe() is invoked for the matching devices. The +auxiliary_driver can also be encapsulated inside custom drivers that make the +core device's functionality extensible by adding additional domain-specific ops +as follows: + +.. code-block:: c + + struct my_ops { + void (*send)(struct auxiliary_device *auxdev); + void (*receive)(struct auxiliary_device *auxdev); + }; + + + struct my_driver { + struct auxiliary_driver auxiliary_drv; + const struct my_ops ops; + }; + +An example of this type of usage is: + +.. code-block:: c + + const struct auxiliary_device_id my_auxiliary_id_table[] = { + { .name = "foo_mod.foo_dev" }, + { }, + }; + + const struct my_ops my_custom_ops = { + .send = my_tx, + .receive = my_rx, + }; + + const struct my_driver my_drv = { + .auxiliary_drv = { + .name = "myauxiliarydrv", + .id_table = my_auxiliary_id_table, + .probe = my_probe, + .remove = my_remove, + .shutdown = my_shutdown, + }, + .ops = my_custom_ops, + }; diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index f357f3eb400c..86759a74b7f1 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -72,6 +72,7 @@ available subsections can be seen below. thermal/index fpga/index acpi/index + auxiliary_bus backlight/lp855x-driver.rst connector console diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 8d7001712062..040be48ce046 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -1,6 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 menu "Generic Driver Options" +config AUXILIARY_BUS + bool + config UEVENT_HELPER bool "Support for uevent helper" help diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 41369fc7004f..5e7bf9669a81 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -7,6 +7,7 @@ obj-y := component.o core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o container.o property.o cacheinfo.o \ swnode.o +obj-$(CONFIG_AUXILIARY_BUS) += auxiliary.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o obj-y += power/ obj-$(CONFIG_ISA_BUS_API) += isa.o diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c new file mode 100644 index 000000000000..ef2af417438b --- /dev/null +++ b/drivers/base/auxiliary.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019-2020 Intel Corporation + * + * Please see Documentation/driver-api/auxiliary_bus.rst for more information. + */ + +#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__ + +#include +#include +#include +#include +#include +#include +#include + +static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id, + const struct auxiliary_device *auxdev) +{ + for (; id->name[0]; id++) { + const char *p = strrchr(dev_name(&auxdev->dev), '.'); + int match_size; + + if (!p) + continue; + match_size = p - dev_name(&auxdev->dev); + + /* use dev_name(&auxdev->dev) prefix before last '.' char to match to */ + if (strlen(id->name) == match_size && + !strncmp(dev_name(&auxdev->dev), id->name, match_size)) + return id; + } + return NULL; +} + +static int auxiliary_match(struct device *dev, struct device_driver *drv) +{ + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + struct auxiliary_driver *auxdrv = to_auxiliary_drv(drv); + + return !!auxiliary_match_id(auxdrv->id_table, auxdev); +} + +static int auxiliary_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + const char *name, *p; + + name = dev_name(dev); + p = strrchr(name, '.'); + + return add_uevent_var(env, "MODALIAS=%s%.*s", AUXILIARY_MODULE_PREFIX, (int)(p - name), + name); +} + +static const struct dev_pm_ops auxiliary_dev_pm_ops = { + SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_generic_suspend, pm_generic_resume) +}; + +static int auxiliary_bus_probe(struct device *dev) +{ + struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + int ret; + + ret = dev_pm_domain_attach(dev, true); + if (ret) { + dev_warn(dev, "Failed to attach to PM Domain : %d\n", ret); + return ret; + } + + ret = auxdrv->probe(auxdev, auxiliary_match_id(auxdrv->id_table, auxdev)); + if (ret) + dev_pm_domain_detach(dev, true); + + return ret; +} + +static int auxiliary_bus_remove(struct device *dev) +{ + struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + int ret = 0; + + if (auxdrv->remove) + ret = auxdrv->remove(auxdev); + dev_pm_domain_detach(dev, true); + + return ret; +} + +static void auxiliary_bus_shutdown(struct device *dev) +{ + struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + + if (auxdrv->shutdown) + auxdrv->shutdown(auxdev); +} + +static struct bus_type auxiliary_bus_type = { + .name = "auxiliary", + .probe = auxiliary_bus_probe, + .remove = auxiliary_bus_remove, + .shutdown = auxiliary_bus_shutdown, + .match = auxiliary_match, + .uevent = auxiliary_uevent, + .pm = &auxiliary_dev_pm_ops, +}; + +/** + * auxiliary_device_init - check auxiliary_device and initialize + * @auxdev: auxiliary device struct + * + * This is the first step in the two-step process to register an auxiliary_device. + * + * When this function returns an error code, then the device_initialize will *not* have + * been performed, and the caller will be responsible to free any memory allocated for the + * auxiliary_device in the error path directly. + * + * It returns 0 on success. On success, the device_initialize has been performed. After this + * point any error unwinding will need to include a call to auxiliary_device_uninit(). + * In this post-initialize error scenario, a call to the device's .release callback will be + * triggered, and all memory clean-up is expected to be handled there. + */ +int auxiliary_device_init(struct auxiliary_device *auxdev) +{ + struct device *dev = &auxdev->dev; + + if (!dev->parent) { + pr_err("auxiliary_device has a NULL dev->parent\n"); + return -EINVAL; + } + + if (!auxdev->name) { + pr_err("auxiliary_device has a NULL name\n"); + return -EINVAL; + } + + dev->bus = &auxiliary_bus_type; + device_initialize(&auxdev->dev); + return 0; +} +EXPORT_SYMBOL_GPL(auxiliary_device_init); + +/** + * __auxiliary_device_add - add an auxiliary bus device + * @auxdev: auxiliary bus device to add to the bus + * @modname: name of the parent device's driver module + * + * This is the second step in the two-step process to register an auxiliary_device. + * + * This function must be called after a successful call to auxiliary_device_init(), which + * will perform the device_initialize. This means that if this returns an error code, then a + * call to auxiliary_device_uninit() must be performed so that the .release callback will + * be triggered to free the memory associated with the auxiliary_device. + * + * The expectation is that users will call the "auxiliary_device_add" macro so that the caller's + * KBUILD_MODNAME is automatically inserted for the modname parameter. Only if a user requires + * a custom name would this version be called directly. + */ +int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname) +{ + struct device *dev = &auxdev->dev; + int ret; + + if (!modname) { + pr_err("auxiliary device modname is NULL\n"); + return -EINVAL; + } + + ret = dev_set_name(dev, "%s.%s.%d", modname, auxdev->name, auxdev->id); + if (ret) { + pr_err("auxiliary device dev_set_name failed: %d\n", ret); + return ret; + } + + ret = device_add(dev); + if (ret) + dev_err(dev, "adding auxiliary device failed!: %d\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(__auxiliary_device_add); + +/** + * auxiliary_find_device - auxiliary device iterator for locating a particular device. + * @start: Device to begin with + * @data: Data to pass to match function + * @match: Callback function to check device + * + * This function returns a reference to a device that is 'found' + * for later use, as determined by the @match callback. + * + * The callback should return 0 if the device doesn't match and non-zero + * if it does. If the callback returns non-zero, this function will + * return to the caller and not iterate over any more devices. + */ +struct auxiliary_device * +auxiliary_find_device(struct device *start, const void *data, + int (*match)(struct device *dev, const void *data)) +{ + struct device *dev; + + dev = bus_find_device(&auxiliary_bus_type, start, data, match); + if (!dev) + return NULL; + + return to_auxiliary_dev(dev); +} +EXPORT_SYMBOL_GPL(auxiliary_find_device); + +/** + * __auxiliary_driver_register - register a driver for auxiliary bus devices + * @auxdrv: auxiliary_driver structure + * @owner: owning module/driver + * @modname: KBUILD_MODNAME for parent driver + */ +int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner, + const char *modname) +{ + if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table)) + return -EINVAL; + + if (auxdrv->name) + auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s.%s", modname, auxdrv->name); + else + auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s", modname); + if (!auxdrv->driver.name) + return -ENOMEM; + + auxdrv->driver.owner = owner; + auxdrv->driver.bus = &auxiliary_bus_type; + auxdrv->driver.mod_name = modname; + + return driver_register(&auxdrv->driver); +} +EXPORT_SYMBOL_GPL(__auxiliary_driver_register); + +/** + * auxiliary_driver_unregister - unregister a driver + * @auxdrv: auxiliary_driver structure + */ +void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv) +{ + driver_unregister(&auxdrv->driver); + kfree(auxdrv->driver.name); +} +EXPORT_SYMBOL_GPL(auxiliary_driver_unregister); + +static int __init auxiliary_bus_init(void) +{ + return bus_register(&auxiliary_bus_type); +} + +static void __exit auxiliary_bus_exit(void) +{ + bus_unregister(&auxiliary_bus_type); +} + +module_init(auxiliary_bus_init); +module_exit(auxiliary_bus_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Auxiliary Bus"); +MODULE_AUTHOR("David Ertman "); +MODULE_AUTHOR("Kiran Patil "); diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h new file mode 100644 index 000000000000..282fbf7bf9af --- /dev/null +++ b/include/linux/auxiliary_bus.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2019-2020 Intel Corporation + * + * Please see Documentation/driver-api/auxiliary_bus.rst for more information. + */ + +#ifndef _AUXILIARY_BUS_H_ +#define _AUXILIARY_BUS_H_ + +#include +#include +#include + +struct auxiliary_device { + struct device dev; + const char *name; + u32 id; +}; + +struct auxiliary_driver { + int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id); + int (*remove)(struct auxiliary_device *auxdev); + void (*shutdown)(struct auxiliary_device *auxdev); + int (*suspend)(struct auxiliary_device *auxdev, pm_message_t state); + int (*resume)(struct auxiliary_device *auxdev); + const char *name; + struct device_driver driver; + const struct auxiliary_device_id *id_table; +}; + +static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) +{ + return container_of(dev, struct auxiliary_device, dev); +} + +static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv) +{ + return container_of(drv, struct auxiliary_driver, driver); +} + +int auxiliary_device_init(struct auxiliary_device *auxdev); +int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname); +#define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME) + +static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev) +{ + put_device(&auxdev->dev); +} + +static inline void auxiliary_device_delete(struct auxiliary_device *auxdev) +{ + device_del(&auxdev->dev); +} + +int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner, + const char *modname); +#define auxiliary_driver_register(auxdrv) \ + __auxiliary_driver_register(auxdrv, THIS_MODULE, KBUILD_MODNAME) + +void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); + +/** + * module_auxiliary_driver() - Helper macro for registering an auxiliary driver + * @__auxiliary_driver: auxiliary driver struct + * + * Helper macro for auxiliary drivers which do not do anything special in + * module init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_auxiliary_driver(__auxiliary_driver) \ + module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister) + +struct auxiliary_device * +auxiliary_find_device(struct device *start, const void *data, + int (*match)(struct device *dev, const void *data)); + +#endif /* _AUXILIARY_BUS_H_ */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5b08a473cdba..c425290b21e2 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -838,4 +838,12 @@ struct mhi_device_id { kernel_ulong_t driver_data; }; +#define AUXILIARY_NAME_SIZE 32 +#define AUXILIARY_MODULE_PREFIX "auxiliary:" + +struct auxiliary_device_id { + char name[AUXILIARY_NAME_SIZE]; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 27007c18e754..e377f52dbfa3 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -243,5 +243,8 @@ int main(void) DEVID(mhi_device_id); DEVID_FIELD(mhi_device_id, chan); + DEVID(auxiliary_device_id); + DEVID_FIELD(auxiliary_device_id, name); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 2417dd1dee33..fb4827027536 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1364,6 +1364,13 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, mhi_device_id, chan); sprintf(alias, MHI_DEVICE_MODALIAS_FMT, *chan); + return 1; +} + +static int do_auxiliary_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD_ADDR(symval, auxiliary_device_id, name); + sprintf(alias, AUXILIARY_MODULE_PREFIX "%s", *name); return 1; } @@ -1442,6 +1449,7 @@ static const struct devtable devtable[] = { {"tee", SIZE_tee_client_device_id, do_tee_entry}, {"wmi", SIZE_wmi_device_id, do_wmi_entry}, {"mhi", SIZE_mhi_device_id, do_mhi_entry}, + {"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry}, }; /* Create MODULE_ALIAS() statements. -- cgit v1.2.3-58-ga151 From 4f19cab76136e800a3f04d8c9aa4d8e770e3d3d8 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Fri, 4 Dec 2020 12:36:05 +0100 Subject: bpf: Add a bpf_sock_from_file helper While eBPF programs can check whether a file is a socket by file->f_op == &socket_file_ops, they cannot convert the void private_data pointer to a struct socket BTF pointer. In order to do this a new helper wrapping sock_from_file is added. This is useful to tracing programs but also other program types inheriting this set of helpers such as iterators or LSM programs. Signed-off-by: Florent Revest Signed-off-by: Daniel Borkmann Acked-by: KP Singh Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20201204113609.1850150-2-revest@google.com --- include/uapi/linux/bpf.h | 9 +++++++++ kernel/trace/bpf_trace.c | 20 ++++++++++++++++++++ scripts/bpf_helpers_doc.py | 4 ++++ tools/include/uapi/linux/bpf.h | 9 +++++++++ 4 files changed, 42 insertions(+) (limited to 'scripts') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1233f14f659f..30b477a26482 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3822,6 +3822,14 @@ union bpf_attr { * The **hash_algo** is returned on success, * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. + * + * struct socket *bpf_sock_from_file(struct file *file) + * Description + * If the given file represents a socket, returns the associated + * socket. + * Return + * A pointer to a struct socket on success or NULL if the file is + * not a socket. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3986,6 +3994,7 @@ union bpf_attr { FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ + FN(sock_from_file), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cb9d7478ef0c..0cf0a6331482 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1270,6 +1270,24 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .arg5_type = ARG_ANYTHING, }; +BPF_CALL_1(bpf_sock_from_file, struct file *, file) +{ + return (unsigned long) sock_from_file(file); +} + +BTF_ID_LIST(bpf_sock_from_file_btf_ids) +BTF_ID(struct, socket) +BTF_ID(struct, file) + +static const struct bpf_func_proto bpf_sock_from_file_proto = { + .func = bpf_sock_from_file, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .ret_btf_id = &bpf_sock_from_file_btf_ids[0], + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_sock_from_file_btf_ids[1], +}; + const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1366,6 +1384,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_per_cpu_ptr_proto; case BPF_FUNC_bpf_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; + case BPF_FUNC_sock_from_file: + return &bpf_sock_from_file_proto; default: return NULL; } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 8b829748d488..867ada23281c 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -437,6 +437,8 @@ class PrinterHelpers(Printer): 'struct path', 'struct btf_ptr', 'struct inode', + 'struct socket', + 'struct file', ] known_types = { '...', @@ -482,6 +484,8 @@ class PrinterHelpers(Printer): 'struct path', 'struct btf_ptr', 'struct inode', + 'struct socket', + 'struct file', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1233f14f659f..30b477a26482 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3822,6 +3822,14 @@ union bpf_attr { * The **hash_algo** is returned on success, * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. + * + * struct socket *bpf_sock_from_file(struct file *file) + * Description + * If the given file represents a socket, returns the associated + * socket. + * Return + * A pointer to a struct socket on success or NULL if the file is + * not a socket. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3986,6 +3994,7 @@ union bpf_attr { FN(bprm_opts_set), \ FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ + FN(sock_from_file), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3-58-ga151