March 2022 - Linux-kselftest-mirror

[PATCH bpf v4] bpf: Support dual-stack sockets in bpf_tcp_check_syncookie

by Maxim Mikityanskiy

bpf_tcp_gen_syncookie looks at the IP version in the IP header and validates the address family of the socket. It supports IPv4 packets in AF_INET6 dual-stack sockets. On the other hand, bpf_tcp_check_syncookie looks only at the address family of the socket, ignoring the real IP version in headers, and validates only the packet size. This implementation has some drawbacks: 1. Packets are not validated properly, allowing a BPF program to trick bpf_tcp_check_syncookie into handling an IPv6 packet on an IPv4 socket. 2. Dual-stack sockets fail the checks on IPv4 packets. IPv4 clients end up receiving a SYNACK with the cookie, but the following ACK gets dropped. This patch fixes these issues by changing the checks in bpf_tcp_check_syncookie to match the ones in bpf_tcp_gen_syncookie. IP version from the header is taken into account, and it is validated properly with address family. Fixes: 399040847084 ("bpf: add helper to check for a valid SYN cookie") Signed-off-by: Maxim Mikityanskiy <maximmi(a)nvidia.com> Reviewed-by: Tariq Toukan <tariqt(a)nvidia.com> --- net/core/filter.c | 17 +++- .../bpf/test_tcp_check_syncookie_user.c | 78 ++++++++++++++----- 2 files changed, 72 insertions(+), 23 deletions(-) v2 changes: moved from bpf-next to bpf. v3 changes: added a selftest. v4 changes: none, CCed Jakub and Arthur from Cloudflare. diff --git a/net/core/filter.c b/net/core/filter.c index a7044e98765e..64470a727ef7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (!th->ack || th->rst || th->syn) return -ENOENT; + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; - switch (sk->sk_family) { - case AF_INET: - if (unlikely(iph_len < sizeof(struct iphdr))) + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) - case AF_INET6: + case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; + if (sk->sk_family != AF_INET6) + return -EINVAL; + ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index b9e991d43155..e7775d3bbe08 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -18,8 +18,9 @@ #include "bpf_rlimit.h" #include "cgroup_helpers.h" -static int start_server(const struct sockaddr *addr, socklen_t len) +static int start_server(const struct sockaddr *addr, socklen_t len, bool dual) { + int mode = !dual; int fd; fd = socket(addr->sa_family, SOCK_STREAM, 0); @@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len) goto out; } + if (addr->sa_family == AF_INET6) { + if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode, + sizeof(mode)) == -1) { + log_err("Failed to set the dual-stack mode"); + goto close_out; + } + } + if (bind(fd, addr, len) == -1) { log_err("Failed to bind server socket"); goto close_out; @@ -47,24 +56,17 @@ static int start_server(const struct sockaddr *addr, socklen_t len) return fd; } -static int connect_to_server(int server_fd) +static int connect_to_server(const struct sockaddr *addr, socklen_t len) { - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); int fd = -1; - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - fd = socket(addr.ss_family, SOCK_STREAM, 0); + fd = socket(addr->sa_family, SOCK_STREAM, 0); if (fd == -1) { log_err("Failed to create client socket"); goto out; } - if (connect(fd, (const struct sockaddr *)&addr, len) == -1) { + if (connect(fd, (const struct sockaddr *)addr, len) == -1) { log_err("Fail to connect to server"); goto close_out; } @@ -116,7 +118,8 @@ static int get_map_fd_by_prog_id(int prog_id, bool *xdp) return map_fd; } -static int run_test(int server_fd, int results_fd, bool xdp) +static int run_test(int server_fd, int results_fd, bool xdp, + const struct sockaddr *addr, socklen_t len) { int client = -1, srv_client = -1; int ret = 0; @@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp) goto err; } - client = connect_to_server(server_fd); + client = connect_to_server(addr, len); if (client == -1) goto err; @@ -199,12 +202,30 @@ static int run_test(int server_fd, int results_fd, bool xdp) return ret; } +static bool get_port(int server_fd, in_port_t *port) +{ + struct sockaddr_in addr; + socklen_t len = sizeof(addr); + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return false; + } + + /* sin_port and sin6_port are located at the same offset. */ + *port = addr.sin_port; + return true; +} + int main(int argc, char **argv) { struct sockaddr_in addr4; struct sockaddr_in6 addr6; + struct sockaddr_in addr4dual; + struct sockaddr_in6 addr6dual; int server = -1; int server_v6 = -1; + int server_dual = -1; int results = -1; int err = 0; bool xdp; @@ -224,25 +245,43 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); addr4.sin_port = 0; + memcpy(&addr4dual, &addr4, sizeof(addr4dual)); memset(&addr6, 0, sizeof(addr6)); addr6.sin6_family = AF_INET6; addr6.sin6_addr = in6addr_loopback; addr6.sin6_port = 0; - server = start_server((const struct sockaddr *)&addr4, sizeof(addr4)); - if (server == -1) + memset(&addr6dual, 0, sizeof(addr6dual)); + addr6dual.sin6_family = AF_INET6; + addr6dual.sin6_addr = in6addr_any; + addr6dual.sin6_port = 0; + + server = start_server((const struct sockaddr *)&addr4, sizeof(addr4), + false); + if (server == -1 || !get_port(server, &addr4.sin_port)) goto err; server_v6 = start_server((const struct sockaddr *)&addr6, - sizeof(addr6)); - if (server_v6 == -1) + sizeof(addr6), false); + if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port)) + goto err; + + server_dual = start_server((const struct sockaddr *)&addr6dual, + sizeof(addr6dual), true); + if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port)) + goto err; + + if (run_test(server, results, xdp, + (const struct sockaddr *)&addr4, sizeof(addr4))) goto err; - if (run_test(server, results, xdp)) + if (run_test(server_v6, results, xdp, + (const struct sockaddr *)&addr6, sizeof(addr6))) goto err; - if (run_test(server_v6, results, xdp)) + if (run_test(server_dual, results, xdp, + (const struct sockaddr *)&addr4dual, sizeof(addr4dual))) goto err; printf("ok\n"); @@ -252,6 +291,7 @@ int main(int argc, char **argv) out: close(server); close(server_v6); + close(server_dual); close(results); return err; } -- 2.30.2

3 years

3
3
0 0

[RFC v4 0/8] Proposal for a GPU cgroup controller

by T.J. Mercier

This patch series revisits the proposal for a GPU cgroup controller to track and limit memory allocations by various device/allocator subsystems. The patch series also contains a simple prototype to illustrate how Android intends to implement DMA-BUF allocator attribution using the GPU cgroup controller. The prototype does not include resource limit enforcements. Changelog: v4: Skip test if not run as root per Shuah Khan Add better test logging for abnormal child termination per Shuah Khan Adjust ordering of charge/uncharge during transfer to avoid potentially hitting cgroup limit per Michal Koutný Adjust gpucg_try_charge critical section for charge transfer functionality Fix uninitialized return code error for dmabuf_try_charge error case v3: Remove Upstreaming Plan from gpu-cgroup.rst per John Stultz Use more common dual author commit message format per John Stultz Remove android from binder changes title per Todd Kjos Add a kselftest for this new behavior per Greg Kroah-Hartman Include details on behavior for all combinations of kernel/userspace versions in changelog (thanks Suren Baghdasaryan) per Greg Kroah-Hartman. Fix pid and uid types in binder UAPI header v2: See the previous revision of this change submitted by Hridya Valsaraju at: https://lore.kernel.org/all/20220115010622.3185921-1-hridya@google.com/ Move dma-buf cgroup charge transfer from a dma_buf_op defined by every heap to a single dma-buf function for all heaps per Daniel Vetter and Christian König. Pointers to struct gpucg and struct gpucg_device tracking the current associations were added to the dma_buf struct to achieve this. Fix incorrect Kconfig help section indentation per Randy Dunlap. History of the GPU cgroup controller ==================================== The GPU/DRM cgroup controller came into being when a consensus[1] was reached that the resources it tracked were unsuitable to be integrated into memcg. Originally, the proposed controller was specific to the DRM subsystem and was intended to track GEM buffers and GPU-specific resources[2]. In order to help establish a unified memory accounting model for all GPU and all related subsystems, Daniel Vetter put forth a suggestion to move it out of the DRM subsystem so that it can be used by other DMA-BUF exporters as well[3]. This RFC proposes an interface that does the same. [1]: https://patchwork.kernel.org/project/dri-devel/cover/20190501140438.9506-1-… [2]: https://lore.kernel.org/amd-gfx/20210126214626.16260-1-brian.welty@intel.co… [3]: https://lore.kernel.org/amd-gfx/YCVOl8%2F87bqRSQei@phenom.ffwll.local/ Hridya Valsaraju (5): gpu: rfc: Proposal for a GPU cgroup controller cgroup: gpu: Add a cgroup controller for allocator attribution of GPU memory dmabuf: heaps: export system_heap buffers with GPU cgroup charging dmabuf: Add gpu cgroup charge transfer function binder: Add a buffer flag to relinquish ownership of fds T.J. Mercier (3): dmabuf: Use the GPU cgroup charge/uncharge APIs binder: use __kernel_pid_t and __kernel_uid_t for userspace selftests: Add binder cgroup gpu memory transfer test Documentation/gpu/rfc/gpu-cgroup.rst | 183 +++++++ Documentation/gpu/rfc/index.rst | 4 + drivers/android/binder.c | 26 + drivers/dma-buf/dma-buf.c | 107 ++++ drivers/dma-buf/dma-heap.c | 27 + drivers/dma-buf/heaps/system_heap.c | 3 + include/linux/cgroup_gpu.h | 139 +++++ include/linux/cgroup_subsys.h | 4 + include/linux/dma-buf.h | 22 +- include/linux/dma-heap.h | 11 + include/uapi/linux/android/binder.h | 5 +- init/Kconfig | 7 + kernel/cgroup/Makefile | 1 + kernel/cgroup/gpu.c | 362 +++++++++++++ .../selftests/drivers/android/binder/Makefile | 8 + .../drivers/android/binder/binder_util.c | 254 +++++++++ .../drivers/android/binder/binder_util.h | 32 ++ .../selftests/drivers/android/binder/config | 4 + .../binder/test_dmabuf_cgroup_transfer.c | 484 ++++++++++++++++++ 19 files changed, 1679 insertions(+), 4 deletions(-) create mode 100644 Documentation/gpu/rfc/gpu-cgroup.rst create mode 100644 include/linux/cgroup_gpu.h create mode 100644 kernel/cgroup/gpu.c create mode 100644 tools/testing/selftests/drivers/android/binder/Makefile create mode 100644 tools/testing/selftests/drivers/android/binder/binder_util.c create mode 100644 tools/testing/selftests/drivers/android/binder/binder_util.h create mode 100644 tools/testing/selftests/drivers/android/binder/config create mode 100644 tools/testing/selftests/drivers/android/binder/test_dmabuf_cgroup_transfer.c -- 2.35.1.1021.g381101b075-goog

3 years

4
21
0 0

Re: [RFC v1 01/10] roadtest: import libvhost-user from QEMU

by Johannes Berg

On Fri, 2022-03-11 at 17:24 +0100, Vincent Whitchurch wrote: > Import the libvhost-user from QEMU for use in the implementation of the > virtio devices in the roadtest backend. > So hm, I wonder if this is the sensible thing to do? Not that I mind importing qemu code, but: 1) the implementation is rather complex in some places, and has support for a LOT of virtio/vhost-user features that are really not needed in these cases, for performance etc. It's also close to 4k LOC. 2) the implementation doesn't support time-travel mode which might come in handy We have another implementation that might be simpler: https://github.com/linux-test-project/usfstl/blob/main/src/vhost.c but it probably has dependencies on other things in this library, but vhost.c itself is only ~1k LOC. (But I need to update it, I'm sure we have some unpublished bugfixes etc. in this code) johannes

3 years

2
1
0 0

[PATCH bpf-next v3 00/17] Introduce eBPF support for HID devices

by Benjamin Tissoires

Hi, This is a followup of my v1 at [0] and v2 at [1]. The short summary of the previous cover letter and discussions is that HID could benefit from BPF for the following use cases: - simple fixup of report descriptor: benefits are faster development time and testing, with the produced bpf program being shipped in the kernel directly (the shipping part is *not* addressed here). - Universal Stylus Interface: allows a user-space program to define its own kernel interface - Surface Dial: somehow similar to the previous one except that userspace can decide to change the shape of the exported device - firewall: still partly missing there, there is not yet interception of hidraw calls, but it's coming in a followup series, I promise - tracing: well, tracing. I think I addressed the comments from the previous version, but there are a few things I'd like to note here: - I did not take the various rev-by and tested-by (thanks a lot for those) because the uapi changed significantly in v3, so I am not very confident in taking those rev-by blindly - I mentioned in my discussion with Song that I'll put a summary of the uapi in the cover letter, but I ended up adding a (long) file in the Documentation directory. So please maybe start by reading 17/17 to have an overview of what I want to achieve - I added in the libbpf and bpf the new type BPF_HID_DRIVER_EVENT, even though I don't have a user of it right now in the kernel. I wanted to have them in the docs, but we might not want to have them ready here. In terms of code, it just means that we can attach such programs types but that they will never get triggered. Anyway, I have been mulling on this for the past 2 weeks, and I think that maybe sharing this now is better than me just starring at the code over and over. Short summary of changes: v3: === - squashed back together most of the libbpf and bpf changes into bigger commits that give a better overview of the whole interactions - reworked the user API to not expose .data as a directly accessible field from the context, but instead forces everyone to use hid_bpf_get_data (or get/set_bits) - added BPF_HID_DRIVER_EVENT (see note above) - addressed the various nitpicks from v2 - added a big Documentation file (and so adding now the doc maintainers to the long list of recipients) v2: === - split the series by subsystem (bpf, HID, libbpf, selftests and samples) - Added an extra patch at the beginning to not require CAP_NET_ADMIN for BPF_PROG_TYPE_LIRC_MODE2 (please shout if this is wrong) - made the bpf context attached to HID program of dynamic size: * the first 1 kB will be able to be addressed directly * the rest can be retrieved through bpf_hid_{set|get}_data (note that I am definitivey not happy with that API, because there is part of it in bits and other in bytes. ouch) - added an extra patch to prevent non GPL HID bpf programs to be loaded of type BPF_PROG_TYPE_HID * same here, not really happy but I don't know where to put that check in verifier.c - added a new flag BPF_F_INSERT_HEAD for BPF_LINK_CREATE syscall when in used with HID program types. * this flag is used for tracing, to be able to load a program before any others that might already have been inserted and that might change the data stream. Cheers, Benjamin [0] https://lore.kernel.org/linux-input/20220224110828.2168231-1-benjamin.tisso… [1] https://lore.kernel.org/linux-input/20220304172852.274126-1-benjamin.tissoi… Benjamin Tissoires (17): bpf: add new is_sys_admin_prog_type() helper bpf: introduce hid program type bpf/verifier: prevent non GPL programs to be loaded against HID libbpf: add HID program type and API HID: hook up with bpf HID: allow to change the report descriptor from an eBPF program selftests/bpf: add tests for the HID-bpf initial implementation selftests/bpf: add report descriptor fixup tests selftests/bpf: Add a test for BPF_F_INSERT_HEAD selftests/bpf: add test for user call of HID bpf programs samples/bpf: add new hid_mouse example bpf/hid: add more HID helpers HID: bpf: implement hid_bpf_get|set_bits HID: add implementation of bpf_hid_raw_request selftests/bpf: add tests for hid_{get|set}_bits helpers selftests/bpf: add tests for bpf_hid_hw_request Documentation: add HID-BPF docs Documentation/hid/hid-bpf.rst | 444 +++++++++++ Documentation/hid/index.rst | 1 + drivers/hid/Makefile | 1 + drivers/hid/hid-bpf.c | 328 ++++++++ drivers/hid/hid-core.c | 34 +- include/linux/bpf-hid.h | 127 +++ include/linux/bpf_types.h | 4 + include/linux/hid.h | 36 +- include/uapi/linux/bpf.h | 67 ++ include/uapi/linux/bpf_hid.h | 71 ++ include/uapi/linux/hid.h | 10 + kernel/bpf/Makefile | 3 + kernel/bpf/btf.c | 1 + kernel/bpf/hid.c | 728 +++++++++++++++++ kernel/bpf/syscall.c | 27 +- kernel/bpf/verifier.c | 7 + samples/bpf/.gitignore | 1 + samples/bpf/Makefile | 4 + samples/bpf/hid_mouse_kern.c | 117 +++ samples/bpf/hid_mouse_user.c | 129 +++ tools/include/uapi/linux/bpf.h | 67 ++ tools/lib/bpf/libbpf.c | 23 +- tools/lib/bpf/libbpf.h | 2 + tools/lib/bpf/libbpf.map | 1 + tools/testing/selftests/bpf/config | 3 + tools/testing/selftests/bpf/prog_tests/hid.c | 788 +++++++++++++++++++ tools/testing/selftests/bpf/progs/hid.c | 205 +++++ 27 files changed, 3204 insertions(+), 25 deletions(-) create mode 100644 Documentation/hid/hid-bpf.rst create mode 100644 drivers/hid/hid-bpf.c create mode 100644 include/linux/bpf-hid.h create mode 100644 include/uapi/linux/bpf_hid.h create mode 100644 kernel/bpf/hid.c create mode 100644 samples/bpf/hid_mouse_kern.c create mode 100644 samples/bpf/hid_mouse_user.c create mode 100644 tools/testing/selftests/bpf/prog_tests/hid.c create mode 100644 tools/testing/selftests/bpf/progs/hid.c -- 2.35.1

3 years

5
43
0 0

[PATCH] Fix kernel build with LLVM=1

by Grigory Vasilyev

The wrong logic is using 1 as a suffix instead of -1. So the build script tries to find clang1 file instead of clang. GEN Makefile HOSTCC scripts/basic/fixdep /bin/sh: line 1: clang1: command not found make[2]: *** [/build/linux/scripts/Makefile.host:95: scripts/basic/fixdep] Error 127 make[1]: *** [/build/linux/Makefile:564: scripts_basic] Error 2 make: *** [Makefile:219: __sub-make] Error 2 Fixes: b8321ed4a40c("Merge tag 'kbuild-v5.18-v2'") Signed-off-by: Grigory Vasilyev <h0tc0d3(a)gmail.com> Reported-by: Grigory Vasilyev <h0tc0d3(a)gmail.com> --- Makefile | 4 ++-- tools/scripts/Makefile.include | 4 ++-- tools/testing/selftests/lib.mk | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Makefile b/Makefile index 18ecb49f1af6..efca890d4ea3 100644 --- a/Makefile +++ b/Makefile @@ -426,8 +426,8 @@ HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null) ifneq ($(LLVM),) ifneq ($(filter %/,$(LLVM)),) LLVM_PREFIX := $(LLVM) -else ifneq ($(filter -%,$(LLVM)),) -LLVM_SUFFIX := $(LLVM) +else ifneq (,$(findstring -, $(LLVM))) +LLVM_SUFFIX := $(filter -%, $(LLVM)) endif HOSTCC = $(LLVM_PREFIX)clang$(LLVM_SUFFIX) diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 0efb8f2b33ce..c7a56d7f0bad 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -54,8 +54,8 @@ endef ifneq ($(LLVM),) ifneq ($(filter %/,$(LLVM)),) LLVM_PREFIX := $(LLVM) -else ifneq ($(filter -%,$(LLVM)),) -LLVM_SUFFIX := $(LLVM) +else ifneq (,$(findstring -, $(LLVM))) +LLVM_SUFFIX := $(filter -%, $(LLVM)) endif $(call allow-override,CC,$(LLVM_PREFIX)clang$(LLVM_SUFFIX)) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 2a2d240cdc1b..42af066cf39e 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -3,8 +3,8 @@ ifneq ($(LLVM),) ifneq ($(filter %/,$(LLVM)),) LLVM_PREFIX := $(LLVM) -else ifneq ($(filter -%,$(LLVM)),) -LLVM_SUFFIX := $(LLVM) +else ifneq (,$(findstring -, $(LLVM))) +LLVM_SUFFIX := $(filter -%, $(LLVM)) endif CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) -- 2.35.1

3 years

2
1
0 0

[PATCH 1/2] [RFC] rtc: expose direct access to hardware alarm time in debugfs

by Mateusz Jończyk

Before Linux 5.17, there was a problem with the CMOS RTC driver: cmos_read_alarm() and cmos_set_alarm() did not check for the UIP (Update in progress) bit, which could have caused it to sometimes fail silently and read bogus values or do not set the alarm correctly. Luckily, this issue was masked by cmos_read_time() invocations in core RTC code - see https://marc.info/?l=linux-rtc&m=164858416511425&w=4 To avoid such a problem in the future in some other driver, I wrote a test unit that reads the alarm time many times in a row. As the alarm time is usually read once and cached by the RTC core, this requires a way for userspace to trigger direct alarm time read from hardware. I think that debugfs is the natural choice for this. So, introduce /sys/kernel/debug/rtc/rtcX/wakealarm_raw. This interface as implemented here does not seem to be that useful to userspace, so there is little risk that it will become kernel ABI. Is this approach correct and worth it? TODO: - should I add a new Kconfig option (like CONFIG_RTC_INTF_DEBUGFS), or just use CONFIG_DEBUG_FS here? I wouldn't like to create unnecessary config options in the kernel. Signed-off-by: Mateusz Jończyk <mat.jonczyk(a)o2.pl> Cc: Alessandro Zummo <a.zummo(a)towertech.it> Cc: Alexandre Belloni <alexandre.belloni(a)bootlin.com> Cc: Shuah Khan <shuah(a)kernel.org> --- drivers/rtc/Makefile | 1 + drivers/rtc/class.c | 3 ++ drivers/rtc/debugfs.c | 112 ++++++++++++++++++++++++++++++++++++++++ drivers/rtc/interface.c | 3 +- include/linux/rtc.h | 16 ++++++ 5 files changed, 133 insertions(+), 2 deletions(-) create mode 100644 drivers/rtc/debugfs.c diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 678a8ef4abae..50e166a97f54 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -14,6 +14,7 @@ rtc-core-$(CONFIG_RTC_NVMEM) += nvmem.o rtc-core-$(CONFIG_RTC_INTF_DEV) += dev.o rtc-core-$(CONFIG_RTC_INTF_PROC) += proc.o rtc-core-$(CONFIG_RTC_INTF_SYSFS) += sysfs.o +rtc-core-$(CONFIG_DEBUG_FS) += debugfs.o obj-$(CONFIG_RTC_LIB_KUNIT_TEST) += lib_test.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 4b460c61f1d8..5673b7b26c0d 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -334,6 +334,7 @@ static void devm_rtc_unregister_device(void *data) * Remove innards of this RTC, then disable it, before * letting any rtc_class_open() users access it again */ + rtc_debugfs_del_device(rtc); rtc_proc_del_device(rtc); if (!test_bit(RTC_NO_CDEV, &rtc->flags)) cdev_device_del(&rtc->char_dev, &rtc->dev); @@ -417,6 +418,7 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) } rtc_proc_add_device(rtc); + rtc_debugfs_add_device(rtc); dev_info(rtc->dev.parent, "registered as %s\n", dev_name(&rtc->dev)); @@ -476,6 +478,7 @@ static int __init rtc_init(void) } rtc_class->pm = RTC_CLASS_DEV_PM_OPS; rtc_dev_init(); + rtc_debugfs_init(); return 0; } subsys_initcall(rtc_init); diff --git a/drivers/rtc/debugfs.c b/drivers/rtc/debugfs.c new file mode 100644 index 000000000000..5ceed5504033 --- /dev/null +++ b/drivers/rtc/debugfs.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +/* + * Debugfs interface for testing RTC alarms. + */ +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/rtc.h> + +static struct dentry *rtc_main_debugfs_dir; + +void rtc_debugfs_init(void) +{ + struct dentry *ret = debugfs_create_dir("rtc", NULL); + + // No error is critical here + if (!IS_ERR(ret)) + rtc_main_debugfs_dir = ret; +} + +/* + * Handler for /sys/kernel/debug/rtc/rtcX/wakealarm_raw . + * This function reads the RTC alarm time directly from hardware. If the RTC + * alarm is enabled, this function returns the alarm time modulo 24h in seconds + * since midnight. + * + * Should be only used for testing of the RTC alarm read functionality in + * drivers - to make sure that the driver returns consistent values. + * + * Used in tools/testing/selftests/rtc/rtctest.c . + */ +static int rtc_debugfs_alarm_read(void *p, u64 *out) +{ + int ret; + struct rtc_device *rtc = p; + struct rtc_wkalrm alm; + + /* Using rtc_read_alarm_internal() instead of __rtc_read_alarm() will + * allow us to avoid any interaction with rtc_read_time() and possibly + * see more issues. + */ + ret = rtc_read_alarm_internal(rtc, &alm); + if (ret != 0) + return ret; + + if (!alm.enabled) { + *out = -1; + return 0; + } + + /* It does not matter if the device does not support seconds resolution + * of the RTC alarm. + */ + if (test_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->features)) + alm.time.tm_sec = 0; + + /* The selftest code works with fully defined alarms only. + */ + if (alm.time.tm_sec == -1 || alm.time.tm_min == -1 || alm.time.tm_hour == -1) { + *out = -2; + return 0; + } + + /* Check if the alarm time is correct. + * rtc_valid_tm() does not allow fields containing "-1", so put in + * something to satisfy it. + */ + if (alm.time.tm_year == -1) + alm.time.tm_year = 100; + if (alm.time.tm_mon == -1) + alm.time.tm_mon = 0; + if (alm.time.tm_mday == -1) + alm.time.tm_mday = 1; + if (rtc_valid_tm(&alm.time)) + return -EINVAL; + + /* We do not duplicate the logic in __rtc_read_alarm() and instead only + * return the alarm time modulo 24h, which all devices should support. + * This should be enough for testing purposes. + */ + *out = alm.time.tm_hour * 3600 + alm.time.tm_min * 60 + alm.time.tm_sec; + + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(rtc_alarm_raw, rtc_debugfs_alarm_read, NULL, "%lld\n"); + +void rtc_debugfs_add_device(struct rtc_device *rtc) +{ + struct dentry *dev_dir; + + if (!rtc_main_debugfs_dir) + return; + + dev_dir = debugfs_create_dir(dev_name(&rtc->dev), rtc_main_debugfs_dir); + + if (IS_ERR(dev_dir)) { + rtc->debugfs_dir = NULL; + return; + } + rtc->debugfs_dir = dev_dir; + + if (test_bit(RTC_FEATURE_ALARM, rtc->features) && rtc->ops->read_alarm) { + debugfs_create_file("wakealarm_raw", 0444, dev_dir, + rtc, &rtc_alarm_raw); + } +} + +void rtc_debugfs_del_device(struct rtc_device *rtc) +{ + debugfs_remove_recursive(rtc->debugfs_dir); + rtc->debugfs_dir = NULL; +} diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index d8e835798153..51c801c82472 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -175,8 +175,7 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) } EXPORT_SYMBOL_GPL(rtc_set_time); -static int rtc_read_alarm_internal(struct rtc_device *rtc, - struct rtc_wkalrm *alarm) +int rtc_read_alarm_internal(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 47fd1c2d3a57..4665bc238a94 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -41,6 +41,7 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) #include <linux/mutex.h> #include <linux/timerqueue.h> #include <linux/workqueue.h> +#include <linux/debugfs.h> extern struct class *rtc_class; @@ -152,6 +153,10 @@ struct rtc_device { time64_t offset_secs; bool set_start_time; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_dir; +#endif + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -190,6 +195,7 @@ extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); +int rtc_read_alarm_internal(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern int rtc_initialize_alarm(struct rtc_device *rtc, @@ -262,4 +268,14 @@ int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps) return 0; } #endif + +#ifdef CONFIG_DEBUG_FS +void rtc_debugfs_init(void); +void rtc_debugfs_add_device(struct rtc_device *rtc); +void rtc_debugfs_del_device(struct rtc_device *rtc); +#else /* CONFIG_DEBUG_FS */ +static inline void rtc_debugfs_init(void) {} +static inline void rtc_debugfs_add_device(struct rtc_device *rtc) {} +static inline void rtc_debugfs_del_device(struct rtc_device *rtc) {} +#endif /* CONFIG_DEBUG_FS */ #endif /* _LINUX_RTC_H_ */ -- 2.25.1

3 years

3
6
0 0

[PATCH] selftest/vm: clarify error statement in gup_test

by Sidhartha Kumar

Print two possible reasons /sys/kernel/debug/gup_test cannot be opened to help users of this test diagnose failures. Signed-off-by: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> Cc: stable(a)vger.kernel.org # 5.15+ --- tools/testing/selftests/vm/gup_test.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c index fe043f67798b0..c496bcefa7a0e 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/vm/gup_test.c @@ -205,7 +205,9 @@ int main(int argc, char **argv) gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); if (gup_fd == -1) { - perror("open"); + perror("failed to open /sys/kernel/debug/gup_test"); + printf("check if CONFIG_GUP_TEST is enabled in kernel config\n"); + printf("check if debugfs is mounted at /sys/kernel/debug\n"); exit(1); } -- 2.24.1

3 years

3
2
0 0

[PATCH v2] selftests/sgx: Use rip relative addressing for encl_stack

by Jarkko Sakkinen

Simplify the test_encl_bootstrap.S flow by using RIP-relative addressing. The compiler automatically puts relative addresses for RIP index addresses. In order to get a clean and tweakless solution, define separate entry point for each TCS. Cc: Reinette Chatre <reinette.chatre(a)intel.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v2: * Based on Reinette's example, make proper structuring with separate entry points for each TCS. --- .../selftests/sgx/test_encl_bootstrap.S | 30 +++++++++++-------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S index 82fb0dfcbd23..cc2353f38bcc 100644 --- a/tools/testing/selftests/sgx/test_encl_bootstrap.S +++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S @@ -10,12 +10,13 @@ .section ".tcs", "aw" .balign 4096 +encl_tcs1: .fill 1, 8, 0 # STATE (set by CPU) .fill 1, 8, 0 # FLAGS .quad encl_ssa_tcs1 # OSSA .fill 1, 4, 0 # CSSA (set by CPU) .fill 1, 4, 1 # NSSA - .quad encl_entry # OENTRY + .quad encl_entry1 # OENTRY .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) .fill 1, 8, 0 # OFSBASE .fill 1, 8, 0 # OGSBASE @@ -23,13 +24,13 @@ .fill 1, 4, 0xFFFFFFFF # GSLIMIT .fill 4024, 1, 0 # Reserved - # TCS2 +encl_tcs2: .fill 1, 8, 0 # STATE (set by CPU) .fill 1, 8, 0 # FLAGS .quad encl_ssa_tcs2 # OSSA .fill 1, 4, 0 # CSSA (set by CPU) .fill 1, 4, 1 # NSSA - .quad encl_entry # OENTRY + .quad encl_entry2 # OENTRY .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) .fill 1, 8, 0 # OFSBASE .fill 1, 8, 0 # OGSBASE @@ -39,15 +40,19 @@ .text -encl_entry: - # RBX contains the base address for TCS, which is the first address - # inside the enclave for TCS #1 and one page into the enclave for - # TCS #2. By adding the value of encl_stack to it, we get - # the absolute address for the stack. - lea (encl_stack)(%rbx), %rax +encl_entry1: + lea (encl_stack1)(%rip), %rax xchg %rsp, %rax push %rax + jmp encl_continue +encl_entry2: + lea (encl_stack2)(%rip), %rax + xchg %rsp, %rax + push %rax + jmp encl_continue + +encl_continue: push %rcx # push the address after EENTER push %rbx # push the enclave base address @@ -84,13 +89,14 @@ encl_entry: encl_ssa_tcs1: .space 4096 + encl_ssa_tcs2: .space 4096 +encl_stack1: .balign 4096 - # Stack of TCS #1 .space 4096 -encl_stack: + +encl_stack2: .balign 4096 - # Stack of TCS #2 .space 4096 -- 2.35.1

3 years

2
2
0 0

Re: [PATCH v2 1/2] selftests/sgx: Use rip relative addressing for encl_stack

by Reinette Chatre

On 3/30/2022 12:03 PM, Jarkko Sakkinen wrote: > On Wed, 2022-03-30 at 10:40 -0700, Reinette Chatre wrote: >> Could you please elaborate how the compiler will fix it up? > > Sure. > > Here's the disassembly of the RBX version: > > [0x000021a9]> pi 1 > lea rax, [rbx + loc.encl_stack] > > Here's the same with s/RBX/RIP/: > > [0x000021a9]> pi 5 > lea rax, loc.encl_stack > > Compiler will substitute correct offset relative to the RIP, > well, because it can and it makes sense. It does not make sense to me because, as proven with my test, the two threads end up sharing the same stack memory. Reinette

3 years

2
3
0 0

[PATCH v2] selftests/seccomp: Add SKIP for failed unshare()

by davidcomponentone＠gmail.com

From: Yang Guang <yang.guang5(a)zte.com.cn> Running the seccomp tests under the kernel with "defconfig" shouldn't fail. Because the CONFIG_USER_NS is not supported in "defconfig". Skipping this case instead of failing it is better. Signed-off-by: Yang Guang <yang.guang5(a)zte.com.cn> Signed-off-by: David Yang <davidcomponentone(a)gmail.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Changes from v1->v2: - Modify the commit message to better understand. --- tools/testing/selftests/seccomp/seccomp_bpf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 313bb0cbfb1e..e9a61cb2eb88 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -3742,7 +3742,10 @@ TEST(user_notification_fault_recv) struct seccomp_notif req = {}; struct seccomp_notif_resp resp = {}; - ASSERT_EQ(unshare(CLONE_NEWUSER), 0); + ASSERT_EQ(unshare(CLONE_NEWUSER), 0) { + if (errno == EINVAL) + SKIP(return, "kernel missing CLONE_NEWUSER support"); + } listener = user_notif_syscall(__NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER); -- 2.30.2

3 years

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror March 2022