- Linux-kselftest-mirror - lists.linaro.org

[PATCH bpf-next 2/2] selftests/bpf: Test kfunc bpf_strcasecmp

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Add testsuites for kfunc bpf_strcasecmp. Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c | 6 ++++++ tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 5 +++++ 2 files changed, 11 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c index 53af438bd998..99d72c68f76a 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c @@ -31,6 +31,8 @@ char *invalid_kern_ptr = (char *)-1; /* Passing NULL to string kfuncs (treated as a userspace ptr) */ SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_null1(void *ctx) { return bpf_strcmp(NULL, "hello"); } SEC("syscall") __retval(USER_PTR_ERR)int test_strcmp_null2(void *ctx) { return bpf_strcmp("hello", NULL); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_null1(void *ctx) { return bpf_strcasecmp(NULL, "HELLO"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcasecmp_null2(void *ctx) { return bpf_strcasecmp("HELLO", NULL); } SEC("syscall") __retval(USER_PTR_ERR)int test_strchr_null(void *ctx) { return bpf_strchr(NULL, 'a'); } SEC("syscall") __retval(USER_PTR_ERR)int test_strchrnul_null(void *ctx) { return bpf_strchrnul(NULL, 'a'); } SEC("syscall") __retval(USER_PTR_ERR)int test_strnchr_null(void *ctx) { return bpf_strnchr(NULL, 1, 'a'); } @@ -49,6 +51,8 @@ SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null2(void *ctx) { return /* Passing userspace ptr to string kfuncs */ SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { return bpf_strcmp(user_ptr, "hello"); } SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr2(void *ctx) { return bpf_strcmp("hello", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr1(void *ctx) { return bpf_strcasecmp(user_ptr, "HELLO"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr2(void *ctx) { return bpf_strcasecmp("HELLO", user_ptr); } SEC("syscall") __retval(USER_PTR_ERR) int test_strchr_user_ptr(void *ctx) { return bpf_strchr(user_ptr, 'a'); } SEC("syscall") __retval(USER_PTR_ERR) int test_strchrnul_user_ptr(void *ctx) { return bpf_strchrnul(user_ptr, 'a'); } SEC("syscall") __retval(USER_PTR_ERR) int test_strnchr_user_ptr(void *ctx) { return bpf_strnchr(user_ptr, 1, 'a'); } @@ -69,6 +73,8 @@ SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr2(void *ctx) { re /* Passing invalid kernel ptr to string kfuncs should always return -EFAULT */ SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault1(void *ctx) { return bpf_strcmp(invalid_kern_ptr, "hello"); } SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault2(void *ctx) { return bpf_strcmp("hello", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault1(void *ctx) { return bpf_strcasecmp(invalid_kern_ptr, "HELLO"); } +SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault2(void *ctx) { return bpf_strcasecmp("HELLO", invalid_kern_ptr); } SEC("syscall") __retval(-EFAULT) int test_strchr_pagefault(void *ctx) { return bpf_strchr(invalid_kern_ptr, 'a'); } SEC("syscall") __retval(-EFAULT) int test_strchrnul_pagefault(void *ctx) { return bpf_strchrnul(invalid_kern_ptr, 'a'); } SEC("syscall") __retval(-EFAULT) int test_strnchr_pagefault(void *ctx) { return bpf_strnchr(invalid_kern_ptr, 1, 'a'); } diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..67830456637b 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -12,6 +12,11 @@ char str[] = "hello world"; /* Functional tests */ __test(0) int test_strcmp_eq(void *ctx) { return bpf_strcmp(str, "hello world"); } __test(1) int test_strcmp_neq(void *ctx) { return bpf_strcmp(str, "hello"); } +__test(0) int test_strcasecmp_eq1(void *ctx) { return bpf_strcasecmp(str, "hello world"); } +__test(0) int test_strcasecmp_eq2(void *ctx) { return bpf_strcasecmp(str, "HELLO WORLD"); } +__test(0) int test_strcasecmp_eq3(void *ctx) { return bpf_strcasecmp(str, "HELLO world"); } +__test(1) int test_strcasecmp_neq1(void *ctx) { return bpf_strcasecmp(str, "hello"); } +__test(1) int test_strcasecmp_neq2(void *ctx) { return bpf_strcasecmp(str, "HELLO"); } __test(1) int test_strchr_found(void *ctx) { return bpf_strchr(str, 'e'); } __test(11) int test_strchr_null(void *ctx) { return bpf_strchr(str, '\0'); } __test(-ENOENT) int test_strchr_notfound(void *ctx) { return bpf_strchr(str, 'x'); } -- 2.51.0

1 month, 1 week

2
1
0 0

[PATCH bpf-next 0/2] bpf: Add kfunc bpf_strcasecmp()

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Kfunc already support bpf_strcmp, this patchset introduce bpf_strcasecmp and add some selftests. Rong Tao (2): bpf: add bpf_strcasecmp kfunc selftests/bpf: Test kfunc bpf_strcasecmp kernel/bpf/helpers.c | 56 ++++++++++++++----- .../bpf/progs/string_kfuncs_failure1.c | 6 ++ .../bpf/progs/string_kfuncs_success.c | 5 ++ 3 files changed, 53 insertions(+), 14 deletions(-) -- 2.51.0

1 month, 1 week

1
0
0 0

[PATCH] selftests: net: fix spelling and grammar mistakes

by Praveen Balakrishnan

Fix several spelling and grammatical mistakes in output messages from the net selftests to improve readability. Only the message strings for the test output have been modified. No changes to the functional logic of the tests have been made. Signed-off-by: Praveen Balakrishnan <praveen.balakrishnan(a)magd.ox.ac.uk> --- tools/testing/selftests/net/openvswitch/ovs-dpctl.py | 2 +- tools/testing/selftests/net/rps_default_mask.sh | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 8a0396bfaf99..b521e0dea506 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -1877,7 +1877,7 @@ class OvsPacket(GenericNetlinkSocket): elif msg["cmd"] == OvsPacket.OVS_PACKET_CMD_EXECUTE: up.execute(msg) else: - print("Unkonwn cmd: %d" % msg["cmd"]) + print("Unknown cmd: %d" % msg["cmd"]) except NetlinkError as ne: raise ne diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh index 4287a8529890..b200019b3c80 100755 --- a/tools/testing/selftests/net/rps_default_mask.sh +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -54,16 +54,16 @@ cleanup echo 1 > /proc/sys/net/core/rps_default_mask setup -chk_rps "changing rps_default_mask dont affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK +chk_rps "changing rps_default_mask doesn't affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK echo 3 > /proc/sys/net/core/rps_default_mask -chk_rps "changing rps_default_mask dont affect existing netns" $NETNS lo 0 +chk_rps "changing rps_default_mask doesn't affect existing netns" $NETNS lo 0 ip link add name $VETH type veth peer netns $NETNS name $VETH ip link set dev $VETH up ip -n $NETNS link set dev $VETH up -chk_rps "changing rps_default_mask affect newly created devices" "" $VETH 3 -chk_rps "changing rps_default_mask don't affect newly child netns[II]" $NETNS $VETH 0 +chk_rps "changing rps_default_mask affects newly created devices" "" $VETH 3 +chk_rps "changing rps_default_mask doesn't affect newly child netns[II]" $NETNS $VETH 0 ip link del dev $VETH ip netns del $NETNS @@ -72,8 +72,8 @@ chk_rps "rps_default_mask is 0 by default in child netns" "$NETNS" lo 0 ip netns exec $NETNS sysctl -qw net.core.rps_default_mask=1 ip link add name $VETH type veth peer netns $NETNS name $VETH -chk_rps "changing rps_default_mask in child ns don't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK +chk_rps "changing rps_default_mask in child ns doesn't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK chk_rps "changing rps_default_mask in child ns affects new childns devices" $NETNS $VETH 1 -chk_rps "changing rps_default_mask in child ns don't affect existing devices" $NETNS lo 0 +chk_rps "changing rps_default_mask in child ns doesn't affect existing devices" $NETNS lo 0 exit $ret -- 2.39.5

1 month, 1 week

3
2
0 0

[RFC PATCH v2 bpf-next 0/3] bpf: cgroup: support writing and freezing cgroups from BPF

by Djalal Harouni

This patch series add support to write cgroup interfaces from BPF. It is useful to freeze a cgroup hierarchy on suspicious activity for a more thorough analysis before killing it. Planned users of this feature are: systemd and BPF tools where the cgroup hierarchy could be a system service, user session, k8s pod or a container. The writing happens via kernfs nodes and the cgroup must be on the default hierarchy. It implements the requests and feedback from v1 [1] where now we use a unified path for cgroup user space and BPF writing. So I want to validate that this is the right approach first. Todo: * Limit size of data to be written. * Further tests. * Add cgroup kill support. # RFC v1 -> v2 * Implemented Alexei and Tejun requests [1]. * Unified path where user space or BPF writing end up taking directly a kernfs_node with an example on the "cgroup.freeze" interface. [1] https://lore.kernel.org/bpf/20240327225334.58474-1-tixxdz@gmail.com/ Djalal Harouni (3): kernfs: cgroup: support writing cgroup interfaces from a kernfs node bpf: cgroup: Add BPF Kfunc to write cgroup interfaces selftests/bpf: add selftest for bpf_cgroup_write_interface include/linux/cgroup.h | 3 ++ kernel/bpf/helpers.c | 45 +++++ kernel/cgroup/cgroup.c | 102 +++++++ tools/testing/selftests/bpf/prog_tests/task_freeze_cgroup.c | 172 ++++++++++++ tools/testing/selftests/bpf/progs/test_task_freeze_cgroup.c | 155 ++++++++++ 5 files changed, 471 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/task_freeze_cgroup.c create mode 100644 tools/testing/selftests/bpf/progs/test_task_freeze_cgroup.c -- 2.34.1

1 month, 1 week

4
15
0 0

[PATCH net] selftests: drv-net: csum: fix interface name for remote host

by Jakub Kicinski

Use cfg.remote_ifname for arguments of remote command. Without this UDP tests fail in NIPA where local interface is called enp1s0 and remote enp0s4. Fixes: 1d0dc857b5d8 ("selftests: drv-net: add checksum tests") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: willemb(a)google.com CC: petrm(a)nvidia.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/hw/csum.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index cd23af875317..3e3a89a34afe 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -17,7 +17,7 @@ from lib.py import bkg, cmd, wait_port_listen ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}" rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}" - tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}" + tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}" with bkg(rx_cmd, exit_wait=True): wait_port_listen(34000, proto="udp") @@ -37,7 +37,7 @@ from lib.py import bkg, cmd, wait_port_listen if extra_args != "-U -Z": extra_args += " -r 1" - rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}" + rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}" tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}" with bkg(rx_cmd, host=cfg.remote, exit_wait=True): -- 2.51.0

1 month, 1 week

4
3
0 0

[PATCH v4 0/2] KVM: guest_memfd: use write for population

by Kalyazin, Nikita

[ based on kvm/next ] Implement guest_memfd allocation and population via the write syscall. This is useful in non-CoCo use cases where the host can access guest memory. Even though the same can also be achieved via userspace mapping and memcpying from userspace, write provides a more performant option because it does not need to set page tables and it does not cause a page fault for every page like memcpy would. Note that memcpy cannot be accelerated via MADV_POPULATE_WRITE as it is not supported by guest_memfd and relies on GUP. Populating 512MiB of guest_memfd on a x86 machine: - via memcpy: 436 ms - via write: 202 ms (-54%) v4: - Switch from implementing the write callback to write_iter - Remove conditional compilation - Rebase to kvm/next v3: - https://lore.kernel.org/kvm/20250303130838.28812-1-kalyazin@amazon.com - David/Mike D: Only compile support for the write syscall if CONFIG_KVM_GMEM_SHARED_MEM (now gone) is enabled. v2: - https://lore.kernel.org/kvm/20241129123929.64790-1-kalyazin@amazon.com - Switch from an ioctl to the write syscall to implement population v1: - https://lore.kernel.org/kvm/20241024095429.54052-1-kalyazin@amazon.com Nikita Kalyazin (2): KVM: guest_memfd: add generic population via write KVM: selftests: update guest_memfd write tests .../testing/selftests/kvm/guest_memfd_test.c | 85 +++++++++++++++++-- virt/kvm/guest_memfd.c | 64 +++++++++++++- 2 files changed, 142 insertions(+), 7 deletions(-) base-commit: a6ad54137af92535cfe32e19e5f3bc1bb7dbd383 -- 2.50.1

1 month, 1 week

4
9
0 0

[PATCH net-next v4] selftests: net: add test for ipv6 fragmentation

by Brett A C Sheffield

Add selftest for the IPv6 fragmentation regression which affected several stable kernels. Commit a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable without some prerequisite commits. This caused a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning -1 (EMSGSIZE). Add selftest to check for this issue by attempting to send a packet larger than the interface MTU. The packet will be fragmented on a working kernel, with sendmsg(2) correctly returning the expected number of bytes sent. When the regression is present, sendmsg returns -1 and sets errno to EMSGSIZE. Link: https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com Signed-off-by: Brett A C Sheffield <bacs(a)librecast.net> --- v4 changes: - fix "else should follow close brace" (checkpatch ERROR) v3 changes: - add usleep instead of busy polling on sendmsg - simplify error handling by using error() and leaving cleanup to O/S - use loopback interface - don't bother creating TAP - send to localhost (::1) v2 changes: - remove superfluous namespace calls - unshare(2) suffices - remove usleep(). Don't wait for the interface to be ready, just send, and handle the (less likely) error case by retrying. - set destination address only once - document our use of the IPv6 link-local source address - send to port 9 (DISCARD) instead of 4242 (DONT PANIC) - ensure sockets are closed on failure paths - use KSFT exit codes for clarity v3: https://lore.kernel.org/netdev/20250901112248.5218-1-bacs@librecast.net v2: https://lore.kernel.org/netdev/20250831102908.14655-1-bacs@librecast.net v1: https://lore.kernel.org/netdev/20250825092548.4436-3-bacs@librecast.net tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_fragmentation.c | 144 ++++++++++++++++++ 3 files changed, 146 insertions(+) create mode 100644 tools/testing/selftests/net/ipv6_fragmentation.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 47c293c2962f..3d4b4a53dfda 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,6 +16,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +ipv6_fragmentation log.txt msg_oob msg_zerocopy diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index eef0b8f8a7b0..276e0481d996 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -117,6 +117,7 @@ TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh +TEST_GEN_PROGS += ipv6_fragmentation TEST_PROGS += route_hint.sh # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c new file mode 100644 index 000000000000..6d1311e26501 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Brett A C Sheffield <bacs(a)librecast.net> + * + * Kernel selftest for the IPv6 fragmentation regression which affected stable + * kernels: + * + * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com + * + * Commit: a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable + * without some prerequisite commits. + * + * This caused a regression when sending IPv6 UDP packets by preventing + * fragmentation and instead returning -1 (EMSGSIZE). + * + * This selftest demonstrates the issue by sending an IPv6 UDP packet to + * localhost (::1) on the loopback interface from the autoconfigured link-local + * address. + * + * sendmsg(2) returns bytes sent correctly on a working kernel, and returns -1 + * (EMSGSIZE) when the regression is present. + * + * The regression was not present in the mainline kernel, but add this test to + * catch similar breakage in future. + */ + +#define _GNU_SOURCE + +#include <error.h> +#include <fcntl.h> +#include <linux/if_tun.h> +#include <net/if.h> +#include <netinet/in.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <unistd.h> +#include "../kselftest.h" + +#define MTU 1500 +#define LARGER_THAN_MTU 8192 + +/* bring up interface */ +static int interface_up(int ctl, struct ifreq *ifr) +{ + if (ioctl(ctl, SIOCGIFFLAGS, ifr) == -1) + error(KSFT_FAIL, errno, "ioctl SIOCGIFFLAGS"); + ifr->ifr_flags = ifr->ifr_flags | IFF_UP; + return ioctl(ctl, SIOCSIFFLAGS, ifr); +} + +/* no need to wait for DAD in our namespace */ +static int disable_dad(char *ifname) +{ + char sysvar[] = "/proc/sys/net/ipv6/conf/%s/accept_dad"; + char fname[IFNAMSIZ + sizeof(sysvar)]; + int fd; + + snprintf(fname, sizeof(fname), sysvar, ifname); + fd = open(fname, O_WRONLY); + if (fd == -1) + error(KSFT_FAIL, errno, "open accept_dad"); + if (write(fd, "0", 1) != 1) + error(KSFT_FAIL, errno, "write accept_dad"); + + return close(fd); +} + +static int setup(void) +{ + struct ifreq ifr = { + .ifr_name = "lo" + }; + int fd = -1; + int ctl; + + /* we need to set MTU, so do this in a namespace to play nicely */ + if (unshare(CLONE_NEWNET) == -1) + error(KSFT_FAIL, errno, "unshare"); + + ctl = socket(AF_LOCAL, SOCK_STREAM, 0); + if (ctl == -1) + error(KSFT_FAIL, errno, "socket"); + + /* ensure MTU is smaller than what we plan to send */ + ifr.ifr_mtu = MTU; + if (ioctl(ctl, SIOCSIFMTU, &ifr) == -1) + error(KSFT_FAIL, errno, "ioctl: set MTU"); + + disable_dad("lo"); + interface_up(ctl, &ifr); + + close(ctl); + return fd; +} + +int main(void) +{ + struct in6_addr addr = { + .s6_addr[15] = 0x01, /* ::1 */ + }; + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = addr, + .sin6_port = 9 /* port 9/udp (DISCARD) */ + }; + char buf[LARGER_THAN_MTU] = {0}; + struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf)}; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_name = (struct sockaddr *)&sa, + .msg_namelen = sizeof(sa), + }; + ssize_t rc; + int ns_fd; + int err = KSFT_FAIL; + int s; + + printf("Testing IPv6 fragmentation\n"); + ns_fd = setup(); + s = socket(AF_INET6, SOCK_DGRAM, 0); +send_again: + rc = sendmsg(s, &msg, 0); + if (rc == -1) { + /* if interface wasn't ready, try again */ + if (errno == EADDRNOTAVAIL) { + usleep(1000); + goto send_again; + } + printf("[FAIL] sendmsg: %s\n", strerror(errno)); + } else if (rc != LARGER_THAN_MTU) { + printf("[FAIL] sendmsg() returned %zi, expected %i\n", rc, LARGER_THAN_MTU); + } else { + printf("[PASS] sendmsg() returned %zi\n", rc); + err = KSFT_PASS; + } + close(s); + close(ns_fd); + return err; +} base-commit: 864ecc4a6dade82d3f70eab43dad0e277aa6fc78 -- 2.49.1

1 month, 1 week

3
2
0 0

[PATCH 2/9] KVM: selftests: Add __packed attribute fallback

by Aqib Faruqui

Kernel UAPI headers use __packed but don't provide the definition in userspace builds. Add a fallback definition matching the kernel's implementation. This follows the same pattern used by BPF and SGX selftests. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kvm/include/kvm_util.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 23a506d7e..7fae7f5e7 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -5,6 +5,10 @@ #ifndef SELFTEST_KVM_UTIL_H #define SELFTEST_KVM_UTIL_H +#ifndef __packed +#define __packed __attribute__((__packed__)) +#endif + #include "test_util.h" #include <linux/compiler.h> -- 2.47.3

1 month, 1 week

3
2
0 0

[PATCH] selftests/mm: directly add pagesize instead of increase until page size

by Wei Yang

The check of is_backed_by_folio() is done on each page. Directly move pointer to next page instead of increase one and check if it is page size aligned. Signed-off-by: Wei Yang <richard.weiyang(a)gmail.com> --- tools/testing/selftests/mm/split_huge_page_test.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 10ae65ea032f..7f7016ba4054 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -423,9 +423,8 @@ static void split_pte_mapped_thp(void) /* smap does not show THPs after mremap, use kpageflags instead */ thp_size = 0; - for (i = 0; i < pagesize * 4; i++) - if (i % pagesize == 0 && - is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd)) + for (i = 0; i < pagesize * 4; i += pagesize) + if (is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd)) thp_size++; if (thp_size != 4) -- 2.34.1

1 month, 1 week

4
8
0 0

[PATCH v7 00/29] KVM: arm64: Implement support for SME

by Mark Brown

I've removed the RFC tag from this version of the series, but the items that I'm looking for feedback on remains the same: - The userspace ABI, in particular: - The vector length used for the SVE registers, access to the SVE registers and access to ZA and (if available) ZT0 depending on the current state of PSTATE.{SM,ZA}. - The use of a single finalisation for both SVE and SME. - The addition of control for enabling fine grained traps in a similar manner to FGU but without the UNDEF, I'm not clear if this is desired at all and at present this requires symmetric read and write traps like FGU. That seemed like it might be desired from an implementation point of view but we already have one case where we enable an asymmetric trap (for ARM64_WORKAROUND_AMPERE_AC03_CPU_38) and it seems generally useful to enable asymmetrically. This series implements support for SME use in non-protected KVM guests. Much of this is very similar to SVE, the main additional challenge that SME presents is that it introduces a new vector length similar to the SVE vector length and two new controls which change the registers seen by guests: - PSTATE.ZA enables the ZA matrix register and, if SME2 is supported, the ZT0 LUT register. - PSTATE.SM enables streaming mode, a new floating point mode which uses the SVE register set with the separately configured SME vector length. In streaming mode implementation of the FFR register is optional. It is also permitted to build systems which support SME without SVE, in this case when not in streaming mode no SVE registers or instructions are available. Further, there is no requirement that there be any overlap in the set of vector lengths supported by SVE and SME in a system, this is expected to be a common situation in practical systems. Since there is a new vector length to configure we introduce a new feature parallel to the existing SVE one with a new pseudo register for the streaming mode vector length. Due to the overlap with SVE caused by streaming mode rather than finalising SME as a separate feature we use the existing SVE finalisation to also finalise SME, a new define KVM_ARM_VCPU_VEC is provided to help make user code clearer. Finalising SVE and SME separately would introduce complication with register access since finalising SVE makes the SVE registers writeable by userspace and doing multiple finalisations results in an error being reported. Dealing with a state where the SVE registers are writeable due to one of SVE or SME being finalised but may have their VL changed by the other being finalised seems like needless complexity with minimal practical utility, it seems clearer to just express directly that only one finalisation can be done in the ABI. Access to the floating point registers follows the architecture: - When both SVE and SME are present: - If PSTATE.SM == 0 the vector length used for the Z and P registers is the SVE vector length. - If PSTATE.SM == 1 the vector length used for the Z and P registers is the SME vector length. - If only SME is present: - If PSTATE.SM == 0 the Z and P registers are inaccessible and the floating point state accessed via the encodings for the V registers. - If PSTATE.SM == 1 the vector length used for the Z and P registers - The SME specific ZA and ZT0 registers are only accessible if SVCR.ZA is 1. The VMM must understand this, in particular when loading state SVCR should be configured before other state. It should be noted that while the architecture refers to PSTATE.SM and PSTATE.ZA these PSTATE bits are not preserved in SPSR_ELx, they are only accessible via SVCR. There are a large number of subfeatures for SME, most of which only offer additional instructions but some of which (SME2 and FA64) add architectural state. These are configured via the ID registers as per usual. Protected KVM supported, with the implementation maintaining the existing restriction that the hypervisor will refuse to run if streaming mode or ZA is enabled. This both simplfies the code and avoids the need to allocate storage for host ZA and ZT0 state, there seems to be little practical use case for supporting this and the memory usage would be non-trivial. The new KVM_ARM_VCPU_VEC feature and ZA and ZT0 registers have not been added to the get-reg-list selftest, the idea of supporting additional features there without restructuring the program to generate all possible feature combinations has been rejected. I will post a separate series which does that restructuring. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v7: - Rebase onto v6.17-rc1. - Handle SMIDR_EL1 as a VM wide ID register and use this in feat_sme_smps(). - Expose affinity fields in SMIDR_EL1. - Remove SMPRI_EL1 from vcpu_sysreg, the value is always 0 currently. - Prevent userspace writes to SMPRIMAP_EL2. - Link to v6: https://lore.kernel.org/r/20250625-kvm-arm64-sme-v6-0-114cff4ffe04@kernel.o… Changes in v6: - Rebase onto v6.16-rc3. - Link to v5: https://lore.kernel.org/r/20250417-kvm-arm64-sme-v5-0-f469a2d5f574@kernel.o… Changes in v5: - Rebase onto v6.15-rc2. - Add pKVM guest support. - Always restore SVCR. - Link to v4: https://lore.kernel.org/r/20250214-kvm-arm64-sme-v4-0-d64a681adcc2@kernel.o… Changes in v4: - Rebase onto v6.14-rc2 and Mark Rutland's fixes. - Expose SME to nested guests. - Additional cleanups and test fixes following on from the rebase. - Flush register state on VMM PSTATE.{SM,ZA}. - Link to v3: https://lore.kernel.org/r/20241220-kvm-arm64-sme-v3-0-05b018c1ffeb@kernel.o… Changes in v3: - Rebase onto v6.12-rc2. - Link to v2: https://lore.kernel.org/r/20231222-kvm-arm64-sme-v2-0-da226cb180bb@kernel.o… Changes in v2: - Rebase onto v6.7-rc3. - Configure subfeatures based on host system only. - Complete nVHE support. - There was some snafu with sending v1 out, it didn't make it to the lists but in case it hit people's inboxes I'm sending as v2. --- Mark Brown (29): arm64/sysreg: Update SMIDR_EL1 to DDI0601 2025-06 arm64/fpsimd: Update FA64 and ZT0 enables when loading SME state arm64/fpsimd: Decide to save ZT0 and streaming mode FFR at bind time arm64/fpsimd: Check enable bit for FA64 when saving EFI state arm64/fpsimd: Determine maximum virtualisable SME vector length KVM: arm64: Introduce non-UNDEF FGT control KVM: arm64: Pay attention to FFR parameter in SVE save and load KVM: arm64: Pull ctxt_has_ helpers to start of sysreg-sr.h KVM: arm64: Move SVE state access macros after feature test macros KVM: arm64: Rename SVE finalization constants to be more general KVM: arm64: Document the KVM ABI for SME KVM: arm64: Define internal features for SME KVM: arm64: Rename sve_state_reg_region KVM: arm64: Store vector lengths in an array KVM: arm64: Implement SME vector length configuration KVM: arm64: Support SME control registers KVM: arm64: Support TPIDR2_EL0 KVM: arm64: Support SME identification registers for guests KVM: arm64: Support SME priority registers KVM: arm64: Provide assembly for SME register access KVM: arm64: Support userspace access to streaming mode Z and P registers KVM: arm64: Flush register state on writes to SVCR.SM and SVCR.ZA KVM: arm64: Expose SME specific state to userspace KVM: arm64: Context switch SME state for guests KVM: arm64: Handle SME exceptions KVM: arm64: Expose SME to nested guests KVM: arm64: Provide interface for configuring and enabling SME for guests KVM: arm64: selftests: Add SME system registers to get-reg-list KVM: arm64: selftests: Add SME to set_id_regs test Documentation/virt/kvm/api.rst | 117 +++++++---- arch/arm64/include/asm/fpsimd.h | 26 +++ arch/arm64/include/asm/kvm_emulate.h | 6 + arch/arm64/include/asm/kvm_host.h | 169 ++++++++++++--- arch/arm64/include/asm/kvm_hyp.h | 5 +- arch/arm64/include/asm/kvm_pkvm.h | 2 +- arch/arm64/include/asm/vncr_mapping.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 33 +++ arch/arm64/kernel/cpufeature.c | 2 - arch/arm64/kernel/fpsimd.c | 89 ++++---- arch/arm64/kvm/arm.c | 10 + arch/arm64/kvm/config.c | 8 +- arch/arm64/kvm/fpsimd.c | 28 ++- arch/arm64/kvm/guest.c | 252 ++++++++++++++++++++--- arch/arm64/kvm/handle_exit.c | 14 ++ arch/arm64/kvm/hyp/fpsimd.S | 28 ++- arch/arm64/kvm/hyp/include/hyp/switch.h | 175 ++++++++++++++-- arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 110 ++++++---- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 86 ++++++-- arch/arm64/kvm/hyp/nvhe/pkvm.c | 85 ++++++-- arch/arm64/kvm/hyp/nvhe/switch.c | 4 +- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 6 + arch/arm64/kvm/hyp/vhe/switch.c | 17 +- arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 7 + arch/arm64/kvm/nested.c | 3 +- arch/arm64/kvm/reset.c | 156 ++++++++++---- arch/arm64/kvm/sys_regs.c | 141 ++++++++++++- arch/arm64/tools/sysreg | 8 +- include/uapi/linux/kvm.h | 1 + tools/testing/selftests/kvm/arm64/get-reg-list.c | 15 +- tools/testing/selftests/kvm/arm64/set_id_regs.c | 27 ++- 31 files changed, 1328 insertions(+), 304 deletions(-) --- base-commit: 062b3e4a1f880f104a8d4b90b767788786aa7b78 change-id: 20230301-kvm-arm64-sme-06a1246d3636 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 month, 1 week

3
31
0 0

[PATCH v1 00/36] mm: remove nth_page()

by David Hildenbrand

This is based on mm-unstable. I will only CC non-MM folks on the cover letter and the respective patch to not flood too many inboxes (the lists receive all patches). -- As discussed recently with Linus, nth_page() is just nasty and we would like to remove it. To recap, the reason we currently need nth_page() within a folio is because on some kernel configs (SPARSEMEM without SPARSEMEM_VMEMMAP), the memmap is allocated per memory section. While buddy allocations cannot cross memory section boundaries, hugetlb and dax folios can. So crossing a memory section means that "page++" could do the wrong thing. Instead, nth_page() on these problematic configs always goes from page->pfn, to the go from (++pfn)->page, which is rather nasty. Likely, many people have no idea when nth_page() is required and when it might be dropped. We refer to such problematic PFN ranges and "non-contiguous pages". If we only deal with "contiguous pages", there is not need for nth_page(). Besides that "obvious" folio case, we might end up using nth_page() within CMA allocations (again, could span memory sections), and in one corner case (kfence) when processing memblock allocations (again, could span memory sections). So let's handle all that, add sanity checks, and remove nth_page(). Patch #1 -> #5 : stop making SPARSEMEM_VMEMMAP user-selectable + cleanups Patch #6 -> #13 : disallow folios to have non-contiguous pages Patch #14 -> #20 : remove nth_page() usage within folios Patch #21 : disallow CMA allocations of non-contiguous pages Patch #22 -> #32 : sanity+check + remove nth_page() usage within SG entry Patch #33 : sanity-check + remove nth_page() usage in unpin_user_page_range_dirty_lock() Patch #34 : remove nth_page() in kfence Patch #35 : adjust stale comment regarding nth_page Patch #36 : mm: remove nth_page() A lot of this is inspired from the discussion at [1] between Linus, Jason and me, so cudos to them. [1] https://lore.kernel.org/all/CAHk-=wiCYfNp4AJLBORU-c7ZyRBUp66W2-Et6cdQ4REx-G… RFC -> v1: * "wireguard: selftests: remove CONFIG_SPARSEMEM_VMEMMAP=y from qemu kernel config" -> Mention that it was never really relevant for the test * "mm/mm_init: make memmap_init_compound() look more like prep_compound_page()" -> Mention the setup of page links * "mm: limit folio/compound page sizes in problematic kernel configs" -> Improve comment for PUD handling, mentioning hugetlb and dax * "mm: simplify folio_page() and folio_page_idx()" -> Call variable "n" * "mm/hugetlb: cleanup hugetlb_folio_init_tail_vmemmap()" -> Keep __init_single_page() and refer to the usage of memblock_reserved_mark_noinit() * "fs: hugetlbfs: cleanup folio in adjust_range_hwpoison()" * "fs: hugetlbfs: remove nth_page() usage within folio in adjust_range_hwpoison()" -> Separate nth_page() removal from cleanups -> Further improve cleanups * "io_uring/zcrx: remove nth_page() usage within folio" -> Keep the io_copy_cache for now and limit to nth_page() removal * "mm/gup: drop nth_page() usage within folio when recording subpages" -> Cleanup record_subpages as bit * "mm/cma: refuse handing out non-contiguous page ranges" -> Replace another instance of "pfn_to_page(pfn)" where we already have the page * "scatterlist: disallow non-contigous page ranges in a single SG entry" -> We have to EXPORT the symbol. I thought about moving it to mm_inline.h, but I really don't want to include that in include/linux/scatterlist.h * "ata: libata-eh: drop nth_page() usage within SG entry" * "mspro_block: drop nth_page() usage within SG entry" * "memstick: drop nth_page() usage within SG entry" * "mmc: drop nth_page() usage within SG entry" -> Keep PAGE_SHIFT * "scsi: scsi_lib: drop nth_page() usage within SG entry" * "scsi: sg: drop nth_page() usage within SG entry" -> Split patches, Keep PAGE_SHIFT * "crypto: remove nth_page() usage within SG entry" -> Keep PAGE_SHIFT * "kfence: drop nth_page() usage" -> Keep modifying i and use "start_pfn" only instead Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jason Gunthorpe <jgg(a)nvidia.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: "Liam R. Howlett" <Liam.Howlett(a)oracle.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Marek Szyprowski <m.szyprowski(a)samsung.com> Cc: Robin Murphy <robin.murphy(a)arm.com> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Marco Elver <elver(a)google.com> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: Brendan Jackman <jackmanb(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Zi Yan <ziy(a)nvidia.com> Cc: Dennis Zhou <dennis(a)kernel.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Christoph Lameter <cl(a)gentwo.org> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: x86(a)kernel.org Cc: linux-arm-kernel(a)lists.infradead.org Cc: linux-mips(a)vger.kernel.org Cc: linux-s390(a)vger.kernel.org Cc: linux-crypto(a)vger.kernel.org Cc: linux-ide(a)vger.kernel.org Cc: intel-gfx(a)lists.freedesktop.org Cc: dri-devel(a)lists.freedesktop.org Cc: linux-mmc(a)vger.kernel.org Cc: linux-arm-kernel(a)axis.com Cc: linux-scsi(a)vger.kernel.org Cc: kvm(a)vger.kernel.org Cc: virtualization(a)lists.linux.dev Cc: linux-mm(a)kvack.org Cc: io-uring(a)vger.kernel.org Cc: iommu(a)lists.linux.dev Cc: kasan-dev(a)googlegroups.com Cc: wireguard(a)lists.zx2c4.com Cc: netdev(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-riscv(a)lists.infradead.org David Hildenbrand (36): mm: stop making SPARSEMEM_VMEMMAP user-selectable arm64: Kconfig: drop superfluous "select SPARSEMEM_VMEMMAP" s390/Kconfig: drop superfluous "select SPARSEMEM_VMEMMAP" x86/Kconfig: drop superfluous "select SPARSEMEM_VMEMMAP" wireguard: selftests: remove CONFIG_SPARSEMEM_VMEMMAP=y from qemu kernel config mm/page_alloc: reject unreasonable folio/compound page sizes in alloc_contig_range_noprof() mm/memremap: reject unreasonable folio/compound page sizes in memremap_pages() mm/hugetlb: check for unreasonable folio sizes when registering hstate mm/mm_init: make memmap_init_compound() look more like prep_compound_page() mm: sanity-check maximum folio size in folio_set_order() mm: limit folio/compound page sizes in problematic kernel configs mm: simplify folio_page() and folio_page_idx() mm/hugetlb: cleanup hugetlb_folio_init_tail_vmemmap() mm/mm/percpu-km: drop nth_page() usage within single allocation fs: hugetlbfs: remove nth_page() usage within folio in adjust_range_hwpoison() fs: hugetlbfs: cleanup folio in adjust_range_hwpoison() mm/pagewalk: drop nth_page() usage within folio in folio_walk_start() mm/gup: drop nth_page() usage within folio when recording subpages io_uring/zcrx: remove nth_page() usage within folio mips: mm: convert __flush_dcache_pages() to __flush_dcache_folio_pages() mm/cma: refuse handing out non-contiguous page ranges dma-remap: drop nth_page() in dma_common_contiguous_remap() scatterlist: disallow non-contigous page ranges in a single SG entry ata: libata-eh: drop nth_page() usage within SG entry drm/i915/gem: drop nth_page() usage within SG entry mspro_block: drop nth_page() usage within SG entry memstick: drop nth_page() usage within SG entry mmc: drop nth_page() usage within SG entry scsi: scsi_lib: drop nth_page() usage within SG entry scsi: sg: drop nth_page() usage within SG entry vfio/pci: drop nth_page() usage within SG entry crypto: remove nth_page() usage within SG entry mm/gup: drop nth_page() usage in unpin_user_page_range_dirty_lock() kfence: drop nth_page() usage block: update comment of "struct bio_vec" regarding nth_page() mm: remove nth_page() arch/arm64/Kconfig | 1 - arch/mips/include/asm/cacheflush.h | 11 +++-- arch/mips/mm/cache.c | 8 ++-- arch/s390/Kconfig | 1 - arch/x86/Kconfig | 1 - crypto/ahash.c | 4 +- crypto/scompress.c | 8 ++-- drivers/ata/libata-sff.c | 6 +-- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 2 +- drivers/memstick/core/mspro_block.c | 3 +- drivers/memstick/host/jmb38x_ms.c | 3 +- drivers/memstick/host/tifm_ms.c | 3 +- drivers/mmc/host/tifm_sd.c | 4 +- drivers/mmc/host/usdhi6rol0.c | 4 +- drivers/scsi/scsi_lib.c | 3 +- drivers/scsi/sg.c | 3 +- drivers/vfio/pci/pds/lm.c | 3 +- drivers/vfio/pci/virtio/migrate.c | 3 +- fs/hugetlbfs/inode.c | 33 +++++-------- include/crypto/scatterwalk.h | 4 +- include/linux/bvec.h | 7 +-- include/linux/mm.h | 48 +++++++++++++++---- include/linux/page-flags.h | 5 +- include/linux/scatterlist.h | 3 +- io_uring/zcrx.c | 4 +- kernel/dma/remap.c | 2 +- mm/Kconfig | 3 +- mm/cma.c | 39 +++++++++------ mm/gup.c | 14 ++++-- mm/hugetlb.c | 22 +++++---- mm/internal.h | 1 + mm/kfence/core.c | 12 +++-- mm/memremap.c | 3 ++ mm/mm_init.c | 15 +++--- mm/page_alloc.c | 5 +- mm/pagewalk.c | 2 +- mm/percpu-km.c | 2 +- mm/util.c | 34 +++++++++++++ tools/testing/scatterlist/linux/mm.h | 1 - .../selftests/wireguard/qemu/kernel.config | 1 - 40 files changed, 202 insertions(+), 129 deletions(-) base-commit: efa7612003b44c220551fd02466bfbad5180fc83 -- 2.50.1

1 month, 1 week

14
141
0 0

[PATCH net-next v3] selftests: net: add test for ipv6 fragmentation

by Brett A C Sheffield

Add selftest for the IPv6 fragmentation regression which affected several stable kernels. Commit a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable without some prerequisite commits. This caused a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning -1 (EMSGSIZE). Add selftest to check for this issue by attempting to send a packet larger than the interface MTU. The packet will be fragmented on a working kernel, with sendmsg(2) correctly returning the expected number of bytes sent. When the regression is present, sendmsg returns -1 and sets errno to EMSGSIZE. Link: https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com Signed-off-by: Brett A C Sheffield <bacs(a)librecast.net> --- Thanks again Willem for the prompt review. I've incorporated your suggested changes into v3. v3 changes: - add usleep instead of busy polling on sendmsg - simplify error handling by using error() and leaving cleanup to O/S - use loopback interface - don't bother creating TAP - send to localhost (::1) v2 changes: - remove superfluous namespace calls - unshare(2) suffices - remove usleep(). Don't wait for the interface to be ready, just send, and handle the (less likely) error case by retrying. - set destination address only once - document our use of the IPv6 link-local source address - send to port 9 (DISCARD) instead of 4242 (DONT PANIC) - ensure sockets are closed on failure paths - use KSFT exit codes for clarity v2: https://lore.kernel.org/netdev/20250831102908.14655-1-bacs@librecast.net v1: https://lore.kernel.org/netdev/20250825092548.4436-3-bacs@librecast.net tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_fragmentation.c | 145 ++++++++++++++++++ 3 files changed, 147 insertions(+) create mode 100644 tools/testing/selftests/net/ipv6_fragmentation.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 47c293c2962f..3d4b4a53dfda 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,6 +16,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +ipv6_fragmentation log.txt msg_oob msg_zerocopy diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index eef0b8f8a7b0..276e0481d996 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -117,6 +117,7 @@ TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh +TEST_GEN_PROGS += ipv6_fragmentation TEST_PROGS += route_hint.sh # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c new file mode 100644 index 000000000000..be79a0340826 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Brett A C Sheffield <bacs(a)librecast.net> + * + * Kernel selftest for the IPv6 fragmentation regression which affected stable + * kernels: + * + * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com + * + * Commit: a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable + * without some prerequisite commits. + * + * This caused a regression when sending IPv6 UDP packets by preventing + * fragmentation and instead returning -1 (EMSGSIZE). + * + * This selftest demonstrates the issue by sending an IPv6 UDP packet to + * localhost (::1) on the loopback interface from the autoconfigured link-local + * address. + * + * sendmsg(2) returns bytes sent correctly on a working kernel, and returns -1 + * (EMSGSIZE) when the regression is present. + * + * The regression was not present in the mainline kernel, but add this test to + * catch similar breakage in future. + */ + +#define _GNU_SOURCE + +#include <error.h> +#include <fcntl.h> +#include <linux/if_tun.h> +#include <net/if.h> +#include <netinet/in.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <unistd.h> +#include "../kselftest.h" + +#define MTU 1500 +#define LARGER_THAN_MTU 8192 + +/* bring up interface */ +static int interface_up(int ctl, struct ifreq *ifr) +{ + if (ioctl(ctl, SIOCGIFFLAGS, ifr) == -1) + error(KSFT_FAIL, errno, "ioctl SIOCGIFFLAGS"); + ifr->ifr_flags = ifr->ifr_flags | IFF_UP; + return ioctl(ctl, SIOCSIFFLAGS, ifr); +} + +/* no need to wait for DAD in our namespace */ +static int disable_dad(char *ifname) +{ + char sysvar[] = "/proc/sys/net/ipv6/conf/%s/accept_dad"; + char fname[IFNAMSIZ + sizeof(sysvar)]; + int fd; + + snprintf(fname, sizeof(fname), sysvar, ifname); + fd = open(fname, O_WRONLY); + if (fd == -1) + error(KSFT_FAIL, errno, "open accept_dad"); + if (write(fd, "0", 1) != 1) + error(KSFT_FAIL, errno, "write accept_dad"); + + return close(fd); +} + +static int setup(void) +{ + struct ifreq ifr = { + .ifr_name = "lo" + }; + int fd = -1; + int ctl; + + /* we need to set MTU, so do this in a namespace to play nicely */ + if (unshare(CLONE_NEWNET) == -1) + error(KSFT_FAIL, errno, "unshare"); + + ctl = socket(AF_LOCAL, SOCK_STREAM, 0); + if (ctl == -1) + error(KSFT_FAIL, errno, "socket"); + + /* ensure MTU is smaller than what we plan to send */ + ifr.ifr_mtu = MTU; + if (ioctl(ctl, SIOCSIFMTU, &ifr) == -1) + error(KSFT_FAIL, errno, "ioctl: set MTU"); + + disable_dad("lo"); + interface_up(ctl, &ifr); + + close(ctl); + return fd; +} + +int main(void) +{ + struct in6_addr addr = { + .s6_addr[15] = 0x01, /* ::1 */ + }; + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = addr, + .sin6_port = 9 /* port 9/udp (DISCARD) */ + }; + char buf[LARGER_THAN_MTU] = {0}; + struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf)}; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_name = (struct sockaddr *)&sa, + .msg_namelen = sizeof(sa), + }; + ssize_t rc; + int ns_fd; + int err = KSFT_FAIL; + int s; + + printf("Testing IPv6 fragmentation\n"); + ns_fd = setup(); + s = socket(AF_INET6, SOCK_DGRAM, 0); +send_again: + rc = sendmsg(s, &msg, 0); + if (rc == -1) { + /* if interface wasn't ready, try again */ + if (errno == EADDRNOTAVAIL) { + usleep(1000); + goto send_again; + } + printf("[FAIL] sendmsg: %s\n", strerror(errno)); + } else if (rc != LARGER_THAN_MTU) { + printf("[FAIL] sendmsg() returned %zi, expected %i\n", rc, LARGER_THAN_MTU); + } + else { + printf("[PASS] sendmsg() returned %zi\n", rc); + err = KSFT_PASS; + } + close(s); + close(ns_fd); + return err; +} base-commit: 864ecc4a6dade82d3f70eab43dad0e277aa6fc78 -- 2.49.1

1 month, 1 week

1
0
0 0

[PATCH v2 0/5] Add Zilsd/Zclsd support in hwprobe and KVM

by Pincheng Wang

Hi all, This is v2 of a short series that adds kernel support for the ratified Zilsd (Load/Store pair) and Zclsd (Compressed Load/Store pair) RISC-V ISA extensions. The series enables kernel-side exposure so user-space (for example glibc) can detect and use these extensions via hwprobe and runtime checks. Patches: - Patch 1：Add device tree bindings documentation for Zilsd and Zclsd. - Patch 2: Extend RISC-V ISA extension string parsing to recognize them. - Patch 3: Export Zilsd and Zclsd via riscv_hwprobe. - Patch 4: Allow KVM guests to use them. - Patch 5: Add KVM selftests. Changes in v2: - Device-tree schema: simplified the rv64 validation for Zilsd by removing a redundant `contais: const: zilsd` in the `if` clause; the simpler `if (riscv, isa-base contains rv64i) then (riscv, isa-extension not contains zilsd)` form is used instead. Behaviour is unchanged, and the logic is cleaner. - Device-tree schema: corrected Zclsd dependency to require both Zilsd and Zca (previous `anyOf` was incorrect; now both are enforced). - Commit message typo fixed: "dt-bidings" -> "dt-bindings" in the Patch 1 commit subject. The v2 changes are documentation/schema corrections in extensions.yaml. No functional changes were made to ISA parsing, hwprobe syscall, KVM guest support or the selftests beyond ensuring the binding correctly documents and validates the extension relationships. Please review v2 and advise if futher changes are needed. Thanks, Pincheng Wang Pincheng Wang (5): dt-bindings: riscv: add Zilsd and Zclsd extension descriptions riscv: add ISA extension parsing for Zilsd and Zclsd riscv: hwprobe: export Zilsd and Zclsd ISA extensions riscv: KVM: allow Zilsd and Zclsd extensions for Guest/VM KVM: riscv: selftests: add Zilsd and Zclsd extension to get-reg-list test Documentation/arch/riscv/hwprobe.rst | 8 +++++ .../devicetree/bindings/riscv/extensions.yaml | 36 +++++++++++++++++++ arch/riscv/include/asm/hwcap.h | 2 ++ arch/riscv/include/uapi/asm/hwprobe.h | 2 ++ arch/riscv/include/uapi/asm/kvm.h | 2 ++ arch/riscv/kernel/cpufeature.c | 24 +++++++++++++ arch/riscv/kernel/sys_hwprobe.c | 2 ++ arch/riscv/kvm/vcpu_onereg.c | 2 ++ .../selftests/kvm/riscv/get-reg-list.c | 6 ++++ 9 files changed, 84 insertions(+) -- 2.39.5

1 month, 2 weeks

3
11
0 0

[PATCH v5 0/7] Add support for FEAT_{LS64, LS64_V} and related tests

by Yicong Yang

From: Yicong Yang <yangyicong(a)hisilicon.com> Armv8.7 introduces single-copy atomic 64-byte loads and stores instructions and its variants named under FEAT_{LS64, LS64_V}. Add support for Armv8.7 FEAT_{LS64, LS64_V}: - Add identifying and enabling in the cpufeature list - Expose the support of these features to userspace through HWCAP3 and cpuinfo - Add related hwcap test - Handle the trap of unsupported memory (normal/uncacheable) access in a VM A real scenario for this feature is that the userspace driver can make use of this to implement direct WQE (workqueue entry) - a mechanism to fill WQE directly into the hardware. Picked Marc's 2 patches form [1] for handling the LS64 trap in a VM on emulated MMIO and the introduce of KVM_EXIT_ARM_LDST64B. [1] https://lore.kernel.org/linux-arm-kernel/20240815125959.2097734-1-maz@kerne… Tested with updated hwcap test: [root@localhost tmp]# dmesg | grep "All CPU(s) started" [ 14.789859] CPU: All CPU(s) started at EL2 [root@localhost tmp]# ./hwcap # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64_V # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 root@localhost:/mnt# dmesg | grep "All CPU(s) started" [ 0.281152] CPU: All CPU(s) started at EL1 root@localhost:/mnt# ./hwcap # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 Change since v4: - Rebase on v6.17-rc2 and fix the conflicts Link: https://lore.kernel.org/linux-arm-kernel/20250715081356.12442-1-yangyicong@… Change since v3: - Inject DABT fault for LS64 fault on unsupported memory but with valid memslot Link: https://lore.kernel.org/linux-arm-kernel/20250626080906.64230-1-yangyicong@… Change since v2: - Handle the LS64 fault to userspace and allow userspace to inject LS64 fault - Reorder the patches to make KVM handling prior to feature support Link: https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-1-yangyicong@… Change since v1: - Drop the support for LS64_ACCDATA - handle the DABT of unsupported memory type after checking the memory attributes Link: https://lore.kernel.org/linux-arm-kernel/20241202135504.14252-1-yangyicong@… Marc Zyngier (2): KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B Yicong Yang (5): KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1 arm64: Add support for FEAT_{LS64, LS64_V} KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest kselftest/arm64: Add HWCAP test for FEAT_{LS64, LS64_V} Documentation/arch/arm64/booting.rst | 12 +++ Documentation/arch/arm64/elf_hwcaps.rst | 6 ++ Documentation/virt/kvm/api.rst | 43 +++++++++-- arch/arm64/include/asm/el2_setup.h | 12 ++- arch/arm64/include/asm/esr.h | 8 ++ arch/arm64/include/asm/hwcap.h | 2 + arch/arm64/include/asm/kvm_emulate.h | 7 ++ arch/arm64/include/uapi/asm/hwcap.h | 2 + arch/arm64/kernel/cpufeature.c | 51 +++++++++++++ arch/arm64/kernel/cpuinfo.c | 2 + arch/arm64/kvm/inject_fault.c | 22 ++++++ arch/arm64/kvm/mmio.c | 27 ++++++- arch/arm64/kvm/mmu.c | 14 +++- arch/arm64/tools/cpucaps | 2 + include/uapi/linux/kvm.h | 3 +- tools/testing/selftests/arm64/abi/hwcap.c | 90 +++++++++++++++++++++++ 16 files changed, 292 insertions(+), 11 deletions(-) -- 2.24.0

1 month, 2 weeks

1
8
0 0

[PATCH v2] KVM: loongarch: selftests: Remove common tests built by TEST_GEN_PROGS_COMMON

by dayss1224＠gmail.com

From: Dong Yang <dayss1224(a)gmail.com> Remove the common KVM test cases already added to TEST_GEN_PROGS_COMMON as following: demand_paging_test dirty_log_test guest_print_test kvm_binary_stats_test kvm_create_max_vcpus kvm_page_table_test set_memory_region_test Fixes: a867688c8cbb ("KVM: selftests: Add supported test cases for LoongArch") Signed-off-by: Quan Zhou <zhouquan(a)iscas.ac.cn> Signed-off-by: Dong Yang <dayss1224(a)gmail.com> Changes in v2: - Add "TEST_GEN_PROGS_loongarch = $(TEST_GEN_PROGS_COMMON)" to include common tests --- tools/testing/selftests/kvm/Makefile.kvm | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 38b95998e1e6..3fd1c2ae68d0 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -198,18 +198,12 @@ TEST_GEN_PROGS_riscv += coalesced_io_test TEST_GEN_PROGS_riscv += get-reg-list TEST_GEN_PROGS_riscv += steal_time +TEST_GEN_PROGS_loongarch = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_loongarch += coalesced_io_test -TEST_GEN_PROGS_loongarch += demand_paging_test TEST_GEN_PROGS_loongarch += dirty_log_perf_test -TEST_GEN_PROGS_loongarch += dirty_log_test -TEST_GEN_PROGS_loongarch += guest_print_test TEST_GEN_PROGS_loongarch += hardware_disable_test -TEST_GEN_PROGS_loongarch += kvm_binary_stats_test -TEST_GEN_PROGS_loongarch += kvm_create_max_vcpus -TEST_GEN_PROGS_loongarch += kvm_page_table_test TEST_GEN_PROGS_loongarch += memslot_modification_stress_test TEST_GEN_PROGS_loongarch += memslot_perf_test -TEST_GEN_PROGS_loongarch += set_memory_region_test SPLIT_TESTS += arch_timer SPLIT_TESTS += get-reg-list base-commit: b23ff7e52a79f4fe2382e3564719b97b718166d1 -- 2.34.1

1 month, 2 weeks

1
0
0 0

[PATCHSET V1 0/2] cpuidle, bpf: Introduce BPF-based extensible cpuidle policy via struct_ops

by Lin Yikai

Summary ---------- Hi, everyone, This patch set introduces an extensible cpuidle governor framework using BPF struct_ops, enabling dynamic implementation of idle-state selection policies via BPF programs. Motivation ---------- As is well-known, CPUs support multiple idle states (e.g., C0, C1, C2, ...), where deeper states reduce power consumption, but results in longer wakeup latency, potentially affecting performance. Existing generic cpuidle governors operate effectively in common scenarios but exhibit suboptimal behavior in specific Android phone's use cases. Our testing reveals that during low-utilization scenarios (e.g., screen-off background tasks like music playback with CPU utilization <10%), the C0 state occupies ~50% of idle time, causing significant energy inefficiency. Reducing C0 to ≤20% could yield ≥5% power savings on mobile phones. To address this, we expect: 1.Dynamic governor switching to power-saved policies for low cpu utilization scenarios (e.g., screen-off mode) 2.Dynamic switching to alternate governors for high-performance scenarios (e.g., gaming) OverView ---------- The BPF cpuidle ext governor registers at postcore_initcall() but remains disabled by default due to its low priority "rating" with value "1". Activation requires adjust higer "rating" than other governors within BPF. Core Components: 1.**struct cpuidle_gov_ext_ops** – BPF-overridable operations: - ops.enable()/ops.disable(): enable or disable callback - ops.select(): cpu Idle-state selection logic - ops.set_stop_tick(): Scheduler tick management after state selection - ops.reflect(): feedback info about previous idle state. - ops.init()/ops.deinit(): Initialization or cleanup. 2.**Critical kfuncs for kernel state access**: - bpf_cpuidle_ext_gov_update_rating(): Activate ext governor by raising rating must be called from "ops.init()" - bpf_cpuidle_ext_gov_latency_req(): get idle-state latency constraints - bpf_tick_nohz_get_sleep_length(): get CPU sleep duration in tickless mode Future work ---------- 1. Scenario detection: Identifying low-utilization states (e.g., screen-off + background music) 2. Policy optimization: Optimizing state-selection algorithms for specific scenarios Lin Yikai (2): Subject: [PATCH v1 1/2] cpuidle: Implement BPF extensible cpuidle class Subject: [PATCH v1 2/2] selftests/bpf: Add selftests drivers/cpuidle/Kconfig | 12 + drivers/cpuidle/governors/Makefile | 1 + drivers/cpuidle/governors/ext.c | 537 ++++++++++++++++++ .../bpf/prog_tests/test_cpuidle_gov_ext.c | 28 + .../selftests/bpf/progs/cpuidle_gov_ext.c | 208 +++++++ 5 files changed, 786 insertions(+) create mode 100644 drivers/cpuidle/governors/ext.c create mode 100644 tools/testing/selftests/bpf/prog_tests/test_cpuidle_gov_ext.c create mode 100644 tools/testing/selftests/bpf/progs/cpuidle_gov_ext.c -- 2.43.0

1 month, 2 weeks

4
6
0 0

[PATCH 0/2] selftests: Centralize kselftest headers to avoid relative includes

by Bala-Vignesh-Reddy

This series centralize the handling of kselftest.h and kselftest_harness.h includes in selftests, replacing relative paths with a non-relative approach using shared -I path. Patch-1 updates the build files (Makefile and lib.mk) and include CFLAGS in sync/Makefile to resolve not found error Patch-2 applies bulk source change (Patch 2 is large but it is replaced automatically) Checked the changes with gcc-13.32 and clang 18.1 Suggested-by: Andrew Morton <akpm(a)linux-foundation.org> Link: https://lore.kernel.org/lkml/20250820143954.33d95635e504e94df01930d0@linux-… Bala-Vignesh-Reddy (2): selftests: Centralize include path for kselftest.h and kselftest_harness.h selftests: Replace relative includes with non-relative for kselftest.h and kselftest_harness.h Signed-off-by: Bala-Vignesh-Reddy <reddybalavignesh9979(a)gmail.com> tools/testing/selftests/Makefile | 4 ++++ tools/testing/selftests/acct/acct_syscall.c | 2 +- tools/testing/selftests/alsa/conf.c | 2 +- tools/testing/selftests/alsa/mixer-test.c | 2 +- tools/testing/selftests/alsa/pcm-test.c | 2 +- tools/testing/selftests/alsa/test-pcmtest-driver.c | 2 +- tools/testing/selftests/alsa/utimer-test.c | 2 +- tools/testing/selftests/arm64/abi/hwcap.c | 2 +- tools/testing/selftests/arm64/abi/ptrace.c | 2 +- tools/testing/selftests/arm64/abi/syscall-abi.c | 2 +- tools/testing/selftests/arm64/fp/fp-ptrace.c | 2 +- tools/testing/selftests/arm64/fp/fp-stress.c | 2 +- tools/testing/selftests/arm64/fp/sve-probe-vls.c | 2 +- tools/testing/selftests/arm64/fp/sve-ptrace.c | 2 +- tools/testing/selftests/arm64/fp/vec-syscfg.c | 2 +- tools/testing/selftests/arm64/fp/za-ptrace.c | 2 +- tools/testing/selftests/arm64/fp/zt-ptrace.c | 2 +- tools/testing/selftests/arm64/gcs/gcs-stress.c | 2 +- tools/testing/selftests/arm64/pauth/pac.c | 2 +- tools/testing/selftests/arm64/tags/tags_test.c | 2 +- tools/testing/selftests/bpf/xskxceiver.c | 2 +- tools/testing/selftests/breakpoints/breakpoint_test.c | 2 +- tools/testing/selftests/breakpoints/breakpoint_test_arm64.c | 2 +- tools/testing/selftests/breakpoints/step_after_suspend_test.c | 2 +- tools/testing/selftests/cachestat/test_cachestat.c | 2 +- tools/testing/selftests/capabilities/test_execve.c | 2 +- tools/testing/selftests/capabilities/validate_cap.c | 2 +- tools/testing/selftests/cgroup/test_core.c | 2 +- tools/testing/selftests/cgroup/test_cpu.c | 2 +- tools/testing/selftests/cgroup/test_cpuset.c | 2 +- tools/testing/selftests/cgroup/test_freezer.c | 2 +- tools/testing/selftests/cgroup/test_hugetlb_memcg.c | 2 +- tools/testing/selftests/cgroup/test_kill.c | 2 +- tools/testing/selftests/cgroup/test_kmem.c | 2 +- tools/testing/selftests/cgroup/test_memcontrol.c | 2 +- tools/testing/selftests/cgroup/test_pids.c | 2 +- tools/testing/selftests/cgroup/test_zswap.c | 2 +- tools/testing/selftests/clone3/clone3.c | 2 +- .../testing/selftests/clone3/clone3_cap_checkpoint_restore.c | 2 +- tools/testing/selftests/clone3/clone3_clear_sighand.c | 2 +- tools/testing/selftests/clone3/clone3_selftests.h | 2 +- tools/testing/selftests/clone3/clone3_set_tid.c | 2 +- tools/testing/selftests/connector/proc_filter.c | 2 +- tools/testing/selftests/core/close_range_test.c | 2 +- tools/testing/selftests/core/unshare_test.c | 2 +- tools/testing/selftests/coredump/stackdump_test.c | 2 +- tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c | 2 +- tools/testing/selftests/drivers/dma-buf/udmabuf.c | 2 +- tools/testing/selftests/drivers/ntsync/ntsync.c | 2 +- .../testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c | 2 +- tools/testing/selftests/exec/check-exec.c | 2 +- tools/testing/selftests/exec/execveat.c | 2 +- tools/testing/selftests/exec/load_address.c | 2 +- tools/testing/selftests/exec/non-regular.c | 2 +- tools/testing/selftests/exec/null-argv.c | 2 +- tools/testing/selftests/exec/recursion-depth.c | 2 +- tools/testing/selftests/fchmodat2/fchmodat2_test.c | 2 +- tools/testing/selftests/filelock/ofdlocks.c | 2 +- tools/testing/selftests/filesystems/anon_inode_test.c | 2 +- tools/testing/selftests/filesystems/binderfs/binderfs_test.c | 2 +- tools/testing/selftests/filesystems/devpts_pts.c | 2 +- tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c | 2 +- tools/testing/selftests/filesystems/eventfd/eventfd_test.c | 2 +- tools/testing/selftests/filesystems/file_stressor.c | 2 +- tools/testing/selftests/filesystems/kernfs_test.c | 2 +- .../selftests/filesystems/mount-notify/mount-notify_test.c | 2 +- .../selftests/filesystems/mount-notify/mount-notify_test_ns.c | 2 +- tools/testing/selftests/filesystems/nsfs/iterate_mntns.c | 2 +- tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c | 2 +- .../selftests/filesystems/overlayfs/set_layers_via_fds.c | 2 +- .../testing/selftests/filesystems/statmount/listmount_test.c | 2 +- .../testing/selftests/filesystems/statmount/statmount_test.c | 2 +- .../selftests/filesystems/statmount/statmount_test_ns.c | 2 +- tools/testing/selftests/filesystems/utils.c | 2 +- tools/testing/selftests/hid/hid_common.h | 2 +- tools/testing/selftests/intel_pstate/aperf.c | 2 +- tools/testing/selftests/iommu/iommufd_utils.h | 2 +- tools/testing/selftests/ipc/msgque.c | 2 +- tools/testing/selftests/ir/ir_loopback.c | 2 +- tools/testing/selftests/kcmp/kcmp_test.c | 2 +- tools/testing/selftests/kselftest_harness.h | 2 +- tools/testing/selftests/kselftest_harness/harness-selftest.c | 2 +- tools/testing/selftests/landlock/audit.h | 2 +- tools/testing/selftests/landlock/common.h | 2 +- tools/testing/selftests/lib.mk | 2 ++ tools/testing/selftests/lsm/lsm_get_self_attr_test.c | 2 +- tools/testing/selftests/lsm/lsm_list_modules_test.c | 2 +- tools/testing/selftests/lsm/lsm_set_self_attr_test.c | 2 +- tools/testing/selftests/media_tests/media_device_open.c | 2 +- tools/testing/selftests/media_tests/media_device_test.c | 2 +- tools/testing/selftests/membarrier/membarrier_test_impl.h | 2 +- tools/testing/selftests/mincore/mincore_selftest.c | 4 ++-- tools/testing/selftests/mm/compaction_test.c | 2 +- tools/testing/selftests/mm/cow.c | 2 +- tools/testing/selftests/mm/droppable.c | 2 +- tools/testing/selftests/mm/guard-regions.c | 2 +- tools/testing/selftests/mm/gup_longterm.c | 2 +- tools/testing/selftests/mm/gup_test.c | 2 +- tools/testing/selftests/mm/hmm-tests.c | 2 +- tools/testing/selftests/mm/hugepage-mmap.c | 2 +- tools/testing/selftests/mm/hugepage-mremap.c | 2 +- tools/testing/selftests/mm/hugetlb-madvise.c | 2 +- tools/testing/selftests/mm/hugetlb-read-hwpoison.c | 2 +- tools/testing/selftests/mm/hugetlb-soft-offline.c | 2 +- tools/testing/selftests/mm/hugetlb_dio.c | 2 +- tools/testing/selftests/mm/hugetlb_fault_after_madv.c | 2 +- tools/testing/selftests/mm/hugetlb_madv_vs_map.c | 2 +- tools/testing/selftests/mm/ksm_functional_tests.c | 2 +- tools/testing/selftests/mm/ksm_tests.c | 2 +- tools/testing/selftests/mm/madv_populate.c | 2 +- tools/testing/selftests/mm/map_fixed_noreplace.c | 2 +- tools/testing/selftests/mm/map_hugetlb.c | 2 +- tools/testing/selftests/mm/map_populate.c | 2 +- tools/testing/selftests/mm/mdwe_test.c | 2 +- tools/testing/selftests/mm/memfd_secret.c | 2 +- tools/testing/selftests/mm/merge.c | 2 +- tools/testing/selftests/mm/migration.c | 2 +- tools/testing/selftests/mm/mkdirty.c | 2 +- tools/testing/selftests/mm/mlock-random-test.c | 2 +- tools/testing/selftests/mm/mlock2-tests.c | 2 +- tools/testing/selftests/mm/mrelease_test.c | 2 +- tools/testing/selftests/mm/mremap_dontunmap.c | 2 +- tools/testing/selftests/mm/mremap_test.c | 2 +- tools/testing/selftests/mm/mseal_test.c | 2 +- tools/testing/selftests/mm/on-fault-limit.c | 2 +- tools/testing/selftests/mm/pagemap_ioctl.c | 2 +- tools/testing/selftests/mm/pfnmap.c | 2 +- tools/testing/selftests/mm/pkey-helpers.h | 2 +- tools/testing/selftests/mm/process_madv.c | 2 +- tools/testing/selftests/mm/soft-dirty.c | 2 +- tools/testing/selftests/mm/split_huge_page_test.c | 2 +- tools/testing/selftests/mm/thuge-gen.c | 2 +- tools/testing/selftests/mm/transhuge-stress.c | 2 +- tools/testing/selftests/mm/uffd-common.h | 2 +- tools/testing/selftests/mm/uffd-wp-mremap.c | 2 +- tools/testing/selftests/mm/va_high_addr_switch.c | 2 +- tools/testing/selftests/mm/virtual_address_range.c | 2 +- tools/testing/selftests/mm/vm_util.c | 2 +- tools/testing/selftests/mm/vm_util.h | 2 +- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 2 +- .../move_mount_set_group/move_mount_set_group_test.c | 2 +- tools/testing/selftests/mqueue/mq_open_tests.c | 2 +- tools/testing/selftests/mqueue/mq_perf_tests.c | 2 +- .../selftests/mseal_system_mappings/sysmap_is_sealed.c | 4 ++-- tools/testing/selftests/nci/nci_dev.c | 2 +- tools/testing/selftests/net/af_unix/diag_uid.c | 2 +- tools/testing/selftests/net/af_unix/msg_oob.c | 2 +- tools/testing/selftests/net/af_unix/scm_inq.c | 2 +- tools/testing/selftests/net/af_unix/scm_pidfd.c | 2 +- tools/testing/selftests/net/af_unix/scm_rights.c | 2 +- tools/testing/selftests/net/af_unix/unix_connect.c | 2 +- tools/testing/selftests/net/bind_timewait.c | 2 +- tools/testing/selftests/net/bind_wildcard.c | 2 +- tools/testing/selftests/net/can/test_raw_filter.c | 2 +- tools/testing/selftests/net/cmsg_sender.c | 2 +- tools/testing/selftests/net/epoll_busy_poll.c | 2 +- tools/testing/selftests/net/gro.c | 2 +- tools/testing/selftests/net/ip_local_port_range.c | 2 +- tools/testing/selftests/net/ipsec.c | 2 +- tools/testing/selftests/net/netfilter/conntrack_dump_flush.c | 2 +- tools/testing/selftests/net/netlink-dumps.c | 2 +- tools/testing/selftests/net/proc_net_pktgen.c | 2 +- tools/testing/selftests/net/psock_fanout.c | 2 +- tools/testing/selftests/net/psock_tpacket.c | 2 +- tools/testing/selftests/net/reuseaddr_ports_exhausted.c | 2 +- tools/testing/selftests/net/reuseport_bpf.c | 2 +- tools/testing/selftests/net/reuseport_bpf_numa.c | 2 +- tools/testing/selftests/net/rxtimestamp.c | 2 +- tools/testing/selftests/net/sk_so_peek_off.c | 2 +- tools/testing/selftests/net/so_incoming_cpu.c | 2 +- tools/testing/selftests/net/socket.c | 2 +- tools/testing/selftests/net/tap.c | 2 +- tools/testing/selftests/net/tcp_ao/lib/setup.c | 2 +- tools/testing/selftests/net/tcp_fastopen_backup_key.c | 2 +- tools/testing/selftests/net/tls.c | 2 +- tools/testing/selftests/net/toeplitz.c | 2 +- tools/testing/selftests/net/tun.c | 2 +- tools/testing/selftests/net/udpgso_bench_tx.c | 2 +- tools/testing/selftests/openat2/helpers.h | 2 +- tools/testing/selftests/openat2/openat2_test.c | 2 +- tools/testing/selftests/openat2/rename_attack_test.c | 2 +- tools/testing/selftests/openat2/resolve_test.c | 2 +- tools/testing/selftests/pci_endpoint/pci_endpoint_test.c | 2 +- tools/testing/selftests/perf_events/mmap.c | 2 +- tools/testing/selftests/perf_events/remove_on_exec.c | 2 +- tools/testing/selftests/perf_events/sigtrap_threads.c | 2 +- tools/testing/selftests/perf_events/watermark_signal.c | 2 +- tools/testing/selftests/pid_namespace/pid_max.c | 2 +- tools/testing/selftests/pid_namespace/regression_enomem.c | 2 +- tools/testing/selftests/pidfd/pidfd.h | 2 +- tools/testing/selftests/pidfd/pidfd_bind_mount.c | 2 +- tools/testing/selftests/pidfd/pidfd_fdinfo_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_file_handle_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_getfd_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_info_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_open_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_poll_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_setattr_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_setns_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_wait.c | 2 +- tools/testing/selftests/pidfd/pidfd_xattr_test.c | 2 +- tools/testing/selftests/prctl/set-anon-vma-name-test.c | 2 +- tools/testing/selftests/prctl/set-process-name.c | 2 +- tools/testing/selftests/proc/proc-maps-race.c | 2 +- tools/testing/selftests/proc/proc-pid-vm.c | 2 +- tools/testing/selftests/ptrace/get_set_sud.c | 2 +- tools/testing/selftests/ptrace/get_syscall_info.c | 2 +- tools/testing/selftests/ptrace/set_syscall_info.c | 2 +- tools/testing/selftests/ptrace/vmaccess.c | 2 +- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/ring-buffer/map_test.c | 2 +- tools/testing/selftests/riscv/abi/pointer_masking.c | 2 +- tools/testing/selftests/riscv/hwprobe/cbo.c | 2 +- tools/testing/selftests/riscv/hwprobe/hwprobe.c | 2 +- tools/testing/selftests/riscv/hwprobe/which-cpus.c | 2 +- tools/testing/selftests/riscv/mm/mmap_bottomup.c | 2 +- tools/testing/selftests/riscv/mm/mmap_default.c | 2 +- tools/testing/selftests/riscv/mm/mmap_test.h | 2 +- tools/testing/selftests/riscv/sigreturn/sigreturn.c | 2 +- tools/testing/selftests/riscv/vector/v_initval.c | 2 +- tools/testing/selftests/riscv/vector/vstate_prctl.c | 2 +- tools/testing/selftests/rseq/basic_percpu_ops_test.c | 2 +- tools/testing/selftests/rseq/rseq.c | 2 +- tools/testing/selftests/rtc/rtctest.c | 2 +- tools/testing/selftests/seccomp/seccomp_benchmark.c | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 2 +- tools/testing/selftests/sgx/main.c | 2 +- tools/testing/selftests/signal/mangle_uc_sigmask.c | 2 +- tools/testing/selftests/signal/sas.c | 2 +- tools/testing/selftests/sparc64/drivers/adi-test.c | 2 +- tools/testing/selftests/sync/Makefile | 2 +- tools/testing/selftests/sync/sync_test.c | 2 +- tools/testing/selftests/sync/synctest.h | 2 +- tools/testing/selftests/syscall_user_dispatch/sud_test.c | 2 +- tools/testing/selftests/tdx/tdx_guest_test.c | 2 +- tools/testing/selftests/timens/timens.h | 2 +- tools/testing/selftests/timers/adjtick.c | 2 +- tools/testing/selftests/timers/alarmtimer-suspend.c | 2 +- tools/testing/selftests/timers/change_skew.c | 2 +- tools/testing/selftests/timers/clocksource-switch.c | 2 +- tools/testing/selftests/timers/freq-step.c | 2 +- tools/testing/selftests/timers/inconsistency-check.c | 2 +- tools/testing/selftests/timers/leap-a-day.c | 2 +- tools/testing/selftests/timers/leapcrash.c | 2 +- tools/testing/selftests/timers/mqueue-lat.c | 2 +- tools/testing/selftests/timers/nanosleep.c | 2 +- tools/testing/selftests/timers/nsleep-lat.c | 2 +- tools/testing/selftests/timers/posix_timers.c | 2 +- tools/testing/selftests/timers/raw_skew.c | 2 +- tools/testing/selftests/timers/rtcpie.c | 2 +- tools/testing/selftests/timers/set-2038.c | 2 +- tools/testing/selftests/timers/set-tai.c | 2 +- tools/testing/selftests/timers/set-timer-lat.c | 2 +- tools/testing/selftests/timers/set-tz.c | 2 +- tools/testing/selftests/timers/skew_consistency.c | 2 +- tools/testing/selftests/timers/threadtest.c | 2 +- tools/testing/selftests/timers/valid-adjtimex.c | 2 +- tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c | 2 +- tools/testing/selftests/tty/tty_tstamp_update.c | 2 +- tools/testing/selftests/uevent/uevent_filtering.c | 2 +- tools/testing/selftests/user_events/abi_test.c | 2 +- tools/testing/selftests/user_events/dyn_test.c | 2 +- tools/testing/selftests/user_events/ftrace_test.c | 2 +- tools/testing/selftests/user_events/perf_test.c | 2 +- tools/testing/selftests/user_events/user_events_selftests.h | 2 +- tools/testing/selftests/vDSO/vdso_test_abi.c | 2 +- tools/testing/selftests/vDSO/vdso_test_chacha.c | 2 +- tools/testing/selftests/vDSO/vdso_test_clock_getres.c | 2 +- tools/testing/selftests/vDSO/vdso_test_correctness.c | 2 +- tools/testing/selftests/vDSO/vdso_test_getcpu.c | 2 +- tools/testing/selftests/vDSO/vdso_test_getrandom.c | 2 +- tools/testing/selftests/vDSO/vdso_test_gettimeofday.c | 2 +- tools/testing/selftests/x86/corrupt_xstate_header.c | 2 +- tools/testing/selftests/x86/helpers.h | 2 +- tools/testing/selftests/x86/lam.c | 2 +- tools/testing/selftests/x86/syscall_numbering.c | 2 +- tools/testing/selftests/x86/test_mremap_vdso.c | 2 +- tools/testing/selftests/x86/test_vsyscall.c | 2 +- tools/testing/selftests/x86/xstate.h | 2 +- 280 files changed, 286 insertions(+), 280 deletions(-) -- 2.43.0

1 month, 2 weeks

3
15
0 0

[PATCH net-next] selftests: net: add test for ipv6 fragmentation

by Brett A C Sheffield

Add selftest for the IPv6 fragmentation regression which affected several stable kernels. Commit a18dfa9925b9 ("ipv6: save dontfrag in cork") was backported to stable without some prerequisite commits. This caused a regression when sending IPv6 UDP packets by preventing fragmentation and instead returning -1 (EMSGSIZE). Add selftest to check for this issue by attempting to send a packet larger than the interface MTU. The packet will be fragmented on a working kernel, with sendmsg(2) correctly returning the expected number of bytes sent. When the regression is present, sendmsg returns -1 and sets errno to EMSGSIZE. Signed-off-by: Brett A C Sheffield <bacs(a)librecast.net> Link: https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_fragmentation.c | 204 ++++++++++++++++++ 3 files changed, 206 insertions(+) create mode 100644 tools/testing/selftests/net/ipv6_fragmentation.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 47c293c2962f..3d4b4a53dfda 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,6 +16,7 @@ ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr +ipv6_fragmentation log.txt msg_oob msg_zerocopy diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b31a71f2b372..f83f91b758ae 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -117,6 +117,7 @@ TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh +TEST_GEN_PROGS += ipv6_fragmentation # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c new file mode 100644 index 000000000000..21e1a3cdc63d --- /dev/null +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Brett A C Sheffield <bacs(a)librecast.net> + * + * Kernel selftest for the IPv6 fragmentation regression which affected + * stable kernels: + * + * https://lore.kernel.org/stable/aElivdUXqd1OqgMY@karahi.gladserv.com + * + * Commit: + * a18dfa9925b9 ("ipv6: save dontfrag in cork") + * was backported to stable without some prerequisite commits. + * + * This caused a regression when sending IPv6 UDP packets by preventing + * fragmentation and instead returning -1 (EMSGSIZE). + * + * This selftest demonstrates the issue. sendmsg returns correctly (8192) + * on a working kernel, and returns -1 (EMSGSIZE) when the regression is + * present. + * + * The regression was not present in the mainline kernel, but add this test to + * catch similar breakage in future. + */ + +#define _GNU_SOURCE + +#include <fcntl.h> +#include <linux/if_tun.h> +#include <net/if.h> +#include <netinet/in.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <unistd.h> + +#define MTU 1500 +#define LARGER_THAN_MTU 8192 + +/* ensure MTU is smaller than what we plan to send */ +static int set_mtu(int ctl, char *ifname, struct ifreq *ifr) +{ + ifr->ifr_mtu = MTU; + return ioctl(ctl, SIOCSIFMTU, ifr); +} + +/* bring up interface */ +static int interface_up(int ctl, char *ifname, struct ifreq *ifr) +{ + if (ioctl(ctl, SIOCGIFFLAGS, ifr) == -1) { + perror("ioctl SIOCGIFFLAGS"); + return -1; + } + ifr->ifr_flags = ifr->ifr_flags | IFF_UP; + return ioctl(ctl, SIOCSIFFLAGS, ifr); +} + +/* no need to wait for DAD in our namespace */ +static int disable_dad(char *ifname) +{ + char sysvar[] = "/proc/sys/net/ipv6/conf/%s/accept_dad"; + char fname[IFNAMSIZ + sizeof(sysvar)]; + int fd; + + snprintf(fname, sizeof(fname), sysvar, ifname); + fd = open(fname, O_WRONLY); + if (fd == -1) { + perror("open accept_dad"); + return -1; + } + if (write(fd, "0", 1) != 1) { + perror("write"); + return -1; + } + return close(fd); +} + +/* create TAP interface that will be deleted when this process exits */ +static int create_interface(int ctl, char *ifname, struct ifreq *ifr) +{ + int fd; + + fd = open("/dev/net/tun", O_RDWR); + if (fd == -1) { + perror("open tun"); + return -1; + } + + ifr->ifr_flags = IFF_TAP | IFF_NO_PI; + if (ioctl(fd, TUNSETIFF, (void *)ifr) == -1) { + close(fd); + perror("ioctl: TUNSETIFF"); + return -1; + } + strcpy(ifname, ifr->ifr_name); + + return fd; +} + +/* we need to set MTU, so do this in a namespace to play nicely */ +static int create_namespace(void) +{ + const char *netns_path = "/proc/self/ns/net"; + int fd; + + if (unshare(CLONE_NEWNET) != 0) { + perror("unshare"); + return -1; + } + + fd = open(netns_path, O_RDONLY); + if (fd == -1) { + perror("open"); + return -1; + } + + if (setns(fd, CLONE_NEWNET)) { + perror("setns"); + return -1; + } + + return 0; +} + +static int setup(void) +{ + struct ifreq ifr = {0}; + char ifname[IFNAMSIZ]; + int fd = -1; + int ctl; + + if (create_namespace() == -1) + return -1; + + ctl = socket(AF_LOCAL, SOCK_STREAM, 0); + if (ctl == -1) + return -1; + + memset(ifname, 0, sizeof(ifname)); + fd = create_interface(ctl, ifname, &ifr); + if (fd == -1) + goto err_close_ctl; + if (disable_dad(ifname) == -1) + goto err_close_fd; + if (interface_up(ctl, ifname, &ifr) == -1) + goto err_close_fd; + if (set_mtu(ctl, ifname, &ifr) == -1) + goto err_close_fd; + usleep(10000); /* give interface a moment to wake up */ + goto err_close_ctl; +err_close_fd: + close(fd); + fd = -1; +err_close_ctl: + close(ctl); + return fd; +} + +int main(void) +{ + /* address doesn't matter, use an IPv6 multicast address for simplicity */ + struct in6_addr addr = { + .s6_addr[0] = 0xff, /* multicast */ + .s6_addr[1] = 0x12, /* set flags (T, link-local) */ + }; + struct sockaddr_in6 sa = { + .sin6_family = AF_INET6, + .sin6_addr = addr, + .sin6_port = 4242 + }; + char buf[LARGER_THAN_MTU] = {0}; + struct iovec iov = { .iov_base = buf, .iov_len = sizeof(buf)}; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_name = (struct sockaddr *)&sa, + .msg_namelen = sizeof(sa), + }; + ssize_t rc; + int ns_fd; + int s; + + printf("Testing IPv6 fragmentation\n"); + ns_fd = setup(); + if (ns_fd == -1) + return 1; + s = socket(AF_INET6, SOCK_DGRAM, 0); + msg.msg_name = (struct sockaddr *)&sa; + msg.msg_namelen = sizeof(sa); + rc = sendmsg(s, &msg, 0); + if (rc == -1) { + perror("send"); + return 1; + } else if (rc != LARGER_THAN_MTU) { + fprintf(stderr, "send() returned %zi\n", rc); + return 1; + } + close(s); + close(ns_fd); + + return 0; +} -- 2.49.1

1 month, 2 weeks

3
5
0 0

[PATCH] kselftest/arm64: Don't open code SVE_PT_SIZE() in fp-ptrace

by Mark Brown

In fp-trace when allocating a buffer to write SVE register data we open code the addition of the header size to the VL depeendent register data size, which lead to an underallocation bug when we cut'n'pasted the code for FPSIMD format writes. Use the SVE_PT_SIZE() macro that the kernel UAPI provides for this. Fixes: b84d2b27954f ("kselftest/arm64: Test FPSIMD format data writes via NT_ARM_SVE in fp-ptrace") Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/fp/fp-ptrace.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c index 124bc883365e..cdd7a45c045d 100644 --- a/tools/testing/selftests/arm64/fp/fp-ptrace.c +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -1187,7 +1187,7 @@ static void sve_write_sve(pid_t child, struct test_config *config) if (!vl) return; - iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", @@ -1234,8 +1234,7 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config) if (!vl) return; - iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, - SVE_PT_REGS_FPSIMD); + iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD); iov.iov_base = malloc(iov.iov_len); if (!iov.iov_base) { ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", --- base-commit: 8f5ae30d69d7543eee0d70083daf4de8fe15d585 change-id: 20250808-arm64-fp-trace-macro-02ede083da51 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 month, 2 weeks

2
1
0 0

[PATCH v4 00/23] ARM64 PMU Partitioning

by Colton Lewis

This series creates a new PMU scheme on ARM, a partitioned PMU that allows reserving a subset of counters for more direct guest access, significantly reducing overhead. More details, including performance benchmarks, can be read in the v1 cover letter linked below. v4: * Apply Mark Brown's non-UNDEF FGT control commit to the PMU FGT controls and calculate those controls with the others in kvm_calculate_traps() * Introduce lazy context swaps for guests that only turns on for guests that have enabled partitioning and accessed PMU registers. * Rename pmu-part.c to pmu-direct.c because future features might achieve direct PMU access without partitioning. * Better explain certain commits, such as why the untrapped registers are safe to untrap. * Reduce the PMU include cleanup down to only what is still necessary and explain why. v3: https://lore.kernel.org/kvm/20250626200459.1153955-1-coltonlewis@google.com/ v2: https://lore.kernel.org/kvm/20250620221326.1261128-1-coltonlewis@google.com/ v1: https://lore.kernel.org/kvm/20250602192702.2125115-1-coltonlewis@google.com/ Colton Lewis (21): arm64: cpufeature: Add cpucap for HPMN0 KVM: arm64: Reorganize PMU functions perf: arm_pmuv3: Introduce method to partition the PMU perf: arm_pmuv3: Generalize counter bitmasks perf: arm_pmuv3: Keep out of guest counter partition KVM: arm64: Account for partitioning in kvm_pmu_get_max_counters() KVM: arm64: Set up FGT for Partitioned PMU KVM: arm64: Writethrough trapped PMEVTYPER register KVM: arm64: Use physical PMSELR for PMXEVTYPER if partitioned KVM: arm64: Writethrough trapped PMOVS register KVM: arm64: Write fast path PMU register handlers KVM: arm64: Setup MDCR_EL2 to handle a partitioned PMU KVM: arm64: Account for partitioning in PMCR_EL0 access KVM: arm64: Context swap Partitioned PMU guest registers KVM: arm64: Enforce PMU event filter at vcpu_load() KVM: arm64: Extract enum debug_owner to enum vcpu_register_owner KVM: arm64: Implement lazy PMU context swaps perf: arm_pmuv3: Handle IRQs for Partitioned PMU guest counters KVM: arm64: Inject recorded guest interrupts KVM: arm64: Add ioctl to partition the PMU when supported KVM: arm64: selftests: Add test case for partitioned PMU Marc Zyngier (1): KVM: arm64: Reorganize PMU includes Mark Brown (1): KVM: arm64: Introduce non-UNDEF FGT control Documentation/virt/kvm/api.rst | 21 + arch/arm/include/asm/arm_pmuv3.h | 38 + arch/arm64/include/asm/arm_pmuv3.h | 61 +- arch/arm64/include/asm/kvm_host.h | 34 +- arch/arm64/include/asm/kvm_pmu.h | 123 +++ arch/arm64/include/asm/kvm_types.h | 7 +- arch/arm64/kernel/cpufeature.c | 8 + arch/arm64/kvm/Makefile | 2 +- arch/arm64/kvm/arm.c | 22 + arch/arm64/kvm/debug.c | 33 +- arch/arm64/kvm/hyp/include/hyp/debug-sr.h | 6 +- arch/arm64/kvm/hyp/include/hyp/switch.h | 181 ++++- arch/arm64/kvm/pmu-direct.c | 395 ++++++++++ arch/arm64/kvm/pmu-emul.c | 674 +--------------- arch/arm64/kvm/pmu.c | 725 ++++++++++++++++++ arch/arm64/kvm/sys_regs.c | 137 +++- arch/arm64/tools/cpucaps | 1 + arch/arm64/tools/sysreg | 6 +- drivers/perf/arm_pmuv3.c | 128 +++- include/linux/perf/arm_pmu.h | 1 + include/linux/perf/arm_pmuv3.h | 14 +- include/uapi/linux/kvm.h | 4 + tools/include/uapi/linux/kvm.h | 2 + .../selftests/kvm/arm64/vpmu_counter_access.c | 62 +- 24 files changed, 1910 insertions(+), 775 deletions(-) create mode 100644 arch/arm64/kvm/pmu-direct.c base-commit: 79150772457f4d45e38b842d786240c36bb1f97f -- 2.50.0.727.gbf7dc18ff4-goog

1 month, 2 weeks

3
30
0 0

[PATCHv4 iproute2-next] iplink: bond_slave: add support for actor_port_prio

by Hangbin Liu

Add support for the actor_port_prio option for bond slaves. This per-port priority can be used by the bonding driver in ad_select to choose the higher-priority aggregator during failover. Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- v4: no update v3: rename ad_actor_port_prio to actor_port_prio v2: no update --- ip/iplink_bond.c | 1 + ip/iplink_bond_slave.c | 18 ++++++++++++++++-- man/man8/ip-link.8.in | 6 ++++++ 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/ip/iplink_bond.c b/ip/iplink_bond.c index d6960f6d9b03..1a2c1b3042a0 100644 --- a/ip/iplink_bond.c +++ b/ip/iplink_bond.c @@ -91,6 +91,7 @@ static const char *ad_select_tbl[] = { "stable", "bandwidth", "count", + "prio", NULL, }; diff --git a/ip/iplink_bond_slave.c b/ip/iplink_bond_slave.c index ad6875006950..c88100e248dd 100644 --- a/ip/iplink_bond_slave.c +++ b/ip/iplink_bond_slave.c @@ -15,7 +15,9 @@ static void print_explain(FILE *f) { - fprintf(f, "Usage: ... bond_slave [ queue_id ID ] [ prio PRIORITY ]\n"); + fprintf(f, "Usage: ... bond_slave [ queue_id ID ] [ prio PRIORITY ]\n" + " [ actor_port_prio PRIORITY ]\n" + ); } static void explain(void) @@ -145,12 +147,18 @@ static void bond_slave_print_opt(struct link_util *lu, FILE *f, struct rtattr *t state); print_slave_oper_state(f, "ad_partner_oper_port_state_str", state); } + + if (tb[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]) + print_int(PRINT_ANY, + "actor_port_prio", + "actor_port_prio %d ", + rta_getattr_u16(tb[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO])); } static int bond_slave_parse_opt(struct link_util *lu, int argc, char **argv, struct nlmsghdr *n) { - __u16 queue_id; + __u16 queue_id, actor_port_prio; int prio; while (argc > 0) { @@ -164,6 +172,12 @@ static int bond_slave_parse_opt(struct link_util *lu, int argc, char **argv, if (get_s32(&prio, *argv, 0)) invarg("prio is invalid", *argv); addattr32(n, 1024, IFLA_BOND_SLAVE_PRIO, prio); + } else if (strcmp(*argv, "actor_port_prio") == 0) { + NEXT_ARG(); + if (get_u16(&actor_port_prio, *argv, 0)) + invarg("actor prio is invalid", *argv); + addattr16(n, 1024, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, + actor_port_prio); } else { if (matches(*argv, "help") != 0) fprintf(stderr, diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in index e3297c577152..7995943ab11f 100644 --- a/man/man8/ip-link.8.in +++ b/man/man8/ip-link.8.in @@ -2846,6 +2846,12 @@ the following additional arguments are supported: (a 32bit signed value). This option only valid for active-backup(1), balance-tlb (5) and balance-alb (6) mode. +.sp +.BI actor_port_prio " PRIORITY" +- set the slave's ad actor port priority for 802.3ad aggregation selection +logic during failover (a 16bit unsigned value). This option only valid for +802.3ad (4) mode. + .in -8 .TP -- 2.50.1

1 month, 2 weeks

2
5
0 0

[PATCH 1/9] KVM: selftests: Add pidfd_open syscall number fallback

by Aqib Faruqui

The kselftest-harness uses pidfd_open() for test timeout handling, but non-glibc C library headers may not define this syscall number. Add architecture-specific fallback definitions to pidfd.h, including support for Alpha (544) and other architectures (434). Update kselftest_harness.h to include pidfd.h for the syscall definitions. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kselftest_harness.h | 1 + tools/testing/selftests/pidfd/pidfd.h | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 2925e47db..1dd3e5a1b 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -69,6 +69,7 @@ #include <unistd.h> #include "kselftest.h" +#include "pidfd/pidfd.h" #define TEST_TIMEOUT_DEFAULT 30 diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index f87993def..c373ff18e 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -45,8 +45,12 @@ #endif #ifndef __NR_pidfd_open +#ifdef __alpha__ +#define __NR_pidfd_open 544 +#else #define __NR_pidfd_open 434 #endif +#endif #ifndef __NR_pidfd_send_signal #define __NR_pidfd_send_signal 424 -- 2.47.3

1 month, 2 weeks

2
1
0 0

[PATCH v4 00/15] Consolidate iommu page table implementations (AMD)

by Jason Gunthorpe

[All the precursor patches are merged now and AMD/RISCV/VTD conversions are written] Currently each of the iommu page table formats duplicates all of the logic to maintain the page table and perform map/unmap/etc operations. There are several different versions of the algorithms between all the different formats. The io-pgtable system provides an interface to help isolate the page table code from the iommu driver, but doesn't provide tools to implement the common algorithms. This makes it very hard to improve the state of the pagetable code under the iommu domains as any proposed improvement needs to alter a large number of different driver code paths. Combined with a lack of software based testing this makes improvement in this area very hard. iommufd wants several new page table operations: - More efficient map/unmap operations, using iommufd's batching logic - unmap that returns the physical addresses into a batch as it progresses - cut that allows splitting areas so large pages can have holes poked in them dynamically (ie guestmemfd hitless shared/private transitions) - More agressive freeing of table memory to avoid waste - Fragmenting large pages so that dirty tracking can be more granular - Reassembling large pages so that VMs can run at full IO performance in migration/dirty tracking error flows - KHO integration for kernel live upgrade Together these are algorithmically complex enough to be a very significant task to go and implement in all the page table formats we support. Just the "server" focused drivers use almost all the formats (ARMv8 S1&S2 / x86 PAE / AMDv1 / VT-D SS / RISCV) Instead of doing the duplicated work, this series takes the first step to consolidate the algorithms into one places. In spirit it is similar to the work Christoph did a few years back to pull the redundant get_user_pages() implementations out of the arch code into core MM. This unlocked a great deal of improvement in that space in the following years. I would like to see the same benefit in iommu as well. My first RFC showed a bigger picture with all most all formats and more algorithms. This series reorganizes that to be narrowly focused on just enough to convert the AMD driver to use the new mechanism. kunit tests are provided that allow good testing of the algorithms and all formats on x86, nothing is arch specific. AMD is one of the simpler options as the HW is quite uniform with few different options/bugs while still requiring the complicated contiguous pages support. The HW also has a very simple range based invalidation approach that is easy to implement. The AMD v1 and AMD v2 page table formats are implemented bit for bit identical to the current code, tested using a compare kunit test that checks against the io-pgtable version (on github, see below). Updating the AMD driver to replace the io-pgtable layer with the new stuff is fairly straightforward now. The layering is fixed up in the new version so that all the invalidation goes through function pointers. Several small fixing patches have come out of this as I've been fixing the problems that the test suite uncovers in the current code, and implementing the fixed version in iommupt. On performance, there is a quite wide variety of implementation designs across all the drivers. Looking at some key performance across the main formats: iommu_map(): pgsz ,avg new,old ns, min new,old ns , min % (+ve is better) 2^12, 53,66 , 51,63 , 19.19 (AMDV1) 256*2^12, 386,1909 , 367,1795 , 79.79 256*2^21, 362,1633 , 355,1556 , 77.77 2^12, 56,62 , 52,59 , 11.11 (AMDv2) 256*2^12, 405,1355 , 357,1292 , 72.72 256*2^21, 393,1160 , 358,1114 , 67.67 2^12, 55,65 , 53,62 , 14.14 (VTD second stage) 256*2^12, 391,518 , 332,512 , 35.35 256*2^21, 383,635 , 336,624 , 46.46 2^12, 57,65 , 55,63 , 12.12 (ARM 64 bit) 256*2^12, 380,389 , 361,369 , 2.02 256*2^21, 358,419 , 345,400 , 13.13 iommu_unmap(): pgsz ,avg new,old ns, min new,old ns , min % (+ve is better) 2^12, 69,88 , 65,85 , 23.23 (AMDv1) 256*2^12, 353,6498 , 331,6029 , 94.94 256*2^21, 373,6014 , 360,5706 , 93.93 2^12, 71,72 , 66,69 , 4.04 (AMDv2) 256*2^12, 228,891 , 206,871 , 76.76 256*2^21, 254,721 , 245,711 , 65.65 2^12, 69,87 , 65,82 , 20.20 (VTD second stage) 256*2^12, 210,321 , 200,315 , 36.36 256*2^21, 255,349 , 238,342 , 30.30 2^12, 72,77 , 68,74 , 8.08 (ARM 64 bit) 256*2^12, 521,357 , 447,346 , -29.29 256*2^21, 489,358 , 433,345 , -25.25 * Above numbers include additional patches to remove the iommu_pgsize() overheads. gcc 13.3.0, i7-12700 This version provides fairly consistent performance across formats. ARM unmap performance is quite different because this version supports contiguous pages and uses a very different algorithm for unmapping. Though why it is so worse compared to AMDv1 I haven't figured out yet. The per-format commits include a more detailed chart. There is a second branch: https://github.com/jgunthorpe/linux/commits/iommu_pt_all Containing supporting work and future steps: - ARM short descriptor (32 bit), ARM long descriptor (64 bit) formats - RISCV format and RISCV conversion https://github.com/jgunthorpe/linux/commits/iommu_pt_riscv - Support for a DMA incoherent HW page table walker - VT-D second stage format and VT-D conversion https://github.com/jgunthorpe/linux/commits/iommu_pt_vtd - DART v1 & v2 format - Draft of a iommufd 'cut' operation to break down huge pages - A compare test that checks the iommupt formats against the iopgtable interface, including updating AMD to have a working iopgtable and patches to make VT-D have an iopgtable for testing. - A performance test to micro-benchmark map and unmap against iogptable My strategy is to go one by one for the drivers: - AMD driver conversion - RISCV page table and driver - Intel VT-D driver and VTDSS page table - Flushing improvements for RISCV - ARM SMMUv3 And concurrently work on the algorithm side: - debugfs content dump, like VT-D has - Cut support - Increase/Decrease page size support - map/unmap batching - KHO As we make more algorithm improvements the value to convert the drivers increases. This is on github: https://github.com/jgunthorpe/linux/commits/iommu_pt v3: - Rebase on v6.16-rc3 - Integrate the HATS/HATDis changes - Remove 'default n' from kconfig - Remove unused 'PT_FIXED_TOP_LEVEL' - Improve comments and coumentation - Fix some compile warnings from kbuild robots v2: https://patch.msgid.link/r/0-v3-a93aab628dbc+521-iommu_pt_jgg@nvidia.com - Rebase on v6.16-rc2 - s/PT_ENTRY_WORD_SIZE/PT_ITEM_WORD_SIZE/s to follow the language better - Comment and documentation updates - Add PT_TOP_PHYS_MASK to help manage alignment restrictions on the top pointer - Add missed force_aperture = true - Make pt_iommu_deinit() take care of the not-yet-inited error case internally as AMD/RISCV/VTD all shared this logic - Change gather_range() into gather_range_pages() so it also deals with the page list. This makes the following cache flushing series simpler - Fix missed update of unmap->unmapped in some error cases - Change clear_contig() to order the gather more logically - Remove goto from the error handling in __map_range_leaf() - s/log2_/oalog2_/ in places where the argument is an oaddr_t - Pass the pts to pt_table_install64/32() - Do not use SIGN_EXTEND for the AMDv2 page table because of Vasant's information on how PASID 0 works. v1: https://patch.msgid.link/r/0-v2-5c26bde5c22d+58b-iommu_pt_jgg@nvidia.com - AMD driver only, many code changes RFC: https://lore.kernel.org/all/0-v1-01fa10580981+1d-iommu_pt_jgg@nvidia.com/ Cc: Michael Roth <michael.roth(a)amd.com> Cc: Alexey Kardashevskiy <aik(a)amd.com> Cc: Pasha Tatashin <pasha.tatashin(a)soleen.com> Cc: James Gowans <jgowans(a)amazon.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Alejandro Jimenez (1): iommu/amd: Use the generic iommu page table Jason Gunthorpe (14): genpt: Generic Page Table base API genpt: Add Documentation/ files iommupt: Add the basic structure of the iommu implementation iommupt: Add the AMD IOMMU v1 page table format iommupt: Add iova_to_phys op iommupt: Add unmap_pages op iommupt: Add map_pages op iommupt: Add read_and_clear_dirty op iommupt: Add a kunit test for Generic Page Table iommupt: Add a mock pagetable format for iommufd selftest to use iommufd: Change the selftest to use iommupt instead of xarray iommupt: Add the x86 64 bit page table format iommu/amd: Remove AMD io_pgtable support iommupt: Add a kunit test for the IOMMU implementation .clang-format | 1 + Documentation/driver-api/generic_pt.rst | 140 ++ Documentation/driver-api/index.rst | 1 + drivers/iommu/Kconfig | 2 + drivers/iommu/Makefile | 1 + drivers/iommu/amd/Kconfig | 5 +- drivers/iommu/amd/Makefile | 2 +- drivers/iommu/amd/amd_iommu.h | 1 - drivers/iommu/amd/amd_iommu_types.h | 109 +- drivers/iommu/amd/io_pgtable.c | 560 -------- drivers/iommu/amd/io_pgtable_v2.c | 370 ------ drivers/iommu/amd/iommu.c | 538 ++++---- drivers/iommu/generic_pt/.kunitconfig | 13 + drivers/iommu/generic_pt/Kconfig | 67 + drivers/iommu/generic_pt/fmt/Makefile | 26 + drivers/iommu/generic_pt/fmt/amdv1.h | 409 ++++++ drivers/iommu/generic_pt/fmt/defs_amdv1.h | 21 + drivers/iommu/generic_pt/fmt/defs_x86_64.h | 21 + drivers/iommu/generic_pt/fmt/iommu_amdv1.c | 15 + drivers/iommu/generic_pt/fmt/iommu_mock.c | 10 + drivers/iommu/generic_pt/fmt/iommu_template.h | 48 + drivers/iommu/generic_pt/fmt/iommu_x86_64.c | 11 + drivers/iommu/generic_pt/fmt/x86_64.h | 248 ++++ drivers/iommu/generic_pt/iommu_pt.h | 1146 +++++++++++++++++ drivers/iommu/generic_pt/kunit_generic_pt.h | 717 +++++++++++ drivers/iommu/generic_pt/kunit_iommu.h | 183 +++ drivers/iommu/generic_pt/kunit_iommu_pt.h | 451 +++++++ drivers/iommu/generic_pt/pt_common.h | 354 +++++ drivers/iommu/generic_pt/pt_defs.h | 323 +++++ drivers/iommu/generic_pt/pt_fmt_defaults.h | 193 +++ drivers/iommu/generic_pt/pt_iter.h | 636 +++++++++ drivers/iommu/generic_pt/pt_log2.h | 130 ++ drivers/iommu/io-pgtable.c | 4 - drivers/iommu/iommufd/Kconfig | 1 + drivers/iommu/iommufd/iommufd_test.h | 11 +- drivers/iommu/iommufd/selftest.c | 438 +++---- include/linux/generic_pt/common.h | 166 +++ include/linux/generic_pt/iommu.h | 270 ++++ include/linux/io-pgtable.h | 2 - tools/testing/selftests/iommu/iommufd.c | 60 +- tools/testing/selftests/iommu/iommufd_utils.h | 12 + 41 files changed, 6124 insertions(+), 1592 deletions(-) create mode 100644 Documentation/driver-api/generic_pt.rst delete mode 100644 drivers/iommu/amd/io_pgtable.c delete mode 100644 drivers/iommu/amd/io_pgtable_v2.c create mode 100644 drivers/iommu/generic_pt/.kunitconfig create mode 100644 drivers/iommu/generic_pt/Kconfig create mode 100644 drivers/iommu/generic_pt/fmt/Makefile create mode 100644 drivers/iommu/generic_pt/fmt/amdv1.h create mode 100644 drivers/iommu/generic_pt/fmt/defs_amdv1.h create mode 100644 drivers/iommu/generic_pt/fmt/defs_x86_64.h create mode 100644 drivers/iommu/generic_pt/fmt/iommu_amdv1.c create mode 100644 drivers/iommu/generic_pt/fmt/iommu_mock.c create mode 100644 drivers/iommu/generic_pt/fmt/iommu_template.h create mode 100644 drivers/iommu/generic_pt/fmt/iommu_x86_64.c create mode 100644 drivers/iommu/generic_pt/fmt/x86_64.h create mode 100644 drivers/iommu/generic_pt/iommu_pt.h create mode 100644 drivers/iommu/generic_pt/kunit_generic_pt.h create mode 100644 drivers/iommu/generic_pt/kunit_iommu.h create mode 100644 drivers/iommu/generic_pt/kunit_iommu_pt.h create mode 100644 drivers/iommu/generic_pt/pt_common.h create mode 100644 drivers/iommu/generic_pt/pt_defs.h create mode 100644 drivers/iommu/generic_pt/pt_fmt_defaults.h create mode 100644 drivers/iommu/generic_pt/pt_iter.h create mode 100644 drivers/iommu/generic_pt/pt_log2.h create mode 100644 include/linux/generic_pt/common.h create mode 100644 include/linux/generic_pt/iommu.h base-commit: 8da0d63bd5726ff656bfa1eacb45d6f5cce65616 -- 2.43.0

1 month, 2 weeks

2
36
0 0

[PATCH 3/9] KVM: selftests: Add pthread_attr_setaffinity_np fallback

by Aqib Faruqui

The pthread_attr_setaffinity_np function is a GNU extension that may not be available in non-glibc C libraries. Some KVM selftests use this function for CPU affinity control. Add a function declaration and weak stub implementation for non-glibc builds. This allows tests to build, with the affinity setting being a no-op and errno set for the caller when the actual function is not available. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kvm/include/kvm_util.h | 4 ++++ tools/testing/selftests/kvm/lib/kvm_util.c | 11 +++++++++++ 2 files changed, 15 insertions(+) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 7fae7f5e7..8177178b5 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -31,6 +31,10 @@ #include "kvm_util_types.h" #include "sparsebit.h" +#ifndef __GLIBC__ +int pthread_attr_setaffinity_np(pthread_attr_t *attr, size_t cpusetsize, const cpu_set_t *cpuset); +#endif /* __GLIBC__ */ + #define KVM_DEV_PATH "/dev/kvm" #define KVM_MAX_VCPUS 512 diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index c3f5142b0..5ce80303d 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -20,6 +20,17 @@ #define KVM_UTIL_MIN_PFN 2 +#ifndef __GLIBC__ +int __attribute__((weak)) +pthread_attr_setaffinity_np(pthread_attr_t *__attr, + size_t __cpusetsize, + const cpu_set_t *__cpuset) +{ + errno = ENOSYS; + return -1; +} +#endif + uint32_t guest_random_seed; struct guest_random_state guest_rng; static uint32_t last_guest_seed; -- 2.47.3

1 month, 2 weeks

2
1
0 0

[PATCH 5/9] KVM: selftests: Prevent PAGE_SIZE redefinition on x86

by Aqib Faruqui

Prevent PAGE_SIZE redefinition warnings that can occur due to namespace pollution from included headers. Add an #ifndef directive before defining PAGE_SIZE to avoid redefinition conflicts. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kvm/include/x86/processor.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 2efb05c2f..3f93d1b4f 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -368,7 +368,9 @@ static inline unsigned int x86_model(unsigned int eax) #define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) #define PAGE_SHIFT 12 +#ifndef PAGE_SIZE #define PAGE_SIZE (1ULL << PAGE_SHIFT) +#endif #define PAGE_MASK (~(PAGE_SIZE-1) & PHYSICAL_PAGE_MASK) #define HUGEPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9)) -- 2.47.3

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next v5 0/2] Fix bpf_strnstr len error

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Fix bpf_strnstr() wrong 'len' parameter, bpf_strnstr("open", "open", 4) should return 0 instead of -ENOENT. And fix a more general case when s2 is a suffix of the first len characters of s1. Rong Tao (2): bpf/helpers: bpf_strnstr: Exact match length selftests/bpf: Add tests for bpf_strnstr kernel/bpf/helpers.c | 9 ++++++++- .../testing/selftests/bpf/progs/string_kfuncs_success.c | 8 ++++++-- 2 files changed, 14 insertions(+), 3 deletions(-) --- v5: Add more commit message and change the patch 0001's comment; v4: Add comment and more selftests; https://lore.kernel.org/all/tencent_CBD40091C14056E8298BE3725B65EE156405@qq… v3: Fix selftests/bpf error in v2, sorry about that; https://lore.kernel.org/lkml/tencent_69BD268FBA201219240B51661D5E96A8D80A@q… v2: Follow Andrii Nakryiko's advise, fix the 'wrong fix'; https://lore.kernel.org/lkml/tencent_DF4DA83EEBFB9246E5E3357BB40911CCA005@q… v1: https://lore.kernel.org/lkml/tencent_65E5988AD52BEC280D22964189505CD6ED06@q… -- 2.51.0

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next v5 1/2] bpf/helpers: bpf_strnstr: Exact match length

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> strnstr should not treat the ending '\0' of s2 as a matching character if the parameter 'len' equal to s2 string length, for example: 1. bpf_strnstr("openat", "open", 4) = -ENOENT 2. bpf_strnstr("openat", "open", 5) = 0 This patch makes (1) return 0, fix just the `len == strlen(s2)` case. And fix a more general case when s2 is a suffix of the first len characters of s1. Fixes: e91370550f1f ("bpf: Add kfuncs for read-only string operations") Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- kernel/bpf/helpers.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 401b4932cc49..91ad124844ae 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -3672,10 +3672,17 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len guard(pagefault)(); for (i = 0; i < XATTR_SIZE_MAX; i++) { - for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) { + for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) { __get_kernel_nofault(&c2, s2__ign + j, char, err_out); if (c2 == '\0') return i; + /** + * We allow reading an extra byte from s2 (note the + * `i + j <= len` above) to cover the case when s2 is + * a suffix of the first len chars of s1. + */ + if (i + j == len) + break; __get_kernel_nofault(&c1, s1__ign + j, char, err_out); if (c1 == '\0') return -ENOENT; -- 2.51.0

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next v5 2/2] selftests/bpf: Add tests for bpf_strnstr

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Add tests for bpf_strnstr(): bpf_strnstr("", "", 0) = 0 bpf_strnstr("hello world", "hello", 5) = 0 bpf_strnstr(str, "hello", 4) = -ENOENT bpf_strnstr("", "a", 0) = -ENOENT Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..a47690174e0e 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } -__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); } -__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } +__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } char _license[] SEC("license") = "GPL"; -- 2.51.0

1 month, 2 weeks

1
0
0 0

[PATCH v8 1/1] selftests/mm/uffd: Refactor non-composite global vars into struct

by Ujwal Kundur

Refactor macros and non-composite global variable definitions into a struct that is defined at the start of a test and is passed around instead of relying on global vars. Signed-off-by: Ujwal Kundur <ujwal.kundur(a)gmail.com> Acked-by: Peter Xu <peterx(a)redhat.com> Reviewed-by: Brendan Jackman <jackmanb(a)google.com> --- v7: https://lore.kernel.org/all/20250817065211.855-1-ujwal.kundur@gmail.com/ Changes since v7: - rebase on mm-new again after cd79a1d9b08a was dropped - address minor formatting nits (David) Changes since v6: - rebased on 6.17-rc1 changes (cd79a1d9b08a) - removes unused args and adds the __unused attribute; since change is cosmetic-only, carry forward Acked-by tag - verified output remains unchanged using virtme-ng Changes since v5: - ensure uffd_global_test_opts_t instances are initialized - verified output remains unchanged using virtme-ng Changes since v4: - define gopts as global within uffd-stress.c to retain existing sigalrm handler logic Changes since v3: - more formatting fixes Changes since v2: - redo patch on mm-new branch Changes since v1: - indentation fixes - squash into single patch to assist bisections tools/testing/selftests/mm/uffd-common.c | 271 ++++----- tools/testing/selftests/mm/uffd-common.h | 78 +-- tools/testing/selftests/mm/uffd-stress.c | 228 ++++---- tools/testing/selftests/mm/uffd-unit-tests.c | 559 ++++++++++--------- tools/testing/selftests/mm/uffd-wp-mremap.c | 20 +- 5 files changed, 615 insertions(+), 541 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index a37088a23ffe..994fe8c03923 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -7,18 +7,29 @@ #include "uffd-common.h" -#define BASE_PMD_ADDR ((void *)(1UL << 30)) - -volatile bool test_uffdio_copy_eexist = true; -unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; -char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -int uffd = -1, uffd_flags, finished, *pipefd, test_type; -bool map_shared; -bool test_uffdio_wp = true; -unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; uffd_test_case_ops_t *uffd_test_case_ops; -atomic_bool ready_for_fork; + +#define BASE_PMD_ADDR ((void *)(1UL << 30)) + +/* pthread_mutex_t starts at page offset 0 */ +pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts) +{ + return (pthread_mutex_t *) (area + nr * gopts->page_size); +} + +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +volatile unsigned long long *area_count(char *area, unsigned long nr, + uffd_global_test_opts_t *gopts) +{ + return (volatile unsigned long long *) + ((unsigned long)(area + nr * gopts->page_size + + sizeof(pthread_mutex_t) + sizeof(unsigned long long) - 1) & + ~(unsigned long)(sizeof(unsigned long long) - 1)); +} static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) { @@ -40,15 +51,15 @@ static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) return mem_fd; } -static void anon_release_pages(char *rel_area) +static void anon_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); } -static int anon_allocate_area(void **alloc_area, bool is_src) +static int anon_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + *alloc_area = mmap(NULL, gopts->nr_pages * gopts->page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (*alloc_area == MAP_FAILED) { *alloc_area = NULL; @@ -57,31 +68,32 @@ static int anon_allocate_area(void **alloc_area, bool is_src) return 0; } -static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) +static void noop_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t len, unsigned long offset) { } -static void hugetlb_release_pages(char *rel_area) +static void hugetlb_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (!map_shared) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + if (!gopts->map_shared) { + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); } else { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE)) err("madvise(MADV_REMOVE) failed"); } } -static int hugetlb_allocate_area(void **alloc_area, bool is_src) +static int hugetlb_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { - off_t size = nr_pages * page_size; + off_t size = gopts->nr_pages * gopts->page_size; off_t offset = is_src ? 0 : size; void *area_alias = NULL; char **alloc_area_alias; int mem_fd = uffd_mem_fd_create(size * 2, true); *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | + (gopts->map_shared ? MAP_SHARED : MAP_PRIVATE) | (is_src ? 0 : MAP_NORESERVE), mem_fd, offset); if (*alloc_area == MAP_FAILED) { @@ -89,7 +101,7 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) return -errno; } - if (map_shared) { + if (gopts->map_shared) { area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); if (area_alias == MAP_FAILED) @@ -97,9 +109,9 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) } if (is_src) { - alloc_area_alias = &area_src_alias; + alloc_area_alias = &gopts->area_src_alias; } else { - alloc_area_alias = &area_dst_alias; + alloc_area_alias = &gopts->area_dst_alias; } if (area_alias) *alloc_area_alias = area_alias; @@ -108,24 +120,25 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) return 0; } -static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) +static void hugetlb_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t len, unsigned long offset) { - if (!map_shared) + if (!gopts->map_shared) return; - *start = (unsigned long) area_dst_alias + offset; + *start = (unsigned long) gopts->area_dst_alias + offset; } -static void shmem_release_pages(char *rel_area) +static void shmem_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE)) err("madvise(MADV_REMOVE) failed"); } -static int shmem_allocate_area(void **alloc_area, bool is_src) +static int shmem_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { void *area_alias = NULL; - size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize(); + size_t bytes = gopts->nr_pages * gopts->page_size, hpage_size = read_pmd_pagesize(); unsigned long offset = is_src ? 0 : bytes; char *p = NULL, *p_alias = NULL; int mem_fd = uffd_mem_fd_create(bytes * 2, false); @@ -159,22 +172,23 @@ static int shmem_allocate_area(void **alloc_area, bool is_src) err("mmap of anonymous memory failed at %p", p_alias); if (is_src) - area_src_alias = area_alias; + gopts->area_src_alias = area_alias; else - area_dst_alias = area_alias; + gopts->area_dst_alias = area_alias; close(mem_fd); return 0; } -static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) +static void shmem_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t len, unsigned long offset) { - *start = (unsigned long)area_dst_alias + offset; + *start = (unsigned long)gopts->area_dst_alias + offset; } -static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) +static void shmem_check_pmd_mapping(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages) { - if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, + if (!check_huge_shmem(gopts->area_dst_alias, expect_nr_hpages, read_pmd_pagesize())) err("Did not find expected %d number of hugepages", expect_nr_hpages); @@ -234,18 +248,18 @@ void uffd_stats_report(struct uffd_args *args, int n_cpus) printf("\n"); } -int userfaultfd_open(uint64_t *features) +int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features) { struct uffdio_api uffdio_api; - uffd = uffd_open(UFFD_FLAGS); - if (uffd < 0) + gopts->uffd = uffd_open(UFFD_FLAGS); + if (gopts->uffd < 0) return -1; - uffd_flags = fcntl(uffd, F_GETFD, NULL); + gopts->uffd_flags = fcntl(gopts->uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; uffdio_api.features = *features; - if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + if (ioctl(gopts->uffd, UFFDIO_API, &uffdio_api)) /* Probably lack of CAP_PTRACE? */ return -1; if (uffdio_api.api != UFFD_API) @@ -255,59 +269,63 @@ int userfaultfd_open(uint64_t *features) return 0; } -static inline void munmap_area(void **area) +static inline void munmap_area(uffd_global_test_opts_t *gopts, void **area) { if (*area) - if (munmap(*area, nr_pages * page_size)) + if (munmap(*area, gopts->nr_pages * gopts->page_size)) err("munmap"); *area = NULL; } -void uffd_test_ctx_clear(void) +void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts) { size_t i; - if (pipefd) { - for (i = 0; i < nr_parallel * 2; ++i) { - if (close(pipefd[i])) + if (gopts->pipefd) { + for (i = 0; i < gopts->nr_parallel * 2; ++i) { + if (close(gopts->pipefd[i])) err("close pipefd"); } - free(pipefd); - pipefd = NULL; + free(gopts->pipefd); + gopts->pipefd = NULL; } - if (count_verify) { - free(count_verify); - count_verify = NULL; + if (gopts->count_verify) { + free(gopts->count_verify); + gopts->count_verify = NULL; } - if (uffd != -1) { - if (close(uffd)) + if (gopts->uffd != -1) { + if (close(gopts->uffd)) err("close uffd"); - uffd = -1; + gopts->uffd = -1; } - munmap_area((void **)&area_src); - munmap_area((void **)&area_src_alias); - munmap_area((void **)&area_dst); - munmap_area((void **)&area_dst_alias); - munmap_area((void **)&area_remap); + munmap_area(gopts, (void **)&gopts->area_src); + munmap_area(gopts, (void **)&gopts->area_src_alias); + munmap_area(gopts, (void **)&gopts->area_dst); + munmap_area(gopts, (void **)&gopts->area_dst_alias); + munmap_area(gopts, (void **)&gopts->area_remap); } -int uffd_test_ctx_init(uint64_t features, const char **errmsg) +int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg) { unsigned long nr, cpu; int ret; + gopts->area_src_alias = NULL; + gopts->area_dst_alias = NULL; + gopts->area_remap = NULL; + if (uffd_test_case_ops && uffd_test_case_ops->pre_alloc) { - ret = uffd_test_case_ops->pre_alloc(errmsg); + ret = uffd_test_case_ops->pre_alloc(gopts, errmsg); if (ret) return ret; } - ret = uffd_test_ops->allocate_area((void **)&area_src, true); - ret |= uffd_test_ops->allocate_area((void **)&area_dst, false); + ret = uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_src, true); + ret |= uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_dst, false); if (ret) { if (errmsg) *errmsg = "memory allocation failed"; @@ -315,26 +333,26 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) } if (uffd_test_case_ops && uffd_test_case_ops->post_alloc) { - ret = uffd_test_case_ops->post_alloc(errmsg); + ret = uffd_test_case_ops->post_alloc(gopts, errmsg); if (ret) return ret; } - ret = userfaultfd_open(&features); + ret = userfaultfd_open(gopts, &features); if (ret) { if (errmsg) *errmsg = "possible lack of privilege"; return ret; } - count_verify = malloc(nr_pages * sizeof(unsigned long long)); - if (!count_verify) + gopts->count_verify = malloc(gopts->nr_pages * sizeof(unsigned long long)); + if (!gopts->count_verify) err("count_verify"); - for (nr = 0; nr < nr_pages; nr++) { - *area_mutex(area_src, nr) = + for (nr = 0; nr < gopts->nr_pages; nr++) { + *area_mutex(gopts->area_src, nr, gopts) = (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; - count_verify[nr] = *area_count(area_src, nr) = 1; + gopts->count_verify[nr] = *area_count(gopts->area_src, nr, gopts) = 1; /* * In the transition between 255 to 256, powerpc will * read out of order in my_bcmp and see both bytes as @@ -342,7 +360,7 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) * after the count, to avoid my_bcmp to trigger false * positives. */ - *(area_count(area_src, nr) + 1) = 1; + *(area_count(gopts->area_src, nr, gopts) + 1) = 1; } /* @@ -363,13 +381,13 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) * proactively split the thp and drop any accidentally initialized * pages within area_dst. */ - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - pipefd = malloc(sizeof(int) * nr_parallel * 2); - if (!pipefd) + gopts->pipefd = malloc(sizeof(int) * gopts->nr_parallel * 2); + if (!gopts->pipefd) err("pipefd"); - for (cpu = 0; cpu < nr_parallel; cpu++) - if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) + if (pipe2(&gopts->pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) err("pipe"); return 0; @@ -416,9 +434,9 @@ static void continue_range(int ufd, __u64 start, __u64 len, bool wp) ret, (int64_t) req.mapped); } -int uffd_read_msg(int ufd, struct uffd_msg *msg) +int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg) { - int ret = read(uffd, msg, sizeof(*msg)); + int ret = read(gopts->uffd, msg, sizeof(*msg)); if (ret != sizeof(*msg)) { if (ret < 0) { @@ -433,7 +451,8 @@ int uffd_read_msg(int ufd, struct uffd_msg *msg) return 0; } -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) +void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, + struct uffd_args *args) { unsigned long offset; @@ -442,7 +461,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { /* Write protect page faults */ - wp_range(uffd, msg->arg.pagefault.address, page_size, false); + wp_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, false); args->wp_faults++; } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { uint8_t *area; @@ -460,12 +479,12 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) * (UFFD-registered). */ - area = (uint8_t *)(area_dst + - ((char *)msg->arg.pagefault.address - - area_dst_alias)); - for (b = 0; b < page_size; ++b) + area = (uint8_t *)(gopts->area_dst + + ((char *)msg->arg.pagefault.address - + gopts->area_dst_alias)); + for (b = 0; b < gopts->page_size; ++b) area[b] = ~area[b]; - continue_range(uffd, msg->arg.pagefault.address, page_size, + continue_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, args->apply_wp); args->minor_faults++; } else { @@ -493,10 +512,10 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault"); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(gopts->page_size-1); - if (copy_page(uffd, offset, args->apply_wp)) + if (copy_page(gopts, offset, args->apply_wp)) args->missing_faults++; } } @@ -504,6 +523,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) void *uffd_poll_thread(void *arg) { struct uffd_args *args = (struct uffd_args *)arg; + uffd_global_test_opts_t *gopts = args->gopts; unsigned long cpu = args->cpu; struct pollfd pollfd[2]; struct uffd_msg msg; @@ -514,12 +534,12 @@ void *uffd_poll_thread(void *arg) if (!args->handle_fault) args->handle_fault = uffd_handle_page_fault; - pollfd[0].fd = uffd; + pollfd[0].fd = gopts->uffd; pollfd[0].events = POLLIN; - pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].fd = gopts->pipefd[cpu*2]; pollfd[1].events = POLLIN; - ready_for_fork = true; + gopts->ready_for_fork = true; for (;;) { ret = poll(pollfd, 2, -1); @@ -537,30 +557,30 @@ void *uffd_poll_thread(void *arg) } if (!(pollfd[0].revents & POLLIN)) err("pollfd[0].revents %d", pollfd[0].revents); - if (uffd_read_msg(uffd, &msg)) + if (uffd_read_msg(gopts, &msg)) continue; switch (msg.event) { default: err("unexpected msg event %u\n", msg.event); break; case UFFD_EVENT_PAGEFAULT: - args->handle_fault(&msg, args); + args->handle_fault(gopts, &msg, args); break; case UFFD_EVENT_FORK: - close(uffd); - uffd = msg.arg.fork.ufd; - pollfd[0].fd = uffd; + close(gopts->uffd); + gopts->uffd = msg.arg.fork.ufd; + pollfd[0].fd = gopts->uffd; break; case UFFD_EVENT_REMOVE: uffd_reg.range.start = msg.arg.remove.start; uffd_reg.range.len = msg.arg.remove.end - msg.arg.remove.start; - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + if (ioctl(gopts->uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) err("remove failure"); break; case UFFD_EVENT_REMAP: - area_remap = area_dst; /* save for later unmap */ - area_dst = (char *)(unsigned long)msg.arg.remap.to; + gopts->area_remap = gopts->area_dst; /* save for later unmap */ + gopts->area_dst = (char *)(unsigned long)msg.arg.remap.to; break; } } @@ -568,17 +588,18 @@ void *uffd_poll_thread(void *arg) return NULL; } -static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, +static void retry_copy_page(uffd_global_test_opts_t *gopts, struct uffdio_copy *uffdio_copy, unsigned long offset) { - uffd_test_ops->alias_mapping(&uffdio_copy->dst, + uffd_test_ops->alias_mapping(gopts, + &uffdio_copy->dst, uffdio_copy->len, offset); - if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { + if (ioctl(gopts->uffd, UFFDIO_COPY, uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy->copy != -EEXIST) err("UFFDIO_COPY retry error: %"PRId64, - (int64_t)uffdio_copy->copy); + (int64_t)uffdio_copy->copy); } else { err("UFFDIO_COPY retry unexpected: %"PRId64, (int64_t)uffdio_copy->copy); @@ -597,60 +618,60 @@ static void wake_range(int ufd, unsigned long addr, unsigned long len) addr), exit(1); } -int __copy_page(int ufd, unsigned long offset, bool retry, bool wp) +int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp) { struct uffdio_copy uffdio_copy; - if (offset >= nr_pages * page_size) + if (offset >= gopts->nr_pages * gopts->page_size) err("unexpected offset %lu\n", offset); - uffdio_copy.dst = (unsigned long) area_dst + offset; - uffdio_copy.src = (unsigned long) area_src + offset; - uffdio_copy.len = page_size; + uffdio_copy.dst = (unsigned long) gopts->area_dst + offset; + uffdio_copy.src = (unsigned long) gopts->area_src + offset; + uffdio_copy.len = gopts->page_size; if (wp) uffdio_copy.mode = UFFDIO_COPY_MODE_WP; else uffdio_copy.mode = 0; uffdio_copy.copy = 0; - if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { + if (ioctl(gopts->uffd, UFFDIO_COPY, &uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy.copy != -EEXIST) err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); - wake_range(ufd, uffdio_copy.dst, page_size); - } else if (uffdio_copy.copy != page_size) { + wake_range(gopts->uffd, uffdio_copy.dst, gopts->page_size); + } else if (uffdio_copy.copy != gopts->page_size) { err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); } else { - if (test_uffdio_copy_eexist && retry) { - test_uffdio_copy_eexist = false; - retry_copy_page(ufd, &uffdio_copy, offset); + if (gopts->test_uffdio_copy_eexist && retry) { + gopts->test_uffdio_copy_eexist = false; + retry_copy_page(gopts, &uffdio_copy, offset); } return 1; } return 0; } -int copy_page(int ufd, unsigned long offset, bool wp) +int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp) { - return __copy_page(ufd, offset, false, wp); + return __copy_page(gopts, offset, false, wp); } -int move_page(int ufd, unsigned long offset, unsigned long len) +int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len) { struct uffdio_move uffdio_move; - if (offset + len > nr_pages * page_size) + if (offset + len > gopts->nr_pages * gopts->page_size) err("unexpected offset %lu and length %lu\n", offset, len); - uffdio_move.dst = (unsigned long) area_dst + offset; - uffdio_move.src = (unsigned long) area_src + offset; + uffdio_move.dst = (unsigned long) gopts->area_dst + offset; + uffdio_move.src = (unsigned long) gopts->area_src + offset; uffdio_move.len = len; uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES; uffdio_move.move = 0; - if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) { + if (ioctl(gopts->uffd, UFFDIO_MOVE, &uffdio_move)) { /* real retval in uffdio_move.move */ if (uffdio_move.move != -EEXIST) err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move); - wake_range(ufd, uffdio_move.dst, len); + wake_range(gopts->uffd, uffdio_move.dst, len); } else if (uffdio_move.move != len) { err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move); } else diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 7700cbfa3975..37d3ca55905f 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -56,20 +56,17 @@ #define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) -/* pthread_mutex_t starts at page offset 0 */ -#define area_mutex(___area, ___nr) \ - ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) -/* - * count is placed in the page after pthread_mutex_t naturally aligned - * to avoid non alignment faults on non-x86 archs. - */ -#define area_count(___area, ___nr) \ - ((volatile unsigned long long *) ((unsigned long) \ - ((___area) + (___nr)*page_size + \ - sizeof(pthread_mutex_t) + \ - sizeof(unsigned long long) - 1) & \ - ~(unsigned long)(sizeof(unsigned long long) \ - - 1))) +struct uffd_global_test_opts { + unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; + char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; + int uffd, uffd_flags, finished, *pipefd, test_type; + bool map_shared; + bool test_uffdio_wp; + unsigned long long *count_verify; + volatile bool test_uffdio_copy_eexist; + atomic_bool ready_for_fork; +}; +typedef struct uffd_global_test_opts uffd_global_test_opts_t; /* Userfaultfd test statistics */ struct uffd_args { @@ -79,50 +76,55 @@ struct uffd_args { unsigned long missing_faults; unsigned long wp_faults; unsigned long minor_faults; + struct uffd_global_test_opts *gopts; /* A custom fault handler; defaults to uffd_handle_page_fault. */ - void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args); + void (*handle_fault)(struct uffd_global_test_opts *gopts, + struct uffd_msg *msg, + struct uffd_args *args); }; struct uffd_test_ops { - int (*allocate_area)(void **alloc_area, bool is_src); - void (*release_pages)(char *rel_area); - void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); - void (*check_pmd_mapping)(void *p, int expect_nr_hpages); + int (*allocate_area)(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src); + void (*release_pages)(uffd_global_test_opts_t *gopts, char *rel_area); + void (*alias_mapping)(uffd_global_test_opts_t *gopts, + __u64 *start, + size_t len, + unsigned long offset); + void (*check_pmd_mapping)(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages); }; typedef struct uffd_test_ops uffd_test_ops_t; struct uffd_test_case_ops { - int (*pre_alloc)(const char **errmsg); - int (*post_alloc)(const char **errmsg); + int (*pre_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg); + int (*post_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg); }; typedef struct uffd_test_case_ops uffd_test_case_ops_t; -extern unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; -extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -extern int uffd, uffd_flags, finished, *pipefd, test_type; -extern bool map_shared; -extern bool test_uffdio_wp; -extern unsigned long long *count_verify; -extern volatile bool test_uffdio_copy_eexist; -extern atomic_bool ready_for_fork; - +extern uffd_global_test_opts_t *uffd_gtest_opts; extern uffd_test_ops_t anon_uffd_test_ops; extern uffd_test_ops_t shmem_uffd_test_ops; extern uffd_test_ops_t hugetlb_uffd_test_ops; extern uffd_test_ops_t *uffd_test_ops; extern uffd_test_case_ops_t *uffd_test_case_ops; +pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts); +volatile unsigned long long *area_count(char *area, + unsigned long nr, + uffd_global_test_opts_t *gopts); + void uffd_stats_report(struct uffd_args *args, int n_cpus); -int uffd_test_ctx_init(uint64_t features, const char **errmsg); -void uffd_test_ctx_clear(void); -int userfaultfd_open(uint64_t *features); -int uffd_read_msg(int ufd, struct uffd_msg *msg); +int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg); +void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts); +int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features); +int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); -int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); -int copy_page(int ufd, unsigned long offset, bool wp); -int move_page(int ufd, unsigned long offset, unsigned long len); +void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args); +int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp); +int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp); +int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len); void *uffd_poll_thread(void *arg); int uffd_open_dev(unsigned int flags); diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 991db8f90727..10154800a73f 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -44,6 +44,12 @@ uint64_t features; #define BOUNCE_VERIFY (1<<2) #define BOUNCE_POLL (1<<3) static int bounces; +/* defined globally for this particular test as the sigalrm handler + * depends on test_uffdio_*_eexist. + * XXX: define gopts in main() when we figure out a way to deal with + * test_uffdio_*_eexist. + */ +static uffd_global_test_opts_t *gopts; /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ #define ALARM_INTERVAL_SECS 10 @@ -76,54 +82,58 @@ static void usage(void) exit(1); } -static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) +static void uffd_stats_reset(uffd_global_test_opts_t *gopts, struct uffd_args *args, + unsigned long n_cpus) { int i; for (i = 0; i < n_cpus; i++) { args[i].cpu = i; - args[i].apply_wp = test_uffdio_wp; + args[i].apply_wp = gopts->test_uffdio_wp; args[i].missing_faults = 0; args[i].wp_faults = 0; args[i].minor_faults = 0; + args[i].gopts = gopts; } } static void *locking_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_args *args = (struct uffd_args *) arg; + uffd_global_test_opts_t *gopts = args->gopts; + unsigned long cpu = (unsigned long) args->cpu; unsigned long page_nr; unsigned long long count; if (!(bounces & BOUNCE_RANDOM)) { page_nr = -bounces; if (!(bounces & BOUNCE_RACINGFAULTS)) - page_nr += cpu * nr_pages_per_cpu; + page_nr += cpu * gopts->nr_pages_per_cpu; } - while (!finished) { + while (!gopts->finished) { if (bounces & BOUNCE_RANDOM) { if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr)) err("getrandom failed"); } else page_nr += 1; - page_nr %= nr_pages; - pthread_mutex_lock(area_mutex(area_dst, page_nr)); - count = *area_count(area_dst, page_nr); - if (count != count_verify[page_nr]) + page_nr %= gopts->nr_pages; + pthread_mutex_lock(area_mutex(gopts->area_dst, page_nr, gopts)); + count = *area_count(gopts->area_dst, page_nr, gopts); + if (count != gopts->count_verify[page_nr]) err("page_nr %lu memory corruption %llu %llu", - page_nr, count, count_verify[page_nr]); + page_nr, count, gopts->count_verify[page_nr]); count++; - *area_count(area_dst, page_nr) = count_verify[page_nr] = count; - pthread_mutex_unlock(area_mutex(area_dst, page_nr)); + *area_count(gopts->area_dst, page_nr, gopts) = gopts->count_verify[page_nr] = count; + pthread_mutex_unlock(area_mutex(gopts->area_dst, page_nr, gopts)); } return NULL; } -static int copy_page_retry(int ufd, unsigned long offset) +static int copy_page_retry(uffd_global_test_opts_t *gopts, unsigned long offset) { - return __copy_page(ufd, offset, true, test_uffdio_wp); + return __copy_page(gopts, offset, true, gopts->test_uffdio_wp); } pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -131,15 +141,16 @@ pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; static void *uffd_read_thread(void *arg) { struct uffd_args *args = (struct uffd_args *)arg; + uffd_global_test_opts_t *gopts = args->gopts; struct uffd_msg msg; pthread_mutex_unlock(&uffd_read_mutex); /* from here cancellation is ok */ for (;;) { - if (uffd_read_msg(uffd, &msg)) + if (uffd_read_msg(gopts, &msg)) continue; - uffd_handle_page_fault(&msg, args); + uffd_handle_page_fault(gopts, &msg, args); } return NULL; @@ -147,32 +158,34 @@ static void *uffd_read_thread(void *arg) static void *background_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_args *args = (struct uffd_args *) arg; + uffd_global_test_opts_t *gopts = args->gopts; + unsigned long cpu = (unsigned long) args->cpu; unsigned long page_nr, start_nr, mid_nr, end_nr; - start_nr = cpu * nr_pages_per_cpu; - end_nr = (cpu+1) * nr_pages_per_cpu; + start_nr = cpu * gopts->nr_pages_per_cpu; + end_nr = (cpu+1) * gopts->nr_pages_per_cpu; mid_nr = (start_nr + end_nr) / 2; /* Copy the first half of the pages */ for (page_nr = start_nr; page_nr < mid_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); + copy_page_retry(gopts, page_nr * gopts->page_size); /* * If we need to test uffd-wp, set it up now. Then we'll have * at least the first half of the pages mapped already which * can be write-protected for testing */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst + start_nr * page_size, - nr_pages_per_cpu * page_size, true); + if (gopts->test_uffdio_wp) + wp_range(gopts->uffd, (unsigned long)gopts->area_dst + start_nr * gopts->page_size, + gopts->nr_pages_per_cpu * gopts->page_size, true); /* * Continue the 2nd half of the page copying, handling write * protection faults if any */ for (page_nr = mid_nr; page_nr < end_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); + copy_page_retry(gopts, page_nr * gopts->page_size); return NULL; } @@ -180,17 +193,21 @@ static void *background_thread(void *arg) static int stress(struct uffd_args *args) { unsigned long cpu; - pthread_t locking_threads[nr_parallel]; - pthread_t uffd_threads[nr_parallel]; - pthread_t background_threads[nr_parallel]; + uffd_global_test_opts_t *gopts = args->gopts; + pthread_t locking_threads[gopts->nr_parallel]; + pthread_t uffd_threads[gopts->nr_parallel]; + pthread_t background_threads[gopts->nr_parallel]; - finished = 0; - for (cpu = 0; cpu < nr_parallel; cpu++) { + gopts->finished = 0; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) { if (pthread_create(&locking_threads[cpu], &attr, - locking_thread, (void *)cpu)) + locking_thread, (void *)&args[cpu])) return 1; if (bounces & BOUNCE_POLL) { - if (pthread_create(&uffd_threads[cpu], &attr, uffd_poll_thread, &args[cpu])) + if (pthread_create(&uffd_threads[cpu], + &attr, + uffd_poll_thread, + (void *) &args[cpu])) err("uffd_poll_thread create"); } else { if (pthread_create(&uffd_threads[cpu], &attr, @@ -200,10 +217,10 @@ static int stress(struct uffd_args *args) pthread_mutex_lock(&uffd_read_mutex); } if (pthread_create(&background_threads[cpu], &attr, - background_thread, (void *)cpu)) + background_thread, (void *)&args[cpu])) return 1; } - for (cpu = 0; cpu < nr_parallel; cpu++) + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) if (pthread_join(background_threads[cpu], NULL)) return 1; @@ -216,17 +233,17 @@ static int stress(struct uffd_args *args) * UFFDIO_COPY without writing zero pages into area_dst * because the background threads already completed). */ - uffd_test_ops->release_pages(area_src); + uffd_test_ops->release_pages(gopts, gopts->area_src); - finished = 1; - for (cpu = 0; cpu < nr_parallel; cpu++) + gopts->finished = 1; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) if (pthread_join(locking_threads[cpu], NULL)) return 1; - for (cpu = 0; cpu < nr_parallel; cpu++) { + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) { char c; if (bounces & BOUNCE_POLL) { - if (write(pipefd[cpu*2+1], &c, 1) != 1) + if (write(gopts->pipefd[cpu*2+1], &c, 1) != 1) err("pipefd write error"); if (pthread_join(uffd_threads[cpu], (void *)&args[cpu])) @@ -242,26 +259,26 @@ static int stress(struct uffd_args *args) return 0; } -static int userfaultfd_stress(void) +static int userfaultfd_stress(uffd_global_test_opts_t *gopts) { void *area; unsigned long nr; - struct uffd_args args[nr_parallel]; - uint64_t mem_size = nr_pages * page_size; + struct uffd_args args[gopts->nr_parallel]; + uint64_t mem_size = gopts->nr_pages * gopts->page_size; int flags = 0; - memset(args, 0, sizeof(struct uffd_args) * nr_parallel); + memset(args, 0, sizeof(struct uffd_args) * gopts->nr_parallel); - if (features & UFFD_FEATURE_WP_UNPOPULATED && test_type == TEST_ANON) + if (features & UFFD_FEATURE_WP_UNPOPULATED && gopts->test_type == TEST_ANON) flags = UFFD_FEATURE_WP_UNPOPULATED; - if (uffd_test_ctx_init(flags, NULL)) + if (uffd_test_ctx_init(gopts, flags, NULL)) err("context init failed"); - if (posix_memalign(&area, page_size, page_size)) + if (posix_memalign(&area, gopts->page_size, gopts->page_size)) err("out of memory"); zeropage = area; - bzero(zeropage, page_size); + bzero(zeropage, gopts->page_size); pthread_mutex_lock(&uffd_read_mutex); @@ -284,18 +301,18 @@ static int userfaultfd_stress(void) fflush(stdout); if (bounces & BOUNCE_POLL) - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); else - fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags & ~O_NONBLOCK); /* register */ - if (uffd_register(uffd, area_dst, mem_size, - true, test_uffdio_wp, false)) + if (uffd_register(gopts->uffd, gopts->area_dst, mem_size, + true, gopts->test_uffdio_wp, false)) err("register failure"); - if (area_dst_alias) { - if (uffd_register(uffd, area_dst_alias, mem_size, - true, test_uffdio_wp, false)) + if (gopts->area_dst_alias) { + if (uffd_register(gopts->uffd, gopts->area_dst_alias, mem_size, + true, gopts->test_uffdio_wp, false)) err("register failure alias"); } @@ -323,87 +340,88 @@ static int userfaultfd_stress(void) * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's * required to MADV_DONTNEED here. */ - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - uffd_stats_reset(args, nr_parallel); + uffd_stats_reset(gopts, args, gopts->nr_parallel); /* bounce pass */ if (stress(args)) { - uffd_test_ctx_clear(); + uffd_test_ctx_clear(gopts); return 1; } /* Clear all the write protections if there is any */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst, - nr_pages * page_size, false); + if (gopts->test_uffdio_wp) + wp_range(gopts->uffd, (unsigned long)gopts->area_dst, + gopts->nr_pages * gopts->page_size, false); /* unregister */ - if (uffd_unregister(uffd, area_dst, mem_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, mem_size)) err("unregister failure"); - if (area_dst_alias) { - if (uffd_unregister(uffd, area_dst_alias, mem_size)) + if (gopts->area_dst_alias) { + if (uffd_unregister(gopts->uffd, gopts->area_dst_alias, mem_size)) err("unregister failure alias"); } /* verification */ if (bounces & BOUNCE_VERIFY) - for (nr = 0; nr < nr_pages; nr++) - if (*area_count(area_dst, nr) != count_verify[nr]) + for (nr = 0; nr < gopts->nr_pages; nr++) + if (*area_count(gopts->area_dst, nr, gopts) != + gopts->count_verify[nr]) err("error area_count %llu %llu %lu\n", - *area_count(area_src, nr), - count_verify[nr], nr); + *area_count(gopts->area_src, nr, gopts), + gopts->count_verify[nr], nr); /* prepare next bounce */ - swap(area_src, area_dst); + swap(gopts->area_src, gopts->area_dst); - swap(area_src_alias, area_dst_alias); + swap(gopts->area_src_alias, gopts->area_dst_alias); - uffd_stats_report(args, nr_parallel); + uffd_stats_report(args, gopts->nr_parallel); } - uffd_test_ctx_clear(); + uffd_test_ctx_clear(gopts); return 0; } -static void set_test_type(const char *type) +static void set_test_type(uffd_global_test_opts_t *gopts, const char *type) { if (!strcmp(type, "anon")) { - test_type = TEST_ANON; + gopts->test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; } else if (!strcmp(type, "hugetlb")) { - test_type = TEST_HUGETLB; + gopts->test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; - map_shared = true; + gopts->map_shared = true; } else if (!strcmp(type, "hugetlb-private")) { - test_type = TEST_HUGETLB; + gopts->test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; } else if (!strcmp(type, "shmem")) { - map_shared = true; - test_type = TEST_SHMEM; + gopts->map_shared = true; + gopts->test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } else if (!strcmp(type, "shmem-private")) { - test_type = TEST_SHMEM; + gopts->test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } } -static void parse_test_type_arg(const char *raw_type) +static void parse_test_type_arg(uffd_global_test_opts_t *gopts, const char *raw_type) { - set_test_type(raw_type); + set_test_type(gopts, raw_type); - if (!test_type) + if (!gopts->test_type) err("failed to parse test type argument: '%s'", raw_type); - if (test_type == TEST_HUGETLB) - page_size = default_huge_page_size(); + if (gopts->test_type == TEST_HUGETLB) + gopts->page_size = default_huge_page_size(); else - page_size = sysconf(_SC_PAGE_SIZE); + gopts->page_size = sysconf(_SC_PAGE_SIZE); - if (!page_size) + if (!gopts->page_size) err("Unable to determine page size"); - if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 - > page_size) + if ((unsigned long) area_count(NULL, 0, gopts) + sizeof(unsigned long long) * 2 + > gopts->page_size) err("Impossible to run this test"); /* @@ -415,21 +433,21 @@ static void parse_test_type_arg(const char *raw_type) if (uffd_get_features(&features) && errno == ENOENT) ksft_exit_skip("failed to get available features (%d)\n", errno); - test_uffdio_wp = test_uffdio_wp && + gopts->test_uffdio_wp = gopts->test_uffdio_wp && (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); - if (test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) - test_uffdio_wp = false; + if (gopts->test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) + gopts->test_uffdio_wp = false; - close(uffd); - uffd = -1; + close(gopts->uffd); + gopts->uffd = -1; } static void sigalrm(int sig) { if (sig != SIGALRM) abort(); - test_uffdio_copy_eexist = true; + gopts->test_uffdio_copy_eexist = true; alarm(ALARM_INTERVAL_SECS); } @@ -438,6 +456,8 @@ int main(int argc, char **argv) unsigned long nr_cpus; size_t bytes; + gopts = (uffd_global_test_opts_t *) malloc(sizeof(uffd_global_test_opts_t)); + if (argc < 4) usage(); @@ -445,11 +465,11 @@ int main(int argc, char **argv) err("failed to arm SIGALRM"); alarm(ALARM_INTERVAL_SECS); - parse_test_type_arg(argv[1]); + parse_test_type_arg(gopts, argv[1]); bytes = atol(argv[2]) * 1024 * 1024; - if (test_type == TEST_HUGETLB && - get_free_hugepages() < 2 * (bytes / page_size) + 10) { + if (gopts->test_type == TEST_HUGETLB && + get_free_hugepages() < 2 * (bytes / gopts->page_size) + 10) { printf("skip: Skipping userfaultfd... not enough hugepages\n"); return KSFT_SKIP; } @@ -459,15 +479,15 @@ int main(int argc, char **argv) /* Don't let calculation below go to zero. */ ksft_print_msg("_SC_NPROCESSORS_ONLN (%lu) too large, capping nr_threads to 32\n", nr_cpus); - nr_parallel = 32; + gopts->nr_parallel = 32; } else { - nr_parallel = nr_cpus; + gopts->nr_parallel = nr_cpus; } - nr_pages_per_cpu = bytes / page_size / nr_parallel; - if (!nr_pages_per_cpu) { + gopts->nr_pages_per_cpu = bytes / gopts->page_size / gopts->nr_parallel; + if (!gopts->nr_pages_per_cpu) { _err("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)", - bytes, page_size, nr_parallel); + bytes, gopts->page_size, gopts->nr_parallel); usage(); } @@ -476,11 +496,11 @@ int main(int argc, char **argv) _err("invalid bounces"); usage(); } - nr_pages = nr_pages_per_cpu * nr_parallel; + gopts->nr_pages = gopts->nr_pages_per_cpu * gopts->nr_parallel; printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", - nr_pages, nr_pages_per_cpu); - return userfaultfd_stress(); + gopts->nr_pages, gopts->nr_pages_per_cpu); + return userfaultfd_stress(gopts); } #else /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 50501b38e34e..9e3be2ee7f1b 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -76,7 +76,7 @@ struct uffd_test_args { typedef struct uffd_test_args uffd_test_args_t; /* Returns: UFFD_TEST_* */ -typedef void (*uffd_test_fn)(uffd_test_args_t *); +typedef void (*uffd_test_fn)(uffd_global_test_opts_t *, uffd_test_args_t *); typedef struct { const char *name; @@ -181,33 +181,6 @@ static int test_uffd_api(bool use_dev) return 1; } -/* - * This function initializes the global variables. TODO: remove global - * vars and then remove this. - */ -static int -uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test, - mem_type_t *mem_type, const char **errmsg) -{ - map_shared = mem_type->shared; - uffd_test_ops = mem_type->mem_ops; - uffd_test_case_ops = test->test_case_ops; - - if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) - page_size = default_huge_page_size(); - else - page_size = psize(); - - /* Ensure we have at least 2 pages */ - nr_pages = MAX(UFFD_TEST_MEM_SIZE, page_size * 2) / page_size; - /* TODO: remove this global var.. it's so ugly */ - nr_parallel = 1; - - /* Initialize test arguments */ - args->mem_type = mem_type; - - return uffd_test_ctx_init(test->uffd_feature_required, errmsg); -} static bool uffd_feature_supported(uffd_test_case_t *test) { @@ -237,7 +210,8 @@ static int pagemap_open(void) } while (0) typedef struct { - int parent_uffd, child_uffd; + uffd_global_test_opts_t *gopts; + int child_uffd; } fork_event_args; static void *fork_event_consumer(void *data) @@ -245,10 +219,10 @@ static void *fork_event_consumer(void *data) fork_event_args *args = data; struct uffd_msg msg = { 0 }; - ready_for_fork = true; + args->gopts->ready_for_fork = true; /* Read until a full msg received */ - while (uffd_read_msg(args->parent_uffd, &msg)); + while (uffd_read_msg(args->gopts, &msg)); if (msg.event != UFFD_EVENT_FORK) err("wrong message: %u\n", msg.event); @@ -304,9 +278,9 @@ static void unpin_pages(pin_args *args) args->pinned = false; } -static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) +static int pagemap_test_fork(uffd_global_test_opts_t *gopts, bool with_event, bool test_pin) { - fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 }; + fork_event_args args = { .gopts = gopts, .child_uffd = -1 }; pthread_t thread; pid_t child; uint64_t value; @@ -314,10 +288,10 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) /* Prepare a thread to resolve EVENT_FORK */ if (with_event) { - ready_for_fork = false; + gopts->ready_for_fork = false; if (pthread_create(&thread, NULL, fork_event_consumer, &args)) err("pthread_create()"); - while (!ready_for_fork) + while (!gopts->ready_for_fork) ; /* Wait for the poll_thread to start executing before forking */ } @@ -328,14 +302,14 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) fd = pagemap_open(); - if (test_pin && pin_pages(&args, area_dst, page_size)) + if (test_pin && pin_pages(&args, gopts->area_dst, gopts->page_size)) /* * Normally when reach here we have pinned in * previous tests, so shouldn't fail anymore */ err("pin page failed in child"); - value = pagemap_get_entry(fd, area_dst); + value = pagemap_get_entry(fd, gopts->area_dst); /* * After fork(), we should handle uffd-wp bit differently: * @@ -361,70 +335,70 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) return result; } -static void uffd_wp_unpopulated_test(uffd_test_args_t *args) +static void uffd_wp_unpopulated_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { uint64_t value; int pagemap_fd; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Test applying pte marker to anon unpopulated */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); /* Test unprotect on anon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Test zap on anon marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - if (madvise(area_dst, page_size, MADV_DONTNEED)) + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); - value = pagemap_get_entry(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Test fault in after marker removed */ - *area_dst = 1; - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 1; + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); /* Test read-zero-page upon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - *(volatile char *)area_dst; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + *(volatile char *)gopts->area_dst; /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); uffd_test_pass(); } -static void uffd_wp_fork_test_common(uffd_test_args_t *args, +static void uffd_wp_fork_test_common(uffd_global_test_opts_t *gopts, uffd_test_args_t *args, bool with_event) { int pagemap_fd; uint64_t value; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 1; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in present pte", with_event ? "missing" : "stall"); goto out; @@ -442,79 +416,80 @@ static void uffd_wp_fork_test_common(uffd_test_args_t *args, * to expose pte markers. */ if (args->mem_type->shared) { - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("MADV_DONTNEED"); } else { /* * NOTE: ignore retval because private-hugetlb doesn't yet * support swapping, so it could fail. */ - madvise(area_dst, page_size, MADV_PAGEOUT); + madvise(gopts->area_dst, gopts->page_size, MADV_PAGEOUT); } /* Uffd-wp should persist even swapped out */ - value = pagemap_get_entry(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte", with_event ? "missing" : "stall"); goto out; } /* Unprotect; this tests swap pte modifications */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Fault in the page from disk */ - *area_dst = 2; - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 2; + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); uffd_test_pass(); out: - if (uffd_unregister(uffd, area_dst, nr_pages * page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size)) err("unregister failed"); close(pagemap_fd); } -static void uffd_wp_fork_test(uffd_test_args_t *args) +static void uffd_wp_fork_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_test_common(args, false); + uffd_wp_fork_test_common(gopts, args, false); } -static void uffd_wp_fork_with_event_test(uffd_test_args_t *args) +static void uffd_wp_fork_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_test_common(args, true); + uffd_wp_fork_test_common(gopts, args, true); } -static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args, +static void uffd_wp_fork_pin_test_common(uffd_global_test_opts_t *gopts, + uffd_test_args_t *args, bool with_event) { int pagemap_fd; pin_args pin_args = {}; - if (uffd_register(uffd, area_dst, page_size, false, true, false)) + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, page_size, true); + *gopts->area_dst = 1; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); /* * 1. First pin, then fork(). This tests fork() special path when * doing early CoW if the page is private. */ - if (pin_pages(&pin_args, area_dst, page_size)) { + if (pin_pages(&pin_args, gopts->area_dst, gopts->page_size)) { uffd_test_skip("Possibly CONFIG_GUP_TEST missing " "or unprivileged"); close(pagemap_fd); - uffd_unregister(uffd, area_dst, page_size); + uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size); return; } - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in early CoW of fork()", with_event ? "missing" : "stall"); unpin_pages(&pin_args); @@ -527,49 +502,50 @@ static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args, * 2. First fork(), then pin (in the child, where test_pin==true). * This tests COR, aka, page unsharing on private memories. */ - if (pagemap_test_fork(uffd, with_event, true)) { + if (pagemap_test_fork(gopts, with_event, true)) { uffd_test_fail("Detected %s uffd-wp bit when RO pin", with_event ? "missing" : "stall"); goto out; } uffd_test_pass(); out: - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("register failed"); close(pagemap_fd); } -static void uffd_wp_fork_pin_test(uffd_test_args_t *args) +static void uffd_wp_fork_pin_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_pin_test_common(args, false); + uffd_wp_fork_pin_test_common(gopts, args, false); } -static void uffd_wp_fork_pin_with_event_test(uffd_test_args_t *args) +static void uffd_wp_fork_pin_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_pin_test_common(args, true); + uffd_wp_fork_pin_test_common(gopts, args, true); } -static void check_memory_contents(char *p) +static void check_memory_contents(uffd_global_test_opts_t *gopts, char *p) { unsigned long i, j; uint8_t expected_byte; - for (i = 0; i < nr_pages; ++i) { + for (i = 0; i < gopts->nr_pages; ++i) { expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); - for (j = 0; j < page_size; j++) { - uint8_t v = *(uint8_t *)(p + (i * page_size) + j); + for (j = 0; j < gopts->page_size; j++) { + uint8_t v = *(uint8_t *)(p + (i * gopts->page_size) + j); if (v != expected_byte) err("unexpected page contents"); } } } -static void uffd_minor_test_common(bool test_collapse, bool test_wp) +static void uffd_minor_test_common(uffd_global_test_opts_t *gopts, bool test_collapse, bool test_wp) { unsigned long p; pthread_t uffd_mon; char c; struct uffd_args args = { 0 }; + args.gopts = gopts; /* * NOTE: MADV_COLLAPSE is not yet compatible with WP, so testing @@ -577,7 +553,7 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) */ assert(!(test_collapse && test_wp)); - if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst_alias, gopts->nr_pages * gopts->page_size, /* NOTE! MADV_COLLAPSE may not work with uffd-wp */ false, test_wp, true)) err("register failure"); @@ -586,9 +562,9 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) * After registering with UFFD, populate the non-UFFD-registered side of * the shared mapping. This should *not* trigger any UFFD minor faults. */ - for (p = 0; p < nr_pages; ++p) - memset(area_dst + (p * page_size), p % ((uint8_t)-1), - page_size); + for (p = 0; p < gopts->nr_pages; ++p) + memset(gopts->area_dst + (p * gopts->page_size), p % ((uint8_t)-1), + gopts->page_size); args.apply_wp = test_wp; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) @@ -600,50 +576,51 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) * fault. uffd_poll_thread will resolve the fault by bit-flipping the * page's contents, and then issuing a CONTINUE ioctl. */ - check_memory_contents(area_dst_alias); + check_memory_contents(gopts, gopts->area_dst_alias); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("join() failed"); if (test_collapse) { - if (madvise(area_dst_alias, nr_pages * page_size, + if (madvise(gopts->area_dst_alias, gopts->nr_pages * gopts->page_size, MADV_COLLAPSE)) { /* It's fine to fail for this one... */ uffd_test_skip("MADV_COLLAPSE failed"); return; } - uffd_test_ops->check_pmd_mapping(area_dst, - nr_pages * page_size / + uffd_test_ops->check_pmd_mapping(gopts, + gopts->area_dst, + gopts->nr_pages * gopts->page_size / read_pmd_pagesize()); /* * This won't cause uffd-fault - it purely just makes sure there * was no corruption. */ - check_memory_contents(area_dst_alias); + check_memory_contents(gopts, gopts->area_dst_alias); } - if (args.missing_faults != 0 || args.minor_faults != nr_pages) + if (args.missing_faults != 0 || args.minor_faults != gopts->nr_pages) uffd_test_fail("stats check error"); else uffd_test_pass(); } -void uffd_minor_test(uffd_test_args_t *args) +void uffd_minor_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_minor_test_common(false, false); + uffd_minor_test_common(gopts, false, false); } -void uffd_minor_wp_test(uffd_test_args_t *args) +void uffd_minor_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_minor_test_common(false, true); + uffd_minor_test_common(gopts, false, true); } -void uffd_minor_collapse_test(uffd_test_args_t *args) +void uffd_minor_collapse_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_minor_test_common(true, false); + uffd_minor_test_common(gopts, true, false); } static sigjmp_buf jbuf, *sigbuf; @@ -678,7 +655,7 @@ static void sighndl(int sig, siginfo_t *siginfo, void *ptr) * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal * feature. Using monitor thread, verify no userfault events are generated. */ -static int faulting_process(int signal_test, bool wp) +static int faulting_process(uffd_global_test_opts_t *gopts, int signal_test, bool wp) { unsigned long nr, i; unsigned long long count; @@ -687,7 +664,7 @@ static int faulting_process(int signal_test, bool wp) struct sigaction act; volatile unsigned long signalled = 0; - split_nr_pages = (nr_pages + 1) / 2; + split_nr_pages = (gopts->nr_pages + 1) / 2; if (signal_test) { sigbuf = &jbuf; @@ -701,7 +678,7 @@ static int faulting_process(int signal_test, bool wp) for (nr = 0; nr < split_nr_pages; nr++) { volatile int steps = 1; - unsigned long offset = nr * page_size; + unsigned long offset = nr * gopts->page_size; if (signal_test) { if (sigsetjmp(*sigbuf, 1) != 0) { @@ -713,15 +690,15 @@ static int faulting_process(int signal_test, bool wp) if (steps == 1) { /* This is a MISSING request */ steps++; - if (copy_page(uffd, offset, wp)) + if (copy_page(gopts, offset, wp)) signalled++; } else { /* This is a WP request */ assert(steps == 2); - wp_range(uffd, - (__u64)area_dst + + wp_range(gopts->uffd, + (__u64)gopts->area_dst + offset, - page_size, false); + gopts->page_size, false); } } else { signalled++; @@ -730,51 +707,53 @@ static int faulting_process(int signal_test, bool wp) } } - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) + count = *area_count(gopts->area_dst, nr, gopts); + if (count != gopts->count_verify[nr]) err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); + nr, count, gopts->count_verify[nr]); /* * Trigger write protection if there is by writing * the same value back. */ - *area_count(area_dst, nr) = count; + *area_count(gopts->area_dst, nr, gopts) = count; } if (signal_test) return signalled != split_nr_pages; - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, - MREMAP_MAYMOVE | MREMAP_FIXED, area_src); - if (area_dst == MAP_FAILED) + gopts->area_dst = mremap(gopts->area_dst, gopts->nr_pages * gopts->page_size, + gopts->nr_pages * gopts->page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, + gopts->area_src); + if (gopts->area_dst == MAP_FAILED) err("mremap"); /* Reset area_src since we just clobbered it */ - area_src = NULL; + gopts->area_src = NULL; - for (; nr < nr_pages; nr++) { - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) { + for (; nr < gopts->nr_pages; nr++) { + count = *area_count(gopts->area_dst, nr, gopts); + if (count != gopts->count_verify[nr]) { err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); + nr, count, gopts->count_verify[nr]); } /* * Trigger write protection if there is by writing * the same value back. */ - *area_count(area_dst, nr) = count; + *area_count(gopts->area_dst, nr, gopts) = count; } - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - for (nr = 0; nr < nr_pages; nr++) - for (i = 0; i < page_size; i++) - if (*(area_dst + nr * page_size + i) != 0) + for (nr = 0; nr < gopts->nr_pages; nr++) + for (i = 0; i < gopts->page_size; i++) + if (*(gopts->area_dst + nr * gopts->page_size + i) != 0) err("page %lu offset %lu is not zero", nr, i); return 0; } -static void uffd_sigbus_test_common(bool wp) +static void uffd_sigbus_test_common(uffd_global_test_opts_t *gopts, bool wp) { unsigned long userfaults; pthread_t uffd_mon; @@ -782,25 +761,26 @@ static void uffd_sigbus_test_common(bool wp) int err; char c; struct uffd_args args = { 0 }; + args.gopts = gopts; - ready_for_fork = false; + gopts->ready_for_fork = false; - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, wp, false)) err("register failure"); - if (faulting_process(1, wp)) + if (faulting_process(gopts, 1, wp)) err("faulting process failed"); - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); args.apply_wp = wp; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - while (!ready_for_fork) + while (!gopts->ready_for_fork) ; /* Wait for the poll_thread to start executing before forking */ pid = fork(); @@ -808,12 +788,12 @@ static void uffd_sigbus_test_common(bool wp) err("fork"); if (!pid) - exit(faulting_process(2, wp)); + exit(faulting_process(gopts, 2, wp)); waitpid(pid, &err, 0); if (err) err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, (void **)&userfaults)) err("pthread_join()"); @@ -824,28 +804,29 @@ static void uffd_sigbus_test_common(bool wp) uffd_test_pass(); } -static void uffd_sigbus_test(uffd_test_args_t *args) +static void uffd_sigbus_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_sigbus_test_common(false); + uffd_sigbus_test_common(gopts, false); } -static void uffd_sigbus_wp_test(uffd_test_args_t *args) +static void uffd_sigbus_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_sigbus_test_common(true); + uffd_sigbus_test_common(gopts, true); } -static void uffd_events_test_common(bool wp) +static void uffd_events_test_common(uffd_global_test_opts_t *gopts, bool wp) { pthread_t uffd_mon; pid_t pid; int err; char c; struct uffd_args args = { 0 }; + args.gopts = gopts; - ready_for_fork = false; + gopts->ready_for_fork = false; - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, wp, false)) err("register failure"); @@ -853,7 +834,7 @@ static void uffd_events_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - while (!ready_for_fork) + while (!gopts->ready_for_fork) ; /* Wait for the poll_thread to start executing before forking */ pid = fork(); @@ -861,39 +842,39 @@ static void uffd_events_test_common(bool wp) err("fork"); if (!pid) - exit(faulting_process(0, wp)); + exit(faulting_process(gopts, 0, wp)); waitpid(pid, &err, 0); if (err) err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("pthread_join()"); - if (args.missing_faults != nr_pages) + if (args.missing_faults != gopts->nr_pages) uffd_test_fail("Fault counts wrong"); else uffd_test_pass(); } -static void uffd_events_test(uffd_test_args_t *args) +static void uffd_events_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_events_test_common(false); + uffd_events_test_common(gopts, false); } -static void uffd_events_wp_test(uffd_test_args_t *args) +static void uffd_events_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_events_test_common(true); + uffd_events_test_common(gopts, true); } -static void retry_uffdio_zeropage(int ufd, +static void retry_uffdio_zeropage(uffd_global_test_opts_t *gopts, struct uffdio_zeropage *uffdio_zeropage) { - uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffd_test_ops->alias_mapping(gopts, &uffdio_zeropage->range.start, uffdio_zeropage->range.len, 0); - if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (ioctl(gopts->uffd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { if (uffdio_zeropage->zeropage != -EEXIST) err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)uffdio_zeropage->zeropage); @@ -903,16 +884,16 @@ static void retry_uffdio_zeropage(int ufd, } } -static bool do_uffdio_zeropage(int ufd, bool has_zeropage) +static bool do_uffdio_zeropage(uffd_global_test_opts_t *gopts, bool has_zeropage) { struct uffdio_zeropage uffdio_zeropage = { 0 }; int ret; __s64 res; - uffdio_zeropage.range.start = (unsigned long) area_dst; - uffdio_zeropage.range.len = page_size; + uffdio_zeropage.range.start = (unsigned long) gopts->area_dst; + uffdio_zeropage.range.len = gopts->page_size; uffdio_zeropage.mode = 0; - ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); + ret = ioctl(gopts->uffd, UFFDIO_ZEROPAGE, &uffdio_zeropage); res = uffdio_zeropage.zeropage; if (ret) { /* real retval in ufdio_zeropage.zeropage */ @@ -921,10 +902,10 @@ static bool do_uffdio_zeropage(int ufd, bool has_zeropage) else if (res != -EINVAL) err("UFFDIO_ZEROPAGE not -EINVAL"); } else if (has_zeropage) { - if (res != page_size) + if (res != gopts->page_size) err("UFFDIO_ZEROPAGE unexpected size"); else - retry_uffdio_zeropage(ufd, &uffdio_zeropage); + retry_uffdio_zeropage(gopts, &uffdio_zeropage); return true; } else err("UFFDIO_ZEROPAGE succeeded"); @@ -950,25 +931,29 @@ uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len) } /* exercise UFFDIO_ZEROPAGE */ -static void uffd_zeropage_test(uffd_test_args_t *args) +static void uffd_zeropage_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { bool has_zeropage; int i; - has_zeropage = uffd_register_detect_zeropage(uffd, area_dst, page_size); - if (area_dst_alias) + has_zeropage = uffd_register_detect_zeropage(gopts->uffd, + gopts->area_dst, + gopts->page_size); + if (gopts->area_dst_alias) /* Ignore the retval; we already have it */ - uffd_register_detect_zeropage(uffd, area_dst_alias, page_size); + uffd_register_detect_zeropage(gopts->uffd, gopts->area_dst_alias, gopts->page_size); - if (do_uffdio_zeropage(uffd, has_zeropage)) - for (i = 0; i < page_size; i++) - if (area_dst[i] != 0) + if (do_uffdio_zeropage(gopts, has_zeropage)) + for (i = 0; i < gopts->page_size; i++) + if (gopts->area_dst[i] != 0) err("data non-zero at offset %d\n", i); - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("unregister"); - if (area_dst_alias && uffd_unregister(uffd, area_dst_alias, page_size)) + if (gopts->area_dst_alias && uffd_unregister(gopts->uffd, + gopts->area_dst_alias, + gopts->page_size)) err("unregister"); uffd_test_pass(); @@ -987,26 +972,27 @@ static void uffd_register_poison(int uffd, void *addr, uint64_t len) err("registered area doesn't support COPY and POISON ioctls"); } -static void do_uffdio_poison(int uffd, unsigned long offset) +static void do_uffdio_poison(uffd_global_test_opts_t *gopts, unsigned long offset) { struct uffdio_poison uffdio_poison = { 0 }; int ret; __s64 res; - uffdio_poison.range.start = (unsigned long) area_dst + offset; - uffdio_poison.range.len = page_size; + uffdio_poison.range.start = (unsigned long) gopts->area_dst + offset; + uffdio_poison.range.len = gopts->page_size; uffdio_poison.mode = 0; - ret = ioctl(uffd, UFFDIO_POISON, &uffdio_poison); + ret = ioctl(gopts->uffd, UFFDIO_POISON, &uffdio_poison); res = uffdio_poison.updated; if (ret) err("UFFDIO_POISON error: %"PRId64, (int64_t)res); - else if (res != page_size) + else if (res != gopts->page_size) err("UFFDIO_POISON unexpected size: %"PRId64, (int64_t)res); } -static void uffd_poison_handle_fault( - struct uffd_msg *msg, struct uffd_args *args) +static void uffd_poison_handle_fault(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args) { unsigned long offset; @@ -1017,20 +1003,20 @@ static void uffd_poison_handle_fault( (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR)) err("unexpected fault type %llu", msg->arg.pagefault.flags); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(gopts->page_size-1); /* Odd pages -> copy zeroed page; even pages -> poison. */ - if (offset & page_size) - copy_page(uffd, offset, false); + if (offset & gopts->page_size) + copy_page(gopts, offset, false); else - do_uffdio_poison(uffd, offset); + do_uffdio_poison(gopts, offset); } /* Make sure to cover odd/even, and minimum duplications */ #define UFFD_POISON_TEST_NPAGES 4 -static void uffd_poison_test(uffd_test_args_t *targs) +static void uffd_poison_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { pthread_t uffd_mon; char c; @@ -1039,15 +1025,17 @@ static void uffd_poison_test(uffd_test_args_t *targs) unsigned long nr_sigbus = 0; unsigned long nr, poison_pages = UFFD_POISON_TEST_NPAGES; - if (nr_pages < poison_pages) { - uffd_test_skip("Too few pages for POISON test"); + if (gopts->nr_pages < poison_pages) { + uffd_test_skip("Too less pages for POISON test"); return; } - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + args.gopts = gopts; + + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); - uffd_register_poison(uffd, area_dst, poison_pages * page_size); - memset(area_src, 0, poison_pages * page_size); + uffd_register_poison(gopts->uffd, gopts->area_dst, poison_pages * gopts->page_size); + memset(gopts->area_src, 0, poison_pages * gopts->page_size); args.handle_fault = uffd_poison_handle_fault; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) @@ -1060,8 +1048,8 @@ static void uffd_poison_test(uffd_test_args_t *targs) err("sigaction"); for (nr = 0; nr < poison_pages; ++nr) { - unsigned long offset = nr * page_size; - const char *bytes = (const char *) area_dst + offset; + unsigned long offset = nr * gopts->page_size; + const char *bytes = (const char *) gopts->area_dst + offset; const char *i; if (sigsetjmp(*sigbuf, 1)) { @@ -1074,14 +1062,14 @@ static void uffd_poison_test(uffd_test_args_t *targs) continue; } - for (i = bytes; i < bytes + page_size; ++i) { + for (i = bytes; i < bytes + gopts->page_size; ++i) { if (*i) err("nonzero byte in area_dst (%p) at %p: %u", - area_dst, i, *i); + gopts->area_dst, i, *i); } } - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("pthread_join()"); @@ -1094,7 +1082,9 @@ static void uffd_poison_test(uffd_test_args_t *targs) } static void -uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args, +uffd_move_handle_fault_common(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args, unsigned long len) { unsigned long offset; @@ -1106,28 +1096,32 @@ uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args, (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE)) err("unexpected fault type %llu", msg->arg.pagefault.flags); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; offset &= ~(len-1); - if (move_page(uffd, offset, len)) + if (move_page(gopts, offset, len)) args->missing_faults++; } -static void uffd_move_handle_fault(struct uffd_msg *msg, +static void uffd_move_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, struct uffd_args *args) { - uffd_move_handle_fault_common(msg, args, page_size); + uffd_move_handle_fault_common(gopts, msg, args, gopts->page_size); } -static void uffd_move_pmd_handle_fault(struct uffd_msg *msg, +static void uffd_move_pmd_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, struct uffd_args *args) { - uffd_move_handle_fault_common(msg, args, read_pmd_pagesize()); + uffd_move_handle_fault_common(gopts, msg, args, read_pmd_pagesize()); } static void -uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, - void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args)) +uffd_move_test_common(uffd_global_test_opts_t *gopts, + uffd_test_args_t *targs, + unsigned long chunk_size, + void (*handle_fault)(struct uffd_global_test_opts *gopts, + struct uffd_msg *msg, struct uffd_args *args) +) { unsigned long nr; pthread_t uffd_mon; @@ -1139,11 +1133,13 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, unsigned long src_offs = 0; unsigned long dst_offs = 0; + args.gopts = gopts; + /* Prevent source pages from being mapped more than once */ - if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK)) + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_DONTFORK)) err("madvise(MADV_DONTFORK) failure"); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, false, false)) err("register failure"); @@ -1151,22 +1147,22 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - step_size = chunk_size / page_size; - step_count = nr_pages / step_size; + step_size = chunk_size / gopts->page_size; + step_count = gopts->nr_pages / step_size; - if (chunk_size > page_size) { - char *aligned_src = ALIGN_UP(area_src, chunk_size); - char *aligned_dst = ALIGN_UP(area_dst, chunk_size); + if (chunk_size > gopts->page_size) { + char *aligned_src = ALIGN_UP(gopts->area_src, chunk_size); + char *aligned_dst = ALIGN_UP(gopts->area_dst, chunk_size); - if (aligned_src != area_src || aligned_dst != area_dst) { - src_offs = (aligned_src - area_src) / page_size; - dst_offs = (aligned_dst - area_dst) / page_size; + if (aligned_src != gopts->area_src || aligned_dst != gopts->area_dst) { + src_offs = (aligned_src - gopts->area_src) / gopts->page_size; + dst_offs = (aligned_dst - gopts->area_dst) / gopts->page_size; step_count--; } - orig_area_src = area_src; - orig_area_dst = area_dst; - area_src = aligned_src; - area_dst = aligned_dst; + orig_area_src = gopts->area_src; + orig_area_dst = gopts->area_dst; + gopts->area_src = aligned_src; + gopts->area_dst = aligned_dst; } /* @@ -1180,34 +1176,34 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, /* Check area_src content */ for (i = 0; i < step_size; i++) { - count = *area_count(area_src, nr + i); - if (count != count_verify[src_offs + nr + i]) + count = *area_count(gopts->area_src, nr + i, gopts); + if (count != gopts->count_verify[src_offs + nr + i]) err("nr %lu source memory invalid %llu %llu\n", - nr + i, count, count_verify[src_offs + nr + i]); + nr + i, count, gopts->count_verify[src_offs + nr + i]); } /* Faulting into area_dst should move the page or the huge page */ for (i = 0; i < step_size; i++) { - count = *area_count(area_dst, nr + i); - if (count != count_verify[dst_offs + nr + i]) + count = *area_count(gopts->area_dst, nr + i, gopts); + if (count != gopts->count_verify[dst_offs + nr + i]) err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[dst_offs + nr + i]); + nr, count, gopts->count_verify[dst_offs + nr + i]); } /* Re-check area_src content which should be empty */ for (i = 0; i < step_size; i++) { - count = *area_count(area_src, nr + i); + count = *area_count(gopts->area_src, nr + i, gopts); if (count != 0) err("nr %lu move failed %llu %llu\n", - nr, count, count_verify[src_offs + nr + i]); + nr, count, gopts->count_verify[src_offs + nr + i]); } } - if (chunk_size > page_size) { - area_src = orig_area_src; - area_dst = orig_area_dst; + if (chunk_size > gopts->page_size) { + gopts->area_src = orig_area_src; + gopts->area_dst = orig_area_dst; } - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("join() failed"); @@ -1218,24 +1214,24 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, uffd_test_pass(); } -static void uffd_move_test(uffd_test_args_t *targs) +static void uffd_move_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { - uffd_move_test_common(targs, page_size, uffd_move_handle_fault); + uffd_move_test_common(gopts, targs, gopts->page_size, uffd_move_handle_fault); } -static void uffd_move_pmd_test(uffd_test_args_t *targs) +static void uffd_move_pmd_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { - if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE)) + if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) err("madvise(MADV_HUGEPAGE) failure"); - uffd_move_test_common(targs, read_pmd_pagesize(), + uffd_move_test_common(gopts, targs, read_pmd_pagesize(), uffd_move_pmd_handle_fault); } -static void uffd_move_pmd_split_test(uffd_test_args_t *targs) +static void uffd_move_pmd_split_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { - if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE)) + if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) err("madvise(MADV_NOHUGEPAGE) failure"); - uffd_move_test_common(targs, read_pmd_pagesize(), + uffd_move_test_common(gopts, targs, read_pmd_pagesize(), uffd_move_pmd_handle_fault); } @@ -1295,6 +1291,11 @@ typedef enum { THR_STATE_UNINTERRUPTIBLE, } thread_state; +typedef struct { + uffd_global_test_opts_t *gopts; + volatile pid_t *pid; +} mmap_changing_thread_args; + static void sleep_short(void) { usleep(1000); @@ -1337,7 +1338,9 @@ static void thread_state_until(pid_t tid, thread_state state) static void *uffd_mmap_changing_thread(void *opaque) { - volatile pid_t *pid = opaque; + mmap_changing_thread_args *args = opaque; + uffd_global_test_opts_t *gopts = args->gopts; + volatile pid_t *pid = args->pid; int ret; /* Unfortunately, it's only fetch-able from the thread itself.. */ @@ -1345,21 +1348,21 @@ static void *uffd_mmap_changing_thread(void *opaque) *pid = syscall(SYS_gettid); /* Inject an event, this will hang solid until the event read */ - ret = madvise(area_dst, page_size, MADV_REMOVE); + ret = madvise(gopts->area_dst, gopts->page_size, MADV_REMOVE); if (ret) err("madvise(MADV_REMOVE) failed"); return NULL; } -static void uffd_consume_message(int fd) +static void uffd_consume_message(uffd_global_test_opts_t *gopts) { struct uffd_msg msg = { 0 }; - while (uffd_read_msg(fd, &msg)); + while (uffd_read_msg(gopts, &msg)); } -static void uffd_mmap_changing_test(uffd_test_args_t *targs) +static void uffd_mmap_changing_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { /* * This stores the real PID (which can be different from how tid is @@ -1368,13 +1371,14 @@ static void uffd_mmap_changing_test(uffd_test_args_t *targs) pid_t pid = 0; pthread_t tid; int ret; + mmap_changing_thread_args args = { gopts, &pid }; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, false, false)) err("uffd_register() failed"); /* Create a thread to generate the racy event */ - ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &pid); + ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &args); if (ret) err("pthread_create() failed"); @@ -1388,26 +1392,26 @@ static void uffd_mmap_changing_test(uffd_test_args_t *targs) /* Wait until the thread hangs at REMOVE event */ thread_state_until(pid, THR_STATE_UNINTERRUPTIBLE); - if (!uffdio_mmap_changing_test_copy(uffd)) + if (!uffdio_mmap_changing_test_copy(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_zeropage(uffd)) + if (!uffdio_mmap_changing_test_zeropage(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_move(uffd)) + if (!uffdio_mmap_changing_test_move(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_poison(uffd)) + if (!uffdio_mmap_changing_test_poison(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_continue(uffd)) + if (!uffdio_mmap_changing_test_continue(gopts->uffd)) return; /* * All succeeded above! Recycle everything. Start by reading the * event so as to kick the thread roll again.. */ - uffd_consume_message(uffd); + uffd_consume_message(gopts); ret = pthread_join(tid, NULL); assert(ret == 0); @@ -1415,10 +1419,10 @@ static void uffd_mmap_changing_test(uffd_test_args_t *targs) uffd_test_pass(); } -static int prevent_hugepages(const char **errmsg) +static int prevent_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg) { /* This should be done before source area is populated */ - if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) { + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) { /* Ignore only if CONFIG_TRANSPARENT_HUGEPAGE=n */ if (errno != EINVAL) { if (errmsg) @@ -1429,10 +1433,10 @@ static int prevent_hugepages(const char **errmsg) return 0; } -static int request_hugepages(const char **errmsg) +static int request_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg) { /* This should be done before source area is populated */ - if (madvise(area_src, nr_pages * page_size, MADV_HUGEPAGE)) { + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) { if (errmsg) { *errmsg = (errno == EINVAL) ? "CONFIG_TRANSPARENT_HUGEPAGE is not set" : @@ -1456,13 +1460,17 @@ struct uffd_test_case_ops uffd_move_test_pmd_case_ops = { * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test. */ static void -do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) +do_register_ioctls_test(uffd_global_test_opts_t *gopts, + uffd_test_args_t *args, + bool miss, + bool wp, + bool minor) { uint64_t ioctls = 0, expected = BIT_ULL(_UFFDIO_WAKE); mem_type_t *mem_type = args->mem_type; int ret; - ret = uffd_register_with_ioctls(uffd, area_dst, page_size, + ret = uffd_register_with_ioctls(gopts->uffd, gopts->area_dst, gopts->page_size, miss, wp, minor, &ioctls); /* @@ -1493,18 +1501,18 @@ do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) "(miss=%d, wp=%d, minor=%d): expected=0x%"PRIx64", " "returned=0x%"PRIx64, miss, wp, minor, expected, ioctls); - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("unregister"); } -static void uffd_register_ioctls_test(uffd_test_args_t *args) +static void uffd_register_ioctls_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { int miss, wp, minor; for (miss = 0; miss <= 1; miss++) for (wp = 0; wp <= 1; wp++) for (minor = 0; minor <= 1; minor++) - do_register_ioctls_test(args, miss, wp, minor); + do_register_ioctls_test(gopts, args, miss, wp, minor); uffd_test_pass(); } @@ -1742,6 +1750,28 @@ int main(int argc, char *argv[]) } for (j = 0; j < n_mems; j++) { mem_type = &mem_types[j]; + + /* Initialize global test options */ + uffd_global_test_opts_t gopts = { 0 }; + + gopts.map_shared = mem_type->shared; + uffd_test_ops = mem_type->mem_ops; + uffd_test_case_ops = test->test_case_ops; + + if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) + gopts.page_size = default_huge_page_size(); + else + gopts.page_size = psize(); + + /* Ensure we have at least 2 pages */ + gopts.nr_pages = MAX(UFFD_TEST_MEM_SIZE, gopts.page_size * 2) + / gopts.page_size; + + gopts.nr_parallel = 1; + + /* Initialize test arguments */ + args.mem_type = mem_type; + if (!(test->mem_targets & mem_type->mem_flag)) continue; @@ -1756,13 +1786,12 @@ int main(int argc, char *argv[]) uffd_test_skip("feature missing"); continue; } - if (uffd_setup_environment(&args, test, mem_type, - &errmsg)) { + if (uffd_test_ctx_init(&gopts, test->uffd_feature_required, &errmsg)) { uffd_test_skip(errmsg); continue; } - test->uffd_fn(&args); - uffd_test_ctx_clear(); + test->uffd_fn(&gopts, &args); + uffd_test_ctx_clear(&gopts); } } diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c index 78038c40aaaf..4e4a591cf527 100644 --- a/tools/testing/selftests/mm/uffd-wp-mremap.c +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -152,7 +152,8 @@ static bool range_is_swapped(void *addr, size_t size) return true; } -static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb) +static void test_one_folio(uffd_global_test_opts_t *gopts, size_t size, bool private, + bool swapout, bool hugetlb) { struct uffdio_writeprotect wp_prms; uint64_t features = 0; @@ -176,21 +177,21 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb } /* Register range for uffd-wp. */ - if (userfaultfd_open(&features)) { + if (userfaultfd_open(gopts, &features)) { if (errno == ENOENT) ksft_test_result_skip("userfaultfd not available\n"); else ksft_test_result_fail("userfaultfd_open() failed\n"); goto out; } - if (uffd_register(uffd, mem, size, false, true, false)) { + if (uffd_register(gopts->uffd, mem, size, false, true, false)) { ksft_test_result_fail("uffd_register() failed\n"); goto out; } wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP; wp_prms.range.start = (uintptr_t)mem; wp_prms.range.len = size; - if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { + if (ioctl(gopts->uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n"); goto out; } @@ -237,9 +238,9 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb out: if (mem) munmap(mem, size); - if (uffd >= 0) { - close(uffd); - uffd = -1; + if (gopts->uffd >= 0) { + close(gopts->uffd); + gopts->uffd = -1; } } @@ -331,6 +332,7 @@ static const struct testcase testcases[] = { int main(int argc, char **argv) { + uffd_global_test_opts_t gopts = { 0 }; struct thp_settings settings; int i, j, plan = 0; @@ -362,8 +364,8 @@ int main(int argc, char **argv) const struct testcase *tc = &testcases[i]; for (j = 0; j < *tc->nr_sizes; j++) - test_one_folio(tc->sizes[j], tc->private, tc->swapout, - tc->hugetlb); + test_one_folio(&gopts, tc->sizes[j], tc->private, + tc->swapout, tc->hugetlb); } /* If THP is supported, restore original THP settings. */ -- 2.30.2

1 month, 2 weeks

1
0
0 0

[PATCH v7 1/1] selftests/mm/uffd: Refactor non-composite global vars into struct

by Ujwal Kundur

Refactor macros and non-composite global variable definitions into a struct that is defined at the start of a test and is passed around instead of relying on global vars. Signed-off-by: Ujwal Kundur <ujwal.kundur(a)gmail.com> Acked-by: Peter Xu <peterx(a)redhat.com> --- Previous versions and discussion at: https://lore.kernel.org/all/20250702152057.4067-1-ujwal.kundur@gmail.com/ Changes since v6: - rebased on 6.17-rc1 changes (cd79a1d9b08a) - removes unused args and adds the __unused attribute; since change is cosmetic-only, carry forward Acked-by tag - verified output remains unchanged using virtme-ng Changes since v5: - ensure uffd_global_test_opts_t instances are initialized - verified output remains unchanged using virtme-ng Changes since v4: - define gopts as global within uffd-stress.c to retain existing sigalrm handler logic Changes since v3: - more formatting fixes Changes since v2: - redo patch on mm-new branch Changes since v1: - indentation fixes - squash into single patch to assist bisections tools/testing/selftests/mm/uffd-common.c | 275 ++++----- tools/testing/selftests/mm/uffd-common.h | 78 +-- tools/testing/selftests/mm/uffd-stress.c | 228 ++++---- tools/testing/selftests/mm/uffd-unit-tests.c | 561 ++++++++++--------- tools/testing/selftests/mm/uffd-wp-mremap.c | 23 +- 5 files changed, 623 insertions(+), 542 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index e309ec886fa7..f4e9a5f43e24 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -7,18 +7,30 @@ #include "uffd-common.h" -#define BASE_PMD_ADDR ((void *)(1UL << 30)) - -volatile bool test_uffdio_copy_eexist = true; -unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; -char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -int uffd = -1, uffd_flags, finished, *pipefd, test_type; -bool map_shared; -bool test_uffdio_wp = true; -unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; uffd_test_case_ops_t *uffd_test_case_ops; -atomic_bool ready_for_fork; + +#define BASE_PMD_ADDR ((void *)(1UL << 30)) + +/* pthread_mutex_t starts at page offset 0 */ +pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts) +{ + return (pthread_mutex_t *) (area + nr * gopts->page_size); +} + +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +volatile unsigned long long *area_count( + char *area, unsigned long nr, + uffd_global_test_opts_t *gopts) +{ + return (volatile unsigned long long *) + ((unsigned long)(area + nr * gopts->page_size + + sizeof(pthread_mutex_t) + sizeof(unsigned long long) - 1) & + ~(unsigned long)(sizeof(unsigned long long) - 1)); +} static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) { @@ -40,15 +52,16 @@ static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) return mem_fd; } -static void anon_release_pages(char *rel_area) +static void anon_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); } -static int anon_allocate_area(void **alloc_area, bool __unused is_src) +static int anon_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, + bool __unused is_src) { - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + *alloc_area = mmap(NULL, gopts->nr_pages * gopts->page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (*alloc_area == MAP_FAILED) { *alloc_area = NULL; @@ -57,32 +70,32 @@ static int anon_allocate_area(void **alloc_area, bool __unused is_src) return 0; } -static void noop_alias_mapping(__u64 __unused *start, size_t __unused len, - unsigned long __unused offset) +static void noop_alias_mapping(uffd_global_test_opts_t *gopts, __u64 __unused *start, + size_t __unused len, unsigned long __unused offset) { } -static void hugetlb_release_pages(char *rel_area) +static void hugetlb_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (!map_shared) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + if (!gopts->map_shared) { + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); } else { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE)) err("madvise(MADV_REMOVE) failed"); } } -static int hugetlb_allocate_area(void **alloc_area, bool is_src) +static int hugetlb_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { - off_t size = nr_pages * page_size; + off_t size = gopts->nr_pages * gopts->page_size; off_t offset = is_src ? 0 : size; void *area_alias = NULL; char **alloc_area_alias; int mem_fd = uffd_mem_fd_create(size * 2, true); *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | + (gopts->map_shared ? MAP_SHARED : MAP_PRIVATE) | (is_src ? 0 : MAP_NORESERVE), mem_fd, offset); if (*alloc_area == MAP_FAILED) { @@ -90,7 +103,7 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) return -errno; } - if (map_shared) { + if (gopts->map_shared) { area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); if (area_alias == MAP_FAILED) @@ -98,9 +111,9 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) } if (is_src) { - alloc_area_alias = &area_src_alias; + alloc_area_alias = &gopts->area_src_alias; } else { - alloc_area_alias = &area_dst_alias; + alloc_area_alias = &gopts->area_dst_alias; } if (area_alias) *alloc_area_alias = area_alias; @@ -109,24 +122,25 @@ static int hugetlb_allocate_area(void **alloc_area, bool is_src) return 0; } -static void hugetlb_alias_mapping(__u64 *start, size_t __unused len, unsigned long offset) +static void hugetlb_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t __unused len, unsigned long offset) { - if (!map_shared) + if (!gopts->map_shared) return; - *start = (unsigned long) area_dst_alias + offset; + *start = (unsigned long) gopts->area_dst_alias + offset; } -static void shmem_release_pages(char *rel_area) +static void shmem_release_pages(uffd_global_test_opts_t *gopts, char *rel_area) { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + if (madvise(rel_area, gopts->nr_pages * gopts->page_size, MADV_REMOVE)) err("madvise(MADV_REMOVE) failed"); } -static int shmem_allocate_area(void **alloc_area, bool is_src) +static int shmem_allocate_area(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src) { void *area_alias = NULL; - size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize(); + size_t bytes = gopts->nr_pages * gopts->page_size, hpage_size = read_pmd_pagesize(); unsigned long offset = is_src ? 0 : bytes; char *p = NULL, *p_alias = NULL; int mem_fd = uffd_mem_fd_create(bytes * 2, false); @@ -160,22 +174,24 @@ static int shmem_allocate_area(void **alloc_area, bool is_src) err("mmap of anonymous memory failed at %p", p_alias); if (is_src) - area_src_alias = area_alias; + gopts->area_src_alias = area_alias; else - area_dst_alias = area_alias; + gopts->area_dst_alias = area_alias; close(mem_fd); return 0; } -static void shmem_alias_mapping(__u64 *start, size_t __unused len, unsigned long offset) +static void shmem_alias_mapping(uffd_global_test_opts_t *gopts, __u64 *start, + size_t __unused len, unsigned long offset) { - *start = (unsigned long)area_dst_alias + offset; + *start = (unsigned long)gopts->area_dst_alias + offset; } -static void shmem_check_pmd_mapping(void __unused *p, int expect_nr_hpages) +static void shmem_check_pmd_mapping(uffd_global_test_opts_t *gopts, void __unused *p, + int expect_nr_hpages) { - if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, + if (!check_huge_shmem(gopts->area_dst_alias, expect_nr_hpages, read_pmd_pagesize())) err("Did not find expected %d number of hugepages", expect_nr_hpages); @@ -235,18 +251,18 @@ void uffd_stats_report(struct uffd_args *args, int n_cpus) printf("\n"); } -int userfaultfd_open(uint64_t *features) +int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features) { struct uffdio_api uffdio_api; - uffd = uffd_open(UFFD_FLAGS); - if (uffd < 0) + gopts->uffd = uffd_open(UFFD_FLAGS); + if (gopts->uffd < 0) return -1; - uffd_flags = fcntl(uffd, F_GETFD, NULL); + gopts->uffd_flags = fcntl(gopts->uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; uffdio_api.features = *features; - if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + if (ioctl(gopts->uffd, UFFDIO_API, &uffdio_api)) /* Probably lack of CAP_PTRACE? */ return -1; if (uffdio_api.api != UFFD_API) @@ -256,59 +272,63 @@ int userfaultfd_open(uint64_t *features) return 0; } -static inline void munmap_area(void **area) +static inline void munmap_area(uffd_global_test_opts_t *gopts, void **area) { if (*area) - if (munmap(*area, nr_pages * page_size)) + if (munmap(*area, gopts->nr_pages * gopts->page_size)) err("munmap"); *area = NULL; } -void uffd_test_ctx_clear(void) +void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts) { size_t i; - if (pipefd) { - for (i = 0; i < nr_parallel * 2; ++i) { - if (close(pipefd[i])) + if (gopts->pipefd) { + for (i = 0; i < gopts->nr_parallel * 2; ++i) { + if (close(gopts->pipefd[i])) err("close pipefd"); } - free(pipefd); - pipefd = NULL; + free(gopts->pipefd); + gopts->pipefd = NULL; } - if (count_verify) { - free(count_verify); - count_verify = NULL; + if (gopts->count_verify) { + free(gopts->count_verify); + gopts->count_verify = NULL; } - if (uffd != -1) { - if (close(uffd)) + if (gopts->uffd != -1) { + if (close(gopts->uffd)) err("close uffd"); - uffd = -1; + gopts->uffd = -1; } - munmap_area((void **)&area_src); - munmap_area((void **)&area_src_alias); - munmap_area((void **)&area_dst); - munmap_area((void **)&area_dst_alias); - munmap_area((void **)&area_remap); + munmap_area(gopts, (void **)&gopts->area_src); + munmap_area(gopts, (void **)&gopts->area_src_alias); + munmap_area(gopts, (void **)&gopts->area_dst); + munmap_area(gopts, (void **)&gopts->area_dst_alias); + munmap_area(gopts, (void **)&gopts->area_remap); } -int uffd_test_ctx_init(uint64_t features, const char **errmsg) +int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg) { unsigned long nr, cpu; int ret; + gopts->area_src_alias = NULL; + gopts->area_dst_alias = NULL; + gopts->area_remap = NULL; + if (uffd_test_case_ops && uffd_test_case_ops->pre_alloc) { - ret = uffd_test_case_ops->pre_alloc(errmsg); + ret = uffd_test_case_ops->pre_alloc(gopts, errmsg); if (ret) return ret; } - ret = uffd_test_ops->allocate_area((void **)&area_src, true); - ret |= uffd_test_ops->allocate_area((void **)&area_dst, false); + ret = uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_src, true); + ret |= uffd_test_ops->allocate_area(gopts, (void **) &gopts->area_dst, false); if (ret) { if (errmsg) *errmsg = "memory allocation failed"; @@ -316,26 +336,26 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) } if (uffd_test_case_ops && uffd_test_case_ops->post_alloc) { - ret = uffd_test_case_ops->post_alloc(errmsg); + ret = uffd_test_case_ops->post_alloc(gopts, errmsg); if (ret) return ret; } - ret = userfaultfd_open(&features); + ret = userfaultfd_open(gopts, &features); if (ret) { if (errmsg) *errmsg = "possible lack of privilege"; return ret; } - count_verify = malloc(nr_pages * sizeof(unsigned long long)); - if (!count_verify) + gopts->count_verify = malloc(gopts->nr_pages * sizeof(unsigned long long)); + if (!gopts->count_verify) err("count_verify"); - for (nr = 0; nr < nr_pages; nr++) { - *area_mutex(area_src, nr) = + for (nr = 0; nr < gopts->nr_pages; nr++) { + *area_mutex(gopts->area_src, nr, gopts) = (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; - count_verify[nr] = *area_count(area_src, nr) = 1; + gopts->count_verify[nr] = *area_count(gopts->area_src, nr, gopts) = 1; /* * In the transition between 255 to 256, powerpc will * read out of order in my_bcmp and see both bytes as @@ -343,7 +363,7 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) * after the count, to avoid my_bcmp to trigger false * positives. */ - *(area_count(area_src, nr) + 1) = 1; + *(area_count(gopts->area_src, nr, gopts) + 1) = 1; } /* @@ -364,13 +384,13 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg) * proactively split the thp and drop any accidentally initialized * pages within area_dst. */ - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - pipefd = malloc(sizeof(int) * nr_parallel * 2); - if (!pipefd) + gopts->pipefd = malloc(sizeof(int) * gopts->nr_parallel * 2); + if (!gopts->pipefd) err("pipefd"); - for (cpu = 0; cpu < nr_parallel; cpu++) - if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) + if (pipe2(&gopts->pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) err("pipe"); return 0; @@ -417,9 +437,9 @@ static void continue_range(int ufd, __u64 start, __u64 len, bool wp) ret, (int64_t) req.mapped); } -int uffd_read_msg(struct uffd_msg *msg) +int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg) { - int ret = read(uffd, msg, sizeof(*msg)); + int ret = read(gopts->uffd, msg, sizeof(*msg)); if (ret != sizeof(*msg)) { if (ret < 0) { @@ -434,7 +454,8 @@ int uffd_read_msg(struct uffd_msg *msg) return 0; } -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) +void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, + struct uffd_args *args) { unsigned long offset; @@ -443,7 +464,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { /* Write protect page faults */ - wp_range(uffd, msg->arg.pagefault.address, page_size, false); + wp_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, false); args->wp_faults++; } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { uint8_t *area; @@ -461,12 +482,12 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) * (UFFD-registered). */ - area = (uint8_t *)(area_dst + - ((char *)msg->arg.pagefault.address - - area_dst_alias)); - for (b = 0; b < page_size; ++b) + area = (uint8_t *)(gopts->area_dst + + ((char *)msg->arg.pagefault.address - + gopts->area_dst_alias)); + for (b = 0; b < gopts->page_size; ++b) area[b] = ~area[b]; - continue_range(uffd, msg->arg.pagefault.address, page_size, + continue_range(gopts->uffd, msg->arg.pagefault.address, gopts->page_size, args->apply_wp); args->minor_faults++; } else { @@ -494,10 +515,10 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault"); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(gopts->page_size-1); - if (copy_page(uffd, offset, args->apply_wp)) + if (copy_page(gopts, offset, args->apply_wp)) args->missing_faults++; } } @@ -505,6 +526,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) void *uffd_poll_thread(void *arg) { struct uffd_args *args = (struct uffd_args *)arg; + uffd_global_test_opts_t *gopts = args->gopts; unsigned long cpu = args->cpu; struct pollfd pollfd[2]; struct uffd_msg msg; @@ -515,12 +537,12 @@ void *uffd_poll_thread(void *arg) if (!args->handle_fault) args->handle_fault = uffd_handle_page_fault; - pollfd[0].fd = uffd; + pollfd[0].fd = gopts->uffd; pollfd[0].events = POLLIN; - pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].fd = gopts->pipefd[cpu*2]; pollfd[1].events = POLLIN; - ready_for_fork = true; + gopts->ready_for_fork = true; for (;;) { ret = poll(pollfd, 2, -1); @@ -538,30 +560,30 @@ void *uffd_poll_thread(void *arg) } if (!(pollfd[0].revents & POLLIN)) err("pollfd[0].revents %d", pollfd[0].revents); - if (uffd_read_msg(&msg)) + if (uffd_read_msg(gopts, &msg)) continue; switch (msg.event) { default: err("unexpected msg event %u\n", msg.event); break; case UFFD_EVENT_PAGEFAULT: - args->handle_fault(&msg, args); + args->handle_fault(gopts, &msg, args); break; case UFFD_EVENT_FORK: - close(uffd); - uffd = msg.arg.fork.ufd; - pollfd[0].fd = uffd; + close(gopts->uffd); + gopts->uffd = msg.arg.fork.ufd; + pollfd[0].fd = gopts->uffd; break; case UFFD_EVENT_REMOVE: uffd_reg.range.start = msg.arg.remove.start; uffd_reg.range.len = msg.arg.remove.end - msg.arg.remove.start; - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + if (ioctl(gopts->uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) err("remove failure"); break; case UFFD_EVENT_REMAP: - area_remap = area_dst; /* save for later unmap */ - area_dst = (char *)(unsigned long)msg.arg.remap.to; + gopts->area_remap = gopts->area_dst; /* save for later unmap */ + gopts->area_dst = (char *)(unsigned long)msg.arg.remap.to; break; } } @@ -569,17 +591,18 @@ void *uffd_poll_thread(void *arg) return NULL; } -static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, +static void retry_copy_page(uffd_global_test_opts_t *gopts, struct uffdio_copy *uffdio_copy, unsigned long offset) { - uffd_test_ops->alias_mapping(&uffdio_copy->dst, + uffd_test_ops->alias_mapping(gopts, + &uffdio_copy->dst, uffdio_copy->len, offset); - if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { + if (ioctl(gopts->uffd, UFFDIO_COPY, uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy->copy != -EEXIST) err("UFFDIO_COPY retry error: %"PRId64, - (int64_t)uffdio_copy->copy); + (int64_t)uffdio_copy->copy); } else { err("UFFDIO_COPY retry unexpected: %"PRId64, (int64_t)uffdio_copy->copy); @@ -598,60 +621,60 @@ static void wake_range(int ufd, unsigned long addr, unsigned long len) addr), exit(1); } -int __copy_page(int ufd, unsigned long offset, bool retry, bool wp) +int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp) { struct uffdio_copy uffdio_copy; - if (offset >= nr_pages * page_size) + if (offset >= gopts->nr_pages * gopts->page_size) err("unexpected offset %lu\n", offset); - uffdio_copy.dst = (unsigned long) area_dst + offset; - uffdio_copy.src = (unsigned long) area_src + offset; - uffdio_copy.len = page_size; + uffdio_copy.dst = (unsigned long) gopts->area_dst + offset; + uffdio_copy.src = (unsigned long) gopts->area_src + offset; + uffdio_copy.len = gopts->page_size; if (wp) uffdio_copy.mode = UFFDIO_COPY_MODE_WP; else uffdio_copy.mode = 0; uffdio_copy.copy = 0; - if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { + if (ioctl(gopts->uffd, UFFDIO_COPY, &uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy.copy != -EEXIST) err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); - wake_range(ufd, uffdio_copy.dst, page_size); - } else if (uffdio_copy.copy != page_size) { + wake_range(gopts->uffd, uffdio_copy.dst, gopts->page_size); + } else if (uffdio_copy.copy != gopts->page_size) { err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); } else { - if (test_uffdio_copy_eexist && retry) { - test_uffdio_copy_eexist = false; - retry_copy_page(ufd, &uffdio_copy, offset); + if (gopts->test_uffdio_copy_eexist && retry) { + gopts->test_uffdio_copy_eexist = false; + retry_copy_page(gopts, &uffdio_copy, offset); } return 1; } return 0; } -int copy_page(int ufd, unsigned long offset, bool wp) +int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp) { - return __copy_page(ufd, offset, false, wp); + return __copy_page(gopts, offset, false, wp); } -int move_page(int ufd, unsigned long offset, unsigned long len) +int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len) { struct uffdio_move uffdio_move; - if (offset + len > nr_pages * page_size) + if (offset + len > gopts->nr_pages * gopts->page_size) err("unexpected offset %lu and length %lu\n", offset, len); - uffdio_move.dst = (unsigned long) area_dst + offset; - uffdio_move.src = (unsigned long) area_src + offset; + uffdio_move.dst = (unsigned long) gopts->area_dst + offset; + uffdio_move.src = (unsigned long) gopts->area_src + offset; uffdio_move.len = len; uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES; uffdio_move.move = 0; - if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) { + if (ioctl(gopts->uffd, UFFDIO_MOVE, &uffdio_move)) { /* real retval in uffdio_move.move */ if (uffdio_move.move != -EEXIST) err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move); - wake_range(ufd, uffdio_move.dst, len); + wake_range(gopts->uffd, uffdio_move.dst, len); } else if (uffdio_move.move != len) { err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move); } else diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 2e7066d69103..37d3ca55905f 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -56,20 +56,17 @@ #define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) -/* pthread_mutex_t starts at page offset 0 */ -#define area_mutex(___area, ___nr) \ - ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) -/* - * count is placed in the page after pthread_mutex_t naturally aligned - * to avoid non alignment faults on non-x86 archs. - */ -#define area_count(___area, ___nr) \ - ((volatile unsigned long long *) ((unsigned long) \ - ((___area) + (___nr)*page_size + \ - sizeof(pthread_mutex_t) + \ - sizeof(unsigned long long) - 1) & \ - ~(unsigned long)(sizeof(unsigned long long) \ - - 1))) +struct uffd_global_test_opts { + unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; + char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; + int uffd, uffd_flags, finished, *pipefd, test_type; + bool map_shared; + bool test_uffdio_wp; + unsigned long long *count_verify; + volatile bool test_uffdio_copy_eexist; + atomic_bool ready_for_fork; +}; +typedef struct uffd_global_test_opts uffd_global_test_opts_t; /* Userfaultfd test statistics */ struct uffd_args { @@ -79,50 +76,55 @@ struct uffd_args { unsigned long missing_faults; unsigned long wp_faults; unsigned long minor_faults; + struct uffd_global_test_opts *gopts; /* A custom fault handler; defaults to uffd_handle_page_fault. */ - void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args); + void (*handle_fault)(struct uffd_global_test_opts *gopts, + struct uffd_msg *msg, + struct uffd_args *args); }; struct uffd_test_ops { - int (*allocate_area)(void **alloc_area, bool is_src); - void (*release_pages)(char *rel_area); - void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); - void (*check_pmd_mapping)(void *p, int expect_nr_hpages); + int (*allocate_area)(uffd_global_test_opts_t *gopts, void **alloc_area, bool is_src); + void (*release_pages)(uffd_global_test_opts_t *gopts, char *rel_area); + void (*alias_mapping)(uffd_global_test_opts_t *gopts, + __u64 *start, + size_t len, + unsigned long offset); + void (*check_pmd_mapping)(uffd_global_test_opts_t *gopts, void *p, int expect_nr_hpages); }; typedef struct uffd_test_ops uffd_test_ops_t; struct uffd_test_case_ops { - int (*pre_alloc)(const char **errmsg); - int (*post_alloc)(const char **errmsg); + int (*pre_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg); + int (*post_alloc)(uffd_global_test_opts_t *gopts, const char **errmsg); }; typedef struct uffd_test_case_ops uffd_test_case_ops_t; -extern unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size; -extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -extern int uffd, uffd_flags, finished, *pipefd, test_type; -extern bool map_shared; -extern bool test_uffdio_wp; -extern unsigned long long *count_verify; -extern volatile bool test_uffdio_copy_eexist; -extern atomic_bool ready_for_fork; - +extern uffd_global_test_opts_t *uffd_gtest_opts; extern uffd_test_ops_t anon_uffd_test_ops; extern uffd_test_ops_t shmem_uffd_test_ops; extern uffd_test_ops_t hugetlb_uffd_test_ops; extern uffd_test_ops_t *uffd_test_ops; extern uffd_test_case_ops_t *uffd_test_case_ops; +pthread_mutex_t *area_mutex(char *area, unsigned long nr, uffd_global_test_opts_t *gopts); +volatile unsigned long long *area_count(char *area, + unsigned long nr, + uffd_global_test_opts_t *gopts); + void uffd_stats_report(struct uffd_args *args, int n_cpus); -int uffd_test_ctx_init(uint64_t features, const char **errmsg); -void uffd_test_ctx_clear(void); -int userfaultfd_open(uint64_t *features); -int uffd_read_msg(struct uffd_msg *msg); +int uffd_test_ctx_init(uffd_global_test_opts_t *gopts, uint64_t features, const char **errmsg); +void uffd_test_ctx_clear(uffd_global_test_opts_t *gopts); +int userfaultfd_open(uffd_global_test_opts_t *gopts, uint64_t *features); +int uffd_read_msg(uffd_global_test_opts_t *gopts, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); -int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); -int copy_page(int ufd, unsigned long offset, bool wp); -int move_page(int ufd, unsigned long offset, unsigned long len); +void uffd_handle_page_fault(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args); +int __copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool retry, bool wp); +int copy_page(uffd_global_test_opts_t *gopts, unsigned long offset, bool wp); +int move_page(uffd_global_test_opts_t *gopts, unsigned long offset, unsigned long len); void *uffd_poll_thread(void *arg); int uffd_open_dev(unsigned int flags); diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 24aac0ae96c6..9b216e842bbb 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -44,6 +44,12 @@ uint64_t features; #define BOUNCE_VERIFY (1<<2) #define BOUNCE_POLL (1<<3) static int bounces; +/* defined globally for this particular test as the sigalrm handler + * depends on test_uffdio_*_eexist. + * XXX: define gopts in main() when we figure out a way to deal with + * test_uffdio_*_eexist. + */ +static uffd_global_test_opts_t *gopts; /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ #define ALARM_INTERVAL_SECS 10 @@ -76,54 +82,58 @@ static void usage(void) exit(1); } -static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) +static void uffd_stats_reset(uffd_global_test_opts_t *gopts, struct uffd_args *args, + unsigned long n_cpus) { int i; for (i = 0; i < n_cpus; i++) { args[i].cpu = i; - args[i].apply_wp = test_uffdio_wp; + args[i].apply_wp = gopts->test_uffdio_wp; args[i].missing_faults = 0; args[i].wp_faults = 0; args[i].minor_faults = 0; + args[i].gopts = gopts; } } static void *locking_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_args *args = (struct uffd_args *) arg; + uffd_global_test_opts_t *gopts = args->gopts; + unsigned long cpu = (unsigned long) args->cpu; unsigned long page_nr; unsigned long long count; if (!(bounces & BOUNCE_RANDOM)) { page_nr = -bounces; if (!(bounces & BOUNCE_RACINGFAULTS)) - page_nr += cpu * nr_pages_per_cpu; + page_nr += cpu * gopts->nr_pages_per_cpu; } - while (!finished) { + while (!gopts->finished) { if (bounces & BOUNCE_RANDOM) { if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr)) err("getrandom failed"); } else page_nr += 1; - page_nr %= nr_pages; - pthread_mutex_lock(area_mutex(area_dst, page_nr)); - count = *area_count(area_dst, page_nr); - if (count != count_verify[page_nr]) + page_nr %= gopts->nr_pages; + pthread_mutex_lock(area_mutex(gopts->area_dst, page_nr, gopts)); + count = *area_count(gopts->area_dst, page_nr, gopts); + if (count != gopts->count_verify[page_nr]) err("page_nr %lu memory corruption %llu %llu", - page_nr, count, count_verify[page_nr]); + page_nr, count, gopts->count_verify[page_nr]); count++; - *area_count(area_dst, page_nr) = count_verify[page_nr] = count; - pthread_mutex_unlock(area_mutex(area_dst, page_nr)); + *area_count(gopts->area_dst, page_nr, gopts) = gopts->count_verify[page_nr] = count; + pthread_mutex_unlock(area_mutex(gopts->area_dst, page_nr, gopts)); } return NULL; } -static int copy_page_retry(int ufd, unsigned long offset) +static int copy_page_retry(uffd_global_test_opts_t *gopts, unsigned long offset) { - return __copy_page(ufd, offset, true, test_uffdio_wp); + return __copy_page(gopts, offset, true, gopts->test_uffdio_wp); } pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -131,15 +141,16 @@ pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; static void *uffd_read_thread(void *arg) { struct uffd_args *args = (struct uffd_args *)arg; + uffd_global_test_opts_t *gopts = args->gopts; struct uffd_msg msg; pthread_mutex_unlock(&uffd_read_mutex); /* from here cancellation is ok */ for (;;) { - if (uffd_read_msg(&msg)) + if (uffd_read_msg(gopts, &msg)) continue; - uffd_handle_page_fault(&msg, args); + uffd_handle_page_fault(gopts, &msg, args); } return NULL; @@ -147,32 +158,34 @@ static void *uffd_read_thread(void *arg) static void *background_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_args *args = (struct uffd_args *) arg; + uffd_global_test_opts_t *gopts = args->gopts; + unsigned long cpu = (unsigned long) args->cpu; unsigned long page_nr, start_nr, mid_nr, end_nr; - start_nr = cpu * nr_pages_per_cpu; - end_nr = (cpu+1) * nr_pages_per_cpu; + start_nr = cpu * gopts->nr_pages_per_cpu; + end_nr = (cpu+1) * gopts->nr_pages_per_cpu; mid_nr = (start_nr + end_nr) / 2; /* Copy the first half of the pages */ for (page_nr = start_nr; page_nr < mid_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); + copy_page_retry(gopts, page_nr * gopts->page_size); /* * If we need to test uffd-wp, set it up now. Then we'll have * at least the first half of the pages mapped already which * can be write-protected for testing */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst + start_nr * page_size, - nr_pages_per_cpu * page_size, true); + if (gopts->test_uffdio_wp) + wp_range(gopts->uffd, (unsigned long)gopts->area_dst + start_nr * gopts->page_size, + gopts->nr_pages_per_cpu * gopts->page_size, true); /* * Continue the 2nd half of the page copying, handling write * protection faults if any */ for (page_nr = mid_nr; page_nr < end_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); + copy_page_retry(gopts, page_nr * gopts->page_size); return NULL; } @@ -180,17 +193,21 @@ static void *background_thread(void *arg) static int stress(struct uffd_args *args) { unsigned long cpu; - pthread_t locking_threads[nr_parallel]; - pthread_t uffd_threads[nr_parallel]; - pthread_t background_threads[nr_parallel]; + uffd_global_test_opts_t *gopts = args->gopts; + pthread_t locking_threads[gopts->nr_parallel]; + pthread_t uffd_threads[gopts->nr_parallel]; + pthread_t background_threads[gopts->nr_parallel]; - finished = 0; - for (cpu = 0; cpu < nr_parallel; cpu++) { + gopts->finished = 0; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) { if (pthread_create(&locking_threads[cpu], &attr, - locking_thread, (void *)cpu)) + locking_thread, (void *)&args[cpu])) return 1; if (bounces & BOUNCE_POLL) { - if (pthread_create(&uffd_threads[cpu], &attr, uffd_poll_thread, &args[cpu])) + if (pthread_create(&uffd_threads[cpu], + &attr, + uffd_poll_thread, + (void *) &args[cpu])) err("uffd_poll_thread create"); } else { if (pthread_create(&uffd_threads[cpu], &attr, @@ -200,10 +217,10 @@ static int stress(struct uffd_args *args) pthread_mutex_lock(&uffd_read_mutex); } if (pthread_create(&background_threads[cpu], &attr, - background_thread, (void *)cpu)) + background_thread, (void *)&args[cpu])) return 1; } - for (cpu = 0; cpu < nr_parallel; cpu++) + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) if (pthread_join(background_threads[cpu], NULL)) return 1; @@ -216,17 +233,17 @@ static int stress(struct uffd_args *args) * UFFDIO_COPY without writing zero pages into area_dst * because the background threads already completed). */ - uffd_test_ops->release_pages(area_src); + uffd_test_ops->release_pages(gopts, gopts->area_src); - finished = 1; - for (cpu = 0; cpu < nr_parallel; cpu++) + gopts->finished = 1; + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) if (pthread_join(locking_threads[cpu], NULL)) return 1; - for (cpu = 0; cpu < nr_parallel; cpu++) { + for (cpu = 0; cpu < gopts->nr_parallel; cpu++) { char c; if (bounces & BOUNCE_POLL) { - if (write(pipefd[cpu*2+1], &c, 1) != 1) + if (write(gopts->pipefd[cpu*2+1], &c, 1) != 1) err("pipefd write error"); if (pthread_join(uffd_threads[cpu], (void *)&args[cpu])) @@ -242,26 +259,26 @@ static int stress(struct uffd_args *args) return 0; } -static int userfaultfd_stress(void) +static int userfaultfd_stress(uffd_global_test_opts_t *gopts) { void *area; unsigned long nr; - struct uffd_args args[nr_parallel]; - uint64_t mem_size = nr_pages * page_size; + struct uffd_args args[gopts->nr_parallel]; + uint64_t mem_size = gopts->nr_pages * gopts->page_size; int flags = 0; - memset(args, 0, sizeof(struct uffd_args) * nr_parallel); + memset(args, 0, sizeof(struct uffd_args) * gopts->nr_parallel); - if (features & UFFD_FEATURE_WP_UNPOPULATED && test_type == TEST_ANON) + if (features & UFFD_FEATURE_WP_UNPOPULATED && gopts->test_type == TEST_ANON) flags = UFFD_FEATURE_WP_UNPOPULATED; - if (uffd_test_ctx_init(flags, NULL)) + if (uffd_test_ctx_init(gopts, flags, NULL)) err("context init failed"); - if (posix_memalign(&area, page_size, page_size)) + if (posix_memalign(&area, gopts->page_size, gopts->page_size)) err("out of memory"); zeropage = area; - bzero(zeropage, page_size); + bzero(zeropage, gopts->page_size); pthread_mutex_lock(&uffd_read_mutex); @@ -284,18 +301,18 @@ static int userfaultfd_stress(void) fflush(stdout); if (bounces & BOUNCE_POLL) - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); else - fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags & ~O_NONBLOCK); /* register */ - if (uffd_register(uffd, area_dst, mem_size, - true, test_uffdio_wp, false)) + if (uffd_register(gopts->uffd, gopts->area_dst, mem_size, + true, gopts->test_uffdio_wp, false)) err("register failure"); - if (area_dst_alias) { - if (uffd_register(uffd, area_dst_alias, mem_size, - true, test_uffdio_wp, false)) + if (gopts->area_dst_alias) { + if (uffd_register(gopts->uffd, gopts->area_dst_alias, mem_size, + true, gopts->test_uffdio_wp, false)) err("register failure alias"); } @@ -323,87 +340,88 @@ static int userfaultfd_stress(void) * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's * required to MADV_DONTNEED here. */ - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - uffd_stats_reset(args, nr_parallel); + uffd_stats_reset(gopts, args, gopts->nr_parallel); /* bounce pass */ if (stress(args)) { - uffd_test_ctx_clear(); + uffd_test_ctx_clear(gopts); return 1; } /* Clear all the write protections if there is any */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst, - nr_pages * page_size, false); + if (gopts->test_uffdio_wp) + wp_range(gopts->uffd, (unsigned long)gopts->area_dst, + gopts->nr_pages * gopts->page_size, false); /* unregister */ - if (uffd_unregister(uffd, area_dst, mem_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, mem_size)) err("unregister failure"); - if (area_dst_alias) { - if (uffd_unregister(uffd, area_dst_alias, mem_size)) + if (gopts->area_dst_alias) { + if (uffd_unregister(gopts->uffd, gopts->area_dst_alias, mem_size)) err("unregister failure alias"); } /* verification */ if (bounces & BOUNCE_VERIFY) - for (nr = 0; nr < nr_pages; nr++) - if (*area_count(area_dst, nr) != count_verify[nr]) + for (nr = 0; nr < gopts->nr_pages; nr++) + if (*area_count(gopts->area_dst, nr, gopts) != + gopts->count_verify[nr]) err("error area_count %llu %llu %lu\n", - *area_count(area_src, nr), - count_verify[nr], nr); + *area_count(gopts->area_src, nr, gopts), + gopts->count_verify[nr], nr); /* prepare next bounce */ - swap(area_src, area_dst); + swap(gopts->area_src, gopts->area_dst); - swap(area_src_alias, area_dst_alias); + swap(gopts->area_src_alias, gopts->area_dst_alias); - uffd_stats_report(args, nr_parallel); + uffd_stats_report(args, gopts->nr_parallel); } - uffd_test_ctx_clear(); + uffd_test_ctx_clear(gopts); return 0; } -static void set_test_type(const char *type) +static void set_test_type(uffd_global_test_opts_t *gopts, const char *type) { if (!strcmp(type, "anon")) { - test_type = TEST_ANON; + gopts->test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; } else if (!strcmp(type, "hugetlb")) { - test_type = TEST_HUGETLB; + gopts->test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; - map_shared = true; + gopts->map_shared = true; } else if (!strcmp(type, "hugetlb-private")) { - test_type = TEST_HUGETLB; + gopts->test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; } else if (!strcmp(type, "shmem")) { - map_shared = true; - test_type = TEST_SHMEM; + gopts->map_shared = true; + gopts->test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } else if (!strcmp(type, "shmem-private")) { - test_type = TEST_SHMEM; + gopts->test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } } -static void parse_test_type_arg(const char *raw_type) +static void parse_test_type_arg(uffd_global_test_opts_t *gopts, const char *raw_type) { - set_test_type(raw_type); + set_test_type(gopts, raw_type); - if (!test_type) + if (!gopts->test_type) err("failed to parse test type argument: '%s'", raw_type); - if (test_type == TEST_HUGETLB) - page_size = default_huge_page_size(); + if (gopts->test_type == TEST_HUGETLB) + gopts->page_size = default_huge_page_size(); else - page_size = sysconf(_SC_PAGE_SIZE); + gopts->page_size = sysconf(_SC_PAGE_SIZE); - if (!page_size) + if (!gopts->page_size) err("Unable to determine page size"); - if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 - > page_size) + if ((unsigned long) area_count(NULL, 0, gopts) + sizeof(unsigned long long) * 2 + > gopts->page_size) err("Impossible to run this test"); /* @@ -415,21 +433,21 @@ static void parse_test_type_arg(const char *raw_type) if (uffd_get_features(&features) && errno == ENOENT) ksft_exit_skip("failed to get available features (%d)\n", errno); - test_uffdio_wp = test_uffdio_wp && + gopts->test_uffdio_wp = gopts->test_uffdio_wp && (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); - if (test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) - test_uffdio_wp = false; + if (gopts->test_type != TEST_ANON && !(features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) + gopts->test_uffdio_wp = false; - close(uffd); - uffd = -1; + close(gopts->uffd); + gopts->uffd = -1; } static void sigalrm(int sig) { if (sig != SIGALRM) abort(); - test_uffdio_copy_eexist = true; + gopts->test_uffdio_copy_eexist = true; alarm(ALARM_INTERVAL_SECS); } @@ -438,6 +456,8 @@ int main(int argc, char **argv) unsigned long nr_cpus; size_t bytes; + gopts = (uffd_global_test_opts_t *) malloc(sizeof(uffd_global_test_opts_t)); + if (argc < 4) usage(); @@ -445,11 +465,11 @@ int main(int argc, char **argv) err("failed to arm SIGALRM"); alarm(ALARM_INTERVAL_SECS); - parse_test_type_arg(argv[1]); + parse_test_type_arg(gopts, argv[1]); bytes = atol(argv[2]) * 1024 * 1024; - if (test_type == TEST_HUGETLB && - get_free_hugepages() < bytes / page_size) { + if (gopts->test_type == TEST_HUGETLB && + get_free_hugepages() < bytes / gopts->page_size) { printf("skip: Skipping userfaultfd... not enough hugepages\n"); return KSFT_SKIP; } @@ -459,15 +479,15 @@ int main(int argc, char **argv) /* Don't let calculation below go to zero. */ ksft_print_msg("_SC_NPROCESSORS_ONLN (%lu) too large, capping nr_threads to 32\n", nr_cpus); - nr_parallel = 32; + gopts->nr_parallel = 32; } else { - nr_parallel = nr_cpus; + gopts->nr_parallel = nr_cpus; } - nr_pages_per_cpu = bytes / page_size / nr_parallel; - if (!nr_pages_per_cpu) { + gopts->nr_pages_per_cpu = bytes / gopts->page_size / gopts->nr_parallel; + if (!gopts->nr_pages_per_cpu) { _err("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)", - bytes, page_size, nr_parallel); + bytes, gopts->page_size, gopts->nr_parallel); usage(); } @@ -476,11 +496,11 @@ int main(int argc, char **argv) _err("invalid bounces"); usage(); } - nr_pages = nr_pages_per_cpu * nr_parallel; + gopts->nr_pages = gopts->nr_pages_per_cpu * gopts->nr_parallel; printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", - nr_pages, nr_pages_per_cpu); - return userfaultfd_stress(); + gopts->nr_pages, gopts->nr_pages_per_cpu); + return userfaultfd_stress(gopts); } #else /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index ee9b407e893e..101eaca2662e 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -76,7 +76,7 @@ struct uffd_test_args { typedef struct uffd_test_args uffd_test_args_t; /* Returns: UFFD_TEST_* */ -typedef void (*uffd_test_fn)(uffd_test_args_t *); +typedef void (*uffd_test_fn)(uffd_global_test_opts_t *, uffd_test_args_t *); typedef struct { const char *name; @@ -181,33 +181,6 @@ static int test_uffd_api(bool use_dev) return 1; } -/* - * This function initializes the global variables. TODO: remove global - * vars and then remove this. - */ -static int -uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test, - mem_type_t *mem_type, const char **errmsg) -{ - map_shared = mem_type->shared; - uffd_test_ops = mem_type->mem_ops; - uffd_test_case_ops = test->test_case_ops; - - if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) - page_size = default_huge_page_size(); - else - page_size = psize(); - - /* Ensure we have at least 2 pages */ - nr_pages = MAX(UFFD_TEST_MEM_SIZE, page_size * 2) / page_size; - /* TODO: remove this global var.. it's so ugly */ - nr_parallel = 1; - - /* Initialize test arguments */ - args->mem_type = mem_type; - - return uffd_test_ctx_init(test->uffd_feature_required, errmsg); -} static bool uffd_feature_supported(uffd_test_case_t *test) { @@ -237,7 +210,8 @@ static int pagemap_open(void) } while (0) typedef struct { - int parent_uffd, child_uffd; + uffd_global_test_opts_t *gopts; + int child_uffd; } fork_event_args; static void *fork_event_consumer(void *data) @@ -245,10 +219,10 @@ static void *fork_event_consumer(void *data) fork_event_args *args = data; struct uffd_msg msg = { 0 }; - ready_for_fork = true; + args->gopts->ready_for_fork = true; /* Read until a full msg received */ - while (uffd_read_msg(&msg)); + while (uffd_read_msg(args->gopts, &msg)); if (msg.event != UFFD_EVENT_FORK) err("wrong message: %u\n", msg.event); @@ -304,9 +278,9 @@ static void unpin_pages(pin_args *args) args->pinned = false; } -static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) +static int pagemap_test_fork(uffd_global_test_opts_t *gopts, bool with_event, bool test_pin) { - fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 }; + fork_event_args args = { .gopts = gopts, .child_uffd = -1 }; pthread_t thread; pid_t child; uint64_t value; @@ -314,10 +288,10 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) /* Prepare a thread to resolve EVENT_FORK */ if (with_event) { - ready_for_fork = false; + gopts->ready_for_fork = false; if (pthread_create(&thread, NULL, fork_event_consumer, &args)) err("pthread_create()"); - while (!ready_for_fork) + while (!gopts->ready_for_fork) ; /* Wait for the poll_thread to start executing before forking */ } @@ -328,14 +302,14 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) fd = pagemap_open(); - if (test_pin && pin_pages(&args, area_dst, page_size)) + if (test_pin && pin_pages(&args, gopts->area_dst, gopts->page_size)) /* * Normally when reach here we have pinned in * previous tests, so shouldn't fail anymore */ err("pin page failed in child"); - value = pagemap_get_entry(fd, area_dst); + value = pagemap_get_entry(fd, gopts->area_dst); /* * After fork(), we should handle uffd-wp bit differently: * @@ -361,70 +335,71 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) return result; } -static void uffd_wp_unpopulated_test(uffd_test_args_t __unused *args) +static void uffd_wp_unpopulated_test(uffd_global_test_opts_t *gopts, + uffd_test_args_t __unused *args) { uint64_t value; int pagemap_fd; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Test applying pte marker to anon unpopulated */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); /* Test unprotect on anon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Test zap on anon marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - if (madvise(area_dst, page_size, MADV_DONTNEED)) + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); - value = pagemap_get_entry(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Test fault in after marker removed */ - *area_dst = 1; - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 1; + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); /* Test read-zero-page upon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - *(volatile char *)area_dst; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + *(volatile char *)gopts->area_dst; /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); uffd_test_pass(); } -static void uffd_wp_fork_test_common(uffd_test_args_t *args, +static void uffd_wp_fork_test_common(uffd_global_test_opts_t *gopts, uffd_test_args_t *args, bool with_event) { int pagemap_fd; uint64_t value; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 1; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in present pte", with_event ? "missing" : "stall"); goto out; @@ -442,79 +417,80 @@ static void uffd_wp_fork_test_common(uffd_test_args_t *args, * to expose pte markers. */ if (args->mem_type->shared) { - if (madvise(area_dst, page_size, MADV_DONTNEED)) + if (madvise(gopts->area_dst, gopts->page_size, MADV_DONTNEED)) err("MADV_DONTNEED"); } else { /* * NOTE: ignore retval because private-hugetlb doesn't yet * support swapping, so it could fail. */ - madvise(area_dst, page_size, MADV_PAGEOUT); + madvise(gopts->area_dst, gopts->page_size, MADV_PAGEOUT); } /* Uffd-wp should persist even swapped out */ - value = pagemap_get_entry(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte", with_event ? "missing" : "stall"); goto out; } /* Unprotect; this tests swap pte modifications */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, false); + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); /* Fault in the page from disk */ - *area_dst = 2; - value = pagemap_get_entry(pagemap_fd, area_dst); + *gopts->area_dst = 2; + value = pagemap_get_entry(pagemap_fd, gopts->area_dst); pagemap_check_wp(value, false); uffd_test_pass(); out: - if (uffd_unregister(uffd, area_dst, nr_pages * page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size)) err("unregister failed"); close(pagemap_fd); } -static void uffd_wp_fork_test(uffd_test_args_t *args) +static void uffd_wp_fork_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_test_common(args, false); + uffd_wp_fork_test_common(gopts, args, false); } -static void uffd_wp_fork_with_event_test(uffd_test_args_t *args) +static void uffd_wp_fork_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_test_common(args, true); + uffd_wp_fork_test_common(gopts, args, true); } -static void uffd_wp_fork_pin_test_common(uffd_test_args_t __unused *args, +static void uffd_wp_fork_pin_test_common(uffd_global_test_opts_t *gopts, + uffd_test_args_t __unused *args, bool with_event) { int pagemap_fd; pin_args pin_args = {}; - if (uffd_register(uffd, area_dst, page_size, false, true, false)) + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->page_size, false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, page_size, true); + *gopts->area_dst = 1; + wp_range(gopts->uffd, (uint64_t)gopts->area_dst, gopts->page_size, true); /* * 1. First pin, then fork(). This tests fork() special path when * doing early CoW if the page is private. */ - if (pin_pages(&pin_args, area_dst, page_size)) { + if (pin_pages(&pin_args, gopts->area_dst, gopts->page_size)) { uffd_test_skip("Possibly CONFIG_GUP_TEST missing " "or unprivileged"); close(pagemap_fd); - uffd_unregister(uffd, area_dst, page_size); + uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size); return; } - if (pagemap_test_fork(uffd, with_event, false)) { + if (pagemap_test_fork(gopts, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in early CoW of fork()", with_event ? "missing" : "stall"); unpin_pages(&pin_args); @@ -527,49 +503,50 @@ static void uffd_wp_fork_pin_test_common(uffd_test_args_t __unused *args, * 2. First fork(), then pin (in the child, where test_pin==true). * This tests COR, aka, page unsharing on private memories. */ - if (pagemap_test_fork(uffd, with_event, true)) { + if (pagemap_test_fork(gopts, with_event, true)) { uffd_test_fail("Detected %s uffd-wp bit when RO pin", with_event ? "missing" : "stall"); goto out; } uffd_test_pass(); out: - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("register failed"); close(pagemap_fd); } -static void uffd_wp_fork_pin_test(uffd_test_args_t *args) +static void uffd_wp_fork_pin_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_pin_test_common(args, false); + uffd_wp_fork_pin_test_common(gopts, args, false); } -static void uffd_wp_fork_pin_with_event_test(uffd_test_args_t *args) +static void uffd_wp_fork_pin_with_event_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { - uffd_wp_fork_pin_test_common(args, true); + uffd_wp_fork_pin_test_common(gopts, args, true); } -static void check_memory_contents(char *p) +static void check_memory_contents(uffd_global_test_opts_t *gopts, char *p) { unsigned long i, j; uint8_t expected_byte; - for (i = 0; i < nr_pages; ++i) { + for (i = 0; i < gopts->nr_pages; ++i) { expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); - for (j = 0; j < page_size; j++) { - uint8_t v = *(uint8_t *)(p + (i * page_size) + j); + for (j = 0; j < gopts->page_size; j++) { + uint8_t v = *(uint8_t *)(p + (i * gopts->page_size) + j); if (v != expected_byte) err("unexpected page contents"); } } } -static void uffd_minor_test_common(bool test_collapse, bool test_wp) +static void uffd_minor_test_common(uffd_global_test_opts_t *gopts, bool test_collapse, bool test_wp) { unsigned long p; pthread_t uffd_mon; char c; struct uffd_args args = { 0 }; + args.gopts = gopts; /* * NOTE: MADV_COLLAPSE is not yet compatible with WP, so testing @@ -577,7 +554,7 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) */ assert(!(test_collapse && test_wp)); - if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst_alias, gopts->nr_pages * gopts->page_size, /* NOTE! MADV_COLLAPSE may not work with uffd-wp */ false, test_wp, true)) err("register failure"); @@ -586,9 +563,9 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) * After registering with UFFD, populate the non-UFFD-registered side of * the shared mapping. This should *not* trigger any UFFD minor faults. */ - for (p = 0; p < nr_pages; ++p) - memset(area_dst + (p * page_size), p % ((uint8_t)-1), - page_size); + for (p = 0; p < gopts->nr_pages; ++p) + memset(gopts->area_dst + (p * gopts->page_size), p % ((uint8_t)-1), + gopts->page_size); args.apply_wp = test_wp; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) @@ -600,50 +577,51 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) * fault. uffd_poll_thread will resolve the fault by bit-flipping the * page's contents, and then issuing a CONTINUE ioctl. */ - check_memory_contents(area_dst_alias); + check_memory_contents(gopts, gopts->area_dst_alias); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("join() failed"); if (test_collapse) { - if (madvise(area_dst_alias, nr_pages * page_size, + if (madvise(gopts->area_dst_alias, gopts->nr_pages * gopts->page_size, MADV_COLLAPSE)) { /* It's fine to fail for this one... */ uffd_test_skip("MADV_COLLAPSE failed"); return; } - uffd_test_ops->check_pmd_mapping(area_dst, - nr_pages * page_size / + uffd_test_ops->check_pmd_mapping(gopts, + gopts->area_dst, + gopts->nr_pages * gopts->page_size / read_pmd_pagesize()); /* * This won't cause uffd-fault - it purely just makes sure there * was no corruption. */ - check_memory_contents(area_dst_alias); + check_memory_contents(gopts, gopts->area_dst_alias); } - if (args.missing_faults != 0 || args.minor_faults != nr_pages) + if (args.missing_faults != 0 || args.minor_faults != gopts->nr_pages) uffd_test_fail("stats check error"); else uffd_test_pass(); } -void uffd_minor_test(uffd_test_args_t __unused *args) +void uffd_minor_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_minor_test_common(false, false); + uffd_minor_test_common(gopts, false, false); } -void uffd_minor_wp_test(uffd_test_args_t __unused *args) +void uffd_minor_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_minor_test_common(false, true); + uffd_minor_test_common(gopts, false, true); } -void uffd_minor_collapse_test(uffd_test_args_t __unused *args) +void uffd_minor_collapse_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_minor_test_common(true, false); + uffd_minor_test_common(gopts, true, false); } static sigjmp_buf jbuf, *sigbuf; @@ -678,7 +656,7 @@ static void sighndl(int sig, siginfo_t __unused *siginfo, void __unused *ptr) * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal * feature. Using monitor thread, verify no userfault events are generated. */ -static int faulting_process(int signal_test, bool wp) +static int faulting_process(uffd_global_test_opts_t *gopts, int signal_test, bool wp) { unsigned long nr, i; unsigned long long count; @@ -687,7 +665,7 @@ static int faulting_process(int signal_test, bool wp) struct sigaction act; volatile unsigned long signalled = 0; - split_nr_pages = (nr_pages + 1) / 2; + split_nr_pages = (gopts->nr_pages + 1) / 2; if (signal_test) { sigbuf = &jbuf; @@ -701,7 +679,7 @@ static int faulting_process(int signal_test, bool wp) for (nr = 0; nr < split_nr_pages; nr++) { volatile int steps = 1; - unsigned long offset = nr * page_size; + unsigned long offset = nr * gopts->page_size; if (signal_test) { if (sigsetjmp(*sigbuf, 1) != 0) { @@ -713,15 +691,15 @@ static int faulting_process(int signal_test, bool wp) if (steps == 1) { /* This is a MISSING request */ steps++; - if (copy_page(uffd, offset, wp)) + if (copy_page(gopts, offset, wp)) signalled++; } else { /* This is a WP request */ assert(steps == 2); - wp_range(uffd, - (__u64)area_dst + + wp_range(gopts->uffd, + (__u64)gopts->area_dst + offset, - page_size, false); + gopts->page_size, false); } } else { signalled++; @@ -730,51 +708,53 @@ static int faulting_process(int signal_test, bool wp) } } - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) + count = *area_count(gopts->area_dst, nr, gopts); + if (count != gopts->count_verify[nr]) err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); + nr, count, gopts->count_verify[nr]); /* * Trigger write protection if there is by writing * the same value back. */ - *area_count(area_dst, nr) = count; + *area_count(gopts->area_dst, nr, gopts) = count; } if (signal_test) return signalled != split_nr_pages; - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, - MREMAP_MAYMOVE | MREMAP_FIXED, area_src); - if (area_dst == MAP_FAILED) + gopts->area_dst = mremap(gopts->area_dst, gopts->nr_pages * gopts->page_size, + gopts->nr_pages * gopts->page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, + gopts->area_src); + if (gopts->area_dst == MAP_FAILED) err("mremap"); /* Reset area_src since we just clobbered it */ - area_src = NULL; + gopts->area_src = NULL; - for (; nr < nr_pages; nr++) { - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) { + for (; nr < gopts->nr_pages; nr++) { + count = *area_count(gopts->area_dst, nr, gopts); + if (count != gopts->count_verify[nr]) { err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); + nr, count, gopts->count_verify[nr]); } /* * Trigger write protection if there is by writing * the same value back. */ - *area_count(area_dst, nr) = count; + *area_count(gopts->area_dst, nr, gopts) = count; } - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); - for (nr = 0; nr < nr_pages; nr++) - for (i = 0; i < page_size; i++) - if (*(area_dst + nr * page_size + i) != 0) + for (nr = 0; nr < gopts->nr_pages; nr++) + for (i = 0; i < gopts->page_size; i++) + if (*(gopts->area_dst + nr * gopts->page_size + i) != 0) err("page %lu offset %lu is not zero", nr, i); return 0; } -static void uffd_sigbus_test_common(bool wp) +static void uffd_sigbus_test_common(uffd_global_test_opts_t *gopts, bool wp) { unsigned long userfaults; pthread_t uffd_mon; @@ -782,25 +762,26 @@ static void uffd_sigbus_test_common(bool wp) int err; char c; struct uffd_args args = { 0 }; + args.gopts = gopts; - ready_for_fork = false; + gopts->ready_for_fork = false; - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, wp, false)) err("register failure"); - if (faulting_process(1, wp)) + if (faulting_process(gopts, 1, wp)) err("faulting process failed"); - uffd_test_ops->release_pages(area_dst); + uffd_test_ops->release_pages(gopts, gopts->area_dst); args.apply_wp = wp; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - while (!ready_for_fork) + while (!gopts->ready_for_fork) ; /* Wait for the poll_thread to start executing before forking */ pid = fork(); @@ -808,12 +789,12 @@ static void uffd_sigbus_test_common(bool wp) err("fork"); if (!pid) - exit(faulting_process(2, wp)); + exit(faulting_process(gopts, 2, wp)); waitpid(pid, &err, 0); if (err) err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, (void **)&userfaults)) err("pthread_join()"); @@ -824,28 +805,29 @@ static void uffd_sigbus_test_common(bool wp) uffd_test_pass(); } -static void uffd_sigbus_test(uffd_test_args_t __unused *args) +static void uffd_sigbus_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_sigbus_test_common(false); + uffd_sigbus_test_common(gopts, false); } -static void uffd_sigbus_wp_test(uffd_test_args_t __unused *args) +static void uffd_sigbus_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_sigbus_test_common(true); + uffd_sigbus_test_common(gopts, true); } -static void uffd_events_test_common(bool wp) +static void uffd_events_test_common(uffd_global_test_opts_t *gopts, bool wp) { pthread_t uffd_mon; pid_t pid; int err; char c; struct uffd_args args = { 0 }; + args.gopts = gopts; - ready_for_fork = false; + gopts->ready_for_fork = false; - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, wp, false)) err("register failure"); @@ -853,7 +835,7 @@ static void uffd_events_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - while (!ready_for_fork) + while (!gopts->ready_for_fork) ; /* Wait for the poll_thread to start executing before forking */ pid = fork(); @@ -861,39 +843,39 @@ static void uffd_events_test_common(bool wp) err("fork"); if (!pid) - exit(faulting_process(0, wp)); + exit(faulting_process(gopts, 0, wp)); waitpid(pid, &err, 0); if (err) err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("pthread_join()"); - if (args.missing_faults != nr_pages) + if (args.missing_faults != gopts->nr_pages) uffd_test_fail("Fault counts wrong"); else uffd_test_pass(); } -static void uffd_events_test(uffd_test_args_t __unused *args) +static void uffd_events_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_events_test_common(false); + uffd_events_test_common(gopts, false); } -static void uffd_events_wp_test(uffd_test_args_t __unused *args) +static void uffd_events_wp_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { - uffd_events_test_common(true); + uffd_events_test_common(gopts, true); } -static void retry_uffdio_zeropage(int ufd, +static void retry_uffdio_zeropage(uffd_global_test_opts_t *gopts, struct uffdio_zeropage *uffdio_zeropage) { - uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffd_test_ops->alias_mapping(gopts, &uffdio_zeropage->range.start, uffdio_zeropage->range.len, 0); - if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (ioctl(gopts->uffd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { if (uffdio_zeropage->zeropage != -EEXIST) err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)uffdio_zeropage->zeropage); @@ -903,16 +885,16 @@ static void retry_uffdio_zeropage(int ufd, } } -static bool do_uffdio_zeropage(int ufd, bool has_zeropage) +static bool do_uffdio_zeropage(uffd_global_test_opts_t *gopts, bool has_zeropage) { struct uffdio_zeropage uffdio_zeropage = { 0 }; int ret; __s64 res; - uffdio_zeropage.range.start = (unsigned long) area_dst; - uffdio_zeropage.range.len = page_size; + uffdio_zeropage.range.start = (unsigned long) gopts->area_dst; + uffdio_zeropage.range.len = gopts->page_size; uffdio_zeropage.mode = 0; - ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); + ret = ioctl(gopts->uffd, UFFDIO_ZEROPAGE, &uffdio_zeropage); res = uffdio_zeropage.zeropage; if (ret) { /* real retval in ufdio_zeropage.zeropage */ @@ -921,10 +903,10 @@ static bool do_uffdio_zeropage(int ufd, bool has_zeropage) else if (res != -EINVAL) err("UFFDIO_ZEROPAGE not -EINVAL"); } else if (has_zeropage) { - if (res != page_size) + if (res != gopts->page_size) err("UFFDIO_ZEROPAGE unexpected size"); else - retry_uffdio_zeropage(ufd, &uffdio_zeropage); + retry_uffdio_zeropage(gopts, &uffdio_zeropage); return true; } else err("UFFDIO_ZEROPAGE succeeded"); @@ -950,25 +932,29 @@ uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len) } /* exercise UFFDIO_ZEROPAGE */ -static void uffd_zeropage_test(uffd_test_args_t __unused *args) +static void uffd_zeropage_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *args) { bool has_zeropage; int i; - has_zeropage = uffd_register_detect_zeropage(uffd, area_dst, page_size); - if (area_dst_alias) + has_zeropage = uffd_register_detect_zeropage(gopts->uffd, + gopts->area_dst, + gopts->page_size); + if (gopts->area_dst_alias) /* Ignore the retval; we already have it */ - uffd_register_detect_zeropage(uffd, area_dst_alias, page_size); + uffd_register_detect_zeropage(gopts->uffd, gopts->area_dst_alias, gopts->page_size); - if (do_uffdio_zeropage(uffd, has_zeropage)) - for (i = 0; i < page_size; i++) - if (area_dst[i] != 0) + if (do_uffdio_zeropage(gopts, has_zeropage)) + for (i = 0; i < gopts->page_size; i++) + if (gopts->area_dst[i] != 0) err("data non-zero at offset %d\n", i); - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("unregister"); - if (area_dst_alias && uffd_unregister(uffd, area_dst_alias, page_size)) + if (gopts->area_dst_alias && uffd_unregister(gopts->uffd, + gopts->area_dst_alias, + gopts->page_size)) err("unregister"); uffd_test_pass(); @@ -987,26 +973,27 @@ static void uffd_register_poison(int uffd, void *addr, uint64_t len) err("registered area doesn't support COPY and POISON ioctls"); } -static void do_uffdio_poison(int uffd, unsigned long offset) +static void do_uffdio_poison(uffd_global_test_opts_t *gopts, unsigned long offset) { struct uffdio_poison uffdio_poison = { 0 }; int ret; __s64 res; - uffdio_poison.range.start = (unsigned long) area_dst + offset; - uffdio_poison.range.len = page_size; + uffdio_poison.range.start = (unsigned long) gopts->area_dst + offset; + uffdio_poison.range.len = gopts->page_size; uffdio_poison.mode = 0; - ret = ioctl(uffd, UFFDIO_POISON, &uffdio_poison); + ret = ioctl(gopts->uffd, UFFDIO_POISON, &uffdio_poison); res = uffdio_poison.updated; if (ret) err("UFFDIO_POISON error: %"PRId64, (int64_t)res); - else if (res != page_size) + else if (res != gopts->page_size) err("UFFDIO_POISON unexpected size: %"PRId64, (int64_t)res); } -static void uffd_poison_handle_fault( - struct uffd_msg *msg, struct uffd_args __unused *args) +static void uffd_poison_handle_fault(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args __unused *args) { unsigned long offset; @@ -1017,20 +1004,20 @@ static void uffd_poison_handle_fault( (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR)) err("unexpected fault type %llu", msg->arg.pagefault.flags); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; + offset &= ~(gopts->page_size-1); /* Odd pages -> copy zeroed page; even pages -> poison. */ - if (offset & page_size) - copy_page(uffd, offset, false); + if (offset & gopts->page_size) + copy_page(gopts, offset, false); else - do_uffdio_poison(uffd, offset); + do_uffdio_poison(gopts, offset); } /* Make sure to cover odd/even, and minimum duplications */ #define UFFD_POISON_TEST_NPAGES 4 -static void uffd_poison_test(uffd_test_args_t __unused *targs) +static void uffd_poison_test(uffd_global_test_opts_t *gopts, uffd_test_args_t __unused *targs) { pthread_t uffd_mon; char c; @@ -1039,15 +1026,17 @@ static void uffd_poison_test(uffd_test_args_t __unused *targs) unsigned long nr_sigbus = 0; unsigned long nr, poison_pages = UFFD_POISON_TEST_NPAGES; - if (nr_pages < poison_pages) { - uffd_test_skip("Too few pages for POISON test"); + if (gopts->nr_pages < poison_pages) { + uffd_test_skip("Too less pages for POISON test"); return; } - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + args.gopts = gopts; + + fcntl(gopts->uffd, F_SETFL, gopts->uffd_flags | O_NONBLOCK); - uffd_register_poison(uffd, area_dst, poison_pages * page_size); - memset(area_src, 0, poison_pages * page_size); + uffd_register_poison(gopts->uffd, gopts->area_dst, poison_pages * gopts->page_size); + memset(gopts->area_src, 0, poison_pages * gopts->page_size); args.handle_fault = uffd_poison_handle_fault; if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) @@ -1060,8 +1049,8 @@ static void uffd_poison_test(uffd_test_args_t __unused *targs) err("sigaction"); for (nr = 0; nr < poison_pages; ++nr) { - unsigned long offset = nr * page_size; - const char *bytes = (const char *) area_dst + offset; + unsigned long offset = nr * gopts->page_size; + const char *bytes = (const char *) gopts->area_dst + offset; const char *i; if (sigsetjmp(*sigbuf, 1)) { @@ -1074,14 +1063,14 @@ static void uffd_poison_test(uffd_test_args_t __unused *targs) continue; } - for (i = bytes; i < bytes + page_size; ++i) { + for (i = bytes; i < bytes + gopts->page_size; ++i) { if (*i) err("nonzero byte in area_dst (%p) at %p: %u", - area_dst, i, *i); + gopts->area_dst, i, *i); } } - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("pthread_join()"); @@ -1094,7 +1083,9 @@ static void uffd_poison_test(uffd_test_args_t __unused *targs) } static void -uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args, +uffd_move_handle_fault_common(uffd_global_test_opts_t *gopts, + struct uffd_msg *msg, + struct uffd_args *args, unsigned long len) { unsigned long offset; @@ -1106,28 +1097,32 @@ uffd_move_handle_fault_common(struct uffd_msg *msg, struct uffd_args *args, (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE)) err("unexpected fault type %llu", msg->arg.pagefault.flags); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset = (char *)(unsigned long)msg->arg.pagefault.address - gopts->area_dst; offset &= ~(len-1); - if (move_page(uffd, offset, len)) + if (move_page(gopts, offset, len)) args->missing_faults++; } -static void uffd_move_handle_fault(struct uffd_msg *msg, +static void uffd_move_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, struct uffd_args *args) { - uffd_move_handle_fault_common(msg, args, page_size); + uffd_move_handle_fault_common(gopts, msg, args, gopts->page_size); } -static void uffd_move_pmd_handle_fault(struct uffd_msg *msg, +static void uffd_move_pmd_handle_fault(uffd_global_test_opts_t *gopts, struct uffd_msg *msg, struct uffd_args *args) { - uffd_move_handle_fault_common(msg, args, read_pmd_pagesize()); + uffd_move_handle_fault_common(gopts, msg, args, read_pmd_pagesize()); } static void -uffd_move_test_common(uffd_test_args_t __unused *targs, unsigned long chunk_size, - void (*handle_fault)(struct uffd_msg *msg, struct uffd_args *args)) +uffd_move_test_common(uffd_global_test_opts_t *gopts, + uffd_test_args_t __unused *targs, + unsigned long chunk_size, + void (*handle_fault)(struct uffd_global_test_opts *gopts, + struct uffd_msg *msg, struct uffd_args *args) +) { unsigned long nr; pthread_t uffd_mon; @@ -1139,11 +1134,13 @@ uffd_move_test_common(uffd_test_args_t __unused *targs, unsigned long chunk_size unsigned long src_offs = 0; unsigned long dst_offs = 0; + args.gopts = gopts; + /* Prevent source pages from being mapped more than once */ - if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK)) + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_DONTFORK)) err("madvise(MADV_DONTFORK) failure"); - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, false, false)) err("register failure"); @@ -1151,22 +1148,22 @@ uffd_move_test_common(uffd_test_args_t __unused *targs, unsigned long chunk_size if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - step_size = chunk_size / page_size; - step_count = nr_pages / step_size; + step_size = chunk_size / gopts->page_size; + step_count = gopts->nr_pages / step_size; - if (chunk_size > page_size) { - char *aligned_src = ALIGN_UP(area_src, chunk_size); - char *aligned_dst = ALIGN_UP(area_dst, chunk_size); + if (chunk_size > gopts->page_size) { + char *aligned_src = ALIGN_UP(gopts->area_src, chunk_size); + char *aligned_dst = ALIGN_UP(gopts->area_dst, chunk_size); - if (aligned_src != area_src || aligned_dst != area_dst) { - src_offs = (aligned_src - area_src) / page_size; - dst_offs = (aligned_dst - area_dst) / page_size; + if (aligned_src != gopts->area_src || aligned_dst != gopts->area_dst) { + src_offs = (aligned_src - gopts->area_src) / gopts->page_size; + dst_offs = (aligned_dst - gopts->area_dst) / gopts->page_size; step_count--; } - orig_area_src = area_src; - orig_area_dst = area_dst; - area_src = aligned_src; - area_dst = aligned_dst; + orig_area_src = gopts->area_src; + orig_area_dst = gopts->area_dst; + gopts->area_src = aligned_src; + gopts->area_dst = aligned_dst; } /* @@ -1180,34 +1177,34 @@ uffd_move_test_common(uffd_test_args_t __unused *targs, unsigned long chunk_size /* Check area_src content */ for (i = 0; i < step_size; i++) { - count = *area_count(area_src, nr + i); - if (count != count_verify[src_offs + nr + i]) + count = *area_count(gopts->area_src, nr + i, gopts); + if (count != gopts->count_verify[src_offs + nr + i]) err("nr %lu source memory invalid %llu %llu\n", - nr + i, count, count_verify[src_offs + nr + i]); + nr + i, count, gopts->count_verify[src_offs + nr + i]); } /* Faulting into area_dst should move the page or the huge page */ for (i = 0; i < step_size; i++) { - count = *area_count(area_dst, nr + i); - if (count != count_verify[dst_offs + nr + i]) + count = *area_count(gopts->area_dst, nr + i, gopts); + if (count != gopts->count_verify[dst_offs + nr + i]) err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[dst_offs + nr + i]); + nr, count, gopts->count_verify[dst_offs + nr + i]); } /* Re-check area_src content which should be empty */ for (i = 0; i < step_size; i++) { - count = *area_count(area_src, nr + i); + count = *area_count(gopts->area_src, nr + i, gopts); if (count != 0) err("nr %lu move failed %llu %llu\n", - nr, count, count_verify[src_offs + nr + i]); + nr, count, gopts->count_verify[src_offs + nr + i]); } } - if (chunk_size > page_size) { - area_src = orig_area_src; - area_dst = orig_area_dst; + if (chunk_size > gopts->page_size) { + gopts->area_src = orig_area_src; + gopts->area_dst = orig_area_dst; } - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + if (write(gopts->pipefd[1], &c, sizeof(c)) != sizeof(c)) err("pipe write"); if (pthread_join(uffd_mon, NULL)) err("join() failed"); @@ -1218,24 +1215,24 @@ uffd_move_test_common(uffd_test_args_t __unused *targs, unsigned long chunk_size uffd_test_pass(); } -static void uffd_move_test(uffd_test_args_t *targs) +static void uffd_move_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { - uffd_move_test_common(targs, page_size, uffd_move_handle_fault); + uffd_move_test_common(gopts, targs, gopts->page_size, uffd_move_handle_fault); } -static void uffd_move_pmd_test(uffd_test_args_t *targs) +static void uffd_move_pmd_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { - if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE)) + if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) err("madvise(MADV_HUGEPAGE) failure"); - uffd_move_test_common(targs, read_pmd_pagesize(), + uffd_move_test_common(gopts, targs, read_pmd_pagesize(), uffd_move_pmd_handle_fault); } -static void uffd_move_pmd_split_test(uffd_test_args_t *targs) +static void uffd_move_pmd_split_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *targs) { - if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE)) + if (madvise(gopts->area_dst, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) err("madvise(MADV_NOHUGEPAGE) failure"); - uffd_move_test_common(targs, read_pmd_pagesize(), + uffd_move_test_common(gopts, targs, read_pmd_pagesize(), uffd_move_pmd_handle_fault); } @@ -1295,6 +1292,11 @@ typedef enum { THR_STATE_UNINTERRUPTIBLE, } thread_state; +typedef struct { + uffd_global_test_opts_t *gopts; + volatile pid_t *pid; +} mmap_changing_thread_args; + static void sleep_short(void) { usleep(1000); @@ -1337,7 +1339,9 @@ static void thread_state_until(pid_t tid, thread_state state) static void *uffd_mmap_changing_thread(void *opaque) { - volatile pid_t *pid = opaque; + mmap_changing_thread_args *args = opaque; + uffd_global_test_opts_t *gopts = args->gopts; + volatile pid_t *pid = args->pid; int ret; /* Unfortunately, it's only fetch-able from the thread itself.. */ @@ -1345,21 +1349,22 @@ static void *uffd_mmap_changing_thread(void *opaque) *pid = syscall(SYS_gettid); /* Inject an event, this will hang solid until the event read */ - ret = madvise(area_dst, page_size, MADV_REMOVE); + ret = madvise(gopts->area_dst, gopts->page_size, MADV_REMOVE); if (ret) err("madvise(MADV_REMOVE) failed"); return NULL; } -static void uffd_consume_message(void) +static void uffd_consume_message(uffd_global_test_opts_t *gopts) { struct uffd_msg msg = { 0 }; - while (uffd_read_msg(&msg)); + while (uffd_read_msg(gopts, &msg)); } -static void uffd_mmap_changing_test(uffd_test_args_t __unused *targs) +static void uffd_mmap_changing_test(uffd_global_test_opts_t *gopts, + uffd_test_args_t __unused *targs) { /* * This stores the real PID (which can be different from how tid is @@ -1368,13 +1373,14 @@ static void uffd_mmap_changing_test(uffd_test_args_t __unused *targs) pid_t pid = 0; pthread_t tid; int ret; + mmap_changing_thread_args args = { gopts, &pid }; - if (uffd_register(uffd, area_dst, nr_pages * page_size, + if (uffd_register(gopts->uffd, gopts->area_dst, gopts->nr_pages * gopts->page_size, true, false, false)) err("uffd_register() failed"); /* Create a thread to generate the racy event */ - ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &pid); + ret = pthread_create(&tid, NULL, uffd_mmap_changing_thread, &args); if (ret) err("pthread_create() failed"); @@ -1388,26 +1394,26 @@ static void uffd_mmap_changing_test(uffd_test_args_t __unused *targs) /* Wait until the thread hangs at REMOVE event */ thread_state_until(pid, THR_STATE_UNINTERRUPTIBLE); - if (!uffdio_mmap_changing_test_copy(uffd)) + if (!uffdio_mmap_changing_test_copy(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_zeropage(uffd)) + if (!uffdio_mmap_changing_test_zeropage(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_move(uffd)) + if (!uffdio_mmap_changing_test_move(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_poison(uffd)) + if (!uffdio_mmap_changing_test_poison(gopts->uffd)) return; - if (!uffdio_mmap_changing_test_continue(uffd)) + if (!uffdio_mmap_changing_test_continue(gopts->uffd)) return; /* * All succeeded above! Recycle everything. Start by reading the * event so as to kick the thread roll again.. */ - uffd_consume_message(); + uffd_consume_message(gopts); ret = pthread_join(tid, NULL); assert(ret == 0); @@ -1415,10 +1421,10 @@ static void uffd_mmap_changing_test(uffd_test_args_t __unused *targs) uffd_test_pass(); } -static int prevent_hugepages(const char **errmsg) +static int prevent_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg) { /* This should be done before source area is populated */ - if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) { + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_NOHUGEPAGE)) { /* Ignore only if CONFIG_TRANSPARENT_HUGEPAGE=n */ if (errno != EINVAL) { if (errmsg) @@ -1429,10 +1435,10 @@ static int prevent_hugepages(const char **errmsg) return 0; } -static int request_hugepages(const char **errmsg) +static int request_hugepages(uffd_global_test_opts_t *gopts, const char **errmsg) { /* This should be done before source area is populated */ - if (madvise(area_src, nr_pages * page_size, MADV_HUGEPAGE)) { + if (madvise(gopts->area_src, gopts->nr_pages * gopts->page_size, MADV_HUGEPAGE)) { if (errmsg) { *errmsg = (errno == EINVAL) ? "CONFIG_TRANSPARENT_HUGEPAGE is not set" : @@ -1456,13 +1462,17 @@ struct uffd_test_case_ops uffd_move_test_pmd_case_ops = { * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test. */ static void -do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) +do_register_ioctls_test(uffd_global_test_opts_t *gopts, + uffd_test_args_t *args, + bool miss, + bool wp, + bool minor) { uint64_t ioctls = 0, expected = BIT_ULL(_UFFDIO_WAKE); mem_type_t *mem_type = args->mem_type; int ret; - ret = uffd_register_with_ioctls(uffd, area_dst, page_size, + ret = uffd_register_with_ioctls(gopts->uffd, gopts->area_dst, gopts->page_size, miss, wp, minor, &ioctls); /* @@ -1493,18 +1503,18 @@ do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) "(miss=%d, wp=%d, minor=%d): expected=0x%"PRIx64", " "returned=0x%"PRIx64, miss, wp, minor, expected, ioctls); - if (uffd_unregister(uffd, area_dst, page_size)) + if (uffd_unregister(gopts->uffd, gopts->area_dst, gopts->page_size)) err("unregister"); } -static void uffd_register_ioctls_test(uffd_test_args_t *args) +static void uffd_register_ioctls_test(uffd_global_test_opts_t *gopts, uffd_test_args_t *args) { int miss, wp, minor; for (miss = 0; miss <= 1; miss++) for (wp = 0; wp <= 1; wp++) for (minor = 0; minor <= 1; minor++) - do_register_ioctls_test(args, miss, wp, minor); + do_register_ioctls_test(gopts, args, miss, wp, minor); uffd_test_pass(); } @@ -1742,6 +1752,28 @@ int main(int argc, char *argv[]) } for (j = 0; j < n_mems; j++) { mem_type = &mem_types[j]; + + /* Initialize global test options */ + uffd_global_test_opts_t gopts = { 0 }; + + gopts.map_shared = mem_type->shared; + uffd_test_ops = mem_type->mem_ops; + uffd_test_case_ops = test->test_case_ops; + + if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) + gopts.page_size = default_huge_page_size(); + else + gopts.page_size = psize(); + + /* Ensure we have at least 2 pages */ + gopts.nr_pages = MAX(UFFD_TEST_MEM_SIZE, gopts.page_size * 2) + / gopts.page_size; + + gopts.nr_parallel = 1; + + /* Initialize test arguments */ + args.mem_type = mem_type; + if (!(test->mem_targets & mem_type->mem_flag)) continue; @@ -1756,13 +1788,12 @@ int main(int argc, char *argv[]) uffd_test_skip("feature missing"); continue; } - if (uffd_setup_environment(&args, test, mem_type, - &errmsg)) { + if (uffd_test_ctx_init(&gopts, test->uffd_feature_required, &errmsg)) { uffd_test_skip(errmsg); continue; } - test->uffd_fn(&args); - uffd_test_ctx_clear(); + test->uffd_fn(&gopts, &args); + uffd_test_ctx_clear(&gopts); } } diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c index b2b6116e6580..ec860625b25b 100644 --- a/tools/testing/selftests/mm/uffd-wp-mremap.c +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -152,7 +152,11 @@ static bool range_is_swapped(void *addr, size_t size) return true; } -static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb) +static void test_one_folio(uffd_global_test_opts_t *gopts, + size_t size, + bool private, + bool swapout, + bool hugetlb) { struct uffdio_writeprotect wp_prms; uint64_t features = 0; @@ -176,21 +180,21 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb } /* Register range for uffd-wp. */ - if (userfaultfd_open(&features)) { + if (userfaultfd_open(gopts, &features)) { if (errno == ENOENT) ksft_test_result_skip("userfaultfd not available\n"); else ksft_test_result_fail("userfaultfd_open() failed\n"); goto out; } - if (uffd_register(uffd, mem, size, false, true, false)) { + if (uffd_register(gopts->uffd, mem, size, false, true, false)) { ksft_test_result_fail("uffd_register() failed\n"); goto out; } wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP; wp_prms.range.start = (uintptr_t)mem; wp_prms.range.len = size; - if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { + if (ioctl(gopts->uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n"); goto out; } @@ -237,9 +241,9 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb out: if (mem) munmap(mem, size); - if (uffd >= 0) { - close(uffd); - uffd = -1; + if (gopts->uffd >= 0) { + close(gopts->uffd); + gopts->uffd = -1; } } @@ -331,6 +335,7 @@ static const struct testcase testcases[] = { int main(void) { + uffd_global_test_opts_t gopts = { 0 }; struct thp_settings settings; int i, j, plan = 0; @@ -362,8 +367,8 @@ int main(void) const struct testcase *tc = &testcases[i]; for (j = 0; j < *tc->nr_sizes; j++) - test_one_folio(tc->sizes[j], tc->private, tc->swapout, - tc->hugetlb); + test_one_folio(&gopts, tc->sizes[j], tc->private, + tc->swapout, tc->hugetlb); } /* If THP is supported, restore original THP settings. */ -- 2.30.2

1 month, 2 weeks

5
7
0 0

[PATCH 9/9] selftests: kselftest: Add ulong typedef for non-glibc compatibility

by Aqib Faruqui

Some C libraries may not define the ulong typedef that is commonly available as a BSD/GNU extension. Add a fallback typedef to ensure ulong is available across all selftest environments. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kselftest.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index f362c6766..a1088a2af 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -58,6 +58,11 @@ #include <stdio.h> #include <sys/utsname.h> #include <sys/syscall.h> +#include <sys/types.h> +#endif + +#ifndef ulong +typedef unsigned long ulong; #endif #ifndef ARRAY_SIZE -- 2.47.3

1 month, 2 weeks

1
0
0 0

[PATCH 8/9] selftests: Fix stdbuf compatibility in mixed libc environments

by Aqib Faruqui

The original stdbuf use only checked if /usr/bin/stdbuf exists in the host's system but failed to verify compatibility between stdbuf and the target test binary. The issue occurs when: - Host system has glibc-based stdbuf from coreutils - Selftest binaries are compiled with a non-glibc toolchain (cross compilation) The fix adds a runtime compatibility test against the target test binary before enabling stdbuf, enabling cross-compiled selftests to run successfully. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kselftest/runner.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 2c3c58e65..8d4e33bd5 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -107,7 +107,7 @@ run_one() echo "# Warning: file $TEST is missing!" echo "not ok $test_num $TEST_HDR_MSG" else - if [ -x /usr/bin/stdbuf ]; then + if [ -x /usr/bin/stdbuf ] && [ -x "$TEST" ] && /usr/bin/stdbuf --output=L ldd "$TEST" >/dev/null 2>&1; then stdbuf="/usr/bin/stdbuf --output=L " fi eval kselftest_cmd_args="\$${kselftest_cmd_args_ref:-}" -- 2.47.3

1 month, 2 weeks

1
0
0 0

[PATCH 7/9] rseq: selftests: Add non-glibc compatibility fixes

by Aqib Faruqui

The rseq selftests rely on features provided by glibc that may not be available in non-glibc C libraries: 1. The __GNU_PREREQ macro and glibc's thread pointer implementation are not available in non-glibc libraries 2. The __NR_rseq syscall number may not be defined in non-glibc headers Add a fallback thread pointer implementation for non-glibc systems using the pre-existing inline assembly to access thread-local storage directly via %fs/%gs registers. Also provide a fallback definition for __NR_rseq when not already defined by the C library headers: 527 for alpha and 293 for other architectures. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- .../selftests/rseq/rseq-x86-thread-pointer.h | 14 ++++++++++++++ tools/testing/selftests/rseq/rseq.c | 8 ++++++++ 2 files changed, 22 insertions(+) diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h index d3133587d..a7c402926 100644 --- a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h +++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h @@ -14,6 +14,7 @@ extern "C" { #endif +#ifdef __GLIBC__ #if __GNUC_PREREQ (11, 1) static inline void *rseq_thread_pointer(void) { @@ -32,6 +33,19 @@ static inline void *rseq_thread_pointer(void) return __result; } #endif /* !GCC 11 */ +#else +static inline void *rseq_thread_pointer(void) +{ + void *__result; + +# ifdef __x86_64__ + __asm__ ("mov %%fs:0, %0" : "=r" (__result)); +# else + __asm__ ("mov %%gs:0, %0" : "=r" (__result)); +# endif + return __result; +} +#endif /* !__GLIBC__ */ #ifdef __cplusplus } diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 663a9cef1..1a6f73c98 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -36,6 +36,14 @@ #include "../kselftest.h" #include "rseq.h" +#ifndef __NR_rseq +#ifdef __alpha__ +#define __NR_rseq 527 +#else +#define __NR_rseq 293 +#endif +#endif + /* * Define weak versions to play nice with binaries that are statically linked * against a libc that doesn't support registering its own rseq. -- 2.47.3

1 month, 2 weeks

1
0
0 0

[PATCH 6/9] KVM: selftests: Add backtrace fallback

by Aqib Faruqui

The backtrace() function is a GNU extension available in glibc but may not be present in non-glibc libraries. KVM selftests use backtrace() for error reporting and debugging. Add conditional inclusion of execinfo.h only for glibc builds and provide a weak stub implementation of backtrace() that returns 0 (stack trace empty) for non-glibc systems. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kvm/lib/assert.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index b49690658..c9778dc6c 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -6,11 +6,19 @@ */ #include "test_util.h" -#include <execinfo.h> #include <sys/syscall.h> +#ifdef __GLIBC__ +#include <execinfo.h> /* backtrace */ +#endif + #include "kselftest.h" +int __attribute__((weak)) backtrace(void **buffer, int size) +{ + return 0; +} + /* Dumps the current stack trace to stderr. */ static void __attribute__((noinline)) test_dump_stack(void); static void test_dump_stack(void) -- 2.47.3

1 month, 2 weeks

1
0
0 0

[PATCH 4/9] selftests: kselftest: Add memfd_create syscall compatibility

by Aqib Faruqui

The memfd_create function and related MFD_* flags may not be available in non-glibc C libraries. Some selftests use memfd_create for memory backing operations. Add fallback definitions for MFD_CLOEXEC and MFD_HUGETLB flags, and provide a memfd_create wrapper. Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kselftest.h | 19 +++++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 1 + 2 files changed, 20 insertions(+) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index c3b6d2604..f362c6766 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -57,6 +57,7 @@ #include <string.h> #include <stdio.h> #include <sys/utsname.h> +#include <sys/syscall.h> #endif #ifndef ARRAY_SIZE @@ -80,6 +81,24 @@ #endif #endif /* end arch */ +#ifndef MFD_CLOEXEC +#define MFD_CLOEXEC 0x0001U +#endif + +#ifndef MFD_HUGETLB +#define MFD_HUGETLB 0x0004U +#endif + +static inline int memfd_create(const char *name, unsigned int flags) +{ +#ifdef __NR_memfd_create + return syscall(__NR_memfd_create, name, flags); +#else + errno = ENOSYS; + return -1; +#endif +} + /* define kselftest exit codes */ #define KSFT_PASS 0 #define KSFT_FAIL 1 diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 5ce80303d..cb5209f6a 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -15,6 +15,7 @@ #include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> +#include <sys/syscall.h> #include <unistd.h> #include <linux/kernel.h> -- 2.47.3

1 month, 2 weeks

1
0
0 0

[PATCH 1/1] KVM: selftests: Fix force_emulation_prefix parameter type mismatch

by Aqib Faruqui

Fix kvm_is_forced_enabled() to use get_kvm_param_bool() instead of get_kvm_param_integer() when reading the "force_emulation_prefix" kernel module parameter. The force_emulation_prefix parameter is a boolean that accepts Y/N values, but the function was incorrectly trying to parse it as an integer using strtol(). Signed-off-by: Aqib Faruqui <aqibaf(a)amazon.com> --- tools/testing/selftests/kvm/include/x86/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 3f93d1b4f..8edf48b5a 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -1323,7 +1323,7 @@ static inline bool kvm_is_pmu_enabled(void) static inline bool kvm_is_forced_emulation_enabled(void) { - return !!get_kvm_param_integer("force_emulation_prefix"); + return get_kvm_param_bool("force_emulation_prefix"); } static inline bool kvm_is_unrestricted_guest_enabled(void) -- 2.47.3

1 month, 2 weeks

2
1
0 0

[PATCH] selftests/net: openvswitch: Fix spelling error in print message

by Madhur Kumar

Fix a typo in a print statement in ovs-dpctl.py: "Unkonwn" → "Unknown". --- tools/testing/selftests/net/openvswitch/ovs-dpctl.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 8a0396bfaf99..b521e0dea506 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -1877,7 +1877,7 @@ class OvsPacket(GenericNetlinkSocket): elif msg["cmd"] == OvsPacket.OVS_PACKET_CMD_EXECUTE: up.execute(msg) else: - print("Unkonwn cmd: %d" % msg["cmd"]) + print("Unknown cmd: %d" % msg["cmd"]) except NetlinkError as ne: raise ne -- 2.50.1

1 month, 2 weeks

2
2
0 0

[PATCH] selftests/move_mount_set_group: fix inconsistent return type in move_mount_set_group_supported()

by Miaoqian Lin

The function is declared to return bool but returns -1 on multiple error paths, which is inconsistent and misleading. Fix this by returning false on all error paths. Fixes: 8374f43123a5 ("tests: add move_mount(MOVE_MOUNT_SET_GROUP) selftest") Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> --- .../move_mount_set_group_test.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c index bcf51d785a37..3f2c94acb29a 100644 --- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c +++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c @@ -197,26 +197,26 @@ static bool move_mount_set_group_supported(void) if (mount("testing", "/tmp", "tmpfs", MS_NOATIME | MS_NODEV, "size=100000,mode=700")) - return -1; + return false; if (mount(NULL, "/tmp", NULL, MS_PRIVATE, 0)) - return -1; + return false; if (mkdir(SET_GROUP_FROM, 0777)) - return -1; + return false; if (mkdir(SET_GROUP_TO, 0777)) - return -1; + return false; if (mount("testing", SET_GROUP_FROM, "tmpfs", MS_NOATIME | MS_NODEV, "size=100000,mode=700")) - return -1; + return false; if (mount(SET_GROUP_FROM, SET_GROUP_TO, NULL, MS_BIND, NULL)) - return -1; + return false; if (mount(NULL, SET_GROUP_FROM, NULL, MS_SHARED, 0)) - return -1; + return false; ret = syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_FROM, AT_FDCWD, SET_GROUP_TO, MOVE_MOUNT_SET_GROUP); -- 2.35.1

1 month, 2 weeks

1
0
0 0

[PATCH bpf-next v4 1/2] bpf/helpers: bpf_strnstr: Exact match length

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> strnstr should not treat the ending '\0' of s2 as a matching character if the parameter 'len' equal to s2 string length, for example: 1. bpf_strnstr("openat", "open", 4) = -ENOENT 2. bpf_strnstr("openat", "open", 5) = 0 This patch makes (1) return 0, indicating a successful match. Fixes: e91370550f1f ("bpf: Add kfuncs for read-only string operations") Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- kernel/bpf/helpers.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 401b4932cc49..bf04881f96ec 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -3672,10 +3672,18 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len guard(pagefault)(); for (i = 0; i < XATTR_SIZE_MAX; i++) { - for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) { + for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) { __get_kernel_nofault(&c2, s2__ign + j, char, err_out); if (c2 == '\0') return i; + /** + * corner case i+j==len to ensure that we matched + * entire s2. for example, param len=3: + * s1: A B C D E F -> i==1 + * s2: B C D -> j==2 + */ + if (i + j == len) + break; __get_kernel_nofault(&c1, s1__ign + j, char, err_out); if (c1 == '\0') return -ENOENT; -- 2.51.0

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next v4 2/2] selftests/bpf: Add tests for bpf_strnstr

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Add tests for bpf_strnstr(): bpf_strnstr("", "", 0) = 0 bpf_strnstr("hello world", "hello", 5) = 0 bpf_strnstr(str, "hello", 4) = -ENOENT bpf_strnstr("", "a", 0) = -ENOENT Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..a47690174e0e 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } -__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); } -__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } +__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } char _license[] SEC("license") = "GPL"; -- 2.51.0

1 month, 2 weeks

1
0
0 0

[PATCH bpf-next v4 0/2] Fix bpf_strnstr len error

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Fix bpf_strnstr() wrong 'len' parameter, bpf_strnstr("open", "open", 4) should return 0 instead of -ENOENT. Rong Tao (2): bpf/helpers: bpf_strnstr: Exact match length selftests/bpf: Add tests for bpf_strnstr kernel/bpf/helpers.c | 10 +++++++++- .../selftests/bpf/progs/string_kfuncs_success.c | 8 ++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) --- v4: Add comment and more selftests; v3: Fix selftests/bpf error in v2, sorry about that; https://lore.kernel.org/lkml/tencent_69BD268FBA201219240B51661D5E96A8D80A@q… v2: Follow Andrii Nakryiko's advise, fix the 'wrong fix'; https://lore.kernel.org/lkml/tencent_DF4DA83EEBFB9246E5E3357BB40911CCA005@q… v1: https://lore.kernel.org/lkml/tencent_65E5988AD52BEC280D22964189505CD6ED06@q… -- 2.51.0

1 month, 2 weeks

1
0
0 0

[PATCH net-next] selftests: drv-net: rss_ctx: fix the queue count check

by Jakub Kicinski

Commit 0d6ccfe6b319 ("selftests: drv-net: rss_ctx: check for all-zero keys") added a skip exception if NIC has fewer than 3 queues enabled, but it's just constructing the object, it's not actually rising this exception. Before: # Exception| net.lib.py.utils.CmdExitFailure: Command failed: ethtool -X enp1s0 equal 3 hkey d1:cc:77:47:9d:ea:15:f2:b9:6c:ef:68:62:c0:45:d5:b0:99:7d:cf:29:53:40:06:3d:8e:b9:bc:d4:70:89:b8:8d:59:04:ea:a9:c2:21:b3:55:b8:ab:6b:d9:48:b4:bd:4c:ff:a5:f0:a8:c2 not ok 1 rss_ctx.test_rss_key_indir After: ok 1 rss_ctx.test_rss_key_indir # SKIP Device has fewer than 3 queues (or doesn't support queue stats) Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- I spotted that NIPA instances with 4 CPUs are failing this test case. They have only 4/2=2 queues. I bumped their CPU count to 6, but test is clearly wrong. CC: shuah(a)kernel.org CC: ecree.xilinx(a)gmail.com CC: gal(a)nvidia.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/hw/rss_ctx.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 7bb552f8b182..9838b8457e5a 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -118,7 +118,7 @@ from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure qcnt = len(_get_rx_cnts(cfg)) if qcnt < 3: - KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)") + raise KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)") data = get_rss(cfg) want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table'] -- 2.51.0

1 month, 2 weeks

3
2
0 0

[PATCH v4 0/7] kunit: Refactor and extend KUnit's parameterized testing framework

by David Gow

Hi all, This is a new version of Marie's patch series, with a couple of extra fixes squashed in, notably: - drm/xe/tests: Fix some additional gen_params signatures https://lore.kernel.org/linux-kselftest/20250821135447.1618942-1-davidgow@g… - kunit: Only output a test plan if we're using kunit_array_gen_params https://lore.kernel.org/linux-kselftest/20250821135447.1618942-2-davidgow@g… These should fix the issues found in linux-next here: https://lore.kernel.org/linux-next/20250818120846.347d64b1@canb.auug.org.au/ These changes only affect patches 3 and 4 of the series, the others are unchanged from v3. Thanks, everyone, and sorry for the inconvenience! Cheers, -- David --- Hello! KUnit offers a parameterized testing framework, where tests can be run multiple times with different inputs. However, the current implementation uses the same `struct kunit` for each parameter run. After each run, the test context gets cleaned up, which creates the following limitations: a. There is no way to store resources that are accessible across the individual parameter runs. b. It's not possible to pass additional context, besides the previous parameter (and potentially anything else that is stored in the current test context), to the parameter generator function. c. Test users are restricted to using pre-defined static arrays of parameter objects or generate_params() to define their parameters. There is no flexibility to make a custom dynamic array without using generate_params(), which can be complex if generating the next parameter depends on more than just the single previous parameter. This patch series resolves these limitations by: 1. [P 1] Giving each parameterized run its own `struct kunit`. It will remove the need to manage state, such as resetting the `test->priv` field or the `test->status_comment` after every parameter run. 2. [P 1] Introducing parameterized test context available to all parameter runs through the parent pointer of type `struct kunit`. This context won't be used to execute any test logic, but will instead be used for storing shared resources. Each parameter run context will have a reference to that parent instance and thus, have access to those resources. 3. [P 2] Introducing param_init() and param_exit() functions that can initialize and exit the parameterized test context. They will run once before and after the parameterized test. param_init() can be used to add resources to share between parameter runs, pass parameter arrays, and any other setup logic. While param_exit() can be used to clean up resources that were not managed by the parameterized test, and any other teardown logic. 4. [P 3] Passing the parameterized test context as an additional argument to generate_params(). This provides generate_params() with more context, making parameter generation much more flexible. The generate_params() implementations in the KCSAN and drm/xe tests have been adapted to match the new function pointer signature. 5. [P 4] Introducing a `params_array` field in `struct kunit`. This will allow the parameterized test context to have direct storage of the parameter array, enabling features like using dynamic parameter arrays or using context beyond just the previous parameter. This will also enable outputting the KTAP test plan for a parameterized test when the parameter count is available. Patches 5 and 6 add examples tests to lib/kunit/kunit-example-test.c to showcase the new features and patch 7 updates the KUnit documentation to reflect all the framework changes. Thank you! -Marie --- Changes in v4: Link to v3 of this patch series: https://lore.kernel.org/linux-kselftest/20250815103604.3857930-1-marievic@g… - Fixup the signatures of some more gen_params functions in the drm/xe driver. - Only print a KTAP test plan if a parameterised test is using the built-in kunit_array_gen_params generating function, fixing the issues with generator functions which skip array elements. Changes in v3: Link to v2 of this patch series: https://lore.kernel.org/all/20250811221739.2694336-1-marievic@google.com/ - Added logic for skipping the parameter runs and updating the test statistics when parameterized test initialization fails. - Minor changes to the documentation. - Commit message formatting. Changes in v2: Link to v1 of this patch series: https://lore.kernel.org/all/20250729193647.3410634-1-marievic@google.com/ - Establish parameterized testing terminology: - "parameterized test" will refer to the group of all runs of a single test function with different parameters. - "parameter run" will refer to the execution of the test case function with a single parameter. - "parameterized test context" is the `struct kunit` that holds the context for the entire parameterized test. - "parameter run context" is the `struct kunit` that holds the context of the individual parameter run. - A test is defined to be a parameterized tests if it was registered with a generator function. - Make comment edits to reflect the established terminology. - Require users to manually pass kunit_array_gen_params() to KUNIT_CASE_PARAM_WITH_INIT() as the generator function, unless they want to provide their own generator function, if the parameter array was registered in param_init(). This is to be consistent with the definition of a parameterized test, i.e. generate_params() is never NULL if it's a parameterized test. - Change name of kunit_get_next_param_and_desc() to kunit_array_gen_params(). - Other minor function name changes such as removing the "__" prefix in front of internal functions. - Change signature of get_description() in `struct params_array` to accept the parameterized test context, as well. - Output the KTAP test plan for a parameterized test when the parameter count is available. - Cover letter was made more concise. - Edits to the example tests. - Fix bug of parameterized test init/exit logic being done outside of the parameterized test check. - Fix bugs identified by the kernel test robot. --- Marie Zhussupova (7): kunit: Add parent kunit for parameterized test context kunit: Introduce param_init/exit for parameterized test context management kunit: Pass parameterized test context to generate_params() kunit: Enable direct registration of parameter arrays to a KUnit test kunit: Add example parameterized test with shared resource management using the Resource API kunit: Add example parameterized test with direct dynamic parameter array setup Documentation: kunit: Document new parameterized test features Documentation/dev-tools/kunit/usage.rst | 342 +++++++++++++++++++++++- drivers/gpu/drm/xe/tests/xe_pci.c | 14 +- drivers/gpu/drm/xe/tests/xe_pci_test.h | 9 +- include/kunit/test.h | 95 ++++++- kernel/kcsan/kcsan_test.c | 2 +- lib/kunit/kunit-example-test.c | 217 +++++++++++++++ lib/kunit/test.c | 94 +++++-- rust/kernel/kunit.rs | 4 + 8 files changed, 740 insertions(+), 37 deletions(-) -- 2.51.0.261.g7ce5a0a67e-goog

1 month, 2 weeks

3
9
0 0

[PATCH bpf-next v3 1/2] bpf/helpers: bpf_strnstr: Exact match length

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> strnstr should not treat the ending '\0' of s2 as a matching character, otherwise the parameter 'len' will be meaningless, for example: 1. bpf_strnstr("openat", "open", 4) = -ENOENT 2. bpf_strnstr("openat", "open", 5) = 0 This patch makes (1) return 0, indicating a successful match. Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- kernel/bpf/helpers.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 401b4932cc49..ced7132980fe 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -3672,10 +3672,12 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len guard(pagefault)(); for (i = 0; i < XATTR_SIZE_MAX; i++) { - for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) { + for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) { __get_kernel_nofault(&c2, s2__ign + j, char, err_out); if (c2 == '\0') return i; + if (i + j == len) + break; __get_kernel_nofault(&c1, s1__ign + j, char, err_out); if (c1 == '\0') return -ENOENT; -- 2.51.0

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next v3 2/2] selftests/bpf: Add tests for bpf_strnstr

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Add two tests for bpf_strnstr(): bpf_strnstr("", "", 0) = 0 bpf_strnstr("hello world", "hello", 5) = 0 Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..1b56bd5860e9 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -30,7 +30,9 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } -__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } __test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } -- 2.51.0

1 month, 2 weeks

2
1
0 0

[PATCH] selftests/bpf: Fix bpf_prog_detach2 usage in test_lirc_mode2

by Ricardo B. Marlière

Commit e9fc3ce99b34 ("libbpf: Streamline error reporting for high-level APIs") redefined the way that bpf_prog_detach2() returns. Therefore, adapt the usage in test_lirc_mode2_user.c. Signed-off-by: Ricardo B. Marlière <rbm(a)suse.com> --- tools/testing/selftests/bpf/test_lirc_mode2_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index 4694422aa76c36faa4afa8832e56040547dc7547..88e4aeab21b7bc37665d6fd3959006c5a83a81c9 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -74,7 +74,7 @@ int main(int argc, char **argv) /* Let's try detach it before it was ever attached */ ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2); - if (ret != -1 || errno != ENOENT) { + if (ret != -ENOENT) { printf("bpf_prog_detach2 not attached should fail: %m\n"); return 1; } --- base-commit: 5b6d6fe1ca7b712c74f78426bb23c465fd34b322 change-id: 20250828-selftests-bpf-45ccf9c6e7d4 Best regards, -- Ricardo B. Marlière <rbm(a)suse.com>

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next] selftests/bpf: Fix the issue where the error code is 0

by Feng Yang

From: Feng Yang <yangfeng(a)kylinos.cn> The error message printed here only uses the previous err value, which results in it being printed as 0. When bpf_map__attach_struct_ops encounters an error, it uses libbpf_err_ptr(err) to set errno = -err and returns NULL. Therefore, strerror(errno) can be used to fix this issue. Fix before: run_subtest:FAIL:1019 bpf_map__attach_struct_ops failed for map pro_epilogue: err=0 Fix after: run_subtest:FAIL:1019 bpf_map__attach_struct_ops failed for map pro_epilogue: Bad file descriptor Signed-off-by: Feng Yang <yangfeng(a)kylinos.cn> --- tools/testing/selftests/bpf/test_loader.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index f361c8aa1daf..686a7d7f87b1 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -1008,8 +1008,8 @@ void run_subtest(struct test_loader *tester, } link = bpf_map__attach_struct_ops(map); if (!link) { - PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: err=%d\n", - bpf_map__name(map), err); + PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: %s\n", + bpf_map__name(map), strerror(errno)); goto tobj_cleanup; } links[links_cnt++] = link; -- 2.27.0

1 month, 2 weeks

2
1
0 0

[PATCH bpf-next v3 0/2] Fix bpf_strnstr len error

by Rong Tao

Fix bpf_strnstr() wrong 'len' parameter, bpf_strnstr("open", "open", 4) should return 0 instead of -ENOENT. Rong Tao (2): bpf/helpers: bpf_strnstr: Exact match length selftests/bpf: Add tests for bpf_strnstr kernel/bpf/helpers.c | 4 +++- tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) --- v3: Fix selftests/bpf error in v2, sorry about that; v2: Follow Andrii Nakryiko's advise, fix the 'wrong fix'; https://lore.kernel.org/lkml/tencent_DF4DA83EEBFB9246E5E3357BB40911CCA005@q… v1: https://lore.kernel.org/lkml/tencent_65E5988AD52BEC280D22964189505CD6ED06@q… -- 2.51.0

1 month, 2 weeks

1
0
0 0

[PATCH] selftests/filesystems: Skip file_stressor test on NFS root

by Anders Roxell

The file_stressor test creates directories in the root filesystem and performs mount namespace operations that can fail on NFS root filesystems due to network filesystem restrictions and permission limitations. Add NFS root filesystem detection using statfs() to check for NFS_SUPER_MAGIC and skip the test gracefully when running on NFS root, providing a clear message about why the test was skipped. This prevents spurious test failures in CI environments that use NFS root while preserving the test's ability to catch SLAB_TYPESAFE_BY_RCU related bugs on local filesystems where it can run properly. Signed-off-by: Anders Roxell <anders.roxell(a)linaro.org> --- tools/testing/selftests/filesystems/file_stressor.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/filesystems/file_stressor.c b/tools/testing/selftests/filesystems/file_stressor.c index 01dd89f8e52f..b9dfe0b6b125 100644 --- a/tools/testing/selftests/filesystems/file_stressor.c +++ b/tools/testing/selftests/filesystems/file_stressor.c @@ -10,12 +10,14 @@ #include <string.h> #include <sys/stat.h> #include <sys/mount.h> +#include <sys/vfs.h> #include <unistd.h> #include "../kselftest_harness.h" #include <linux/types.h> #include <linux/mount.h> +#include <linux/magic.h> #include <sys/syscall.h> static inline int sys_fsopen(const char *fsname, unsigned int flags) @@ -58,8 +60,13 @@ FIXTURE(file_stressor) { FIXTURE_SETUP(file_stressor) { + struct statfs sfs; int fd_context; + /* Skip test if root filesystem is NFS */ + if (statfs("/", &sfs) == 0 && sfs.f_type == NFS_SUPER_MAGIC) + SKIP(return, "Test requires local root filesystem, NFS root detected"); + ASSERT_EQ(unshare(CLONE_NEWNS), 0); ASSERT_EQ(mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL), 0); ASSERT_EQ(mkdir("/slab_typesafe_by_rcu", 0755), 0); -- 2.50.1

1 month, 2 weeks

1
0
0 0

[PATCH bpf-next v5] selftests/bpf: Add LPM trie microbenchmarks

by Matt Fleming

From: Matt Fleming <mfleming(a)cloudflare.com> Add benchmarks for the standard set of operations: LOOKUP, INSERT, UPDATE, DELETE. Also include benchmarks to measure the overhead of the bench framework itself (NOOP) as well as the overhead of generating keys (BASELINE). Lastly, this includes a benchmark for FREE (trie_free()) which is known to have terrible performance for maps with many entries. Benchmarks operate on tries without gaps in the key range, i.e. each test begins or ends with a trie with valid keys in the range [0, nr_entries). This is intended to cause maximum branching when traversing the trie. LOOKUP, UPDATE, DELETE, and FREE fill a BPF LPM trie from userspace using bpf_map_update_batch() and run the corresponding benchmark operation via bpf_loop(). INSERT starts with an empty map and fills it kernel-side from bpf_loop(). FREE records the time to free a filled LPM trie by attaching and destroying a BPF prog. NOOP measures the overhead of the test harness by running an empty function with bpf_loop(). BASELINE is similar to NOOP except that the function generates a key. Each operation runs 10,000 times using bpf_loop(). Note that this value is intentionally independent of the number of entries in the LPM trie so that the stability of the results isn't affected by the number of entries. For those benchmarks that need to reset the LPM trie once it's full (INSERT) or empty (DELETE), throughput and latency results are scaled by the fraction of a second the operation actually ran to ignore any time spent reinitialising the trie. By default, benchmarks run using sequential keys in the range [0, nr_entries). BASELINE, LOOKUP, and UPDATE can use random keys via the --random parameter but beware there is a runtime cost involved in generating random keys. Other benchmarks are prohibited from using random keys because it can skew the results, e.g. when inserting an existing key or deleting a missing one. All measurements are recorded from within the kernel to eliminate syscall overhead. Most benchmarks run an XDP program to generate stats but FREE needs to collect latencies using fentry/fexit on map_free_deferred() because it's not possible to use fentry directly on lpm_trie.c since commit c83508da5620 ("bpf: Avoid deadlock caused by nested kprobe and fentry bpf programs") and there's no way to create/destroy a map from within an XDP program. Here is example output from an AMD EPYC 9684X 96-Core machine for each of the benchmarks using a trie with 10K entries and a 32-bit prefix length, e.g. $ ./bench lpm-trie-$op \ --prefix_len=32 \ --producers=1 \ --nr_entries=10000 noop: throughput 74.417 ± 0.032 M ops/s ( 74.417M ops/prod), latency 13.438 ns/op baseline: throughput 70.107 ± 0.171 M ops/s ( 70.107M ops/prod), latency 14.264 ns/op lookup: throughput 8.467 ± 0.047 M ops/s ( 8.467M ops/prod), latency 118.109 ns/op insert: throughput 2.440 ± 0.015 M ops/s ( 2.440M ops/prod), latency 409.290 ns/op update: throughput 2.806 ± 0.042 M ops/s ( 2.806M ops/prod), latency 356.322 ns/op delete: throughput 4.625 ± 0.011 M ops/s ( 4.625M ops/prod), latency 215.613 ns/op free: throughput 0.578 ± 0.006 K ops/s ( 0.578K ops/prod), latency 1.730 ms/op And the same benchmarks using random keys: $ ./bench lpm-trie-$op \ --prefix_len=32 \ --producers=1 \ --nr_entries=10000 \ --random noop: throughput 74.259 ± 0.335 M ops/s ( 74.259M ops/prod), latency 13.466 ns/op baseline: throughput 35.150 ± 0.144 M ops/s ( 35.150M ops/prod), latency 28.450 ns/op lookup: throughput 7.119 ± 0.048 M ops/s ( 7.119M ops/prod), latency 140.469 ns/op insert: N/A update: throughput 2.736 ± 0.012 M ops/s ( 2.736M ops/prod), latency 365.523 ns/op delete: N/A free: N/A Signed-off-by: Matt Fleming <mfleming(a)cloudflare.com> Signed-off-by: Jesper Dangaard Brouer <hawk(a)kernel.org> --- Changes in v5: - Fix uninitialised read of blackbox variable to avoid gcc-bpf CI failure Changes in v4: - Incorporate Jesper's NOOP and BASELINE benchmarks - Remove use of double underscore naming - Add --random parameter to use random keys (linear by default) - Fractional second reporting to make delete op times accurate - Check return value of bpf_map_update_elem() - Make latency_free_start a global var and remove hashmap Changes in v3: - Replace BPF_CORE_READ() with BPF_CORE_READ_STR_INTO() to avoid gcc-bpf CI build failure Changes in v2: - Add Jesper's Tested-by and Revewied-by tags - Remove use of atomic_*() in favour of __sync_add_and_fetch() - Use a file-local 'deleted_entries' in the DELETE op benchmark and add a comment explaining why non-atomic accesses are safe. - Bump 'hits' with the number of bpf_loop() loops actually executed tools/testing/selftests/bpf/Makefile | 2 + tools/testing/selftests/bpf/bench.c | 16 + tools/testing/selftests/bpf/bench.h | 1 + .../selftests/bpf/benchs/bench_lpm_trie_map.c | 555 ++++++++++++++++++ tools/testing/selftests/bpf/progs/lpm_trie.h | 30 + .../selftests/bpf/progs/lpm_trie_bench.c | 230 ++++++++ .../selftests/bpf/progs/lpm_trie_map.c | 19 + 7 files changed, 853 insertions(+) create mode 100644 tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie.h create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie_bench.c create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie_map.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4863106034df..c6555497372f 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -816,6 +816,7 @@ $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h $(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h $(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h $(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h +$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ @@ -837,6 +838,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_htab_mem.o \ $(OUTPUT)/bench_bpf_crypto.o \ $(OUTPUT)/bench_sockmap.o \ + $(OUTPUT)/bench_lpm_trie_map.o \ # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index ddd73d06a1eb..23ed6feee0d9 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -284,6 +284,7 @@ extern struct argp bench_htab_mem_argp; extern struct argp bench_trigger_batch_argp; extern struct argp bench_crypto_argp; extern struct argp bench_sockmap_argp; +extern struct argp bench_lpm_trie_map_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -299,6 +300,7 @@ static const struct argp_child bench_parsers[] = { { &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 }, { &bench_crypto_argp, 0, "bpf crypto benchmark", 0 }, { &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 }, + { &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 }, {}, }; @@ -558,6 +560,13 @@ extern const struct bench bench_htab_mem; extern const struct bench bench_crypto_encrypt; extern const struct bench bench_crypto_decrypt; extern const struct bench bench_sockmap; +extern const struct bench bench_lpm_trie_noop; +extern const struct bench bench_lpm_trie_baseline; +extern const struct bench bench_lpm_trie_lookup; +extern const struct bench bench_lpm_trie_insert; +extern const struct bench bench_lpm_trie_update; +extern const struct bench bench_lpm_trie_delete; +extern const struct bench bench_lpm_trie_free; static const struct bench *benchs[] = { &bench_count_global, @@ -625,6 +634,13 @@ static const struct bench *benchs[] = { &bench_crypto_encrypt, &bench_crypto_decrypt, &bench_sockmap, + &bench_lpm_trie_noop, + &bench_lpm_trie_baseline, + &bench_lpm_trie_lookup, + &bench_lpm_trie_insert, + &bench_lpm_trie_update, + &bench_lpm_trie_delete, + &bench_lpm_trie_free, }; static void find_benchmark(void) diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 005c401b3e22..bea323820ffb 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -46,6 +46,7 @@ struct bench_res { unsigned long gp_ns; unsigned long gp_ct; unsigned int stime; + unsigned long duration_ns; }; struct bench { diff --git a/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c new file mode 100644 index 000000000000..246f6cb3387d --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +/* + * All of these benchmarks operate on tries with keys in the range + * [0, args.nr_entries), i.e. there are no gaps or partially filled + * branches of the trie for any key < args.nr_entries. + * + * This gives an idea of worst-case behaviour. + */ + +#include <argp.h> +#include <linux/time64.h> +#include <linux/if_ether.h> +#include "lpm_trie_bench.skel.h" +#include "lpm_trie_map.skel.h" +#include "bench.h" +#include "testing_helpers.h" +#include "progs/lpm_trie.h" + +static struct ctx { + struct lpm_trie_bench *bench; +} ctx; + +static struct { + __u32 nr_entries; + __u32 prefixlen; + bool random; +} args = { + .nr_entries = 0, + .prefixlen = 32, + .random = false, +}; + +enum { + ARG_NR_ENTRIES = 9000, + ARG_PREFIX_LEN, + ARG_RANDOM, +}; + +static const struct argp_option opts[] = { + { "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0, + "Number of unique entries in the LPM trie" }, + { "prefix_len", ARG_PREFIX_LEN, "PREFIX_LEN", 0, + "Number of prefix bits to use in the LPM trie" }, + { "random", ARG_RANDOM, NULL, 0, "Access random keys during op" }, + {}, +}; + +static error_t lpm_parse_arg(int key, char *arg, struct argp_state *state) +{ + long ret; + + switch (key) { + case ARG_NR_ENTRIES: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid nr_entries count."); + argp_usage(state); + } + args.nr_entries = ret; + break; + case ARG_PREFIX_LEN: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid prefix_len value."); + argp_usage(state); + } + args.prefixlen = ret; + break; + case ARG_RANDOM: + args.random = true; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +const struct argp bench_lpm_trie_map_argp = { + .options = opts, + .parser = lpm_parse_arg, +}; + +static void validate_common(void) +{ + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer\n"); + exit(1); + } + + if (args.nr_entries == 0) { + fprintf(stderr, "Missing --nr_entries parameter\n"); + exit(1); + } + + if ((1UL << args.prefixlen) < args.nr_entries) { + fprintf(stderr, "prefix_len value too small for nr_entries\n"); + exit(1); + } +} + +static void lpm_insert_validate(void) +{ + validate_common(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-insert requires a single producer\n"); + exit(1); + } + + if (args.random) { + fprintf(stderr, "lpm-trie-insert does not support --random\n"); + exit(1); + } +} + +static void lpm_delete_validate(void) +{ + validate_common(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-delete requires a single producer\n"); + exit(1); + } + + if (args.random) { + fprintf(stderr, "lpm-trie-delete does not support --random\n"); + exit(1); + } +} + +static void lpm_free_validate(void) +{ + validate_common(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-free requires a single producer\n"); + exit(1); + } + + if (args.random) { + fprintf(stderr, "lpm-trie-free does not support --random\n"); + exit(1); + } +} + +static struct trie_key *keys; +static __u32 *vals; + +static void fill_map(int map_fd) +{ + int err; + + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + err = bpf_map_update_batch(map_fd, keys, vals, &args.nr_entries, &opts); + if (err) { + fprintf(stderr, "failed to batch update keys to map: %d\n", + -err); + exit(1); + } +} + +static void empty_map(int map_fd) +{ + int err; + + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + err = bpf_map_delete_batch(map_fd, keys, &args.nr_entries, &opts); + if (err) { + fprintf(stderr, "failed to batch delete keys for map: %d\n", + -err); + exit(1); + } +} + +static void attach_prog(void) +{ + int i; + + ctx.bench = lpm_trie_bench__open_and_load(); + if (!ctx.bench) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + ctx.bench->bss->nr_entries = args.nr_entries; + ctx.bench->bss->prefixlen = args.prefixlen; + ctx.bench->bss->random = args.random; + + if (lpm_trie_bench__attach(ctx.bench)) { + fprintf(stderr, "failed to attach skeleton\n"); + exit(1); + } + + keys = calloc(args.nr_entries, sizeof(*keys)); + vals = calloc(args.nr_entries, sizeof(*vals)); + + for (i = 0; i < args.nr_entries; i++) { + struct trie_key *k = &keys[i]; + __u32 *v = &vals[i]; + + k->prefixlen = args.prefixlen; + k->data = i; + *v = 1; + } +} + +static void attach_prog_and_fill_map(void) +{ + int fd; + + attach_prog(); + + fd = bpf_map__fd(ctx.bench->maps.trie_map); + fill_map(fd); +} + +static void lpm_noop_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_NOOP; +} + +static void lpm_baseline_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_BASELINE; +} + +static void lpm_lookup_setup(void) +{ + attach_prog_and_fill_map(); + ctx.bench->bss->op = LPM_OP_LOOKUP; +} + +static void lpm_insert_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_INSERT; +} + +static void lpm_update_setup(void) +{ + attach_prog_and_fill_map(); + ctx.bench->bss->op = LPM_OP_UPDATE; +} + +static void lpm_delete_setup(void) +{ + attach_prog_and_fill_map(); + ctx.bench->bss->op = LPM_OP_DELETE; +} + +static void lpm_free_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_FREE; +} + +static void lpm_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.bench->bss->hits, 0); + res->duration_ns = atomic_swap(&ctx.bench->bss->duration_ns, 0); +} + +static void bench_reinit_map(void) +{ + int fd = bpf_map__fd(ctx.bench->maps.trie_map); + + switch (ctx.bench->bss->op) { + case LPM_OP_INSERT: + /* trie_map needs to be emptied */ + empty_map(fd); + break; + case LPM_OP_DELETE: + /* trie_map needs to be refilled */ + fill_map(fd); + break; + default: + fprintf(stderr, "Unexpected REINIT return code for op %d\n", + ctx.bench->bss->op); + exit(1); + } +} + +/* For NOOP, BASELINE, LOOKUP, INSERT, UPDATE, and DELETE */ +static void *lpm_producer(void *unused __always_unused) +{ + int err; + char in[ETH_HLEN]; /* unused */ + + LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = in, + .data_size_in = sizeof(in), .repeat = 1, ); + + while (true) { + int fd = bpf_program__fd(ctx.bench->progs.run_bench); + err = bpf_prog_test_run_opts(fd, &opts); + if (err) { + fprintf(stderr, "failed to run BPF prog: %d\n", err); + exit(1); + } + + /* Check for kernel error code */ + if ((int)opts.retval < 0) { + fprintf(stderr, "BPF prog returned error: %d\n", + opts.retval); + exit(1); + } + + switch (opts.retval) { + case LPM_BENCH_SUCCESS: + break; + case LPM_BENCH_REINIT_MAP: + bench_reinit_map(); + break; + default: + fprintf(stderr, "Unexpected BPF prog return code %d for op %d\n", + opts.retval, ctx.bench->bss->op); + exit(1); + } + } + + return NULL; +} + +static void *lpm_free_producer(void *unused __always_unused) +{ + while (true) { + struct lpm_trie_map *skel; + + skel = lpm_trie_map__open_and_load(); + if (!skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + fill_map(bpf_map__fd(skel->maps.trie_free_map)); + lpm_trie_map__destroy(skel); + } + + return NULL; +} + +/* + * The standard bench op_report_*() functions assume measurements are + * taken over a 1-second interval but operations that modify the map + * (INSERT, DELETE, and FREE) cannot run indefinitely without + * "resetting" the map to the initial state. Depending on the size of + * the map, this likely needs to happen before the 1-second timer fires. + * + * Calculate the fraction of a second over which the op measurement was + * taken (to ignore any time spent doing the reset) and report the + * throughput results per second. + */ +static void frac_second_report_progress(int iter, struct bench_res *res, + long delta_ns, double rate_divisor, + char rate) +{ + double hits_per_sec, hits_per_prod; + + hits_per_sec = res->hits / rate_divisor / + (res->duration_ns / (double)NSEC_PER_SEC); + hits_per_prod = hits_per_sec / env.producer_cnt; + + printf("Iter %3d (%7.3lfus): ", iter, + (delta_ns - NSEC_PER_SEC) / 1000.0); + printf("hits %8.3lf%c/s (%7.3lf%c/prod)\n", hits_per_sec, rate, + hits_per_prod, rate); +} + +static void frac_second_report_final(struct bench_res res[], int res_cnt, + double lat_divisor, double rate_divisor, + char rate, const char *unit) +{ + double hits_mean = 0.0, hits_stddev = 0.0; + double latency = 0.0; + int i; + + for (i = 0; i < res_cnt; i++) { + double val = res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_mean += val / (0.0 + res_cnt); + latency += res[i].duration_ns / res[i].hits / (0.0 + res_cnt); + } + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) { + double val = + res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_stddev += (hits_mean - val) * (hits_mean - val) / + (res_cnt - 1.0); + } + + hits_stddev = sqrt(hits_stddev); + } + printf("Summary: throughput %8.3lf \u00B1 %5.3lf %c ops/s (%7.3lf%c ops/prod), ", + hits_mean, hits_stddev, rate, hits_mean / env.producer_cnt, + rate); + printf("latency %8.3lf %s/op\n", + latency / lat_divisor / env.producer_cnt, unit); +} + +static void insert_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double rate_divisor = 1000000.0; + char rate = 'M'; + + frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate); +} + +static void delete_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double rate_divisor = 1000000.0; + char rate = 'M'; + + frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate); +} + +static void free_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double rate_divisor = 1000.0; + char rate = 'K'; + + frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate); +} + +static void insert_ops_report_final(struct bench_res res[], int res_cnt) +{ + double lat_divisor = 1.0; + double rate_divisor = 1000000.0; + const char *unit = "ns"; + char rate = 'M'; + + frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate, + unit); +} + +static void delete_ops_report_final(struct bench_res res[], int res_cnt) +{ + double lat_divisor = 1.0; + double rate_divisor = 1000000.0; + const char *unit = "ns"; + char rate = 'M'; + + frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate, + unit); +} + +static void free_ops_report_final(struct bench_res res[], int res_cnt) +{ + double lat_divisor = 1000000.0; + double rate_divisor = 1000.0; + const char *unit = "ms"; + char rate = 'K'; + + frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate, + unit); +} + +/* noop bench measures harness-overhead */ +const struct bench bench_lpm_trie_noop = { + .name = "lpm-trie-noop", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_noop_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* baseline overhead for lookup and update */ +const struct bench bench_lpm_trie_baseline = { + .name = "lpm-trie-baseline", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_baseline_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* measure cost of doing a lookup on existing entries in a full trie */ +const struct bench bench_lpm_trie_lookup = { + .name = "lpm-trie-lookup", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_lookup_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* measure cost of inserting new entries into an empty trie */ +const struct bench bench_lpm_trie_insert = { + .name = "lpm-trie-insert", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_insert_validate, + .setup = lpm_insert_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = insert_ops_report_progress, + .report_final = insert_ops_report_final, +}; + +/* measure cost of updating existing entries in a full trie */ +const struct bench bench_lpm_trie_update = { + .name = "lpm-trie-update", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_update_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* measure cost of deleting existing entries from a full trie */ +const struct bench bench_lpm_trie_delete = { + .name = "lpm-trie-delete", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_delete_validate, + .setup = lpm_delete_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = delete_ops_report_progress, + .report_final = delete_ops_report_final, +}; + +/* measure cost of freeing a full trie */ +const struct bench bench_lpm_trie_free = { + .name = "lpm-trie-free", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_free_validate, + .setup = lpm_free_setup, + .producer_thread = lpm_free_producer, + .measure = lpm_measure, + .report_progress = free_ops_report_progress, + .report_final = free_ops_report_final, +}; diff --git a/tools/testing/selftests/bpf/progs/lpm_trie.h b/tools/testing/selftests/bpf/progs/lpm_trie.h new file mode 100644 index 000000000000..76aa5821807f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PROGS_LPM_TRIE_H +#define __PROGS_LPM_TRIE_H + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +/* Benchmark operations */ +enum { + LPM_OP_NOOP = 0, + LPM_OP_BASELINE, + LPM_OP_LOOKUP, + LPM_OP_INSERT, + LPM_OP_UPDATE, + LPM_OP_DELETE, + LPM_OP_FREE +}; + +/* + * Return values from run_bench. + * + * Negative values are also allowed and represent kernel error codes. + */ +#define LPM_BENCH_SUCCESS 0 +#define LPM_BENCH_REINIT_MAP 1 /* Reset trie to initial state for current op */ + +#endif diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_bench.c b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c new file mode 100644 index 000000000000..1b48c67b02ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +#include <vmlinux.h> +#include <errno.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" +#include "bpf_atomic.h" +#include "progs/lpm_trie.h" + +#define BPF_OBJ_NAME_LEN 16U +#define MAX_ENTRIES 100000000 +#define NR_LOOPS 10000 + +char _license[] SEC("license") = "GPL"; + +/* Filled by userspace. See fill_map() in bench_lpm_trie_map.c */ +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_map SEC(".maps"); + +long hits; +long duration_ns; + +/* Configured from userspace */ +__u32 nr_entries; +__u32 prefixlen; +bool random; +__u8 op; + +static __u64 latency_free_start; + +SEC("fentry/bpf_map_free_deferred") +int BPF_PROG(trie_free_entry, struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + char name[BPF_OBJ_NAME_LEN]; + u32 map_type; + + map_type = BPF_CORE_READ(map, map_type); + if (map_type != BPF_MAP_TYPE_LPM_TRIE) + return 0; + + /* + * Ideally we'd have access to the map ID but that's already + * freed before we enter trie_free(). + */ + BPF_CORE_READ_STR_INTO(&name, map, name); + if (bpf_strncmp(name, BPF_OBJ_NAME_LEN, "trie_free_map")) + return 0; + + latency_free_start = bpf_ktime_get_ns(); + + return 0; +} + +SEC("fexit/bpf_map_free_deferred") +int BPF_PROG(trie_free_exit, struct work_struct *work) +{ + __u64 val; + + if (!latency_free_start) + return 0; + + val = bpf_ktime_get_ns() - latency_free_start; + latency_free_start = 0; + + __sync_add_and_fetch(&duration_ns, val); + __sync_add_and_fetch(&hits, 1); + + return 0; +} + +static __u32 cur_key; + +static __always_inline void generate_key(struct trie_key *key) +{ + key->prefixlen = prefixlen; + + if (random) + key->data = bpf_get_prandom_u32() % nr_entries; + else + key->data = cur_key++ % nr_entries; +} + +static int noop(__u32 index, __u32 *unused) +{ + return 0; +} + +static int baseline(__u32 index, __u32 *unused) +{ + struct trie_key key; + __u32 blackbox = 0; + + generate_key(&key); + /* Avoid compiler optimizing out the modulo */ + barrier_var(blackbox); + blackbox = READ_ONCE(key.data); + + return 0; +} + +static int lookup(__u32 index, int *retval) +{ + struct trie_key key; + + generate_key(&key); + if (!bpf_map_lookup_elem(&trie_map, &key)) { + *retval = -ENOENT; + return 1; + } + + return 0; +} + +static int insert(__u32 index, int *retval) +{ + struct trie_key key; + u32 val = 1; + int err; + + generate_key(&key); + err = bpf_map_update_elem(&trie_map, &key, &val, BPF_NOEXIST); + if (err) { + *retval = err; + return 1; + } + + /* Is this the last entry? */ + if (key.data == nr_entries - 1) { + /* For atomicity concerns, see the comment in delete() */ + *retval = LPM_BENCH_REINIT_MAP; + return 1; + } + + return 0; +} + +static int update(__u32 index, int *retval) +{ + struct trie_key key; + u32 val = 1; + int err; + + generate_key(&key); + err = bpf_map_update_elem(&trie_map, &key, &val, BPF_EXIST); + if (err) { + *retval = err; + return 1; + } + + return 0; +} + +static int delete(__u32 index, int *retval) +{ + struct trie_key key; + int err; + + generate_key(&key); + err = bpf_map_delete_elem(&trie_map, &key); + if (err) { + *retval = err; + return 1; + } + + /* Do we need to refill the map? */ + if (key.data == nr_entries - 1) { + /* + * Atomicity isn't required because DELETE only supports + * one producer running concurrently. What we need is a + * way to track how many entries have been deleted from + * the trie between consecutive invocations of the BPF + * prog because a single bpf_loop() call might not + * delete all entries, e.g. when NR_LOOPS < nr_entries. + */ + *retval = LPM_BENCH_REINIT_MAP; + return 1; + } + + return 0; +} + +SEC("xdp") +int BPF_PROG(run_bench) +{ + int err = LPM_BENCH_SUCCESS; + u64 start, delta; + int loops; + + start = bpf_ktime_get_ns(); + + switch (op) { + case LPM_OP_NOOP: + loops = bpf_loop(NR_LOOPS, noop, NULL, 0); + break; + case LPM_OP_BASELINE: + loops = bpf_loop(NR_LOOPS, baseline, NULL, 0); + break; + case LPM_OP_LOOKUP: + loops = bpf_loop(NR_LOOPS, lookup, &err, 0); + break; + case LPM_OP_INSERT: + loops = bpf_loop(NR_LOOPS, insert, &err, 0); + break; + case LPM_OP_UPDATE: + loops = bpf_loop(NR_LOOPS, update, &err, 0); + break; + case LPM_OP_DELETE: + loops = bpf_loop(NR_LOOPS, delete, &err, 0); + break; + default: + bpf_printk("invalid benchmark operation\n"); + return -1; + } + + delta = bpf_ktime_get_ns() - start; + + __sync_add_and_fetch(&duration_ns, delta); + __sync_add_and_fetch(&hits, loops); + + return err; +} diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_map.c b/tools/testing/selftests/bpf/progs/lpm_trie_map.c new file mode 100644 index 000000000000..2ab43e2cd6c6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_map.c @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_ENTRIES 100000000 + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_free_map SEC(".maps"); -- 2.34.1

1 month, 2 weeks

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror