April 2019 - Linux-kselftest-mirror

[PATCH RFC 1/2] Add polling support to pidfd

by Joel Fernandes (Google)

pidfd are /proc/pid directory file descriptors referring to a task group leader. Android low memory killer (LMK) needs pidfd polling support to replace code that currently checks for existence of /proc/pid for knowing a process that is signalled to be killed has died, which is both racy and slow. The pidfd poll approach is race-free, and also allows the LMK to do other things (such as by polling on other fds) while awaiting the process being killed to die. It prevents a situation where a PID is reused between when LMK sends a kill signal and checks for existence of the PID, since the wrong PID is now possibly checked for existence. In this patch, we follow the same mechanism used uhen the parent of the task group is to be notified, that is when the tasks waiting on a poll of pidfd are also awakened. We have decided to include the waitqueue in struct pid for the following reasons: 1. The wait queue has to survive for the lifetime of the poll. Including it in task_struct would not be option in this case because the task can be reaped and destroyed before the poll returns. 2. By including the struct pid for the waitqueue means that during de_exec, the thread doing de_thread() automatically gets the new waitqueue/pid even though its task_struct is different. Appropriate test cases are added in the second patch to provide coverage of all the cases the patch is handling. Andy had a similar patch [1] in the past which was a good reference however this patch tries to handle different situations properly related to thread group existence, and how/where it notifies. And also solves other bugs (existence of taks_struct). Daniel had a similar patch [2] recently which this patch supercedes. [1] https://lore.kernel.org/patchwork/patch/345098/ [2] https://lore.kernel.org/lkml/20181029175322.189042-1-dancol@google.com/ Cc: luto(a)amacapital.net Cc: rostedt(a)goodmis.org Cc: dancol(a)google.com Cc: christian(a)brauner.io Cc: jannh(a)google.com Cc: surenb(a)google.com Cc: torvalds(a)linux-foundation.org Co-developed-by: Daniel Colascione <dancol(a)google.com> Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org> --- fs/proc/base.c | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/pid.h | 3 +++ kernel/exit.c | 1 - kernel/pid.c | 2 ++ kernel/signal.c | 14 ++++++++++++++ 5 files changed, 58 insertions(+), 1 deletion(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 6a803a0b75df..879900082647 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3069,8 +3069,47 @@ static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } +static unsigned int proc_tgid_base_poll(struct file *file, struct poll_table_struct *pts) +{ + int poll_flags = 0; + struct task_struct *task; + struct pid *pid; + + task = get_proc_task(file->f_path.dentry->d_inode); + + WARN_ON_ONCE(task && !thread_group_leader(task)); + + /* + * tasklist_lock must be held because to avoid racing with + * changes in exit_state and wake up. Basically to avoid: + * + * P0: read exit_state = 0 + * P1: write exit_state = EXIT_DEAD + * P1: Do a wake up - wq is empty, so do nothing + * P0: Queue for polling - wait forever. + */ + read_lock(&tasklist_lock); + if (!task) + poll_flags = POLLIN | POLLRDNORM | POLLERR; + else if (task->exit_state == EXIT_DEAD) + poll_flags = POLLIN | POLLRDNORM; + else if (task->exit_state == EXIT_ZOMBIE && thread_group_empty(task)) + poll_flags = POLLIN | POLLRDNORM; + + if (!poll_flags) { + pid = proc_pid(file->f_path.dentry->d_inode); + poll_wait(file, &pid->wait_pidfd, pts); + } + read_unlock(&tasklist_lock); + + if (task) + put_task_struct(task); + return poll_flags; +} + static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, + .poll = proc_tgid_base_poll, .iterate_shared = proc_tgid_base_readdir, .llseek = generic_file_llseek, }; diff --git a/include/linux/pid.h b/include/linux/pid.h index b6f4ba16065a..2e0dcbc6d14e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -3,6 +3,7 @@ #define _LINUX_PID_H #include <linux/rculist.h> +#include <linux/wait.h> enum pid_type { @@ -60,6 +61,8 @@ struct pid unsigned int level; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; + /* wait queue for pidfd pollers */ + wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[1]; }; diff --git a/kernel/exit.c b/kernel/exit.c index 2166c2d92ddc..c386ec52687d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -181,7 +181,6 @@ static void delayed_put_task_struct(struct rcu_head *rhp) put_task_struct(tsk); } - void release_task(struct task_struct *p) { struct task_struct *leader; diff --git a/kernel/pid.c b/kernel/pid.c index 20881598bdfa..5c90c239242f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -214,6 +214,8 @@ struct pid *alloc_pid(struct pid_namespace *ns) for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); + init_waitqueue_head(&pid->wait_pidfd); + upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) diff --git a/kernel/signal.c b/kernel/signal.c index f98448cf2def..e3781703ef7e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1800,6 +1800,17 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) return ret; } +static void do_wakeup_pidfd_pollers(struct task_struct *task) +{ + struct pid *pid; + + lockdep_assert_held(&tasklist_lock); + + pid = get_task_pid(task, PIDTYPE_PID); + wake_up_all(&pid->wait_pidfd); + put_pid(pid); +} + /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. @@ -1823,6 +1834,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig) BUG_ON(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); + /* Wake up all pidfd waiters */ + do_wakeup_pidfd_pollers(tsk); + if (sig != SIGCHLD) { /* * This is only possible if parent == real_parent. -- 2.21.0.392.gf8f6787159e-goog

5 years

11
64
0 0

[PATCH 0/6] selftests: Move test output to diagnostic lines

by Kees Cook

This refactors the selftest Makefiles to extract the test running logic to be reused between "run_tests" and "emit_tests", while also fixing up the test output to be TAP version 13 compliant: - added "plan" line - fixed result line syntax - moved all test output to be "# "-prefixed as TAP "diagnostic" lines The prefixing code includes a fallback mode for limited execution environments. -Kees Kees Cook (6): selftests: Extract single-test shell logic from lib.mk selftests: Use runner.sh for emit targets selftests: Extract logic for multiple test runs selftests/runner: Add plan line and fix result line syntax selftests/runner: Distinguish between missing and non-executable selftests: Move test output to diagnostic lines tools/testing/selftests/.gitignore | 1 - tools/testing/selftests/Makefile | 18 +++-- tools/testing/selftests/kselftest/prefix.pl | 23 ++++++ tools/testing/selftests/kselftest/runner.sh | 80 +++++++++++++++++++++ tools/testing/selftests/lib.mk | 61 +++------------- 5 files changed, 119 insertions(+), 64 deletions(-) create mode 100755 tools/testing/selftests/kselftest/prefix.pl create mode 100644 tools/testing/selftests/kselftest/runner.sh -- 2.17.1

5 years

2
13
0 0

next-20190423 kselftest results

by ci_notify＠linaro.org

Summary ------------------------------------------------------------------------ kernel: 5.1.0-rc6 git repo: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git git branch: master git commit: 76c938fcaa4b4a5d8f05fa907925d5043834964e git describe: next-20190423 Test details: https://qa-reports.linaro.org/lkft/linux-next-oe/build/next-20190423 Regressions (compared to build next-20190418) ------------------------------------------------------------------------ hi6220-hikey - arm64: kselftest: * membarrier_membarrier_test qemu_arm: kselftest: * bpf_test_sock_addr.sh * membarrier_membarrier_test * net_run_netsocktests * net_tls * pidfd_pidfd_test * rseq_basic_percpu_ops_test * rseq_basic_test * rseq_param_test * rseq_param_test_benchmark * rseq_param_test_compare_twice qemu_arm64: kselftest: * membarrier_membarrier_test * net_msg_zerocopy.sh * net_run_netsocktests * net_tls * pidfd_pidfd_test * rseq_basic_percpu_ops_test * rseq_basic_test * rseq_param_test * rseq_param_test_benchmark * rseq_param_test_compare_twice * seccomp_seccomp_bpf qemu_x86_64: kselftest: * membarrier_membarrier_test * net_msg_zerocopy.sh * net_run_netsocktests * net_tls * pidfd_pidfd_test * rseq_basic_percpu_ops_test * rseq_basic_test * rseq_param_test * rseq_param_test_benchmark * rseq_param_test_compare_twice * rseq_run_param_test.sh * seccomp_seccomp_bpf x86_64: kselftest: * bpf_test_sockmap * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test kselftest-vsyscall-mode-native: * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test kselftest-vsyscall-mode-none: * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test x86_64: kselftest: * bpf_test_sockmap * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test kselftest-vsyscall-mode-native: * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test kselftest-vsyscall-mode-none: * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test x86_64: kselftest: * bpf_test_sockmap * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test kselftest-vsyscall-mode-native: * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test kselftest-vsyscall-mode-none: * membarrier_membarrier_test * net_msg_zerocopy.sh * pidfd_pidfd_test Fixes (compared to build next-20190418) ------------------------------------------------------------------------ i386: kselftest: * bpf_test_sock_addr.sh qemu_arm64: kselftest: * bpf_test_sockmap x86_64: kselftest-vsyscall-mode-native: * bpf_test_sock_addr.sh kselftest-vsyscall-mode-none: * bpf_test_sock_addr.sh x86_64: kselftest-vsyscall-mode-native: * bpf_test_sock_addr.sh kselftest-vsyscall-mode-none: * bpf_test_sock_addr.sh In total: ------------------------------------------------------------------------ Ran 1176 total tests in the following environments and test suites. pass 682 fail 392 xfail 0 skip 102 Environments -------------- - dragonboard-410c - arm64 - hi6220-hikey - arm64 - i386 - juno-r2 - arm64 - qemu_arm - qemu_arm64 - qemu_i386 - qemu_x86_64 - x15 - arm - x86_64 Test Suites ----------- * boot-lkft-kselftests-master-506 * kselftest * boot-lkft-kselftests-vsyscall-mode-native-master-506 * boot-lkft-kselftests-vsyscall-mode-none-master-506 * kselftest-vsyscall-mode-native * kselftest-vsyscall-mode-none Failures ------------------------------------------------------------------------ qemu_x86_64: * kselftest/binderfs_binderfs_test * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lirc_mode2_user * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_tc_edt.sh * kselftest/bpf_test_tc_tunnel.sh * kselftest/cgroup_test_core * kselftest/cpufreq_main.sh * kselftest/dma-buf_udmabuf * kselftest/firmware_fw_run_tests.sh * kselftest/kvm_clear_dirty_log_test * kselftest/kvm_cr4_cpuid_sync_test * kselftest/kvm_dirty_log_test * kselftest/kvm_evmcs_test * kselftest/kvm_hyperv_cpuid * kselftest/kvm_platform_info_test * kselftest/kvm_set_sregs_test * kselftest/kvm_smm_test * kselftest/kvm_state_test * kselftest/kvm_sync_regs_test * kselftest/kvm_vmx_close_while_nested_test * kselftest/kvm_vmx_tsc_adjust_test * kselftest/lib_bitmap.sh * kselftest/lib_prime_numbers.sh * kselftest/lib_printf.sh * kselftest/lib_strscpy.sh * kselftest/livepatch_test-callbacks.sh * kselftest/livepatch_test-livepatch.sh * kselftest/livepatch_test-shadow-vars.sh * kselftest/membarrier_membarrier_test * kselftest/net_fib-onlink-tests.sh * kselftest/net_ip_defrag.sh * kselftest/net_msg_zerocopy.sh * kselftest/net_pmtu.sh * kselftest/net_psock_snd.sh * kselftest/net_run_netsocktests * kselftest/net_test_vxlan_under_vrf.sh * kselftest/net_tls * kselftest/net_xfrm_policy.sh * kselftest/pidfd_pidfd_test * kselftest/pstore_pstore_tests * kselftest/rseq_basic_percpu_ops_test * kselftest/rseq_basic_test * kselftest/rseq_param_test * kselftest/rseq_param_test_benchmark * kselftest/rseq_param_test_compare_twice * kselftest/rseq_run_param_test.sh * kselftest/rtc_rtctest * kselftest/seccomp_seccomp_bpf * kselftest/timestamping_txtimestamp.sh * kselftest/tpm2_test_smoke.sh * kselftest/tpm2_test_space.sh * kselftest/vm_run_vmtests * kselftest/x86_fsgsbase_64 qemu_arm: * kselftest/binderfs_binderfs_test * kselftest/bpf_get_cgroup_id_user * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lirc_mode2_user * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_select_reuseport * kselftest/bpf_test_sock_addr.sh * kselftest/bpf_test_sockmap * kselftest/bpf_test_sysctl * kselftest/bpf_test_tc_edt.sh * kselftest/bpf_test_tcp_check_syncookie.sh * kselftest/bpf_test_tcpnotify_user * kselftest/bpf_test_tc_tunnel.sh * kselftest/bpf_test_verifier * kselftest/cgroup_test_core * kselftest/cpufreq_main.sh * kselftest/dma-buf_udmabuf * kselftest/firmware_fw_run_tests.sh * kselftest/kvm_clear_dirty_log_test * kselftest/kvm_cr4_cpuid_sync_test * kselftest/kvm_dirty_log_test * kselftest/kvm_evmcs_test * kselftest/kvm_hyperv_cpuid * kselftest/kvm_platform_info_test * kselftest/kvm_set_sregs_test * kselftest/kvm_smm_test * kselftest/kvm_state_test * kselftest/kvm_sync_regs_test * kselftest/kvm_vmx_close_while_nested_test * kselftest/kvm_vmx_tsc_adjust_test * kselftest/lib_bitmap.sh * kselftest/lib_prime_numbers.sh * kselftest/lib_printf.sh * kselftest/lib_strscpy.sh * kselftest/livepatch_test-callbacks.sh * kselftest/livepatch_test-livepatch.sh * kselftest/livepatch_test-shadow-vars.sh * kselftest/membarrier_membarrier_test * kselftest/net_fib-onlink-tests.sh * kselftest/net_fib_tests.sh * kselftest/net_ip_defrag.sh * kselftest/net_msg_zerocopy.sh * kselftest/net_pmtu.sh * kselftest/net_psock_snd.sh * kselftest/net_reuseport_bpf_numa * kselftest/net_run_netsocktests * kselftest/net_test_vxlan_under_vrf.sh * kselftest/net_tls * kselftest/pidfd_pidfd_test * kselftest/proc_proc-self-map-files-002 * kselftest/proc_proc-self-syscall * kselftest/pstore_pstore_tests * kselftest/rseq_basic_percpu_ops_test * kselftest/rseq_basic_test * kselftest/rseq_param_test * kselftest/rseq_param_test_benchmark * kselftest/rseq_param_test_compare_twice * kselftest/rtc_rtctest * kselftest/seccomp_seccomp_bpf * kselftest/timestamping_txtimestamp.sh * kselftest/tpm2_test_smoke.sh * kselftest/tpm2_test_space.sh * kselftest/vm_run_vmtests qemu_i386: * kselftest/bpf_test_progs x86: * kselftest/binderfs_binderfs_test * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lirc_mode2_user * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_sockmap * kselftest/bpf_test_tc_tunnel.sh * kselftest/cgroup_test_core * kselftest/dma-buf_udmabuf * kselftest/firmware_fw_run_tests.sh * kselftest/kvm_clear_dirty_log_test * kselftest/kvm_cr4_cpuid_sync_test * kselftest/kvm_dirty_log_test * kselftest/kvm_evmcs_test * kselftest/kvm_hyperv_cpuid * kselftest/kvm_platform_info_test * kselftest/kvm_set_sregs_test * kselftest/kvm_smm_test * kselftest/kvm_state_test * kselftest/kvm_sync_regs_test * kselftest/kvm_vmx_close_while_nested_test * kselftest/kvm_vmx_tsc_adjust_test * kselftest/lib_bitmap.sh * kselftest/lib_prime_numbers.sh * kselftest/lib_printf.sh * kselftest/lib_strscpy.sh * kselftest/livepatch_test-callbacks.sh * kselftest/livepatch_test-livepatch.sh * kselftest/livepatch_test-shadow-vars.sh * kselftest/membarrier_membarrier_test * kselftest/net_fib-onlink-tests.sh * kselftest/net_ip_defrag.sh * kselftest/net_msg_zerocopy.sh * kselftest/net_pmtu.sh * kselftest/net_psock_snd.sh * kselftest/net_test_vxlan_under_vrf.sh * kselftest/net_xfrm_policy.sh * kselftest/pidfd_pidfd_test * kselftest/timestamping_txtimestamp.sh * kselftest-vsyscall-mode-none/binderfs_binderfs_test * kselftest-vsyscall-mode-none/bpf_test_flow_dissector.sh * kselftest-vsyscall-mode-none/bpf_test_lirc_mode2_user * kselftest-vsyscall-mode-none/bpf_test_lwt_ip_encap.sh * kselftest-vsyscall-mode-none/bpf_test_lwt_seg6local.sh * kselftest-vsyscall-mode-none/bpf_test_netcnt * kselftest-vsyscall-mode-none/bpf_test_progs * kselftest-vsyscall-mode-none/bpf_test_sockmap * kselftest-vsyscall-mode-none/bpf_test_tc_edt.sh * kselftest-vsyscall-mode-none/bpf_test_tc_tunnel.sh * kselftest-vsyscall-mode-none/cgroup_test_core * kselftest-vsyscall-mode-none/dma-buf_udmabuf * kselftest-vsyscall-mode-none/firmware_fw_run_tests.sh * kselftest-vsyscall-mode-none/kvm_clear_dirty_log_test * kselftest-vsyscall-mode-none/kvm_dirty_log_test * kselftest-vsyscall-mode-none/kvm_evmcs_test * kselftest-vsyscall-mode-none/kvm_hyperv_cpuid * kselftest-vsyscall-mode-none/kvm_platform_info_test * kselftest-vsyscall-mode-none/kvm_set_sregs_test * kselftest-vsyscall-mode-none/kvm_smm_test * kselftest-vsyscall-mode-none/kvm_state_test * kselftest-vsyscall-mode-none/kvm_sync_regs_test * kselftest-vsyscall-mode-none/kvm_vmx_tsc_adjust_test * kselftest-vsyscall-mode-none/lib_bitmap.sh * kselftest-vsyscall-mode-none/lib_prime_numbers.sh * kselftest-vsyscall-mode-none/lib_printf.sh * kselftest-vsyscall-mode-none/lib_strscpy.sh * kselftest-vsyscall-mode-none/livepatch_test-callbacks.sh * kselftest-vsyscall-mode-none/livepatch_test-livepatch.sh * kselftest-vsyscall-mode-none/livepatch_test-shadow-vars.sh * kselftest-vsyscall-mode-none/membarrier_membarrier_test * kselftest-vsyscall-mode-none/net_fib-onlink-tests.sh * kselftest-vsyscall-mode-none/net_ip_defrag.sh * kselftest-vsyscall-mode-none/net_msg_zerocopy.sh * kselftest-vsyscall-mode-none/net_pmtu.sh * kselftest-vsyscall-mode-none/net_psock_snd.sh * kselftest-vsyscall-mode-none/net_test_vxlan_under_vrf.sh * kselftest-vsyscall-mode-none/net_xfrm_policy.sh * kselftest-vsyscall-mode-none/pidfd_pidfd_test * kselftest-vsyscall-mode-none/timestamping_txtimestamp.sh * kselftest-vsyscall-mode-native/binderfs_binderfs_test * kselftest-vsyscall-mode-native/bpf_test_flow_dissector.sh * kselftest-vsyscall-mode-native/bpf_test_lirc_mode2_user * kselftest-vsyscall-mode-native/bpf_test_lwt_ip_encap.sh * kselftest-vsyscall-mode-native/bpf_test_lwt_seg6local.sh * kselftest-vsyscall-mode-native/bpf_test_netcnt * kselftest-vsyscall-mode-native/bpf_test_progs * kselftest-vsyscall-mode-native/bpf_test_sockmap * kselftest-vsyscall-mode-native/bpf_test_tc_edt.sh * kselftest-vsyscall-mode-native/bpf_test_tc_tunnel.sh * kselftest-vsyscall-mode-native/cgroup_test_core * kselftest-vsyscall-mode-native/firmware_fw_run_tests.sh * kselftest-vsyscall-mode-native/kvm_clear_dirty_log_test * kselftest-vsyscall-mode-native/kvm_cr4_cpuid_sync_test * kselftest-vsyscall-mode-native/kvm_dirty_log_test * kselftest-vsyscall-mode-native/kvm_evmcs_test * kselftest-vsyscall-mode-native/kvm_hyperv_cpuid * kselftest-vsyscall-mode-native/kvm_platform_info_test * kselftest-vsyscall-mode-native/kvm_set_sregs_test * kselftest-vsyscall-mode-native/kvm_smm_test * kselftest-vsyscall-mode-native/kvm_state_test * kselftest-vsyscall-mode-native/kvm_sync_regs_test * kselftest-vsyscall-mode-native/kvm_vmx_close_while_nested_test * kselftest-vsyscall-mode-native/kvm_vmx_tsc_adjust_test * kselftest-vsyscall-mode-native/lib_bitmap.sh * kselftest-vsyscall-mode-native/lib_prime_numbers.sh * kselftest-vsyscall-mode-native/lib_printf.sh * kselftest-vsyscall-mode-native/lib_strscpy.sh * kselftest-vsyscall-mode-native/livepatch_test-callbacks.sh * kselftest-vsyscall-mode-native/livepatch_test-livepatch.sh * kselftest-vsyscall-mode-native/livepatch_test-shadow-vars.sh * kselftest-vsyscall-mode-native/membarrier_membarrier_test * kselftest-vsyscall-mode-native/net_fib-onlink-tests.sh * kselftest-vsyscall-mode-native/net_ip_defrag.sh * kselftest-vsyscall-mode-native/net_msg_zerocopy.sh * kselftest-vsyscall-mode-native/net_pmtu.sh * kselftest-vsyscall-mode-native/net_psock_snd.sh * kselftest-vsyscall-mode-native/net_test_vxlan_under_vrf.sh * kselftest-vsyscall-mode-native/net_xfrm_policy.sh * kselftest-vsyscall-mode-native/pidfd_pidfd_test * kselftest-vsyscall-mode-native/timestamping_txtimestamp.sh juno-r2: * kselftest/binderfs_binderfs_test * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lirc_mode2_user * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_select_reuseport * kselftest/bpf_test_tc_edt.sh * kselftest/bpf_test_tcp_check_syncookie.sh * kselftest/bpf_test_tc_tunnel.sh * kselftest/bpf_test_verifier * kselftest/cgroup_test_core * kselftest/cpufreq_main.sh * kselftest/dma-buf_udmabuf * kselftest/kvm_cr4_cpuid_sync_test * kselftest/kvm_dirty_log_test * kselftest/kvm_evmcs_test * kselftest/kvm_hyperv_cpuid * kselftest/kvm_platform_info_test * kselftest/kvm_set_sregs_test * kselftest/kvm_smm_test * kselftest/kvm_state_test * kselftest/kvm_sync_regs_test * kselftest/kvm_vmx_close_while_nested_test * kselftest/kvm_vmx_tsc_adjust_test * kselftest/lib_bitmap.sh * kselftest/lib_prime_numbers.sh * kselftest/lib_printf.sh * kselftest/lib_strscpy.sh * kselftest/livepatch_test-callbacks.sh * kselftest/livepatch_test-livepatch.sh * kselftest/livepatch_test-shadow-vars.sh * kselftest/membarrier_membarrier_test x15: * boot-lkft-kselftests-master-506/x15 hi6220-hikey: * kselftest/binderfs_binderfs_test * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_select_reuseport * kselftest/bpf_test_sock_addr.sh * kselftest/bpf_test_tc_edt.sh * kselftest/bpf_test_tcp_check_syncookie.sh * kselftest/bpf_test_tc_tunnel.sh * kselftest/bpf_test_verifier * kselftest/cgroup_test_core * kselftest/dma-buf_udmabuf * kselftest/firmware_fw_run_tests.sh * kselftest/kvm_clear_dirty_log_test * kselftest/kvm_cr4_cpuid_sync_test * kselftest/kvm_dirty_log_test * kselftest/kvm_evmcs_test * kselftest/kvm_hyperv_cpuid * kselftest/kvm_platform_info_test * kselftest/kvm_set_sregs_test * kselftest/kvm_smm_test * kselftest/kvm_state_test * kselftest/kvm_sync_regs_test * kselftest/kvm_vmx_close_while_nested_test * kselftest/kvm_vmx_tsc_adjust_test * kselftest/lib_bitmap.sh * kselftest/lib_prime_numbers.sh * kselftest/lib_printf.sh * kselftest/lib_strscpy.sh * kselftest/livepatch_test-callbacks.sh * kselftest/livepatch_test-livepatch.sh * kselftest/livepatch_test-shadow-vars.sh * kselftest/membarrier_membarrier_test qemu_arm64: * kselftest/binderfs_binderfs_test * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lirc_mode2_user * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_maps * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_select_reuseport * kselftest/bpf_test_sock_addr.sh * kselftest/bpf_test_tc_edt.sh * kselftest/bpf_test_tcp_check_syncookie.sh * kselftest/bpf_test_tc_tunnel.sh * kselftest/bpf_test_verifier * kselftest/cgroup_test_core * kselftest/cpufreq_main.sh * kselftest/dma-buf_udmabuf * kselftest/firmware_fw_run_tests.sh * kselftest/kvm_clear_dirty_log_test * kselftest/kvm_cr4_cpuid_sync_test * kselftest/kvm_dirty_log_test * kselftest/kvm_evmcs_test * kselftest/kvm_hyperv_cpuid * kselftest/kvm_platform_info_test * kselftest/kvm_set_sregs_test * kselftest/kvm_smm_test * kselftest/kvm_state_test * kselftest/kvm_sync_regs_test * kselftest/kvm_vmx_close_while_nested_test * kselftest/kvm_vmx_tsc_adjust_test * kselftest/lib_bitmap.sh * kselftest/lib_prime_numbers.sh * kselftest/lib_printf.sh * kselftest/lib_strscpy.sh * kselftest/livepatch_test-callbacks.sh * kselftest/livepatch_test-livepatch.sh * kselftest/livepatch_test-shadow-vars.sh * kselftest/membarrier_membarrier_test * kselftest/net_fib-onlink-tests.sh * kselftest/net_fib_tests.sh * kselftest/net_ip_defrag.sh * kselftest/net_msg_zerocopy.sh * kselftest/net_pmtu.sh * kselftest/net_psock_snd.sh * kselftest/net_run_netsocktests * kselftest/net_test_vxlan_under_vrf.sh * kselftest/net_tls * kselftest/pidfd_pidfd_test * kselftest/pstore_pstore_tests * kselftest/rseq_basic_percpu_ops_test * kselftest/rseq_basic_test * kselftest/rseq_param_test * kselftest/rseq_param_test_benchmark * kselftest/rseq_param_test_compare_twice * kselftest/rtc_rtctest * kselftest/seccomp_seccomp_bpf * kselftest/timestamping_txtimestamp.sh * kselftest/tpm2_test_smoke.sh * kselftest/tpm2_test_space.sh * kselftest/vm_run_vmtests dragonboard-410c: * boot-lkft-kselftests-master-506/dragonboard-410c i386: * kselftest/binderfs_binderfs_test * kselftest/bpf_get_cgroup_id_user * kselftest/bpf_test_flow_dissector.sh * kselftest/bpf_test_lirc_mode2_user * kselftest/bpf_test_lwt_ip_encap.sh * kselftest/bpf_test_lwt_seg6local.sh * kselftest/bpf_test_maps * kselftest/bpf_test_netcnt * kselftest/bpf_test_progs * kselftest/bpf_test_sockmap * kselftest/bpf_test_tc_edt.sh * kselftest/bpf_test_tc_tunnel.sh * kselftest/cgroup_test_core * kselftest/dma-buf_udmabuf * kselftest/firmware_fw_run_tests.sh Skips ------------------------------------------------------------------------ No skips -- Linaro LKFT https://lkft.linaro.org

5 years

1
0
0 0

[PATCH bpf-next v3 5/5] selftests: bpf: test writable buffers in raw tps

by Matt Mullins

This tests that: * a BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE cannot be attached if it uses either: * a variable offset to the tracepoint buffer, or * an offset beyond the size of the tracepoint buffer * a tracer can modify the buffer provided when attached to a writable tracepoint in bpf_prog_test_run Signed-off-by: Matt Mullins <mmullins(a)fb.com> --- include/trace/events/bpf_test_run.h | 50 ++++++++++++ net/bpf/test_run.c | 4 + .../raw_tp_writable_reject_nbd_invalid.c | 40 ++++++++++ .../bpf/prog_tests/raw_tp_writable_test_run.c | 80 +++++++++++++++++++ .../selftests/bpf/verifier/raw_tp_writable.c | 34 ++++++++ 5 files changed, 208 insertions(+) create mode 100644 include/trace/events/bpf_test_run.h create mode 100644 tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c create mode 100644 tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c create mode 100644 tools/testing/selftests/bpf/verifier/raw_tp_writable.c diff --git a/include/trace/events/bpf_test_run.h b/include/trace/events/bpf_test_run.h new file mode 100644 index 000000000000..abf466839ea4 --- /dev/null +++ b/include/trace/events/bpf_test_run.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bpf_test_run + +#if !defined(_TRACE_NBD_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BPF_TEST_RUN_H + +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(bpf_test_finish, + + TP_PROTO(int *err), + + TP_ARGS(err), + + TP_STRUCT__entry( + __field(int, err) + ), + + TP_fast_assign( + __entry->err = *err; + ), + + TP_printk("bpf_test_finish with err=%d", __entry->err) +); + +#ifdef DEFINE_EVENT_WRITABLE +#undef BPF_TEST_RUN_DEFINE_EVENT +#define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size) \ + DEFINE_EVENT_WRITABLE(template, call, PARAMS(proto), \ + PARAMS(args), size) +#else +#undef BPF_TEST_RUN_DEFINE_EVENT +#define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size) \ + DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args)) +#endif + +BPF_TEST_RUN_DEFINE_EVENT(bpf_test_finish, bpf_test_finish, + + TP_PROTO(int *err), + + TP_ARGS(err), + + sizeof(int) +); + +#endif + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fab142b796ef..25e757102595 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -13,6 +13,9 @@ #include <net/sock.h> #include <net/tcp.h> +#define CREATE_TRACE_POINTS +#include <trace/events/bpf_test_run.h> + static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time) { @@ -100,6 +103,7 @@ static int bpf_test_finish(const union bpf_attr *kattr, if (err != -ENOSPC) err = 0; out: + trace_bpf_test_finish(&err); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c new file mode 100644 index 000000000000..328d5c4b084b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/nbd.h> + +void test_raw_tp_writable_reject_nbd_invalid(void) +{ + __u32 duration = 0; + char error[4096]; + int bpf_fd = -1, tp_fd = -1; + + const struct bpf_insn program[] = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 128), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr load_attr = { + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .license = "GPL v2", + .insns = program, + .insns_cnt = sizeof(program) / sizeof(struct bpf_insn), + .log_level = 2, + }; + + bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", + "failed: %d errno %d\n", bpf_fd, errno)) + return; + + tp_fd = bpf_raw_tracepoint_open("nbd_send_request", bpf_fd); + if (CHECK(tp_fd >= 0, "bpf_raw_tracepoint_writable opened", + "erroneously succeeded\n")) + goto out_bpffd; + + close(tp_fd); +out_bpffd: + close(bpf_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c new file mode 100644 index 000000000000..4145925f9cab --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/nbd.h> + +void test_raw_tp_writable_test_run(void) +{ + __u32 duration = 0; + char error[4096]; + + const struct bpf_insn trace_program[] = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_LD_IMM64(BPF_REG_0, 42), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr load_attr = { + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .license = "GPL v2", + .insns = trace_program, + .insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn), + .log_level = 2, + }; + + int bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", + "failed: %d errno %d\n", bpf_fd, errno)) + return; + + const struct bpf_insn skb_program[] = { + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr skb_load_attr = { + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .license = "GPL v2", + .insns = skb_program, + .insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn), + }; + + int filter_fd = + bpf_load_program_xattr(&skb_load_attr, error, sizeof(error)); + if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", + filter_fd, errno)) + goto out_bpffd; + + int tp_fd = bpf_raw_tracepoint_open("bpf_test_finish", bpf_fd); + if (CHECK(tp_fd < 0, "bpf_raw_tracepoint_writable opened", + "failed: %d errno %d\n", tp_fd, errno)) + goto out_filterfd; + + char test_skb[128] = { + 0, + }; + + __u32 prog_ret; + int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, + 0, &prog_ret, 0); + CHECK(err != 42, "test_run", + "tracepoint did not modify return value\n"); + CHECK(prog_ret != 0, "test_run_ret", + "socket_filter did not return 0\n"); + + close(tp_fd); + + err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0, + &prog_ret, 0); + CHECK(err != 0, "test_run_notrace", + "test_run failed with %d errno %d\n", err, errno); + CHECK(prog_ret != 0, "test_run_ret_notrace", + "socket_filter did not return 0\n"); + +out_filterfd: + close(filter_fd); +out_bpffd: + close(bpf_fd); +} diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c new file mode 100644 index 000000000000..95b5d70a1dc1 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c @@ -0,0 +1,34 @@ +{ + "raw_tracepoint_writable: reject variable offset", + .insns = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + + BPF_LD_MAP_FD(BPF_REG_1, 0), + /* move the key (== 0) to r10-8 */ + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + /* lookup in the map */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + + /* exit clean if null */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + /* shift the buffer pointer to a variable location */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_0), + /* clobber whatever's there */ + BPF_MOV64_IMM(BPF_REG_7, 4242), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 1, }, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)", +}, -- 2.17.1

5 years

2
3
0 0

[PATCH v4 00/10] Support using MSI interrupts in ntb_transport

by Logan Gunthorpe

This is version 4 of the MSI interrupts for ntb_transport patchset. It's mostly a resend of v3 but with spelling and grammar fixes found by Bjorn. I've addressed the feedback so far and rebased on the latest kernel and would like this to be considered for merging this cycle. The only outstanding issue I know of is that it still will not work with IDT hardware, but ntb_transport doesn't work with IDT hardware and there is still no sensible common infrastructure to support ntb_peer_mw_set_trans(). Thus, I decline to consider that complication in this patchset. However, I'll be happy to review work that adds this feature in the future. Also, as the port number and resource index stuff is a bit complicated, I made a quick out of tree test fixture to ensure it's correct[1]. As an excerise I also wrote some test code[2] using the upcomming KUnit feature. Logan [1] https://repl.it/repls/ExcitingPresentFile [2] https://github.com/sbates130272/linux-p2pmem/commits/ntb_kunit -- Changes in v4: * Rebased onto v5.1-rc6 (No changes) * Numerous grammar and spelling mistakes spotted by Bjorn -- Changes in v3: * Rebased onto v5.1-rc1 (Dropped the first two patches as they have been merged, and cleaned up some minor conflicts in the PCI tree) * Added a new patch (#3) to calculate logical port numbers that are port numbers from 0 to (number of ports - 1). This is then used in ntb_peer_resource_idx() to fix the issues brought up by Serge. * Fixed missing __iomem and iowrite calls (as noticed by Serge) * Added patch 10 which describes ntb_msi_test in the documentation file (as requested by Serge) * A couple other minor nits and documentation fixes -- Changes in v2: * Cleaned up the changes in intel_irq_remapping.c to make them less confusing and add a comment. (Per discussion with Jacob and Joerg) * Fixed a nit from Bjorn and collected his Ack * Added a Kconfig dependancy on CONFIG_PCI_MSI for CONFIG_NTB_MSI as the Kbuild robot hit a random config that didn't build without it. * Worked in a callback for when the MSI descriptor changes so that the clients can resend the new address and data values to the peer. On my test system this was never necessary, but there may be other platforms where this can occur. I tested this by hacking in a path to rewrite the MSI descriptor when I change the cpu affinity of an IRQ. There's a bit of uncertainty over the latency of the change, but without hardware this can acctually occur on we can't test this. This was the result of a discussion with Dave. -- This patch series adds optional support for using MSI interrupts instead of NTB doorbells in ntb_transport. This is desirable seeing doorbells on current hardware are quite slow and therefore switching to MSI interrupts provides a significant performance gain. On switchtec hardware, a simple apples-to-apples comparison shows ntb_netdev/iperf numbers going from 3.88Gb/s to 14.1Gb/s when switching to MSI interrupts. To do this, a couple changes are required outside of the NTB tree: 1) The IOMMU must know to accept MSI requests from aliased bused numbers seeing NTB hardware typically sends proxied request IDs through additional requester IDs. The first patch in this series adds support for the Intel IOMMU. A quirk to add these aliases for switchtec hardware was already accepted. See commit ad281ecf1c7d ("PCI: Add DMA alias quirk for Microsemi Switchtec NTB") for a description of NTB proxy IDs and why this is necessary. 2) NTB transport (and other clients) may often need more MSI interrupts than the NTB hardware actually advertises support for. However, seeing these interrupts will not be triggered by the hardware but through an NTB memory window, the hardware does not actually need support or need to know about them. Therefore we add the concept of Virtual MSI interrupts which are allocated just like any other MSI interrupt but are not programmed into the hardware's MSI table. This is done in Patch 2 and then made use of in Patch 3. The remaining patches in this series add a library for dealing with MSI interrupts, a test client and finally support in ntb_transport. The series is based off of v5.1-rc6 plus the patches in ntb-next. A git repo is available here: https://github.com/sbates130272/linux-p2pmem/ ntb_transport_msi_v4 Thanks, Logan -- Logan Gunthorpe (10): PCI/MSI: Support allocating virtual MSI interrupts PCI/switchtec: Add module parameter to request more interrupts NTB: Introduce helper functions to calculate logical port number NTB: Introduce functions to calculate multi-port resource index NTB: Rename ntb.c to support multiple source files in the module NTB: Introduce MSI library NTB: Introduce NTB MSI Test Client NTB: Add ntb_msi_test support to ntb_test NTB: Add MSI interrupt support to ntb_transport NTB: Describe the ntb_msi_test client in the documentation. Documentation/ntb.txt | 27 ++ drivers/ntb/Kconfig | 11 + drivers/ntb/Makefile | 3 + drivers/ntb/{ntb.c => core.c} | 0 drivers/ntb/msi.c | 415 +++++++++++++++++++++++ drivers/ntb/ntb_transport.c | 169 ++++++++- drivers/ntb/test/Kconfig | 9 + drivers/ntb/test/Makefile | 1 + drivers/ntb/test/ntb_msi_test.c | 433 ++++++++++++++++++++++++ drivers/pci/msi.c | 54 ++- drivers/pci/switch/switchtec.c | 12 +- include/linux/msi.h | 8 + include/linux/ntb.h | 196 ++++++++++- include/linux/pci.h | 9 + tools/testing/selftests/ntb/ntb_test.sh | 54 ++- 15 files changed, 1386 insertions(+), 15 deletions(-) rename drivers/ntb/{ntb.c => core.c} (100%) create mode 100644 drivers/ntb/msi.c create mode 100644 drivers/ntb/test/ntb_msi_test.c -- 2.20.1

5 years

1
10
0 0

[PATCH AUTOSEL 5.0 86/98] KVM: selftests: complete IO before migrating guest state

by Sasha Levin

From: Sean Christopherson <sean.j.christopherson(a)intel.com> [ Upstream commit 0f73bbc851ed32d22bbd86be09e0365c460bcd2e ] Documentation/virtual/kvm/api.txt states: NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding operations are complete (and guest state is consistent) only after userspace has re-entered the kernel with KVM_RUN. The kernel side will first finish incomplete operations and then check for pending signals. Userspace can re-enter the guest with an unmasked signal pending to complete pending operations. Because guest state may be inconsistent, starting state migration after an IO exit without first completing IO may result in test failures, e.g. a proposed change to KVM's handling of %rip in its fast PIO handling[1] will cause the new VM, i.e. the post-migration VM, to have its %rip set to the IN instruction that triggered KVM_EXIT_IO, leading to a test assertion due to a stage mismatch. For simplicitly, require KVM_CAP_IMMEDIATE_EXIT to complete IO and skip the test if it's not available. The addition of KVM_CAP_IMMEDIATE_EXIT predates the state selftest by more than a year. [1] https://patchwork.kernel.org/patch/10848545/ Fixes: fa3899add1056 ("kvm: selftests: add basic test for state save and restore") Reported-by: Jim Mattson <jmattson(a)google.com> Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Sasha Levin (Microsoft) <sashal(a)kernel.org> --- tools/testing/selftests/kvm/include/kvm_util.h | 1 + tools/testing/selftests/kvm/lib/kvm_util.c | 16 ++++++++++++++++ .../testing/selftests/kvm/x86_64/state_test.c | 18 ++++++++++++++++-- 3 files changed, 33 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a84785b02557..07b71ad9734a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index b52cfdefecbf..efa0aad8b3c6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1121,6 +1121,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) return rc; } +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + vcpu->state->immediate_exit = 1; + ret = ioctl(vcpu->fd, KVM_RUN, NULL); + vcpu->state->immediate_exit = 0; + + TEST_ASSERT(ret == -1 && errno == EINTR, + "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i", + ret, errno); +} + /* * VM VCPU Set MP State * diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 4b3f556265f1..30f75856cf39 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -134,6 +134,11 @@ int main(int argc, char *argv[]) struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { + fprintf(stderr, "immediate_exit not available, skipping test\n"); + exit(KSFT_SKIP); + } + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); @@ -156,8 +161,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(&regs1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, &regs1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -176,6 +179,17 @@ int main(int argc, char *argv[]) uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx", stage, (ulong)uc.args[1]); + /* + * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees + * guest state is consistent only after userspace re-enters the + * kernel with KVM_RUN. Complete IO prior to migrating state + * to a new VM. + */ + vcpu_run_complete_io(vm, VCPU_ID); + + memset(&regs1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, &regs1); + state = vcpu_save_state(vm, VCPU_ID); kvm_vm_release(vm); -- 2.19.1

5 years

1
0
0 0

[PATCH AUTOSEL 5.0 85/98] KVM: selftests: disable stack protector for all KVM tests

by Sasha Levin

From: Sean Christopherson <sean.j.christopherson(a)intel.com> [ Upstream commit ffac839d040619847217647434b2b02469926871 ] Since 4.8.3, gcc has enabled -fstack-protector by default. This is problematic for the KVM selftests as they do not configure fs or gs segments (the stack canary is pulled from fs:0x28). With the default behavior, gcc will insert a stack canary on any function that creates buffers of 8 bytes or more. As a result, ucall() will hit a triple fault shutdown due to reading a bad fs segment when inserting its stack canary, i.e. every test fails with an unexpected SHUTDOWN. Fixes: 14c47b7530e2d ("kvm: selftests: introduce ucall") Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Sasha Levin (Microsoft) <sashal(a)kernel.org> --- tools/testing/selftests/kvm/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 212b8f0032ae..cb4a992d6dd3 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -28,8 +28,8 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -no-pie -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. -LDFLAGS += -pthread +CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. +LDFLAGS += -pthread -no-pie # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ -- 2.19.1

5 years

1
0
0 0

[PATCH AUTOSEL 5.0 84/98] KVM: selftests: explicitly disable PIE for tests

by Sasha Levin

From: Sean Christopherson <sean.j.christopherson(a)intel.com> [ Upstream commit 0a3f29b5a77d6c27796d7a7adabafd199dc066d5 ] KVM selftests embed the guest "image" as a function in the test itself and extract the guest code at runtime by manually parsing the elf headers. The parsing is very simple and doesn't supporting fancy things like position independent executables. Recent versions of gcc enable pie by default, which results in triple fault shutdowns in the guest due to the virtual address in the headers not matching up with the virtual address retrieved from the function pointer. Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Sasha Levin (Microsoft) <sashal(a)kernel.org> --- tools/testing/selftests/kvm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index f9a0e9938480..212b8f0032ae 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -28,7 +28,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. +CFLAGS += -O2 -g -std=gnu99 -no-pie -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. LDFLAGS += -pthread # After inclusion, $(OUTPUT) is defined and -- 2.19.1

5 years

1
0
0 0

[PATCH AUTOSEL 5.0 83/98] KVM: selftests: assert on exit reason in CR4/cpuid sync test

by Sasha Levin

From: Sean Christopherson <sean.j.christopherson(a)intel.com> [ Upstream commit 8df98ae0ab2ead9a02228756eec26f8d7b17f499 ] ...so that the test doesn't end up in an infinite loop if it fails for whatever reason, e.g. SHUTDOWN due to gcc inserting stack canary code into ucall() and attempting to derefence a null segment. Fixes: ca359066889f7 ("kvm: selftests: add cr4_cpuid_sync_test") Cc: Wei Huang <wei(a)redhat.com> Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Sasha Levin (Microsoft) <sashal(a)kernel.org> --- .../kvm/x86_64/cr4_cpuid_sync_test.c | 35 ++++++++++--------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index d503a51fad30..7c2c4d4055a8 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -87,22 +87,25 @@ int main(int argc, char *argv[]) while (1) { rc = _vcpu_run(vm, VCPU_ID); - if (run->exit_reason == KVM_EXIT_IO) { - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - /* emulate hypervisor clearing CR4.OSXSAVE */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); - sregs.cr4 &= ~X86_CR4_OSXSAVE; - vcpu_sregs_set(vm, VCPU_ID, &sregs); - break; - case UCALL_ABORT: - TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); - break; - case UCALL_DONE: - goto done; - default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); - } + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + /* emulate hypervisor clearing CR4.OSXSAVE */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.cr4 &= ~X86_CR4_OSXSAVE; + vcpu_sregs_set(vm, VCPU_ID, &sregs); + break; + case UCALL_ABORT: + TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); } } -- 2.19.1

5 years

1
0
0 0

[PATCH v2 76/79] docs: blockdev: convert to ReST

by Mauro Carvalho Chehab

Rename the blockdev documentation files to ReST, add an index for them and adjust in order to produce a nice html output via the Sphinx build system. The drbd sub-directory contains some graphs and data flows. Add those too to the documentation. At its new index.rst, let's add a :orphan: while this is not linked to the main index.rst file, in order to avoid build warnings. Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung(a)kernel.org> --- .../admin-guide/kernel-parameters.txt | 18 +- ...structure-v9.txt => data-structure-v9.rst} | 6 +- Documentation/blockdev/drbd/figures.rst | 28 +++ .../blockdev/drbd/{README.txt => index.rst} | 15 +- .../blockdev/{floppy.txt => floppy.rst} | 88 ++++---- Documentation/blockdev/index.rst | 16 ++ Documentation/blockdev/{nbd.txt => nbd.rst} | 1 + .../blockdev/{paride.txt => paride.rst} | 144 +++++++------ .../blockdev/{ramdisk.txt => ramdisk.rst} | 55 ++--- Documentation/blockdev/{zram.txt => zram.rst} | 195 ++++++++++++------ MAINTAINERS | 8 +- drivers/block/Kconfig | 8 +- drivers/block/floppy.c | 2 +- drivers/block/zram/Kconfig | 6 +- tools/testing/selftests/zram/README | 2 +- 15 files changed, 374 insertions(+), 218 deletions(-) rename Documentation/blockdev/drbd/{data-structure-v9.txt => data-structure-v9.rst} (94%) create mode 100644 Documentation/blockdev/drbd/figures.rst rename Documentation/blockdev/drbd/{README.txt => index.rst} (55%) rename Documentation/blockdev/{floppy.txt => floppy.rst} (81%) create mode 100644 Documentation/blockdev/index.rst rename Documentation/blockdev/{nbd.txt => nbd.rst} (96%) rename Documentation/blockdev/{paride.txt => paride.rst} (85%) rename Documentation/blockdev/{ramdisk.txt => ramdisk.rst} (84%) rename Documentation/blockdev/{zram.txt => zram.rst} (76%) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 65d66010b134..a6297aff5598 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1248,7 +1248,7 @@ See also Documentation/fault-injection/. floppy= [HW] - See Documentation/blockdev/floppy.txt. + See Documentation/blockdev/floppy.rst. force_pal_cache_flush [IA-64] Avoid check_sal_cache_flush which may hang on @@ -2227,7 +2227,7 @@ memblock=debug [KNL] Enable memblock debug messages. load_ramdisk= [RAM] List of ramdisks to load from floppy - See Documentation/blockdev/ramdisk.txt. + See Documentation/blockdev/ramdisk.rst. lockd.nlm_grace_period=P [NFS] Assign grace period. Format: <integer> @@ -3197,7 +3197,7 @@ pcd. [PARIDE] See header of drivers/block/paride/pcd.c. - See also Documentation/blockdev/paride.txt. + See also Documentation/blockdev/paride.rst. pci=option[,option...] [PCI] various PCI subsystem options. @@ -3439,7 +3439,7 @@ needed on a platform with proper driver support. pd. [PARIDE] - See Documentation/blockdev/paride.txt. + See Documentation/blockdev/paride.rst. pdcchassis= [PARISC,HW] Disable/Enable PDC Chassis Status codes at boot time. @@ -3454,10 +3454,10 @@ and performance comparison. pf. [PARIDE] - See Documentation/blockdev/paride.txt. + See Documentation/blockdev/paride.rst. pg. [PARIDE] - See Documentation/blockdev/paride.txt. + See Documentation/blockdev/paride.rst. pirq= [SMP,APIC] Manual mp-table setup See Documentation/x86/i386/IO-APIC.txt. @@ -3569,7 +3569,7 @@ prompt_ramdisk= [RAM] List of RAM disks to prompt for floppy disk before loading. - See Documentation/blockdev/ramdisk.txt. + See Documentation/blockdev/ramdisk.rst. psi= [KNL] Enable or disable pressure stall information tracking. @@ -3591,7 +3591,7 @@ pstore.backend= Specify the name of the pstore backend to use pt. [PARIDE] - See Documentation/blockdev/paride.txt. + See Documentation/blockdev/paride.rst. pti= [X86_64] Control Page Table Isolation of user and kernel address spaces. Disabling this feature @@ -3620,7 +3620,7 @@ See Documentation/admin-guide/md.rst. ramdisk_size= [RAM] Sizes of RAM disks in kilobytes - See Documentation/blockdev/ramdisk.txt. + See Documentation/blockdev/ramdisk.rst. random.trust_cpu={on,off} [KNL] Enable or disable trusting the use of the diff --git a/Documentation/blockdev/drbd/data-structure-v9.txt b/Documentation/blockdev/drbd/data-structure-v9.rst similarity index 94% rename from Documentation/blockdev/drbd/data-structure-v9.txt rename to Documentation/blockdev/drbd/data-structure-v9.rst index 1e52a0e32624..66036b901644 100644 --- a/Documentation/blockdev/drbd/data-structure-v9.txt +++ b/Documentation/blockdev/drbd/data-structure-v9.rst @@ -1,3 +1,7 @@ +================================ +kernel data structure for DRBD-9 +================================ + This describes the in kernel data structure for DRBD-9. Starting with Linux v3.14 we are reorganizing DRBD to use this data structure. @@ -10,7 +14,7 @@ device is represented by a block device locally. The DRBD objects are interconnected to form a matrix as depicted below; a drbd_peer_device object sits at each intersection between a drbd_device and a -drbd_connection: +drbd_connection:: /--------------+---------------+.....+---------------\ | resource | device | | device | diff --git a/Documentation/blockdev/drbd/figures.rst b/Documentation/blockdev/drbd/figures.rst new file mode 100644 index 000000000000..3e3fd4b8a478 --- /dev/null +++ b/Documentation/blockdev/drbd/figures.rst @@ -0,0 +1,28 @@ +.. The here included files are intended to help understand the implementation + +Data flows that Relate some functions, and write packets +======================================================== + +.. kernel-figure:: DRBD-8.3-data-packets.svg + :alt: DRBD-8.3-data-packets.svg + :align: center + +.. kernel-figure:: DRBD-data-packets.svg + :alt: DRBD-data-packets.svg + :align: center + + +Sub graphs of DRBD's state transitions +====================================== + +.. kernel-figure:: conn-states-8.dot + :alt: conn-states-8.dot + :align: center + +.. kernel-figure:: disk-states-8.dot + :alt: disk-states-8.dot + :align: center + +.. kernel-figure:: node-states-8.dot + :alt: node-states-8.dot + :align: center diff --git a/Documentation/blockdev/drbd/README.txt b/Documentation/blockdev/drbd/index.rst similarity index 55% rename from Documentation/blockdev/drbd/README.txt rename to Documentation/blockdev/drbd/index.rst index 627b0a1bf35e..68ecd5c113e9 100644 --- a/Documentation/blockdev/drbd/README.txt +++ b/Documentation/blockdev/drbd/index.rst @@ -1,4 +1,9 @@ +========================================== +Distributed Replicated Block Device - DRBD +========================================== + Description +=========== DRBD is a shared-nothing, synchronously replicated block device. It is designed to serve as a building block for high availability @@ -7,10 +12,8 @@ Description Please visit http://www.drbd.org to find out more. -The here included files are intended to help understand the implementation +.. toctree:: + :maxdepth: 1 -DRBD-8.3-data-packets.svg, DRBD-data-packets.svg - relates some functions, and write packets. - -conn-states-8.dot, disk-states-8.dot, node-states-8.dot - The sub graphs of DRBD's state transitions + data-structure-v9 + figures diff --git a/Documentation/blockdev/floppy.txt b/Documentation/blockdev/floppy.rst similarity index 81% rename from Documentation/blockdev/floppy.txt rename to Documentation/blockdev/floppy.rst index e2240f5ab64d..4a8f31cf4139 100644 --- a/Documentation/blockdev/floppy.txt +++ b/Documentation/blockdev/floppy.rst @@ -1,35 +1,37 @@ -This file describes the floppy driver. +============= +Floppy Driver +============= FAQ list: ========= - A FAQ list may be found in the fdutils package (see below), and also +A FAQ list may be found in the fdutils package (see below), and also at <http://fdutils.linux.lu/faq.html>. LILO configuration options (Thinkpad users, read this) ====================================================== - The floppy driver is configured using the 'floppy=' option in +The floppy driver is configured using the 'floppy=' option in lilo. This option can be typed at the boot prompt, or entered in the lilo configuration file. - Example: If your kernel is called linux-2.6.9, type the following line -at the lilo boot prompt (if you have a thinkpad): +Example: If your kernel is called linux-2.6.9, type the following line +at the lilo boot prompt (if you have a thinkpad):: linux-2.6.9 floppy=thinkpad You may also enter the following line in /etc/lilo.conf, in the description -of linux-2.6.9: +of linux-2.6.9:: append = "floppy=thinkpad" - Several floppy related options may be given, example: +Several floppy related options may be given, example:: linux-2.6.9 floppy=daring floppy=two_fdc append = "floppy=daring floppy=two_fdc" - If you give options both in the lilo config file and on the boot +If you give options both in the lilo config file and on the boot prompt, the option strings of both places are concatenated, the boot prompt options coming last. That's why there are also options to restore the default behavior. @@ -38,21 +40,23 @@ restore the default behavior. Module configuration options ============================ - If you use the floppy driver as a module, use the following syntax: -modprobe floppy floppy="<options>" +If you use the floppy driver as a module, use the following syntax:: -Example: - modprobe floppy floppy="omnibook messages" + modprobe floppy floppy="<options>" - If you need certain options enabled every time you load the floppy driver, -you can put: +Example:: - options floppy floppy="omnibook messages" + modprobe floppy floppy="omnibook messages" + +If you need certain options enabled every time you load the floppy driver, +you can put:: + + options floppy floppy="omnibook messages" in a configuration file in /etc/modprobe.d/. - The floppy driver related options are: +The floppy driver related options are: floppy=asus_pci Sets the bit mask to allow only units 0 and 1. (default) @@ -70,8 +74,7 @@ in a configuration file in /etc/modprobe.d/. Tells the floppy driver that you have only one floppy controller. (default) - floppy=two_fdc - floppy=<address>,two_fdc + floppy=two_fdc / floppy=<address>,two_fdc Tells the floppy driver that you have two floppy controllers. The second floppy controller is assumed to be at <address>. This option is not needed if the second controller is at address @@ -84,8 +87,7 @@ in a configuration file in /etc/modprobe.d/. floppy=0,thinkpad Tells the floppy driver that you don't have a Thinkpad. - floppy=omnibook - floppy=nodma + floppy=omnibook / floppy=nodma Tells the floppy driver not to use Dma for data transfers. This is needed on HP Omnibooks, which don't have a workable DMA channel for the floppy driver. This option is also useful @@ -144,14 +146,16 @@ in a configuration file in /etc/modprobe.d/. described in the physical CMOS), or if your BIOS uses non-standard CMOS types. The CMOS types are: - 0 - Use the value of the physical CMOS - 1 - 5 1/4 DD - 2 - 5 1/4 HD - 3 - 3 1/2 DD - 4 - 3 1/2 HD - 5 - 3 1/2 ED - 6 - 3 1/2 ED - 16 - unknown or not installed + == ================================== + 0 Use the value of the physical CMOS + 1 5 1/4 DD + 2 5 1/4 HD + 3 3 1/2 DD + 4 3 1/2 HD + 5 3 1/2 ED + 6 3 1/2 ED + 16 unknown or not installed + == ================================== (Note: there are two valid types for ED drives. This is because 5 was initially chosen to represent floppy *tapes*, and 6 for ED drives. @@ -162,8 +166,7 @@ in a configuration file in /etc/modprobe.d/. Print a warning message when an unexpected interrupt is received. (default) - floppy=no_unexpected_interrupts - floppy=L40SX + floppy=no_unexpected_interrupts / floppy=L40SX Don't print a message when an unexpected interrupt is received. This is needed on IBM L40SX laptops in certain video modes. (There seems to be an interaction between video and floppy. The unexpected @@ -199,47 +202,54 @@ in a configuration file in /etc/modprobe.d/. Sets the floppy DMA channel to <nr> instead of 2. floppy=slow - Use PS/2 stepping rate: - " PS/2 floppies have much slower step rates than regular floppies. + Use PS/2 stepping rate:: + + PS/2 floppies have much slower step rates than regular floppies. It's been recommended that take about 1/4 of the default speed - in some more extreme cases." + in some more extreme cases. Supporting utilities and additional documentation: ================================================== - Additional parameters of the floppy driver can be configured at +Additional parameters of the floppy driver can be configured at runtime. Utilities which do this can be found in the fdutils package. This package also contains a new version of mtools which allows to access high capacity disks (up to 1992K on a high density 3 1/2 disk!). It also contains additional documentation about the floppy driver. The latest version can be found at fdutils homepage: + http://fdutils.linux.lu The fdutils releases can be found at: + http://fdutils.linux.lu/download.html + http://www.tux.org/pub/knaff/fdutils/ + ftp://metalab.unc.edu/pub/Linux/utils/disk-management/ Reporting problems about the floppy driver ========================================== - If you have a question or a bug report about the floppy driver, mail +If you have a question or a bug report about the floppy driver, mail me at Alain.Knaff(a)poboxes.com . If you post to Usenet, preferably use comp.os.linux.hardware. As the volume in these groups is rather high, be sure to include the word "floppy" (or "FLOPPY") in the subject line. If the reported problem happens when mounting floppy disks, be sure to mention also the type of the filesystem in the subject line. - Be sure to read the FAQ before mailing/posting any bug reports! +Be sure to read the FAQ before mailing/posting any bug reports! - Alain +Alain Changelog ========= -10-30-2004 : Cleanup, updating, add reference to module configuration. +10-30-2004 : + Cleanup, updating, add reference to module configuration. James Nelson <james4765(a)gmail.com> -6-3-2000 : Original Document +6-3-2000 : + Original Document diff --git a/Documentation/blockdev/index.rst b/Documentation/blockdev/index.rst new file mode 100644 index 000000000000..a9af6ed8b4aa --- /dev/null +++ b/Documentation/blockdev/index.rst @@ -0,0 +1,16 @@ +:orphan: + +=========================== +The Linux RapidIO Subsystem +=========================== + +.. toctree:: + :maxdepth: 1 + + floppy + nbd + paride + ramdisk + zram + + drbd/index diff --git a/Documentation/blockdev/nbd.txt b/Documentation/blockdev/nbd.rst similarity index 96% rename from Documentation/blockdev/nbd.txt rename to Documentation/blockdev/nbd.rst index db242ea2bce8..db0c96e46661 100644 --- a/Documentation/blockdev/nbd.txt +++ b/Documentation/blockdev/nbd.rst @@ -1,3 +1,4 @@ +================================== Network Block Device (TCP version) ================================== diff --git a/Documentation/blockdev/paride.txt b/Documentation/blockdev/paride.rst similarity index 85% rename from Documentation/blockdev/paride.txt rename to Documentation/blockdev/paride.rst index ee6717e3771d..b7fdd77513ab 100644 --- a/Documentation/blockdev/paride.txt +++ b/Documentation/blockdev/paride.rst @@ -1,9 +1,11 @@ - - Linux and parallel port IDE devices +=================================== +Linux and parallel port IDE devices +=================================== PARIDE v1.03 (c) 1997-8 Grant Guenther <grant(a)torque.net> 1. Introduction +=============== Owing to the simplicity and near universality of the parallel port interface to personal computers, many external devices such as portable hard-disk, @@ -35,17 +37,17 @@ devices. It does not cover parallel port SCSI devices, "ditto" tape drives or scanners. Many different devices are supported by the parallel port IDE subsystem, including: - MicroSolutions backpack CD-ROM - MicroSolutions backpack PD/CD - MicroSolutions backpack hard-drives - MicroSolutions backpack 8000t tape drive - SyQuest EZ-135, EZ-230 & SparQ drives - Avatar Shark - Imation Superdisk LS-120 - Maxell Superdisk LS-120 - FreeCom Power CD - Hewlett-Packard 5GB and 8GB tape drives - Hewlett-Packard 7100 and 7200 CD-RW drives + - MicroSolutions backpack CD-ROM + - MicroSolutions backpack PD/CD + - MicroSolutions backpack hard-drives + - MicroSolutions backpack 8000t tape drive + - SyQuest EZ-135, EZ-230 & SparQ drives + - Avatar Shark + - Imation Superdisk LS-120 + - Maxell Superdisk LS-120 + - FreeCom Power CD + - Hewlett-Packard 5GB and 8GB tape drives + - Hewlett-Packard 7100 and 7200 CD-RW drives as well as most of the clone and no-name products on the market. @@ -55,11 +57,13 @@ paride module which provides a registry and some common methods for accessing the parallel ports. The second component is a set of high-level drivers for each of the different types of supported devices: + === ============= pd IDE disk pcd ATAPI CD-ROM pf ATAPI disk pt ATAPI tape pg ATAPI generic + === ============= (Currently, the pg driver is only used with CD-R drives). @@ -69,6 +73,7 @@ for each of the parallel port IDE adapter chips. Thanks to the interest and encouragement of Linux users from many parts of the world, support is available for almost all known adapter protocols: + ==== ====================================== ==== aten ATEN EH-100 (HK) bpck Microsolutions backpack (US) comm DataStor (old-type) "commuter" adapter (TW) @@ -83,9 +88,11 @@ support is available for almost all known adapter protocols: ktti KT Technology PHd adapter (SG) on20 OnSpec 90c20 (US) on26 OnSpec 90c26 (US) + ==== ====================================== ==== 2. Using the PARIDE subsystem +============================= While configuring the Linux kernel, you may choose either to build the PARIDE drivers into your kernel, or to build them as modules. @@ -105,8 +112,9 @@ subsystem to try them all for you. For the "brand-name" products listed above, here are the protocol and high-level drivers that you would use: + ================ ============ ====== ======== Manufacturer Model Driver Protocol - + ================ ============ ====== ======== MicroSolutions CD-ROM pcd bpck MicroSolutions PD drive pf bpck MicroSolutions hard-drive pd bpck @@ -119,8 +127,10 @@ and high-level drivers that you would use: Hewlett-Packard 5GB Tape pt epat Hewlett-Packard 7200e (CD) pcd epat Hewlett-Packard 7200e (CD-R) pg epat + ================ ============ ====== ======== 2.1 Configuring built-in drivers +--------------------------------- We recommend that you get to know how the drivers work and how to configure them as loadable modules, before attempting to compile a @@ -143,7 +153,7 @@ protocol identification number and, for some devices, the drive's chain ID. While your system is booting, a number of messages are displayed on the console. Like all such messages, they can be reviewed with the 'dmesg' command. Among those messages will be -some lines like: +some lines like:: paride: bpck registered as protocol 0 paride: epat registered as protocol 1 @@ -161,7 +171,7 @@ As an example, let's assume that you have a MicroSolutions PD/CD drive with unit ID number 36 connected to the parallel port at 0x378, a SyQuest EZ-135 connected to the chained port on the PD/CD drive and also an Imation Superdisk connected to port 0x278. You could give the following -options on your boot command: +options on your boot command:: pd.drive0=0x378,1 pf.drive0=0x278,1 pf.drive1=0x378,0,36 @@ -175,18 +185,21 @@ PARPORT parallel port sharing system that is included by the if you want to use chains of devices on the same parallel port. 2.2 Loading and configuring PARIDE as modules +---------------------------------------------- It is much faster and simpler to get to understand the PARIDE drivers if you use them as loadable kernel modules. -Note 1: using these drivers with the "kerneld" automatic module loading -system is not recommended for beginners, and is not documented here. +Note 1: + using these drivers with the "kerneld" automatic module loading + system is not recommended for beginners, and is not documented here. -Note 2: if you build PARPORT support as a loadable module, PARIDE must -also be built as loadable modules, and PARPORT must be loaded before the -PARIDE modules. +Note 2: + if you build PARPORT support as a loadable module, PARIDE must + also be built as loadable modules, and PARPORT must be loaded before + the PARIDE modules. -To use PARIDE, you must begin by +To use PARIDE, you must begin by:: insmod paride @@ -196,7 +209,7 @@ among other tasks. Then, load as many of the protocol modules as you think you might need. As you load each module, it will register the protocols that it supports, and print a log message to your kernel log file and your console. For -example: +example:: # insmod epat paride: epat registered as protocol 0 @@ -211,7 +224,7 @@ individual co-ordinates when you load the driver. For example, if you had two no-name CD-ROM drives both using the KingByte KBIC-951A adapter, one on port 0x378 and the other on 0x3bc -you could give the following command: +you could give the following command:: # insmod pcd drive0=0x378,1 drive1=0x3bc,1 @@ -220,7 +233,7 @@ but check the source files in linux/drivers/block/paride for more information. (Hopefully someone will write some man pages one day !). As another example, here's what happens when PARPORT is installed, and -a SyQuest EZ-135 is attached to port 0x378: +a SyQuest EZ-135 is attached to port 0x378:: # insmod paride paride: version 1.0 installed @@ -237,46 +250,47 @@ Note that the last line is the output from the generic partition table scanner - in this case it reports that it has found a disk with one partition. 2.3 Using a PARIDE device +-------------------------- Once the drivers have been loaded, you can access PARIDE devices in the same way as their traditional counterparts. You will probably need to create the device "special files". Here is a simple script that you can -cut to a file and execute: +cut to a file and execute:: -#!/bin/bash -# -# mkd -- a script to create the device special files for the PARIDE subsystem -# -function mkdev { - mknod $1 $2 $3 $4 ; chmod 0660 $1 ; chown root:disk $1 -} -# -function pd { - D=$( printf \\$( printf "x%03x" $[ $1 + 97 ] ) ) - mkdev pd$D b 45 $[ $1 * 16 ] - for P in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 - do mkdev pd$D$P b 45 $[ $1 * 16 + $P ] - done -} -# -cd /dev -# -for u in 0 1 2 3 ; do pd $u ; done -for u in 0 1 2 3 ; do mkdev pcd$u b 46 $u ; done -for u in 0 1 2 3 ; do mkdev pf$u b 47 $u ; done -for u in 0 1 2 3 ; do mkdev pt$u c 96 $u ; done -for u in 0 1 2 3 ; do mkdev npt$u c 96 $[ $u + 128 ] ; done -for u in 0 1 2 3 ; do mkdev pg$u c 97 $u ; done -# -# end of mkd + #!/bin/bash + # + # mkd -- a script to create the device special files for the PARIDE subsystem + # + function mkdev { + mknod $1 $2 $3 $4 ; chmod 0660 $1 ; chown root:disk $1 + } + # + function pd { + D=$( printf \\$( printf "x%03x" $[ $1 + 97 ] ) ) + mkdev pd$D b 45 $[ $1 * 16 ] + for P in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + do mkdev pd$D$P b 45 $[ $1 * 16 + $P ] + done + } + # + cd /dev + # + for u in 0 1 2 3 ; do pd $u ; done + for u in 0 1 2 3 ; do mkdev pcd$u b 46 $u ; done + for u in 0 1 2 3 ; do mkdev pf$u b 47 $u ; done + for u in 0 1 2 3 ; do mkdev pt$u c 96 $u ; done + for u in 0 1 2 3 ; do mkdev npt$u c 96 $[ $u + 128 ] ; done + for u in 0 1 2 3 ; do mkdev pg$u c 97 $u ; done + # + # end of mkd With the device files and drivers in place, you can access PARIDE devices -like any other Linux device. For example, to mount a CD-ROM in pcd0, use: +like any other Linux device. For example, to mount a CD-ROM in pcd0, use:: mount /dev/pcd0 /cdrom If you have a fresh Avatar Shark cartridge, and the drive is pda, you -might do something like: +might do something like:: fdisk /dev/pda -- make a new partition table with partition 1 of type 83 @@ -289,13 +303,14 @@ might do something like: Devices like the Imation superdisk work in the same way, except that they do not have a partition table. For example to make a 120MB -floppy that you could share with a DOS system: +floppy that you could share with a DOS system:: mkdosfs /dev/pf0 mount /dev/pf0 /mnt 2.4 The pf driver +------------------ The pf driver is intended for use with parallel port ATAPI disk devices. The most common devices in this category are PD drives @@ -304,6 +319,7 @@ partitioned. Consequently, the pf driver does not support partitioned media. This may be changed in a future version of the driver. 2.5 Using the pt driver +------------------------ The pt driver for parallel port ATAPI tape drives is a minimal driver. It does not yet support many of the standard tape ioctl operations. @@ -311,6 +327,7 @@ For best performance, a block size of 32KB should be used. You will probably want to set the parallel port delay to 0, if you can. 2.6 Using the pg driver +------------------------ The pg driver can be used in conjunction with the cdrecord program to create CD-ROMs. Please get cdrecord version 1.6.1 or later @@ -322,8 +339,10 @@ in EPP mode, try to use "bidirectional" or "PS/2" mode and 1x speeds only. 3. Troubleshooting +================== 3.1 Use EPP mode if you can +---------------------------- The most common problems that people report with the PARIDE drivers concern the parallel port CMOS settings. At this time, none of the @@ -332,6 +351,7 @@ If you are able to do so, please set your parallel port into EPP mode using your CMOS setup procedure. 3.2 Check the port delay +------------------------- Some parallel ports cannot reliably transfer data at full speed. To offset the errors, the PARIDE protocol modules introduce a "port @@ -347,6 +367,7 @@ read the comments at the beginning of the driver source files in linux/drivers/block/paride. 3.3 Some drives need a printer reset +------------------------------------- There appear to be a number of "noname" external drives on the market that do not always power up correctly. We have noticed this with some @@ -354,7 +375,7 @@ drives based on OnSpec and older Freecom adapters. In these rare cases, the adapter can often be reinitialised by issuing a "printer reset" on the parallel port. As the reset operation is potentially disruptive in multiple device environments, the PARIDE drivers will not do it -automatically. You can however, force a printer reset by doing: +automatically. You can however, force a printer reset by doing:: insmod lp reset=1 rmmod lp @@ -364,6 +385,7 @@ your paride drivers as modules, and arrange to do the printer reset before loading the PARIDE drivers. 3.4 Use the verbose option and dmesg if you need help +------------------------------------------------------ While a lot of testing has gone into these drivers to make them work as smoothly as possible, problems will arise. If you do have problems, @@ -373,7 +395,7 @@ clues, then please make sure that only one drive is hooked to your system, and that either (a) PARPORT is enabled or (b) no other device driver is using your parallel port (check in /proc/ioports). Then, load the appropriate drivers (you can load several protocol modules if you want) -as in: +as in:: # insmod paride # insmod epat @@ -394,12 +416,14 @@ by e-mail to grant(a)torque.net, or join the linux-parport mailing list and post your report there. 3.5 For more information or help +--------------------------------- You can join the linux-parport mailing list by sending a mail message -to +to: + linux-parport-request(a)torque.net -with the single word +with the single word:: subscribe @@ -412,6 +436,6 @@ have in your mail headers, when sending mail to the list server. You might also find some useful information on the linux-parport web pages (although they are not always up to date) at - http://web.archive.org/web/*/http://www.torque.net/parport/ + http://web.archive.org/web/%2E/http://www.torque.net/parport/ diff --git a/Documentation/blockdev/ramdisk.txt b/Documentation/blockdev/ramdisk.rst similarity index 84% rename from Documentation/blockdev/ramdisk.txt rename to Documentation/blockdev/ramdisk.rst index 501e12e0323e..b7c2268f8dec 100644 --- a/Documentation/blockdev/ramdisk.txt +++ b/Documentation/blockdev/ramdisk.rst @@ -1,7 +1,8 @@ +========================================== Using the RAM disk block device with Linux ------------------------------------------- +========================================== -Contents: +.. Contents: 1) Overview 2) Kernel Command Line Parameters @@ -42,7 +43,7 @@ rescue floppy disk. 2a) Kernel Command Line Parameters ramdisk_size=N - ============== + Size of the ramdisk. This parameter tells the RAM disk driver to set up RAM disks of N k size. The default is 4096 (4 MB). @@ -50,16 +51,13 @@ default is 4096 (4 MB). 2b) Module parameters rd_nr - ===== - /dev/ramX devices created. + /dev/ramX devices created. max_part - ======== - Maximum partition number. + Maximum partition number. rd_size - ======= - See ramdisk_size. + See ramdisk_size. 3) Using "rdev -r" ------------------ @@ -71,11 +69,11 @@ to 2 MB (2^11) of where to find the RAM disk (this used to be the size). Bit prompt/wait sequence is to be given before trying to read the RAM disk. Since the RAM disk dynamically grows as data is being written into it, a size field is not required. Bits 11 to 13 are not currently used and may as well be zero. -These numbers are no magical secrets, as seen below: +These numbers are no magical secrets, as seen below:: -./arch/x86/kernel/setup.c:#define RAMDISK_IMAGE_START_MASK 0x07FF -./arch/x86/kernel/setup.c:#define RAMDISK_PROMPT_FLAG 0x8000 -./arch/x86/kernel/setup.c:#define RAMDISK_LOAD_FLAG 0x4000 + ./arch/x86/kernel/setup.c:#define RAMDISK_IMAGE_START_MASK 0x07FF + ./arch/x86/kernel/setup.c:#define RAMDISK_PROMPT_FLAG 0x8000 + ./arch/x86/kernel/setup.c:#define RAMDISK_LOAD_FLAG 0x4000 Consider a typical two floppy disk setup, where you will have the kernel on disk one, and have already put a RAM disk image onto disk #2. @@ -92,20 +90,23 @@ sequence so that you have a chance to switch floppy disks. The command line equivalent is: "prompt_ramdisk=1" Putting that together gives 2^15 + 2^14 + 0 = 49152 for an rdev word. -So to create disk one of the set, you would do: +So to create disk one of the set, you would do:: /usr/src/linux# cat arch/x86/boot/zImage > /dev/fd0 /usr/src/linux# rdev /dev/fd0 /dev/fd0 /usr/src/linux# rdev -r /dev/fd0 49152 -If you make a boot disk that has LILO, then for the above, you would use: +If you make a boot disk that has LILO, then for the above, you would use:: + append = "ramdisk_start=0 load_ramdisk=1 prompt_ramdisk=1" -Since the default start = 0 and the default prompt = 1, you could use: + +Since the default start = 0 and the default prompt = 1, you could use:: + append = "load_ramdisk=1" 4) An Example of Creating a Compressed RAM Disk ----------------------------------------------- +----------------------------------------------- To create a RAM disk image, you will need a spare block device to construct it on. This can be the RAM disk device itself, or an @@ -120,11 +121,11 @@ a) Decide on the RAM disk size that you want. Say 2 MB for this example. Create it by writing to the RAM disk device. (This step is not currently required, but may be in the future.) It is wise to zero out the area (esp. for disks) so that maximal compression is achieved for - the unused blocks of the image that you are about to create. + the unused blocks of the image that you are about to create:: dd if=/dev/zero of=/dev/ram0 bs=1k count=2048 -b) Make a filesystem on it. Say ext2fs for this example. +b) Make a filesystem on it. Say ext2fs for this example:: mke2fs -vm0 /dev/ram0 2048 @@ -133,11 +134,11 @@ c) Mount it, copy the files you want to it (eg: /etc/* /dev/* ...) d) Compress the contents of the RAM disk. The level of compression will be approximately 50% of the space used by the files. Unused - space on the RAM disk will compress to almost nothing. + space on the RAM disk will compress to almost nothing:: dd if=/dev/ram0 bs=1k count=2048 | gzip -v9 > /tmp/ram_image.gz -e) Put the kernel onto the floppy +e) Put the kernel onto the floppy:: dd if=zImage of=/dev/fd0 bs=1k @@ -146,13 +147,13 @@ f) Put the RAM disk image onto the floppy, after the kernel. Use an offset (possibly larger) kernel onto the same floppy later without overlapping the RAM disk image. An offset of 400 kB for kernels about 350 kB in size would be reasonable. Make sure offset+size of ram_image.gz is - not larger than the total space on your floppy (usually 1440 kB). + not larger than the total space on your floppy (usually 1440 kB):: dd if=/tmp/ram_image.gz of=/dev/fd0 bs=1k seek=400 g) Use "rdev" to set the boot device, RAM disk offset, prompt flag, etc. For prompt_ramdisk=1, load_ramdisk=1, ramdisk_start=400, one would - have 2^15 + 2^14 + 400 = 49552. + have 2^15 + 2^14 + 400 = 49552:: rdev /dev/fd0 /dev/fd0 rdev -r /dev/fd0 49552 @@ -160,15 +161,17 @@ g) Use "rdev" to set the boot device, RAM disk offset, prompt flag, etc. That is it. You now have your boot/root compressed RAM disk floppy. Some users may wish to combine steps (d) and (f) by using a pipe. --------------------------------------------------------------------------- + Paul Gortmaker 12/95 Changelog: ---------- -10-22-04 : Updated to reflect changes in command line options, remove +10-22-04 : + Updated to reflect changes in command line options, remove obsolete references, general cleanup. James Nelson (james4765(a)gmail.com) -12-95 : Original Document +12-95 : + Original Document diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.rst similarity index 76% rename from Documentation/blockdev/zram.txt rename to Documentation/blockdev/zram.rst index 4df0ce271085..2111231c9c0f 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.rst @@ -1,7 +1,9 @@ +======================================== zram: Compressed RAM based block devices ----------------------------------------- +======================================== -* Introduction +Introduction +============ The zram module creates RAM based block devices named /dev/zram<id> (<id> = 0, 1, ...). Pages written to these disks are compressed and stored @@ -12,9 +14,11 @@ use as swap disks, various caches under /var and maybe many more :) Statistics for individual zram devices are exported through sysfs nodes at /sys/block/zram<id>/ -* Usage +Usage +===== There are several ways to configure and manage zram device(-s): + a) using zram and zram_control sysfs attributes b) using zramctl utility, provided by util-linux (util-linux(a)vger.kernel.org). @@ -22,7 +26,7 @@ In this document we will describe only 'manual' zram configuration steps, IOW, zram and zram_control sysfs attributes. In order to get a better idea about zramctl please consult util-linux -documentation, zramctl man-page or `zramctl --help'. Please be informed +documentation, zramctl man-page or `zramctl --help`. Please be informed that zram maintainers do not develop/maintain util-linux or zramctl, should you have any questions please contact util-linux(a)vger.kernel.org @@ -30,19 +34,23 @@ Following shows a typical sequence of steps for using zram. WARNING ======= + For the sake of simplicity we skip error checking parts in most of the examples below. However, it is your sole responsibility to handle errors. zram sysfs attributes always return negative values in case of errors. The list of possible return codes: --EBUSY -- an attempt to modify an attribute that cannot be changed once -the device has been initialised. Please reset device first; --ENOMEM -- zram was not able to allocate enough memory to fulfil your -needs; --EINVAL -- invalid input has been provided. + +======== ============================================================= +-EBUSY an attempt to modify an attribute that cannot be changed once + the device has been initialised. Please reset device first; +-ENOMEM zram was not able to allocate enough memory to fulfil your + needs; +-EINVAL invalid input has been provided. +======== ============================================================= If you use 'echo', the returned value that is changed by 'echo' utility, -and, in general case, something like: +and, in general case, something like:: echo 3 > /sys/block/zram0/max_comp_streams if [ $? -ne 0 ]; @@ -51,7 +59,11 @@ and, in general case, something like: should suffice. -1) Load Module: +1) Load Module +============== + +:: + modprobe zram num_devices=4 This creates 4 devices: /dev/zram{0,1,2,3} @@ -59,6 +71,8 @@ num_devices parameter is optional and tells zram how many devices should be pre-created. Default: 1. 2) Set max number of compression streams +======================================== + Regardless the value passed to this attribute, ZRAM will always allocate multiple compression streams - one per online CPUs - thus allowing several concurrent compression operations. The number of @@ -66,16 +80,20 @@ allocated compression streams goes down when some of the CPUs become offline. There is no single-compression-stream mode anymore, unless you are running a UP system or has only 1 CPU online. -To find out how many streams are currently available: +To find out how many streams are currently available:: + cat /sys/block/zram0/max_comp_streams 3) Select compression algorithm +=============================== + Using comp_algorithm device attribute one can see available and currently selected (shown in square brackets) compression algorithms, change selected compression algorithm (once the device is initialised there is no way to change compression algorithm). -Examples: +Examples:: + #show supported compression algorithms cat /sys/block/zram0/comp_algorithm lzo [lz4] @@ -83,20 +101,23 @@ Examples: #select lzo compression algorithm echo lzo > /sys/block/zram0/comp_algorithm -For the time being, the `comp_algorithm' content does not necessarily +For the time being, the `comp_algorithm` content does not necessarily show every compression algorithm supported by the kernel. We keep this list primarily to simplify device configuration and one can configure a new device with a compression algorithm that is not listed in -`comp_algorithm'. The thing is that, internally, ZRAM uses Crypto API +`comp_algorithm`. The thing is that, internally, ZRAM uses Crypto API and, if some of the algorithms were built as modules, it's impossible to list all of them using, for instance, /proc/crypto or any other method. This, however, has an advantage of permitting the usage of custom crypto compression modules (implementing S/W or H/W compression). 4) Set Disksize +=============== + Set disk size by writing the value to sysfs node 'disksize'. The value can be either in bytes or you can use mem suffixes. -Examples: +Examples:: + # Initialize /dev/zram0 with 50MB disksize echo $((50*1024*1024)) > /sys/block/zram0/disksize @@ -111,10 +132,13 @@ since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the size of the disk when not in use so a huge zram is wasteful. 5) Set memory limit: Optional +============================= + Set memory limit by writing the value to sysfs node 'mem_limit'. The value can be either in bytes or you can use mem suffixes. In addition, you could change the value in runtime. -Examples: +Examples:: + # limit /dev/zram0 with 50MB memory echo $((50*1024*1024)) > /sys/block/zram0/mem_limit @@ -126,7 +150,11 @@ Examples: # To disable memory limit echo 0 > /sys/block/zram0/mem_limit -6) Activate: +6) Activate +=========== + +:: + mkswap /dev/zram0 swapon /dev/zram0 @@ -134,6 +162,7 @@ Examples: mount /dev/zram1 /tmp 7) Add/remove zram devices +========================== zram provides a control interface, which enables dynamic (on-demand) device addition and removal. @@ -142,37 +171,44 @@ In order to add a new /dev/zramX device, perform read operation on hot_add attribute. This will return either new device's device id (meaning that you can use /dev/zram<id>) or error code. -Example: +Example:: + cat /sys/class/zram-control/hot_add 1 To remove the existing /dev/zramX device (where X is a device id) -execute +execute:: + echo X > /sys/class/zram-control/hot_remove -8) Stats: +8) Stats +======== + Per-device statistics are exported as various nodes under /sys/block/zram<id>/ A brief description of exported device attributes. For more details please read Documentation/ABI/testing/sysfs-block-zram. +====================== ====== =============================================== Name access description ----- ------ ----------- +====================== ====== =============================================== disksize RW show and set the device's disk size initstate RO shows the initialization state of the device reset WO trigger device reset -mem_used_max WO reset the `mem_used_max' counter (see later) -mem_limit WO specifies the maximum amount of memory ZRAM can use - to store the compressed data -writeback_limit WO specifies the maximum amount of write IO zram can - write out to backing device as 4KB unit +mem_used_max WO reset the `mem_used_max` counter (see later) +mem_limit WO specifies the maximum amount of memory ZRAM can + use to store the compressed data +writeback_limit WO specifies the maximum amount of write IO zram + can write out to backing device as 4KB unit writeback_limit_enable RW show and set writeback_limit feature -max_comp_streams RW the number of possible concurrent compress operations +max_comp_streams RW the number of possible concurrent compress + operations comp_algorithm RW show and change the compression algorithm compact WO trigger memory compaction debug_stat RO this file is used for zram debugging purposes backing_dev RW set up backend storage for zram to write out idle WO mark allocated slot as idle +====================== ====== =============================================== User space is advised to use the following files to read the device statistics. @@ -188,23 +224,31 @@ The stat file represents device's I/O statistics not accounted by block layer and, thus, not available in zram<id>/stat file. It consists of a single line of text and contains the following stats separated by whitespace: - failed_reads the number of failed reads - failed_writes the number of failed writes - invalid_io the number of non-page-size-aligned I/O requests + + ============= ============================================================= + failed_reads The number of failed reads + failed_writes The number of failed writes + invalid_io The number of non-page-size-aligned I/O requests notify_free Depending on device usage scenario it may account + a) the number of pages freed because of swap slot free - notifications or b) the number of pages freed because of - REQ_OP_DISCARD requests sent by bio. The former ones are - sent to a swap block device when a swap slot is freed, - which implies that this disk is being used as a swap disk. + notifications + b) the number of pages freed because of + REQ_OP_DISCARD requests sent by bio. The former ones are + sent to a swap block device when a swap slot is freed, + which implies that this disk is being used as a swap disk. + The latter ones are sent by filesystem mounted with discard option, whenever some data blocks are getting discarded. + ============= ============================================================= File /sys/block/zram<id>/mm_stat The stat file represents device's mm statistics. It consists of a single line of text and contains the following stats separated by whitespace: + + ================ ============================================================= orig_data_size uncompressed size of data stored in this disk. This excludes same-element-filled pages (same_pages) since no memory is allocated for them. @@ -223,58 +267,71 @@ line of text and contains the following stats separated by whitespace: No memory is allocated for such pages. pages_compacted the number of pages freed during compaction huge_pages the number of incompressible pages + ================ ============================================================= File /sys/block/zram<id>/bd_stat The stat file represents device's backing device statistics. It consists of a single line of text and contains the following stats separated by whitespace: + + ============== ============================================================= bd_count size of data written in backing device. Unit: 4K bytes bd_reads the number of reads from backing device Unit: 4K bytes bd_writes the number of writes to backing device Unit: 4K bytes + ============== ============================================================= + +9) Deactivate +============= + +:: -9) Deactivate: swapoff /dev/zram0 umount /dev/zram1 -10) Reset: - Write any positive value to 'reset' sysfs node - echo 1 > /sys/block/zram0/reset - echo 1 > /sys/block/zram1/reset +10) Reset +========= + + Write any positive value to 'reset' sysfs node:: + + echo 1 > /sys/block/zram0/reset + echo 1 > /sys/block/zram1/reset This frees all the memory allocated for the given device and resets the disksize to zero. You must set the disksize again before reusing the device. -* Optional Feature +Optional Feature +================ -= writeback +writeback +--------- With CONFIG_ZRAM_WRITEBACK, zram can write idle/incompressible page to backing storage rather than keeping it in memory. -To use the feature, admin should set up backing device via +To use the feature, admin should set up backing device via:: - "echo /dev/sda5 > /sys/block/zramX/backing_dev" + echo /dev/sda5 > /sys/block/zramX/backing_dev before disksize setting. It supports only partition at this moment. -If admin want to use incompressible page writeback, they could do via +If admin want to use incompressible page writeback, they could do via:: - "echo huge > /sys/block/zramX/write" + echo huge > /sys/block/zramX/write To use idle page writeback, first, user need to declare zram pages -as idle. +as idle:: - "echo all > /sys/block/zramX/idle" + echo all > /sys/block/zramX/idle From now on, any pages on zram are idle pages. The idle mark will be removed until someone request access of the block. IOW, unless there is access request, those pages are still idle pages. -Admin can request writeback of those idle pages at right timing via +Admin can request writeback of those idle pages at right timing via:: - "echo idle > /sys/block/zramX/writeback" + echo idle > /sys/block/zramX/writeback With the command, zram writeback idle pages from memory to the storage. @@ -285,7 +342,7 @@ to guarantee storage health for entire product life. To overcome the concern, zram supports "writeback_limit" feature. The "writeback_limit_enable"'s default value is 0 so that it doesn't limit any writeback. IOW, if admin want to apply writeback budget, he should -enable writeback_limit_enable via +enable writeback_limit_enable via:: $ echo 1 > /sys/block/zramX/writeback_limit_enable @@ -296,7 +353,7 @@ until admin set the budget via /sys/block/zramX/writeback_limit. assigned via /sys/block/zramX/writeback_limit is meaninless.) If admin want to limit writeback as per-day 400M, he could do it -like below. +like below:: $ MB_SHIFT=20 $ 4K_SHIFT=12 @@ -305,16 +362,16 @@ like below. $ echo 1 > /sys/block/zram0/writeback_limit_enable If admin want to allow further write again once the bugdet is exausted, -he could do it like below +he could do it like below:: $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \ /sys/block/zram0/writeback_limit -If admin want to see remaining writeback budget since he set, +If admin want to see remaining writeback budget since he set:: $ cat /sys/block/zramX/writeback_limit -If admin want to disable writeback limit, he could do +If admin want to disable writeback limit, he could do:: $ echo 0 > /sys/block/zramX/writeback_limit_enable @@ -326,25 +383,35 @@ budget in next setting is user's job. If admin want to measure writeback count in a certain period, he could know it via /sys/block/zram0/bd_stat's 3rd column. -= memory tracking +memory tracking +=============== With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the zram block. It could be useful to catch cold or incompressible pages of the process with*pagemap. + If you enable the feature, you could see block state via -/sys/kernel/debug/zram/zram0/block_state". The output is as follows, +/sys/kernel/debug/zram/zram0/block_state". The output is as follows:: 300 75.033841 .wh. 301 63.806904 s... 302 63.806919 ..hi -First column is zram's block index. -Second column is access time since the system was booted -Third column is state of the block. -(s: same page -w: written page to backing store -h: huge page -i: idle page) +First column + zram's block index. +Second column + access time since the system was booted +Third column + state of the block: + + s: + same page + w: + written page to backing store + h: + huge page + i: + idle page First line of above example says 300th block is accessed at 75.033841sec and the block's state is huge so it is written back to the backing diff --git a/MAINTAINERS b/MAINTAINERS index ca1d09d0c44b..3ed27c0c36d8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10823,7 +10823,7 @@ M: Josef Bacik <josef(a)toxicpanda.com> S: Maintained L: linux-block(a)vger.kernel.org L: nbd(a)other.debian.org -F: Documentation/blockdev/nbd.txt +F: Documentation/blockdev/nbd.rst F: drivers/block/nbd.c F: include/uapi/linux/nbd.h @@ -11801,7 +11801,7 @@ PARIDE DRIVERS FOR PARALLEL PORT IDE DEVICES M: Tim Waugh <tim(a)cyberelk.net> L: linux-parport(a)lists.infradead.org (subscribers-only) S: Maintained -F: Documentation/blockdev/paride.txt +F: Documentation/blockdev/paride.rst F: drivers/block/paride/ PARISC ARCHITECTURE @@ -13077,7 +13077,7 @@ F: drivers/net/wireless/ralink/rt2x00/ RAMDISK RAM BLOCK DEVICE DRIVER M: Jens Axboe <axboe(a)kernel.dk> S: Maintained -F: Documentation/blockdev/ramdisk.txt +F: Documentation/blockdev/ramdisk.rst F: drivers/block/brd.c RANCHU VIRTUAL BOARD FOR MIPS @@ -17360,7 +17360,7 @@ R: Sergey Senozhatsky <sergey.senozhatsky.work(a)gmail.com> L: linux-kernel(a)vger.kernel.org S: Maintained F: drivers/block/zram/ -F: Documentation/blockdev/zram.txt +F: Documentation/blockdev/zram.rst ZS DECSTATION Z85C30 SERIAL DRIVER M: "Maciej W. Rozycki" <macro(a)linux-mips.org> diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 96ec7e0fc1ea..c43690b973d8 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -31,7 +31,7 @@ config BLK_DEV_FD If you want to use the floppy disk drive(s) of your PC under Linux, say Y. Information about this driver, especially important for IBM Thinkpad users, is contained in - <file:Documentation/blockdev/floppy.txt>. + <file:Documentation/blockdev/floppy.rst>. That file also contains the location of the Floppy driver FAQ as well as location of the fdutils package used to configure additional parameters of the driver at run time. @@ -96,7 +96,7 @@ config PARIDE your computer's parallel port. Most of them are actually IDE devices using a parallel port IDE adapter. This option enables the PARIDE subsystem which contains drivers for many of these external drives. - Read <file:Documentation/blockdev/paride.txt> for more information. + Read <file:Documentation/blockdev/paride.rst> for more information. If you have said Y to the "Parallel-port support" configuration option, you may share a single port between your printer and other @@ -261,7 +261,7 @@ config BLK_DEV_NBD userland (making server and client physically the same computer, communicating using the loopback network device). - Read <file:Documentation/blockdev/nbd.txt> for more information, + Read <file:Documentation/blockdev/nbd.rst> for more information, especially about where to find the server code, which runs in user space and does not need special kernel support. @@ -303,7 +303,7 @@ config BLK_DEV_RAM during the initial install of Linux. Note that the kernel command line option "ramdisk=XX" is now obsolete. - For details, read <file:Documentation/blockdev/ramdisk.txt>. + For details, read <file:Documentation/blockdev/ramdisk.rst>. To compile this driver as a module, choose M here: the module will be called brd. An alias "rd" has been defined diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b8998abd86a5..14701be9f916 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4423,7 +4423,7 @@ static int __init floppy_setup(char *str) pr_cont("\n"); } else DPRINT("botched floppy option\n"); - DPRINT("Read Documentation/blockdev/floppy.txt\n"); + DPRINT("Read Documentation/blockdev/floppy.rst\n"); return 0; } diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 1ffc64770643..e06b99d54816 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -12,7 +12,7 @@ config ZRAM It has several use cases, for example: /tmp storage, use as swap disks and maybe many more. - See Documentation/blockdev/zram.txt for more information. + See Documentation/blockdev/zram.rst for more information. config ZRAM_WRITEBACK bool "Write back incompressible or idle page to backing device" @@ -26,7 +26,7 @@ config ZRAM_WRITEBACK With /sys/block/zramX/{idle,writeback}, application could ask idle page's writeback to the backing device to save in memory. - See Documentation/blockdev/zram.txt for more information. + See Documentation/blockdev/zram.rst for more information. config ZRAM_MEMORY_TRACKING bool "Track zRam block status" @@ -36,4 +36,4 @@ config ZRAM_MEMORY_TRACKING of zRAM. Admin could see the information via /sys/kernel/debug/zram/zramX/block_state. - See Documentation/blockdev/zram.txt for more information. + See Documentation/blockdev/zram.rst for more information. diff --git a/tools/testing/selftests/zram/README b/tools/testing/selftests/zram/README index 7972cc512408..5fa378391d3b 100644 --- a/tools/testing/selftests/zram/README +++ b/tools/testing/selftests/zram/README @@ -37,4 +37,4 @@ Commands required for testing: - mkfs/ mkfs.ext4 For more information please refer: -kernel-source-tree/Documentation/blockdev/zram.txt +kernel-source-tree/Documentation/blockdev/zram.rst -- 2.20.1

5 years

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror April 2019