Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "VM:
   - z3fold fixes and enhancements by Henry Burns and Vitaly Wool

   - more accurate reclaimed slab caches calculations by Yafang Shao

   - fix MAP_UNINITIALIZED UAPI symbol to not depend on config, by
     Christoph Hellwig

   - !CONFIG_MMU fixes by Christoph Hellwig

   - new novmcoredd parameter to omit device dumps from vmcore, by
     Kairui Song

   - new test_meminit module for testing heap and pagealloc
     initialization, by Alexander Potapenko

   - ioremap improvements for huge mappings, by Anshuman Khandual

   - generalize kprobe page fault handling, by Anshuman Khandual

   - device-dax hotplug fixes and improvements, by Pavel Tatashin

   - enable synchronous DAX fault on powerpc, by Aneesh Kumar K.V

   - add pte_devmap() support for arm64, by Robin Murphy

   - unify locked_vm accounting with a helper, by Daniel Jordan

   - several misc fixes

  core/lib:
   - new typeof_member() macro including some users, by Alexey Dobriyan

   - make BIT() and GENMASK() available in asm, by Masahiro Yamada

   - changed LIST_POISON2 on x86_64 to 0xdead000000000122 for better
     code generation, by Alexey Dobriyan

   - rbtree code size optimizations, by Michel Lespinasse

   - convert struct pid count to refcount_t, by Joel Fernandes

  get_maintainer.pl:
   - add --no-moderated switch to skip moderated ML's, by Joe Perches

  misc:
   - ptrace PTRACE_GET_SYSCALL_INFO interface

   - coda updates

   - gdb scripts, various"

[ Using merge message suggestion from Vlastimil Babka, with some editing - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (100 commits)
  fs/select.c: use struct_size() in kmalloc()
  mm: add account_locked_vm utility function
  arm64: mm: implement pte_devmap support
  mm: introduce ARCH_HAS_PTE_DEVMAP
  mm: clean up is_device_*_page() definitions
  mm/mmap: move common defines to mman-common.h
  mm: move MAP_SYNC to asm-generic/mman-common.h
  device-dax: "Hotremove" persistent memory that is used like normal RAM
  mm/hotplug: make remove_memory() interface usable
  device-dax: fix memory and resource leak if hotplug fails
  include/linux/lz4.h: fix spelling and copy-paste errors in documentation
  ipc/mqueue.c: only perform resource calculation if user valid
  include/asm-generic/bug.h: fix "cut here" for WARN_ON for __WARN_TAINT architectures
  scripts/gdb: add helpers to find and list devices
  scripts/gdb: add lx-genpd-summary command
  drivers/pps/pps.c: clear offset flags in PPS_SETPARAMS ioctl
  kernel/pid.c: convert struct pid count to refcount_t
  drivers/rapidio/devices/rio_mport_cdev.c: NUL terminate some strings
  select: shift restore_saved_sigmask_unless() into poll_select_copy_remaining()
  select: change do_poll() to return -ERESTARTNOHAND rather than -EINTR
  ...

4 files changed, 132 insertions, 65 deletions

diff --git a/kernel/pid.c b/kernel/pid.c
index 16263b526560..0a9f2e437217 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -37,14 +37,14 @@
 #include <linux/init_task.h>
 #include <linux/syscalls.h>
 #include <linux/proc_ns.h>
-#include <linux/proc_fs.h>
+#include <linux/refcount.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 
 struct pid init_struct_pid = {
-        .count          = ATOMIC_INIT(1),
+        .count          = REFCOUNT_INIT(1),
         .tasks          = {
                 { .first = NULL },
                 { .first = NULL },
@@ -108,8 +108,7 @@ void put_pid(struct pid *pid)
                 return;
 
         ns = pid->numbers[pid->level].ns;
-        if ((atomic_read(&pid->count) == 1) ||
-             atomic_dec_and_test(&pid->count)) {
+        if (refcount_dec_and_test(&pid->count)) {
                 kmem_cache_free(ns->pid_cachep, pid);
                 put_pid_ns(ns);
         }
@@ -212,7 +211,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
         }
 
         get_pid_ns(ns);
-        atomic_set(&pid->count, 1);
+        refcount_set(&pid->count, 1);
         for (type = 0; type < PIDTYPE_MAX; ++type)
                 INIT_HLIST_HEAD(&pid->tasks[type]);
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 83a531cea2f3..cb9ddcc08119 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -32,6 +32,8 @@
 #include <linux/compat.h>
 #include <linux/sched/signal.h>
 
+#include <asm/syscall.h>        /* for syscall_get_* */
+
 /*
  * Access another process' address space via ptrace.
  * Source/target buffer must be kernel space,
@@ -897,7 +899,100 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
  * to ensure no machine forgets it.
  */
 EXPORT_SYMBOL_GPL(task_user_regset_view);
-#endif
+
+static unsigned long
+ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
+                              struct ptrace_syscall_info *info)
+{
+        unsigned long args[ARRAY_SIZE(info->entry.args)];
+        int i;
+
+        info->op = PTRACE_SYSCALL_INFO_ENTRY;
+        info->entry.nr = syscall_get_nr(child, regs);
+        syscall_get_arguments(child, regs, args);
+        for (i = 0; i < ARRAY_SIZE(args); i++)
+                info->entry.args[i] = args[i];
+
+        /* args is the last field in struct ptrace_syscall_info.entry */
+        return offsetofend(struct ptrace_syscall_info, entry.args);
+}
+
+static unsigned long
+ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs,
+                                struct ptrace_syscall_info *info)
+{
+        /*
+         * As struct ptrace_syscall_info.entry is currently a subset
+         * of struct ptrace_syscall_info.seccomp, it makes sense to
+         * initialize that subset using ptrace_get_syscall_info_entry().
+         * This can be reconsidered in the future if these structures
+         * diverge significantly enough.
+         */
+        ptrace_get_syscall_info_entry(child, regs, info);
+        info->op = PTRACE_SYSCALL_INFO_SECCOMP;
+        info->seccomp.ret_data = child->ptrace_message;
+
+        /* ret_data is the last field in struct ptrace_syscall_info.seccomp */
+        return offsetofend(struct ptrace_syscall_info, seccomp.ret_data);
+}
+
+static unsigned long
+ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
+                             struct ptrace_syscall_info *info)
+{
+        info->op = PTRACE_SYSCALL_INFO_EXIT;
+        info->exit.rval = syscall_get_error(child, regs);
+        info->exit.is_error = !!info->exit.rval;
+        if (!info->exit.is_error)
+                info->exit.rval = syscall_get_return_value(child, regs);
+
+        /* is_error is the last field in struct ptrace_syscall_info.exit */
+        return offsetofend(struct ptrace_syscall_info, exit.is_error);
+}
+
+static int
+ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size,
+                        void __user *datavp)
+{
+        struct pt_regs *regs = task_pt_regs(child);
+        struct ptrace_syscall_info info = {
+                .op = PTRACE_SYSCALL_INFO_NONE,
+                .arch = syscall_get_arch(child),
+                .instruction_pointer = instruction_pointer(regs),
+                .stack_pointer = user_stack_pointer(regs),
+        };
+        unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry);
+        unsigned long write_size;
+
+        /*
+         * This does not need lock_task_sighand() to access
+         * child->last_siginfo because ptrace_freeze_traced()
+         * called earlier by ptrace_check_attach() ensures that
+         * the tracee cannot go away and clear its last_siginfo.
+         */
+        switch (child->last_siginfo ? child->last_siginfo->si_code : 0) {
+        case SIGTRAP | 0x80:
+                switch (child->ptrace_message) {
+                case PTRACE_EVENTMSG_SYSCALL_ENTRY:
+                        actual_size = ptrace_get_syscall_info_entry(child, regs,
+                                                                    &info);
+                        break;
+                case PTRACE_EVENTMSG_SYSCALL_EXIT:
+                        actual_size = ptrace_get_syscall_info_exit(child, regs,
+                                                                   &info);
+                        break;
+                }
+                break;
+        case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8):
+                actual_size = ptrace_get_syscall_info_seccomp(child, regs,
+                                                              &info);
+                break;
+        }
+
+        write_size = min(actual_size, user_size);
+        return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size;
+}
+#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
 
 int ptrace_request(struct task_struct *child, long request,
                    unsigned long addr, unsigned long data)
@@ -1114,6 +1209,10 @@ int ptrace_request(struct task_struct *child, long request,
                         ret = __put_user(kiov.iov_len, &uiov->iov_len);
                 break;
         }
+
+        case PTRACE_GET_SYSCALL_INFO:
+                ret = ptrace_get_syscall_info(child, addr, datavp);
+                break;
 #endif
 
         case PTRACE_SECCOMP_GET_FILTER:
diff --git a/kernel/signal.c b/kernel/signal.c
index dabe100d2091..91b789dd6e72 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2951,80 +2951,49 @@ EXPORT_SYMBOL(sigprocmask);
  *
  * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
  * epoll_pwait where a new sigmask is passed from userland for the syscalls.
+ *
+ * Note that it does set_restore_sigmask() in advance, so it must be always
+ * paired with restore_saved_sigmask_unless() before return from syscall.
  */
-int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set,
-                     sigset_t *oldset, size_t sigsetsize)
+int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize)
 {
-        if (!usigmask)
-                return 0;
+        sigset_t kmask;
 
+        if (!umask)
+                return 0;
         if (sigsetsize != sizeof(sigset_t))
                 return -EINVAL;
-        if (copy_from_user(set, usigmask, sizeof(sigset_t)))
+        if (copy_from_user(&kmask, umask, sizeof(sigset_t)))
                 return -EFAULT;
 
-        *oldset = current->blocked;
-        set_current_blocked(set);
+        set_restore_sigmask();
+        current->saved_sigmask = current->blocked;
+        set_current_blocked(&kmask);
 
         return 0;
 }
-EXPORT_SYMBOL(set_user_sigmask);
 
 #ifdef CONFIG_COMPAT
-int set_compat_user_sigmask(const compat_sigset_t __user *usigmask,
-                            sigset_t *set, sigset_t *oldset,
+int set_compat_user_sigmask(const compat_sigset_t __user *umask,
                             size_t sigsetsize)
 {
-        if (!usigmask)
-                return 0;
+        sigset_t kmask;
 
+        if (!umask)
+                return 0;
         if (sigsetsize != sizeof(compat_sigset_t))
                 return -EINVAL;
-        if (get_compat_sigset(set, usigmask))
+        if (get_compat_sigset(&kmask, umask))
                 return -EFAULT;
 
-        *oldset = current->blocked;
-        set_current_blocked(set);
+        set_restore_sigmask();
+        current->saved_sigmask = current->blocked;
+        set_current_blocked(&kmask);
 
         return 0;
 }
-EXPORT_SYMBOL(set_compat_user_sigmask);
 #endif
 
-/*
- * restore_user_sigmask:
- * usigmask: sigmask passed in from userland.
- * sigsaved: saved sigmask when the syscall started and changed the sigmask to
- *           usigmask.
- *
- * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
- * epoll_pwait where a new sigmask is passed in from userland for the syscalls.
- */
-void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved,
-                                bool interrupted)
-{
-
-        if (!usigmask)
-                return;
-        /*
-         * When signals are pending, do not restore them here.
-         * Restoring sigmask here can lead to delivering signals that the above
-         * syscalls are intended to block because of the sigmask passed in.
-         */
-        if (interrupted) {
-                current->saved_sigmask = *sigsaved;
-                set_restore_sigmask();
-                return;
-        }
-
-        /*
-         * This is needed because the fast syscall return path does not restore
-         * saved_sigmask when signals are not pending.
-         */
-        set_current_blocked(sigsaved);
-}
-EXPORT_SYMBOL(restore_user_sigmask);
-
 /**
  *  sys_rt_sigprocmask - change the list of currently blocked signals
  *  @how: whether to add, remove, or set signals
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1c1ad1e14f21..43186ccfa139 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -188,17 +188,17 @@ extern int no_unaligned_warning;
  * enum sysctl_writes_mode - supported sysctl write modes
  *
  * @SYSCTL_WRITES_LEGACY: each write syscall must fully contain the sysctl value
- *      to be written, and multiple writes on the same sysctl file descriptor
- *      will rewrite the sysctl value, regardless of file position. No warning
- *      is issued when the initial position is not 0.
+ *      to be written, and multiple writes on the same sysctl file descriptor
+ *      will rewrite the sysctl value, regardless of file position. No warning
+ *      is issued when the initial position is not 0.
  * @SYSCTL_WRITES_WARN: same as above but warn when the initial file position is
- *      not 0.
+ *      not 0.
  * @SYSCTL_WRITES_STRICT: writes to numeric sysctl entries must always be at
- *      file position 0 and the value must be fully contained in the buffer
- *      sent to the write syscall. If dealing with strings respect the file
- *      position, but restrict this to the max length of the buffer, anything
- *      passed the max lenght will be ignored. Multiple writes will append
- *      to the buffer.
+ *      file position 0 and the value must be fully contained in the buffer
+ *      sent to the write syscall. If dealing with strings respect the file
+ *      position, but restrict this to the max length of the buffer, anything
+ *      passed the max length will be ignored. Multiple writes will append
+ *      to the buffer.
  *
  * These write modes control how current file position affects the behavior of
  * updating sysctl values through the proc interface on each write.