Merge branch 'akpm' (patches from Andrew)

Merge third patch-bomb from Andrew Morton:
 "I'm pretty much done for -rc1 now:

   - the rest of MM, basically

   - lib/ updates

   - checkpatch, epoll, hfs, fatfs, ptrace, coredump, exit

   - cpu_mask simplifications

   - kexec, rapidio, MAINTAINERS etc, etc.

   - more dma-mapping cleanups/simplifications from hch"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (109 commits)
  MAINTAINERS: add/fix git URLs for various subsystems
  mm: memcontrol: add "sock" to cgroup2 memory.stat
  mm: memcontrol: basic memory statistics in cgroup2 memory controller
  mm: memcontrol: do not uncharge old page in page cache replacement
  Documentation: cgroup: add memory.swap.{current,max} description
  mm: free swap cache aggressively if memcg swap is full
  mm: vmscan: do not scan anon pages if memcg swap limit is hit
  swap.h: move memcg related stuff to the end of the file
  mm: memcontrol: replace mem_cgroup_lruvec_online with mem_cgroup_online
  mm: vmscan: pass memcg to get_scan_count()
  mm: memcontrol: charge swap to cgroup2
  mm: memcontrol: clean up alloc, online, offline, free functions
  mm: memcontrol: flatten struct cg_proto
  mm: memcontrol: rein in the CONFIG space madness
  net: drop tcp_memcontrol.c
  mm: memcontrol: introduce CONFIG_MEMCG_LEGACY_KMEM
  mm: memcontrol: allow to disable kmem accounting for cgroup2
  mm: memcontrol: account "kmem" consumers in cgroup2 memory controller
  mm: memcontrol: move kmem accounting code to CONFIG_MEMCG
  mm: memcontrol: separate kmem code from legacy tcp accounting code
  ...

14 files changed, 104 insertions, 96 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 85ff5e2..5b9d396 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -759,71 +759,33 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
 EXPORT_SYMBOL(cpu_all_bits);
 
 #ifdef CONFIG_INIT_ALL_POSSIBLE
-static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
-	= CPU_BITS_ALL;
+struct cpumask __cpu_possible_mask __read_mostly
+	= {CPU_BITS_ALL};
 #else
-static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
+struct cpumask __cpu_possible_mask __read_mostly;
 #endif
-const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
-EXPORT_SYMBOL(cpu_possible_mask);
+EXPORT_SYMBOL(__cpu_possible_mask);
 
-static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
-const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
-EXPORT_SYMBOL(cpu_online_mask);
+struct cpumask __cpu_online_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_online_mask);
 
-static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
-const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
-EXPORT_SYMBOL(cpu_present_mask);
+struct cpumask __cpu_present_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_present_mask);
 
-static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
-const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
-EXPORT_SYMBOL(cpu_active_mask);
-
-void set_cpu_possible(unsigned int cpu, bool possible)
-{
-	if (possible)
-		cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
-	else
-		cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
-}
-
-void set_cpu_present(unsigned int cpu, bool present)
-{
-	if (present)
-		cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
-	else
-		cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
-}
-
-void set_cpu_online(unsigned int cpu, bool online)
-{
-	if (online) {
-		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
-		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
-	} else {
-		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
-	}
-}
-
-void set_cpu_active(unsigned int cpu, bool active)
-{
-	if (active)
-		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
-	else
-		cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
-}
+struct cpumask __cpu_active_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_active_mask);
 
 void init_cpu_present(const struct cpumask *src)
 {
-	cpumask_copy(to_cpumask(cpu_present_bits), src);
+	cpumask_copy(&__cpu_present_mask, src);
 }
 
 void init_cpu_possible(const struct cpumask *src)
 {
-	cpumask_copy(to_cpumask(cpu_possible_bits), src);
+	cpumask_copy(&__cpu_possible_mask, src);
 }
 
 void init_cpu_online(const struct cpumask *src)
 {
-	cpumask_copy(to_cpumask(cpu_online_bits), src);
+	cpumask_copy(&__cpu_online_mask, src);
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bf82441..c095741 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3376,7 +3376,7 @@ find_lively_task_by_vpid(pid_t vpid)
 
 	/* Reuse ptrace permission checks for now. */
 	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
 		goto errout;
 
 	return task;
diff --git a/kernel/exit.c b/kernel/exit.c
index 07110c6..10e0882 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -59,8 +59,6 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
-static void exit_mm(struct task_struct *tsk);
-
 static void __unhash_process(struct task_struct *p, bool group_dead)
 {
 	nr_threads--;
@@ -1120,8 +1118,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 static int *task_stopped_code(struct task_struct *p, bool ptrace)
 {
 	if (ptrace) {
-		if (task_is_stopped_or_traced(p) &&
-		    !(p->jobctl & JOBCTL_LISTENING))
+		if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING))
 			return &p->exit_code;
 	} else {
 		if (p->signal->flags & SIGNAL_STOP_STOPPED)
diff --git a/kernel/futex.c b/kernel/futex.c
index c6f5145..0773f2b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2884,7 +2884,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
 	}
 
 	ret = -EPERM;
-	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
 		goto err_unlock;
 
 	head = p->robust_list;
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 55c8c93..4ae3232 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
 	}
 
 	ret = -EPERM;
-	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
 		goto err_unlock;
 
 	head = p->compat_robust_list;
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 0aa69ea..3a47fa9 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 			&task2->signal->cred_guard_mutex);
 	if (ret)
 		goto err;
-	if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
-	    !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+	if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
+	    !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) {
 		ret = -EPERM;
 		goto err_unlock;
 	}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index d873b64..ee70aef 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -63,16 +63,16 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
 	if (ret)
 		goto out_free_image;
 
-	ret = sanity_check_segment_list(image);
-	if (ret)
-		goto out_free_image;
-
-	 /* Enable the special crash kernel control page allocation policy. */
 	if (kexec_on_panic) {
+		/* Enable special crash kernel control page alloc policy. */
 		image->control_page = crashk_res.start;
 		image->type = KEXEC_TYPE_CRASH;
 	}
 
+	ret = sanity_check_segment_list(image);
+	if (ret)
+		goto out_free_image;
+
 	/*
 	 * Find a location for the control code buffer, and add it
 	 * the vector of segments so that it's pages will also be
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index c823f30..8dc6591 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -310,12 +310,9 @@ static void kimage_free_pages(struct page *page)
 
 void kimage_free_page_list(struct list_head *list)
 {
-	struct list_head *pos, *next;
+	struct page *page, *next;
 
-	list_for_each_safe(pos, next, list) {
-		struct page *page;
-
-		page = list_entry(pos, struct page, lru);
+	list_for_each_entry_safe(page, next, list, lru) {
 		list_del(&page->lru);
 		kimage_free_pages(page);
 	}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b70ada0..007b791 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -109,11 +109,13 @@ int __weak arch_kimage_file_post_load_cleanup(struct kimage *image)
 	return -EINVAL;
 }
 
+#ifdef CONFIG_KEXEC_VERIFY_SIG
 int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
 					unsigned long buf_len)
 {
 	return -EKEYREJECTED;
 }
+#endif
 
 /* Apply relocations of type RELA */
 int __weak
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index e4392a6..0a52315 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -15,6 +15,27 @@ int kimage_is_destination_range(struct kimage *image,
 extern struct mutex kexec_mutex;
 
 #ifdef CONFIG_KEXEC_FILE
+struct kexec_sha_region {
+	unsigned long start;
+	unsigned long len;
+};
+
+/*
+ * Keeps track of buffer parameters as provided by caller for requesting
+ * memory placement of buffer.
+ */
+struct kexec_buf {
+	struct kimage *image;
+	char *buffer;
+	unsigned long bufsz;
+	unsigned long mem;
+	unsigned long memsz;
+	unsigned long buf_align;
+	unsigned long buf_min;
+	unsigned long buf_max;
+	bool top_down;		/* allocate from top of memory hole */
+};
+
 void kimage_file_post_load_cleanup(struct kimage *image);
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e794391..c963ba5 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -233,7 +233,11 @@ struct printk_log {
 	u8 facility;		/* syslog facility */
 	u8 flags:5;		/* internal record flags */
 	u8 level:3;		/* syslog level */
-};
+}
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+__packed __aligned(4)
+#endif
+;
 
 /*
  * The logbuf_lock protects kmsg buffer, indices, counters.  This can be taken
@@ -274,11 +278,7 @@ static u32 clear_idx;
 #define LOG_FACILITY(v)		((v) >> 3 & 0xff)
 
 /* record buffer */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-#define LOG_ALIGN 4
-#else
 #define LOG_ALIGN __alignof__(struct printk_log)
-#endif
 #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
 static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index b760bae..2341efe 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -219,6 +219,14 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	const struct cred *cred = current_cred(), *tcred;
+	int dumpable = 0;
+	kuid_t caller_uid;
+	kgid_t caller_gid;
+
+	if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) {
+		WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n");
+		return -EPERM;
+	}
 
 	/* May we inspect the given task?
 	 * This check is used both for attaching with ptrace
@@ -228,18 +236,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	 * because setting up the necessary parent/child relationship
 	 * or halting the specified task is impossible.
 	 */
-	int dumpable = 0;
+
 	/* Don't let security modules deny introspection */
 	if (same_thread_group(task, current))
 		return 0;
 	rcu_read_lock();
+	if (mode & PTRACE_MODE_FSCREDS) {
+		caller_uid = cred->fsuid;
+		caller_gid = cred->fsgid;
+	} else {
+		/*
+		 * Using the euid would make more sense here, but something
+		 * in userland might rely on the old behavior, and this
+		 * shouldn't be a security problem since
+		 * PTRACE_MODE_REALCREDS implies that the caller explicitly
+		 * used a syscall that requests access to another process
+		 * (and not a filesystem syscall to procfs).
+		 */
+		caller_uid = cred->uid;
+		caller_gid = cred->gid;
+	}
 	tcred = __task_cred(task);
-	if (uid_eq(cred->uid, tcred->euid) &&
-	    uid_eq(cred->uid, tcred->suid) &&
-	    uid_eq(cred->uid, tcred->uid)  &&
-	    gid_eq(cred->gid, tcred->egid) &&
-	    gid_eq(cred->gid, tcred->sgid) &&
-	    gid_eq(cred->gid, tcred->gid))
+	if (uid_eq(caller_uid, tcred->euid) &&
+	    uid_eq(caller_uid, tcred->suid) &&
+	    uid_eq(caller_uid, tcred->uid)  &&
+	    gid_eq(caller_gid, tcred->egid) &&
+	    gid_eq(caller_gid, tcred->sgid) &&
+	    gid_eq(caller_gid, tcred->gid))
 		goto ok;
 	if (ptrace_has_cap(tcred->user_ns, mode))
 		goto ok;
@@ -306,7 +329,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 		goto out;
 
 	task_lock(task);
-	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
 	task_unlock(task);
 	if (retval)
 		goto unlock_creds;
@@ -364,8 +387,14 @@ unlock_creds:
 	mutex_unlock(&task->signal->cred_guard_mutex);
 out:
 	if (!retval) {
-		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
-			    TASK_UNINTERRUPTIBLE);
+		/*
+		 * We do not bother to change retval or clear JOBCTL_TRAPPING
+		 * if wait_on_bit() was interrupted by SIGKILL. The tracer will
+		 * not return to user-mode, it will exit and clear this bit in
+		 * __ptrace_unlink() if it wasn't already cleared by the tracee;
+		 * and until then nobody can ptrace this task.
+		 */
+		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
 		proc_ptrace_connector(task, PTRACE_ATTACH);
 	}
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 6af9212..78947de 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1853,11 +1853,13 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 		user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
 	}
 
-	if (prctl_map.exe_fd != (u32)-1)
+	if (prctl_map.exe_fd != (u32)-1) {
 		error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
-	down_read(&mm->mmap_sem);
-	if (error)
-		goto out;
+		if (error)
+			return error;
+	}
+
+	down_write(&mm->mmap_sem);
 
 	/*
 	 * We don't validate if these members are pointing to
@@ -1894,10 +1896,8 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 	if (prctl_map.auxv_size)
 		memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
 
-	error = 0;
-out:
-	up_read(&mm->mmap_sem);
-	return error;
+	up_write(&mm->mmap_sem);
+	return 0;
 }
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 
@@ -1963,7 +1963,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
 
 	error = -EINVAL;
 
-	down_read(&mm->mmap_sem);
+	down_write(&mm->mmap_sem);
 	vma = find_vma(mm, addr);
 
 	prctl_map.start_code	= mm->start_code;
@@ -2056,7 +2056,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
 
 	error = 0;
 out:
-	up_read(&mm->mmap_sem);
+	up_write(&mm->mmap_sem);
 	return error;
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c810f8a..9142036 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -173,7 +173,7 @@ extern int no_unaligned_warning;
 #define SYSCTL_WRITES_WARN	 0
 #define SYSCTL_WRITES_STRICT	 1
 
-static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
 
 static int proc_do_cad_pid(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);