!357 Backport CVEs, bugfixes, performance and other

Merge Pull Request from: @zhangjialin11 
 
Pull new CVEs:
CVE-2023-20928
CVE-2022-4696
CVE-2023-0210
CVE-2022-4842

fs bugfixes from Li Lingfeng, yangerkun and Zhihao Cheng
mm bugfixes from Ye Weihua, Ma Wupeng and Zheng Zucheng
tracing bugfixes from Zheng Yejian
performance from Jialin Zhang
other from Guo Mengqi






 
 
Link:https://gitee.com/openeuler/kernel/pulls/357 

Reviewed-by: Zheng Zengkai <zhengzengkai@huawei.com> 
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com> 

arch/arm64/configs/openeuler_defconfig

@@ -3395,7 +3395,6 @@ CONFIG_TCG_TIS_ST33ZP24_I2C=m
 CONFIG_TCG_TIS_ST33ZP24_SPI=m
 # CONFIG_XILLYBUS is not set
 CONFIG_PIN_MEMORY_DEV=m
-CONFIG_HISI_SVM=m
 # CONFIG_RANDOM_TRUST_CPU is not set
 # CONFIG_RANDOM_TRUST_BOOTLOADER is not set
 # end of Character devices

drivers/android/binder.c

@@ -6081,6 +6081,7 @@ const struct file_operations binder_fops = {
 	.open = binder_open,
 	.flush = binder_flush,
 	.release = binder_release,
+	.may_pollfree = true,
 };
 
 static int __init init_binder_device(const char *name)

drivers/android/binder_alloc.c

@@ -212,7 +212,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		mm = alloc->vma_vm_mm;
 
 	if (mm) {
-		mmap_read_lock(mm);
+		mmap_write_lock(mm);
 		vma = alloc->vma;
 	}
 
@@ -270,7 +270,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		trace_binder_alloc_page_end(alloc, index);
 	}
 	if (mm) {
-		mmap_read_unlock(mm);
+		mmap_write_unlock(mm);
 		mmput(mm);
 	}
 	return 0;
@@ -303,7 +303,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 	}
 err_no_vma:
 	if (mm) {
-		mmap_read_unlock(mm);
+		mmap_write_unlock(mm);
 		mmput(mm);
 	}
 	return vma ? -ENOMEM : -ESRCH;

drivers/char/Kconfig

@@ -478,16 +478,6 @@ config PIN_MEMORY_DEV
 	help
 	  pin memory driver
 
-config HISI_SVM
-	tristate "Hisilicon svm driver"
-	depends on ARM64 && ARM_SMMU_V3 && MMU_NOTIFIER
-	default m
-	help
-	  This driver provides character-level access to Hisilicon
-	  SVM chipset. Typically, you can bind a task to the
-	  svm and share the virtual memory with hisilicon svm device.
-	  When in doubt, say "N".
-
 config RANDOM_TRUST_CPU
 	bool "Initialize RNG using CPU RNG instructions"
 	default y

drivers/char/Makefile

@@ -48,4 +48,3 @@ obj-$(CONFIG_XILLYBUS)		+= xillybus/
 obj-$(CONFIG_POWERNV_OP_PANEL)	+= powernv-op-panel.o
 obj-$(CONFIG_ADI)		+= adi.o
 obj-$(CONFIG_PIN_MEMORY_DEV)	+= pin_memory.o
-obj-$(CONFIG_HISI_SVM)		+= svm.o

fs/io_uring.c

@@ -935,7 +935,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.hash_reg_file		= 1,
 		.unbound_nonreg_file	= 1,
-		.work_flags		= IO_WQ_WORK_BLKCG,
+		.work_flags		= IO_WQ_WORK_BLKCG | IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_PROVIDE_BUFFERS] = {},
 	[IORING_OP_REMOVE_BUFFERS] = {},
@@ -5233,6 +5233,11 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
 	struct io_ring_ctx *ctx = req->ctx;
 	bool cancel = false;
 
+	if (req->file->f_op->may_pollfree) {
+		spin_lock_irq(&ctx->completion_lock);
+		return -EOPNOTSUPP;
+	}
+
 	INIT_HLIST_NODE(&req->hash_node);
 	io_init_poll_iocb(poll, mask, wake_func);
 	poll->file = req->file;

fs/iomap/buffered-io.c

@@ -1460,13 +1460,6 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
 			PF_MEMALLOC))
 		goto redirty;
 
-	/*
-	 * Given that we do not allow direct reclaim to call us, we should
-	 * never be called in a recursive filesystem reclaim context.
-	 */
-	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
-		goto redirty;
-
 	/*
 	 * Is this page beyond the end of the file?
 	 *

fs/ksmbd/auth.c

@@ -321,7 +321,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
 	dn_off = le32_to_cpu(authblob->DomainName.BufferOffset);
 	dn_len = le16_to_cpu(authblob->DomainName.Length);
 
-	if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len)
+	if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len ||
+	    nt_len < CIFS_ENCPWD_SIZE)
 		return -EINVAL;
 
 	/* TODO : use domain name that imported from configuration file */

fs/ntfs3/attrib.c

@@ -1949,7 +1949,7 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 		return -ENOENT;
 
 	if (!attr_b->non_res) {
-		u32 data_size = le32_to_cpu(attr->res.data_size);
+		u32 data_size = le32_to_cpu(attr_b->res.data_size);
 		u32 from, to;
 
 		if (vbo > data_size)

fs/signalfd.c

@@ -248,6 +248,7 @@ static const struct file_operations signalfd_fops = {
 	.poll		= signalfd_poll,
 	.read		= signalfd_read,
 	.llseek		= noop_llseek,
+	.may_pollfree	= true,
 };
 
 static int do_signalfd4(int ufd, sigset_t *mask, int flags)

fs/xfs/libxfs/xfs_btree.c

@@ -2811,7 +2811,7 @@ xfs_btree_split_worker(
 	struct xfs_btree_split_args	*args = container_of(work,
 						struct xfs_btree_split_args, work);
 	unsigned long		pflags;
-	unsigned long		new_pflags = PF_MEMALLOC_NOFS;
+	unsigned long		new_pflags = 0;
 
 	/*
 	 * we are in a transaction context here, but may also be doing work
@@ -2823,12 +2823,20 @@ xfs_btree_split_worker(
 		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 
 	current_set_flags_nested(&pflags, new_pflags);
+	xfs_trans_set_context(args->cur->bc_tp);
 
 	args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
 					 args->key, args->curp, args->stat);
-	complete(args->done);
 
+	xfs_trans_clear_context(args->cur->bc_tp);
 	current_restore_flags_nested(&pflags, new_pflags);
+
+	/*
+	 * Do not access args after complete() has run here. We don't own args
+	 * and the owner may run and free args before we return here.
+	 */
+	complete(args->done);
+
 }
 
 /*

fs/xfs/xfs_aops.c

@@ -98,7 +98,7 @@ xfs_setfilesize_ioend(
 	 * thus we need to mark ourselves as being in a transaction manually.
 	 * Similarly for freeze protection.
 	 */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_set_context(tp);
 	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
 	/* we abort the update if there was an IO error */
@@ -538,6 +538,12 @@ xfs_vm_writepage(
 {
 	struct xfs_writepage_ctx wpc = { };
 
+	if (WARN_ON_ONCE(current->journal_info)) {
+		redirty_page_for_writepage(wbc, page);
+		unlock_page(page);
+		return 0;
+	}
+
 	return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
 
@@ -548,6 +554,13 @@ xfs_vm_writepages(
 {
 	struct xfs_writepage_ctx wpc = { };
 
+	/*
+	 * Writing back data in a transaction context can result in recursive
+	 * transactions. This is bad, so issue a warning and get out of here.
+	 */
+	if (WARN_ON_ONCE(current->journal_info))
+		return 0;
+
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
 	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
 }

fs/xfs/xfs_fsops.c

@@ -374,46 +374,36 @@ xfs_reserve_blocks(
 	 * If the request is larger than the current reservation, reserve the
 	 * blocks before we update the reserve counters. Sample m_fdblocks and
 	 * perform a partial reservation if the request exceeds free space.
+	 *
+	 * The code below estimates how many blocks it can request from
+	 * fdblocks to stash in the reserve pool.  This is a classic TOCTOU
+	 * race since fdblocks updates are not always coordinated via
+	 * m_sb_lock.  Set the reserve size even if there's not enough free
+	 * space to fill it because mod_fdblocks will refill an undersized
+	 * reserve when it can.
 	 */
-	error = -ENOSPC;
-	do {
-		free = percpu_counter_sum(&mp->m_fdblocks) -
-						mp->m_alloc_set_aside;
-		if (free <= 0)
-			break;
-
-		delta = request - mp->m_resblks;
-		lcounter = free - delta;
-		if (lcounter < 0)
-			/* We can't satisfy the request, just get what we can */
-			fdblks_delta = free;
-		else
-			fdblks_delta = delta;
-
+	free = percpu_counter_sum(&mp->m_fdblocks) -
+						xfs_fdblocks_unavailable(mp);
+	delta = request - mp->m_resblks;
+	mp->m_resblks = request;
+	if (delta > 0 && free > 0) {
 		/*
 		 * We'll either succeed in getting space from the free block
-		 * count or we'll get an ENOSPC. If we get a ENOSPC, it means
-		 * things changed while we were calculating fdblks_delta and so
-		 * we should try again to see if there is anything left to
-		 * reserve.
+		 * count or we'll get an ENOSPC.  Don't set the reserved flag
+		 * here - we don't want to reserve the extra reserve blocks
+		 * from the reserve.
 		 *
-		 * Don't set the reserved flag here - we don't want to reserve
-		 * the extra reserve blocks from the reserve.....
+		 * The desired reserve size can change after we drop the lock.
+		 * Use mod_fdblocks to put the space into the reserve or into
+		 * fdblocks as appropriate.
 		 */
+		fdblks_delta = min(free, delta);
 		spin_unlock(&mp->m_sb_lock);
 		error = xfs_mod_fdblocks(mp, -fdblks_delta, 0);
+		if (!error)
+			xfs_mod_fdblocks(mp, fdblks_delta, 0);
 		spin_lock(&mp->m_sb_lock);
-	} while (error == -ENOSPC);
-
-	/*
-	 * Update the reserve counters if blocks have been successfully
-	 * allocated.
-	 */
-	if (!error && fdblks_delta) {
-		mp->m_resblks += fdblks_delta;
-		mp->m_resblks_avail += fdblks_delta;
 	}
-
 out:
 	if (outval) {
 		outval->resblks = mp->m_resblks;

fs/xfs/xfs_mount.h

@@ -467,6 +467,14 @@ extern void	xfs_unmountfs(xfs_mount_t *);
  */
 #define XFS_FDBLOCKS_BATCH	1024
 
+/* Accessor added for 5.10.y backport */
+static inline uint64_t
+xfs_fdblocks_unavailable(
+	struct xfs_mount	*mp)
+{
+	return mp->m_alloc_set_aside;
+}
+
 extern int	xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
 				 bool reserved);
 extern int	xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);

fs/xfs/xfs_trans.c

@@ -72,6 +72,7 @@ xfs_trans_free(
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	trace_xfs_trans_free(tp, _RET_IP_);
+	xfs_trans_clear_context(tp);
 	if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
@@ -123,7 +124,8 @@ xfs_trans_dup(
 
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
-	ntp->t_pflags = tp->t_pflags;
+
+	xfs_trans_switch_context(tp, ntp);
 
 	/* move deferred ops over to the new tp */
 	xfs_defer_move(ntp, tp);
@@ -157,9 +159,6 @@ xfs_trans_reserve(
 	int			error = 0;
 	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
-	/* Mark this thread as being in a transaction */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	/*
 	 * Attempt to reserve the needed disk blocks by decrementing
 	 * the number needed from the number available.  This will
@@ -167,10 +166,8 @@ xfs_trans_reserve(
 	 */
 	if (blocks > 0) {
 		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
-		if (error != 0) {
-			current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+		if (error != 0)
 			return -ENOSPC;
-		}
 		tp->t_blk_res += blocks;
 	}
 
@@ -244,9 +241,6 @@ xfs_trans_reserve(
 		xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
 		tp->t_blk_res = 0;
 	}
-
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	return error;
 }
 
@@ -272,6 +266,7 @@ xfs_trans_alloc(
 	tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
+	xfs_trans_set_context(tp);
 
 	/*
 	 * Zero-reservation ("empty") transactions can't modify anything, so
@@ -893,7 +888,6 @@ __xfs_trans_commit(
 
 	xlog_cil_commit(mp->m_log, tp, &commit_seq, regrant);
 
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free(tp);
 
 	/*
@@ -925,7 +919,6 @@ __xfs_trans_commit(
 			xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
 		tp->t_ticket = NULL;
 	}
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free_items(tp, !!error);
 	xfs_trans_free(tp);
 
@@ -985,9 +978,6 @@ xfs_trans_cancel(
 		tp->t_ticket = NULL;
 	}
 
-	/* mark this thread as no longer being in a transaction */
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	xfs_trans_free_items(tp, dirty);
 	xfs_trans_free(tp);
 }

fs/xfs/xfs_trans.h

@@ -266,4 +266,34 @@ int xfs_trans_alloc_ichange(struct xfs_inode *ip, struct xfs_dquot *udqp,
 		struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, bool force,
 		struct xfs_trans **tpp);
 
+static inline void
+xfs_trans_set_context(
+	struct xfs_trans	*tp)
+{
+	ASSERT(current->journal_info == NULL);
+	tp->t_pflags = memalloc_nofs_save();
+	current->journal_info = tp;
+}
+
+static inline void
+xfs_trans_clear_context(
+	struct xfs_trans	*tp)
+{
+	if (current->journal_info == tp) {
+		memalloc_nofs_restore(tp->t_pflags);
+		current->journal_info = NULL;
+	}
+}
+
+static inline void
+xfs_trans_switch_context(
+	struct xfs_trans	*old_tp,
+	struct xfs_trans	*new_tp)
+{
+	ASSERT(current->journal_info == old_tp);
+	new_tp->t_pflags = old_tp->t_pflags;
+	old_tp->t_pflags = 0;
+	current->journal_info = new_tp;
+}
+
 #endif	/* __XFS_TRANS_H__ */

include/linux/fault-inject.h

@@ -20,7 +20,6 @@ struct fault_attr {
 	atomic_t space;
 	unsigned long verbose;
 	bool task_filter;
-	bool no_warn;
 	unsigned long stacktrace_depth;
 	unsigned long require_start;
 	unsigned long require_end;
@@ -32,6 +31,10 @@ struct fault_attr {
 	struct dentry *dname;
 };
 
+enum fault_flags {
+	FAULT_NOWARN =	1 << 0,
+};
+
 #define FAULT_ATTR_INITIALIZER {					\
 		.interval = 1,						\
 		.times = ATOMIC_INIT(1),				\
@@ -40,11 +43,11 @@ struct fault_attr {
 		.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED,	\
 		.verbose = 2,						\
 		.dname = NULL,						\
-		.no_warn = false,					\
 	}
 
 #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
 int setup_fault_attr(struct fault_attr *attr, char *str);
+bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags);
 bool should_fail(struct fault_attr *attr, ssize_t size);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

include/linux/fs.h

@@ -1899,7 +1899,7 @@ struct file_operations {
 				   loff_t len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
 
-	KABI_RESERVE(1)
+	KABI_USE(1, bool may_pollfree)
 	KABI_RESERVE(2)
 	KABI_RESERVE(3)
 	KABI_RESERVE(4)

include/linux/sched.h

@@ -673,6 +673,12 @@ struct wake_q_node {
 * struct task_struct_resvd - KABI extension struct
 */
 struct task_struct_resvd {
+	/* pointer back to the main task_struct */
+	struct task_struct	*task;
+
+#ifdef CONFIG_MMU
+	struct timer_list	oom_reaper_timer;
+#endif
 };
 
 struct task_struct {

init/init_task.c

@@ -57,6 +57,10 @@ unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
 };
 #endif
 
+static struct task_struct_resvd init_task_struct_resvd = {
+	.task = &init_task,
+};
+
 /*
  * Set up the first task table, touch at your own risk!. Base=0,
  * limit=0x1fffff (=2MB)
@@ -213,6 +217,7 @@ struct task_struct init_task
 #ifdef CONFIG_SECCOMP_FILTER
 	.seccomp	= { .filter_count = ATOMIC_INIT(0) },
 #endif
+	._resvd = &init_task_struct_resvd,
 };
 EXPORT_SYMBOL(init_task);
 

kernel/fork.c

@@ -174,6 +174,7 @@ static inline struct task_struct *alloc_task_struct_node(int node)
 
 static inline void free_task_struct(struct task_struct *tsk)
 {
+	kfree(tsk->_resvd);
 	kmem_cache_free(task_struct_cachep, tsk);
 }
 #endif
@@ -851,6 +852,18 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 }
 
+static bool dup_resvd_task_struct(struct task_struct *dst,
+				  struct task_struct *orig, int node)
+{
+	dst->_resvd = kmalloc_node(sizeof(struct task_struct_resvd),
+					  GFP_KERNEL, node);
+	if (!dst->_resvd)
+		return false;
+
+	dst->_resvd->task = dst;
+	return true;
+}
+
 static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
@@ -863,6 +876,12 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk = alloc_task_struct_node(node);
 	if (!tsk)
 		return NULL;
+	/*
+	 * before proceeding, we need to make tsk->_resvd = NULL,
+	 * otherwise the error paths below, if taken, might end up causing
+	 * a double-free for task_struct_resvd extension object.
+	 */
+	WRITE_ONCE(tsk->_resvd, NULL);
 
 	stack = alloc_thread_stack_node(tsk, node);
 	if (!stack)
@@ -888,7 +907,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	refcount_set(&tsk->stack_refcount, 1);
 #endif
 
-	if (err)
+	if (err || !dup_resvd_task_struct(tsk, orig, node))
 		goto free_stack;
 
 	err = scs_prepare(tsk, node);

kernel/sched/autogroup.c

@@ -5,7 +5,7 @@
 #include <linux/nospec.h>
 #include "sched.h"
 
-unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
+unsigned int __read_mostly sysctl_sched_autogroup_enabled;
 static struct autogroup autogroup_default;
 static atomic_t autogroup_seq_nr;
 

kernel/trace/trace_osnoise.c

@@ -2103,6 +2103,13 @@ static int osnoise_hook_events(void)
 	return -EINVAL;
 }
 
+static void osnoise_unhook_events(void)
+{
+	unhook_thread_events();
+	unhook_softirq_events();
+	unhook_irq_events();
+}
+
 /*
  * osnoise_workload_start - start the workload and hook to events
  */
@@ -2135,7 +2142,14 @@ static int osnoise_workload_start(void)
 
 	retval = start_per_cpu_kthreads();
 	if (retval) {
-		unhook_irq_events();
+		trace_osnoise_callback_enabled = false;
+		/*
+		 * Make sure that ftrace_nmi_enter/exit() see
+		 * trace_osnoise_callback_enabled as false before continuing.
+		 */
+		barrier();
+
+		osnoise_unhook_events();
 		return retval;
 	}
 
@@ -2157,6 +2171,17 @@ static void osnoise_workload_stop(void)
 	if (osnoise_has_registered_instances())
 		return;
 
+	/*
+	 * If callbacks were already disabled in a previous stop
+	 * call, there is no need to disable then again.
+	 *
+	 * For instance, this happens when tracing is stopped via:
+	 * echo 0 > tracing_on
+	 * echo nop > current_tracer.
+	 */
+	if (!trace_osnoise_callback_enabled)
+		return;
+
 	trace_osnoise_callback_enabled = false;
 	/*
 	 * Make sure that ftrace_nmi_enter/exit() see
@@ -2166,9 +2191,7 @@ static void osnoise_workload_stop(void)
 
 	stop_per_cpu_kthreads();
 
-	unhook_irq_events();
-	unhook_softirq_events();
-	unhook_thread_events();
+	osnoise_unhook_events();
 }
 
 static void osnoise_tracer_start(struct trace_array *tr)

lib/fault-inject.c

@@ -41,9 +41,6 @@ EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
-	if (attr->no_warn)
-		return;
-
 	if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) {
 		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
 		       "name %pd, interval %lu, probability %lu, "
@@ -103,7 +100,7 @@ static inline bool fail_stacktrace(struct fault_attr *attr)
  * http://www.nongnu.org/failmalloc/
  */
 
-bool should_fail(struct fault_attr *attr, ssize_t size)
+bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags)
 {
 	if (in_task()) {
 		unsigned int fail_nth = READ_ONCE(current->fail_nth);
@@ -146,13 +143,19 @@ bool should_fail(struct fault_attr *attr, ssize_t size)
 		return false;
 
 fail:
-	fail_dump(attr);
+	if (!(flags & FAULT_NOWARN))
+		fail_dump(attr);
 
 	if (atomic_read(&attr->times) != -1)
 		atomic_dec_not_zero(&attr->times);
 
 	return true;
 }
+
+bool should_fail(struct fault_attr *attr, ssize_t size)
+{
+	return should_fail_ex(attr, size, 0);
+}
 EXPORT_SYMBOL_GPL(should_fail);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

mm/failslab.c

@@ -16,6 +16,8 @@ static struct {
 
 bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
+	int flags = 0;
+
 	/* No fault-injection for bootstrap cache */
 	if (unlikely(s == kmem_cache))
 		return false;
@@ -30,10 +32,16 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
 		return false;
 
+	/*
+	 * In some cases, it expects to specify __GFP_NOWARN
+	 * to avoid printing any information(not just a warning),
+	 * thus avoiding deadlocks. See commit 6b9dbedbe349 for
+	 * details.
+	 */
 	if (gfpflags & __GFP_NOWARN)
-		failslab.attr.no_warn = true;
+		flags |= FAULT_NOWARN;
 
-	return should_fail(&failslab.attr, s->object_size);
+	return should_fail_ex(&failslab.attr, s->object_size, flags);
 }
 
 static int __init setup_failslab(char *str)

mm/filemap.c

@@ -1956,7 +1956,6 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
 				next_idx = page->index + thp_nr_pages(page);
 			if (page->index < start)
 				goto put;
-			VM_BUG_ON_PAGE(page->index != xas.xa_index, page);
 			if (page->index + thp_nr_pages(page) - 1 > end)
 				goto put;
 			if (!trylock_page(page))

mm/mmap.c

@@ -1479,9 +1479,11 @@ unsigned long __do_mmap_mm(struct mm_struct *mm, struct file *file,
 			pkey = 0;
 	}
 
+#ifdef CONFIG_ASCEND_FEATURES
 	/* Physical address is within 4G */
 	if (flags & MAP_PA32BIT)
 		vm_flags |= VM_PA32BIT;
+#endif
 
 	/* Do simple checking here so the lower-level routines won't have
 	 * to. we assume access permissions have been handled by the open

mm/oom_kill.c

@@ -680,7 +680,7 @@ static void oom_reap_task(struct task_struct *tsk)
 	 */
 	set_bit(MMF_OOM_SKIP, &mm->flags);
 
-	/* Drop a reference taken by wake_oom_reaper */
+	/* Drop a reference taken by queue_oom_reaper */
 	put_task_struct(tsk);
 }
 
@@ -690,12 +690,12 @@ static int oom_reaper(void *unused)
 		struct task_struct *tsk = NULL;
 
 		wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
-		spin_lock(&oom_reaper_lock);
+		spin_lock_irq(&oom_reaper_lock);
 		if (oom_reaper_list != NULL) {
 			tsk = oom_reaper_list;
 			oom_reaper_list = tsk->oom_reaper_list;
 		}
-		spin_unlock(&oom_reaper_lock);
+		spin_unlock_irq(&oom_reaper_lock);
 
 		if (tsk)
 			oom_reap_task(tsk);
@@ -704,22 +704,49 @@ static int oom_reaper(void *unused)
 	return 0;
 }
 
-static void wake_oom_reaper(struct task_struct *tsk)
+static void wake_oom_reaper(struct timer_list *timer)
 {
-	/* mm is already queued? */
-	if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
-		return;
+	struct task_struct_resvd *tsk_resvd = container_of(timer,
+			struct task_struct_resvd, oom_reaper_timer);
+	struct task_struct *tsk = tsk_resvd->task;
+	struct mm_struct *mm = tsk->signal->oom_mm;
+	unsigned long flags;
 
-	get_task_struct(tsk);
+	/* The victim managed to terminate on its own - see exit_mmap */
+	if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
+		put_task_struct(tsk);
+		return;
+	}
 
-	spin_lock(&oom_reaper_lock);
+	spin_lock_irqsave(&oom_reaper_lock, flags);
 	tsk->oom_reaper_list = oom_reaper_list;
 	oom_reaper_list = tsk;
-	spin_unlock(&oom_reaper_lock);
+	spin_unlock_irqrestore(&oom_reaper_lock, flags);
 	trace_wake_reaper(tsk->pid);
 	wake_up(&oom_reaper_wait);
 }
 
+/*
+ * Give the OOM victim time to exit naturally before invoking the oom_reaping.
+ * The timers timeout is arbitrary... the longer it is, the longer the worst
+ * case scenario for the OOM can take. If it is too small, the oom_reaper can
+ * get in the way and release resources needed by the process exit path.
+ * e.g. The futex robust list can sit in Anon|Private memory that gets reaped
+ * before the exit path is able to wake the futex waiters.
+ */
+#define OOM_REAPER_DELAY (2*HZ)
+static void queue_oom_reaper(struct task_struct *tsk)
+{
+	/* mm is already queued? */
+	if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
+		return;
+
+	get_task_struct(tsk);
+	timer_setup(&tsk->_resvd->oom_reaper_timer, wake_oom_reaper, 0);
+	tsk->_resvd->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY;
+	add_timer(&tsk->_resvd->oom_reaper_timer);
+}
+
 static int __init oom_init(void)
 {
 	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
@@ -727,7 +754,7 @@ static int __init oom_init(void)
 }
 subsys_initcall(oom_init)
 #else
-static inline void wake_oom_reaper(struct task_struct *tsk)
+static inline void queue_oom_reaper(struct task_struct *tsk)
 {
 }
 #endif /* CONFIG_MMU */
@@ -978,7 +1005,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
 	rcu_read_unlock();
 
 	if (can_oom_reap)
-		wake_oom_reaper(victim);
+		queue_oom_reaper(victim);
 
 	mmdrop(mm);
 	put_task_struct(victim);
@@ -1014,7 +1041,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	task_lock(victim);
 	if (task_will_free_mem(victim)) {
 		mark_oom_victim(victim);
-		wake_oom_reaper(victim);
+		queue_oom_reaper(victim);
 		task_unlock(victim);
 		put_task_struct(victim);
 		return;
@@ -1156,7 +1183,7 @@ bool out_of_memory(struct oom_control *oc)
 	 */
 	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		wake_oom_reaper(current);
+		queue_oom_reaper(current);
 		return true;
 	}
 

mm/page_alloc.c

@@ -3545,6 +3545,8 @@ __setup("fail_page_alloc=", setup_fail_page_alloc);
 
 static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
+	int flags = 0;
+
 	if (order < fail_page_alloc.min_order)
 		return false;
 	if (gfp_mask & __GFP_NOFAIL)
@@ -3555,10 +3557,11 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 			(gfp_mask & __GFP_DIRECT_RECLAIM))
 		return false;
 
+	/* See comment in __should_failslab() */
 	if (gfp_mask & __GFP_NOWARN)
-		fail_page_alloc.attr.no_warn = true;
+		flags |= FAULT_NOWARN;
 
-	return should_fail(&fail_page_alloc.attr, 1 << order);
+	return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags);
 }
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

mm/shmem.c

@@ -2573,19 +2573,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct address_space *mapping = inode->i_mapping;
 	pgoff_t index;
 	unsigned long offset;
-	enum sgp_type sgp = SGP_READ;
 	int error = 0;
 	ssize_t retval = 0;
 	loff_t *ppos = &iocb->ki_pos;
 
-	/*
-	 * Might this read be for a stacking filesystem?  Then when reading
-	 * holes of a sparse file, we actually need to allocate those pages,
-	 * and even mark them dirty, so it cannot exceed the max_blocks limit.
-	 */
-	if (!iter_is_iovec(to))
-		sgp = SGP_CACHE;
-
 	index = *ppos >> PAGE_SHIFT;
 	offset = *ppos & ~PAGE_MASK;
 
@@ -2604,15 +2595,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 				break;
 		}
 
-		error = shmem_getpage(inode, index, &page, sgp);
+		error = shmem_getpage(inode, index, &page, SGP_READ);
 		if (error) {
 			if (error == -EINVAL)
 				error = 0;
 			break;
 		}
 		if (page) {
-			if (sgp == SGP_CACHE)
-				set_page_dirty(page);
 			unlock_page(page);
 		}
 
@@ -2646,22 +2635,34 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			 */
 			if (!offset)
 				mark_page_accessed(page);
+			/*
+			 * Ok, we have the page, and it's up-to-date, so
+			 * now we can copy it to user space...
+			 */
+			ret = copy_page_to_iter(page, offset, nr, to);
+			put_page(page);
+
+		} else if (iter_is_iovec(to)) {
+			/*
+			 * Copy to user tends to be so well optimized, but
+			 * clear_user() not so much, that it is noticeably
+			 * faster to copy the zero page instead of clearing.
+			 */
+			ret = copy_page_to_iter(ZERO_PAGE(0), offset, nr, to);
 		} else {
-			page = ZERO_PAGE(0);
-			get_page(page);
+			/*
+			 * But submitting the same page twice in a row to
+			 * splice() - or others? - can result in confusion:
+			 * so don't attempt that optimization on pipes etc.
+			 */
+			ret = iov_iter_zero(nr, to);
 		}
 
-		/*
-		 * Ok, we have the page, and it's up-to-date, so
-		 * now we can copy it to user space...
-		 */
-		ret = copy_page_to_iter(page, offset, nr, to);
 		retval += ret;
 		offset += ret;
 		index += offset >> PAGE_SHIFT;
 		offset &= ~PAGE_MASK;
 
-		put_page(page);
 		if (!iov_iter_count(to))
 			break;
 		if (ret < nr) {