[RFC PATCH] Add proc interface to set PF_MEMALLOC flags

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



There are several storage drivers like dm-multipath, iscsi, and nbd that
have userspace components that can run in the IO path. For example,
iscsi and nbd's userspace deamons may need to recreate a socket and/or
send IO on it, and dm-multipath's daemon multipathd may need to send IO
to figure out the state of paths and re-set them up.

In the kernel these drivers have access to GFP_NOIO/GFP_NOFS and the
memalloc_*_save/restore functions to control the allocation behavior,
but for userspace we would end up hitting a allocation that ended up
writing data back to the same device we are trying to allocate for.

This patch allows the userspace deamon to set the PF_MEMALLOC* flags
through procfs. It currently only supports PF_MEMALLOC_NOIO, but
depending on what other drivers and userspace file systems need, for
the final version I can add the other flags for that file or do a file
per flag or just do a memalloc_noio file.

Signed-off-by: Mike Christie <mchristi@xxxxxxxxxx>
---
 Documentation/filesystems/proc.txt |  6 ++++
 fs/proc/base.c                     | 53 ++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 99ca040e3f90..b5456a61a013 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -46,6 +46,7 @@ Table of Contents
   3.10  /proc/<pid>/timerslack_ns - Task timerslack value
   3.11	/proc/<pid>/patch_state - Livepatch patch operation state
   3.12	/proc/<pid>/arch_status - Task architecture specific information
+  3.13  /proc/<pid>/memalloc - Control task's memory reclaim behavior
 
   4	Configuring procfs
   4.1	Mount options
@@ -1980,6 +1981,11 @@ Example
  $ cat /proc/6753/arch_status
  AVX512_elapsed_ms:      8
 
+3.13 /proc/<pid>/memalloc - Control task's memory reclaim behavior
+-----------------------------------------------------------------------
+A value of "noio" indicates that when a task allocates memory it will not
+reclaim memory that requires starting phisical IO.
+
 Description
 -----------
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ebea9501afb8..c4faa3464602 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1223,6 +1223,57 @@ static const struct file_operations proc_oom_score_adj_operations = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t memalloc_read(struct file *file, char __user *buf, size_t count,
+			     loff_t *ppos)
+{
+	struct task_struct *task;
+	ssize_t rc = 0;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+
+	if (task->flags & PF_MEMALLOC_NOIO)
+		rc = simple_read_from_buffer(buf, count, ppos, "noio", 4);
+	put_task_struct(task);
+	return rc;
+}
+
+static ssize_t memalloc_write(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[5];
+	int rc = count;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count != sizeof(buffer) - 1)
+		return -EINVAL;
+
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+	buffer[count] = '\0';
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+
+	if (!strcmp(buffer, "noio")) {
+		task->flags |= PF_MEMALLOC_NOIO;
+	} else {
+		rc = -EINVAL;
+	}
+
+	put_task_struct(task);
+	return rc;
+}
+
+static const struct file_operations proc_memalloc_operations = {
+	.read		= memalloc_read,
+	.write		= memalloc_write,
+	.llseek		= default_llseek,
+};
+
 #ifdef CONFIG_AUDIT
 #define TMPBUFLEN 11
 static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
@@ -3097,6 +3148,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 	ONE("arch_status", S_IRUGO, proc_pid_arch_status),
 #endif
+	REG("memalloc", S_IRUGO|S_IWUSR, proc_memalloc_operations),
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3487,6 +3539,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 	ONE("arch_status", S_IRUGO, proc_pid_arch_status),
 #endif
+	REG("memalloc", S_IRUGO|S_IWUSR, proc_memalloc_operations),
 };
 
 static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
-- 
2.21.0




[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Index of Archives]     [SCSI Target Devel]     [Linux SCSI Target Infrastructure]     [Kernel Newbies]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Linux IIO]     [Samba]     [Device Mapper]

  Powered by Linux