From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/eventfd.c | 117 ++++++++++++++++++++++++++++++++++++----------------------
1 files changed, 73 insertions(+), 44 deletions(-)
diff --git a/kernel/fs/eventfd.c b/kernel/fs/eventfd.c
index ce1d171..3673eb8 100644
--- a/kernel/fs/eventfd.c
+++ b/kernel/fs/eventfd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/eventfd.c
*
@@ -21,8 +22,12 @@
#include <linux/eventfd.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/idr.h>
+#include <linux/uio.h>
DEFINE_PER_CPU(int, eventfd_wake_count);
+
+static DEFINE_IDA(eventfd_ida);
struct eventfd_ctx {
struct kref kref;
@@ -37,23 +42,10 @@
*/
__u64 count;
unsigned int flags;
+ int id;
};
-/**
- * eventfd_signal - Adds @n to the eventfd counter.
- * @ctx: [in] Pointer to the eventfd context.
- * @n: [in] Value of the counter to be added to the eventfd internal counter.
- * The value cannot be negative.
- *
- * This function is supposed to be called by the kernel in paths that do not
- * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
- * value, and we signal this as overflow condition by returning a EPOLLERR
- * to poll(2).
- *
- * Returns the amount by which the counter was incremented. This will be less
- * than @n if the counter has overflowed.
- */
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask)
{
unsigned long flags;
@@ -74,16 +66,37 @@
n = ULLONG_MAX - ctx->count;
ctx->count += n;
if (waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, EPOLLIN);
+ wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
this_cpu_dec(eventfd_wake_count);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return n;
}
+
+/**
+ * eventfd_signal - Adds @n to the eventfd counter.
+ * @ctx: [in] Pointer to the eventfd context.
+ * @n: [in] Value of the counter to be added to the eventfd internal counter.
+ * The value cannot be negative.
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returning a EPOLLERR
+ * to poll(2).
+ *
+ * Returns the amount by which the counter was incremented. This will be less
+ * than @n if the counter has overflowed.
+ */
+__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+{
+ return eventfd_signal_mask(ctx, n, 0);
+}
EXPORT_SYMBOL_GPL(eventfd_signal);
static void eventfd_free_ctx(struct eventfd_ctx *ctx)
{
+ if (ctx->id >= 0)
+ ida_simple_remove(&eventfd_ida, ctx->id);
kfree(ctx);
}
@@ -174,11 +187,14 @@
return events;
}
-static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
{
- *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
+ lockdep_assert_held(&ctx->wqh.lock);
+
+ *cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count;
ctx->count -= *cnt;
}
+EXPORT_SYMBOL_GPL(eventfd_ctx_do_read);
/**
* eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
@@ -209,32 +225,32 @@
}
EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
-static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
- loff_t *ppos)
+static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to)
{
+ struct file *file = iocb->ki_filp;
struct eventfd_ctx *ctx = file->private_data;
- ssize_t res;
__u64 ucnt = 0;
DECLARE_WAITQUEUE(wait, current);
- if (count < sizeof(ucnt))
+ if (iov_iter_count(to) < sizeof(ucnt))
return -EINVAL;
-
spin_lock_irq(&ctx->wqh.lock);
- res = -EAGAIN;
- if (ctx->count > 0)
- res = sizeof(ucnt);
- else if (!(file->f_flags & O_NONBLOCK)) {
+ if (!ctx->count) {
+ if ((file->f_flags & O_NONBLOCK) ||
+ (iocb->ki_flags & IOCB_NOWAIT)) {
+ spin_unlock_irq(&ctx->wqh.lock);
+ return -EAGAIN;
+ }
__add_wait_queue(&ctx->wqh, &wait);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
- if (ctx->count > 0) {
- res = sizeof(ucnt);
+ if (ctx->count)
break;
- }
if (signal_pending(current)) {
- res = -ERESTARTSYS;
- break;
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ spin_unlock_irq(&ctx->wqh.lock);
+ return -ERESTARTSYS;
}
spin_unlock_irq(&ctx->wqh.lock);
schedule();
@@ -243,17 +259,14 @@
__remove_wait_queue(&ctx->wqh, &wait);
__set_current_state(TASK_RUNNING);
}
- if (likely(res > 0)) {
- eventfd_ctx_do_read(ctx, &ucnt);
- if (waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
- }
+ eventfd_ctx_do_read(ctx, &ucnt);
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
spin_unlock_irq(&ctx->wqh.lock);
-
- if (res > 0 && put_user(ucnt, (__u64 __user *)buf))
+ if (unlikely(copy_to_iter(&ucnt, sizeof(ucnt), to) != sizeof(ucnt)))
return -EFAULT;
- return res;
+ return sizeof(ucnt);
}
static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
@@ -312,6 +325,7 @@
seq_printf(m, "eventfd-count: %16llx\n",
(unsigned long long)ctx->count);
spin_unlock_irq(&ctx->wqh.lock);
+ seq_printf(m, "eventfd-id: %d\n", ctx->id);
}
#endif
@@ -321,7 +335,7 @@
#endif
.release = eventfd_release,
.poll = eventfd_poll,
- .read = eventfd_read,
+ .read_iter = eventfd_read,
.write = eventfd_write,
.llseek = noop_llseek,
};
@@ -398,6 +412,7 @@
static int do_eventfd(unsigned int count, int flags)
{
struct eventfd_ctx *ctx;
+ struct file *file;
int fd;
/* Check the EFD_* constants for consistency. */
@@ -415,12 +430,26 @@
init_waitqueue_head(&ctx->wqh);
ctx->count = count;
ctx->flags = flags;
+ ctx->id = ida_simple_get(&eventfd_ida, 0, 0, GFP_KERNEL);
- fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx,
- O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS));
+ flags &= EFD_SHARED_FCNTL_FLAGS;
+ flags |= O_RDWR;
+ fd = get_unused_fd_flags(flags);
if (fd < 0)
- eventfd_free_ctx(ctx);
+ goto err;
+ file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx, flags);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ fd = PTR_ERR(file);
+ goto err;
+ }
+
+ file->f_mode |= FMODE_NOWAIT;
+ fd_install(fd, file);
+ return fd;
+err:
+ eventfd_free_ctx(ctx);
return fd;
}
--
Gitblit v1.6.2