xsk: add user memory registration support sockopt

In this commit the base structure of the AF_XDP address family is set
up. Further, we introduce the abilty register a window of user memory
to the kernel via the XDP_UMEM_REG setsockopt syscall. The memory
window is viewed by an AF_XDP socket as a set of equally large
frames. After a user memory registration all frames are "owned" by the
user application, and not the kernel.

v2: More robust checks on umem creation and unaccount on error.
    Call set_page_dirty_lock on cleanup.
    Simplified xdp_umem_reg.

Co-authored-by: Magnus Karlsson <[email protected]>
Signed-off-by: Magnus Karlsson <[email protected]>
Signed-off-by: Björn Töpel <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>

include/net/xdp_sock.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * AF_XDP internal functions
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _LINUX_XDP_SOCK_H
+#define _LINUX_XDP_SOCK_H
+
+#include <linux/mutex.h>
+#include <net/sock.h>
+
+struct xdp_umem;
+
+struct xdp_sock {
+	/* struct sock must be the first member of struct xdp_sock */
+	struct sock sk;
+	struct xdp_umem *umem;
+	/* Protects multiple processes in the control path */
+	struct mutex mutex;
+};
+
+#endif /* _LINUX_XDP_SOCK_H */

include/uapi/linux/if_xdp.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+ *
+ * if_xdp: XDP socket user-space interface
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * Author(s): Björn Töpel <[email protected]>
+ *	      Magnus Karlsson <[email protected]>
+ */
+
+#ifndef _LINUX_IF_XDP_H
+#define _LINUX_IF_XDP_H
+
+#include <linux/types.h>
+
+/* XDP socket options */
+#define XDP_UMEM_REG			3
+
+struct xdp_umem_reg {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 frame_size; /* Frame size */
+	__u32 frame_headroom; /* Frame head room */
+};
+
+#endif /* _LINUX_IF_XDP_H */

net/Makefile

@@ -85,3 +85,4 @@ obj-y				+= l3mdev/
 endif
 obj-$(CONFIG_QRTR)		+= qrtr/
 obj-$(CONFIG_NET_NCSI)		+= ncsi/
+obj-$(CONFIG_XDP_SOCKETS)	+= xdp/

net/xdp/Makefile

@@ -0,0 +1,2 @@
+obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o
+

net/xdp/xdp_umem.c

@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/mm.h>
+
+#include "xdp_umem.h"
+
+#define XDP_UMEM_MIN_FRAME_SIZE 2048
+
+int xdp_umem_create(struct xdp_umem **umem)
+{
+	*umem = kzalloc(sizeof(**umem), GFP_KERNEL);
+
+	if (!(*umem))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void xdp_umem_unpin_pages(struct xdp_umem *umem)
+{
+	unsigned int i;
+
+	if (umem->pgs) {
+		for (i = 0; i < umem->npgs; i++) {
+			struct page *page = umem->pgs[i];
+
+			set_page_dirty_lock(page);
+			put_page(page);
+		}
+
+		kfree(umem->pgs);
+		umem->pgs = NULL;
+	}
+}
+
+static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
+{
+	if (umem->user) {
+		atomic_long_sub(umem->npgs, &umem->user->locked_vm);
+		free_uid(umem->user);
+	}
+}
+
+static void xdp_umem_release(struct xdp_umem *umem)
+{
+	struct task_struct *task;
+	struct mm_struct *mm;
+
+	if (umem->pgs) {
+		xdp_umem_unpin_pages(umem);
+
+		task = get_pid_task(umem->pid, PIDTYPE_PID);
+		put_pid(umem->pid);
+		if (!task)
+			goto out;
+		mm = get_task_mm(task);
+		put_task_struct(task);
+		if (!mm)
+			goto out;
+
+		mmput(mm);
+		umem->pgs = NULL;
+	}
+
+	xdp_umem_unaccount_pages(umem);
+out:
+	kfree(umem);
+}
+
+static void xdp_umem_release_deferred(struct work_struct *work)
+{
+	struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
+
+	xdp_umem_release(umem);
+}
+
+void xdp_get_umem(struct xdp_umem *umem)
+{
+	atomic_inc(&umem->users);
+}
+
+void xdp_put_umem(struct xdp_umem *umem)
+{
+	if (!umem)
+		return;
+
+	if (atomic_dec_and_test(&umem->users)) {
+		INIT_WORK(&umem->work, xdp_umem_release_deferred);
+		schedule_work(&umem->work);
+	}
+}
+
+static int xdp_umem_pin_pages(struct xdp_umem *umem)
+{
+	unsigned int gup_flags = FOLL_WRITE;
+	long npgs;
+	int err;
+
+	umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL);
+	if (!umem->pgs)
+		return -ENOMEM;
+
+	down_write(&current->mm->mmap_sem);
+	npgs = get_user_pages(umem->address, umem->npgs,
+			      gup_flags, &umem->pgs[0], NULL);
+	up_write(&current->mm->mmap_sem);
+
+	if (npgs != umem->npgs) {
+		if (npgs >= 0) {
+			umem->npgs = npgs;
+			err = -ENOMEM;
+			goto out_pin;
+		}
+		err = npgs;
+		goto out_pgs;
+	}
+	return 0;
+
+out_pin:
+	xdp_umem_unpin_pages(umem);
+out_pgs:
+	kfree(umem->pgs);
+	umem->pgs = NULL;
+	return err;
+}
+
+static int xdp_umem_account_pages(struct xdp_umem *umem)
+{
+	unsigned long lock_limit, new_npgs, old_npgs;
+
+	if (capable(CAP_IPC_LOCK))
+		return 0;
+
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	umem->user = get_uid(current_user());
+
+	do {
+		old_npgs = atomic_long_read(&umem->user->locked_vm);
+		new_npgs = old_npgs + umem->npgs;
+		if (new_npgs > lock_limit) {
+			free_uid(umem->user);
+			umem->user = NULL;
+			return -ENOBUFS;
+		}
+	} while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs,
+				     new_npgs) != old_npgs);
+	return 0;
+}
+
+int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+{
+	u32 frame_size = mr->frame_size, frame_headroom = mr->frame_headroom;
+	u64 addr = mr->addr, size = mr->len;
+	unsigned int nframes, nfpp;
+	int size_chk, err;
+
+	if (!umem)
+		return -EINVAL;
+
+	if (frame_size < XDP_UMEM_MIN_FRAME_SIZE || frame_size > PAGE_SIZE) {
+		/* Strictly speaking we could support this, if:
+		 * - huge pages, or*
+		 * - using an IOMMU, or
+		 * - making sure the memory area is consecutive
+		 * but for now, we simply say "computer says no".
+		 */
+		return -EINVAL;
+	}
+
+	if (!is_power_of_2(frame_size))
+		return -EINVAL;
+
+	if (!PAGE_ALIGNED(addr)) {
+		/* Memory area has to be page size aligned. For
+		 * simplicity, this might change.
+		 */
+		return -EINVAL;
+	}
+
+	if ((addr + size) < addr)
+		return -EINVAL;
+
+	nframes = size / frame_size;
+	if (nframes == 0 || nframes > UINT_MAX)
+		return -EINVAL;
+
+	nfpp = PAGE_SIZE / frame_size;
+	if (nframes < nfpp || nframes % nfpp)
+		return -EINVAL;
+
+	frame_headroom = ALIGN(frame_headroom, 64);
+
+	size_chk = frame_size - frame_headroom - XDP_PACKET_HEADROOM;
+	if (size_chk < 0)
+		return -EINVAL;
+
+	umem->pid = get_task_pid(current, PIDTYPE_PID);
+	umem->size = (size_t)size;
+	umem->address = (unsigned long)addr;
+	umem->props.frame_size = frame_size;
+	umem->props.nframes = nframes;
+	umem->frame_headroom = frame_headroom;
+	umem->npgs = size / PAGE_SIZE;
+	umem->pgs = NULL;
+	umem->user = NULL;
+
+	umem->frame_size_log2 = ilog2(frame_size);
+	umem->nfpp_mask = nfpp - 1;
+	umem->nfpplog2 = ilog2(nfpp);
+	atomic_set(&umem->users, 1);
+
+	err = xdp_umem_account_pages(umem);
+	if (err)
+		goto out;
+
+	err = xdp_umem_pin_pages(umem);
+	if (err)
+		goto out_account;
+	return 0;
+
+out_account:
+	xdp_umem_unaccount_pages(umem);
+out:
+	put_pid(umem->pid);
+	return err;
+}

net/xdp/xdp_umem.h

@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef XDP_UMEM_H_
+#define XDP_UMEM_H_
+
+#include <linux/mm.h>
+#include <linux/if_xdp.h>
+#include <linux/workqueue.h>
+
+#include "xdp_umem_props.h"
+
+struct xdp_umem {
+	struct page **pgs;
+	struct xdp_umem_props props;
+	u32 npgs;
+	u32 frame_headroom;
+	u32 nfpp_mask;
+	u32 nfpplog2;
+	u32 frame_size_log2;
+	struct user_struct *user;
+	struct pid *pid;
+	unsigned long address;
+	size_t size;
+	atomic_t users;
+	struct work_struct work;
+};
+
+int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr);
+void xdp_get_umem(struct xdp_umem *umem);
+void xdp_put_umem(struct xdp_umem *umem);
+int xdp_umem_create(struct xdp_umem **umem);
+
+#endif /* XDP_UMEM_H_ */

net/xdp/xdp_umem_props.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef XDP_UMEM_PROPS_H_
+#define XDP_UMEM_PROPS_H_
+
+struct xdp_umem_props {
+	u32 frame_size;
+	u32 nframes;
+};
+
+#endif /* XDP_UMEM_PROPS_H_ */