Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 349 insertions, 0 deletions

diff --git a/kernel/fail_function.c b/kernel/fail_function.c
new file mode 100644
index 0000000..21b0122
--- /dev/null
+++ b/kernel/fail_function.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fail_function.c: Function-based error injection
+ */
+#include <linux/error-injection.h>
+#include <linux/debugfs.h>
+#include <linux/fault-inject.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
+
+struct fei_attr {
+	struct list_head list;
+	struct kprobe kp;
+	unsigned long retval;
+};
+static DEFINE_MUTEX(fei_lock);
+static LIST_HEAD(fei_attr_list);
+static DECLARE_FAULT_ATTR(fei_fault_attr);
+static struct dentry *fei_debugfs_dir;
+
+static unsigned long adjust_error_retval(unsigned long addr, unsigned long retv)
+{
+	switch (get_injectable_error_type(addr)) {
+	case EI_ETYPE_NULL:
+		if (retv != 0)
+			return 0;
+		break;
+	case EI_ETYPE_ERRNO:
+		if (retv < (unsigned long)-MAX_ERRNO)
+			return (unsigned long)-EINVAL;
+		break;
+	case EI_ETYPE_ERRNO_NULL:
+		if (retv != 0 && retv < (unsigned long)-MAX_ERRNO)
+			return (unsigned long)-EINVAL;
+		break;
+	}
+
+	return retv;
+}
+
+static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr)
+{
+	struct fei_attr *attr;
+
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	if (attr) {
+		attr->kp.symbol_name = kstrdup(sym, GFP_KERNEL);
+		if (!attr->kp.symbol_name) {
+			kfree(attr);
+			return NULL;
+		}
+		attr->kp.pre_handler = fei_kprobe_handler;
+		attr->retval = adjust_error_retval(addr, 0);
+		INIT_LIST_HEAD(&attr->list);
+	}
+	return attr;
+}
+
+static void fei_attr_free(struct fei_attr *attr)
+{
+	if (attr) {
+		kfree(attr->kp.symbol_name);
+		kfree(attr);
+	}
+}
+
+static struct fei_attr *fei_attr_lookup(const char *sym)
+{
+	struct fei_attr *attr;
+
+	list_for_each_entry(attr, &fei_attr_list, list) {
+		if (!strcmp(attr->kp.symbol_name, sym))
+			return attr;
+	}
+
+	return NULL;
+}
+
+static bool fei_attr_is_valid(struct fei_attr *_attr)
+{
+	struct fei_attr *attr;
+
+	list_for_each_entry(attr, &fei_attr_list, list) {
+		if (attr == _attr)
+			return true;
+	}
+
+	return false;
+}
+
+static int fei_retval_set(void *data, u64 val)
+{
+	struct fei_attr *attr = data;
+	unsigned long retv = (unsigned long)val;
+	int err = 0;
+
+	mutex_lock(&fei_lock);
+	/*
+	 * Since this operation can be done after retval file is removed,
+	 * It is safer to check the attr is still valid before accessing
+	 * its member.
+	 */
+	if (!fei_attr_is_valid(attr)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	if (attr->kp.addr) {
+		if (adjust_error_retval((unsigned long)attr->kp.addr,
+					val) != retv)
+			err = -EINVAL;
+	}
+	if (!err)
+		attr->retval = val;
+out:
+	mutex_unlock(&fei_lock);
+
+	return err;
+}
+
+static int fei_retval_get(void *data, u64 *val)
+{
+	struct fei_attr *attr = data;
+	int err = 0;
+
+	mutex_lock(&fei_lock);
+	/* Here we also validate @attr to ensure it still exists. */
+	if (!fei_attr_is_valid(attr))
+		err = -ENOENT;
+	else
+		*val = attr->retval;
+	mutex_unlock(&fei_lock);
+
+	return err;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fei_retval_ops, fei_retval_get, fei_retval_set,
+			 "%llx\n");
+
+static int fei_debugfs_add_attr(struct fei_attr *attr)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir(attr->kp.symbol_name, fei_debugfs_dir);
+	if (!dir)
+		return -ENOMEM;
+
+	if (!debugfs_create_file("retval", 0600, dir, attr, &fei_retval_ops)) {
+		debugfs_remove_recursive(dir);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void fei_debugfs_remove_attr(struct fei_attr *attr)
+{
+	struct dentry *dir;
+
+	dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir);
+	if (dir)
+		debugfs_remove_recursive(dir);
+}
+
+static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
+{
+	struct fei_attr *attr = container_of(kp, struct fei_attr, kp);
+
+	if (should_fail(&fei_fault_attr, 1)) {
+		regs_set_return_value(regs, attr->retval);
+		override_function_with_return(regs);
+		/* Kprobe specific fixup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
+		return 1;
+	}
+
+	return 0;
+}
+NOKPROBE_SYMBOL(fei_kprobe_handler)
+
+static void *fei_seq_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&fei_lock);
+	return seq_list_start(&fei_attr_list, *pos);
+}
+
+static void fei_seq_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&fei_lock);
+}
+
+static void *fei_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &fei_attr_list, pos);
+}
+
+static int fei_seq_show(struct seq_file *m, void *v)
+{
+	struct fei_attr *attr = list_entry(v, struct fei_attr, list);
+
+	seq_printf(m, "%pf\n", attr->kp.addr);
+	return 0;
+}
+
+static const struct seq_operations fei_seq_ops = {
+	.start	= fei_seq_start,
+	.next	= fei_seq_next,
+	.stop	= fei_seq_stop,
+	.show	= fei_seq_show,
+};
+
+static int fei_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fei_seq_ops);
+}
+
+static void fei_attr_remove(struct fei_attr *attr)
+{
+	fei_debugfs_remove_attr(attr);
+	unregister_kprobe(&attr->kp);
+	list_del(&attr->list);
+	fei_attr_free(attr);
+}
+
+static void fei_attr_remove_all(void)
+{
+	struct fei_attr *attr, *n;
+
+	list_for_each_entry_safe(attr, n, &fei_attr_list, list) {
+		fei_attr_remove(attr);
+	}
+}
+
+static ssize_t fei_write(struct file *file, const char __user *buffer,
+			 size_t count, loff_t *ppos)
+{
+	struct fei_attr *attr;
+	unsigned long addr;
+	char *buf, *sym;
+	int ret;
+
+	/* cut off if it is too long */
+	if (count > KSYM_NAME_LEN)
+		count = KSYM_NAME_LEN;
+	buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, buffer, count)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	buf[count] = '\0';
+	sym = strstrip(buf);
+
+	mutex_lock(&fei_lock);
+
+	/* Writing just spaces will remove all injection points */
+	if (sym[0] == '\0') {
+		fei_attr_remove_all();
+		ret = count;
+		goto out;
+	}
+	/* Writing !function will remove one injection point */
+	if (sym[0] == '!') {
+		attr = fei_attr_lookup(sym + 1);
+		if (!attr) {
+			ret = -ENOENT;
+			goto out;
+		}
+		fei_attr_remove(attr);
+		ret = count;
+		goto out;
+	}
+
+	addr = kallsyms_lookup_name(sym);
+	if (!addr) {
+		ret = -EINVAL;
+		goto out;
+	}
+	if (!within_error_injection_list(addr)) {
+		ret = -ERANGE;
+		goto out;
+	}
+	if (fei_attr_lookup(sym)) {
+		ret = -EBUSY;
+		goto out;
+	}
+	attr = fei_attr_new(sym, addr);
+	if (!attr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = register_kprobe(&attr->kp);
+	if (!ret)
+		ret = fei_debugfs_add_attr(attr);
+	if (ret < 0)
+		fei_attr_remove(attr);
+	else {
+		list_add_tail(&attr->list, &fei_attr_list);
+		ret = count;
+	}
+out:
+	kfree(buf);
+	mutex_unlock(&fei_lock);
+	return ret;
+}
+
+static const struct file_operations fei_ops = {
+	.open =		fei_open,
+	.read =		seq_read,
+	.write =	fei_write,
+	.llseek =	seq_lseek,
+	.release =	seq_release,
+};
+
+static int __init fei_debugfs_init(void)
+{
+	struct dentry *dir;
+
+	dir = fault_create_debugfs_attr("fail_function", NULL,
+					&fei_fault_attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	/* injectable attribute is just a symlink of error_inject/list */
+	if (!debugfs_create_symlink("injectable", dir,
+				    "../error_injection/list"))
+		goto error;
+
+	if (!debugfs_create_file("inject", 0600, dir, NULL, &fei_ops))
+		goto error;
+
+	fei_debugfs_dir = dir;
+
+	return 0;
+error:
+	debugfs_remove_recursive(dir);
+	return -ENOMEM;
+}
+
+late_initcall(fei_debugfs_init);