first commit

.editorconfig

@@ -0,0 +1,22 @@
+# top-most EditorConfig file
+root = true
+
+# Unix-style newlines with a newline ending every file
+[*]
+end_of_line = lf
+insert_final_newline = true
+charset = utf-8
+indent_size = 2
+
+# Tab indentation (no size specified)
+[Makefile]
+indent_style = tab
+
+# YAML
+[*.yml]
+indent_style = space
+indent_size = 2
+
+[*.{c,h}]
+indent_style = space
+indent_size = 4

.gitignore

@@ -0,0 +1,7 @@
+!.gitkeep
+.vscode
+arpl.img*
+/buildroot-2022.02.2
+test.sh
+docker/Dockerfile
+docker/cache

PLATFORMS

@@ -0,0 +1,8 @@
+bromolow	3.10.108
+apollolake	4.4.180
+broadwell	4.4.180
+broadwellnk	4.4.180
+denverton	4.4.180
+geminilake	4.4.180
+v1000   4.4.180
+purley  4.4.180

README.md

@@ -0,0 +1 @@
+# arpl

TODO

@@ -0,0 +1,23 @@
+A fazer
+ - Implementar update do bzimage e ramdisk online
+
+Concluidos:
+ - Generalizar código dos addons
+ - Implementar checagem de conflito entre addons *** Usado alternativa de ter listagem de módulos não necessários ***
+ - Tirar MAXDISKS dos arquivos dos modelos e adicionar menu no synoinfo para configurar máximo de HDs
+ - mudar na configs dos modelos os módulos builtin para módulos não necessários
+ - Mudar palavra "extra" para "cmdline"
+ - Implementar exibição de cmdline e synoinfo dos modelos
+ - Adicionar checagem no grub para exibir ou não menu de boot
+ - Bug no boot.sh, se usuário mudar a variável netif_num o script repassa os macX sem considerar o novo número de interfaces 
+   *** TIRADO obrigatoriedade no LKM de passar esses parâmetros ***
+ - bug com macs, com 2 placas os MACs podem se inverter, checar isso
+   *** Resolvido com solução anterior ***
+ - Verifica se plataforma vai rodar na máquina checando as flags da CPU
+ - Implementar seleção da versão do LKM (dev ou prod)
+ - Usando TTYD para acesso via web
+ - Verificar se fica legal colocar na config dos modelos os addons obrigatórios como o qjs-dtb *** Usado outra maneira ***
+ - Implementar escolha de maxdisks
+
+
+https://kb.synology.com/en-me/DSM/tutorial/What_kind_of_CPU_does_my_NAS_have

Taskfile.yaml

@@ -0,0 +1,22 @@
+# https://taskfile.dev
+
+version: '3'
+
+tasks:
+  build-img:
+    cmds:
+      - ./img-gen.sh
+
+  build-docker-img:
+    dir: docker
+    cmds:
+      - ./build.sh
+
+  compile-lkms:
+    cmds:
+      - ./compile-lkm.sh
+
+  compile-addons:
+    dir: addons
+    cmds:
+      - ./compile-addons.sh {{.CLI_ARGS}}

addons/9p/install.sh

@@ -0,0 +1,6 @@
+if [ "${1}" = "rd" ]; then
+  echo "Installing module for Plan 9 Resource Sharing Support (9P2000)"
+  ${INSMOD} "/modules/9pnet.ko"
+  ${INSMOD} "/modules/9pnet_virtio.ko"
+  ${INSMOD} "/modules/9p.ko" ${PARAMS}
+fi

addons/9p/manifest.yml

@@ -0,0 +1,28 @@
+version: 1
+name: 9p
+description: "Driver for Plan 9 Resource Sharing Support (9P2000)"
+available-for:
+  bromolow-3.10.108:
+    install-script: &script "install.sh"
+    modules: true
+  apollolake-4.4.180:
+    install-script: *script
+    modules: true
+  broadwell-4.4.180:
+    install-script: *script
+    modules: true
+  broadwellnk-4.4.180:
+    install-script: *script
+    modules: true
+  denverton-4.4.180:
+    install-script: *script
+    modules: true
+  geminilake-4.4.180:
+    install-script: *script
+    modules: true
+  v1000-4.4.180:
+    install-script: *script
+    modules: true
+  purley-4.4.180:
+    install-script: *script
+    modules: true

addons/9p/src/3.10.108/Makefile

@@ -0,0 +1,36 @@
+obj-m := 9p.o
+
+9p-objs := \
+	vfs_super.o \
+	vfs_inode.o \
+	vfs_inode_dotl.o \
+	vfs_addr.o \
+	vfs_file.o \
+	vfs_dir.o \
+	vfs_dentry.o \
+	v9fs.o \
+	fid.o  \
+	xattr.o \
+	xattr_user.o
+
+9p-y += cache.o
+9p-n += acl.o
+
+obj-m := 9pnet.o
+obj-m += 9pnet_virtio.o
+obj-n += 9pnet_rdma.o
+
+9pnet-objs := \
+        mod.o \
+        client.o \
+        error.o \
+        util.o \
+        protocol.o \
+        trans_fd.o \
+        trans_common.o \
+
+9pnet_virtio-objs := \
+        trans_virtio.o
+
+9pnet_rdma-objs := \
+        trans_rdma.o

addons/9p/src/3.10.108/acl.c

@@ -0,0 +1,375 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/posix_acl_xattr.h>
+#include "xattr.h"
+#include "acl.h"
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name)
+{
+	ssize_t size;
+	void *value = NULL;
+	struct posix_acl *acl = NULL;
+
+	size = v9fs_fid_xattr_get(fid, name, NULL, 0);
+	if (size > 0) {
+		value = kzalloc(size, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		size = v9fs_fid_xattr_get(fid, name, value, size);
+		if (size > 0) {
+			acl = posix_acl_from_xattr(&init_user_ns, value, size);
+			if (IS_ERR(acl))
+				goto err_out;
+		}
+	} else if (size == -ENODATA || size == 0 ||
+		   size == -ENOSYS || size == -EOPNOTSUPP) {
+		acl = NULL;
+	} else
+		acl = ERR_PTR(-EIO);
+
+err_out:
+	kfree(value);
+	return acl;
+}
+
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+	int retval = 0;
+	struct posix_acl *pacl, *dacl;
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+			((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
+		set_cached_acl(inode, ACL_TYPE_DEFAULT, NULL);
+		set_cached_acl(inode, ACL_TYPE_ACCESS, NULL);
+		return 0;
+	}
+	/* get the default/access acl values and cache them */
+	dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT);
+	pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS);
+
+	if (!IS_ERR(dacl) && !IS_ERR(pacl)) {
+		set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+		set_cached_acl(inode, ACL_TYPE_ACCESS, pacl);
+	} else
+		retval = -EIO;
+
+	if (!IS_ERR(dacl))
+		posix_acl_release(dacl);
+
+	if (!IS_ERR(pacl))
+		posix_acl_release(pacl);
+
+	return retval;
+}
+
+static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type)
+{
+	struct posix_acl *acl;
+	/*
+	 * 9p Always cache the acl value when
+	 * instantiating the inode (v9fs_inode_from_fid)
+	 */
+	acl = get_cached_acl(inode, type);
+	BUG_ON(acl == ACL_NOT_CACHED);
+	return acl;
+}
+
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type)
+{
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+			((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
+		/*
+		 * On access = client  and acl = on mode get the acl
+		 * values from the server
+		 */
+		return NULL;
+	}
+	return v9fs_get_cached_acl(inode, type);
+
+}
+
+static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
+{
+	int retval;
+	char *name;
+	size_t size;
+	void *buffer;
+	if (!acl)
+		return 0;
+
+	/* Set a setxattr request to server */
+	size = posix_acl_xattr_size(acl->a_count);
+	buffer = kmalloc(size, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+	retval = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+	if (retval < 0)
+		goto err_free_out;
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	retval = v9fs_fid_xattr_set(fid, name, buffer, size, 0);
+err_free_out:
+	kfree(buffer);
+	return retval;
+}
+
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+	int retval = 0;
+	struct posix_acl *acl;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	acl = v9fs_get_cached_acl(inode, ACL_TYPE_ACCESS);
+	if (acl) {
+		retval = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+		if (retval)
+			return retval;
+		set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+		retval = v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
+		posix_acl_release(acl);
+	}
+	return retval;
+}
+
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+			struct posix_acl *dacl, struct posix_acl *acl)
+{
+	set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+	set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+	v9fs_set_acl(fid, ACL_TYPE_DEFAULT, dacl);
+	v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
+	return 0;
+}
+
+void v9fs_put_acl(struct posix_acl *dacl,
+		  struct posix_acl *acl)
+{
+	posix_acl_release(dacl);
+	posix_acl_release(acl);
+}
+
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+		  struct posix_acl **dpacl, struct posix_acl **pacl)
+{
+	int retval = 0;
+	umode_t mode = *modep;
+	struct posix_acl *acl = NULL;
+
+	if (!S_ISLNK(mode)) {
+		acl = v9fs_get_cached_acl(dir, ACL_TYPE_DEFAULT);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		if (!acl)
+			mode &= ~current_umask();
+	}
+	if (acl) {
+		if (S_ISDIR(mode))
+			*dpacl = posix_acl_dup(acl);
+		retval = posix_acl_create(&acl, GFP_NOFS, &mode);
+		if (retval < 0)
+			return retval;
+		if (retval > 0)
+			*pacl = acl;
+		else
+			posix_acl_release(acl);
+	}
+	*modep  = mode;
+	return 0;
+}
+
+static int v9fs_remote_get_acl(struct dentry *dentry, const char *name,
+			       void *buffer, size_t size, int type)
+{
+	char *full_name;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		full_name =  POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		full_name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	return v9fs_xattr_get(dentry, full_name, buffer, size);
+}
+
+static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name,
+			      void *buffer, size_t size, int type)
+{
+	struct v9fs_session_info *v9ses;
+	struct posix_acl *acl;
+	int error;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	/*
+	 * We allow set/get/list of acl when access=client is not specified
+	 */
+	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
+		return v9fs_remote_get_acl(dentry, name, buffer, size, type);
+
+	acl = v9fs_get_cached_acl(dentry->d_inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+	error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+	posix_acl_release(acl);
+
+	return error;
+}
+
+static int v9fs_remote_set_acl(struct dentry *dentry, const char *name,
+			      const void *value, size_t size,
+			      int flags, int type)
+{
+	char *full_name;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		full_name =  POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		full_name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	return v9fs_xattr_set(dentry, full_name, value, size, flags);
+}
+
+
+static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
+			      const void *value, size_t size,
+			      int flags, int type)
+{
+	int retval;
+	struct posix_acl *acl;
+	struct v9fs_session_info *v9ses;
+	struct inode *inode = dentry->d_inode;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	/*
+	 * set the attribute on the remote. Without even looking at the
+	 * xattr value. We leave it to the server to validate
+	 */
+	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
+		return v9fs_remote_set_acl(dentry, name,
+					   value, size, flags, type);
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+	if (value) {
+		/* update the cached acl value */
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		else if (acl) {
+			retval = posix_acl_valid(acl);
+			if (retval)
+				goto err_out;
+		}
+	} else
+		acl = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		if (acl) {
+			struct iattr iattr;
+
+			retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
+			if (retval)
+				goto err_out;
+			if (!acl) {
+				/*
+				 * ACL can be represented
+				 * by the mode bits. So don't
+				 * update ACL.
+				 */
+				value = NULL;
+				size = 0;
+			}
+			iattr.ia_valid = ATTR_MODE;
+			/* FIXME should we update ctime ?
+			 * What is the following setxattr update the
+			 * mode ?
+			 */
+			v9fs_vfs_setattr_dotl(dentry, &iattr);
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		if (!S_ISDIR(inode->i_mode)) {
+			retval = acl ? -EINVAL : 0;
+			goto err_out;
+		}
+		break;
+	default:
+		BUG();
+	}
+	retval = v9fs_xattr_set(dentry, name, value, size, flags);
+	if (!retval)
+		set_cached_acl(inode, type, acl);
+err_out:
+	posix_acl_release(acl);
+	return retval;
+}
+
+const struct xattr_handler v9fs_xattr_acl_access_handler = {
+	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.flags	= ACL_TYPE_ACCESS,
+	.get	= v9fs_xattr_get_acl,
+	.set	= v9fs_xattr_set_acl,
+};
+
+const struct xattr_handler v9fs_xattr_acl_default_handler = {
+	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.flags	= ACL_TYPE_DEFAULT,
+	.get	= v9fs_xattr_get_acl,
+	.set	= v9fs_xattr_set_acl,
+};

addons/9p/src/3.10.108/acl.h

@@ -0,0 +1,55 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+#ifndef FS_9P_ACL_H
+#define FS_9P_ACL_H
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+extern int v9fs_get_acl(struct inode *, struct p9_fid *);
+extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type);
+extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
+extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
+			       struct posix_acl *, struct posix_acl *);
+extern int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+			 struct posix_acl **dpacl, struct posix_acl **pacl);
+extern void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
+#else
+#define v9fs_iop_get_acl NULL
+static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+	return 0;
+}
+static inline int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+	return 0;
+}
+static inline int v9fs_set_create_acl(struct inode *inode,
+				      struct p9_fid *fid,
+				      struct posix_acl *dacl,
+				      struct posix_acl *acl)
+{
+	return 0;
+}
+static inline void v9fs_put_acl(struct posix_acl *dacl,
+				struct posix_acl *acl)
+{
+}
+static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+				struct posix_acl **dpacl,
+				struct posix_acl **pacl)
+{
+	return 0;
+}
+
+#endif
+#endif /* FS_9P_XATTR_H */

addons/9p/src/3.10.108/cache.c

@@ -0,0 +1,415 @@
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/jiffies.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+
+#include "v9fs.h"
+#include "cache.h"
+
+#define CACHETAG_LEN  11
+
+struct fscache_netfs v9fs_cache_netfs = {
+	.name 		= "9p",
+	.version 	= 0,
+};
+
+/**
+ * v9fs_random_cachetag - Generate a random tag to be associated
+ *			  with a new cache session.
+ *
+ * The value of jiffies is used for a fairly randomly cache tag.
+ */
+
+static
+int v9fs_random_cachetag(struct v9fs_session_info *v9ses)
+{
+	v9ses->cachetag = kmalloc(CACHETAG_LEN, GFP_KERNEL);
+	if (!v9ses->cachetag)
+		return -ENOMEM;
+
+	return scnprintf(v9ses->cachetag, CACHETAG_LEN, "%lu", jiffies);
+}
+
+static uint16_t v9fs_cache_session_get_key(const void *cookie_netfs_data,
+					   void *buffer, uint16_t bufmax)
+{
+	struct v9fs_session_info *v9ses;
+	uint16_t klen = 0;
+
+	v9ses = (struct v9fs_session_info *)cookie_netfs_data;
+	p9_debug(P9_DEBUG_FSC, "session %p buf %p size %u\n",
+		 v9ses, buffer, bufmax);
+
+	if (v9ses->cachetag)
+		klen = strlen(v9ses->cachetag);
+
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, v9ses->cachetag, klen);
+	p9_debug(P9_DEBUG_FSC, "cache session tag %s\n", v9ses->cachetag);
+	return klen;
+}
+
+const struct fscache_cookie_def v9fs_cache_session_index_def = {
+	.name		= "9P.session",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= v9fs_cache_session_get_key,
+};
+
+void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses)
+{
+	/* If no cache session tag was specified, we generate a random one. */
+	if (!v9ses->cachetag)
+		v9fs_random_cachetag(v9ses);
+
+	v9ses->fscache = fscache_acquire_cookie(v9fs_cache_netfs.primary_index,
+						&v9fs_cache_session_index_def,
+						v9ses);
+	p9_debug(P9_DEBUG_FSC, "session %p get cookie %p\n",
+		 v9ses, v9ses->fscache);
+}
+
+void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses)
+{
+	p9_debug(P9_DEBUG_FSC, "session %p put cookie %p\n",
+		 v9ses, v9ses->fscache);
+	fscache_relinquish_cookie(v9ses->fscache, 0);
+	v9ses->fscache = NULL;
+}
+
+
+static uint16_t v9fs_cache_inode_get_key(const void *cookie_netfs_data,
+					 void *buffer, uint16_t bufmax)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	memcpy(buffer, &v9inode->qid.path, sizeof(v9inode->qid.path));
+	p9_debug(P9_DEBUG_FSC, "inode %p get key %llu\n",
+		 &v9inode->vfs_inode, v9inode->qid.path);
+	return sizeof(v9inode->qid.path);
+}
+
+static void v9fs_cache_inode_get_attr(const void *cookie_netfs_data,
+				      uint64_t *size)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	*size = i_size_read(&v9inode->vfs_inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get attr %llu\n",
+		 &v9inode->vfs_inode, *size);
+}
+
+static uint16_t v9fs_cache_inode_get_aux(const void *cookie_netfs_data,
+					 void *buffer, uint16_t buflen)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	memcpy(buffer, &v9inode->qid.version, sizeof(v9inode->qid.version));
+	p9_debug(P9_DEBUG_FSC, "inode %p get aux %u\n",
+		 &v9inode->vfs_inode, v9inode->qid.version);
+	return sizeof(v9inode->qid.version);
+}
+
+static enum
+fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data,
+					    const void *buffer,
+					    uint16_t buflen)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+
+	if (buflen != sizeof(v9inode->qid.version))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	if (memcmp(buffer, &v9inode->qid.version,
+		   sizeof(v9inode->qid.version)))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data)
+{
+	struct v9fs_inode *v9inode = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	for (;;) {
+		nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+const struct fscache_cookie_def v9fs_cache_inode_index_def = {
+	.name		= "9p.inode",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= v9fs_cache_inode_get_key,
+	.get_attr	= v9fs_cache_inode_get_attr,
+	.get_aux	= v9fs_cache_inode_get_aux,
+	.check_aux	= v9fs_cache_inode_check_aux,
+	.now_uncached	= v9fs_cache_inode_now_uncached,
+};
+
+void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode;
+	struct v9fs_session_info *v9ses;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	v9inode = V9FS_I(inode);
+	if (v9inode->fscache)
+		return;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
+						  &v9fs_cache_inode_index_def,
+						  v9inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
+		 inode, v9inode->fscache);
+}
+
+void v9fs_cache_inode_put_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+	p9_debug(P9_DEBUG_FSC, "inode %p put cookie %p\n",
+		 inode, v9inode->fscache);
+
+	fscache_relinquish_cookie(v9inode->fscache, 0);
+	v9inode->fscache = NULL;
+}
+
+void v9fs_cache_inode_flush_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+	p9_debug(P9_DEBUG_FSC, "inode %p flush cookie %p\n",
+		 inode, v9inode->fscache);
+
+	fscache_relinquish_cookie(v9inode->fscache, 1);
+	v9inode->fscache = NULL;
+}
+
+void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_fid *fid;
+
+	if (!v9inode->fscache)
+		return;
+
+	spin_lock(&v9inode->fscache_lock);
+	fid = filp->private_data;
+	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+		v9fs_cache_inode_flush_cookie(inode);
+	else
+		v9fs_cache_inode_get_cookie(inode);
+
+	spin_unlock(&v9inode->fscache_lock);
+}
+
+void v9fs_cache_inode_reset_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct v9fs_session_info *v9ses;
+	struct fscache_cookie *old;
+
+	if (!v9inode->fscache)
+		return;
+
+	old = v9inode->fscache;
+
+	spin_lock(&v9inode->fscache_lock);
+	fscache_relinquish_cookie(v9inode->fscache, 1);
+
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
+						  &v9fs_cache_inode_index_def,
+						  v9inode);
+	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
+		 inode, old, v9inode->fscache);
+
+	spin_unlock(&v9inode->fscache_lock);
+}
+
+int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	BUG_ON(!v9inode->fscache);
+
+	return fscache_maybe_release_page(v9inode->fscache, page, gfp);
+}
+
+void __v9fs_fscache_invalidate_page(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	BUG_ON(!v9inode->fscache);
+
+	if (PageFsCache(page)) {
+		fscache_wait_on_page_write(v9inode->fscache, page);
+		BUG_ON(!PageLocked(page));
+		fscache_uncache_page(v9inode->fscache, page);
+	}
+}
+
+static void v9fs_vfs_readpage_complete(struct page *page, void *data,
+				       int error)
+{
+	if (!error)
+		SetPageUptodate(page);
+
+	unlock_page(page);
+}
+
+/**
+ * __v9fs_readpage_from_fscache - read a page from cache
+ *
+ * Returns 0 if the pages are in cache and a BIO is submitted,
+ * 1 if the pages are not in cache and -error otherwise.
+ */
+
+int __v9fs_readpage_from_fscache(struct inode *inode, struct page *page)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	if (!v9inode->fscache)
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_page(v9inode->fscache,
+					 page,
+					 v9fs_vfs_readpage_complete,
+					 NULL,
+					 GFP_KERNEL);
+	switch (ret) {
+	case -ENOBUFS:
+	case -ENODATA:
+		p9_debug(P9_DEBUG_FSC, "page/inode not in cache %d\n", ret);
+		return 1;
+	case 0:
+		p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
+		return ret;
+	default:
+		p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
+		return ret;
+	}
+}
+
+/**
+ * __v9fs_readpages_from_fscache - read multiple pages from cache
+ *
+ * Returns 0 if the pages are in cache and a BIO is submitted,
+ * 1 if the pages are not in cache and -error otherwise.
+ */
+
+int __v9fs_readpages_from_fscache(struct inode *inode,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p pages %u\n", inode, *nr_pages);
+	if (!v9inode->fscache)
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_pages(v9inode->fscache,
+					  mapping, pages, nr_pages,
+					  v9fs_vfs_readpage_complete,
+					  NULL,
+					  mapping_gfp_mask(mapping));
+	switch (ret) {
+	case -ENOBUFS:
+	case -ENODATA:
+		p9_debug(P9_DEBUG_FSC, "pages/inodes not in cache %d\n", ret);
+		return 1;
+	case 0:
+		BUG_ON(!list_empty(pages));
+		BUG_ON(*nr_pages != 0);
+		p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
+		return ret;
+	default:
+		p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
+		return ret;
+	}
+}
+
+/**
+ * __v9fs_readpage_to_fscache - write a page to the cache
+ *
+ */
+
+void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	ret = fscache_write_page(v9inode->fscache, page, GFP_KERNEL);
+	p9_debug(P9_DEBUG_FSC, "ret =  %d\n", ret);
+	if (ret != 0)
+		v9fs_uncache_page(inode, page);
+}
+
+/*
+ * wait for a page to complete writing to the cache
+ */
+void __v9fs_fscache_wait_on_page_write(struct inode *inode, struct page *page)
+{
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	if (PageFsCache(page))
+		fscache_wait_on_page_write(v9inode->fscache, page);
+}

addons/9p/src/3.10.108/cache.h

@@ -0,0 +1,139 @@
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#ifndef _9P_CACHE_H
+#ifdef CONFIG_9P_FSCACHE
+#include <linux/fscache.h>
+#include <linux/spinlock.h>
+
+extern struct fscache_netfs v9fs_cache_netfs;
+extern const struct fscache_cookie_def v9fs_cache_session_index_def;
+extern const struct fscache_cookie_def v9fs_cache_inode_index_def;
+
+extern void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses);
+extern void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses);
+
+extern void v9fs_cache_inode_get_cookie(struct inode *inode);
+extern void v9fs_cache_inode_put_cookie(struct inode *inode);
+extern void v9fs_cache_inode_flush_cookie(struct inode *inode);
+extern void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp);
+extern void v9fs_cache_inode_reset_cookie(struct inode *inode);
+
+extern int __v9fs_cache_register(void);
+extern void __v9fs_cache_unregister(void);
+
+extern int __v9fs_fscache_release_page(struct page *page, gfp_t gfp);
+extern void __v9fs_fscache_invalidate_page(struct page *page);
+extern int __v9fs_readpage_from_fscache(struct inode *inode,
+					struct page *page);
+extern int __v9fs_readpages_from_fscache(struct inode *inode,
+					 struct address_space *mapping,
+					 struct list_head *pages,
+					 unsigned *nr_pages);
+extern void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page);
+extern void __v9fs_fscache_wait_on_page_write(struct inode *inode,
+					      struct page *page);
+
+static inline int v9fs_fscache_release_page(struct page *page,
+					    gfp_t gfp)
+{
+	return __v9fs_fscache_release_page(page, gfp);
+}
+
+static inline void v9fs_fscache_invalidate_page(struct page *page)
+{
+	__v9fs_fscache_invalidate_page(page);
+}
+
+static inline int v9fs_readpage_from_fscache(struct inode *inode,
+					     struct page *page)
+{
+	return __v9fs_readpage_from_fscache(inode, page);
+}
+
+static inline int v9fs_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return __v9fs_readpages_from_fscache(inode, mapping, pages,
+					     nr_pages);
+}
+
+static inline void v9fs_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{
+	if (PageFsCache(page))
+		__v9fs_readpage_to_fscache(inode, page);
+}
+
+static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	fscache_uncache_page(v9inode->fscache, page);
+	BUG_ON(PageFsCache(page));
+}
+
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
+{
+	return __v9fs_fscache_wait_on_page_write(inode, page);
+}
+
+#else /* CONFIG_9P_FSCACHE */
+
+static inline int v9fs_fscache_release_page(struct page *page,
+					    gfp_t gfp) {
+	return 1;
+}
+
+static inline void v9fs_fscache_invalidate_page(struct page *page) {}
+
+static inline int v9fs_readpage_from_fscache(struct inode *inode,
+					     struct page *page)
+{
+	return -ENOBUFS;
+}
+
+static inline int v9fs_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return -ENOBUFS;
+}
+
+static inline void v9fs_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{}
+
+static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
+{}
+
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
+{
+	return;
+}
+
+#endif /* CONFIG_9P_FSCACHE */
+#endif /* _9P_CACHE_H */

addons/9p/src/3.10.108/error.c

@@ -0,0 +1,247 @@
+/*
+ * linux/fs/9p/error.c
+ *
+ * Error string handling
+ *
+ * Plan 9 uses error strings, Unix uses error numbers.  These functions
+ * try to help manage that and provide for dynamically adding error
+ * mappings.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/errno.h>
+#include <net/9p/9p.h>
+
+/**
+ * struct errormap - map string errors from Plan 9 to Linux numeric ids
+ * @name: string sent over 9P
+ * @val: numeric id most closely representing @name
+ * @namelen: length of string
+ * @list: hash-table list for string lookup
+ */
+struct errormap {
+	char *name;
+	int val;
+
+	int namelen;
+	struct hlist_node list;
+};
+
+#define ERRHASHSZ		32
+static struct hlist_head hash_errmap[ERRHASHSZ];
+
+/* FixMe - reduce to a reasonable size */
+static struct errormap errmap[] = {
+	{"Operation not permitted", EPERM},
+	{"wstat prohibited", EPERM},
+	{"No such file or directory", ENOENT},
+	{"directory entry not found", ENOENT},
+	{"file not found", ENOENT},
+	{"Interrupted system call", EINTR},
+	{"Input/output error", EIO},
+	{"No such device or address", ENXIO},
+	{"Argument list too long", E2BIG},
+	{"Bad file descriptor", EBADF},
+	{"Resource temporarily unavailable", EAGAIN},
+	{"Cannot allocate memory", ENOMEM},
+	{"Permission denied", EACCES},
+	{"Bad address", EFAULT},
+	{"Block device required", ENOTBLK},
+	{"Device or resource busy", EBUSY},
+	{"File exists", EEXIST},
+	{"Invalid cross-device link", EXDEV},
+	{"No such device", ENODEV},
+	{"Not a directory", ENOTDIR},
+	{"Is a directory", EISDIR},
+	{"Invalid argument", EINVAL},
+	{"Too many open files in system", ENFILE},
+	{"Too many open files", EMFILE},
+	{"Text file busy", ETXTBSY},
+	{"File too large", EFBIG},
+	{"No space left on device", ENOSPC},
+	{"Illegal seek", ESPIPE},
+	{"Read-only file system", EROFS},
+	{"Too many links", EMLINK},
+	{"Broken pipe", EPIPE},
+	{"Numerical argument out of domain", EDOM},
+	{"Numerical result out of range", ERANGE},
+	{"Resource deadlock avoided", EDEADLK},
+	{"File name too long", ENAMETOOLONG},
+	{"No locks available", ENOLCK},
+	{"Function not implemented", ENOSYS},
+	{"Directory not empty", ENOTEMPTY},
+	{"Too many levels of symbolic links", ELOOP},
+	{"No message of desired type", ENOMSG},
+	{"Identifier removed", EIDRM},
+	{"No data available", ENODATA},
+	{"Machine is not on the network", ENONET},
+	{"Package not installed", ENOPKG},
+	{"Object is remote", EREMOTE},
+	{"Link has been severed", ENOLINK},
+	{"Communication error on send", ECOMM},
+	{"Protocol error", EPROTO},
+	{"Bad message", EBADMSG},
+	{"File descriptor in bad state", EBADFD},
+	{"Streams pipe error", ESTRPIPE},
+	{"Too many users", EUSERS},
+	{"Socket operation on non-socket", ENOTSOCK},
+	{"Message too long", EMSGSIZE},
+	{"Protocol not available", ENOPROTOOPT},
+	{"Protocol not supported", EPROTONOSUPPORT},
+	{"Socket type not supported", ESOCKTNOSUPPORT},
+	{"Operation not supported", EOPNOTSUPP},
+	{"Protocol family not supported", EPFNOSUPPORT},
+	{"Network is down", ENETDOWN},
+	{"Network is unreachable", ENETUNREACH},
+	{"Network dropped connection on reset", ENETRESET},
+	{"Software caused connection abort", ECONNABORTED},
+	{"Connection reset by peer", ECONNRESET},
+	{"No buffer space available", ENOBUFS},
+	{"Transport endpoint is already connected", EISCONN},
+	{"Transport endpoint is not connected", ENOTCONN},
+	{"Cannot send after transport endpoint shutdown", ESHUTDOWN},
+	{"Connection timed out", ETIMEDOUT},
+	{"Connection refused", ECONNREFUSED},
+	{"Host is down", EHOSTDOWN},
+	{"No route to host", EHOSTUNREACH},
+	{"Operation already in progress", EALREADY},
+	{"Operation now in progress", EINPROGRESS},
+	{"Is a named type file", EISNAM},
+	{"Remote I/O error", EREMOTEIO},
+	{"Disk quota exceeded", EDQUOT},
+/* errors from fossil, vacfs, and u9fs */
+	{"fid unknown or out of range", EBADF},
+	{"permission denied", EACCES},
+	{"file does not exist", ENOENT},
+	{"authentication failed", ECONNREFUSED},
+	{"bad offset in directory read", ESPIPE},
+	{"bad use of fid", EBADF},
+	{"wstat can't convert between files and directories", EPERM},
+	{"directory is not empty", ENOTEMPTY},
+	{"file exists", EEXIST},
+	{"file already exists", EEXIST},
+	{"file or directory already exists", EEXIST},
+	{"fid already in use", EBADF},
+	{"file in use", ETXTBSY},
+	{"i/o error", EIO},
+	{"file already open for I/O", ETXTBSY},
+	{"illegal mode", EINVAL},
+	{"illegal name", ENAMETOOLONG},
+	{"not a directory", ENOTDIR},
+	{"not a member of proposed group", EPERM},
+	{"not owner", EACCES},
+	{"only owner can change group in wstat", EACCES},
+	{"read only file system", EROFS},
+	{"no access to special file", EPERM},
+	{"i/o count too large", EIO},
+	{"unknown group", EINVAL},
+	{"unknown user", EINVAL},
+	{"bogus wstat buffer", EPROTO},
+	{"exclusive use file already open", EAGAIN},
+	{"corrupted directory entry", EIO},
+	{"corrupted file entry", EIO},
+	{"corrupted block label", EIO},
+	{"corrupted meta data", EIO},
+	{"illegal offset", EINVAL},
+	{"illegal path element", ENOENT},
+	{"root of file system is corrupted", EIO},
+	{"corrupted super block", EIO},
+	{"protocol botch", EPROTO},
+	{"file system is full", ENOSPC},
+	{"file is in use", EAGAIN},
+	{"directory entry is not allocated", ENOENT},
+	{"file is read only", EROFS},
+	{"file has been removed", EIDRM},
+	{"only support truncation to zero length", EPERM},
+	{"cannot remove root", EPERM},
+	{"file too big", EFBIG},
+	{"venti i/o error", EIO},
+	/* these are not errors */
+	{"u9fs rhostsauth: no authentication required", 0},
+	{"u9fs authnone: no authentication required", 0},
+	{NULL, -1}
+};
+
+/**
+ * p9_error_init - preload mappings into hash list
+ *
+ */
+
+int p9_error_init(void)
+{
+	struct errormap *c;
+	int bucket;
+
+	/* initialize hash table */
+	for (bucket = 0; bucket < ERRHASHSZ; bucket++)
+		INIT_HLIST_HEAD(&hash_errmap[bucket]);
+
+	/* load initial error map into hash table */
+	for (c = errmap; c->name != NULL; c++) {
+		c->namelen = strlen(c->name);
+		bucket = jhash(c->name, c->namelen, 0) % ERRHASHSZ;
+		INIT_HLIST_NODE(&c->list);
+		hlist_add_head(&c->list, &hash_errmap[bucket]);
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL(p9_error_init);
+
+/**
+ * errstr2errno - convert error string to error number
+ * @errstr: error string
+ * @len: length of error string
+ *
+ */
+
+int p9_errstr2errno(char *errstr, int len)
+{
+	int errno;
+	struct errormap *c;
+	int bucket;
+
+	errno = 0;
+	c = NULL;
+	bucket = jhash(errstr, len, 0) % ERRHASHSZ;
+	hlist_for_each_entry(c, &hash_errmap[bucket], list) {
+		if (c->namelen == len && !memcmp(c->name, errstr, len)) {
+			errno = c->val;
+			break;
+		}
+	}
+
+	if (errno == 0) {
+		/* TODO: if error isn't found, add it dynamically */
+		errstr[len] = 0;
+		pr_err("%s: server reported unknown error %s\n",
+		       __func__, errstr);
+		errno = ESERVERFAULT;
+	}
+
+	return -errno;
+}
+EXPORT_SYMBOL(p9_errstr2errno);

addons/9p/src/3.10.108/fid.c

@@ -0,0 +1,306 @@
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/idr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * v9fs_fid_add - add a fid to a dentry
+ * @dentry: dentry that the fid is being added to
+ * @fid: fid to add
+ *
+ */
+
+static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid)
+{
+	hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata);
+}
+
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
+{
+	spin_lock(&dentry->d_lock);
+	__add_fid(dentry, fid);
+	spin_unlock(&dentry->d_lock);
+}
+
+/**
+ * v9fs_fid_find - retrieve a fid that belongs to the specified uid
+ * @dentry: dentry to look for fid in
+ * @uid: return fid that belongs to the specified user
+ * @any: if non-zero, return any fid associated with the dentry
+ *
+ */
+
+static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
+{
+	struct p9_fid *fid, *ret;
+
+	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p) uid %d any %d\n",
+		 dentry->d_name.name, dentry, from_kuid(&init_user_ns, uid),
+		 any);
+	ret = NULL;
+	/* we'll recheck under lock if there's anything to look in */
+	if (dentry->d_fsdata) {
+		struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
+		spin_lock(&dentry->d_lock);
+		hlist_for_each_entry(fid, h, dlist) {
+			if (any || uid_eq(fid->uid, uid)) {
+				ret = fid;
+				break;
+			}
+		}
+		spin_unlock(&dentry->d_lock);
+	}
+
+	return ret;
+}
+
+/*
+ * We need to hold v9ses->rename_sem as long as we hold references
+ * to returned path array. Array element contain pointers to
+ * dentry names.
+ */
+static int build_path_from_dentry(struct v9fs_session_info *v9ses,
+				  struct dentry *dentry, char ***names)
+{
+	int n = 0, i;
+	char **wnames;
+	struct dentry *ds;
+
+	for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
+		n++;
+
+	wnames = kmalloc(sizeof(char *) * n, GFP_KERNEL);
+	if (!wnames)
+		goto err_out;
+
+	for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
+		wnames[i] = (char  *)ds->d_name.name;
+
+	*names = wnames;
+	return n;
+err_out:
+	return -ENOMEM;
+}
+
+static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
+					       kuid_t uid, int any)
+{
+	struct dentry *ds;
+	char **wnames, *uname;
+	int i, n, l, clone, access;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid, *old_fid = NULL;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	access = v9ses->flags & V9FS_ACCESS_MASK;
+	fid = v9fs_fid_find(dentry, uid, any);
+	if (fid)
+		return fid;
+	/*
+	 * we don't have a matching fid. To do a TWALK we need
+	 * parent fid. We need to prevent rename when we want to
+	 * look at the parent.
+	 */
+	down_read(&v9ses->rename_sem);
+	ds = dentry->d_parent;
+	fid = v9fs_fid_find(ds, uid, any);
+	if (fid) {
+		/* Found the parent fid do a lookup with that */
+		fid = p9_client_walk(fid, 1, (char **)&dentry->d_name.name, 1);
+		goto fid_out;
+	}
+	up_read(&v9ses->rename_sem);
+
+	/* start from the root and try to do a lookup */
+	fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any);
+	if (!fid) {
+		/* the user is not attached to the fs yet */
+		if (access == V9FS_ACCESS_SINGLE)
+			return ERR_PTR(-EPERM);
+
+		if (v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses))
+				uname = NULL;
+		else
+			uname = v9ses->uname;
+
+		fid = p9_client_attach(v9ses->clnt, NULL, uname, uid,
+				       v9ses->aname);
+		if (IS_ERR(fid))
+			return fid;
+
+		v9fs_fid_add(dentry->d_sb->s_root, fid);
+	}
+	/* If we are root ourself just return that */
+	if (dentry->d_sb->s_root == dentry)
+		return fid;
+	/*
+	 * Do a multipath walk with attached root.
+	 * When walking parent we need to make sure we
+	 * don't have a parallel rename happening
+	 */
+	down_read(&v9ses->rename_sem);
+	n  = build_path_from_dentry(v9ses, dentry, &wnames);
+	if (n < 0) {
+		fid = ERR_PTR(n);
+		goto err_out;
+	}
+	clone = 1;
+	i = 0;
+	while (i < n) {
+		l = min(n - i, P9_MAXWELEM);
+		/*
+		 * We need to hold rename lock when doing a multipath
+		 * walk to ensure none of the patch component change
+		 */
+		fid = p9_client_walk(fid, l, &wnames[i], clone);
+		if (IS_ERR(fid)) {
+			if (old_fid) {
+				/*
+				 * If we fail, clunk fid which are mapping
+				 * to path component and not the last component
+				 * of the path.
+				 */
+				p9_client_clunk(old_fid);
+			}
+			kfree(wnames);
+			goto err_out;
+		}
+		old_fid = fid;
+		i += l;
+		clone = 0;
+	}
+	kfree(wnames);
+fid_out:
+	if (!IS_ERR(fid)) {
+		spin_lock(&dentry->d_lock);
+		if (d_unhashed(dentry)) {
+			spin_unlock(&dentry->d_lock);
+			p9_client_clunk(fid);
+			fid = ERR_PTR(-ENOENT);
+		} else {
+			__add_fid(dentry, fid);
+			spin_unlock(&dentry->d_lock);
+		}
+	}
+err_out:
+	up_read(&v9ses->rename_sem);
+	return fid;
+}
+
+/**
+ * v9fs_fid_lookup - lookup for a fid, try to walk if not found
+ * @dentry: dentry to look for fid in
+ *
+ * Look for a fid in the specified dentry for the current user.
+ * If no fid is found, try to create one walking from a fid from the parent
+ * dentry (if it has one), or the root dentry. If the user haven't accessed
+ * the fs yet, attach now and walk from the root.
+ */
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
+{
+	kuid_t uid;
+	int  any, access;
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	access = v9ses->flags & V9FS_ACCESS_MASK;
+	switch (access) {
+	case V9FS_ACCESS_SINGLE:
+	case V9FS_ACCESS_USER:
+	case V9FS_ACCESS_CLIENT:
+		uid = current_fsuid();
+		any = 0;
+		break;
+
+	case V9FS_ACCESS_ANY:
+		uid = v9ses->uid;
+		any = 1;
+		break;
+
+	default:
+		uid = INVALID_UID;
+		any = 0;
+		break;
+	}
+	return v9fs_fid_lookup_with_uid(dentry, uid, any);
+}
+
+struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
+{
+	struct p9_fid *fid, *ret;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return fid;
+
+	ret = p9_client_walk(fid, 0, NULL, 1);
+	return ret;
+}
+
+static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, kuid_t uid)
+{
+	struct p9_fid *fid, *ret;
+
+	fid = v9fs_fid_lookup_with_uid(dentry, uid, 0);
+	if (IS_ERR(fid))
+		return fid;
+
+	ret = p9_client_walk(fid, 0, NULL, 1);
+	return ret;
+}
+
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
+{
+	int err;
+	struct p9_fid *fid;
+
+	fid = v9fs_fid_clone_with_uid(dentry, GLOBAL_ROOT_UID);
+	if (IS_ERR(fid))
+		goto error_out;
+	/*
+	 * writeback fid will only be used to write back the
+	 * dirty pages. We always request for the open fid in read-write
+	 * mode so that a partial page write which result in page
+	 * read can work.
+	 */
+	err = p9_client_open(fid, O_RDWR);
+	if (err < 0) {
+		p9_client_clunk(fid);
+		fid = ERR_PTR(err);
+		goto error_out;
+	}
+error_out:
+	return fid;
+}

addons/9p/src/3.10.108/fid.h

@@ -0,0 +1,30 @@
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_FID_H
+#define FS_9P_FID_H
+#include <linux/list.h>
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
+struct p9_fid *v9fs_fid_clone(struct dentry *dentry);
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
+#endif

addons/9p/src/3.10.108/mod.c

@@ -0,0 +1,201 @@
+/*
+ *  net/9p/9p.c
+ *
+ *  9P entry point
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/moduleparam.h>
+#include <net/9p/9p.h>
+#include <linux/fs.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_NET_9P_DEBUG
+unsigned int p9_debug_level = 0;	/* feature-rific global debug level  */
+EXPORT_SYMBOL(p9_debug_level);
+module_param_named(debug, p9_debug_level, uint, 0);
+MODULE_PARM_DESC(debug, "9P debugging level");
+
+void _p9_debug(enum p9_debug_flags level, const char *func,
+		const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	if ((p9_debug_level & level) != level)
+		return;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (level == P9_DEBUG_9P)
+		pr_notice("(%8.8d) %pV", task_pid_nr(current), &vaf);
+	else
+		pr_notice("-- %s (%d): %pV", func, task_pid_nr(current), &vaf);
+
+	va_end(args);
+}
+EXPORT_SYMBOL(_p9_debug);
+#endif
+
+/*
+ * Dynamic Transport Registration Routines
+ *
+ */
+
+static DEFINE_SPINLOCK(v9fs_trans_lock);
+static LIST_HEAD(v9fs_trans_list);
+
+/**
+ * v9fs_register_trans - register a new transport with 9p
+ * @m: structure describing the transport module and entry points
+ *
+ */
+void v9fs_register_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_add_tail(&m->list, &v9fs_trans_list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_register_trans);
+
+/**
+ * v9fs_unregister_trans - unregister a 9p transport
+ * @m: the transport to remove
+ *
+ */
+void v9fs_unregister_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_del_init(&m->list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_unregister_trans);
+
+/**
+ * v9fs_get_trans_by_name - get transport with the matching name
+ * @name: string identifying transport
+ *
+ */
+struct p9_trans_module *v9fs_get_trans_by_name(char *s)
+{
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (strcmp(t->name, s) == 0 &&
+		    try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
+}
+EXPORT_SYMBOL(v9fs_get_trans_by_name);
+
+/**
+ * v9fs_get_default_trans - get the default transport
+ *
+ */
+
+struct p9_trans_module *v9fs_get_default_trans(void)
+{
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (t->def && try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	if (!found)
+		list_for_each_entry(t, &v9fs_trans_list, list)
+			if (try_module_get(t->owner)) {
+				found = t;
+				break;
+			}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
+}
+EXPORT_SYMBOL(v9fs_get_default_trans);
+
+/**
+ * v9fs_put_trans - put trans
+ * @m: transport to put
+ *
+ */
+void v9fs_put_trans(struct p9_trans_module *m)
+{
+	if (m)
+		module_put(m->owner);
+}
+
+/**
+ * init_p9 - Initialize module
+ *
+ */
+static int __init init_p9(void)
+{
+	int ret = 0;
+
+	p9_error_init();
+	pr_info("Installing 9P2000 support\n");
+	p9_trans_fd_init();
+
+	return ret;
+}
+
+/**
+ * exit_p9 - shutdown module
+ *
+ */
+
+static void __exit exit_p9(void)
+{
+	pr_info("Unloading 9P2000 support\n");
+
+	p9_trans_fd_exit();
+}
+
+module_init(init_p9)
+module_exit(exit_p9)
+
+MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>");
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>");
+MODULE_LICENSE("GPL");

addons/9p/src/3.10.108/protocol.c

@@ -0,0 +1,636 @@
+/*
+ * net/9p/protocol.c
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include "protocol.h"
+
+#include <trace/events/9p.h>
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
+
+void p9stat_free(struct p9_wstat *stbuf)
+{
+	kfree(stbuf->name);
+	kfree(stbuf->uid);
+	kfree(stbuf->gid);
+	kfree(stbuf->muid);
+	kfree(stbuf->extension);
+}
+EXPORT_SYMBOL(p9stat_free);
+
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
+{
+	size_t len = min(pdu->size - pdu->offset, size);
+	memcpy(data, &pdu->sdata[pdu->offset], len);
+	pdu->offset += len;
+	return size - len;
+}
+
+static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
+{
+	size_t len = min(pdu->capacity - pdu->size, size);
+	memcpy(&pdu->sdata[pdu->size], data, len);
+	pdu->size += len;
+	return size - len;
+}
+
+static size_t
+pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size)
+{
+	size_t len = min(pdu->capacity - pdu->size, size);
+	if (copy_from_user(&pdu->sdata[pdu->size], udata, len))
+		len = 0;
+
+	pdu->size += len;
+	return size - len;
+}
+
+/*
+	b - int8_t
+	w - int16_t
+	d - int32_t
+	q - int64_t
+	s - string
+	u - numeric uid
+	g - numeric gid
+	S - stat
+	Q - qid
+	D - data blob (int32_t size followed by void *, results are not freed)
+	T - array of strings (int16_t count, followed by strings)
+	R - array of qids (int16_t count, followed by qids)
+	A - stat for 9p2000.L (p9_stat_dotl)
+	? - if optional = 1, continue parsing
+*/
+
+static int
+p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
+	va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t *val = va_arg(ap, int8_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+			}
+			break;
+		case 'w':{
+				int16_t *val = va_arg(ap, int16_t *);
+				__le16 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le16_to_cpu(le_val);
+			}
+			break;
+		case 'd':{
+				int32_t *val = va_arg(ap, int32_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le32_to_cpu(le_val);
+			}
+			break;
+		case 'q':{
+				int64_t *val = va_arg(ap, int64_t *);
+				__le64 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le64_to_cpu(le_val);
+			}
+			break;
+		case 's':{
+				char **sptr = va_arg(ap, char **);
+				uint16_t len;
+
+				errcode = p9pdu_readf(pdu, proto_version,
+								"w", &len);
+				if (errcode)
+					break;
+
+				*sptr = kmalloc(len + 1, GFP_NOFS);
+				if (*sptr == NULL) {
+					errcode = -EFAULT;
+					break;
+				}
+				if (pdu_read(pdu, *sptr, len)) {
+					errcode = -EFAULT;
+					kfree(*sptr);
+					*sptr = NULL;
+				} else
+					(*sptr)[len] = 0;
+			}
+			break;
+		case 'u': {
+				kuid_t *uid = va_arg(ap, kuid_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*uid = make_kuid(&init_user_ns,
+						 le32_to_cpu(le_val));
+			} break;
+		case 'g': {
+				kgid_t *gid = va_arg(ap, kgid_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*gid = make_kgid(&init_user_ns,
+						 le32_to_cpu(le_val));
+			} break;
+		case 'Q':{
+				struct p9_qid *qid =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_readf(pdu, proto_version, "bdq",
+						      &qid->type, &qid->version,
+						      &qid->path);
+			}
+			break;
+		case 'S':{
+				struct p9_wstat *stbuf =
+				    va_arg(ap, struct p9_wstat *);
+
+				memset(stbuf, 0, sizeof(struct p9_wstat));
+				stbuf->n_uid = stbuf->n_muid = INVALID_UID;
+				stbuf->n_gid = INVALID_GID;
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version,
+						"wwdQdddqssss?sugu",
+						&stbuf->size, &stbuf->type,
+						&stbuf->dev, &stbuf->qid,
+						&stbuf->mode, &stbuf->atime,
+						&stbuf->mtime, &stbuf->length,
+						&stbuf->name, &stbuf->uid,
+						&stbuf->gid, &stbuf->muid,
+						&stbuf->extension,
+						&stbuf->n_uid, &stbuf->n_gid,
+						&stbuf->n_muid);
+				if (errcode)
+					p9stat_free(stbuf);
+			}
+			break;
+		case 'D':{
+				uint32_t *count = va_arg(ap, uint32_t *);
+				void **data = va_arg(ap, void **);
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version, "d", count);
+				if (!errcode) {
+					*count =
+					    min_t(uint32_t, *count,
+						  pdu->size - pdu->offset);
+					*data = &pdu->sdata[pdu->offset];
+				}
+			}
+			break;
+		case 'T':{
+				uint16_t *nwname = va_arg(ap, uint16_t *);
+				char ***wnames = va_arg(ap, char ***);
+
+				errcode = p9pdu_readf(pdu, proto_version,
+								"w", nwname);
+				if (!errcode) {
+					*wnames =
+					    kmalloc(sizeof(char *) * *nwname,
+						    GFP_NOFS);
+					if (!*wnames)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwname; i++) {
+						errcode =
+						    p9pdu_readf(pdu,
+								proto_version,
+								"s",
+								&(*wnames)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					if (*wnames) {
+						int i;
+
+						for (i = 0; i < *nwname; i++)
+							kfree((*wnames)[i]);
+					}
+					kfree(*wnames);
+					*wnames = NULL;
+				}
+			}
+			break;
+		case 'R':{
+				int16_t *nwqid = va_arg(ap, int16_t *);
+				struct p9_qid **wqids =
+				    va_arg(ap, struct p9_qid **);
+
+				*wqids = NULL;
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version, "w", nwqid);
+				if (!errcode) {
+					*wqids =
+					    kmalloc(*nwqid *
+						    sizeof(struct p9_qid),
+						    GFP_NOFS);
+					if (*wqids == NULL)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwqid; i++) {
+						errcode =
+						    p9pdu_readf(pdu,
+								proto_version,
+								"Q",
+								&(*wqids)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					kfree(*wqids);
+					*wqids = NULL;
+				}
+			}
+			break;
+		case 'A': {
+				struct p9_stat_dotl *stbuf =
+				    va_arg(ap, struct p9_stat_dotl *);
+
+				memset(stbuf, 0, sizeof(struct p9_stat_dotl));
+				errcode =
+				    p9pdu_readf(pdu, proto_version,
+					"qQdugqqqqqqqqqqqqqqq",
+					&stbuf->st_result_mask,
+					&stbuf->qid,
+					&stbuf->st_mode,
+					&stbuf->st_uid, &stbuf->st_gid,
+					&stbuf->st_nlink,
+					&stbuf->st_rdev, &stbuf->st_size,
+					&stbuf->st_blksize, &stbuf->st_blocks,
+					&stbuf->st_atime_sec,
+					&stbuf->st_atime_nsec,
+					&stbuf->st_mtime_sec,
+					&stbuf->st_mtime_nsec,
+					&stbuf->st_ctime_sec,
+					&stbuf->st_ctime_nsec,
+					&stbuf->st_btime_sec,
+					&stbuf->st_btime_nsec,
+					&stbuf->st_gen,
+					&stbuf->st_data_version);
+			}
+			break;
+		case '?':
+			if ((proto_version != p9_proto_2000u) &&
+				(proto_version != p9_proto_2000L))
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int
+p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
+	va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t val = va_arg(ap, int);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'w':{
+				__le16 val = cpu_to_le16(va_arg(ap, int));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'd':{
+				__le32 val = cpu_to_le32(va_arg(ap, int32_t));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'q':{
+				__le64 val = cpu_to_le64(va_arg(ap, int64_t));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 's':{
+				const char *sptr = va_arg(ap, const char *);
+				uint16_t len = 0;
+				if (sptr)
+					len = min_t(size_t, strlen(sptr),
+								USHRT_MAX);
+
+				errcode = p9pdu_writef(pdu, proto_version,
+								"w", len);
+				if (!errcode && pdu_write(pdu, sptr, len))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'u': {
+				kuid_t uid = va_arg(ap, kuid_t);
+				__le32 val = cpu_to_le32(
+						from_kuid(&init_user_ns, uid));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			} break;
+		case 'g': {
+				kgid_t gid = va_arg(ap, kgid_t);
+				__le32 val = cpu_to_le32(
+						from_kgid(&init_user_ns, gid));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			} break;
+		case 'Q':{
+				const struct p9_qid *qid =
+				    va_arg(ap, const struct p9_qid *);
+				errcode =
+				    p9pdu_writef(pdu, proto_version, "bdq",
+						 qid->type, qid->version,
+						 qid->path);
+			} break;
+		case 'S':{
+				const struct p9_wstat *stbuf =
+				    va_arg(ap, const struct p9_wstat *);
+				errcode =
+				    p9pdu_writef(pdu, proto_version,
+						 "wwdQdddqssss?sugu",
+						 stbuf->size, stbuf->type,
+						 stbuf->dev, &stbuf->qid,
+						 stbuf->mode, stbuf->atime,
+						 stbuf->mtime, stbuf->length,
+						 stbuf->name, stbuf->uid,
+						 stbuf->gid, stbuf->muid,
+						 stbuf->extension, stbuf->n_uid,
+						 stbuf->n_gid, stbuf->n_muid);
+			} break;
+		case 'D':{
+				uint32_t count = va_arg(ap, uint32_t);
+				const void *data = va_arg(ap, const void *);
+
+				errcode = p9pdu_writef(pdu, proto_version, "d",
+									count);
+				if (!errcode && pdu_write(pdu, data, count))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'U':{
+				int32_t count = va_arg(ap, int32_t);
+				const char __user *udata =
+						va_arg(ap, const void __user *);
+				errcode = p9pdu_writef(pdu, proto_version, "d",
+									count);
+				if (!errcode && pdu_write_u(pdu, udata, count))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'T':{
+				uint16_t nwname = va_arg(ap, int);
+				const char **wnames = va_arg(ap, const char **);
+
+				errcode = p9pdu_writef(pdu, proto_version, "w",
+									nwname);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwname; i++) {
+						errcode =
+						    p9pdu_writef(pdu,
+								proto_version,
+								 "s",
+								 wnames[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'R':{
+				int16_t nwqid = va_arg(ap, int);
+				struct p9_qid *wqids =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_writef(pdu, proto_version, "w",
+									nwqid);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwqid; i++) {
+						errcode =
+						    p9pdu_writef(pdu,
+								proto_version,
+								 "Q",
+								 &wqids[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'I':{
+				struct p9_iattr_dotl *p9attr = va_arg(ap,
+							struct p9_iattr_dotl *);
+
+				errcode = p9pdu_writef(pdu, proto_version,
+							"ddugqqqqq",
+							p9attr->valid,
+							p9attr->mode,
+							p9attr->uid,
+							p9attr->gid,
+							p9attr->size,
+							p9attr->atime_sec,
+							p9attr->atime_nsec,
+							p9attr->mtime_sec,
+							p9attr->mtime_nsec);
+			}
+			break;
+		case '?':
+			if ((proto_version != p9_proto_2000u) &&
+				(proto_version != p9_proto_2000L))
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vreadf(pdu, proto_version, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vwritef(pdu, proto_version, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st)
+{
+	struct p9_fcall fake_pdu;
+	int ret;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "S", st);
+	if (ret) {
+		p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
+		trace_9p_protocol_dump(clnt, &fake_pdu);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(p9stat_read);
+
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type)
+{
+	pdu->id = type;
+	return p9pdu_writef(pdu, 0, "dbw", 0, type, tag);
+}
+
+int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu)
+{
+	int size = pdu->size;
+	int err;
+
+	pdu->size = 0;
+	err = p9pdu_writef(pdu, 0, "d", size);
+	pdu->size = size;
+
+	trace_9p_protocol_dump(clnt, pdu);
+	p9_debug(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n",
+		 pdu->size, pdu->id, pdu->tag);
+
+	return err;
+}
+
+void p9pdu_reset(struct p9_fcall *pdu)
+{
+	pdu->offset = 0;
+	pdu->size = 0;
+}
+
+int p9dirent_read(struct p9_client *clnt, char *buf, int len,
+		  struct p9_dirent *dirent)
+{
+	struct p9_fcall fake_pdu;
+	int ret;
+	char *nameptr;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "Qqbs", &dirent->qid,
+			  &dirent->d_off, &dirent->d_type, &nameptr);
+	if (ret) {
+		p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret);
+		trace_9p_protocol_dump(clnt, &fake_pdu);
+		goto out;
+	}
+
+	strcpy(dirent->d_name, nameptr);
+	kfree(nameptr);
+
+out:
+	return fake_pdu.offset;
+}
+EXPORT_SYMBOL(p9dirent_read);

addons/9p/src/3.10.108/protocol.h

@@ -0,0 +1,34 @@
+/*
+ * net/9p/protocol.h
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+int p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
+								va_list ap);
+int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type);
+int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu);
+void p9pdu_reset(struct p9_fcall *pdu);
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size);

addons/9p/src/3.10.108/trans_common.c

@@ -0,0 +1,69 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <linux/scatterlist.h>
+#include "trans_common.h"
+
+/**
+ *  p9_release_req_pages - Release pages after the transaction.
+ */
+void p9_release_pages(struct page **pages, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++)
+		if (pages[i])
+			put_page(pages[i]);
+}
+EXPORT_SYMBOL(p9_release_pages);
+
+/**
+ * p9_nr_pages - Return number of pages needed to accommodate the payload.
+ */
+int p9_nr_pages(char *data, int len)
+{
+	unsigned long start_page, end_page;
+	start_page =  (unsigned long)data >> PAGE_SHIFT;
+	end_page = ((unsigned long)data + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	return end_page - start_page;
+}
+EXPORT_SYMBOL(p9_nr_pages);
+
+/**
+ * payload_gup - Translates user buffer into kernel pages and
+ * pins them either for read/write through get_user_pages_fast().
+ * @req: Request to be sent to server.
+ * @pdata_off: data offset into the first page after translation (gup).
+ * @pdata_len: Total length of the IO. gup may not return requested # of pages.
+ * @nr_pages: number of pages to accommodate the payload
+ * @rw: Indicates if the pages are for read or write.
+ */
+
+int p9_payload_gup(char *data, int *nr_pages, struct page **pages, int write)
+{
+	int nr_mapped_pages;
+
+	nr_mapped_pages = get_user_pages_fast((unsigned long)data,
+					      *nr_pages, write, pages);
+	if (nr_mapped_pages <= 0)
+		return nr_mapped_pages;
+
+	*nr_pages = nr_mapped_pages;
+	return 0;
+}
+EXPORT_SYMBOL(p9_payload_gup);

addons/9p/src/3.10.108/trans_common.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+void p9_release_pages(struct page **, int);
+int p9_payload_gup(char *, int *, struct page **, int);
+int p9_nr_pages(char *, int);

addons/9p/src/3.10.108/trans_rdma.c

@@ -0,0 +1,719 @@
+/*
+ * linux/fs/9p/trans_rdma.c
+ *
+ * RDMA transport layer based on the trans_fd.c implementation.
+ *
+ *  Copyright (C) 2008 by Tom Tucker <tom@opengridcomputing.com>
+ *  Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
+ *  Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/parser.h>
+#include <linux/semaphore.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+
+#define P9_PORT			5640
+#define P9_RDMA_SQ_DEPTH	32
+#define P9_RDMA_RQ_DEPTH	32
+#define P9_RDMA_SEND_SGE	4
+#define P9_RDMA_RECV_SGE	4
+#define P9_RDMA_IRD		0
+#define P9_RDMA_ORD		0
+#define P9_RDMA_TIMEOUT		30000		/* 30 seconds */
+#define P9_RDMA_MAXSIZE		(4*4096)	/* Min SGE is 4, so we can
+						 * safely advertise a maxsize
+						 * of 64k */
+
+/**
+ * struct p9_trans_rdma - RDMA transport instance
+ *
+ * @state: tracks the transport state machine for connection setup and tear down
+ * @cm_id: The RDMA CM ID
+ * @pd: Protection Domain pointer
+ * @qp: Queue Pair pointer
+ * @cq: Completion Queue pointer
+ * @dm_mr: DMA Memory Region pointer
+ * @lkey: The local access only memory region key
+ * @timeout: Number of uSecs to wait for connection management events
+ * @sq_depth: The depth of the Send Queue
+ * @sq_sem: Semaphore for the SQ
+ * @rq_depth: The depth of the Receive Queue.
+ * @rq_count: Count of requests in the Receive Queue.
+ * @addr: The remote peer's address
+ * @req_lock: Protects the active request list
+ * @cm_done: Completion event for connection management tracking
+ */
+struct p9_trans_rdma {
+	enum {
+		P9_RDMA_INIT,
+		P9_RDMA_ADDR_RESOLVED,
+		P9_RDMA_ROUTE_RESOLVED,
+		P9_RDMA_CONNECTED,
+		P9_RDMA_FLUSHING,
+		P9_RDMA_CLOSING,
+		P9_RDMA_CLOSED,
+	} state;
+	struct rdma_cm_id *cm_id;
+	struct ib_pd *pd;
+	struct ib_qp *qp;
+	struct ib_cq *cq;
+	struct ib_mr *dma_mr;
+	u32 lkey;
+	long timeout;
+	int sq_depth;
+	struct semaphore sq_sem;
+	int rq_depth;
+	atomic_t rq_count;
+	struct sockaddr_in addr;
+	spinlock_t req_lock;
+
+	struct completion cm_done;
+};
+
+/**
+ * p9_rdma_context - Keeps track of in-process WR
+ *
+ * @wc_op: The original WR op for when the CQE completes in error.
+ * @busa: Bus address to unmap when the WR completes
+ * @req: Keeps track of requests (send)
+ * @rc: Keepts track of replies (receive)
+ */
+struct p9_rdma_req;
+struct p9_rdma_context {
+	enum ib_wc_opcode wc_op;
+	dma_addr_t busa;
+	union {
+		struct p9_req_t *req;
+		struct p9_fcall *rc;
+	};
+};
+
+/**
+ * p9_rdma_opts - Collection of mount options
+ * @port: port of connection
+ * @sq_depth: The requested depth of the SQ. This really doesn't need
+ * to be any deeper than the number of threads used in the client
+ * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
+ * @timeout: Time to wait in msecs for CM events
+ */
+struct p9_rdma_opts {
+	short port;
+	int sq_depth;
+	int rq_depth;
+	long timeout;
+};
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ */
+enum {
+	/* Options that take integer arguments */
+	Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, Opt_err,
+};
+
+static match_table_t tokens = {
+	{Opt_port, "port=%u"},
+	{Opt_sq_depth, "sq=%u"},
+	{Opt_rq_depth, "rq=%u"},
+	{Opt_timeout, "timeout=%u"},
+	{Opt_err, NULL},
+};
+
+/**
+ * parse_opts - parse mount options into rdma options structure
+ * @params: options string passed from mount
+ * @opts: rdma transport-specific structure to parse options into
+ *
+ * Returns 0 upon success, -ERRNO upon failure
+ */
+static int parse_opts(char *params, struct p9_rdma_opts *opts)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	char *options, *tmp_options;
+
+	opts->port = P9_PORT;
+	opts->sq_depth = P9_RDMA_SQ_DEPTH;
+	opts->rq_depth = P9_RDMA_RQ_DEPTH;
+	opts->timeout = P9_RDMA_TIMEOUT;
+
+	if (!params)
+		return 0;
+
+	tmp_options = kstrdup(params, GFP_KERNEL);
+	if (!tmp_options) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "failed to allocate copy of option string\n");
+		return -ENOMEM;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		int r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		r = match_int(&args[0], &option);
+		if (r < 0) {
+			p9_debug(P9_DEBUG_ERROR,
+				 "integer field, but no integer?\n");
+			continue;
+		}
+		switch (token) {
+		case Opt_port:
+			opts->port = option;
+			break;
+		case Opt_sq_depth:
+			opts->sq_depth = option;
+			break;
+		case Opt_rq_depth:
+			opts->rq_depth = option;
+			break;
+		case Opt_timeout:
+			opts->timeout = option;
+			break;
+		default:
+			continue;
+		}
+	}
+	/* RQ must be at least as large as the SQ */
+	opts->rq_depth = max(opts->rq_depth, opts->sq_depth);
+	kfree(tmp_options);
+	return 0;
+}
+
+static int
+p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
+{
+	struct p9_client *c = id->context;
+	struct p9_trans_rdma *rdma = c->trans;
+	switch (event->event) {
+	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_INIT);
+		rdma->state = P9_RDMA_ADDR_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_ADDR_RESOLVED);
+		rdma->state = P9_RDMA_ROUTE_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ESTABLISHED:
+		BUG_ON(rdma->state != P9_RDMA_ROUTE_RESOLVED);
+		rdma->state = P9_RDMA_CONNECTED;
+		break;
+
+	case RDMA_CM_EVENT_DISCONNECTED:
+		if (rdma)
+			rdma->state = P9_RDMA_CLOSED;
+		if (c)
+			c->status = Disconnected;
+		break;
+
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		break;
+
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ROUTE_ERROR:
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+	case RDMA_CM_EVENT_MULTICAST_JOIN:
+	case RDMA_CM_EVENT_MULTICAST_ERROR:
+	case RDMA_CM_EVENT_REJECTED:
+	case RDMA_CM_EVENT_CONNECT_REQUEST:
+	case RDMA_CM_EVENT_CONNECT_RESPONSE:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+	case RDMA_CM_EVENT_ADDR_ERROR:
+	case RDMA_CM_EVENT_UNREACHABLE:
+		c->status = Disconnected;
+		rdma_disconnect(rdma->cm_id);
+		break;
+	default:
+		BUG();
+	}
+	complete(&rdma->cm_done);
+	return 0;
+}
+
+static void
+handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	struct p9_req_t *req;
+	int err = 0;
+	int16_t tag;
+
+	req = NULL;
+	ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize,
+							 DMA_FROM_DEVICE);
+
+	if (status != IB_WC_SUCCESS)
+		goto err_out;
+
+	err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+	if (err)
+		goto err_out;
+
+	req = p9_tag_lookup(client, tag);
+	if (!req)
+		goto err_out;
+
+	req->rc = c->rc;
+	req->status = REQ_STATUS_RCVD;
+	p9_client_cb(client, req);
+
+	return;
+
+ err_out:
+	p9_debug(P9_DEBUG_ERROR, "req %p err %d status %d\n", req, err, status);
+	rdma->state = P9_RDMA_FLUSHING;
+	client->status = Disconnected;
+}
+
+static void
+handle_send(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	ib_dma_unmap_single(rdma->cm_id->device,
+			    c->busa, c->req->tc->size,
+			    DMA_TO_DEVICE);
+}
+
+static void qp_event_handler(struct ib_event *event, void *context)
+{
+	p9_debug(P9_DEBUG_ERROR, "QP event %d context %p\n",
+		 event->event, context);
+}
+
+static void cq_comp_handler(struct ib_cq *cq, void *cq_context)
+{
+	struct p9_client *client = cq_context;
+	struct p9_trans_rdma *rdma = client->trans;
+	int ret;
+	struct ib_wc wc;
+
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+	while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
+		struct p9_rdma_context *c = (void *) (unsigned long) wc.wr_id;
+
+		switch (c->wc_op) {
+		case IB_WC_RECV:
+			atomic_dec(&rdma->rq_count);
+			handle_recv(client, rdma, c, wc.status, wc.byte_len);
+			break;
+
+		case IB_WC_SEND:
+			handle_send(client, rdma, c, wc.status, wc.byte_len);
+			up(&rdma->sq_sem);
+			break;
+
+		default:
+			pr_err("unexpected completion type, c->wc_op=%d, wc.opcode=%d, status=%d\n",
+			       c->wc_op, wc.opcode, wc.status);
+			break;
+		}
+		kfree(c);
+	}
+}
+
+static void cq_event_handler(struct ib_event *e, void *v)
+{
+	p9_debug(P9_DEBUG_ERROR, "CQ event %d context %p\n", e->event, v);
+}
+
+static void rdma_destroy_trans(struct p9_trans_rdma *rdma)
+{
+	if (!rdma)
+		return;
+
+	if (rdma->dma_mr && !IS_ERR(rdma->dma_mr))
+		ib_dereg_mr(rdma->dma_mr);
+
+	if (rdma->qp && !IS_ERR(rdma->qp))
+		ib_destroy_qp(rdma->qp);
+
+	if (rdma->pd && !IS_ERR(rdma->pd))
+		ib_dealloc_pd(rdma->pd);
+
+	if (rdma->cq && !IS_ERR(rdma->cq))
+		ib_destroy_cq(rdma->cq);
+
+	if (rdma->cm_id && !IS_ERR(rdma->cm_id))
+		rdma_destroy_id(rdma->cm_id);
+
+	kfree(rdma);
+}
+
+static int
+post_recv(struct p9_client *client, struct p9_rdma_context *c)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_recv_wr wr, *bad_wr;
+	struct ib_sge sge;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->rc->sdata, client->msize,
+				    DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
+		goto error;
+
+	sge.addr = c->busa;
+	sge.length = client->msize;
+	sge.lkey = rdma->lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_RECV;
+	wr.wr_id = (unsigned long) c;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+	return ib_post_recv(rdma->qp, &wr, &bad_wr);
+
+ error:
+	p9_debug(P9_DEBUG_ERROR, "EIO\n");
+	return -EIO;
+}
+
+static int rdma_request(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_send_wr wr, *bad_wr;
+	struct ib_sge sge;
+	int err = 0;
+	unsigned long flags;
+	struct p9_rdma_context *c = NULL;
+	struct p9_rdma_context *rpl_context = NULL;
+
+	/* Allocate an fcall for the reply */
+	rpl_context = kmalloc(sizeof *rpl_context, GFP_NOFS);
+	if (!rpl_context) {
+		err = -ENOMEM;
+		goto err_close;
+	}
+
+	/*
+	 * If the request has a buffer, steal it, otherwise
+	 * allocate a new one.  Typically, requests should already
+	 * have receive buffers allocated and just swap them around
+	 */
+	if (!req->rc) {
+		req->rc = kmalloc(sizeof(struct p9_fcall)+client->msize,
+				  GFP_NOFS);
+		if (req->rc) {
+			req->rc->sdata = (char *) req->rc +
+						sizeof(struct p9_fcall);
+			req->rc->capacity = client->msize;
+		}
+	}
+	rpl_context->rc = req->rc;
+	if (!rpl_context->rc) {
+		err = -ENOMEM;
+		goto err_free2;
+	}
+
+	/*
+	 * Post a receive buffer for this request. We need to ensure
+	 * there is a reply buffer available for every outstanding
+	 * request. A flushed request can result in no reply for an
+	 * outstanding request, so we must keep a count to avoid
+	 * overflowing the RQ.
+	 */
+	if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) {
+		err = post_recv(client, rpl_context);
+		if (err)
+			goto err_free1;
+	} else
+		atomic_dec(&rdma->rq_count);
+
+	/* remove posted receive buffer from request structure */
+	req->rc = NULL;
+
+	/* Post the request */
+	c = kmalloc(sizeof *c, GFP_NOFS);
+	if (!c) {
+		err = -ENOMEM;
+		goto err_free1;
+	}
+	c->req = req;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->req->tc->sdata, c->req->tc->size,
+				    DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
+		goto error;
+
+	sge.addr = c->busa;
+	sge.length = c->req->tc->size;
+	sge.lkey = rdma->lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_SEND;
+	wr.wr_id = (unsigned long) c;
+	wr.opcode = IB_WR_SEND;
+	wr.send_flags = IB_SEND_SIGNALED;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+
+	if (down_interruptible(&rdma->sq_sem))
+		goto error;
+
+	return ib_post_send(rdma->qp, &wr, &bad_wr);
+
+ error:
+	kfree(c);
+	kfree(rpl_context->rc);
+	kfree(rpl_context);
+	p9_debug(P9_DEBUG_ERROR, "EIO\n");
+	return -EIO;
+ err_free1:
+	kfree(rpl_context->rc);
+ err_free2:
+	kfree(rpl_context);
+ err_close:
+	spin_lock_irqsave(&rdma->req_lock, flags);
+	if (rdma->state < P9_RDMA_CLOSING) {
+		rdma->state = P9_RDMA_CLOSING;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+		rdma_disconnect(rdma->cm_id);
+	} else
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+	return err;
+}
+
+static void rdma_close(struct p9_client *client)
+{
+	struct p9_trans_rdma *rdma;
+
+	if (!client)
+		return;
+
+	rdma = client->trans;
+	if (!rdma)
+		return;
+
+	client->status = Disconnected;
+	rdma_disconnect(rdma->cm_id);
+	rdma_destroy_trans(rdma);
+}
+
+/**
+ * alloc_rdma - Allocate and initialize the rdma transport structure
+ * @opts: Mount options structure
+ */
+static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts)
+{
+	struct p9_trans_rdma *rdma;
+
+	rdma = kzalloc(sizeof(struct p9_trans_rdma), GFP_KERNEL);
+	if (!rdma)
+		return NULL;
+
+	rdma->sq_depth = opts->sq_depth;
+	rdma->rq_depth = opts->rq_depth;
+	rdma->timeout = opts->timeout;
+	spin_lock_init(&rdma->req_lock);
+	init_completion(&rdma->cm_done);
+	sema_init(&rdma->sq_sem, rdma->sq_depth);
+	atomic_set(&rdma->rq_count, 0);
+
+	return rdma;
+}
+
+/* its not clear to me we can do anything after send has been posted */
+static int rdma_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
+/**
+ * trans_create_rdma - Transport method for creating atransport instance
+ * @client: client instance
+ * @addr: IP address string
+ * @args: Mount options string
+ */
+static int
+rdma_create_trans(struct p9_client *client, const char *addr, char *args)
+{
+	int err;
+	struct p9_rdma_opts opts;
+	struct p9_trans_rdma *rdma;
+	struct rdma_conn_param conn_param;
+	struct ib_qp_init_attr qp_attr;
+	struct ib_device_attr devattr;
+
+	/* Parse the transport specific mount options */
+	err = parse_opts(args, &opts);
+	if (err < 0)
+		return err;
+
+	/* Create and initialize the RDMA transport structure */
+	rdma = alloc_rdma(&opts);
+	if (!rdma)
+		return -ENOMEM;
+
+	/* Create the RDMA CM ID */
+	rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP,
+				     IB_QPT_RC);
+	if (IS_ERR(rdma->cm_id))
+		goto error;
+
+	/* Associate the client with the transport */
+	client->trans = rdma;
+
+	/* Resolve the server's address */
+	rdma->addr.sin_family = AF_INET;
+	rdma->addr.sin_addr.s_addr = in_aton(addr);
+	rdma->addr.sin_port = htons(opts.port);
+	err = rdma_resolve_addr(rdma->cm_id, NULL,
+				(struct sockaddr *)&rdma->addr,
+				rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ADDR_RESOLVED))
+		goto error;
+
+	/* Resolve the route to the server */
+	err = rdma_resolve_route(rdma->cm_id, rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED))
+		goto error;
+
+	/* Query the device attributes */
+	err = ib_query_device(rdma->cm_id->device, &devattr);
+	if (err)
+		goto error;
+
+	/* Create the Completion Queue */
+	rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler,
+				cq_event_handler, client,
+				opts.sq_depth + opts.rq_depth + 1, 0);
+	if (IS_ERR(rdma->cq))
+		goto error;
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+
+	/* Create the Protection Domain */
+	rdma->pd = ib_alloc_pd(rdma->cm_id->device);
+	if (IS_ERR(rdma->pd))
+		goto error;
+
+	/* Cache the DMA lkey in the transport */
+	rdma->dma_mr = NULL;
+	if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
+		rdma->lkey = rdma->cm_id->device->local_dma_lkey;
+	else {
+		rdma->dma_mr = ib_get_dma_mr(rdma->pd, IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(rdma->dma_mr))
+			goto error;
+		rdma->lkey = rdma->dma_mr->lkey;
+	}
+
+	/* Create the Queue Pair */
+	memset(&qp_attr, 0, sizeof qp_attr);
+	qp_attr.event_handler = qp_event_handler;
+	qp_attr.qp_context = client;
+	qp_attr.cap.max_send_wr = opts.sq_depth;
+	qp_attr.cap.max_recv_wr = opts.rq_depth;
+	qp_attr.cap.max_send_sge = P9_RDMA_SEND_SGE;
+	qp_attr.cap.max_recv_sge = P9_RDMA_RECV_SGE;
+	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	qp_attr.qp_type = IB_QPT_RC;
+	qp_attr.send_cq = rdma->cq;
+	qp_attr.recv_cq = rdma->cq;
+	err = rdma_create_qp(rdma->cm_id, rdma->pd, &qp_attr);
+	if (err)
+		goto error;
+	rdma->qp = rdma->cm_id->qp;
+
+	/* Request a connection */
+	memset(&conn_param, 0, sizeof(conn_param));
+	conn_param.private_data = NULL;
+	conn_param.private_data_len = 0;
+	conn_param.responder_resources = P9_RDMA_IRD;
+	conn_param.initiator_depth = P9_RDMA_ORD;
+	err = rdma_connect(rdma->cm_id, &conn_param);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_CONNECTED))
+		goto error;
+
+	client->status = Connected;
+
+	return 0;
+
+error:
+	rdma_destroy_trans(rdma);
+	return -ENOTCONN;
+}
+
+static struct p9_trans_module p9_rdma_trans = {
+	.name = "rdma",
+	.maxsize = P9_RDMA_MAXSIZE,
+	.def = 0,
+	.owner = THIS_MODULE,
+	.create = rdma_create_trans,
+	.close = rdma_close,
+	.request = rdma_request,
+	.cancel = rdma_cancel,
+};
+
+/**
+ * p9_trans_rdma_init - Register the 9P RDMA transport driver
+ */
+static int __init p9_trans_rdma_init(void)
+{
+	v9fs_register_trans(&p9_rdma_trans);
+	return 0;
+}
+
+static void __exit p9_trans_rdma_exit(void)
+{
+	v9fs_unregister_trans(&p9_rdma_trans);
+}
+
+module_init(p9_trans_rdma_init);
+module_exit(p9_trans_rdma_exit);
+
+MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>");
+MODULE_DESCRIPTION("RDMA Transport for 9P");
+MODULE_LICENSE("Dual BSD/GPL");

addons/9p/src/3.10.108/trans_virtio.c

@@ -0,0 +1,730 @@
+/*
+ * The Virtio 9p transport driver
+ *
+ * This is a block based transport driver based on the lguest block driver
+ * code.
+ *
+ *  Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation
+ *
+ *  Based on virtio console driver
+ *  Copyright (C) 2006, 2007 Rusty Russell, IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <linux/scatterlist.h>
+#include <linux/swap.h>
+#include <linux/virtio.h>
+#include <linux/virtio_9p.h>
+#include "trans_common.h"
+
+#define VIRTQUEUE_NUM	128
+
+/* a single mutex to manage channel initialization and attachment */
+static DEFINE_MUTEX(virtio_9p_lock);
+static DECLARE_WAIT_QUEUE_HEAD(vp_wq);
+static atomic_t vp_pinned = ATOMIC_INIT(0);
+
+/**
+ * struct virtio_chan - per-instance transport information
+ * @initialized: whether the channel is initialized
+ * @inuse: whether the channel is in use
+ * @lock: protects multiple elements within this structure
+ * @client: client instance
+ * @vdev: virtio dev associated with this channel
+ * @vq: virtio queue associated with this channel
+ * @sg: scatter gather list which is used to pack a request (protected?)
+ *
+ * We keep all per-channel information in a structure.
+ * This structure is allocated within the devices dev->mem space.
+ * A pointer to the structure will get put in the transport private.
+ *
+ */
+
+struct virtio_chan {
+	bool inuse;
+
+	spinlock_t lock;
+
+	struct p9_client *client;
+	struct virtio_device *vdev;
+	struct virtqueue *vq;
+	int ring_bufs_avail;
+	wait_queue_head_t *vc_wq;
+	/* This is global limit. Since we don't have a global structure,
+	 * will be placing it in each channel.
+	 */
+	unsigned long p9_max_pages;
+	/* Scatterlist: can be too big for stack. */
+	struct scatterlist sg[VIRTQUEUE_NUM];
+
+	int tag_len;
+	/*
+	 * tag name to identify a mount Non-null terminated
+	 */
+	char *tag;
+
+	struct list_head chan_list;
+};
+
+static struct list_head virtio_chan_list;
+
+/* How many bytes left in this page. */
+static unsigned int rest_of_page(void *data)
+{
+	return PAGE_SIZE - ((unsigned long)data % PAGE_SIZE);
+}
+
+/**
+ * p9_virtio_close - reclaim resources of a channel
+ * @client: client instance
+ *
+ * This reclaims a channel by freeing its resources and
+ * reseting its inuse flag.
+ *
+ */
+
+static void p9_virtio_close(struct p9_client *client)
+{
+	struct virtio_chan *chan = client->trans;
+
+	mutex_lock(&virtio_9p_lock);
+	if (chan)
+		chan->inuse = false;
+	mutex_unlock(&virtio_9p_lock);
+}
+
+/**
+ * req_done - callback which signals activity from the server
+ * @vq: virtio queue activity was received on
+ *
+ * This notifies us that the server has triggered some activity
+ * on the virtio channel - most likely a response to request we
+ * sent.  Figure out which requests now have responses and wake up
+ * those threads.
+ *
+ * Bugs: could do with some additional sanity checking, but appears to work.
+ *
+ */
+
+static void req_done(struct virtqueue *vq)
+{
+	struct virtio_chan *chan = vq->vdev->priv;
+	struct p9_fcall *rc;
+	unsigned int len;
+	struct p9_req_t *req;
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_TRANS, ": request done\n");
+
+	while (1) {
+		spin_lock_irqsave(&chan->lock, flags);
+		rc = virtqueue_get_buf(chan->vq, &len);
+		if (rc == NULL) {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			break;
+		}
+		chan->ring_bufs_avail = 1;
+		spin_unlock_irqrestore(&chan->lock, flags);
+		/* Wakeup if anyone waiting for VirtIO ring space. */
+		wake_up(chan->vc_wq);
+		p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc);
+		p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
+		req = p9_tag_lookup(chan->client, rc->tag);
+		req->status = REQ_STATUS_RCVD;
+		p9_client_cb(chan->client, req);
+	}
+}
+
+/**
+ * pack_sg_list - pack a scatter gather list from a linear buffer
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @limit: maximum segment to pack data to
+ * @data: data to pack into scatter/gather list
+ * @count: amount of data to pack into the scatter/gather list
+ *
+ * sg_lists have multiple segments of various sizes.  This will pack
+ * arbitrary data into an existing scatter gather list, segmenting the
+ * data as necessary within constraints.
+ *
+ */
+
+static int pack_sg_list(struct scatterlist *sg, int start,
+			int limit, char *data, int count)
+{
+	int s;
+	int index = start;
+
+	while (count) {
+		s = rest_of_page(data);
+		if (s > count)
+			s = count;
+		BUG_ON(index > limit);
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
+		sg_set_buf(&sg[index++], data, s);
+		count -= s;
+		data += s;
+	}
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
+	return index-start;
+}
+
+/* We don't currently allow canceling of virtio requests */
+static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
+/**
+ * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
+ * this takes a list of pages.
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @pdata: a list of pages to add into sg.
+ * @nr_pages: number of pages to pack into the scatter/gather list
+ * @data: data to pack into scatter/gather list
+ * @count: amount of data to pack into the scatter/gather list
+ */
+static int
+pack_sg_list_p(struct scatterlist *sg, int start, int limit,
+	       struct page **pdata, int nr_pages, char *data, int count)
+{
+	int i = 0, s;
+	int data_off;
+	int index = start;
+
+	BUG_ON(nr_pages > (limit - start));
+	/*
+	 * if the first page doesn't start at
+	 * page boundary find the offset
+	 */
+	data_off = offset_in_page(data);
+	while (nr_pages) {
+		s = rest_of_page(data);
+		if (s > count)
+			s = count;
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
+		sg_set_page(&sg[index++], pdata[i++], s, data_off);
+		data_off = 0;
+		data += s;
+		count -= s;
+		nr_pages--;
+	}
+
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
+	return index - start;
+}
+
+/**
+ * p9_virtio_request - issue a request
+ * @client: client instance issuing the request
+ * @req: request to be issued
+ *
+ */
+
+static int
+p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
+{
+	int err;
+	int in, out, out_sgs, in_sgs;
+	unsigned long flags;
+	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[2];
+
+	p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n");
+
+	req->status = REQ_STATUS_SENT;
+req_retry:
+	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+	/* Handle out VirtIO ring buffers */
+	out = pack_sg_list(chan->sg, 0,
+			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	in = pack_sg_list(chan->sg, out,
+			  VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+				GFP_ATOMIC);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			chan->ring_bufs_avail = 0;
+			spin_unlock_irqrestore(&chan->lock, flags);
+			err = wait_event_interruptible(*chan->vc_wq,
+							chan->ring_bufs_avail);
+			if (err  == -ERESTARTSYS)
+				return err;
+
+			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
+			goto req_retry;
+		} else {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			p9_debug(P9_DEBUG_TRANS,
+				 "virtio rpc add_sgs returned failure\n");
+			return -EIO;
+		}
+	}
+	virtqueue_kick(chan->vq);
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
+	return 0;
+}
+
+static int p9_get_mapped_pages(struct virtio_chan *chan,
+			       struct page **pages, char *data,
+			       int nr_pages, int write, int kern_buf)
+{
+	int err;
+	if (!kern_buf) {
+		/*
+		 * We allow only p9_max_pages pinned. We wait for the
+		 * Other zc request to finish here
+		 */
+		if (atomic_read(&vp_pinned) >= chan->p9_max_pages) {
+			err = wait_event_interruptible(vp_wq,
+			      (atomic_read(&vp_pinned) < chan->p9_max_pages));
+			if (err == -ERESTARTSYS)
+				return err;
+		}
+		err = p9_payload_gup(data, &nr_pages, pages, write);
+		if (err < 0)
+			return err;
+		atomic_add(nr_pages, &vp_pinned);
+	} else {
+		/* kernel buffer, no need to pin pages */
+		int s, index = 0;
+		int count = nr_pages;
+		while (nr_pages) {
+			s = rest_of_page(data);
+			if (is_vmalloc_addr(data))
+				pages[index++] = vmalloc_to_page(data);
+			else
+				pages[index++] = kmap_to_page(data);
+			data += s;
+			nr_pages--;
+		}
+		nr_pages = count;
+	}
+	return nr_pages;
+}
+
+/**
+ * p9_virtio_zc_request - issue a zero copy request
+ * @client: client instance issuing the request
+ * @req: request to be issued
+ * @uidata: user bffer that should be ued for zero copy read
+ * @uodata: user buffer that shoud be user for zero copy write
+ * @inlen: read buffer size
+ * @olen: write buffer size
+ * @hdrlen: reader header size, This is the size of response protocol data
+ *
+ */
+static int
+p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
+		     char *uidata, char *uodata, int inlen,
+		     int outlen, int in_hdr_len, int kern_buf)
+{
+	int in, out, err, out_sgs, in_sgs;
+	unsigned long flags;
+	int in_nr_pages = 0, out_nr_pages = 0;
+	struct page **in_pages = NULL, **out_pages = NULL;
+	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[4];
+
+	p9_debug(P9_DEBUG_TRANS, "virtio request\n");
+
+	if (uodata) {
+		out_nr_pages = p9_nr_pages(uodata, outlen);
+		out_pages = kmalloc(sizeof(struct page *) * out_nr_pages,
+				    GFP_NOFS);
+		if (!out_pages) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+		out_nr_pages = p9_get_mapped_pages(chan, out_pages, uodata,
+						   out_nr_pages, 0, kern_buf);
+		if (out_nr_pages < 0) {
+			err = out_nr_pages;
+			kfree(out_pages);
+			out_pages = NULL;
+			goto err_out;
+		}
+	}
+	if (uidata) {
+		in_nr_pages = p9_nr_pages(uidata, inlen);
+		in_pages = kmalloc(sizeof(struct page *) * in_nr_pages,
+				   GFP_NOFS);
+		if (!in_pages) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+		in_nr_pages = p9_get_mapped_pages(chan, in_pages, uidata,
+						  in_nr_pages, 1, kern_buf);
+		if (in_nr_pages < 0) {
+			err = in_nr_pages;
+			kfree(in_pages);
+			in_pages = NULL;
+			goto err_out;
+		}
+	}
+	req->status = REQ_STATUS_SENT;
+req_retry_pinned:
+	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+
+	/* out data */
+	out = pack_sg_list(chan->sg, 0,
+			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	if (out_pages) {
+		sgs[out_sgs++] = chan->sg + out;
+		out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
+				      out_pages, out_nr_pages, uodata, outlen);
+	}
+		
+	/*
+	 * Take care of in data
+	 * For example TREAD have 11.
+	 * 11 is the read/write header = PDU Header(7) + IO Size (4).
+	 * Arrange in such a way that server places header in the
+	 * alloced memory and payload onto the user buffer.
+	 */
+	in = pack_sg_list(chan->sg, out,
+			  VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	if (in_pages) {
+		sgs[out_sgs + in_sgs++] = chan->sg + out + in;
+		in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM,
+				     in_pages, in_nr_pages, uidata, inlen);
+	}
+
+	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+				GFP_ATOMIC);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			chan->ring_bufs_avail = 0;
+			spin_unlock_irqrestore(&chan->lock, flags);
+			err = wait_event_interruptible(*chan->vc_wq,
+						       chan->ring_bufs_avail);
+			if (err  == -ERESTARTSYS)
+				goto err_out;
+
+			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
+			goto req_retry_pinned;
+		} else {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			p9_debug(P9_DEBUG_TRANS,
+				 "virtio rpc add_sgs returned failure\n");
+			err = -EIO;
+			goto err_out;
+		}
+	}
+	virtqueue_kick(chan->vq);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
+	err = wait_event_interruptible(*req->wq,
+				       req->status >= REQ_STATUS_RCVD);
+	/*
+	 * Non kernel buffers are pinned, unpin them
+	 */
+err_out:
+	if (!kern_buf) {
+		if (in_pages) {
+			p9_release_pages(in_pages, in_nr_pages);
+			atomic_sub(in_nr_pages, &vp_pinned);
+		}
+		if (out_pages) {
+			p9_release_pages(out_pages, out_nr_pages);
+			atomic_sub(out_nr_pages, &vp_pinned);
+		}
+		/* wakeup anybody waiting for slots to pin pages */
+		wake_up(&vp_wq);
+	}
+	kfree(in_pages);
+	kfree(out_pages);
+	return err;
+}
+
+static ssize_t p9_mount_tag_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct virtio_chan *chan;
+	struct virtio_device *vdev;
+
+	vdev = dev_to_virtio(dev);
+	chan = vdev->priv;
+
+	return snprintf(buf, chan->tag_len + 1, "%s", chan->tag);
+}
+
+static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL);
+
+/**
+ * p9_virtio_probe - probe for existence of 9P virtio channels
+ * @vdev: virtio device to probe
+ *
+ * This probes for existing virtio channels.
+ *
+ */
+
+static int p9_virtio_probe(struct virtio_device *vdev)
+{
+	__u16 tag_len;
+	char *tag;
+	int err;
+	struct virtio_chan *chan;
+
+	chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL);
+	if (!chan) {
+		pr_err("Failed to allocate virtio 9P channel\n");
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	chan->vdev = vdev;
+
+	/* We expect one virtqueue, for requests. */
+	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
+	if (IS_ERR(chan->vq)) {
+		err = PTR_ERR(chan->vq);
+		goto out_free_vq;
+	}
+	chan->vq->vdev->priv = chan;
+	spin_lock_init(&chan->lock);
+
+	sg_init_table(chan->sg, VIRTQUEUE_NUM);
+
+	chan->inuse = false;
+	if (virtio_has_feature(vdev, VIRTIO_9P_MOUNT_TAG)) {
+		vdev->config->get(vdev,
+				offsetof(struct virtio_9p_config, tag_len),
+				&tag_len, sizeof(tag_len));
+	} else {
+		err = -EINVAL;
+		goto out_free_vq;
+	}
+	tag = kmalloc(tag_len, GFP_KERNEL);
+	if (!tag) {
+		err = -ENOMEM;
+		goto out_free_vq;
+	}
+	vdev->config->get(vdev, offsetof(struct virtio_9p_config, tag),
+			tag, tag_len);
+	chan->tag = tag;
+	chan->tag_len = tag_len;
+	err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	if (err) {
+		goto out_free_tag;
+	}
+	chan->vc_wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
+	if (!chan->vc_wq) {
+		err = -ENOMEM;
+		goto out_free_tag;
+	}
+	init_waitqueue_head(chan->vc_wq);
+	chan->ring_bufs_avail = 1;
+	/* Ceiling limit to avoid denial of service attacks */
+	chan->p9_max_pages = nr_free_buffer_pages()/4;
+
+	mutex_lock(&virtio_9p_lock);
+	list_add_tail(&chan->chan_list, &virtio_chan_list);
+	mutex_unlock(&virtio_9p_lock);
+
+	/* Let udev rules use the new mount_tag attribute. */
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
+	return 0;
+
+out_free_tag:
+	kfree(tag);
+out_free_vq:
+	vdev->config->del_vqs(vdev);
+	kfree(chan);
+fail:
+	return err;
+}
+
+
+/**
+ * p9_virtio_create - allocate a new virtio channel
+ * @client: client instance invoking this transport
+ * @devname: string identifying the channel to connect to (unused)
+ * @args: args passed from sys_mount() for per-transport options (unused)
+ *
+ * This sets up a transport channel for 9p communication.  Right now
+ * we only match the first available channel, but eventually we couldlook up
+ * alternate channels by matching devname versus a virtio_config entry.
+ * We use a simple reference count mechanism to ensure that only a single
+ * mount has a channel open at a time.
+ *
+ */
+
+static int
+p9_virtio_create(struct p9_client *client, const char *devname, char *args)
+{
+	struct virtio_chan *chan;
+	int ret = -ENOENT;
+	int found = 0;
+
+	mutex_lock(&virtio_9p_lock);
+	list_for_each_entry(chan, &virtio_chan_list, chan_list) {
+		if (!strncmp(devname, chan->tag, chan->tag_len) &&
+		    strlen(devname) == chan->tag_len) {
+			if (!chan->inuse) {
+				chan->inuse = true;
+				found = 1;
+				break;
+			}
+			ret = -EBUSY;
+		}
+	}
+	mutex_unlock(&virtio_9p_lock);
+
+	if (!found) {
+		pr_err("no channels available\n");
+		return ret;
+	}
+
+	client->trans = (void *)chan;
+	client->status = Connected;
+	chan->client = client;
+
+	return 0;
+}
+
+/**
+ * p9_virtio_remove - clean up resources associated with a virtio device
+ * @vdev: virtio device to remove
+ *
+ */
+
+static void p9_virtio_remove(struct virtio_device *vdev)
+{
+	struct virtio_chan *chan = vdev->priv;
+
+	if (chan->inuse)
+		p9_virtio_close(chan->client);
+	vdev->config->del_vqs(vdev);
+
+	mutex_lock(&virtio_9p_lock);
+	list_del(&chan->chan_list);
+	mutex_unlock(&virtio_9p_lock);
+	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+	kfree(chan->tag);
+	kfree(chan->vc_wq);
+	kfree(chan);
+
+}
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static unsigned int features[] = {
+	VIRTIO_9P_MOUNT_TAG,
+};
+
+/* The standard "struct lguest_driver": */
+static struct virtio_driver p9_virtio_drv = {
+	.feature_table  = features,
+	.feature_table_size = ARRAY_SIZE(features),
+	.driver.name    = KBUILD_MODNAME,
+	.driver.owner	= THIS_MODULE,
+	.id_table	= id_table,
+	.probe		= p9_virtio_probe,
+	.remove		= p9_virtio_remove,
+};
+
+static struct p9_trans_module p9_virtio_trans = {
+	.name = "virtio",
+	.create = p9_virtio_create,
+	.close = p9_virtio_close,
+	.request = p9_virtio_request,
+	.zc_request = p9_virtio_zc_request,
+	.cancel = p9_virtio_cancel,
+	/*
+	 * We leave one entry for input and one entry for response
+	 * headers. We also skip one more entry to accomodate, address
+	 * that are not at page boundary, that can result in an extra
+	 * page in zero copy.
+	 */
+	.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
+	.def = 0,
+	.owner = THIS_MODULE,
+};
+
+/* The standard init function */
+static int __init p9_virtio_init(void)
+{
+	INIT_LIST_HEAD(&virtio_chan_list);
+
+	v9fs_register_trans(&p9_virtio_trans);
+	return register_virtio_driver(&p9_virtio_drv);
+}
+
+static void __exit p9_virtio_cleanup(void)
+{
+	unregister_virtio_driver(&p9_virtio_drv);
+	v9fs_unregister_trans(&p9_virtio_trans);
+}
+
+module_init(p9_virtio_init);
+module_exit(p9_virtio_cleanup);
+
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_DESCRIPTION("Virtio 9p Transport");
+MODULE_LICENSE("GPL");

addons/9p/src/3.10.108/util.c

@@ -0,0 +1,141 @@
+/*
+ *  net/9p/util.c
+ *
+ *  This file contains some helper functions
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+
+/**
+ * struct p9_idpool - per-connection accounting for tag idpool
+ * @lock: protects the pool
+ * @pool: idr to allocate tag id from
+ *
+ */
+
+struct p9_idpool {
+	spinlock_t lock;
+	struct idr pool;
+};
+
+/**
+ * p9_idpool_create - create a new per-connection id pool
+ *
+ */
+
+struct p9_idpool *p9_idpool_create(void)
+{
+	struct p9_idpool *p;
+
+	p = kmalloc(sizeof(struct p9_idpool), GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&p->lock);
+	idr_init(&p->pool);
+
+	return p;
+}
+EXPORT_SYMBOL(p9_idpool_create);
+
+/**
+ * p9_idpool_destroy - create a new per-connection id pool
+ * @p: idpool to destroy
+ */
+
+void p9_idpool_destroy(struct p9_idpool *p)
+{
+	idr_destroy(&p->pool);
+	kfree(p);
+}
+EXPORT_SYMBOL(p9_idpool_destroy);
+
+/**
+ * p9_idpool_get - allocate numeric id from pool
+ * @p: pool to allocate from
+ *
+ * Bugs: This seems to be an awful generic function, should it be in idr.c with
+ *            the lock included in struct idr?
+ */
+
+int p9_idpool_get(struct p9_idpool *p)
+{
+	int i;
+	unsigned long flags;
+
+	idr_preload(GFP_NOFS);
+	spin_lock_irqsave(&p->lock, flags);
+
+	/* no need to store exactly p, we just need something non-null */
+	i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT);
+
+	spin_unlock_irqrestore(&p->lock, flags);
+	idr_preload_end();
+	if (i < 0)
+		return -1;
+
+	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
+	return i;
+}
+EXPORT_SYMBOL(p9_idpool_get);
+
+/**
+ * p9_idpool_put - release numeric id from pool
+ * @id: numeric id which is being released
+ * @p: pool to release id into
+ *
+ * Bugs: This seems to be an awful generic function, should it be in idr.c with
+ *            the lock included in struct idr?
+ */
+
+void p9_idpool_put(int id, struct p9_idpool *p)
+{
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
+
+	spin_lock_irqsave(&p->lock, flags);
+	idr_remove(&p->pool, id);
+	spin_unlock_irqrestore(&p->lock, flags);
+}
+EXPORT_SYMBOL(p9_idpool_put);
+
+/**
+ * p9_idpool_check - check if the specified id is available
+ * @id: id to check
+ * @p: pool to check
+ */
+
+int p9_idpool_check(int id, struct p9_idpool *p)
+{
+	return idr_find(&p->pool, id) != NULL;
+}
+EXPORT_SYMBOL(p9_idpool_check);
+

addons/9p/src/3.10.108/v9fs.c

@@ -0,0 +1,677 @@
+/*
+ *  linux/fs/9p/v9fs.c
+ *
+ *  This file contains functions assisting in mapping VFS to 9P2000
+ *
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+
+static DEFINE_SPINLOCK(v9fs_sessionlist_lock);
+static LIST_HEAD(v9fs_sessionlist);
+struct kmem_cache *v9fs_inode_cache;
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ *  NOTE: each transport will parse its own options
+ */
+
+enum {
+	/* Options that take integer arguments */
+	Opt_debug, Opt_dfltuid, Opt_dfltgid, Opt_afid,
+	/* String options */
+	Opt_uname, Opt_remotename, Opt_trans, Opt_cache, Opt_cachetag,
+	/* Options that take no arguments */
+	Opt_nodevmap,
+	/* Cache options */
+	Opt_cache_loose, Opt_fscache,
+	/* Access options */
+	Opt_access, Opt_posixacl,
+	/* Error token */
+	Opt_err
+};
+
+static const match_table_t tokens = {
+	{Opt_debug, "debug=%x"},
+	{Opt_dfltuid, "dfltuid=%u"},
+	{Opt_dfltgid, "dfltgid=%u"},
+	{Opt_afid, "afid=%u"},
+	{Opt_uname, "uname=%s"},
+	{Opt_remotename, "aname=%s"},
+	{Opt_nodevmap, "nodevmap"},
+	{Opt_cache, "cache=%s"},
+	{Opt_cache_loose, "loose"},
+	{Opt_fscache, "fscache"},
+	{Opt_cachetag, "cachetag=%s"},
+	{Opt_access, "access=%s"},
+	{Opt_posixacl, "posixacl"},
+	{Opt_err, NULL}
+};
+
+/* Interpret mount options for cache mode */
+static int get_cache_mode(char *s)
+{
+	int version = -EINVAL;
+
+	if (!strcmp(s, "loose")) {
+		version = CACHE_LOOSE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: loose\n");
+	} else if (!strcmp(s, "fscache")) {
+		version = CACHE_FSCACHE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n");
+	} else if (!strcmp(s, "none")) {
+		version = CACHE_NONE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: none\n");
+	} else
+		pr_info("Unknown Cache mode %s\n", s);
+	return version;
+}
+
+/**
+ * v9fs_parse_options - parse mount options into session structure
+ * @v9ses: existing v9fs session information
+ *
+ * Return 0 upon success, -ERRNO upon failure.
+ */
+
+static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
+{
+	char *options, *tmp_options;
+	substring_t args[MAX_OPT_ARGS];
+	char *p;
+	int option = 0;
+	char *s, *e;
+	int ret = 0;
+
+	/* setup defaults */
+	v9ses->afid = ~0;
+	v9ses->debug = 0;
+	v9ses->cache = CACHE_NONE;
+#ifdef CONFIG_9P_FSCACHE
+	v9ses->cachetag = NULL;
+#endif
+
+	if (!opts)
+		return 0;
+
+	tmp_options = kstrdup(opts, GFP_KERNEL);
+	if (!tmp_options) {
+		ret = -ENOMEM;
+		goto fail_option_alloc;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token, r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_debug:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->debug = option;
+#ifdef CONFIG_NET_9P_DEBUG
+			p9_debug_level = option;
+#endif
+			break;
+
+		case Opt_dfltuid:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->dfltuid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(v9ses->dfltuid)) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "uid field, but not a uid?\n");
+				ret = -EINVAL;
+				continue;
+			}
+			break;
+		case Opt_dfltgid:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->dfltgid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(v9ses->dfltgid)) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "gid field, but not a gid?\n");
+				ret = -EINVAL;
+				continue;
+			}
+			break;
+		case Opt_afid:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->afid = option;
+			break;
+		case Opt_uname:
+			kfree(v9ses->uname);
+			v9ses->uname = match_strdup(&args[0]);
+			if (!v9ses->uname) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
+			break;
+		case Opt_remotename:
+			kfree(v9ses->aname);
+			v9ses->aname = match_strdup(&args[0]);
+			if (!v9ses->aname) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
+			break;
+		case Opt_nodevmap:
+			v9ses->nodev = 1;
+			break;
+		case Opt_cache_loose:
+			v9ses->cache = CACHE_LOOSE;
+			break;
+		case Opt_fscache:
+			v9ses->cache = CACHE_FSCACHE;
+			break;
+		case Opt_cachetag:
+#ifdef CONFIG_9P_FSCACHE
+			v9ses->cachetag = match_strdup(&args[0]);
+#endif
+			break;
+		case Opt_cache:
+			s = match_strdup(&args[0]);
+			if (!s) {
+				ret = -ENOMEM;
+				p9_debug(P9_DEBUG_ERROR,
+					 "problem allocating copy of cache arg\n");
+				goto free_and_return;
+			}
+			ret = get_cache_mode(s);
+			if (ret == -EINVAL) {
+				kfree(s);
+				goto free_and_return;
+			}
+
+			v9ses->cache = ret;
+			kfree(s);
+			break;
+
+		case Opt_access:
+			s = match_strdup(&args[0]);
+			if (!s) {
+				ret = -ENOMEM;
+				p9_debug(P9_DEBUG_ERROR,
+					 "problem allocating copy of access arg\n");
+				goto free_and_return;
+			}
+
+			v9ses->flags &= ~V9FS_ACCESS_MASK;
+			if (strcmp(s, "user") == 0)
+				v9ses->flags |= V9FS_ACCESS_USER;
+			else if (strcmp(s, "any") == 0)
+				v9ses->flags |= V9FS_ACCESS_ANY;
+			else if (strcmp(s, "client") == 0) {
+				v9ses->flags |= V9FS_ACCESS_CLIENT;
+			} else {
+				uid_t uid;
+				v9ses->flags |= V9FS_ACCESS_SINGLE;
+				uid = simple_strtoul(s, &e, 10);
+				if (*e != '\0') {
+					ret = -EINVAL;
+					pr_info("Unknown access argument %s\n",
+						s);
+					kfree(s);
+					goto free_and_return;
+				}
+				v9ses->uid = make_kuid(current_user_ns(), uid);
+				if (!uid_valid(v9ses->uid)) {
+					ret = -EINVAL;
+					pr_info("Uknown uid %s\n", s);
+					kfree(s);
+					goto free_and_return;
+				}
+			}
+
+			kfree(s);
+			break;
+
+		case Opt_posixacl:
+#ifdef CONFIG_9P_FS_POSIX_ACL
+			v9ses->flags |= V9FS_POSIX_ACL;
+#else
+			p9_debug(P9_DEBUG_ERROR,
+				 "Not defined CONFIG_9P_FS_POSIX_ACL. Ignoring posixacl option\n");
+#endif
+			break;
+
+		default:
+			continue;
+		}
+	}
+
+free_and_return:
+	kfree(tmp_options);
+fail_option_alloc:
+	return ret;
+}
+
+/**
+ * v9fs_session_init - initialize session
+ * @v9ses: session information structure
+ * @dev_name: device being mounted
+ * @data: options
+ *
+ */
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
+		  const char *dev_name, char *data)
+{
+	int retval = -EINVAL;
+	struct p9_fid *fid;
+	int rc;
+
+	v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
+	if (!v9ses->uname)
+		return ERR_PTR(-ENOMEM);
+
+	v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
+	if (!v9ses->aname) {
+		kfree(v9ses->uname);
+		return ERR_PTR(-ENOMEM);
+	}
+	init_rwsem(&v9ses->rename_sem);
+
+	rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
+	if (rc) {
+		kfree(v9ses->aname);
+		kfree(v9ses->uname);
+		return ERR_PTR(rc);
+	}
+
+	spin_lock(&v9fs_sessionlist_lock);
+	list_add(&v9ses->slist, &v9fs_sessionlist);
+	spin_unlock(&v9fs_sessionlist_lock);
+
+	v9ses->uid = INVALID_UID;
+	v9ses->dfltuid = V9FS_DEFUID;
+	v9ses->dfltgid = V9FS_DEFGID;
+
+	v9ses->clnt = p9_client_create(dev_name, data);
+	if (IS_ERR(v9ses->clnt)) {
+		retval = PTR_ERR(v9ses->clnt);
+		v9ses->clnt = NULL;
+		p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
+		goto error;
+	}
+
+	v9ses->flags = V9FS_ACCESS_USER;
+
+	if (p9_is_proto_dotl(v9ses->clnt)) {
+		v9ses->flags = V9FS_ACCESS_CLIENT;
+		v9ses->flags |= V9FS_PROTO_2000L;
+	} else if (p9_is_proto_dotu(v9ses->clnt)) {
+		v9ses->flags |= V9FS_PROTO_2000U;
+	}
+
+	rc = v9fs_parse_options(v9ses, data);
+	if (rc < 0) {
+		retval = rc;
+		goto error;
+	}
+
+	v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
+
+	if (!v9fs_proto_dotl(v9ses) &&
+	    ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
+		/*
+		 * We support ACCESS_CLIENT only for dotl.
+		 * Fall back to ACCESS_USER
+		 */
+		v9ses->flags &= ~V9FS_ACCESS_MASK;
+		v9ses->flags |= V9FS_ACCESS_USER;
+	}
+	/*FIXME !! */
+	/* for legacy mode, fall back to V9FS_ACCESS_ANY */
+	if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) &&
+		((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) {
+
+		v9ses->flags &= ~V9FS_ACCESS_MASK;
+		v9ses->flags |= V9FS_ACCESS_ANY;
+		v9ses->uid = INVALID_UID;
+	}
+	if (!v9fs_proto_dotl(v9ses) ||
+		!((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
+		/*
+		 * We support ACL checks on clinet only if the protocol is
+		 * 9P2000.L and access is V9FS_ACCESS_CLIENT.
+		 */
+		v9ses->flags &= ~V9FS_ACL_MASK;
+	}
+
+	fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID,
+							v9ses->aname);
+	if (IS_ERR(fid)) {
+		retval = PTR_ERR(fid);
+		fid = NULL;
+		p9_debug(P9_DEBUG_ERROR, "cannot attach\n");
+		goto error;
+	}
+
+	if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE)
+		fid->uid = v9ses->uid;
+	else
+		fid->uid = INVALID_UID;
+
+#ifdef CONFIG_9P_FSCACHE
+	/* register the session for caching */
+	v9fs_cache_session_get_cookie(v9ses);
+#endif
+
+	return fid;
+
+error:
+	bdi_destroy(&v9ses->bdi);
+	return ERR_PTR(retval);
+}
+
+/**
+ * v9fs_session_close - shutdown a session
+ * @v9ses: session information structure
+ *
+ */
+
+void v9fs_session_close(struct v9fs_session_info *v9ses)
+{
+	if (v9ses->clnt) {
+		p9_client_destroy(v9ses->clnt);
+		v9ses->clnt = NULL;
+	}
+
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->fscache) {
+		v9fs_cache_session_put_cookie(v9ses);
+		kfree(v9ses->cachetag);
+	}
+#endif
+	kfree(v9ses->uname);
+	kfree(v9ses->aname);
+
+	bdi_destroy(&v9ses->bdi);
+
+	spin_lock(&v9fs_sessionlist_lock);
+	list_del(&v9ses->slist);
+	spin_unlock(&v9fs_sessionlist_lock);
+}
+
+/**
+ * v9fs_session_cancel - terminate a session
+ * @v9ses: session to terminate
+ *
+ * mark transport as disconnected and cancel all pending requests.
+ */
+
+void v9fs_session_cancel(struct v9fs_session_info *v9ses) {
+	p9_debug(P9_DEBUG_ERROR, "cancel session %p\n", v9ses);
+	p9_client_disconnect(v9ses->clnt);
+}
+
+/**
+ * v9fs_session_begin_cancel - Begin terminate of a session
+ * @v9ses: session to terminate
+ *
+ * After this call we don't allow any request other than clunk.
+ */
+
+void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses)
+{
+	p9_debug(P9_DEBUG_ERROR, "begin cancel session %p\n", v9ses);
+	p9_client_begin_disconnect(v9ses->clnt);
+}
+
+extern int v9fs_error_init(void);
+
+static struct kobject *v9fs_kobj;
+
+#ifdef CONFIG_9P_FSCACHE
+/**
+ * caches_show - list caches associated with a session
+ *
+ * Returns the size of buffer written.
+ */
+
+static ssize_t caches_show(struct kobject *kobj,
+			   struct kobj_attribute *attr,
+			   char *buf)
+{
+	ssize_t n = 0, count = 0, limit = PAGE_SIZE;
+	struct v9fs_session_info *v9ses;
+
+	spin_lock(&v9fs_sessionlist_lock);
+	list_for_each_entry(v9ses, &v9fs_sessionlist, slist) {
+		if (v9ses->cachetag) {
+			n = snprintf(buf, limit, "%s\n", v9ses->cachetag);
+			if (n < 0) {
+				count = n;
+				break;
+			}
+
+			count += n;
+			limit -= n;
+		}
+	}
+
+	spin_unlock(&v9fs_sessionlist_lock);
+	return count;
+}
+
+static struct kobj_attribute v9fs_attr_cache = __ATTR_RO(caches);
+#endif /* CONFIG_9P_FSCACHE */
+
+static struct attribute *v9fs_attrs[] = {
+#ifdef CONFIG_9P_FSCACHE
+	&v9fs_attr_cache.attr,
+#endif
+	NULL,
+};
+
+static struct attribute_group v9fs_attr_group = {
+	.attrs = v9fs_attrs,
+};
+
+/**
+ * v9fs_sysfs_init - Initialize the v9fs sysfs interface
+ *
+ */
+
+static int v9fs_sysfs_init(void)
+{
+	v9fs_kobj = kobject_create_and_add("9p", fs_kobj);
+	if (!v9fs_kobj)
+		return -ENOMEM;
+
+	if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) {
+		kobject_put(v9fs_kobj);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * v9fs_sysfs_cleanup - Unregister the v9fs sysfs interface
+ *
+ */
+
+static void v9fs_sysfs_cleanup(void)
+{
+	sysfs_remove_group(v9fs_kobj, &v9fs_attr_group);
+	kobject_put(v9fs_kobj);
+}
+
+static void v9fs_inode_init_once(void *foo)
+{
+	struct v9fs_inode *v9inode = (struct v9fs_inode *)foo;
+#ifdef CONFIG_9P_FSCACHE
+	v9inode->fscache = NULL;
+#endif
+	memset(&v9inode->qid, 0, sizeof(v9inode->qid));
+	inode_init_once(&v9inode->vfs_inode);
+}
+
+/**
+ * v9fs_init_inode_cache - initialize a cache for 9P
+ * Returns 0 on success.
+ */
+static int v9fs_init_inode_cache(void)
+{
+	v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache",
+					  sizeof(struct v9fs_inode),
+					  0, (SLAB_RECLAIM_ACCOUNT|
+					      SLAB_MEM_SPREAD),
+					  v9fs_inode_init_once);
+	if (!v9fs_inode_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * v9fs_destroy_inode_cache - destroy the cache of 9P inode
+ *
+ */
+static void v9fs_destroy_inode_cache(void)
+{
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+	kmem_cache_destroy(v9fs_inode_cache);
+}
+
+static int v9fs_cache_register(void)
+{
+	int ret;
+	ret = v9fs_init_inode_cache();
+	if (ret < 0)
+		return ret;
+#ifdef CONFIG_9P_FSCACHE
+	return fscache_register_netfs(&v9fs_cache_netfs);
+#else
+	return ret;
+#endif
+}
+
+static void v9fs_cache_unregister(void)
+{
+	v9fs_destroy_inode_cache();
+#ifdef CONFIG_9P_FSCACHE
+	fscache_unregister_netfs(&v9fs_cache_netfs);
+#endif
+}
+
+/**
+ * init_v9fs - Initialize module
+ *
+ */
+
+static int __init init_v9fs(void)
+{
+	int err;
+	pr_info("Installing v9fs 9p2000 file system support\n");
+	/* TODO: Setup list of registered trasnport modules */
+
+	err = v9fs_cache_register();
+	if (err < 0) {
+		pr_err("Failed to register v9fs for caching\n");
+		return err;
+	}
+
+	err = v9fs_sysfs_init();
+	if (err < 0) {
+		pr_err("Failed to register with sysfs\n");
+		goto out_cache;
+	}
+	err = register_filesystem(&v9fs_fs_type);
+	if (err < 0) {
+		pr_err("Failed to register filesystem\n");
+		goto out_sysfs_cleanup;
+	}
+
+	return 0;
+
+out_sysfs_cleanup:
+	v9fs_sysfs_cleanup();
+
+out_cache:
+	v9fs_cache_unregister();
+
+	return err;
+}
+
+/**
+ * exit_v9fs - shutdown module
+ *
+ */
+
+static void __exit exit_v9fs(void)
+{
+	v9fs_sysfs_cleanup();
+	v9fs_cache_unregister();
+	unregister_filesystem(&v9fs_fs_type);
+}
+
+module_init(init_v9fs)
+module_exit(exit_v9fs)
+
+MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>");
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>");
+MODULE_LICENSE("GPL");

addons/9p/src/3.10.108/v9fs.h

@@ -0,0 +1,227 @@
+/*
+ * V9FS definitions.
+ *
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_V9FS_H
+#define FS_9P_V9FS_H
+
+#include <linux/backing-dev.h>
+
+/**
+ * enum p9_session_flags - option flags for each 9P session
+ * @V9FS_PROTO_2000U: whether or not to use 9P2000.u extensions
+ * @V9FS_PROTO_2000L: whether or not to use 9P2000.l extensions
+ * @V9FS_ACCESS_SINGLE: only the mounting user can access the hierarchy
+ * @V9FS_ACCESS_USER: a new attach will be issued for every user (default)
+ * @V9FS_ACCESS_CLIENT: Just like user, but access check is performed on client.
+ * @V9FS_ACCESS_ANY: use a single attach for all users
+ * @V9FS_ACCESS_MASK: bit mask of different ACCESS options
+ * @V9FS_POSIX_ACL: POSIX ACLs are enforced
+ *
+ * Session flags reflect options selected by users at mount time
+ */
+#define	V9FS_ACCESS_ANY (V9FS_ACCESS_SINGLE | \
+			 V9FS_ACCESS_USER |   \
+			 V9FS_ACCESS_CLIENT)
+#define V9FS_ACCESS_MASK V9FS_ACCESS_ANY
+#define V9FS_ACL_MASK V9FS_POSIX_ACL
+
+enum p9_session_flags {
+	V9FS_PROTO_2000U	= 0x01,
+	V9FS_PROTO_2000L	= 0x02,
+	V9FS_ACCESS_SINGLE	= 0x04,
+	V9FS_ACCESS_USER	= 0x08,
+	V9FS_ACCESS_CLIENT	= 0x10,
+	V9FS_POSIX_ACL		= 0x20
+};
+
+/* possible values of ->cache */
+/**
+ * enum p9_cache_modes - user specified cache preferences
+ * @CACHE_NONE: do not cache data, dentries, or directory contents (default)
+ * @CACHE_LOOSE: cache data, dentries, and directory contents w/no consistency
+ *
+ * eventually support loose, tight, time, session, default always none
+ */
+
+enum p9_cache_modes {
+	CACHE_NONE,
+	CACHE_LOOSE,
+	CACHE_FSCACHE,
+};
+
+/**
+ * struct v9fs_session_info - per-instance session information
+ * @flags: session options of type &p9_session_flags
+ * @nodev: set to 1 to disable device mapping
+ * @debug: debug level
+ * @afid: authentication handle
+ * @cache: cache mode of type &p9_cache_modes
+ * @cachetag: the tag of the cache associated with this session
+ * @fscache: session cookie associated with FS-Cache
+ * @options: copy of options string given by user
+ * @uname: string user name to mount hierarchy as
+ * @aname: mount specifier for remote hierarchy
+ * @maxdata: maximum data to be sent/recvd per protocol message
+ * @dfltuid: default numeric userid to mount hierarchy as
+ * @dfltgid: default numeric groupid to mount hierarchy as
+ * @uid: if %V9FS_ACCESS_SINGLE, the numeric uid which mounted the hierarchy
+ * @clnt: reference to 9P network client instantiated for this session
+ * @slist: reference to list of registered 9p sessions
+ *
+ * This structure holds state for each session instance established during
+ * a sys_mount() .
+ *
+ * Bugs: there seems to be a lot of state which could be condensed and/or
+ * removed.
+ */
+
+struct v9fs_session_info {
+	/* options */
+	unsigned char flags;
+	unsigned char nodev;
+	unsigned short debug;
+	unsigned int afid;
+	unsigned int cache;
+#ifdef CONFIG_9P_FSCACHE
+	char *cachetag;
+	struct fscache_cookie *fscache;
+#endif
+
+	char *uname;		/* user name to mount as */
+	char *aname;		/* name of remote hierarchy being mounted */
+	unsigned int maxdata;	/* max data for client interface */
+	kuid_t dfltuid;		/* default uid/muid for legacy support */
+	kgid_t dfltgid;		/* default gid for legacy support */
+	kuid_t uid;		/* if ACCESS_SINGLE, the uid that has access */
+	struct p9_client *clnt;	/* 9p client */
+	struct list_head slist; /* list of sessions registered with v9fs */
+	struct backing_dev_info bdi;
+	struct rw_semaphore rename_sem;
+};
+
+/* cache_validity flags */
+#define V9FS_INO_INVALID_ATTR 0x01
+
+struct v9fs_inode {
+#ifdef CONFIG_9P_FSCACHE
+	spinlock_t fscache_lock;
+	struct fscache_cookie *fscache;
+#endif
+	struct p9_qid qid;
+	unsigned int cache_validity;
+	struct p9_fid *writeback_fid;
+	struct mutex v_mutex;
+	struct inode vfs_inode;
+};
+
+static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
+{
+	return container_of(inode, struct v9fs_inode, vfs_inode);
+}
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
+									char *);
+extern void v9fs_session_close(struct v9fs_session_info *v9ses);
+extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
+extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
+extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
+			unsigned int flags);
+extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
+extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
+extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry);
+extern void v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd,
+			void *p);
+extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
+					 struct p9_fid *fid,
+					 struct super_block *sb, int new);
+extern const struct inode_operations v9fs_dir_inode_operations_dotl;
+extern const struct inode_operations v9fs_file_inode_operations_dotl;
+extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
+extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
+					      struct p9_fid *fid,
+					      struct super_block *sb, int new);
+
+/* other default globals */
+#define V9FS_PORT	564
+#define V9FS_DEFUSER	"nobody"
+#define V9FS_DEFANAME	""
+#define V9FS_DEFUID	KUIDT_INIT(-2)
+#define V9FS_DEFGID	KGIDT_INIT(-2)
+
+static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
+{
+	return (inode->i_sb->s_fs_info);
+}
+
+static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry)
+{
+	return dentry->d_sb->s_fs_info;
+}
+
+static inline int v9fs_proto_dotu(struct v9fs_session_info *v9ses)
+{
+	return v9ses->flags & V9FS_PROTO_2000U;
+}
+
+static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
+{
+	return v9ses->flags & V9FS_PROTO_2000L;
+}
+
+/**
+ * v9fs_get_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			struct super_block *sb)
+{
+	if (v9fs_proto_dotl(v9ses))
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 0);
+	else
+		return v9fs_inode_from_fid(v9ses, fid, sb, 0);
+}
+
+/**
+ * v9fs_get_new_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_new_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			    struct super_block *sb)
+{
+	if (v9fs_proto_dotl(v9ses))
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 1);
+	else
+		return v9fs_inode_from_fid(v9ses, fid, sb, 1);
+}
+
+#endif

addons/9p/src/3.10.108/v9fs_vfs.h

@@ -0,0 +1,88 @@
+/*
+ * V9FS VFS extensions.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_V9FS_VFS_H
+#define FS_9P_V9FS_VFS_H
+
+/* plan9 semantics are that created files are implicitly opened.
+ * But linux semantics are that you call create, then open.
+ * the plan9 approach is superior as it provides an atomic
+ * open.
+ * we track the create fid here. When the file is opened, if fidopen is
+ * non-zero, we use the fid and can skip some steps.
+ * there may be a better way to do this, but I don't know it.
+ * one BAD way is to clunk the fid on create, then open it again:
+ * you lose the atomicity of file open
+ */
+
+/* special case:
+ * unlink calls remove, which is an implicit clunk. So we have to track
+ * that kind of thing so that we don't try to clunk a dead fid.
+ */
+#define P9_LOCK_TIMEOUT (30*HZ)
+
+extern struct file_system_type v9fs_fs_type;
+extern const struct address_space_operations v9fs_addr_operations;
+extern const struct file_operations v9fs_file_operations;
+extern const struct file_operations v9fs_file_operations_dotl;
+extern const struct file_operations v9fs_dir_operations;
+extern const struct file_operations v9fs_dir_operations_dotl;
+extern const struct dentry_operations v9fs_dentry_operations;
+extern const struct dentry_operations v9fs_cached_dentry_operations;
+extern const struct file_operations v9fs_cached_file_operations;
+extern const struct file_operations v9fs_cached_file_operations_dotl;
+extern struct kmem_cache *v9fs_inode_cache;
+
+struct inode *v9fs_alloc_inode(struct super_block *sb);
+void v9fs_destroy_inode(struct inode *inode);
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t);
+int v9fs_init_inode(struct v9fs_session_info *v9ses,
+		    struct inode *inode, umode_t mode, dev_t);
+void v9fs_evict_inode(struct inode *inode);
+ino_t v9fs_qid2ino(struct p9_qid *qid);
+void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
+void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *);
+int v9fs_dir_release(struct inode *inode, struct file *filp);
+int v9fs_file_open(struct inode *inode, struct file *file);
+void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
+int v9fs_uflags2omode(int uflags, int extended);
+
+ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64);
+ssize_t v9fs_fid_readn(struct p9_fid *, char *, char __user *, u32, u64);
+void v9fs_blank_wstat(struct p9_wstat *wstat);
+int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *);
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+			 int datasync);
+ssize_t v9fs_file_write_internal(struct inode *, struct p9_fid *,
+				 const char __user *, size_t, loff_t *, int);
+int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
+int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode);
+static inline void v9fs_invalidate_inode_attr(struct inode *inode)
+{
+	struct v9fs_inode *v9inode;
+	v9inode = V9FS_I(inode);
+	v9inode->cache_validity |= V9FS_INO_INVALID_ATTR;
+	return;
+}
+
+int v9fs_open_to_dotl_flags(int flags);
+#endif

addons/9p/src/3.10.108/vfs_addr.c

@@ -0,0 +1,353 @@
+/*
+ *  linux/fs/9p/vfs_addr.c
+ *
+ * This file contians vfs address (mmap) ops for 9P2000.
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/pagemap.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/aio.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+#include "fid.h"
+
+/**
+ * v9fs_fid_readpage - read an entire page in from 9P
+ *
+ * @fid: fid being read
+ * @page: structure to page
+ *
+ */
+static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
+{
+	int retval;
+	loff_t offset;
+	char *buffer;
+	struct inode *inode;
+
+	inode = page->mapping->host;
+	p9_debug(P9_DEBUG_VFS, "\n");
+
+	BUG_ON(!PageLocked(page));
+
+	retval = v9fs_readpage_from_fscache(inode, page);
+	if (retval == 0)
+		return retval;
+
+	buffer = kmap(page);
+	offset = page_offset(page);
+
+	retval = v9fs_fid_readn(fid, buffer, NULL, PAGE_CACHE_SIZE, offset);
+	if (retval < 0) {
+		v9fs_uncache_page(inode, page);
+		goto done;
+	}
+
+	memset(buffer + retval, 0, PAGE_CACHE_SIZE - retval);
+	flush_dcache_page(page);
+	SetPageUptodate(page);
+
+	v9fs_readpage_to_fscache(inode, page);
+	retval = 0;
+
+done:
+	kunmap(page);
+	unlock_page(page);
+	return retval;
+}
+
+/**
+ * v9fs_vfs_readpage - read an entire page in from 9P
+ *
+ * @filp: file being read
+ * @page: structure to page
+ *
+ */
+
+static int v9fs_vfs_readpage(struct file *filp, struct page *page)
+{
+	return v9fs_fid_readpage(filp->private_data, page);
+}
+
+/**
+ * v9fs_vfs_readpages - read a set of pages from 9P
+ *
+ * @filp: file being read
+ * @mapping: the address space
+ * @pages: list of pages to read
+ * @nr_pages: count of pages to read
+ *
+ */
+
+static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping,
+			     struct list_head *pages, unsigned nr_pages)
+{
+	int ret = 0;
+	struct inode *inode;
+
+	inode = mapping->host;
+	p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, filp);
+
+	ret = v9fs_readpages_from_fscache(inode, mapping, pages, &nr_pages);
+	if (ret == 0)
+		return ret;
+
+	ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp);
+	p9_debug(P9_DEBUG_VFS, "  = %d\n", ret);
+	return ret;
+}
+
+/**
+ * v9fs_release_page - release the private state associated with a page
+ *
+ * Returns 1 if the page can be released, false otherwise.
+ */
+
+static int v9fs_release_page(struct page *page, gfp_t gfp)
+{
+	if (PagePrivate(page))
+		return 0;
+	return v9fs_fscache_release_page(page, gfp);
+}
+
+/**
+ * v9fs_invalidate_page - Invalidate a page completely or partially
+ *
+ * @page: structure to page
+ * @offset: offset in the page
+ */
+
+static void v9fs_invalidate_page(struct page *page, unsigned long offset)
+{
+	/*
+	 * If called with zero offset, we should release
+	 * the private state assocated with the page
+	 */
+	if (offset == 0)
+		v9fs_fscache_invalidate_page(page);
+}
+
+static int v9fs_vfs_writepage_locked(struct page *page)
+{
+	char *buffer;
+	int retval, len;
+	loff_t offset, size;
+	mm_segment_t old_fs;
+	struct v9fs_inode *v9inode;
+	struct inode *inode = page->mapping->host;
+
+	v9inode = V9FS_I(inode);
+	size = i_size_read(inode);
+	if (page->index == size >> PAGE_CACHE_SHIFT)
+		len = size & ~PAGE_CACHE_MASK;
+	else
+		len = PAGE_CACHE_SIZE;
+
+	set_page_writeback(page);
+
+	buffer = kmap(page);
+	offset = page_offset(page);
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* We should have writeback_fid always set */
+	BUG_ON(!v9inode->writeback_fid);
+
+	retval = v9fs_file_write_internal(inode,
+					  v9inode->writeback_fid,
+					  (__force const char __user *)buffer,
+					  len, &offset, 0);
+	if (retval > 0)
+		retval = 0;
+
+	set_fs(old_fs);
+	kunmap(page);
+	end_page_writeback(page);
+	return retval;
+}
+
+static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+	int retval;
+
+	retval = v9fs_vfs_writepage_locked(page);
+	if (retval < 0) {
+		if (retval == -EAGAIN) {
+			redirty_page_for_writepage(wbc, page);
+			retval = 0;
+		} else {
+			SetPageError(page);
+			mapping_set_error(page->mapping, retval);
+		}
+	} else
+		retval = 0;
+
+	unlock_page(page);
+	return retval;
+}
+
+/**
+ * v9fs_launder_page - Writeback a dirty page
+ * Returns 0 on success.
+ */
+
+static int v9fs_launder_page(struct page *page)
+{
+	int retval;
+	struct inode *inode = page->mapping->host;
+
+	v9fs_fscache_wait_on_page_write(inode, page);
+	if (clear_page_dirty_for_io(page)) {
+		retval = v9fs_vfs_writepage_locked(page);
+		if (retval)
+			return retval;
+	}
+	return 0;
+}
+
+/**
+ * v9fs_direct_IO - 9P address space operation for direct I/O
+ * @rw: direction (read or write)
+ * @iocb: target I/O control block
+ * @iov: array of vectors that define I/O buffer
+ * @pos: offset in file to begin the operation
+ * @nr_segs: size of iovec array
+ *
+ * The presence of v9fs_direct_IO() in the address space ops vector
+ * allowes open() O_DIRECT flags which would have failed otherwise.
+ *
+ * In the non-cached mode, we shunt off direct read and write requests before
+ * the VFS gets them, so this method should never be called.
+ *
+ * Direct IO is not 'yet' supported in the cached mode. Hence when
+ * this routine is called through generic_file_aio_read(), the read/write fails
+ * with an error.
+ *
+ */
+static ssize_t
+v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
+	       loff_t pos, unsigned long nr_segs)
+{
+	/*
+	 * FIXME
+	 * Now that we do caching with cache mode enabled, We need
+	 * to support direct IO
+	 */
+	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
+		 iocb->ki_filp->f_path.dentry->d_name.name,
+		 (long long)pos, nr_segs);
+
+	return -EINVAL;
+}
+
+static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{
+	int retval = 0;
+	struct page *page;
+	struct v9fs_inode *v9inode;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	struct inode *inode = mapping->host;
+
+	v9inode = V9FS_I(inode);
+start:
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page) {
+		retval = -ENOMEM;
+		goto out;
+	}
+	BUG_ON(!v9inode->writeback_fid);
+	if (PageUptodate(page))
+		goto out;
+
+	if (len == PAGE_CACHE_SIZE)
+		goto out;
+
+	retval = v9fs_fid_readpage(v9inode->writeback_fid, page);
+	page_cache_release(page);
+	if (!retval)
+		goto start;
+out:
+	*pagep = page;
+	return retval;
+}
+
+static int v9fs_write_end(struct file *filp, struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct page *page, void *fsdata)
+{
+	loff_t last_pos = pos + copied;
+	struct inode *inode = page->mapping->host;
+
+	if (unlikely(copied < len)) {
+		/*
+		 * zero out the rest of the area
+		 */
+		unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+
+		zero_user(page, from + copied, len - copied);
+		flush_dcache_page(page);
+	}
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+	/*
+	 * No need to use i_size_read() here, the i_size
+	 * cannot change under us because we hold the i_mutex.
+	 */
+	if (last_pos > inode->i_size) {
+		inode_add_bytes(inode, last_pos - inode->i_size);
+		i_size_write(inode, last_pos);
+	}
+	set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+
+	return copied;
+}
+
+
+const struct address_space_operations v9fs_addr_operations = {
+	.readpage = v9fs_vfs_readpage,
+	.readpages = v9fs_vfs_readpages,
+	.set_page_dirty = __set_page_dirty_nobuffers,
+	.writepage = v9fs_vfs_writepage,
+	.write_begin = v9fs_write_begin,
+	.write_end = v9fs_write_end,
+	.releasepage = v9fs_release_page,
+	.invalidatepage = v9fs_invalidate_page,
+	.launder_page = v9fs_launder_page,
+	.direct_IO = v9fs_direct_IO,
+};

addons/9p/src/3.10.108/vfs_dentry.c

@@ -0,0 +1,139 @@
+/*
+ *  linux/fs/9p/vfs_dentry.c
+ *
+ * This file contians vfs dentry ops for the 9P2000 protocol.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * v9fs_dentry_delete - called when dentry refcount equals 0
+ * @dentry:  dentry in question
+ *
+ * By returning 1 here we should remove cacheing of unused
+ * dentry components.
+ *
+ */
+
+static int v9fs_dentry_delete(const struct dentry *dentry)
+{
+	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
+		 dentry->d_name.name, dentry);
+
+	return 1;
+}
+
+/**
+ * v9fs_cached_dentry_delete - called when dentry refcount equals 0
+ * @dentry:  dentry in question
+ *
+ */
+static int v9fs_cached_dentry_delete(const struct dentry *dentry)
+{
+	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
+		 dentry->d_name.name, dentry);
+
+	/* Don't cache negative dentries */
+	if (!dentry->d_inode)
+		return 1;
+	return 0;
+}
+
+/**
+ * v9fs_dentry_release - called when dentry is going to be freed
+ * @dentry:  dentry that is being release
+ *
+ */
+
+static void v9fs_dentry_release(struct dentry *dentry)
+{
+	struct hlist_node *p, *n;
+	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
+		 dentry->d_name.name, dentry);
+	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+		p9_client_clunk(hlist_entry(p, struct p9_fid, dlist));
+	dentry->d_fsdata = NULL;
+}
+
+static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct p9_fid *fid;
+	struct inode *inode;
+	struct v9fs_inode *v9inode;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = dentry->d_inode;
+	if (!inode)
+		goto out_valid;
+
+	v9inode = V9FS_I(inode);
+	if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
+		int retval;
+		struct v9fs_session_info *v9ses;
+		fid = v9fs_fid_lookup(dentry);
+		if (IS_ERR(fid))
+			return PTR_ERR(fid);
+
+		v9ses = v9fs_inode2v9ses(inode);
+		if (v9fs_proto_dotl(v9ses))
+			retval = v9fs_refresh_inode_dotl(fid, inode);
+		else
+			retval = v9fs_refresh_inode(fid, inode);
+		if (retval == -ENOENT)
+			return 0;
+		if (retval < 0)
+			return retval;
+	}
+out_valid:
+	return 1;
+}
+
+const struct dentry_operations v9fs_cached_dentry_operations = {
+	.d_revalidate = v9fs_lookup_revalidate,
+	.d_weak_revalidate = v9fs_lookup_revalidate,
+	.d_delete = v9fs_cached_dentry_delete,
+	.d_release = v9fs_dentry_release,
+};
+
+const struct dentry_operations v9fs_dentry_operations = {
+	.d_delete = v9fs_dentry_delete,
+	.d_release = v9fs_dentry_release,
+};

addons/9p/src/3.10.108/vfs_dir.c

@@ -0,0 +1,269 @@
+/*
+ * linux/fs/9p/vfs_dir.c
+ *
+ * This file contains vfs directory ops for the 9P2000 protocol.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * struct p9_rdir - readdir accounting
+ * @mutex: mutex protecting readdir
+ * @head: start offset of current dirread buffer
+ * @tail: end offset of current dirread buffer
+ * @buf: dirread buffer
+ *
+ * private structure for keeping track of readdir
+ * allocated on demand
+ */
+
+struct p9_rdir {
+	int head;
+	int tail;
+	uint8_t buf[];
+};
+
+/**
+ * dt_type - return file type
+ * @mistat: mistat structure
+ *
+ */
+
+static inline int dt_type(struct p9_wstat *mistat)
+{
+	unsigned long perm = mistat->mode;
+	int rettype = DT_REG;
+
+	if (perm & P9_DMDIR)
+		rettype = DT_DIR;
+	if (perm & P9_DMSYMLINK)
+		rettype = DT_LNK;
+
+	return rettype;
+}
+
+static void p9stat_init(struct p9_wstat *stbuf)
+{
+	stbuf->name  = NULL;
+	stbuf->uid   = NULL;
+	stbuf->gid   = NULL;
+	stbuf->muid  = NULL;
+	stbuf->extension = NULL;
+}
+
+/**
+ * v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir
+ * @filp: opened file structure
+ * @buflen: Length in bytes of buffer to allocate
+ *
+ */
+
+static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen)
+{
+	struct p9_fid *fid = filp->private_data;
+	if (!fid->rdir)
+		fid->rdir = kzalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
+	return fid->rdir;
+}
+
+/**
+ * v9fs_dir_readdir - read a directory
+ * @filp: opened file structure
+ * @dirent: directory structure ???
+ * @filldir: function to populate directory structure ???
+ *
+ */
+
+static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	int over;
+	struct p9_wstat st;
+	int err = 0;
+	struct p9_fid *fid;
+	int buflen;
+	int reclen = 0;
+	struct p9_rdir *rdir;
+
+	p9_debug(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
+	fid = filp->private_data;
+
+	buflen = fid->clnt->msize - P9_IOHDRSZ;
+
+	rdir = v9fs_alloc_rdir_buf(filp, buflen);
+	if (!rdir)
+		return -ENOMEM;
+
+	while (1) {
+		if (rdir->tail == rdir->head) {
+			err = v9fs_file_readn(filp, rdir->buf, NULL,
+							buflen, filp->f_pos);
+			if (err <= 0)
+				return err;
+
+			rdir->head = 0;
+			rdir->tail = err;
+		}
+		while (rdir->head < rdir->tail) {
+			p9stat_init(&st);
+			err = p9stat_read(fid->clnt, rdir->buf + rdir->head,
+					  rdir->tail - rdir->head, &st);
+			if (err) {
+				p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+				p9stat_free(&st);
+				return -EIO;
+			}
+			reclen = st.size+2;
+
+			over = filldir(dirent, st.name, strlen(st.name),
+			    filp->f_pos, v9fs_qid2ino(&st.qid), dt_type(&st));
+
+			p9stat_free(&st);
+
+			if (over)
+				return 0;
+
+			rdir->head += reclen;
+			filp->f_pos += reclen;
+		}
+	}
+}
+
+/**
+ * v9fs_dir_readdir_dotl - read a directory
+ * @filp: opened file structure
+ * @dirent: buffer to fill dirent structures
+ * @filldir: function to populate dirent structures
+ *
+ */
+static int v9fs_dir_readdir_dotl(struct file *filp, void *dirent,
+						filldir_t filldir)
+{
+	int over;
+	int err = 0;
+	struct p9_fid *fid;
+	int buflen;
+	struct p9_rdir *rdir;
+	struct p9_dirent curdirent;
+	u64 oldoffset = 0;
+
+	p9_debug(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
+	fid = filp->private_data;
+
+	buflen = fid->clnt->msize - P9_READDIRHDRSZ;
+
+	rdir = v9fs_alloc_rdir_buf(filp, buflen);
+	if (!rdir)
+		return -ENOMEM;
+
+	while (1) {
+		if (rdir->tail == rdir->head) {
+			err = p9_client_readdir(fid, rdir->buf, buflen,
+						filp->f_pos);
+			if (err <= 0)
+				return err;
+
+			rdir->head = 0;
+			rdir->tail = err;
+		}
+
+		while (rdir->head < rdir->tail) {
+
+			err = p9dirent_read(fid->clnt, rdir->buf + rdir->head,
+					    rdir->tail - rdir->head,
+					    &curdirent);
+			if (err < 0) {
+				p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+				return -EIO;
+			}
+
+			/* d_off in dirent structure tracks the offset into
+			 * the next dirent in the dir. However, filldir()
+			 * expects offset into the current dirent. Hence
+			 * while calling filldir send the offset from the
+			 * previous dirent structure.
+			 */
+			over = filldir(dirent, curdirent.d_name,
+					strlen(curdirent.d_name),
+					oldoffset, v9fs_qid2ino(&curdirent.qid),
+					curdirent.d_type);
+			oldoffset = curdirent.d_off;
+
+			if (over)
+				return 0;
+
+			filp->f_pos = curdirent.d_off;
+			rdir->head += err;
+		}
+	}
+}
+
+
+/**
+ * v9fs_dir_release - close a directory
+ * @inode: inode of the directory
+ * @filp: file pointer to a directory
+ *
+ */
+
+int v9fs_dir_release(struct inode *inode, struct file *filp)
+{
+	struct p9_fid *fid;
+
+	fid = filp->private_data;
+	p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n",
+		 inode, filp, fid ? fid->fid : -1);
+	if (fid)
+		p9_client_clunk(fid);
+	return 0;
+}
+
+const struct file_operations v9fs_dir_operations = {
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+	.readdir = v9fs_dir_readdir,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+};
+
+const struct file_operations v9fs_dir_operations_dotl = {
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+	.readdir = v9fs_dir_readdir_dotl,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+        .fsync = v9fs_file_fsync_dotl,
+};

addons/9p/src/3.10.108/vfs_file.c

@@ -0,0 +1,790 @@
+/*
+ *  linux/fs/9p/vfs_file.c
+ *
+ * This file contians vfs file ops for 9P2000.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/utsname.h>
+#include <asm/uaccess.h>
+#include <linux/idr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "cache.h"
+
+static const struct vm_operations_struct v9fs_file_vm_ops;
+
+/**
+ * v9fs_file_open - open a file (or directory)
+ * @inode: inode to be opened
+ * @file: file being opened
+ *
+ */
+
+int v9fs_file_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct v9fs_inode *v9inode;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
+	int omode;
+
+	p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file);
+	v9inode = V9FS_I(inode);
+	v9ses = v9fs_inode2v9ses(inode);
+	if (v9fs_proto_dotl(v9ses))
+		omode = v9fs_open_to_dotl_flags(file->f_flags);
+	else
+		omode = v9fs_uflags2omode(file->f_flags,
+					v9fs_proto_dotu(v9ses));
+	fid = file->private_data;
+	if (!fid) {
+		fid = v9fs_fid_clone(file->f_path.dentry);
+		if (IS_ERR(fid))
+			return PTR_ERR(fid);
+
+		err = p9_client_open(fid, omode);
+		if (err < 0) {
+			p9_client_clunk(fid);
+			return err;
+		}
+		if ((file->f_flags & O_APPEND) &&
+			(!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)))
+			generic_file_llseek(file, 0, SEEK_END);
+	}
+
+	file->private_data = fid;
+	mutex_lock(&v9inode->v_mutex);
+	if (v9ses->cache && !v9inode->writeback_fid &&
+	    ((file->f_flags & O_ACCMODE) != O_RDONLY)) {
+		/*
+		 * clone a fid and add it to writeback_fid
+		 * we do it during open time instead of
+		 * page dirty time via write_begin/page_mkwrite
+		 * because we want write after unlink usecase
+		 * to work.
+		 */
+		fid = v9fs_writeback_fid(file->f_path.dentry);
+		if (IS_ERR(fid)) {
+			err = PTR_ERR(fid);
+			mutex_unlock(&v9inode->v_mutex);
+			goto out_error;
+		}
+		v9inode->writeback_fid = (void *) fid;
+	}
+	mutex_unlock(&v9inode->v_mutex);
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->cache)
+		v9fs_cache_inode_set_cookie(inode, file);
+#endif
+	return 0;
+out_error:
+	p9_client_clunk(file->private_data);
+	file->private_data = NULL;
+	return err;
+}
+
+/**
+ * v9fs_file_lock - lock a file (or directory)
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ * Bugs: this looks like a local only lock, we should extend into 9P
+ *       by using open exclusive
+ */
+
+static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	int res = 0;
+	struct inode *inode = file_inode(filp);
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		return -ENOLCK;
+
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+		filemap_write_and_wait(inode->i_mapping);
+		invalidate_mapping_pages(&inode->i_data, 0, -1);
+	}
+
+	return res;
+}
+
+static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	struct p9_flock flock;
+	struct p9_fid *fid;
+	uint8_t status;
+	int res = 0;
+	unsigned char fl_type;
+
+	fid = filp->private_data;
+	BUG_ON(fid == NULL);
+
+	if ((fl->fl_flags & FL_POSIX) != FL_POSIX)
+		BUG();
+
+	res = posix_lock_file_wait(filp, fl);
+	if (res < 0)
+		goto out;
+
+	/* convert posix lock to p9 tlock args */
+	memset(&flock, 0, sizeof(flock));
+	/* map the lock type */
+	switch (fl->fl_type) {
+	case F_RDLCK:
+		flock.type = P9_LOCK_TYPE_RDLCK;
+		break;
+	case F_WRLCK:
+		flock.type = P9_LOCK_TYPE_WRLCK;
+		break;
+	case F_UNLCK:
+		flock.type = P9_LOCK_TYPE_UNLCK;
+		break;
+	}
+	flock.start = fl->fl_start;
+	if (fl->fl_end == OFFSET_MAX)
+		flock.length = 0;
+	else
+		flock.length = fl->fl_end - fl->fl_start + 1;
+	flock.proc_id = fl->fl_pid;
+	flock.client_id = utsname()->nodename;
+	if (IS_SETLKW(cmd))
+		flock.flags = P9_LOCK_FLAGS_BLOCK;
+
+	/*
+	 * if its a blocked request and we get P9_LOCK_BLOCKED as the status
+	 * for lock request, keep on trying
+	 */
+	for (;;) {
+		res = p9_client_lock_dotl(fid, &flock, &status);
+		if (res < 0)
+			break;
+
+		if (status != P9_LOCK_BLOCKED)
+			break;
+		if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
+			break;
+		if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
+			break;
+	}
+
+	/* map 9p status to VFS status */
+	switch (status) {
+	case P9_LOCK_SUCCESS:
+		res = 0;
+		break;
+	case P9_LOCK_BLOCKED:
+		res = -EAGAIN;
+		break;
+	case P9_LOCK_ERROR:
+	case P9_LOCK_GRACE:
+		res = -ENOLCK;
+		break;
+	default:
+		BUG();
+	}
+
+	/*
+	 * incase server returned error for lock request, revert
+	 * it locally
+	 */
+	if (res < 0 && fl->fl_type != F_UNLCK) {
+		fl_type = fl->fl_type;
+		fl->fl_type = F_UNLCK;
+		res = posix_lock_file_wait(filp, fl);
+		fl->fl_type = fl_type;
+	}
+out:
+	return res;
+}
+
+static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
+{
+	struct p9_getlock glock;
+	struct p9_fid *fid;
+	int res = 0;
+
+	fid = filp->private_data;
+	BUG_ON(fid == NULL);
+
+	posix_test_lock(filp, fl);
+	/*
+	 * if we have a conflicting lock locally, no need to validate
+	 * with server
+	 */
+	if (fl->fl_type != F_UNLCK)
+		return res;
+
+	/* convert posix lock to p9 tgetlock args */
+	memset(&glock, 0, sizeof(glock));
+	glock.type  = P9_LOCK_TYPE_UNLCK;
+	glock.start = fl->fl_start;
+	if (fl->fl_end == OFFSET_MAX)
+		glock.length = 0;
+	else
+		glock.length = fl->fl_end - fl->fl_start + 1;
+	glock.proc_id = fl->fl_pid;
+	glock.client_id = utsname()->nodename;
+
+	res = p9_client_getlock_dotl(fid, &glock);
+	if (res < 0)
+		return res;
+	/* map 9p lock type to os lock type */
+	switch (glock.type) {
+	case P9_LOCK_TYPE_RDLCK:
+		fl->fl_type = F_RDLCK;
+		break;
+	case P9_LOCK_TYPE_WRLCK:
+		fl->fl_type = F_WRLCK;
+		break;
+	case P9_LOCK_TYPE_UNLCK:
+		fl->fl_type = F_UNLCK;
+		break;
+	}
+	if (glock.type != P9_LOCK_TYPE_UNLCK) {
+		fl->fl_start = glock.start;
+		if (glock.length == 0)
+			fl->fl_end = OFFSET_MAX;
+		else
+			fl->fl_end = glock.start + glock.length - 1;
+		fl->fl_pid = glock.proc_id;
+	}
+	return res;
+}
+
+/**
+ * v9fs_file_lock_dotl - lock a file (or directory)
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ */
+
+static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
+{
+	struct inode *inode = file_inode(filp);
+	int ret = -ENOLCK;
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
+		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		goto out_err;
+
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+		filemap_write_and_wait(inode->i_mapping);
+		invalidate_mapping_pages(&inode->i_data, 0, -1);
+	}
+
+	if (IS_SETLK(cmd) || IS_SETLKW(cmd))
+		ret = v9fs_file_do_lock(filp, cmd, fl);
+	else if (IS_GETLK(cmd))
+		ret = v9fs_file_getlock(filp, fl);
+	else
+		ret = -EINVAL;
+out_err:
+	return ret;
+}
+
+/**
+ * v9fs_file_flock_dotl - lock a file
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ */
+
+static int v9fs_file_flock_dotl(struct file *filp, int cmd,
+	struct file_lock *fl)
+{
+	struct inode *inode = file_inode(filp);
+	int ret = -ENOLCK;
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
+		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		goto out_err;
+
+	if (!(fl->fl_flags & FL_FLOCK))
+		goto out_err;
+
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+		filemap_write_and_wait(inode->i_mapping);
+		invalidate_mapping_pages(&inode->i_data, 0, -1);
+	}
+	/* Convert flock to posix lock */
+	fl->fl_owner = (fl_owner_t)filp;
+	fl->fl_start = 0;
+	fl->fl_end = OFFSET_MAX;
+	fl->fl_flags |= FL_POSIX;
+	fl->fl_flags ^= FL_FLOCK;
+
+	if (IS_SETLK(cmd) | IS_SETLKW(cmd))
+		ret = v9fs_file_do_lock(filp, cmd, fl);
+	else
+		ret = -EINVAL;
+out_err:
+	return ret;
+}
+
+/**
+ * v9fs_fid_readn - read from a fid
+ * @fid: fid to read
+ * @data: data buffer to read data into
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+ssize_t
+v9fs_fid_readn(struct p9_fid *fid, char *data, char __user *udata, u32 count,
+	       u64 offset)
+{
+	int n, total, size;
+
+	p9_debug(P9_DEBUG_VFS, "fid %d offset %llu count %d\n",
+		 fid->fid, (long long unsigned)offset, count);
+	n = 0;
+	total = 0;
+	size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
+	do {
+		n = p9_client_read(fid, data, udata, offset, count);
+		if (n <= 0)
+			break;
+
+		if (data)
+			data += n;
+		if (udata)
+			udata += n;
+
+		offset += n;
+		count -= n;
+		total += n;
+	} while (count > 0 && n == size);
+
+	if (n < 0)
+		total = n;
+
+	return total;
+}
+
+/**
+ * v9fs_file_readn - read from a file
+ * @filp: file pointer to read
+ * @data: data buffer to read data into
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+ssize_t
+v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
+	       u64 offset)
+{
+	return v9fs_fid_readn(filp->private_data, data, udata, count, offset);
+}
+
+/**
+ * v9fs_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+
+static ssize_t
+v9fs_file_read(struct file *filp, char __user *udata, size_t count,
+	       loff_t * offset)
+{
+	int ret;
+	struct p9_fid *fid;
+	size_t size;
+
+	p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", count, *offset);
+	fid = filp->private_data;
+
+	size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
+	if (count > size)
+		ret = v9fs_file_readn(filp, NULL, udata, count, *offset);
+	else
+		ret = p9_client_read(fid, NULL, udata, *offset, count);
+
+	if (ret > 0)
+		*offset += ret;
+
+	return ret;
+}
+
+ssize_t
+v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid,
+			 const char __user *data, size_t count,
+			 loff_t *offset, int invalidate)
+{
+	int n;
+	loff_t i_size;
+	size_t total = 0;
+	struct p9_client *clnt;
+	loff_t origin = *offset;
+	unsigned long pg_start, pg_end;
+
+	p9_debug(P9_DEBUG_VFS, "data %p count %d offset %x\n",
+		 data, (int)count, (int)*offset);
+
+	clnt = fid->clnt;
+	do {
+		n = p9_client_write(fid, NULL, data+total, origin+total, count);
+		if (n <= 0)
+			break;
+		count -= n;
+		total += n;
+	} while (count > 0);
+
+	if (invalidate && (total > 0)) {
+		pg_start = origin >> PAGE_CACHE_SHIFT;
+		pg_end = (origin + total - 1) >> PAGE_CACHE_SHIFT;
+		if (inode->i_mapping && inode->i_mapping->nrpages)
+			invalidate_inode_pages2_range(inode->i_mapping,
+						      pg_start, pg_end);
+		*offset += total;
+		i_size = i_size_read(inode);
+		if (*offset > i_size) {
+			inode_add_bytes(inode, *offset - i_size);
+			i_size_write(inode, *offset);
+		}
+	}
+	if (n < 0)
+		return n;
+
+	return total;
+}
+
+/**
+ * v9fs_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_file_write(struct file *filp, const char __user * data,
+		size_t count, loff_t *offset)
+{
+	ssize_t retval = 0;
+	loff_t origin = *offset;
+
+
+	retval = generic_write_checks(filp, &origin, &count, 0);
+	if (retval)
+		goto out;
+
+	retval = -EINVAL;
+	if ((ssize_t) count < 0)
+		goto out;
+	retval = 0;
+	if (!count)
+		goto out;
+
+	retval = v9fs_file_write_internal(file_inode(filp),
+					filp->private_data,
+					data, count, &origin, 1);
+	/* update offset on successful write */
+	if (retval > 0)
+		*offset = origin;
+out:
+	return retval;
+}
+
+
+static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
+			   int datasync)
+{
+	struct p9_fid *fid;
+	struct inode *inode = filp->f_mapping->host;
+	struct p9_wstat wstat;
+	int retval;
+
+	retval = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (retval)
+		return retval;
+
+	mutex_lock(&inode->i_mutex);
+	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+	fid = filp->private_data;
+	v9fs_blank_wstat(&wstat);
+
+	retval = p9_client_wstat(fid, &wstat);
+	mutex_unlock(&inode->i_mutex);
+
+	return retval;
+}
+
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+			 int datasync)
+{
+	struct p9_fid *fid;
+	struct inode *inode = filp->f_mapping->host;
+	int retval;
+
+	retval = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (retval)
+		return retval;
+
+	mutex_lock(&inode->i_mutex);
+	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+	fid = filp->private_data;
+
+	retval = p9_client_fsync(fid, datasync);
+	mutex_unlock(&inode->i_mutex);
+
+	return retval;
+}
+
+static int
+v9fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int retval;
+
+	retval = generic_file_mmap(file, vma);
+	if (!retval)
+		vma->vm_ops = &v9fs_file_vm_ops;
+
+	return retval;
+}
+
+static int
+v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct v9fs_inode *v9inode;
+	struct page *page = vmf->page;
+	struct file *filp = vma->vm_file;
+	struct inode *inode = file_inode(filp);
+
+
+	p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
+		 page, (unsigned long)filp->private_data);
+
+	/* Update file times before taking page lock */
+	file_update_time(filp);
+
+	v9inode = V9FS_I(inode);
+	/* make sure the cache has finished storing the page */
+	v9fs_fscache_wait_on_page_write(inode, page);
+	BUG_ON(!v9inode->writeback_fid);
+	lock_page(page);
+	if (page->mapping != inode->i_mapping)
+		goto out_unlock;
+	wait_for_stable_page(page);
+
+	return VM_FAULT_LOCKED;
+out_unlock:
+	unlock_page(page);
+	return VM_FAULT_NOPAGE;
+}
+
+static ssize_t
+v9fs_direct_read(struct file *filp, char __user *udata, size_t count,
+		 loff_t *offsetp)
+{
+	loff_t size, offset;
+	struct inode *inode;
+	struct address_space *mapping;
+
+	offset = *offsetp;
+	mapping = filp->f_mapping;
+	inode = mapping->host;
+	if (!count)
+		return 0;
+	size = i_size_read(inode);
+	if (offset < size)
+		filemap_write_and_wait_range(mapping, offset,
+					     offset + count - 1);
+
+	return v9fs_file_read(filp, udata, count, offsetp);
+}
+
+/**
+ * v9fs_cached_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+static ssize_t
+v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
+		      loff_t *offset)
+{
+	if (filp->f_flags & O_DIRECT)
+		return v9fs_direct_read(filp, data, count, offset);
+	return do_sync_read(filp, data, count, offset);
+}
+
+static ssize_t
+v9fs_direct_write(struct file *filp, const char __user * data,
+		  size_t count, loff_t *offsetp)
+{
+	loff_t offset;
+	ssize_t retval;
+	struct inode *inode;
+	struct address_space *mapping;
+
+	offset = *offsetp;
+	mapping = filp->f_mapping;
+	inode = mapping->host;
+	if (!count)
+		return 0;
+
+	mutex_lock(&inode->i_mutex);
+	retval = filemap_write_and_wait_range(mapping, offset,
+					      offset + count - 1);
+	if (retval)
+		goto err_out;
+	/*
+	 * After a write we want buffered reads to be sure to go to disk to get
+	 * the new data.  We invalidate clean cached page from the region we're
+	 * about to write.  We do this *before* the write so that if we fail
+	 * here we fall back to buffered write
+	 */
+	if (mapping->nrpages) {
+		pgoff_t pg_start = offset >> PAGE_CACHE_SHIFT;
+		pgoff_t pg_end   = (offset + count - 1) >> PAGE_CACHE_SHIFT;
+
+		retval = invalidate_inode_pages2_range(mapping,
+							pg_start, pg_end);
+		/*
+		 * If a page can not be invalidated, fall back
+		 * to buffered write.
+		 */
+		if (retval) {
+			if (retval == -EBUSY)
+				goto buff_write;
+			goto err_out;
+		}
+	}
+	retval = v9fs_file_write(filp, data, count, offsetp);
+err_out:
+	mutex_unlock(&inode->i_mutex);
+	return retval;
+
+buff_write:
+	mutex_unlock(&inode->i_mutex);
+	return do_sync_write(filp, data, count, offsetp);
+}
+
+/**
+ * v9fs_cached_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_cached_file_write(struct file *filp, const char __user * data,
+		       size_t count, loff_t *offset)
+{
+
+	if (filp->f_flags & O_DIRECT)
+		return v9fs_direct_write(filp, data, count, offset);
+	return do_sync_write(filp, data, count, offset);
+}
+
+static const struct vm_operations_struct v9fs_file_vm_ops = {
+	.fault = filemap_fault,
+	.page_mkwrite = v9fs_vm_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
+};
+
+
+const struct file_operations v9fs_cached_file_operations = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_cached_file_read,
+	.write = v9fs_cached_file_write,
+	.aio_read = generic_file_aio_read,
+	.aio_write = generic_file_aio_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = v9fs_file_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_cached_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_cached_file_read,
+	.write = v9fs_cached_file_write,
+	.aio_read = generic_file_aio_read,
+	.aio_write = generic_file_aio_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = v9fs_file_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};
+
+const struct file_operations v9fs_file_operations = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_file_read,
+	.write = v9fs_file_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = generic_file_readonly_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_file_read,
+	.write = v9fs_file_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = generic_file_readonly_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};

addons/9p/src/3.10.108/vfs_super.c

@@ -0,0 +1,368 @@
+/*
+ *  linux/fs/9p/vfs_super.c
+ *
+ * This file contians superblock ops for 9P2000. It is intended that
+ * you mount this file system on directories.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/magic.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "xattr.h"
+#include "acl.h"
+
+static const struct super_operations v9fs_super_ops, v9fs_super_ops_dotl;
+
+/**
+ * v9fs_set_super - set the superblock
+ * @s: super block
+ * @data: file system specific data
+ *
+ */
+
+static int v9fs_set_super(struct super_block *s, void *data)
+{
+	s->s_fs_info = data;
+	return set_anon_super(s, data);
+}
+
+/**
+ * v9fs_fill_super - populate superblock with info
+ * @sb: superblock
+ * @v9ses: session information
+ * @flags: flags propagated from v9fs_mount()
+ *
+ */
+
+static void
+v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
+		int flags, void *data)
+{
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
+	sb->s_blocksize = 1 << sb->s_blocksize_bits;
+	sb->s_magic = V9FS_MAGIC;
+	if (v9fs_proto_dotl(v9ses)) {
+		sb->s_op = &v9fs_super_ops_dotl;
+		sb->s_xattr = v9fs_xattr_handlers;
+	} else
+		sb->s_op = &v9fs_super_ops;
+	sb->s_bdi = &v9ses->bdi;
+	if (v9ses->cache)
+		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE;
+
+	sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
+	if (!v9ses->cache)
+		sb->s_flags |= MS_SYNCHRONOUS;
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+	if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL)
+		sb->s_flags |= MS_POSIXACL;
+#endif
+
+	save_mount_options(sb, data);
+}
+
+/**
+ * v9fs_mount - mount a superblock
+ * @fs_type: file system type
+ * @flags: mount flags
+ * @dev_name: device name that was mounted
+ * @data: mount options
+ *
+ */
+
+static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data)
+{
+	struct super_block *sb = NULL;
+	struct inode *inode = NULL;
+	struct dentry *root = NULL;
+	struct v9fs_session_info *v9ses = NULL;
+	umode_t mode = S_IRWXUGO | S_ISVTX;
+	struct p9_fid *fid;
+	int retval = 0;
+
+	p9_debug(P9_DEBUG_VFS, "\n");
+
+	v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
+	if (!v9ses)
+		return ERR_PTR(-ENOMEM);
+
+	fid = v9fs_session_init(v9ses, dev_name, data);
+	if (IS_ERR(fid)) {
+		retval = PTR_ERR(fid);
+		/*
+		 * we need to call session_close to tear down some
+		 * of the data structure setup by session_init
+		 */
+		goto close_session;
+	}
+
+	sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
+	if (IS_ERR(sb)) {
+		retval = PTR_ERR(sb);
+		goto clunk_fid;
+	}
+	v9fs_fill_super(sb, v9ses, flags, data);
+
+	if (v9ses->cache)
+		sb->s_d_op = &v9fs_cached_dentry_operations;
+	else
+		sb->s_d_op = &v9fs_dentry_operations;
+
+	inode = v9fs_get_inode(sb, S_IFDIR | mode, 0);
+	if (IS_ERR(inode)) {
+		retval = PTR_ERR(inode);
+		goto release_sb;
+	}
+
+	root = d_make_root(inode);
+	if (!root) {
+		retval = -ENOMEM;
+		goto release_sb;
+	}
+	sb->s_root = root;
+	if (v9fs_proto_dotl(v9ses)) {
+		struct p9_stat_dotl *st = NULL;
+		st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
+		if (IS_ERR(st)) {
+			retval = PTR_ERR(st);
+			goto release_sb;
+		}
+		root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+		v9fs_stat2inode_dotl(st, root->d_inode);
+		kfree(st);
+	} else {
+		struct p9_wstat *st = NULL;
+		st = p9_client_stat(fid);
+		if (IS_ERR(st)) {
+			retval = PTR_ERR(st);
+			goto release_sb;
+		}
+
+		root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+		v9fs_stat2inode(st, root->d_inode, sb);
+
+		p9stat_free(st);
+		kfree(st);
+	}
+	retval = v9fs_get_acl(inode, fid);
+	if (retval)
+		goto release_sb;
+	v9fs_fid_add(root, fid);
+
+	p9_debug(P9_DEBUG_VFS, " simple set mount, return 0\n");
+	return dget(sb->s_root);
+
+clunk_fid:
+	p9_client_clunk(fid);
+close_session:
+	v9fs_session_close(v9ses);
+	kfree(v9ses);
+	return ERR_PTR(retval);
+
+release_sb:
+	/*
+	 * we will do the session_close and root dentry release
+	 * in the below call. But we need to clunk fid, because we haven't
+	 * attached the fid to dentry so it won't get clunked
+	 * automatically.
+	 */
+	p9_client_clunk(fid);
+	deactivate_locked_super(sb);
+	return ERR_PTR(retval);
+}
+
+/**
+ * v9fs_kill_super - Kill Superblock
+ * @s: superblock
+ *
+ */
+
+static void v9fs_kill_super(struct super_block *s)
+{
+	struct v9fs_session_info *v9ses = s->s_fs_info;
+
+	p9_debug(P9_DEBUG_VFS, " %p\n", s);
+
+	kill_anon_super(s);
+
+	v9fs_session_cancel(v9ses);
+	v9fs_session_close(v9ses);
+	kfree(v9ses);
+	s->s_fs_info = NULL;
+	p9_debug(P9_DEBUG_VFS, "exiting kill_super\n");
+}
+
+static void
+v9fs_umount_begin(struct super_block *sb)
+{
+	struct v9fs_session_info *v9ses;
+
+	v9ses = sb->s_fs_info;
+	v9fs_session_begin_cancel(v9ses);
+}
+
+static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
+	struct p9_rstatfs rs;
+	int res;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid)) {
+		res = PTR_ERR(fid);
+		goto done;
+	}
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	if (v9fs_proto_dotl(v9ses)) {
+		res = p9_client_statfs(fid, &rs);
+		if (res == 0) {
+			buf->f_type = rs.type;
+			buf->f_bsize = rs.bsize;
+			buf->f_blocks = rs.blocks;
+			buf->f_bfree = rs.bfree;
+			buf->f_bavail = rs.bavail;
+			buf->f_files = rs.files;
+			buf->f_ffree = rs.ffree;
+			buf->f_fsid.val[0] = rs.fsid & 0xFFFFFFFFUL;
+			buf->f_fsid.val[1] = (rs.fsid >> 32) & 0xFFFFFFFFUL;
+			buf->f_namelen = rs.namelen;
+		}
+		if (res != -ENOSYS)
+			goto done;
+	}
+	res = simple_statfs(dentry, buf);
+done:
+	return res;
+}
+
+static int v9fs_drop_inode(struct inode *inode)
+{
+	struct v9fs_session_info *v9ses;
+	v9ses = v9fs_inode2v9ses(inode);
+	if (v9ses->cache)
+		return generic_drop_inode(inode);
+	/*
+	 * in case of non cached mode always drop the
+	 * the inode because we want the inode attribute
+	 * to always match that on the server.
+	 */
+	return 1;
+}
+
+static int v9fs_write_inode(struct inode *inode,
+			    struct writeback_control *wbc)
+{
+	int ret;
+	struct p9_wstat wstat;
+	struct v9fs_inode *v9inode;
+	/*
+	 * send an fsync request to server irrespective of
+	 * wbc->sync_mode.
+	 */
+	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
+	v9inode = V9FS_I(inode);
+	if (!v9inode->writeback_fid)
+		return 0;
+	v9fs_blank_wstat(&wstat);
+
+	ret = p9_client_wstat(v9inode->writeback_fid, &wstat);
+	if (ret < 0) {
+		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		return ret;
+	}
+	return 0;
+}
+
+static int v9fs_write_inode_dotl(struct inode *inode,
+				 struct writeback_control *wbc)
+{
+	int ret;
+	struct v9fs_inode *v9inode;
+	/*
+	 * send an fsync request to server irrespective of
+	 * wbc->sync_mode.
+	 */
+	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
+	v9inode = V9FS_I(inode);
+	if (!v9inode->writeback_fid)
+		return 0;
+	ret = p9_client_fsync(v9inode->writeback_fid, 0);
+	if (ret < 0) {
+		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		return ret;
+	}
+	return 0;
+}
+
+static const struct super_operations v9fs_super_ops = {
+	.alloc_inode = v9fs_alloc_inode,
+	.destroy_inode = v9fs_destroy_inode,
+	.statfs = simple_statfs,
+	.evict_inode = v9fs_evict_inode,
+	.show_options = generic_show_options,
+	.umount_begin = v9fs_umount_begin,
+	.write_inode = v9fs_write_inode,
+};
+
+static const struct super_operations v9fs_super_ops_dotl = {
+	.alloc_inode = v9fs_alloc_inode,
+	.destroy_inode = v9fs_destroy_inode,
+	.statfs = v9fs_statfs,
+	.drop_inode = v9fs_drop_inode,
+	.evict_inode = v9fs_evict_inode,
+	.show_options = generic_show_options,
+	.umount_begin = v9fs_umount_begin,
+	.write_inode = v9fs_write_inode_dotl,
+};
+
+struct file_system_type v9fs_fs_type = {
+	.name = "9p",
+	.mount = v9fs_mount,
+	.kill_sb = v9fs_kill_super,
+	.owner = THIS_MODULE,
+	.fs_flags = FS_RENAME_DOES_D_MOVE,
+};
+MODULE_ALIAS_FS("9p");

addons/9p/src/3.10.108/xattr.c

@@ -0,0 +1,175 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "fid.h"
+#include "xattr.h"
+
+ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
+			   void *buffer, size_t buffer_size)
+{
+	ssize_t retval;
+	int msize, read_count;
+	u64 offset = 0, attr_size;
+	struct p9_fid *attr_fid;
+
+	attr_fid = p9_client_xattrwalk(fid, name, &attr_size);
+	if (IS_ERR(attr_fid)) {
+		retval = PTR_ERR(attr_fid);
+		p9_debug(P9_DEBUG_VFS, "p9_client_attrwalk failed %zd\n",
+			 retval);
+		attr_fid = NULL;
+		goto error;
+	}
+	if (!buffer_size) {
+		/* request to get the attr_size */
+		retval = attr_size;
+		goto error;
+	}
+	if (attr_size > buffer_size) {
+		retval = -ERANGE;
+		goto error;
+	}
+	msize = attr_fid->clnt->msize;
+	while (attr_size) {
+		if (attr_size > (msize - P9_IOHDRSZ))
+			read_count = msize - P9_IOHDRSZ;
+		else
+			read_count = attr_size;
+		read_count = p9_client_read(attr_fid, ((char *)buffer)+offset,
+					NULL, offset, read_count);
+		if (read_count < 0) {
+			/* error in xattr read */
+			retval = read_count;
+			goto error;
+		}
+		offset += read_count;
+		attr_size -= read_count;
+	}
+	/* Total read xattr bytes */
+	retval = offset;
+error:
+	if (attr_fid)
+		p9_client_clunk(attr_fid);
+	return retval;
+
+}
+
+
+/*
+ * v9fs_xattr_get()
+ *
+ * Copy an extended attribute into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
+		       void *buffer, size_t buffer_size)
+{
+	struct p9_fid *fid;
+
+	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n",
+		 name, buffer_size);
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+
+	return v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
+}
+
+/*
+ * v9fs_xattr_set()
+ *
+ * Create, replace or remove an extended attribute for this inode. Buffer
+ * is NULL to remove an existing extended attribute, and non-NULL to
+ * either replace an existing extended attribute, or create a new extended
+ * attribute. The flags XATTR_REPLACE and XATTR_CREATE
+ * specify that an extended attribute must exist and must not exist
+ * previous to the call, respectively.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int v9fs_xattr_set(struct dentry *dentry, const char *name,
+		   const void *value, size_t value_len, int flags)
+{
+	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+	return v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+}
+
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+		   const void *value, size_t value_len, int flags)
+{
+	u64 offset = 0;
+	int retval, msize, write_count;
+
+	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
+		 name, value_len, flags);
+
+	/* Clone it */
+	fid = p9_client_walk(fid, 0, NULL, 1);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+
+	/*
+	 * On success fid points to xattr
+	 */
+	retval = p9_client_xattrcreate(fid, name, value_len, flags);
+	if (retval < 0) {
+		p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n",
+			 retval);
+		p9_client_clunk(fid);
+		return retval;
+	}
+	msize = fid->clnt->msize;
+	while (value_len) {
+		if (value_len > (msize - P9_IOHDRSZ))
+			write_count = msize - P9_IOHDRSZ;
+		else
+			write_count = value_len;
+		write_count = p9_client_write(fid, ((char *)value)+offset,
+					NULL, offset, write_count);
+		if (write_count < 0) {
+			/* error in xattr write */
+			retval = write_count;
+			break;
+		}
+		offset += write_count;
+		value_len -= write_count;
+	}
+	return p9_client_clunk(fid);
+}
+
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	return v9fs_xattr_get(dentry, NULL, buffer, buffer_size);
+}
+
+const struct xattr_handler *v9fs_xattr_handlers[] = {
+	&v9fs_xattr_user_handler,
+#ifdef CONFIG_9P_FS_POSIX_ACL
+	&v9fs_xattr_acl_access_handler,
+	&v9fs_xattr_acl_default_handler,
+#endif
+	NULL
+};

addons/9p/src/3.10.108/xattr.h

@@ -0,0 +1,35 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+#ifndef FS_9P_XATTR_H
+#define FS_9P_XATTR_H
+
+#include <linux/xattr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+extern const struct xattr_handler *v9fs_xattr_handlers[];
+extern struct xattr_handler v9fs_xattr_user_handler;
+extern const struct xattr_handler v9fs_xattr_acl_access_handler;
+extern const struct xattr_handler v9fs_xattr_acl_default_handler;
+
+extern ssize_t v9fs_fid_xattr_get(struct p9_fid *, const char *,
+				  void *, size_t);
+extern ssize_t v9fs_xattr_get(struct dentry *, const char *,
+			      void *, size_t);
+extern int v9fs_fid_xattr_set(struct p9_fid *, const char *,
+			  const void *, size_t, int);
+extern int v9fs_xattr_set(struct dentry *, const char *,
+			  const void *, size_t, int);
+extern ssize_t v9fs_listxattr(struct dentry *, char *, size_t);
+#endif /* FS_9P_XATTR_H */

addons/9p/src/3.10.108/xattr_user.c

@@ -0,0 +1,80 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include "xattr.h"
+
+static int v9fs_xattr_user_get(struct dentry *dentry, const char *name,
+			void *buffer, size_t size, int type)
+{
+	int retval;
+	char *full_name;
+	size_t name_len;
+	size_t prefix_len = XATTR_USER_PREFIX_LEN;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+
+	name_len = strlen(name);
+	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+	if (!full_name)
+		return -ENOMEM;
+	memcpy(full_name, XATTR_USER_PREFIX, prefix_len);
+	memcpy(full_name+prefix_len, name, name_len);
+	full_name[prefix_len + name_len] = '\0';
+
+	retval = v9fs_xattr_get(dentry, full_name, buffer, size);
+	kfree(full_name);
+	return retval;
+}
+
+static int v9fs_xattr_user_set(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags, int type)
+{
+	int retval;
+	char *full_name;
+	size_t name_len;
+	size_t prefix_len = XATTR_USER_PREFIX_LEN;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+
+	name_len = strlen(name);
+	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+	if (!full_name)
+		return -ENOMEM;
+	memcpy(full_name, XATTR_USER_PREFIX, prefix_len);
+	memcpy(full_name + prefix_len, name, name_len);
+	full_name[prefix_len + name_len] = '\0';
+
+	retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
+	kfree(full_name);
+	return retval;
+}
+
+struct xattr_handler v9fs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.get	= v9fs_xattr_user_get,
+	.set	= v9fs_xattr_user_set,
+};

addons/9p/src/4.4.180/Makefile

@@ -0,0 +1,35 @@
+obj-m := 9p.o
+
+9p-objs := \
+	vfs_super.o \
+	vfs_inode.o \
+	vfs_inode_dotl.o \
+	vfs_addr.o \
+	vfs_file.o \
+	vfs_dir.o \
+	vfs_dentry.o \
+	v9fs.o \
+	fid.o  \
+	xattr.o
+
+9p-y += cache.o
+9p-n += acl.o
+
+obj-m := 9pnet.o
+obj-m += 9pnet_virtio.o
+obj-n += 9pnet_rdma.o
+
+9pnet-objs := \
+        mod.o \
+        client.o \
+        error.o \
+        util.o \
+        protocol.o \
+        trans_fd.o \
+        trans_common.o \
+
+9pnet_virtio-objs := \
+        trans_virtio.o
+
+9pnet_rdma-objs := \
+        trans_rdma.o

addons/9p/src/4.4.180/acl.c

@@ -0,0 +1,338 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/posix_acl_xattr.h>
+#include "xattr.h"
+#include "acl.h"
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name)
+{
+	ssize_t size;
+	void *value = NULL;
+	struct posix_acl *acl = NULL;
+
+	size = v9fs_fid_xattr_get(fid, name, NULL, 0);
+	if (size > 0) {
+		value = kzalloc(size, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		size = v9fs_fid_xattr_get(fid, name, value, size);
+		if (size > 0) {
+			acl = posix_acl_from_xattr(&init_user_ns, value, size);
+			if (IS_ERR(acl))
+				goto err_out;
+		}
+	} else if (size == -ENODATA || size == 0 ||
+		   size == -ENOSYS || size == -EOPNOTSUPP) {
+		acl = NULL;
+	} else
+		acl = ERR_PTR(-EIO);
+
+err_out:
+	kfree(value);
+	return acl;
+}
+
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+	int retval = 0;
+	struct posix_acl *pacl, *dacl;
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+			((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
+		set_cached_acl(inode, ACL_TYPE_DEFAULT, NULL);
+		set_cached_acl(inode, ACL_TYPE_ACCESS, NULL);
+		return 0;
+	}
+	/* get the default/access acl values and cache them */
+	dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT);
+	pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS);
+
+	if (!IS_ERR(dacl) && !IS_ERR(pacl)) {
+		set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+		set_cached_acl(inode, ACL_TYPE_ACCESS, pacl);
+	} else
+		retval = -EIO;
+
+	if (!IS_ERR(dacl))
+		posix_acl_release(dacl);
+
+	if (!IS_ERR(pacl))
+		posix_acl_release(pacl);
+
+	return retval;
+}
+
+static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type)
+{
+	struct posix_acl *acl;
+	/*
+	 * 9p Always cache the acl value when
+	 * instantiating the inode (v9fs_inode_from_fid)
+	 */
+	acl = get_cached_acl(inode, type);
+	BUG_ON(acl == ACL_NOT_CACHED);
+	return acl;
+}
+
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type)
+{
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+			((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
+		/*
+		 * On access = client  and acl = on mode get the acl
+		 * values from the server
+		 */
+		return NULL;
+	}
+	return v9fs_get_cached_acl(inode, type);
+
+}
+
+static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
+{
+	int retval;
+	char *name;
+	size_t size;
+	void *buffer;
+	if (!acl)
+		return 0;
+
+	/* Set a setxattr request to server */
+	size = posix_acl_xattr_size(acl->a_count);
+	buffer = kmalloc(size, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+	retval = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+	if (retval < 0)
+		goto err_free_out;
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	retval = v9fs_fid_xattr_set(fid, name, buffer, size, 0);
+err_free_out:
+	kfree(buffer);
+	return retval;
+}
+
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+	int retval = 0;
+	struct posix_acl *acl;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	acl = v9fs_get_cached_acl(inode, ACL_TYPE_ACCESS);
+	if (acl) {
+		retval = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+		if (retval)
+			return retval;
+		set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+		retval = v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
+		posix_acl_release(acl);
+	}
+	return retval;
+}
+
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+			struct posix_acl *dacl, struct posix_acl *acl)
+{
+	set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+	set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+	v9fs_set_acl(fid, ACL_TYPE_DEFAULT, dacl);
+	v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
+	return 0;
+}
+
+void v9fs_put_acl(struct posix_acl *dacl,
+		  struct posix_acl *acl)
+{
+	posix_acl_release(dacl);
+	posix_acl_release(acl);
+}
+
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+		  struct posix_acl **dpacl, struct posix_acl **pacl)
+{
+	int retval = 0;
+	umode_t mode = *modep;
+	struct posix_acl *acl = NULL;
+
+	if (!S_ISLNK(mode)) {
+		acl = v9fs_get_cached_acl(dir, ACL_TYPE_DEFAULT);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		if (!acl)
+			mode &= ~current_umask();
+	}
+	if (acl) {
+		if (S_ISDIR(mode))
+			*dpacl = posix_acl_dup(acl);
+		retval = __posix_acl_create(&acl, GFP_NOFS, &mode);
+		if (retval < 0)
+			return retval;
+		if (retval > 0)
+			*pacl = acl;
+		else
+			posix_acl_release(acl);
+	}
+	*modep  = mode;
+	return 0;
+}
+
+static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
+			      struct dentry *dentry, const char *name,
+			      void *buffer, size_t size)
+{
+	struct v9fs_session_info *v9ses;
+	struct posix_acl *acl;
+	int error;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	/*
+	 * We allow set/get/list of acl when access=client is not specified
+	 */
+	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
+		return v9fs_xattr_get(dentry, handler->prefix, buffer, size);
+
+	acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+	error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+	posix_acl_release(acl);
+
+	return error;
+}
+
+static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
+			      struct dentry *dentry, const char *name,
+			      const void *value, size_t size, int flags)
+{
+	int retval;
+	struct posix_acl *acl;
+	struct v9fs_session_info *v9ses;
+	struct inode *inode = d_inode(dentry);
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	/*
+	 * set the attribute on the remote. Without even looking at the
+	 * xattr value. We leave it to the server to validate
+	 */
+	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
+		return v9fs_xattr_set(dentry, handler->prefix, value, size,
+				      flags);
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+	if (value) {
+		/* update the cached acl value */
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		else if (acl) {
+			retval = posix_acl_valid(acl);
+			if (retval)
+				goto err_out;
+		}
+	} else
+		acl = NULL;
+
+	switch (handler->flags) {
+	case ACL_TYPE_ACCESS:
+		if (acl) {
+			struct iattr iattr;
+			struct posix_acl *old_acl = acl;
+
+			retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
+			if (retval)
+				goto err_out;
+			if (!acl) {
+				/*
+				 * ACL can be represented
+				 * by the mode bits. So don't
+				 * update ACL.
+				 */
+				posix_acl_release(old_acl);
+				value = NULL;
+				size = 0;
+			}
+			iattr.ia_valid = ATTR_MODE;
+			/* FIXME should we update ctime ?
+			 * What is the following setxattr update the
+			 * mode ?
+			 */
+			v9fs_vfs_setattr_dotl(dentry, &iattr);
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		if (!S_ISDIR(inode->i_mode)) {
+			retval = acl ? -EINVAL : 0;
+			goto err_out;
+		}
+		break;
+	default:
+		BUG();
+	}
+	retval = v9fs_xattr_set(dentry, handler->prefix, value, size, flags);
+	if (!retval)
+		set_cached_acl(inode, handler->flags, acl);
+err_out:
+	posix_acl_release(acl);
+	return retval;
+}
+
+const struct xattr_handler v9fs_xattr_acl_access_handler = {
+	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.flags	= ACL_TYPE_ACCESS,
+	.get	= v9fs_xattr_get_acl,
+	.set	= v9fs_xattr_set_acl,
+};
+
+const struct xattr_handler v9fs_xattr_acl_default_handler = {
+	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.flags	= ACL_TYPE_DEFAULT,
+	.get	= v9fs_xattr_get_acl,
+	.set	= v9fs_xattr_set_acl,
+};

addons/9p/src/4.4.180/acl.h

@@ -0,0 +1,55 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+#ifndef FS_9P_ACL_H
+#define FS_9P_ACL_H
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+extern int v9fs_get_acl(struct inode *, struct p9_fid *);
+extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type);
+extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
+extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
+			       struct posix_acl *, struct posix_acl *);
+extern int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+			 struct posix_acl **dpacl, struct posix_acl **pacl);
+extern void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
+#else
+#define v9fs_iop_get_acl NULL
+static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+	return 0;
+}
+static inline int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+	return 0;
+}
+static inline int v9fs_set_create_acl(struct inode *inode,
+				      struct p9_fid *fid,
+				      struct posix_acl *dacl,
+				      struct posix_acl *acl)
+{
+	return 0;
+}
+static inline void v9fs_put_acl(struct posix_acl *dacl,
+				struct posix_acl *acl)
+{
+}
+static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+				struct posix_acl **dpacl,
+				struct posix_acl **pacl)
+{
+	return 0;
+}
+
+#endif
+#endif /* FS_9P_XATTR_H */

addons/9p/src/4.4.180/cache.c

@@ -0,0 +1,414 @@
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/jiffies.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+
+#include "v9fs.h"
+#include "cache.h"
+
+#define CACHETAG_LEN  11
+
+struct fscache_netfs v9fs_cache_netfs = {
+	.name 		= "9p",
+	.version 	= 0,
+};
+
+/**
+ * v9fs_random_cachetag - Generate a random tag to be associated
+ *			  with a new cache session.
+ *
+ * The value of jiffies is used for a fairly randomly cache tag.
+ */
+
+static
+int v9fs_random_cachetag(struct v9fs_session_info *v9ses)
+{
+	v9ses->cachetag = kmalloc(CACHETAG_LEN, GFP_KERNEL);
+	if (!v9ses->cachetag)
+		return -ENOMEM;
+
+	return scnprintf(v9ses->cachetag, CACHETAG_LEN, "%lu", jiffies);
+}
+
+static uint16_t v9fs_cache_session_get_key(const void *cookie_netfs_data,
+					   void *buffer, uint16_t bufmax)
+{
+	struct v9fs_session_info *v9ses;
+	uint16_t klen = 0;
+
+	v9ses = (struct v9fs_session_info *)cookie_netfs_data;
+	p9_debug(P9_DEBUG_FSC, "session %p buf %p size %u\n",
+		 v9ses, buffer, bufmax);
+
+	if (v9ses->cachetag)
+		klen = strlen(v9ses->cachetag);
+
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, v9ses->cachetag, klen);
+	p9_debug(P9_DEBUG_FSC, "cache session tag %s\n", v9ses->cachetag);
+	return klen;
+}
+
+const struct fscache_cookie_def v9fs_cache_session_index_def = {
+	.name		= "9P.session",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= v9fs_cache_session_get_key,
+};
+
+void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses)
+{
+	/* If no cache session tag was specified, we generate a random one. */
+	if (!v9ses->cachetag)
+		v9fs_random_cachetag(v9ses);
+
+	v9ses->fscache = fscache_acquire_cookie(v9fs_cache_netfs.primary_index,
+						&v9fs_cache_session_index_def,
+						v9ses, true);
+	p9_debug(P9_DEBUG_FSC, "session %p get cookie %p\n",
+		 v9ses, v9ses->fscache);
+}
+
+void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses)
+{
+	p9_debug(P9_DEBUG_FSC, "session %p put cookie %p\n",
+		 v9ses, v9ses->fscache);
+	fscache_relinquish_cookie(v9ses->fscache, 0);
+	v9ses->fscache = NULL;
+}
+
+
+static uint16_t v9fs_cache_inode_get_key(const void *cookie_netfs_data,
+					 void *buffer, uint16_t bufmax)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	memcpy(buffer, &v9inode->qid.path, sizeof(v9inode->qid.path));
+	p9_debug(P9_DEBUG_FSC, "inode %p get key %llu\n",
+		 &v9inode->vfs_inode, v9inode->qid.path);
+	return sizeof(v9inode->qid.path);
+}
+
+static void v9fs_cache_inode_get_attr(const void *cookie_netfs_data,
+				      uint64_t *size)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	*size = i_size_read(&v9inode->vfs_inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get attr %llu\n",
+		 &v9inode->vfs_inode, *size);
+}
+
+static uint16_t v9fs_cache_inode_get_aux(const void *cookie_netfs_data,
+					 void *buffer, uint16_t buflen)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	memcpy(buffer, &v9inode->qid.version, sizeof(v9inode->qid.version));
+	p9_debug(P9_DEBUG_FSC, "inode %p get aux %u\n",
+		 &v9inode->vfs_inode, v9inode->qid.version);
+	return sizeof(v9inode->qid.version);
+}
+
+static enum
+fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data,
+					    const void *buffer,
+					    uint16_t buflen)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+
+	if (buflen != sizeof(v9inode->qid.version))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	if (memcmp(buffer, &v9inode->qid.version,
+		   sizeof(v9inode->qid.version)))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data)
+{
+	struct v9fs_inode *v9inode = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	for (;;) {
+		nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+const struct fscache_cookie_def v9fs_cache_inode_index_def = {
+	.name		= "9p.inode",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= v9fs_cache_inode_get_key,
+	.get_attr	= v9fs_cache_inode_get_attr,
+	.get_aux	= v9fs_cache_inode_get_aux,
+	.check_aux	= v9fs_cache_inode_check_aux,
+	.now_uncached	= v9fs_cache_inode_now_uncached,
+};
+
+void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode;
+	struct v9fs_session_info *v9ses;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	v9inode = V9FS_I(inode);
+	if (v9inode->fscache)
+		return;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
+						  &v9fs_cache_inode_index_def,
+						  v9inode, true);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
+		 inode, v9inode->fscache);
+}
+
+void v9fs_cache_inode_put_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+	p9_debug(P9_DEBUG_FSC, "inode %p put cookie %p\n",
+		 inode, v9inode->fscache);
+
+	fscache_relinquish_cookie(v9inode->fscache, 0);
+	v9inode->fscache = NULL;
+}
+
+void v9fs_cache_inode_flush_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+	p9_debug(P9_DEBUG_FSC, "inode %p flush cookie %p\n",
+		 inode, v9inode->fscache);
+
+	fscache_relinquish_cookie(v9inode->fscache, 1);
+	v9inode->fscache = NULL;
+}
+
+void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+
+	mutex_lock(&v9inode->fscache_lock);
+
+	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+		v9fs_cache_inode_flush_cookie(inode);
+	else
+		v9fs_cache_inode_get_cookie(inode);
+
+	mutex_unlock(&v9inode->fscache_lock);
+}
+
+void v9fs_cache_inode_reset_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct v9fs_session_info *v9ses;
+	struct fscache_cookie *old;
+
+	if (!v9inode->fscache)
+		return;
+
+	old = v9inode->fscache;
+
+	mutex_lock(&v9inode->fscache_lock);
+	fscache_relinquish_cookie(v9inode->fscache, 1);
+
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
+						  &v9fs_cache_inode_index_def,
+						  v9inode, true);
+	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
+		 inode, old, v9inode->fscache);
+
+	mutex_unlock(&v9inode->fscache_lock);
+}
+
+int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	BUG_ON(!v9inode->fscache);
+
+	return fscache_maybe_release_page(v9inode->fscache, page, gfp);
+}
+
+void __v9fs_fscache_invalidate_page(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	BUG_ON(!v9inode->fscache);
+
+	if (PageFsCache(page)) {
+		fscache_wait_on_page_write(v9inode->fscache, page);
+		BUG_ON(!PageLocked(page));
+		fscache_uncache_page(v9inode->fscache, page);
+	}
+}
+
+static void v9fs_vfs_readpage_complete(struct page *page, void *data,
+				       int error)
+{
+	if (!error)
+		SetPageUptodate(page);
+
+	unlock_page(page);
+}
+
+/**
+ * __v9fs_readpage_from_fscache - read a page from cache
+ *
+ * Returns 0 if the pages are in cache and a BIO is submitted,
+ * 1 if the pages are not in cache and -error otherwise.
+ */
+
+int __v9fs_readpage_from_fscache(struct inode *inode, struct page *page)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	if (!v9inode->fscache)
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_page(v9inode->fscache,
+					 page,
+					 v9fs_vfs_readpage_complete,
+					 NULL,
+					 GFP_KERNEL);
+	switch (ret) {
+	case -ENOBUFS:
+	case -ENODATA:
+		p9_debug(P9_DEBUG_FSC, "page/inode not in cache %d\n", ret);
+		return 1;
+	case 0:
+		p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
+		return ret;
+	default:
+		p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
+		return ret;
+	}
+}
+
+/**
+ * __v9fs_readpages_from_fscache - read multiple pages from cache
+ *
+ * Returns 0 if the pages are in cache and a BIO is submitted,
+ * 1 if the pages are not in cache and -error otherwise.
+ */
+
+int __v9fs_readpages_from_fscache(struct inode *inode,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p pages %u\n", inode, *nr_pages);
+	if (!v9inode->fscache)
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_pages(v9inode->fscache,
+					  mapping, pages, nr_pages,
+					  v9fs_vfs_readpage_complete,
+					  NULL,
+					  mapping_gfp_mask(mapping));
+	switch (ret) {
+	case -ENOBUFS:
+	case -ENODATA:
+		p9_debug(P9_DEBUG_FSC, "pages/inodes not in cache %d\n", ret);
+		return 1;
+	case 0:
+		BUG_ON(!list_empty(pages));
+		BUG_ON(*nr_pages != 0);
+		p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
+		return ret;
+	default:
+		p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
+		return ret;
+	}
+}
+
+/**
+ * __v9fs_readpage_to_fscache - write a page to the cache
+ *
+ */
+
+void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	ret = fscache_write_page(v9inode->fscache, page, GFP_KERNEL);
+	p9_debug(P9_DEBUG_FSC, "ret =  %d\n", ret);
+	if (ret != 0)
+		v9fs_uncache_page(inode, page);
+}
+
+/*
+ * wait for a page to complete writing to the cache
+ */
+void __v9fs_fscache_wait_on_page_write(struct inode *inode, struct page *page)
+{
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	if (PageFsCache(page))
+		fscache_wait_on_page_write(v9inode->fscache, page);
+}

addons/9p/src/4.4.180/cache.h

@@ -0,0 +1,152 @@
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#ifndef _9P_CACHE_H
+#define _9P_CACHE_H
+#ifdef CONFIG_9P_FSCACHE
+#include <linux/fscache.h>
+#include <linux/spinlock.h>
+
+extern struct fscache_netfs v9fs_cache_netfs;
+extern const struct fscache_cookie_def v9fs_cache_session_index_def;
+extern const struct fscache_cookie_def v9fs_cache_inode_index_def;
+
+extern void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses);
+extern void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses);
+
+extern void v9fs_cache_inode_get_cookie(struct inode *inode);
+extern void v9fs_cache_inode_put_cookie(struct inode *inode);
+extern void v9fs_cache_inode_flush_cookie(struct inode *inode);
+extern void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp);
+extern void v9fs_cache_inode_reset_cookie(struct inode *inode);
+
+extern int __v9fs_cache_register(void);
+extern void __v9fs_cache_unregister(void);
+
+extern int __v9fs_fscache_release_page(struct page *page, gfp_t gfp);
+extern void __v9fs_fscache_invalidate_page(struct page *page);
+extern int __v9fs_readpage_from_fscache(struct inode *inode,
+					struct page *page);
+extern int __v9fs_readpages_from_fscache(struct inode *inode,
+					 struct address_space *mapping,
+					 struct list_head *pages,
+					 unsigned *nr_pages);
+extern void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page);
+extern void __v9fs_fscache_wait_on_page_write(struct inode *inode,
+					      struct page *page);
+
+static inline int v9fs_fscache_release_page(struct page *page,
+					    gfp_t gfp)
+{
+	return __v9fs_fscache_release_page(page, gfp);
+}
+
+static inline void v9fs_fscache_invalidate_page(struct page *page)
+{
+	__v9fs_fscache_invalidate_page(page);
+}
+
+static inline int v9fs_readpage_from_fscache(struct inode *inode,
+					     struct page *page)
+{
+	return __v9fs_readpage_from_fscache(inode, page);
+}
+
+static inline int v9fs_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return __v9fs_readpages_from_fscache(inode, mapping, pages,
+					     nr_pages);
+}
+
+static inline void v9fs_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{
+	if (PageFsCache(page))
+		__v9fs_readpage_to_fscache(inode, page);
+}
+
+static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	fscache_uncache_page(v9inode->fscache, page);
+	BUG_ON(PageFsCache(page));
+}
+
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
+{
+	return __v9fs_fscache_wait_on_page_write(inode, page);
+}
+
+#else /* CONFIG_9P_FSCACHE */
+
+static inline void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+}
+
+static inline void v9fs_cache_inode_put_cookie(struct inode *inode)
+{
+}
+
+static inline void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *file)
+{
+}
+
+static inline int v9fs_fscache_release_page(struct page *page,
+					    gfp_t gfp) {
+	return 1;
+}
+
+static inline void v9fs_fscache_invalidate_page(struct page *page) {}
+
+static inline int v9fs_readpage_from_fscache(struct inode *inode,
+					     struct page *page)
+{
+	return -ENOBUFS;
+}
+
+static inline int v9fs_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return -ENOBUFS;
+}
+
+static inline void v9fs_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{}
+
+static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
+{}
+
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
+{
+	return;
+}
+
+#endif /* CONFIG_9P_FSCACHE */
+#endif /* _9P_CACHE_H */

addons/9p/src/4.4.180/error.c

@@ -0,0 +1,247 @@
+/*
+ * linux/fs/9p/error.c
+ *
+ * Error string handling
+ *
+ * Plan 9 uses error strings, Unix uses error numbers.  These functions
+ * try to help manage that and provide for dynamically adding error
+ * mappings.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/errno.h>
+#include <net/9p/9p.h>
+
+/**
+ * struct errormap - map string errors from Plan 9 to Linux numeric ids
+ * @name: string sent over 9P
+ * @val: numeric id most closely representing @name
+ * @namelen: length of string
+ * @list: hash-table list for string lookup
+ */
+struct errormap {
+	char *name;
+	int val;
+
+	int namelen;
+	struct hlist_node list;
+};
+
+#define ERRHASHSZ		32
+static struct hlist_head hash_errmap[ERRHASHSZ];
+
+/* FixMe - reduce to a reasonable size */
+static struct errormap errmap[] = {
+	{"Operation not permitted", EPERM},
+	{"wstat prohibited", EPERM},
+	{"No such file or directory", ENOENT},
+	{"directory entry not found", ENOENT},
+	{"file not found", ENOENT},
+	{"Interrupted system call", EINTR},
+	{"Input/output error", EIO},
+	{"No such device or address", ENXIO},
+	{"Argument list too long", E2BIG},
+	{"Bad file descriptor", EBADF},
+	{"Resource temporarily unavailable", EAGAIN},
+	{"Cannot allocate memory", ENOMEM},
+	{"Permission denied", EACCES},
+	{"Bad address", EFAULT},
+	{"Block device required", ENOTBLK},
+	{"Device or resource busy", EBUSY},
+	{"File exists", EEXIST},
+	{"Invalid cross-device link", EXDEV},
+	{"No such device", ENODEV},
+	{"Not a directory", ENOTDIR},
+	{"Is a directory", EISDIR},
+	{"Invalid argument", EINVAL},
+	{"Too many open files in system", ENFILE},
+	{"Too many open files", EMFILE},
+	{"Text file busy", ETXTBSY},
+	{"File too large", EFBIG},
+	{"No space left on device", ENOSPC},
+	{"Illegal seek", ESPIPE},
+	{"Read-only file system", EROFS},
+	{"Too many links", EMLINK},
+	{"Broken pipe", EPIPE},
+	{"Numerical argument out of domain", EDOM},
+	{"Numerical result out of range", ERANGE},
+	{"Resource deadlock avoided", EDEADLK},
+	{"File name too long", ENAMETOOLONG},
+	{"No locks available", ENOLCK},
+	{"Function not implemented", ENOSYS},
+	{"Directory not empty", ENOTEMPTY},
+	{"Too many levels of symbolic links", ELOOP},
+	{"No message of desired type", ENOMSG},
+	{"Identifier removed", EIDRM},
+	{"No data available", ENODATA},
+	{"Machine is not on the network", ENONET},
+	{"Package not installed", ENOPKG},
+	{"Object is remote", EREMOTE},
+	{"Link has been severed", ENOLINK},
+	{"Communication error on send", ECOMM},
+	{"Protocol error", EPROTO},
+	{"Bad message", EBADMSG},
+	{"File descriptor in bad state", EBADFD},
+	{"Streams pipe error", ESTRPIPE},
+	{"Too many users", EUSERS},
+	{"Socket operation on non-socket", ENOTSOCK},
+	{"Message too long", EMSGSIZE},
+	{"Protocol not available", ENOPROTOOPT},
+	{"Protocol not supported", EPROTONOSUPPORT},
+	{"Socket type not supported", ESOCKTNOSUPPORT},
+	{"Operation not supported", EOPNOTSUPP},
+	{"Protocol family not supported", EPFNOSUPPORT},
+	{"Network is down", ENETDOWN},
+	{"Network is unreachable", ENETUNREACH},
+	{"Network dropped connection on reset", ENETRESET},
+	{"Software caused connection abort", ECONNABORTED},
+	{"Connection reset by peer", ECONNRESET},
+	{"No buffer space available", ENOBUFS},
+	{"Transport endpoint is already connected", EISCONN},
+	{"Transport endpoint is not connected", ENOTCONN},
+	{"Cannot send after transport endpoint shutdown", ESHUTDOWN},
+	{"Connection timed out", ETIMEDOUT},
+	{"Connection refused", ECONNREFUSED},
+	{"Host is down", EHOSTDOWN},
+	{"No route to host", EHOSTUNREACH},
+	{"Operation already in progress", EALREADY},
+	{"Operation now in progress", EINPROGRESS},
+	{"Is a named type file", EISNAM},
+	{"Remote I/O error", EREMOTEIO},
+	{"Disk quota exceeded", EDQUOT},
+/* errors from fossil, vacfs, and u9fs */
+	{"fid unknown or out of range", EBADF},
+	{"permission denied", EACCES},
+	{"file does not exist", ENOENT},
+	{"authentication failed", ECONNREFUSED},
+	{"bad offset in directory read", ESPIPE},
+	{"bad use of fid", EBADF},
+	{"wstat can't convert between files and directories", EPERM},
+	{"directory is not empty", ENOTEMPTY},
+	{"file exists", EEXIST},
+	{"file already exists", EEXIST},
+	{"file or directory already exists", EEXIST},
+	{"fid already in use", EBADF},
+	{"file in use", ETXTBSY},
+	{"i/o error", EIO},
+	{"file already open for I/O", ETXTBSY},
+	{"illegal mode", EINVAL},
+	{"illegal name", ENAMETOOLONG},
+	{"not a directory", ENOTDIR},
+	{"not a member of proposed group", EPERM},
+	{"not owner", EACCES},
+	{"only owner can change group in wstat", EACCES},
+	{"read only file system", EROFS},
+	{"no access to special file", EPERM},
+	{"i/o count too large", EIO},
+	{"unknown group", EINVAL},
+	{"unknown user", EINVAL},
+	{"bogus wstat buffer", EPROTO},
+	{"exclusive use file already open", EAGAIN},
+	{"corrupted directory entry", EIO},
+	{"corrupted file entry", EIO},
+	{"corrupted block label", EIO},
+	{"corrupted meta data", EIO},
+	{"illegal offset", EINVAL},
+	{"illegal path element", ENOENT},
+	{"root of file system is corrupted", EIO},
+	{"corrupted super block", EIO},
+	{"protocol botch", EPROTO},
+	{"file system is full", ENOSPC},
+	{"file is in use", EAGAIN},
+	{"directory entry is not allocated", ENOENT},
+	{"file is read only", EROFS},
+	{"file has been removed", EIDRM},
+	{"only support truncation to zero length", EPERM},
+	{"cannot remove root", EPERM},
+	{"file too big", EFBIG},
+	{"venti i/o error", EIO},
+	/* these are not errors */
+	{"u9fs rhostsauth: no authentication required", 0},
+	{"u9fs authnone: no authentication required", 0},
+	{NULL, -1}
+};
+
+/**
+ * p9_error_init - preload mappings into hash list
+ *
+ */
+
+int p9_error_init(void)
+{
+	struct errormap *c;
+	int bucket;
+
+	/* initialize hash table */
+	for (bucket = 0; bucket < ERRHASHSZ; bucket++)
+		INIT_HLIST_HEAD(&hash_errmap[bucket]);
+
+	/* load initial error map into hash table */
+	for (c = errmap; c->name != NULL; c++) {
+		c->namelen = strlen(c->name);
+		bucket = jhash(c->name, c->namelen, 0) % ERRHASHSZ;
+		INIT_HLIST_NODE(&c->list);
+		hlist_add_head(&c->list, &hash_errmap[bucket]);
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL(p9_error_init);
+
+/**
+ * errstr2errno - convert error string to error number
+ * @errstr: error string
+ * @len: length of error string
+ *
+ */
+
+int p9_errstr2errno(char *errstr, int len)
+{
+	int errno;
+	struct errormap *c;
+	int bucket;
+
+	errno = 0;
+	c = NULL;
+	bucket = jhash(errstr, len, 0) % ERRHASHSZ;
+	hlist_for_each_entry(c, &hash_errmap[bucket], list) {
+		if (c->namelen == len && !memcmp(c->name, errstr, len)) {
+			errno = c->val;
+			break;
+		}
+	}
+
+	if (errno == 0) {
+		/* TODO: if error isn't found, add it dynamically */
+		errstr[len] = 0;
+		pr_err("%s: server reported unknown error %s\n",
+		       __func__, errstr);
+		errno = ESERVERFAULT;
+	}
+
+	return -errno;
+}
+EXPORT_SYMBOL(p9_errstr2errno);

addons/9p/src/4.4.180/fid.c

@@ -0,0 +1,306 @@
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/idr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * v9fs_fid_add - add a fid to a dentry
+ * @dentry: dentry that the fid is being added to
+ * @fid: fid to add
+ *
+ */
+
+static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid)
+{
+	hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata);
+}
+
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
+{
+	spin_lock(&dentry->d_lock);
+	__add_fid(dentry, fid);
+	spin_unlock(&dentry->d_lock);
+}
+
+/**
+ * v9fs_fid_find - retrieve a fid that belongs to the specified uid
+ * @dentry: dentry to look for fid in
+ * @uid: return fid that belongs to the specified user
+ * @any: if non-zero, return any fid associated with the dentry
+ *
+ */
+
+static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
+{
+	struct p9_fid *fid, *ret;
+
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p) uid %d any %d\n",
+		 dentry, dentry, from_kuid(&init_user_ns, uid),
+		 any);
+	ret = NULL;
+	/* we'll recheck under lock if there's anything to look in */
+	if (dentry->d_fsdata) {
+		struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
+		spin_lock(&dentry->d_lock);
+		hlist_for_each_entry(fid, h, dlist) {
+			if (any || uid_eq(fid->uid, uid)) {
+				ret = fid;
+				break;
+			}
+		}
+		spin_unlock(&dentry->d_lock);
+	}
+
+	return ret;
+}
+
+/*
+ * We need to hold v9ses->rename_sem as long as we hold references
+ * to returned path array. Array element contain pointers to
+ * dentry names.
+ */
+static int build_path_from_dentry(struct v9fs_session_info *v9ses,
+				  struct dentry *dentry, char ***names)
+{
+	int n = 0, i;
+	char **wnames;
+	struct dentry *ds;
+
+	for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
+		n++;
+
+	wnames = kmalloc(sizeof(char *) * n, GFP_KERNEL);
+	if (!wnames)
+		goto err_out;
+
+	for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
+		wnames[i] = (char  *)ds->d_name.name;
+
+	*names = wnames;
+	return n;
+err_out:
+	return -ENOMEM;
+}
+
+static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
+					       kuid_t uid, int any)
+{
+	struct dentry *ds;
+	char **wnames, *uname;
+	int i, n, l, clone, access;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid, *old_fid = NULL;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	access = v9ses->flags & V9FS_ACCESS_MASK;
+	fid = v9fs_fid_find(dentry, uid, any);
+	if (fid)
+		return fid;
+	/*
+	 * we don't have a matching fid. To do a TWALK we need
+	 * parent fid. We need to prevent rename when we want to
+	 * look at the parent.
+	 */
+	down_read(&v9ses->rename_sem);
+	ds = dentry->d_parent;
+	fid = v9fs_fid_find(ds, uid, any);
+	if (fid) {
+		/* Found the parent fid do a lookup with that */
+		fid = p9_client_walk(fid, 1, (char **)&dentry->d_name.name, 1);
+		goto fid_out;
+	}
+	up_read(&v9ses->rename_sem);
+
+	/* start from the root and try to do a lookup */
+	fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any);
+	if (!fid) {
+		/* the user is not attached to the fs yet */
+		if (access == V9FS_ACCESS_SINGLE)
+			return ERR_PTR(-EPERM);
+
+		if (v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses))
+				uname = NULL;
+		else
+			uname = v9ses->uname;
+
+		fid = p9_client_attach(v9ses->clnt, NULL, uname, uid,
+				       v9ses->aname);
+		if (IS_ERR(fid))
+			return fid;
+
+		v9fs_fid_add(dentry->d_sb->s_root, fid);
+	}
+	/* If we are root ourself just return that */
+	if (dentry->d_sb->s_root == dentry)
+		return fid;
+	/*
+	 * Do a multipath walk with attached root.
+	 * When walking parent we need to make sure we
+	 * don't have a parallel rename happening
+	 */
+	down_read(&v9ses->rename_sem);
+	n  = build_path_from_dentry(v9ses, dentry, &wnames);
+	if (n < 0) {
+		fid = ERR_PTR(n);
+		goto err_out;
+	}
+	clone = 1;
+	i = 0;
+	while (i < n) {
+		l = min(n - i, P9_MAXWELEM);
+		/*
+		 * We need to hold rename lock when doing a multipath
+		 * walk to ensure none of the patch component change
+		 */
+		fid = p9_client_walk(fid, l, &wnames[i], clone);
+		if (IS_ERR(fid)) {
+			if (old_fid) {
+				/*
+				 * If we fail, clunk fid which are mapping
+				 * to path component and not the last component
+				 * of the path.
+				 */
+				p9_client_clunk(old_fid);
+			}
+			kfree(wnames);
+			goto err_out;
+		}
+		old_fid = fid;
+		i += l;
+		clone = 0;
+	}
+	kfree(wnames);
+fid_out:
+	if (!IS_ERR(fid)) {
+		spin_lock(&dentry->d_lock);
+		if (d_unhashed(dentry)) {
+			spin_unlock(&dentry->d_lock);
+			p9_client_clunk(fid);
+			fid = ERR_PTR(-ENOENT);
+		} else {
+			__add_fid(dentry, fid);
+			spin_unlock(&dentry->d_lock);
+		}
+	}
+err_out:
+	up_read(&v9ses->rename_sem);
+	return fid;
+}
+
+/**
+ * v9fs_fid_lookup - lookup for a fid, try to walk if not found
+ * @dentry: dentry to look for fid in
+ *
+ * Look for a fid in the specified dentry for the current user.
+ * If no fid is found, try to create one walking from a fid from the parent
+ * dentry (if it has one), or the root dentry. If the user haven't accessed
+ * the fs yet, attach now and walk from the root.
+ */
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
+{
+	kuid_t uid;
+	int  any, access;
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	access = v9ses->flags & V9FS_ACCESS_MASK;
+	switch (access) {
+	case V9FS_ACCESS_SINGLE:
+	case V9FS_ACCESS_USER:
+	case V9FS_ACCESS_CLIENT:
+		uid = current_fsuid();
+		any = 0;
+		break;
+
+	case V9FS_ACCESS_ANY:
+		uid = v9ses->uid;
+		any = 1;
+		break;
+
+	default:
+		uid = INVALID_UID;
+		any = 0;
+		break;
+	}
+	return v9fs_fid_lookup_with_uid(dentry, uid, any);
+}
+
+struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
+{
+	struct p9_fid *fid, *ret;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return fid;
+
+	ret = p9_client_walk(fid, 0, NULL, 1);
+	return ret;
+}
+
+static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, kuid_t uid)
+{
+	struct p9_fid *fid, *ret;
+
+	fid = v9fs_fid_lookup_with_uid(dentry, uid, 0);
+	if (IS_ERR(fid))
+		return fid;
+
+	ret = p9_client_walk(fid, 0, NULL, 1);
+	return ret;
+}
+
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
+{
+	int err;
+	struct p9_fid *fid;
+
+	fid = v9fs_fid_clone_with_uid(dentry, GLOBAL_ROOT_UID);
+	if (IS_ERR(fid))
+		goto error_out;
+	/*
+	 * writeback fid will only be used to write back the
+	 * dirty pages. We always request for the open fid in read-write
+	 * mode so that a partial page write which result in page
+	 * read can work.
+	 */
+	err = p9_client_open(fid, O_RDWR);
+	if (err < 0) {
+		p9_client_clunk(fid);
+		fid = ERR_PTR(err);
+		goto error_out;
+	}
+error_out:
+	return fid;
+}

addons/9p/src/4.4.180/fid.h

@@ -0,0 +1,30 @@
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_FID_H
+#define FS_9P_FID_H
+#include <linux/list.h>
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
+struct p9_fid *v9fs_fid_clone(struct dentry *dentry);
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
+#endif

addons/9p/src/4.4.180/mod.c

@@ -0,0 +1,201 @@
+/*
+ *  net/9p/9p.c
+ *
+ *  9P entry point
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/moduleparam.h>
+#include <net/9p/9p.h>
+#include <linux/fs.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_NET_9P_DEBUG
+unsigned int p9_debug_level = 0;	/* feature-rific global debug level  */
+EXPORT_SYMBOL(p9_debug_level);
+module_param_named(debug, p9_debug_level, uint, 0);
+MODULE_PARM_DESC(debug, "9P debugging level");
+
+void _p9_debug(enum p9_debug_flags level, const char *func,
+		const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	if ((p9_debug_level & level) != level)
+		return;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (level == P9_DEBUG_9P)
+		pr_notice("(%8.8d) %pV", task_pid_nr(current), &vaf);
+	else
+		pr_notice("-- %s (%d): %pV", func, task_pid_nr(current), &vaf);
+
+	va_end(args);
+}
+EXPORT_SYMBOL(_p9_debug);
+#endif
+
+/*
+ * Dynamic Transport Registration Routines
+ *
+ */
+
+static DEFINE_SPINLOCK(v9fs_trans_lock);
+static LIST_HEAD(v9fs_trans_list);
+
+/**
+ * v9fs_register_trans - register a new transport with 9p
+ * @m: structure describing the transport module and entry points
+ *
+ */
+void v9fs_register_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_add_tail(&m->list, &v9fs_trans_list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_register_trans);
+
+/**
+ * v9fs_unregister_trans - unregister a 9p transport
+ * @m: the transport to remove
+ *
+ */
+void v9fs_unregister_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_del_init(&m->list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_unregister_trans);
+
+/**
+ * v9fs_get_trans_by_name - get transport with the matching name
+ * @name: string identifying transport
+ *
+ */
+struct p9_trans_module *v9fs_get_trans_by_name(char *s)
+{
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (strcmp(t->name, s) == 0 &&
+		    try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
+}
+EXPORT_SYMBOL(v9fs_get_trans_by_name);
+
+/**
+ * v9fs_get_default_trans - get the default transport
+ *
+ */
+
+struct p9_trans_module *v9fs_get_default_trans(void)
+{
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (t->def && try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	if (!found)
+		list_for_each_entry(t, &v9fs_trans_list, list)
+			if (try_module_get(t->owner)) {
+				found = t;
+				break;
+			}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
+}
+EXPORT_SYMBOL(v9fs_get_default_trans);
+
+/**
+ * v9fs_put_trans - put trans
+ * @m: transport to put
+ *
+ */
+void v9fs_put_trans(struct p9_trans_module *m)
+{
+	if (m)
+		module_put(m->owner);
+}
+
+/**
+ * init_p9 - Initialize module
+ *
+ */
+static int __init init_p9(void)
+{
+	int ret = 0;
+
+	p9_error_init();
+	pr_info("Installing 9P2000 support\n");
+	p9_trans_fd_init();
+
+	return ret;
+}
+
+/**
+ * exit_p9 - shutdown module
+ *
+ */
+
+static void __exit exit_p9(void)
+{
+	pr_info("Unloading 9P2000 support\n");
+
+	p9_trans_fd_exit();
+}
+
+module_init(init_p9)
+module_exit(exit_p9)
+
+MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>");
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>");
+MODULE_LICENSE("GPL");

addons/9p/src/4.4.180/protocol.c

@@ -0,0 +1,634 @@
+/*
+ * net/9p/protocol.c
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/uio.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include "protocol.h"
+
+#include <trace/events/9p.h>
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
+
+void p9stat_free(struct p9_wstat *stbuf)
+{
+	kfree(stbuf->name);
+	stbuf->name = NULL;
+	kfree(stbuf->uid);
+	stbuf->uid = NULL;
+	kfree(stbuf->gid);
+	stbuf->gid = NULL;
+	kfree(stbuf->muid);
+	stbuf->muid = NULL;
+	kfree(stbuf->extension);
+	stbuf->extension = NULL;
+}
+EXPORT_SYMBOL(p9stat_free);
+
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
+{
+	size_t len = min(pdu->size - pdu->offset, size);
+	memcpy(data, &pdu->sdata[pdu->offset], len);
+	pdu->offset += len;
+	return size - len;
+}
+
+static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
+{
+	size_t len = min(pdu->capacity - pdu->size, size);
+	memcpy(&pdu->sdata[pdu->size], data, len);
+	pdu->size += len;
+	return size - len;
+}
+
+static size_t
+pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size)
+{
+	size_t len = min(pdu->capacity - pdu->size, size);
+	struct iov_iter i = *from;
+	if (copy_from_iter(&pdu->sdata[pdu->size], len, &i) != len)
+		len = 0;
+
+	pdu->size += len;
+	return size - len;
+}
+
+/*
+	b - int8_t
+	w - int16_t
+	d - int32_t
+	q - int64_t
+	s - string
+	u - numeric uid
+	g - numeric gid
+	S - stat
+	Q - qid
+	D - data blob (int32_t size followed by void *, results are not freed)
+	T - array of strings (int16_t count, followed by strings)
+	R - array of qids (int16_t count, followed by qids)
+	A - stat for 9p2000.L (p9_stat_dotl)
+	? - if optional = 1, continue parsing
+*/
+
+static int
+p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
+	va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t *val = va_arg(ap, int8_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+			}
+			break;
+		case 'w':{
+				int16_t *val = va_arg(ap, int16_t *);
+				__le16 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le16_to_cpu(le_val);
+			}
+			break;
+		case 'd':{
+				int32_t *val = va_arg(ap, int32_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le32_to_cpu(le_val);
+			}
+			break;
+		case 'q':{
+				int64_t *val = va_arg(ap, int64_t *);
+				__le64 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = le64_to_cpu(le_val);
+			}
+			break;
+		case 's':{
+				char **sptr = va_arg(ap, char **);
+				uint16_t len;
+
+				errcode = p9pdu_readf(pdu, proto_version,
+								"w", &len);
+				if (errcode)
+					break;
+
+				*sptr = kmalloc(len + 1, GFP_NOFS);
+				if (*sptr == NULL) {
+					errcode = -EFAULT;
+					break;
+				}
+				if (pdu_read(pdu, *sptr, len)) {
+					errcode = -EFAULT;
+					kfree(*sptr);
+					*sptr = NULL;
+				} else
+					(*sptr)[len] = 0;
+			}
+			break;
+		case 'u': {
+				kuid_t *uid = va_arg(ap, kuid_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*uid = make_kuid(&init_user_ns,
+						 le32_to_cpu(le_val));
+			} break;
+		case 'g': {
+				kgid_t *gid = va_arg(ap, kgid_t *);
+				__le32 le_val;
+				if (pdu_read(pdu, &le_val, sizeof(le_val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*gid = make_kgid(&init_user_ns,
+						 le32_to_cpu(le_val));
+			} break;
+		case 'Q':{
+				struct p9_qid *qid =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_readf(pdu, proto_version, "bdq",
+						      &qid->type, &qid->version,
+						      &qid->path);
+			}
+			break;
+		case 'S':{
+				struct p9_wstat *stbuf =
+				    va_arg(ap, struct p9_wstat *);
+
+				memset(stbuf, 0, sizeof(struct p9_wstat));
+				stbuf->n_uid = stbuf->n_muid = INVALID_UID;
+				stbuf->n_gid = INVALID_GID;
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version,
+						"wwdQdddqssss?sugu",
+						&stbuf->size, &stbuf->type,
+						&stbuf->dev, &stbuf->qid,
+						&stbuf->mode, &stbuf->atime,
+						&stbuf->mtime, &stbuf->length,
+						&stbuf->name, &stbuf->uid,
+						&stbuf->gid, &stbuf->muid,
+						&stbuf->extension,
+						&stbuf->n_uid, &stbuf->n_gid,
+						&stbuf->n_muid);
+				if (errcode)
+					p9stat_free(stbuf);
+			}
+			break;
+		case 'D':{
+				uint32_t *count = va_arg(ap, uint32_t *);
+				void **data = va_arg(ap, void **);
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version, "d", count);
+				if (!errcode) {
+					*count =
+					    min_t(uint32_t, *count,
+						  pdu->size - pdu->offset);
+					*data = &pdu->sdata[pdu->offset];
+				}
+			}
+			break;
+		case 'T':{
+				uint16_t *nwname = va_arg(ap, uint16_t *);
+				char ***wnames = va_arg(ap, char ***);
+
+				errcode = p9pdu_readf(pdu, proto_version,
+								"w", nwname);
+				if (!errcode) {
+					*wnames =
+					    kmalloc(sizeof(char *) * *nwname,
+						    GFP_NOFS);
+					if (!*wnames)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwname; i++) {
+						errcode =
+						    p9pdu_readf(pdu,
+								proto_version,
+								"s",
+								&(*wnames)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					if (*wnames) {
+						int i;
+
+						for (i = 0; i < *nwname; i++)
+							kfree((*wnames)[i]);
+					}
+					kfree(*wnames);
+					*wnames = NULL;
+				}
+			}
+			break;
+		case 'R':{
+				uint16_t *nwqid = va_arg(ap, uint16_t *);
+				struct p9_qid **wqids =
+				    va_arg(ap, struct p9_qid **);
+
+				*wqids = NULL;
+
+				errcode =
+				    p9pdu_readf(pdu, proto_version, "w", nwqid);
+				if (!errcode) {
+					*wqids =
+					    kmalloc(*nwqid *
+						    sizeof(struct p9_qid),
+						    GFP_NOFS);
+					if (*wqids == NULL)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwqid; i++) {
+						errcode =
+						    p9pdu_readf(pdu,
+								proto_version,
+								"Q",
+								&(*wqids)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					kfree(*wqids);
+					*wqids = NULL;
+				}
+			}
+			break;
+		case 'A': {
+				struct p9_stat_dotl *stbuf =
+				    va_arg(ap, struct p9_stat_dotl *);
+
+				memset(stbuf, 0, sizeof(struct p9_stat_dotl));
+				errcode =
+				    p9pdu_readf(pdu, proto_version,
+					"qQdugqqqqqqqqqqqqqqq",
+					&stbuf->st_result_mask,
+					&stbuf->qid,
+					&stbuf->st_mode,
+					&stbuf->st_uid, &stbuf->st_gid,
+					&stbuf->st_nlink,
+					&stbuf->st_rdev, &stbuf->st_size,
+					&stbuf->st_blksize, &stbuf->st_blocks,
+					&stbuf->st_atime_sec,
+					&stbuf->st_atime_nsec,
+					&stbuf->st_mtime_sec,
+					&stbuf->st_mtime_nsec,
+					&stbuf->st_ctime_sec,
+					&stbuf->st_ctime_nsec,
+					&stbuf->st_btime_sec,
+					&stbuf->st_btime_nsec,
+					&stbuf->st_gen,
+					&stbuf->st_data_version);
+			}
+			break;
+		case '?':
+			if ((proto_version != p9_proto_2000u) &&
+				(proto_version != p9_proto_2000L))
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int
+p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
+	va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t val = va_arg(ap, int);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'w':{
+				__le16 val = cpu_to_le16(va_arg(ap, int));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'd':{
+				__le32 val = cpu_to_le32(va_arg(ap, int32_t));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'q':{
+				__le64 val = cpu_to_le64(va_arg(ap, int64_t));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 's':{
+				const char *sptr = va_arg(ap, const char *);
+				uint16_t len = 0;
+				if (sptr)
+					len = min_t(size_t, strlen(sptr),
+								USHRT_MAX);
+
+				errcode = p9pdu_writef(pdu, proto_version,
+								"w", len);
+				if (!errcode && pdu_write(pdu, sptr, len))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'u': {
+				kuid_t uid = va_arg(ap, kuid_t);
+				__le32 val = cpu_to_le32(
+						from_kuid(&init_user_ns, uid));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			} break;
+		case 'g': {
+				kgid_t gid = va_arg(ap, kgid_t);
+				__le32 val = cpu_to_le32(
+						from_kgid(&init_user_ns, gid));
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			} break;
+		case 'Q':{
+				const struct p9_qid *qid =
+				    va_arg(ap, const struct p9_qid *);
+				errcode =
+				    p9pdu_writef(pdu, proto_version, "bdq",
+						 qid->type, qid->version,
+						 qid->path);
+			} break;
+		case 'S':{
+				const struct p9_wstat *stbuf =
+				    va_arg(ap, const struct p9_wstat *);
+				errcode =
+				    p9pdu_writef(pdu, proto_version,
+						 "wwdQdddqssss?sugu",
+						 stbuf->size, stbuf->type,
+						 stbuf->dev, &stbuf->qid,
+						 stbuf->mode, stbuf->atime,
+						 stbuf->mtime, stbuf->length,
+						 stbuf->name, stbuf->uid,
+						 stbuf->gid, stbuf->muid,
+						 stbuf->extension, stbuf->n_uid,
+						 stbuf->n_gid, stbuf->n_muid);
+			} break;
+		case 'V':{
+				uint32_t count = va_arg(ap, uint32_t);
+				struct iov_iter *from =
+						va_arg(ap, struct iov_iter *);
+				errcode = p9pdu_writef(pdu, proto_version, "d",
+									count);
+				if (!errcode && pdu_write_u(pdu, from, count))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'T':{
+				uint16_t nwname = va_arg(ap, int);
+				const char **wnames = va_arg(ap, const char **);
+
+				errcode = p9pdu_writef(pdu, proto_version, "w",
+									nwname);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwname; i++) {
+						errcode =
+						    p9pdu_writef(pdu,
+								proto_version,
+								 "s",
+								 wnames[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'R':{
+				uint16_t nwqid = va_arg(ap, int);
+				struct p9_qid *wqids =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_writef(pdu, proto_version, "w",
+									nwqid);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwqid; i++) {
+						errcode =
+						    p9pdu_writef(pdu,
+								proto_version,
+								 "Q",
+								 &wqids[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'I':{
+				struct p9_iattr_dotl *p9attr = va_arg(ap,
+							struct p9_iattr_dotl *);
+
+				errcode = p9pdu_writef(pdu, proto_version,
+							"ddugqqqqq",
+							p9attr->valid,
+							p9attr->mode,
+							p9attr->uid,
+							p9attr->gid,
+							p9attr->size,
+							p9attr->atime_sec,
+							p9attr->atime_nsec,
+							p9attr->mtime_sec,
+							p9attr->mtime_nsec);
+			}
+			break;
+		case '?':
+			if ((proto_version != p9_proto_2000u) &&
+				(proto_version != p9_proto_2000L))
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vreadf(pdu, proto_version, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vwritef(pdu, proto_version, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st)
+{
+	struct p9_fcall fake_pdu;
+	int ret;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "S", st);
+	if (ret) {
+		p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
+		trace_9p_protocol_dump(clnt, &fake_pdu);
+		return ret;
+	}
+
+	return fake_pdu.offset;
+}
+EXPORT_SYMBOL(p9stat_read);
+
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type)
+{
+	pdu->id = type;
+	return p9pdu_writef(pdu, 0, "dbw", 0, type, tag);
+}
+
+int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu)
+{
+	int size = pdu->size;
+	int err;
+
+	pdu->size = 0;
+	err = p9pdu_writef(pdu, 0, "d", size);
+	pdu->size = size;
+
+	trace_9p_protocol_dump(clnt, pdu);
+	p9_debug(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n",
+		 pdu->size, pdu->id, pdu->tag);
+
+	return err;
+}
+
+void p9pdu_reset(struct p9_fcall *pdu)
+{
+	pdu->offset = 0;
+	pdu->size = 0;
+}
+
+int p9dirent_read(struct p9_client *clnt, char *buf, int len,
+		  struct p9_dirent *dirent)
+{
+	struct p9_fcall fake_pdu;
+	int ret;
+	char *nameptr;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	ret = p9pdu_readf(&fake_pdu, clnt->proto_version, "Qqbs", &dirent->qid,
+			  &dirent->d_off, &dirent->d_type, &nameptr);
+	if (ret) {
+		p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret);
+		trace_9p_protocol_dump(clnt, &fake_pdu);
+		goto out;
+	}
+
+	strcpy(dirent->d_name, nameptr);
+	kfree(nameptr);
+
+out:
+	return fake_pdu.offset;
+}
+EXPORT_SYMBOL(p9dirent_read);

addons/9p/src/4.4.180/protocol.h

@@ -0,0 +1,34 @@
+/*
+ * net/9p/protocol.h
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+int p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
+								va_list ap);
+int p9pdu_readf(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type);
+int p9pdu_finalize(struct p9_client *clnt, struct p9_fcall *pdu);
+void p9pdu_reset(struct p9_fcall *pdu);
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size);

addons/9p/src/4.4.180/trans_common.c

@@ -0,0 +1,29 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+
+/**
+ *  p9_release_req_pages - Release pages after the transaction.
+ */
+void p9_release_pages(struct page **pages, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++)
+		if (pages[i])
+			put_page(pages[i]);
+}
+EXPORT_SYMBOL(p9_release_pages);

addons/9p/src/4.4.180/trans_common.h

@@ -0,0 +1,15 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+void p9_release_pages(struct page **, int);

addons/9p/src/4.4.180/trans_rdma.c

@@ -0,0 +1,784 @@
+/*
+ * linux/fs/9p/trans_rdma.c
+ *
+ * RDMA transport layer based on the trans_fd.c implementation.
+ *
+ *  Copyright (C) 2008 by Tom Tucker <tom@opengridcomputing.com>
+ *  Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
+ *  Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/parser.h>
+#include <linux/semaphore.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+
+#define P9_PORT			5640
+#define P9_RDMA_SQ_DEPTH	32
+#define P9_RDMA_RQ_DEPTH	32
+#define P9_RDMA_SEND_SGE	4
+#define P9_RDMA_RECV_SGE	4
+#define P9_RDMA_IRD		0
+#define P9_RDMA_ORD		0
+#define P9_RDMA_TIMEOUT		30000		/* 30 seconds */
+#define P9_RDMA_MAXSIZE		(1024*1024)	/* 1MB */
+
+/**
+ * struct p9_trans_rdma - RDMA transport instance
+ *
+ * @state: tracks the transport state machine for connection setup and tear down
+ * @cm_id: The RDMA CM ID
+ * @pd: Protection Domain pointer
+ * @qp: Queue Pair pointer
+ * @cq: Completion Queue pointer
+ * @dm_mr: DMA Memory Region pointer
+ * @lkey: The local access only memory region key
+ * @timeout: Number of uSecs to wait for connection management events
+ * @sq_depth: The depth of the Send Queue
+ * @sq_sem: Semaphore for the SQ
+ * @rq_depth: The depth of the Receive Queue.
+ * @rq_sem: Semaphore for the RQ
+ * @excess_rc : Amount of posted Receive Contexts without a pending request.
+ *		See rdma_request()
+ * @addr: The remote peer's address
+ * @req_lock: Protects the active request list
+ * @cm_done: Completion event for connection management tracking
+ */
+struct p9_trans_rdma {
+	enum {
+		P9_RDMA_INIT,
+		P9_RDMA_ADDR_RESOLVED,
+		P9_RDMA_ROUTE_RESOLVED,
+		P9_RDMA_CONNECTED,
+		P9_RDMA_FLUSHING,
+		P9_RDMA_CLOSING,
+		P9_RDMA_CLOSED,
+	} state;
+	struct rdma_cm_id *cm_id;
+	struct ib_pd *pd;
+	struct ib_qp *qp;
+	struct ib_cq *cq;
+	long timeout;
+	int sq_depth;
+	struct semaphore sq_sem;
+	int rq_depth;
+	struct semaphore rq_sem;
+	atomic_t excess_rc;
+	struct sockaddr_in addr;
+	spinlock_t req_lock;
+
+	struct completion cm_done;
+};
+
+/**
+ * p9_rdma_context - Keeps track of in-process WR
+ *
+ * @wc_op: The original WR op for when the CQE completes in error.
+ * @busa: Bus address to unmap when the WR completes
+ * @req: Keeps track of requests (send)
+ * @rc: Keepts track of replies (receive)
+ */
+struct p9_rdma_req;
+struct p9_rdma_context {
+	enum ib_wc_opcode wc_op;
+	dma_addr_t busa;
+	union {
+		struct p9_req_t *req;
+		struct p9_fcall *rc;
+	};
+};
+
+/**
+ * p9_rdma_opts - Collection of mount options
+ * @port: port of connection
+ * @sq_depth: The requested depth of the SQ. This really doesn't need
+ * to be any deeper than the number of threads used in the client
+ * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
+ * @timeout: Time to wait in msecs for CM events
+ */
+struct p9_rdma_opts {
+	short port;
+	int sq_depth;
+	int rq_depth;
+	long timeout;
+	int privport;
+};
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ */
+enum {
+	/* Options that take integer arguments */
+	Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout,
+	/* Options that take no argument */
+	Opt_privport,
+	Opt_err,
+};
+
+static match_table_t tokens = {
+	{Opt_port, "port=%u"},
+	{Opt_sq_depth, "sq=%u"},
+	{Opt_rq_depth, "rq=%u"},
+	{Opt_timeout, "timeout=%u"},
+	{Opt_privport, "privport"},
+	{Opt_err, NULL},
+};
+
+/**
+ * parse_opts - parse mount options into rdma options structure
+ * @params: options string passed from mount
+ * @opts: rdma transport-specific structure to parse options into
+ *
+ * Returns 0 upon success, -ERRNO upon failure
+ */
+static int parse_opts(char *params, struct p9_rdma_opts *opts)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	char *options, *tmp_options;
+
+	opts->port = P9_PORT;
+	opts->sq_depth = P9_RDMA_SQ_DEPTH;
+	opts->rq_depth = P9_RDMA_RQ_DEPTH;
+	opts->timeout = P9_RDMA_TIMEOUT;
+	opts->privport = 0;
+
+	if (!params)
+		return 0;
+
+	tmp_options = kstrdup(params, GFP_KERNEL);
+	if (!tmp_options) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "failed to allocate copy of option string\n");
+		return -ENOMEM;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		int r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		if ((token != Opt_err) && (token != Opt_privport)) {
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				continue;
+			}
+		}
+		switch (token) {
+		case Opt_port:
+			opts->port = option;
+			break;
+		case Opt_sq_depth:
+			opts->sq_depth = option;
+			break;
+		case Opt_rq_depth:
+			opts->rq_depth = option;
+			break;
+		case Opt_timeout:
+			opts->timeout = option;
+			break;
+		case Opt_privport:
+			opts->privport = 1;
+			break;
+		default:
+			continue;
+		}
+	}
+	/* RQ must be at least as large as the SQ */
+	opts->rq_depth = max(opts->rq_depth, opts->sq_depth);
+	kfree(tmp_options);
+	return 0;
+}
+
+static int
+p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
+{
+	struct p9_client *c = id->context;
+	struct p9_trans_rdma *rdma = c->trans;
+	switch (event->event) {
+	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_INIT);
+		rdma->state = P9_RDMA_ADDR_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_ADDR_RESOLVED);
+		rdma->state = P9_RDMA_ROUTE_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ESTABLISHED:
+		BUG_ON(rdma->state != P9_RDMA_ROUTE_RESOLVED);
+		rdma->state = P9_RDMA_CONNECTED;
+		break;
+
+	case RDMA_CM_EVENT_DISCONNECTED:
+		if (rdma)
+			rdma->state = P9_RDMA_CLOSED;
+		if (c)
+			c->status = Disconnected;
+		break;
+
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		break;
+
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ROUTE_ERROR:
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+	case RDMA_CM_EVENT_MULTICAST_JOIN:
+	case RDMA_CM_EVENT_MULTICAST_ERROR:
+	case RDMA_CM_EVENT_REJECTED:
+	case RDMA_CM_EVENT_CONNECT_REQUEST:
+	case RDMA_CM_EVENT_CONNECT_RESPONSE:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+	case RDMA_CM_EVENT_ADDR_ERROR:
+	case RDMA_CM_EVENT_UNREACHABLE:
+		c->status = Disconnected;
+		rdma_disconnect(rdma->cm_id);
+		break;
+	default:
+		BUG();
+	}
+	complete(&rdma->cm_done);
+	return 0;
+}
+
+static void
+handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	struct p9_req_t *req;
+	int err = 0;
+	int16_t tag;
+
+	req = NULL;
+	ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize,
+							 DMA_FROM_DEVICE);
+
+	if (status != IB_WC_SUCCESS)
+		goto err_out;
+
+	err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+	if (err)
+		goto err_out;
+
+	req = p9_tag_lookup(client, tag);
+	if (!req)
+		goto err_out;
+
+	/* Check that we have not yet received a reply for this request.
+	 */
+	if (unlikely(req->rc)) {
+		pr_err("Duplicate reply for request %d", tag);
+		goto err_out;
+	}
+
+	req->rc = c->rc;
+	p9_client_cb(client, req, REQ_STATUS_RCVD);
+
+	return;
+
+ err_out:
+	p9_debug(P9_DEBUG_ERROR, "req %p err %d status %d\n", req, err, status);
+	rdma->state = P9_RDMA_FLUSHING;
+	client->status = Disconnected;
+}
+
+static void
+handle_send(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	ib_dma_unmap_single(rdma->cm_id->device,
+			    c->busa, c->req->tc->size,
+			    DMA_TO_DEVICE);
+}
+
+static void qp_event_handler(struct ib_event *event, void *context)
+{
+	p9_debug(P9_DEBUG_ERROR, "QP event %d context %p\n",
+		 event->event, context);
+}
+
+static void cq_comp_handler(struct ib_cq *cq, void *cq_context)
+{
+	struct p9_client *client = cq_context;
+	struct p9_trans_rdma *rdma = client->trans;
+	int ret;
+	struct ib_wc wc;
+
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+	while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
+		struct p9_rdma_context *c = (void *) (unsigned long) wc.wr_id;
+
+		switch (c->wc_op) {
+		case IB_WC_RECV:
+			handle_recv(client, rdma, c, wc.status, wc.byte_len);
+			up(&rdma->rq_sem);
+			break;
+
+		case IB_WC_SEND:
+			handle_send(client, rdma, c, wc.status, wc.byte_len);
+			up(&rdma->sq_sem);
+			break;
+
+		default:
+			pr_err("unexpected completion type, c->wc_op=%d, wc.opcode=%d, status=%d\n",
+			       c->wc_op, wc.opcode, wc.status);
+			break;
+		}
+		kfree(c);
+	}
+}
+
+static void cq_event_handler(struct ib_event *e, void *v)
+{
+	p9_debug(P9_DEBUG_ERROR, "CQ event %d context %p\n", e->event, v);
+}
+
+static void rdma_destroy_trans(struct p9_trans_rdma *rdma)
+{
+	if (!rdma)
+		return;
+
+	if (rdma->qp && !IS_ERR(rdma->qp))
+		ib_destroy_qp(rdma->qp);
+
+	if (rdma->pd && !IS_ERR(rdma->pd))
+		ib_dealloc_pd(rdma->pd);
+
+	if (rdma->cq && !IS_ERR(rdma->cq))
+		ib_destroy_cq(rdma->cq);
+
+	if (rdma->cm_id && !IS_ERR(rdma->cm_id))
+		rdma_destroy_id(rdma->cm_id);
+
+	kfree(rdma);
+}
+
+static int
+post_recv(struct p9_client *client, struct p9_rdma_context *c)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_recv_wr wr, *bad_wr;
+	struct ib_sge sge;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->rc->sdata, client->msize,
+				    DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
+		goto error;
+
+	sge.addr = c->busa;
+	sge.length = client->msize;
+	sge.lkey = rdma->pd->local_dma_lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_RECV;
+	wr.wr_id = (unsigned long) c;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+	return ib_post_recv(rdma->qp, &wr, &bad_wr);
+
+ error:
+	p9_debug(P9_DEBUG_ERROR, "EIO\n");
+	return -EIO;
+}
+
+static int rdma_request(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_send_wr wr, *bad_wr;
+	struct ib_sge sge;
+	int err = 0;
+	unsigned long flags;
+	struct p9_rdma_context *c = NULL;
+	struct p9_rdma_context *rpl_context = NULL;
+
+	/* When an error occurs between posting the recv and the send,
+	 * there will be a receive context posted without a pending request.
+	 * Since there is no way to "un-post" it, we remember it and skip
+	 * post_recv() for the next request.
+	 * So here,
+	 * see if we are this `next request' and need to absorb an excess rc.
+	 * If yes, then drop and free our own, and do not recv_post().
+	 **/
+	if (unlikely(atomic_read(&rdma->excess_rc) > 0)) {
+		if ((atomic_sub_return(1, &rdma->excess_rc) >= 0)) {
+			/* Got one ! */
+			kfree(req->rc);
+			req->rc = NULL;
+			goto dont_need_post_recv;
+		} else {
+			/* We raced and lost. */
+			atomic_inc(&rdma->excess_rc);
+		}
+	}
+
+	/* Allocate an fcall for the reply */
+	rpl_context = kmalloc(sizeof *rpl_context, GFP_NOFS);
+	if (!rpl_context) {
+		err = -ENOMEM;
+		goto recv_error;
+	}
+	rpl_context->rc = req->rc;
+
+	/*
+	 * Post a receive buffer for this request. We need to ensure
+	 * there is a reply buffer available for every outstanding
+	 * request. A flushed request can result in no reply for an
+	 * outstanding request, so we must keep a count to avoid
+	 * overflowing the RQ.
+	 */
+	if (down_interruptible(&rdma->rq_sem)) {
+		err = -EINTR;
+		goto recv_error;
+	}
+
+	err = post_recv(client, rpl_context);
+	if (err) {
+		p9_debug(P9_DEBUG_FCALL, "POST RECV failed\n");
+		goto recv_error;
+	}
+	/* remove posted receive buffer from request structure */
+	req->rc = NULL;
+
+dont_need_post_recv:
+	/* Post the request */
+	c = kmalloc(sizeof *c, GFP_NOFS);
+	if (!c) {
+		err = -ENOMEM;
+		goto send_error;
+	}
+	c->req = req;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->req->tc->sdata, c->req->tc->size,
+				    DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) {
+		err = -EIO;
+		goto send_error;
+	}
+
+	sge.addr = c->busa;
+	sge.length = c->req->tc->size;
+	sge.lkey = rdma->pd->local_dma_lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_SEND;
+	wr.wr_id = (unsigned long) c;
+	wr.opcode = IB_WR_SEND;
+	wr.send_flags = IB_SEND_SIGNALED;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+
+	if (down_interruptible(&rdma->sq_sem)) {
+		err = -EINTR;
+		goto send_error;
+	}
+
+	/* Mark request as `sent' *before* we actually send it,
+	 * because doing if after could erase the REQ_STATUS_RCVD
+	 * status in case of a very fast reply.
+	 */
+	req->status = REQ_STATUS_SENT;
+	err = ib_post_send(rdma->qp, &wr, &bad_wr);
+	if (err)
+		goto send_error;
+
+	/* Success */
+	return 0;
+
+ /* Handle errors that happened during or while preparing the send: */
+ send_error:
+	req->status = REQ_STATUS_ERROR;
+	kfree(c);
+	p9_debug(P9_DEBUG_ERROR, "Error %d in rdma_request()\n", err);
+
+	/* Ach.
+	 *  We did recv_post(), but not send. We have one recv_post in excess.
+	 */
+	atomic_inc(&rdma->excess_rc);
+	return err;
+
+ /* Handle errors that happened during or while preparing post_recv(): */
+ recv_error:
+	kfree(rpl_context);
+	spin_lock_irqsave(&rdma->req_lock, flags);
+	if (rdma->state < P9_RDMA_CLOSING) {
+		rdma->state = P9_RDMA_CLOSING;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+		rdma_disconnect(rdma->cm_id);
+	} else
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+	return err;
+}
+
+static void rdma_close(struct p9_client *client)
+{
+	struct p9_trans_rdma *rdma;
+
+	if (!client)
+		return;
+
+	rdma = client->trans;
+	if (!rdma)
+		return;
+
+	client->status = Disconnected;
+	rdma_disconnect(rdma->cm_id);
+	rdma_destroy_trans(rdma);
+}
+
+/**
+ * alloc_rdma - Allocate and initialize the rdma transport structure
+ * @opts: Mount options structure
+ */
+static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts)
+{
+	struct p9_trans_rdma *rdma;
+
+	rdma = kzalloc(sizeof(struct p9_trans_rdma), GFP_KERNEL);
+	if (!rdma)
+		return NULL;
+
+	rdma->sq_depth = opts->sq_depth;
+	rdma->rq_depth = opts->rq_depth;
+	rdma->timeout = opts->timeout;
+	spin_lock_init(&rdma->req_lock);
+	init_completion(&rdma->cm_done);
+	sema_init(&rdma->sq_sem, rdma->sq_depth);
+	sema_init(&rdma->rq_sem, rdma->rq_depth);
+	atomic_set(&rdma->excess_rc, 0);
+
+	return rdma;
+}
+
+static int rdma_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	/* Nothing to do here.
+	 * We will take care of it (if we have to) in rdma_cancelled()
+	 */
+	return 1;
+}
+
+/* A request has been fully flushed without a reply.
+ * That means we have posted one buffer in excess.
+ */
+static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	atomic_inc(&rdma->excess_rc);
+	return 0;
+}
+
+static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma)
+{
+	struct sockaddr_in cl = {
+		.sin_family = AF_INET,
+		.sin_addr.s_addr = htonl(INADDR_ANY),
+	};
+	int port, err = -EINVAL;
+
+	for (port = P9_DEF_MAX_RESVPORT; port >= P9_DEF_MIN_RESVPORT; port--) {
+		cl.sin_port = htons((ushort)port);
+		err = rdma_bind_addr(rdma->cm_id, (struct sockaddr *)&cl);
+		if (err != -EADDRINUSE)
+			break;
+	}
+	return err;
+}
+
+/**
+ * trans_create_rdma - Transport method for creating atransport instance
+ * @client: client instance
+ * @addr: IP address string
+ * @args: Mount options string
+ */
+static int
+rdma_create_trans(struct p9_client *client, const char *addr, char *args)
+{
+	int err;
+	struct p9_rdma_opts opts;
+	struct p9_trans_rdma *rdma;
+	struct rdma_conn_param conn_param;
+	struct ib_qp_init_attr qp_attr;
+	struct ib_cq_init_attr cq_attr = {};
+
+	if (addr == NULL)
+		return -EINVAL;
+
+	/* Parse the transport specific mount options */
+	err = parse_opts(args, &opts);
+	if (err < 0)
+		return err;
+
+	/* Create and initialize the RDMA transport structure */
+	rdma = alloc_rdma(&opts);
+	if (!rdma)
+		return -ENOMEM;
+
+	/* Create the RDMA CM ID */
+	rdma->cm_id = rdma_create_id(&init_net, p9_cm_event_handler, client,
+				     RDMA_PS_TCP, IB_QPT_RC);
+	if (IS_ERR(rdma->cm_id))
+		goto error;
+
+	/* Associate the client with the transport */
+	client->trans = rdma;
+
+	/* Bind to a privileged port if we need to */
+	if (opts.privport) {
+		err = p9_rdma_bind_privport(rdma);
+		if (err < 0) {
+			pr_err("%s (%d): problem binding to privport: %d\n",
+			       __func__, task_pid_nr(current), -err);
+			goto error;
+		}
+	}
+
+	/* Resolve the server's address */
+	rdma->addr.sin_family = AF_INET;
+	rdma->addr.sin_addr.s_addr = in_aton(addr);
+	rdma->addr.sin_port = htons(opts.port);
+	err = rdma_resolve_addr(rdma->cm_id, NULL,
+				(struct sockaddr *)&rdma->addr,
+				rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ADDR_RESOLVED))
+		goto error;
+
+	/* Resolve the route to the server */
+	err = rdma_resolve_route(rdma->cm_id, rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED))
+		goto error;
+
+	/* Create the Completion Queue */
+	cq_attr.cqe = opts.sq_depth + opts.rq_depth + 1;
+	rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler,
+				cq_event_handler, client,
+				&cq_attr);
+	if (IS_ERR(rdma->cq))
+		goto error;
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+
+	/* Create the Protection Domain */
+	rdma->pd = ib_alloc_pd(rdma->cm_id->device);
+	if (IS_ERR(rdma->pd))
+		goto error;
+
+	/* Create the Queue Pair */
+	memset(&qp_attr, 0, sizeof qp_attr);
+	qp_attr.event_handler = qp_event_handler;
+	qp_attr.qp_context = client;
+	qp_attr.cap.max_send_wr = opts.sq_depth;
+	qp_attr.cap.max_recv_wr = opts.rq_depth;
+	qp_attr.cap.max_send_sge = P9_RDMA_SEND_SGE;
+	qp_attr.cap.max_recv_sge = P9_RDMA_RECV_SGE;
+	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	qp_attr.qp_type = IB_QPT_RC;
+	qp_attr.send_cq = rdma->cq;
+	qp_attr.recv_cq = rdma->cq;
+	err = rdma_create_qp(rdma->cm_id, rdma->pd, &qp_attr);
+	if (err)
+		goto error;
+	rdma->qp = rdma->cm_id->qp;
+
+	/* Request a connection */
+	memset(&conn_param, 0, sizeof(conn_param));
+	conn_param.private_data = NULL;
+	conn_param.private_data_len = 0;
+	conn_param.responder_resources = P9_RDMA_IRD;
+	conn_param.initiator_depth = P9_RDMA_ORD;
+	err = rdma_connect(rdma->cm_id, &conn_param);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_CONNECTED))
+		goto error;
+
+	client->status = Connected;
+
+	return 0;
+
+error:
+	rdma_destroy_trans(rdma);
+	return -ENOTCONN;
+}
+
+static struct p9_trans_module p9_rdma_trans = {
+	.name = "rdma",
+	.maxsize = P9_RDMA_MAXSIZE,
+	.def = 0,
+	.owner = THIS_MODULE,
+	.create = rdma_create_trans,
+	.close = rdma_close,
+	.request = rdma_request,
+	.cancel = rdma_cancel,
+	.cancelled = rdma_cancelled,
+};
+
+/**
+ * p9_trans_rdma_init - Register the 9P RDMA transport driver
+ */
+static int __init p9_trans_rdma_init(void)
+{
+	v9fs_register_trans(&p9_rdma_trans);
+	return 0;
+}
+
+static void __exit p9_trans_rdma_exit(void)
+{
+	v9fs_unregister_trans(&p9_rdma_trans);
+}
+
+module_init(p9_trans_rdma_init);
+module_exit(p9_trans_rdma_exit);
+
+MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>");
+MODULE_DESCRIPTION("RDMA Transport for 9P");
+MODULE_LICENSE("Dual BSD/GPL");

addons/9p/src/4.4.180/trans_virtio.c

@@ -0,0 +1,788 @@
+/*
+ * The Virtio 9p transport driver
+ *
+ * This is a block based transport driver based on the lguest block driver
+ * code.
+ *
+ *  Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation
+ *
+ *  Based on virtio console driver
+ *  Copyright (C) 2006, 2007 Rusty Russell, IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <linux/parser.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <linux/scatterlist.h>
+#include <linux/swap.h>
+#include <linux/virtio.h>
+#include <linux/virtio_9p.h>
+#include "trans_common.h"
+
+#define VIRTQUEUE_NUM	128
+
+/* a single mutex to manage channel initialization and attachment */
+static DEFINE_MUTEX(virtio_9p_lock);
+static DECLARE_WAIT_QUEUE_HEAD(vp_wq);
+static atomic_t vp_pinned = ATOMIC_INIT(0);
+
+/**
+ * struct virtio_chan - per-instance transport information
+ * @initialized: whether the channel is initialized
+ * @inuse: whether the channel is in use
+ * @lock: protects multiple elements within this structure
+ * @client: client instance
+ * @vdev: virtio dev associated with this channel
+ * @vq: virtio queue associated with this channel
+ * @sg: scatter gather list which is used to pack a request (protected?)
+ *
+ * We keep all per-channel information in a structure.
+ * This structure is allocated within the devices dev->mem space.
+ * A pointer to the structure will get put in the transport private.
+ *
+ */
+
+struct virtio_chan {
+	bool inuse;
+
+	spinlock_t lock;
+
+	struct p9_client *client;
+	struct virtio_device *vdev;
+	struct virtqueue *vq;
+	int ring_bufs_avail;
+	wait_queue_head_t *vc_wq;
+	/* This is global limit. Since we don't have a global structure,
+	 * will be placing it in each channel.
+	 */
+	unsigned long p9_max_pages;
+	/* Scatterlist: can be too big for stack. */
+	struct scatterlist sg[VIRTQUEUE_NUM];
+
+	int tag_len;
+	/*
+	 * tag name to identify a mount Non-null terminated
+	 */
+	char *tag;
+
+	struct list_head chan_list;
+};
+
+static struct list_head virtio_chan_list;
+
+/* How many bytes left in this page. */
+static unsigned int rest_of_page(void *data)
+{
+	return PAGE_SIZE - ((unsigned long)data % PAGE_SIZE);
+}
+
+/**
+ * p9_virtio_close - reclaim resources of a channel
+ * @client: client instance
+ *
+ * This reclaims a channel by freeing its resources and
+ * reseting its inuse flag.
+ *
+ */
+
+static void p9_virtio_close(struct p9_client *client)
+{
+	struct virtio_chan *chan = client->trans;
+
+	mutex_lock(&virtio_9p_lock);
+	if (chan)
+		chan->inuse = false;
+	mutex_unlock(&virtio_9p_lock);
+}
+
+/**
+ * req_done - callback which signals activity from the server
+ * @vq: virtio queue activity was received on
+ *
+ * This notifies us that the server has triggered some activity
+ * on the virtio channel - most likely a response to request we
+ * sent.  Figure out which requests now have responses and wake up
+ * those threads.
+ *
+ * Bugs: could do with some additional sanity checking, but appears to work.
+ *
+ */
+
+static void req_done(struct virtqueue *vq)
+{
+	struct virtio_chan *chan = vq->vdev->priv;
+	struct p9_fcall *rc;
+	unsigned int len;
+	struct p9_req_t *req;
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_TRANS, ": request done\n");
+
+	while (1) {
+		spin_lock_irqsave(&chan->lock, flags);
+		rc = virtqueue_get_buf(chan->vq, &len);
+		if (rc == NULL) {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			break;
+		}
+		chan->ring_bufs_avail = 1;
+		spin_unlock_irqrestore(&chan->lock, flags);
+		/* Wakeup if anyone waiting for VirtIO ring space. */
+		wake_up(chan->vc_wq);
+		p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc);
+		p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
+		req = p9_tag_lookup(chan->client, rc->tag);
+		p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
+	}
+}
+
+/**
+ * pack_sg_list - pack a scatter gather list from a linear buffer
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @limit: maximum segment to pack data to
+ * @data: data to pack into scatter/gather list
+ * @count: amount of data to pack into the scatter/gather list
+ *
+ * sg_lists have multiple segments of various sizes.  This will pack
+ * arbitrary data into an existing scatter gather list, segmenting the
+ * data as necessary within constraints.
+ *
+ */
+
+static int pack_sg_list(struct scatterlist *sg, int start,
+			int limit, char *data, int count)
+{
+	int s;
+	int index = start;
+
+	while (count) {
+		s = rest_of_page(data);
+		if (s > count)
+			s = count;
+		BUG_ON(index >= limit);
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
+		sg_set_buf(&sg[index++], data, s);
+		count -= s;
+		data += s;
+	}
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
+	return index-start;
+}
+
+/* We don't currently allow canceling of virtio requests */
+static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
+/**
+ * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
+ * this takes a list of pages.
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @pdata: a list of pages to add into sg.
+ * @nr_pages: number of pages to pack into the scatter/gather list
+ * @offs: amount of data in the beginning of first page _not_ to pack
+ * @count: amount of data to pack into the scatter/gather list
+ */
+static int
+pack_sg_list_p(struct scatterlist *sg, int start, int limit,
+	       struct page **pdata, int nr_pages, size_t offs, int count)
+{
+	int i = 0, s;
+	int data_off = offs;
+	int index = start;
+
+	BUG_ON(nr_pages > (limit - start));
+	/*
+	 * if the first page doesn't start at
+	 * page boundary find the offset
+	 */
+	while (nr_pages) {
+		s = PAGE_SIZE - data_off;
+		if (s > count)
+			s = count;
+		BUG_ON(index >= limit);
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
+		sg_set_page(&sg[index++], pdata[i++], s, data_off);
+		data_off = 0;
+		count -= s;
+		nr_pages--;
+	}
+
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
+	return index - start;
+}
+
+/**
+ * p9_virtio_request - issue a request
+ * @client: client instance issuing the request
+ * @req: request to be issued
+ *
+ */
+
+static int
+p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
+{
+	int err;
+	int in, out, out_sgs, in_sgs;
+	unsigned long flags;
+	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[2];
+
+	p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n");
+
+	req->status = REQ_STATUS_SENT;
+req_retry:
+	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+	/* Handle out VirtIO ring buffers */
+	out = pack_sg_list(chan->sg, 0,
+			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	in = pack_sg_list(chan->sg, out,
+			  VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+				GFP_ATOMIC);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			chan->ring_bufs_avail = 0;
+			spin_unlock_irqrestore(&chan->lock, flags);
+			err = wait_event_killable(*chan->vc_wq,
+						  chan->ring_bufs_avail);
+			if (err  == -ERESTARTSYS)
+				return err;
+
+			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
+			goto req_retry;
+		} else {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			p9_debug(P9_DEBUG_TRANS,
+				 "virtio rpc add_sgs returned failure\n");
+			return -EIO;
+		}
+	}
+	virtqueue_kick(chan->vq);
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
+	return 0;
+}
+
+static int p9_get_mapped_pages(struct virtio_chan *chan,
+			       struct page ***pages,
+			       struct iov_iter *data,
+			       int count,
+			       size_t *offs,
+			       int *need_drop)
+{
+	int nr_pages;
+	int err;
+
+	if (!iov_iter_count(data))
+		return 0;
+
+	if (!(data->type & ITER_KVEC)) {
+		int n;
+		/*
+		 * We allow only p9_max_pages pinned. We wait for the
+		 * Other zc request to finish here
+		 */
+		if (atomic_read(&vp_pinned) >= chan->p9_max_pages) {
+			err = wait_event_killable(vp_wq,
+			      (atomic_read(&vp_pinned) < chan->p9_max_pages));
+			if (err == -ERESTARTSYS)
+				return err;
+		}
+		n = iov_iter_get_pages_alloc(data, pages, count, offs);
+		if (n < 0)
+			return n;
+		*need_drop = 1;
+		nr_pages = DIV_ROUND_UP(n + *offs, PAGE_SIZE);
+		atomic_add(nr_pages, &vp_pinned);
+		return n;
+	} else {
+		/* kernel buffer, no need to pin pages */
+		int index;
+		size_t len;
+		void *p;
+
+		/* we'd already checked that it's non-empty */
+		while (1) {
+			len = iov_iter_single_seg_count(data);
+			if (likely(len)) {
+				p = data->kvec->iov_base + data->iov_offset;
+				break;
+			}
+			iov_iter_advance(data, 0);
+		}
+		if (len > count)
+			len = count;
+
+		nr_pages = DIV_ROUND_UP((unsigned long)p + len, PAGE_SIZE) -
+			   (unsigned long)p / PAGE_SIZE;
+
+		*pages = kmalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+		if (!*pages)
+			return -ENOMEM;
+
+		*need_drop = 0;
+		p -= (*offs = (unsigned long)p % PAGE_SIZE);
+		for (index = 0; index < nr_pages; index++) {
+			if (is_vmalloc_addr(p))
+				(*pages)[index] = vmalloc_to_page(p);
+			else
+				(*pages)[index] = kmap_to_page(p);
+			p += PAGE_SIZE;
+		}
+		return len;
+	}
+}
+
+/**
+ * p9_virtio_zc_request - issue a zero copy request
+ * @client: client instance issuing the request
+ * @req: request to be issued
+ * @uidata: user bffer that should be ued for zero copy read
+ * @uodata: user buffer that shoud be user for zero copy write
+ * @inlen: read buffer size
+ * @olen: write buffer size
+ * @hdrlen: reader header size, This is the size of response protocol data
+ *
+ */
+static int
+p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
+		     struct iov_iter *uidata, struct iov_iter *uodata,
+		     int inlen, int outlen, int in_hdr_len)
+{
+	int in, out, err, out_sgs, in_sgs;
+	unsigned long flags;
+	int in_nr_pages = 0, out_nr_pages = 0;
+	struct page **in_pages = NULL, **out_pages = NULL;
+	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[4];
+	size_t offs;
+	int need_drop = 0;
+
+	p9_debug(P9_DEBUG_TRANS, "virtio request\n");
+
+	if (uodata) {
+		__le32 sz;
+		int n = p9_get_mapped_pages(chan, &out_pages, uodata,
+					    outlen, &offs, &need_drop);
+		if (n < 0)
+			return n;
+		out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
+		if (n != outlen) {
+			__le32 v = cpu_to_le32(n);
+			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			outlen = n;
+		}
+		/* The size field of the message must include the length of the
+		 * header and the length of the data.  We didn't actually know
+		 * the length of the data until this point so add it in now.
+		 */
+		sz = cpu_to_le32(req->tc->size + outlen);
+		memcpy(&req->tc->sdata[0], &sz, sizeof(sz));
+	} else if (uidata) {
+		int n = p9_get_mapped_pages(chan, &in_pages, uidata,
+					    inlen, &offs, &need_drop);
+		if (n < 0)
+			return n;
+		in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
+		if (n != inlen) {
+			__le32 v = cpu_to_le32(n);
+			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			inlen = n;
+		}
+	}
+	req->status = REQ_STATUS_SENT;
+req_retry_pinned:
+	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+
+	/* out data */
+	out = pack_sg_list(chan->sg, 0,
+			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	if (out_pages) {
+		sgs[out_sgs++] = chan->sg + out;
+		out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
+				      out_pages, out_nr_pages, offs, outlen);
+	}
+		
+	/*
+	 * Take care of in data
+	 * For example TREAD have 11.
+	 * 11 is the read/write header = PDU Header(7) + IO Size (4).
+	 * Arrange in such a way that server places header in the
+	 * alloced memory and payload onto the user buffer.
+	 */
+	in = pack_sg_list(chan->sg, out,
+			  VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	if (in_pages) {
+		sgs[out_sgs + in_sgs++] = chan->sg + out + in;
+		in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM,
+				     in_pages, in_nr_pages, offs, inlen);
+	}
+
+	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
+				GFP_ATOMIC);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			chan->ring_bufs_avail = 0;
+			spin_unlock_irqrestore(&chan->lock, flags);
+			err = wait_event_killable(*chan->vc_wq,
+						  chan->ring_bufs_avail);
+			if (err  == -ERESTARTSYS)
+				goto err_out;
+
+			p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
+			goto req_retry_pinned;
+		} else {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			p9_debug(P9_DEBUG_TRANS,
+				 "virtio rpc add_sgs returned failure\n");
+			err = -EIO;
+			goto err_out;
+		}
+	}
+	virtqueue_kick(chan->vq);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
+	err = wait_event_killable(*req->wq, req->status >= REQ_STATUS_RCVD);
+	/*
+	 * Non kernel buffers are pinned, unpin them
+	 */
+err_out:
+	if (need_drop) {
+		if (in_pages) {
+			p9_release_pages(in_pages, in_nr_pages);
+			atomic_sub(in_nr_pages, &vp_pinned);
+		}
+		if (out_pages) {
+			p9_release_pages(out_pages, out_nr_pages);
+			atomic_sub(out_nr_pages, &vp_pinned);
+		}
+		/* wakeup anybody waiting for slots to pin pages */
+		wake_up(&vp_wq);
+	}
+	kfree(in_pages);
+	kfree(out_pages);
+	return err;
+}
+
+static ssize_t p9_mount_tag_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct virtio_chan *chan;
+	struct virtio_device *vdev;
+
+	vdev = dev_to_virtio(dev);
+	chan = vdev->priv;
+
+	memcpy(buf, chan->tag, chan->tag_len);
+	buf[chan->tag_len] = 0;
+
+	return chan->tag_len + 1;
+}
+
+static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL);
+
+/**
+ * p9_virtio_probe - probe for existence of 9P virtio channels
+ * @vdev: virtio device to probe
+ *
+ * This probes for existing virtio channels.
+ *
+ */
+
+static int p9_virtio_probe(struct virtio_device *vdev)
+{
+	__u16 tag_len;
+	char *tag;
+	int err;
+	struct virtio_chan *chan;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL);
+	if (!chan) {
+		pr_err("Failed to allocate virtio 9P channel\n");
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	chan->vdev = vdev;
+
+	/* We expect one virtqueue, for requests. */
+	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
+	if (IS_ERR(chan->vq)) {
+		err = PTR_ERR(chan->vq);
+		goto out_free_chan;
+	}
+	chan->vq->vdev->priv = chan;
+	spin_lock_init(&chan->lock);
+
+	sg_init_table(chan->sg, VIRTQUEUE_NUM);
+
+	chan->inuse = false;
+	if (virtio_has_feature(vdev, VIRTIO_9P_MOUNT_TAG)) {
+		virtio_cread(vdev, struct virtio_9p_config, tag_len, &tag_len);
+	} else {
+		err = -EINVAL;
+		goto out_free_vq;
+	}
+	tag = kmalloc(tag_len, GFP_KERNEL);
+	if (!tag) {
+		err = -ENOMEM;
+		goto out_free_vq;
+	}
+
+	virtio_cread_bytes(vdev, offsetof(struct virtio_9p_config, tag),
+			   tag, tag_len);
+	chan->tag = tag;
+	chan->tag_len = tag_len;
+	err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	if (err) {
+		goto out_free_tag;
+	}
+	chan->vc_wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
+	if (!chan->vc_wq) {
+		err = -ENOMEM;
+		goto out_free_tag;
+	}
+	init_waitqueue_head(chan->vc_wq);
+	chan->ring_bufs_avail = 1;
+	/* Ceiling limit to avoid denial of service attacks */
+	chan->p9_max_pages = nr_free_buffer_pages()/4;
+
+	virtio_device_ready(vdev);
+
+	mutex_lock(&virtio_9p_lock);
+	list_add_tail(&chan->chan_list, &virtio_chan_list);
+	mutex_unlock(&virtio_9p_lock);
+
+	/* Let udev rules use the new mount_tag attribute. */
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
+	return 0;
+
+out_free_tag:
+	kfree(tag);
+out_free_vq:
+	vdev->config->del_vqs(vdev);
+out_free_chan:
+	kfree(chan);
+fail:
+	return err;
+}
+
+
+/**
+ * p9_virtio_create - allocate a new virtio channel
+ * @client: client instance invoking this transport
+ * @devname: string identifying the channel to connect to (unused)
+ * @args: args passed from sys_mount() for per-transport options (unused)
+ *
+ * This sets up a transport channel for 9p communication.  Right now
+ * we only match the first available channel, but eventually we couldlook up
+ * alternate channels by matching devname versus a virtio_config entry.
+ * We use a simple reference count mechanism to ensure that only a single
+ * mount has a channel open at a time.
+ *
+ */
+
+static int
+p9_virtio_create(struct p9_client *client, const char *devname, char *args)
+{
+	struct virtio_chan *chan;
+	int ret = -ENOENT;
+	int found = 0;
+
+	if (devname == NULL)
+		return -EINVAL;
+
+	mutex_lock(&virtio_9p_lock);
+	list_for_each_entry(chan, &virtio_chan_list, chan_list) {
+		if (!strncmp(devname, chan->tag, chan->tag_len) &&
+		    strlen(devname) == chan->tag_len) {
+			if (!chan->inuse) {
+				chan->inuse = true;
+				found = 1;
+				break;
+			}
+			ret = -EBUSY;
+		}
+	}
+	mutex_unlock(&virtio_9p_lock);
+
+	if (!found) {
+		pr_err("no channels available\n");
+		return ret;
+	}
+
+	client->trans = (void *)chan;
+	client->status = Connected;
+	chan->client = client;
+
+	return 0;
+}
+
+/**
+ * p9_virtio_remove - clean up resources associated with a virtio device
+ * @vdev: virtio device to remove
+ *
+ */
+
+static void p9_virtio_remove(struct virtio_device *vdev)
+{
+	struct virtio_chan *chan = vdev->priv;
+	unsigned long warning_time;
+
+	mutex_lock(&virtio_9p_lock);
+
+	/* Remove self from list so we don't get new users. */
+	list_del(&chan->chan_list);
+	warning_time = jiffies;
+
+	/* Wait for existing users to close. */
+	while (chan->inuse) {
+		mutex_unlock(&virtio_9p_lock);
+		msleep(250);
+		if (time_after(jiffies, warning_time + 10 * HZ)) {
+			dev_emerg(&vdev->dev,
+				  "p9_virtio_remove: waiting for device in use.\n");
+			warning_time = jiffies;
+		}
+		mutex_lock(&virtio_9p_lock);
+	}
+
+	mutex_unlock(&virtio_9p_lock);
+
+	vdev->config->reset(vdev);
+	vdev->config->del_vqs(vdev);
+
+	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+	kfree(chan->tag);
+	kfree(chan->vc_wq);
+	kfree(chan);
+
+}
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static unsigned int features[] = {
+	VIRTIO_9P_MOUNT_TAG,
+};
+
+/* The standard "struct lguest_driver": */
+static struct virtio_driver p9_virtio_drv = {
+	.feature_table  = features,
+	.feature_table_size = ARRAY_SIZE(features),
+	.driver.name    = KBUILD_MODNAME,
+	.driver.owner	= THIS_MODULE,
+	.id_table	= id_table,
+	.probe		= p9_virtio_probe,
+	.remove		= p9_virtio_remove,
+};
+
+static struct p9_trans_module p9_virtio_trans = {
+	.name = "virtio",
+	.create = p9_virtio_create,
+	.close = p9_virtio_close,
+	.request = p9_virtio_request,
+	.zc_request = p9_virtio_zc_request,
+	.cancel = p9_virtio_cancel,
+	/*
+	 * We leave one entry for input and one entry for response
+	 * headers. We also skip one more entry to accomodate, address
+	 * that are not at page boundary, that can result in an extra
+	 * page in zero copy.
+	 */
+	.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
+	.def = 1,
+	.owner = THIS_MODULE,
+};
+
+/* The standard init function */
+static int __init p9_virtio_init(void)
+{
+	INIT_LIST_HEAD(&virtio_chan_list);
+
+	v9fs_register_trans(&p9_virtio_trans);
+	return register_virtio_driver(&p9_virtio_drv);
+}
+
+static void __exit p9_virtio_cleanup(void)
+{
+	unregister_virtio_driver(&p9_virtio_drv);
+	v9fs_unregister_trans(&p9_virtio_trans);
+}
+
+module_init(p9_virtio_init);
+module_exit(p9_virtio_cleanup);
+
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_DESCRIPTION("Virtio 9p Transport");
+MODULE_LICENSE("GPL");

addons/9p/src/4.4.180/util.c

@@ -0,0 +1,141 @@
+/*
+ *  net/9p/util.c
+ *
+ *  This file contains some helper functions
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+
+/**
+ * struct p9_idpool - per-connection accounting for tag idpool
+ * @lock: protects the pool
+ * @pool: idr to allocate tag id from
+ *
+ */
+
+struct p9_idpool {
+	spinlock_t lock;
+	struct idr pool;
+};
+
+/**
+ * p9_idpool_create - create a new per-connection id pool
+ *
+ */
+
+struct p9_idpool *p9_idpool_create(void)
+{
+	struct p9_idpool *p;
+
+	p = kmalloc(sizeof(struct p9_idpool), GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&p->lock);
+	idr_init(&p->pool);
+
+	return p;
+}
+EXPORT_SYMBOL(p9_idpool_create);
+
+/**
+ * p9_idpool_destroy - create a new per-connection id pool
+ * @p: idpool to destroy
+ */
+
+void p9_idpool_destroy(struct p9_idpool *p)
+{
+	idr_destroy(&p->pool);
+	kfree(p);
+}
+EXPORT_SYMBOL(p9_idpool_destroy);
+
+/**
+ * p9_idpool_get - allocate numeric id from pool
+ * @p: pool to allocate from
+ *
+ * Bugs: This seems to be an awful generic function, should it be in idr.c with
+ *            the lock included in struct idr?
+ */
+
+int p9_idpool_get(struct p9_idpool *p)
+{
+	int i;
+	unsigned long flags;
+
+	idr_preload(GFP_NOFS);
+	spin_lock_irqsave(&p->lock, flags);
+
+	/* no need to store exactly p, we just need something non-null */
+	i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT);
+
+	spin_unlock_irqrestore(&p->lock, flags);
+	idr_preload_end();
+	if (i < 0)
+		return -1;
+
+	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
+	return i;
+}
+EXPORT_SYMBOL(p9_idpool_get);
+
+/**
+ * p9_idpool_put - release numeric id from pool
+ * @id: numeric id which is being released
+ * @p: pool to release id into
+ *
+ * Bugs: This seems to be an awful generic function, should it be in idr.c with
+ *            the lock included in struct idr?
+ */
+
+void p9_idpool_put(int id, struct p9_idpool *p)
+{
+	unsigned long flags;
+
+	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
+
+	spin_lock_irqsave(&p->lock, flags);
+	idr_remove(&p->pool, id);
+	spin_unlock_irqrestore(&p->lock, flags);
+}
+EXPORT_SYMBOL(p9_idpool_put);
+
+/**
+ * p9_idpool_check - check if the specified id is available
+ * @id: id to check
+ * @p: pool to check
+ */
+
+int p9_idpool_check(int id, struct p9_idpool *p)
+{
+	return idr_find(&p->pool, id) != NULL;
+}
+EXPORT_SYMBOL(p9_idpool_check);
+

addons/9p/src/4.4.180/v9fs.c

@@ -0,0 +1,700 @@
+/*
+ *  linux/fs/9p/v9fs.c
+ *
+ *  This file contains functions assisting in mapping VFS to 9P2000
+ *
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+
+static DEFINE_SPINLOCK(v9fs_sessionlist_lock);
+static LIST_HEAD(v9fs_sessionlist);
+struct kmem_cache *v9fs_inode_cache;
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ *  NOTE: each transport will parse its own options
+ */
+
+enum {
+	/* Options that take integer arguments */
+	Opt_debug, Opt_dfltuid, Opt_dfltgid, Opt_afid,
+	/* String options */
+	Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag,
+	/* Options that take no arguments */
+	Opt_nodevmap,
+	/* Cache options */
+	Opt_cache_loose, Opt_fscache, Opt_mmap,
+	/* Access options */
+	Opt_access, Opt_posixacl,
+	/* Lock timeout option */
+	Opt_locktimeout,
+	/* Error token */
+	Opt_err
+};
+
+static const match_table_t tokens = {
+	{Opt_debug, "debug=%x"},
+	{Opt_dfltuid, "dfltuid=%u"},
+	{Opt_dfltgid, "dfltgid=%u"},
+	{Opt_afid, "afid=%u"},
+	{Opt_uname, "uname=%s"},
+	{Opt_remotename, "aname=%s"},
+	{Opt_nodevmap, "nodevmap"},
+	{Opt_cache, "cache=%s"},
+	{Opt_cache_loose, "loose"},
+	{Opt_fscache, "fscache"},
+	{Opt_mmap, "mmap"},
+	{Opt_cachetag, "cachetag=%s"},
+	{Opt_access, "access=%s"},
+	{Opt_posixacl, "posixacl"},
+	{Opt_locktimeout, "locktimeout=%u"},
+	{Opt_err, NULL}
+};
+
+/* Interpret mount options for cache mode */
+static int get_cache_mode(char *s)
+{
+	int version = -EINVAL;
+
+	if (!strcmp(s, "loose")) {
+		version = CACHE_LOOSE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: loose\n");
+	} else if (!strcmp(s, "fscache")) {
+		version = CACHE_FSCACHE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n");
+	} else if (!strcmp(s, "mmap")) {
+		version = CACHE_MMAP;
+		p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n");
+	} else if (!strcmp(s, "none")) {
+		version = CACHE_NONE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: none\n");
+	} else
+		pr_info("Unknown Cache mode %s\n", s);
+	return version;
+}
+
+/**
+ * v9fs_parse_options - parse mount options into session structure
+ * @v9ses: existing v9fs session information
+ *
+ * Return 0 upon success, -ERRNO upon failure.
+ */
+
+static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
+{
+	char *options, *tmp_options;
+	substring_t args[MAX_OPT_ARGS];
+	char *p;
+	int option = 0;
+	char *s, *e;
+	int ret = 0;
+
+	/* setup defaults */
+	v9ses->afid = ~0;
+	v9ses->debug = 0;
+	v9ses->cache = CACHE_NONE;
+#ifdef CONFIG_9P_FSCACHE
+	v9ses->cachetag = NULL;
+#endif
+	v9ses->session_lock_timeout = P9_LOCK_TIMEOUT;
+
+	if (!opts)
+		return 0;
+
+	tmp_options = kstrdup(opts, GFP_KERNEL);
+	if (!tmp_options) {
+		ret = -ENOMEM;
+		goto fail_option_alloc;
+	}
+	options = tmp_options;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token, r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_debug:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->debug = option;
+#ifdef CONFIG_NET_9P_DEBUG
+			p9_debug_level = option;
+#endif
+			break;
+
+		case Opt_dfltuid:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->dfltuid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(v9ses->dfltuid)) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "uid field, but not a uid?\n");
+				ret = -EINVAL;
+				continue;
+			}
+			break;
+		case Opt_dfltgid:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->dfltgid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(v9ses->dfltgid)) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "gid field, but not a gid?\n");
+				ret = -EINVAL;
+				continue;
+			}
+			break;
+		case Opt_afid:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			v9ses->afid = option;
+			break;
+		case Opt_uname:
+			kfree(v9ses->uname);
+			v9ses->uname = match_strdup(&args[0]);
+			if (!v9ses->uname) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
+			break;
+		case Opt_remotename:
+			kfree(v9ses->aname);
+			v9ses->aname = match_strdup(&args[0]);
+			if (!v9ses->aname) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
+			break;
+		case Opt_nodevmap:
+			v9ses->nodev = 1;
+			break;
+		case Opt_cache_loose:
+			v9ses->cache = CACHE_LOOSE;
+			break;
+		case Opt_fscache:
+			v9ses->cache = CACHE_FSCACHE;
+			break;
+		case Opt_mmap:
+			v9ses->cache = CACHE_MMAP;
+			break;
+		case Opt_cachetag:
+#ifdef CONFIG_9P_FSCACHE
+			v9ses->cachetag = match_strdup(&args[0]);
+#endif
+			break;
+		case Opt_cache:
+			s = match_strdup(&args[0]);
+			if (!s) {
+				ret = -ENOMEM;
+				p9_debug(P9_DEBUG_ERROR,
+					 "problem allocating copy of cache arg\n");
+				goto free_and_return;
+			}
+			ret = get_cache_mode(s);
+			if (ret == -EINVAL) {
+				kfree(s);
+				goto free_and_return;
+			}
+
+			v9ses->cache = ret;
+			kfree(s);
+			break;
+
+		case Opt_access:
+			s = match_strdup(&args[0]);
+			if (!s) {
+				ret = -ENOMEM;
+				p9_debug(P9_DEBUG_ERROR,
+					 "problem allocating copy of access arg\n");
+				goto free_and_return;
+			}
+
+			v9ses->flags &= ~V9FS_ACCESS_MASK;
+			if (strcmp(s, "user") == 0)
+				v9ses->flags |= V9FS_ACCESS_USER;
+			else if (strcmp(s, "any") == 0)
+				v9ses->flags |= V9FS_ACCESS_ANY;
+			else if (strcmp(s, "client") == 0) {
+				v9ses->flags |= V9FS_ACCESS_CLIENT;
+			} else {
+				uid_t uid;
+				v9ses->flags |= V9FS_ACCESS_SINGLE;
+				uid = simple_strtoul(s, &e, 10);
+				if (*e != '\0') {
+					ret = -EINVAL;
+					pr_info("Unknown access argument %s\n",
+						s);
+					kfree(s);
+					goto free_and_return;
+				}
+				v9ses->uid = make_kuid(current_user_ns(), uid);
+				if (!uid_valid(v9ses->uid)) {
+					ret = -EINVAL;
+					pr_info("Uknown uid %s\n", s);
+					kfree(s);
+					goto free_and_return;
+				}
+			}
+
+			kfree(s);
+			break;
+
+		case Opt_posixacl:
+#ifdef CONFIG_9P_FS_POSIX_ACL
+			v9ses->flags |= V9FS_POSIX_ACL;
+#else
+			p9_debug(P9_DEBUG_ERROR,
+				 "Not defined CONFIG_9P_FS_POSIX_ACL. Ignoring posixacl option\n");
+#endif
+			break;
+
+		case Opt_locktimeout:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			if (option < 1) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "locktimeout must be a greater than zero integer.\n");
+				ret = -EINVAL;
+				continue;
+			}
+			v9ses->session_lock_timeout = (long)option * HZ;
+			break;
+
+		default:
+			continue;
+		}
+	}
+
+free_and_return:
+	kfree(tmp_options);
+fail_option_alloc:
+	return ret;
+}
+
+/**
+ * v9fs_session_init - initialize session
+ * @v9ses: session information structure
+ * @dev_name: device being mounted
+ * @data: options
+ *
+ */
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
+		  const char *dev_name, char *data)
+{
+	struct p9_fid *fid;
+	int rc = -ENOMEM;
+
+	v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
+	if (!v9ses->uname)
+		goto err_names;
+
+	v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
+	if (!v9ses->aname)
+		goto err_names;
+	init_rwsem(&v9ses->rename_sem);
+
+	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
+	if (rc)
+		goto err_names;
+
+	v9ses->uid = INVALID_UID;
+	v9ses->dfltuid = V9FS_DEFUID;
+	v9ses->dfltgid = V9FS_DEFGID;
+
+	v9ses->clnt = p9_client_create(dev_name, data);
+	if (IS_ERR(v9ses->clnt)) {
+		rc = PTR_ERR(v9ses->clnt);
+		p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
+		goto err_bdi;
+	}
+
+	v9ses->flags = V9FS_ACCESS_USER;
+
+	if (p9_is_proto_dotl(v9ses->clnt)) {
+		v9ses->flags = V9FS_ACCESS_CLIENT;
+		v9ses->flags |= V9FS_PROTO_2000L;
+	} else if (p9_is_proto_dotu(v9ses->clnt)) {
+		v9ses->flags |= V9FS_PROTO_2000U;
+	}
+
+	rc = v9fs_parse_options(v9ses, data);
+	if (rc < 0)
+		goto err_clnt;
+
+	v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
+
+	if (!v9fs_proto_dotl(v9ses) &&
+	    ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
+		/*
+		 * We support ACCESS_CLIENT only for dotl.
+		 * Fall back to ACCESS_USER
+		 */
+		v9ses->flags &= ~V9FS_ACCESS_MASK;
+		v9ses->flags |= V9FS_ACCESS_USER;
+	}
+	/*FIXME !! */
+	/* for legacy mode, fall back to V9FS_ACCESS_ANY */
+	if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) &&
+		((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) {
+
+		v9ses->flags &= ~V9FS_ACCESS_MASK;
+		v9ses->flags |= V9FS_ACCESS_ANY;
+		v9ses->uid = INVALID_UID;
+	}
+	if (!v9fs_proto_dotl(v9ses) ||
+		!((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
+		/*
+		 * We support ACL checks on clinet only if the protocol is
+		 * 9P2000.L and access is V9FS_ACCESS_CLIENT.
+		 */
+		v9ses->flags &= ~V9FS_ACL_MASK;
+	}
+
+	fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID,
+							v9ses->aname);
+	if (IS_ERR(fid)) {
+		rc = PTR_ERR(fid);
+		p9_debug(P9_DEBUG_ERROR, "cannot attach\n");
+		goto err_clnt;
+	}
+
+	if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE)
+		fid->uid = v9ses->uid;
+	else
+		fid->uid = INVALID_UID;
+
+#ifdef CONFIG_9P_FSCACHE
+	/* register the session for caching */
+	v9fs_cache_session_get_cookie(v9ses);
+#endif
+	spin_lock(&v9fs_sessionlist_lock);
+	list_add(&v9ses->slist, &v9fs_sessionlist);
+	spin_unlock(&v9fs_sessionlist_lock);
+
+	return fid;
+
+err_clnt:
+	p9_client_destroy(v9ses->clnt);
+err_bdi:
+	bdi_destroy(&v9ses->bdi);
+err_names:
+	kfree(v9ses->uname);
+	kfree(v9ses->aname);
+	return ERR_PTR(rc);
+}
+
+/**
+ * v9fs_session_close - shutdown a session
+ * @v9ses: session information structure
+ *
+ */
+
+void v9fs_session_close(struct v9fs_session_info *v9ses)
+{
+	if (v9ses->clnt) {
+		p9_client_destroy(v9ses->clnt);
+		v9ses->clnt = NULL;
+	}
+
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->fscache) {
+		v9fs_cache_session_put_cookie(v9ses);
+		kfree(v9ses->cachetag);
+	}
+#endif
+	kfree(v9ses->uname);
+	kfree(v9ses->aname);
+
+	bdi_destroy(&v9ses->bdi);
+
+	spin_lock(&v9fs_sessionlist_lock);
+	list_del(&v9ses->slist);
+	spin_unlock(&v9fs_sessionlist_lock);
+}
+
+/**
+ * v9fs_session_cancel - terminate a session
+ * @v9ses: session to terminate
+ *
+ * mark transport as disconnected and cancel all pending requests.
+ */
+
+void v9fs_session_cancel(struct v9fs_session_info *v9ses) {
+	p9_debug(P9_DEBUG_ERROR, "cancel session %p\n", v9ses);
+	p9_client_disconnect(v9ses->clnt);
+}
+
+/**
+ * v9fs_session_begin_cancel - Begin terminate of a session
+ * @v9ses: session to terminate
+ *
+ * After this call we don't allow any request other than clunk.
+ */
+
+void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses)
+{
+	p9_debug(P9_DEBUG_ERROR, "begin cancel session %p\n", v9ses);
+	p9_client_begin_disconnect(v9ses->clnt);
+}
+
+extern int v9fs_error_init(void);
+
+static struct kobject *v9fs_kobj;
+
+#ifdef CONFIG_9P_FSCACHE
+/**
+ * caches_show - list caches associated with a session
+ *
+ * Returns the size of buffer written.
+ */
+
+static ssize_t caches_show(struct kobject *kobj,
+			   struct kobj_attribute *attr,
+			   char *buf)
+{
+	ssize_t n = 0, count = 0, limit = PAGE_SIZE;
+	struct v9fs_session_info *v9ses;
+
+	spin_lock(&v9fs_sessionlist_lock);
+	list_for_each_entry(v9ses, &v9fs_sessionlist, slist) {
+		if (v9ses->cachetag) {
+			n = snprintf(buf, limit, "%s\n", v9ses->cachetag);
+			if (n < 0) {
+				count = n;
+				break;
+			}
+
+			count += n;
+			limit -= n;
+		}
+	}
+
+	spin_unlock(&v9fs_sessionlist_lock);
+	return count;
+}
+
+static struct kobj_attribute v9fs_attr_cache = __ATTR_RO(caches);
+#endif /* CONFIG_9P_FSCACHE */
+
+static struct attribute *v9fs_attrs[] = {
+#ifdef CONFIG_9P_FSCACHE
+	&v9fs_attr_cache.attr,
+#endif
+	NULL,
+};
+
+static struct attribute_group v9fs_attr_group = {
+	.attrs = v9fs_attrs,
+};
+
+/**
+ * v9fs_sysfs_init - Initialize the v9fs sysfs interface
+ *
+ */
+
+static int __init v9fs_sysfs_init(void)
+{
+	v9fs_kobj = kobject_create_and_add("9p", fs_kobj);
+	if (!v9fs_kobj)
+		return -ENOMEM;
+
+	if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) {
+		kobject_put(v9fs_kobj);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * v9fs_sysfs_cleanup - Unregister the v9fs sysfs interface
+ *
+ */
+
+static void v9fs_sysfs_cleanup(void)
+{
+	sysfs_remove_group(v9fs_kobj, &v9fs_attr_group);
+	kobject_put(v9fs_kobj);
+}
+
+static void v9fs_inode_init_once(void *foo)
+{
+	struct v9fs_inode *v9inode = (struct v9fs_inode *)foo;
+#ifdef CONFIG_9P_FSCACHE
+	v9inode->fscache = NULL;
+#endif
+	memset(&v9inode->qid, 0, sizeof(v9inode->qid));
+	inode_init_once(&v9inode->vfs_inode);
+}
+
+/**
+ * v9fs_init_inode_cache - initialize a cache for 9P
+ * Returns 0 on success.
+ */
+static int v9fs_init_inode_cache(void)
+{
+	v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache",
+					  sizeof(struct v9fs_inode),
+					  0, (SLAB_RECLAIM_ACCOUNT|
+					      SLAB_MEM_SPREAD),
+					  v9fs_inode_init_once);
+	if (!v9fs_inode_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * v9fs_destroy_inode_cache - destroy the cache of 9P inode
+ *
+ */
+static void v9fs_destroy_inode_cache(void)
+{
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+	kmem_cache_destroy(v9fs_inode_cache);
+}
+
+static int v9fs_cache_register(void)
+{
+	int ret;
+	ret = v9fs_init_inode_cache();
+	if (ret < 0)
+		return ret;
+#ifdef CONFIG_9P_FSCACHE
+	ret = fscache_register_netfs(&v9fs_cache_netfs);
+	if (ret < 0)
+		v9fs_destroy_inode_cache();
+#endif
+	return ret;
+}
+
+static void v9fs_cache_unregister(void)
+{
+	v9fs_destroy_inode_cache();
+#ifdef CONFIG_9P_FSCACHE
+	fscache_unregister_netfs(&v9fs_cache_netfs);
+#endif
+}
+
+/**
+ * init_v9fs - Initialize module
+ *
+ */
+
+static int __init init_v9fs(void)
+{
+	int err;
+	pr_info("Installing v9fs 9p2000 file system support\n");
+	/* TODO: Setup list of registered trasnport modules */
+
+	err = v9fs_cache_register();
+	if (err < 0) {
+		pr_err("Failed to register v9fs for caching\n");
+		return err;
+	}
+
+	err = v9fs_sysfs_init();
+	if (err < 0) {
+		pr_err("Failed to register with sysfs\n");
+		goto out_cache;
+	}
+	err = register_filesystem(&v9fs_fs_type);
+	if (err < 0) {
+		pr_err("Failed to register filesystem\n");
+		goto out_sysfs_cleanup;
+	}
+
+	return 0;
+
+out_sysfs_cleanup:
+	v9fs_sysfs_cleanup();
+
+out_cache:
+	v9fs_cache_unregister();
+
+	return err;
+}
+
+/**
+ * exit_v9fs - shutdown module
+ *
+ */
+
+static void __exit exit_v9fs(void)
+{
+	v9fs_sysfs_cleanup();
+	v9fs_cache_unregister();
+	unregister_filesystem(&v9fs_fs_type);
+}
+
+module_init(init_v9fs)
+module_exit(exit_v9fs)
+
+MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>");
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>");
+MODULE_LICENSE("GPL");

addons/9p/src/4.4.180/v9fs.h

@@ -0,0 +1,226 @@
+/*
+ * V9FS definitions.
+ *
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_V9FS_H
+#define FS_9P_V9FS_H
+
+#include <linux/backing-dev.h>
+
+/**
+ * enum p9_session_flags - option flags for each 9P session
+ * @V9FS_PROTO_2000U: whether or not to use 9P2000.u extensions
+ * @V9FS_PROTO_2000L: whether or not to use 9P2000.l extensions
+ * @V9FS_ACCESS_SINGLE: only the mounting user can access the hierarchy
+ * @V9FS_ACCESS_USER: a new attach will be issued for every user (default)
+ * @V9FS_ACCESS_CLIENT: Just like user, but access check is performed on client.
+ * @V9FS_ACCESS_ANY: use a single attach for all users
+ * @V9FS_ACCESS_MASK: bit mask of different ACCESS options
+ * @V9FS_POSIX_ACL: POSIX ACLs are enforced
+ *
+ * Session flags reflect options selected by users at mount time
+ */
+#define	V9FS_ACCESS_ANY (V9FS_ACCESS_SINGLE | \
+			 V9FS_ACCESS_USER |   \
+			 V9FS_ACCESS_CLIENT)
+#define V9FS_ACCESS_MASK V9FS_ACCESS_ANY
+#define V9FS_ACL_MASK V9FS_POSIX_ACL
+
+enum p9_session_flags {
+	V9FS_PROTO_2000U	= 0x01,
+	V9FS_PROTO_2000L	= 0x02,
+	V9FS_ACCESS_SINGLE	= 0x04,
+	V9FS_ACCESS_USER	= 0x08,
+	V9FS_ACCESS_CLIENT	= 0x10,
+	V9FS_POSIX_ACL		= 0x20
+};
+
+/* possible values of ->cache */
+/**
+ * enum p9_cache_modes - user specified cache preferences
+ * @CACHE_NONE: do not cache data, dentries, or directory contents (default)
+ * @CACHE_LOOSE: cache data, dentries, and directory contents w/no consistency
+ *
+ * eventually support loose, tight, time, session, default always none
+ */
+
+enum p9_cache_modes {
+	CACHE_NONE,
+	CACHE_MMAP,
+	CACHE_LOOSE,
+	CACHE_FSCACHE,
+};
+
+/**
+ * struct v9fs_session_info - per-instance session information
+ * @flags: session options of type &p9_session_flags
+ * @nodev: set to 1 to disable device mapping
+ * @debug: debug level
+ * @afid: authentication handle
+ * @cache: cache mode of type &p9_cache_modes
+ * @cachetag: the tag of the cache associated with this session
+ * @fscache: session cookie associated with FS-Cache
+ * @uname: string user name to mount hierarchy as
+ * @aname: mount specifier for remote hierarchy
+ * @maxdata: maximum data to be sent/recvd per protocol message
+ * @dfltuid: default numeric userid to mount hierarchy as
+ * @dfltgid: default numeric groupid to mount hierarchy as
+ * @uid: if %V9FS_ACCESS_SINGLE, the numeric uid which mounted the hierarchy
+ * @clnt: reference to 9P network client instantiated for this session
+ * @slist: reference to list of registered 9p sessions
+ *
+ * This structure holds state for each session instance established during
+ * a sys_mount() .
+ *
+ * Bugs: there seems to be a lot of state which could be condensed and/or
+ * removed.
+ */
+
+struct v9fs_session_info {
+	/* options */
+	unsigned char flags;
+	unsigned char nodev;
+	unsigned short debug;
+	unsigned int afid;
+	unsigned int cache;
+#ifdef CONFIG_9P_FSCACHE
+	char *cachetag;
+	struct fscache_cookie *fscache;
+#endif
+
+	char *uname;		/* user name to mount as */
+	char *aname;		/* name of remote hierarchy being mounted */
+	unsigned int maxdata;	/* max data for client interface */
+	kuid_t dfltuid;		/* default uid/muid for legacy support */
+	kgid_t dfltgid;		/* default gid for legacy support */
+	kuid_t uid;		/* if ACCESS_SINGLE, the uid that has access */
+	struct p9_client *clnt;	/* 9p client */
+	struct list_head slist; /* list of sessions registered with v9fs */
+	struct backing_dev_info bdi;
+	struct rw_semaphore rename_sem;
+	long session_lock_timeout; /* retry interval for blocking locks */
+};
+
+/* cache_validity flags */
+#define V9FS_INO_INVALID_ATTR 0x01
+
+struct v9fs_inode {
+#ifdef CONFIG_9P_FSCACHE
+	struct mutex fscache_lock;
+	struct fscache_cookie *fscache;
+#endif
+	struct p9_qid qid;
+	unsigned int cache_validity;
+	struct p9_fid *writeback_fid;
+	struct mutex v_mutex;
+	struct inode vfs_inode;
+};
+
+static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
+{
+	return container_of(inode, struct v9fs_inode, vfs_inode);
+}
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
+									char *);
+extern void v9fs_session_close(struct v9fs_session_info *v9ses);
+extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
+extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
+extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
+			unsigned int flags);
+extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
+extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
+extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry);
+extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
+					 struct p9_fid *fid,
+					 struct super_block *sb, int new);
+extern const struct inode_operations v9fs_dir_inode_operations_dotl;
+extern const struct inode_operations v9fs_file_inode_operations_dotl;
+extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
+extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
+					      struct p9_fid *fid,
+					      struct super_block *sb, int new);
+
+/* other default globals */
+#define V9FS_PORT	564
+#define V9FS_DEFUSER	"nobody"
+#define V9FS_DEFANAME	""
+#define V9FS_DEFUID	KUIDT_INIT(-2)
+#define V9FS_DEFGID	KGIDT_INIT(-2)
+
+static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
+{
+	return (inode->i_sb->s_fs_info);
+}
+
+static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry)
+{
+	return dentry->d_sb->s_fs_info;
+}
+
+static inline int v9fs_proto_dotu(struct v9fs_session_info *v9ses)
+{
+	return v9ses->flags & V9FS_PROTO_2000U;
+}
+
+static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
+{
+	return v9ses->flags & V9FS_PROTO_2000L;
+}
+
+/**
+ * v9fs_get_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			struct super_block *sb)
+{
+	if (v9fs_proto_dotl(v9ses))
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 0);
+	else
+		return v9fs_inode_from_fid(v9ses, fid, sb, 0);
+}
+
+/**
+ * v9fs_get_new_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_new_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			    struct super_block *sb)
+{
+	if (v9fs_proto_dotl(v9ses))
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 1);
+	else
+		return v9fs_inode_from_fid(v9ses, fid, sb, 1);
+}
+
+#endif

addons/9p/src/4.4.180/v9fs_vfs.h

@@ -0,0 +1,105 @@
+/*
+ * V9FS VFS extensions.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_V9FS_VFS_H
+#define FS_9P_V9FS_VFS_H
+
+/* plan9 semantics are that created files are implicitly opened.
+ * But linux semantics are that you call create, then open.
+ * the plan9 approach is superior as it provides an atomic
+ * open.
+ * we track the create fid here. When the file is opened, if fidopen is
+ * non-zero, we use the fid and can skip some steps.
+ * there may be a better way to do this, but I don't know it.
+ * one BAD way is to clunk the fid on create, then open it again:
+ * you lose the atomicity of file open
+ */
+
+/* special case:
+ * unlink calls remove, which is an implicit clunk. So we have to track
+ * that kind of thing so that we don't try to clunk a dead fid.
+ */
+#define P9_LOCK_TIMEOUT (30*HZ)
+
+/* flags for v9fs_stat2inode() & v9fs_stat2inode_dotl() */
+#define V9FS_STAT2INODE_KEEP_ISIZE 1
+
+extern struct file_system_type v9fs_fs_type;
+extern const struct address_space_operations v9fs_addr_operations;
+extern const struct file_operations v9fs_file_operations;
+extern const struct file_operations v9fs_file_operations_dotl;
+extern const struct file_operations v9fs_dir_operations;
+extern const struct file_operations v9fs_dir_operations_dotl;
+extern const struct dentry_operations v9fs_dentry_operations;
+extern const struct dentry_operations v9fs_cached_dentry_operations;
+extern const struct file_operations v9fs_cached_file_operations;
+extern const struct file_operations v9fs_cached_file_operations_dotl;
+extern const struct file_operations v9fs_mmap_file_operations;
+extern const struct file_operations v9fs_mmap_file_operations_dotl;
+extern struct kmem_cache *v9fs_inode_cache;
+
+struct inode *v9fs_alloc_inode(struct super_block *sb);
+void v9fs_destroy_inode(struct inode *inode);
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t);
+int v9fs_init_inode(struct v9fs_session_info *v9ses,
+		    struct inode *inode, umode_t mode, dev_t);
+void v9fs_evict_inode(struct inode *inode);
+ino_t v9fs_qid2ino(struct p9_qid *qid);
+void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
+		      struct super_block *sb, unsigned int flags);
+void v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
+			   unsigned int flags);
+int v9fs_dir_release(struct inode *inode, struct file *filp);
+int v9fs_file_open(struct inode *inode, struct file *file);
+void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
+int v9fs_uflags2omode(int uflags, int extended);
+
+void v9fs_blank_wstat(struct p9_wstat *wstat);
+int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *);
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+			 int datasync);
+int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
+int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode);
+static inline void v9fs_invalidate_inode_attr(struct inode *inode)
+{
+	struct v9fs_inode *v9inode;
+	v9inode = V9FS_I(inode);
+	v9inode->cache_validity |= V9FS_INO_INVALID_ATTR;
+	return;
+}
+
+int v9fs_open_to_dotl_flags(int flags);
+
+static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size)
+{
+	/*
+	 * 32-bit need the lock, concurrent updates could break the
+	 * sequences and make i_size_read() loop forever.
+	 * 64-bit updates are atomic and can skip the locking.
+	 */
+	if (sizeof(i_size) > sizeof(long))
+		spin_lock(&inode->i_lock);
+	i_size_write(inode, i_size);
+	if (sizeof(i_size) > sizeof(long))
+		spin_unlock(&inode->i_lock);
+}
+#endif

addons/9p/src/4.4.180/vfs_addr.c

@@ -0,0 +1,351 @@
+/*
+ *  linux/fs/9p/vfs_addr.c
+ *
+ * This file contians vfs address (mmap) ops for 9P2000.
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/pagemap.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/uio.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+#include "fid.h"
+
+/**
+ * v9fs_fid_readpage - read an entire page in from 9P
+ *
+ * @fid: fid being read
+ * @page: structure to page
+ *
+ */
+static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE};
+	struct iov_iter to;
+	int retval, err;
+
+	p9_debug(P9_DEBUG_VFS, "\n");
+
+	BUG_ON(!PageLocked(page));
+
+	retval = v9fs_readpage_from_fscache(inode, page);
+	if (retval == 0)
+		return retval;
+
+	iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE);
+
+	retval = p9_client_read(fid, page_offset(page), &to, &err);
+	if (err) {
+		v9fs_uncache_page(inode, page);
+		retval = err;
+		goto done;
+	}
+
+	zero_user(page, retval, PAGE_SIZE - retval);
+	flush_dcache_page(page);
+	SetPageUptodate(page);
+
+	v9fs_readpage_to_fscache(inode, page);
+	retval = 0;
+
+done:
+	unlock_page(page);
+	return retval;
+}
+
+/**
+ * v9fs_vfs_readpage - read an entire page in from 9P
+ *
+ * @filp: file being read
+ * @page: structure to page
+ *
+ */
+
+static int v9fs_vfs_readpage(struct file *filp, struct page *page)
+{
+	return v9fs_fid_readpage(filp->private_data, page);
+}
+
+/**
+ * v9fs_vfs_readpages - read a set of pages from 9P
+ *
+ * @filp: file being read
+ * @mapping: the address space
+ * @pages: list of pages to read
+ * @nr_pages: count of pages to read
+ *
+ */
+
+static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping,
+			     struct list_head *pages, unsigned nr_pages)
+{
+	int ret = 0;
+	struct inode *inode;
+
+	inode = mapping->host;
+	p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, filp);
+
+	ret = v9fs_readpages_from_fscache(inode, mapping, pages, &nr_pages);
+	if (ret == 0)
+		return ret;
+
+	ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp);
+	p9_debug(P9_DEBUG_VFS, "  = %d\n", ret);
+	return ret;
+}
+
+/**
+ * v9fs_release_page - release the private state associated with a page
+ *
+ * Returns 1 if the page can be released, false otherwise.
+ */
+
+static int v9fs_release_page(struct page *page, gfp_t gfp)
+{
+	if (PagePrivate(page))
+		return 0;
+	return v9fs_fscache_release_page(page, gfp);
+}
+
+/**
+ * v9fs_invalidate_page - Invalidate a page completely or partially
+ *
+ * @page: structure to page
+ * @offset: offset in the page
+ */
+
+static void v9fs_invalidate_page(struct page *page, unsigned int offset,
+				 unsigned int length)
+{
+	/*
+	 * If called with zero offset, we should release
+	 * the private state assocated with the page
+	 */
+	if (offset == 0 && length == PAGE_CACHE_SIZE)
+		v9fs_fscache_invalidate_page(page);
+}
+
+static int v9fs_vfs_writepage_locked(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	loff_t size = i_size_read(inode);
+	struct iov_iter from;
+	struct bio_vec bvec;
+	int err, len;
+
+	if (page->index == size >> PAGE_CACHE_SHIFT)
+		len = size & ~PAGE_CACHE_MASK;
+	else
+		len = PAGE_CACHE_SIZE;
+
+	bvec.bv_page = page;
+	bvec.bv_offset = 0;
+	bvec.bv_len = len;
+	iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len);
+
+	/* We should have writeback_fid always set */
+	BUG_ON(!v9inode->writeback_fid);
+
+	set_page_writeback(page);
+
+	p9_client_write(v9inode->writeback_fid, page_offset(page), &from, &err);
+
+	end_page_writeback(page);
+	return err;
+}
+
+static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+	int retval;
+
+	p9_debug(P9_DEBUG_VFS, "page %p\n", page);
+
+	retval = v9fs_vfs_writepage_locked(page);
+	if (retval < 0) {
+		if (retval == -EAGAIN) {
+			redirty_page_for_writepage(wbc, page);
+			retval = 0;
+		} else {
+			SetPageError(page);
+			mapping_set_error(page->mapping, retval);
+		}
+	} else
+		retval = 0;
+
+	unlock_page(page);
+	return retval;
+}
+
+/**
+ * v9fs_launder_page - Writeback a dirty page
+ * Returns 0 on success.
+ */
+
+static int v9fs_launder_page(struct page *page)
+{
+	int retval;
+	struct inode *inode = page->mapping->host;
+
+	v9fs_fscache_wait_on_page_write(inode, page);
+	if (clear_page_dirty_for_io(page)) {
+		retval = v9fs_vfs_writepage_locked(page);
+		if (retval)
+			return retval;
+	}
+	return 0;
+}
+
+/**
+ * v9fs_direct_IO - 9P address space operation for direct I/O
+ * @iocb: target I/O control block
+ * @pos: offset in file to begin the operation
+ *
+ * The presence of v9fs_direct_IO() in the address space ops vector
+ * allowes open() O_DIRECT flags which would have failed otherwise.
+ *
+ * In the non-cached mode, we shunt off direct read and write requests before
+ * the VFS gets them, so this method should never be called.
+ *
+ * Direct IO is not 'yet' supported in the cached mode. Hence when
+ * this routine is called through generic_file_aio_read(), the read/write fails
+ * with an error.
+ *
+ */
+static ssize_t
+v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t n;
+	int err = 0;
+	if (iov_iter_rw(iter) == WRITE) {
+		n = p9_client_write(file->private_data, pos, iter, &err);
+		if (n) {
+			struct inode *inode = file_inode(file);
+			loff_t i_size = i_size_read(inode);
+			if (pos + n > i_size)
+				inode_add_bytes(inode, pos + n - i_size);
+		}
+	} else {
+		n = p9_client_read(file->private_data, pos, iter, &err);
+	}
+	return n ? n : err;
+}
+
+static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{
+	int retval = 0;
+	struct page *page;
+	struct v9fs_inode *v9inode;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	struct inode *inode = mapping->host;
+
+
+	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
+
+	v9inode = V9FS_I(inode);
+start:
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page) {
+		retval = -ENOMEM;
+		goto out;
+	}
+	BUG_ON(!v9inode->writeback_fid);
+	if (PageUptodate(page))
+		goto out;
+
+	if (len == PAGE_CACHE_SIZE)
+		goto out;
+
+	retval = v9fs_fid_readpage(v9inode->writeback_fid, page);
+	page_cache_release(page);
+	if (!retval)
+		goto start;
+out:
+	*pagep = page;
+	return retval;
+}
+
+static int v9fs_write_end(struct file *filp, struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct page *page, void *fsdata)
+{
+	loff_t last_pos = pos + copied;
+	struct inode *inode = page->mapping->host;
+
+	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
+
+	if (unlikely(copied < len)) {
+		/*
+		 * zero out the rest of the area
+		 */
+		unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+
+		zero_user(page, from + copied, len - copied);
+		flush_dcache_page(page);
+	}
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+	/*
+	 * No need to use i_size_read() here, the i_size
+	 * cannot change under us because we hold the i_mutex.
+	 */
+	if (last_pos > inode->i_size) {
+		inode_add_bytes(inode, last_pos - inode->i_size);
+		i_size_write(inode, last_pos);
+	}
+	set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+
+	return copied;
+}
+
+
+const struct address_space_operations v9fs_addr_operations = {
+	.readpage = v9fs_vfs_readpage,
+	.readpages = v9fs_vfs_readpages,
+	.set_page_dirty = __set_page_dirty_nobuffers,
+	.writepage = v9fs_vfs_writepage,
+	.write_begin = v9fs_write_begin,
+	.write_end = v9fs_write_end,
+	.releasepage = v9fs_release_page,
+	.invalidatepage = v9fs_invalidate_page,
+	.launder_page = v9fs_launder_page,
+	.direct_IO = v9fs_direct_IO,
+};

addons/9p/src/4.4.180/vfs_dentry.c

@@ -0,0 +1,122 @@
+/*
+ *  linux/fs/9p/vfs_dentry.c
+ *
+ * This file contians vfs dentry ops for the 9P2000 protocol.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * v9fs_cached_dentry_delete - called when dentry refcount equals 0
+ * @dentry:  dentry in question
+ *
+ */
+static int v9fs_cached_dentry_delete(const struct dentry *dentry)
+{
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+		 dentry, dentry);
+
+	/* Don't cache negative dentries */
+	if (d_really_is_negative(dentry))
+		return 1;
+	return 0;
+}
+
+/**
+ * v9fs_dentry_release - called when dentry is going to be freed
+ * @dentry:  dentry that is being release
+ *
+ */
+
+static void v9fs_dentry_release(struct dentry *dentry)
+{
+	struct hlist_node *p, *n;
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+		 dentry, dentry);
+	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+		p9_client_clunk(hlist_entry(p, struct p9_fid, dlist));
+	dentry->d_fsdata = NULL;
+}
+
+static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct p9_fid *fid;
+	struct inode *inode;
+	struct v9fs_inode *v9inode;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = d_inode(dentry);
+	if (!inode)
+		goto out_valid;
+
+	v9inode = V9FS_I(inode);
+	if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
+		int retval;
+		struct v9fs_session_info *v9ses;
+		fid = v9fs_fid_lookup(dentry);
+		if (IS_ERR(fid))
+			return PTR_ERR(fid);
+
+		v9ses = v9fs_inode2v9ses(inode);
+		if (v9fs_proto_dotl(v9ses))
+			retval = v9fs_refresh_inode_dotl(fid, inode);
+		else
+			retval = v9fs_refresh_inode(fid, inode);
+		if (retval == -ENOENT)
+			return 0;
+		if (retval < 0)
+			return retval;
+	}
+out_valid:
+	return 1;
+}
+
+const struct dentry_operations v9fs_cached_dentry_operations = {
+	.d_revalidate = v9fs_lookup_revalidate,
+	.d_weak_revalidate = v9fs_lookup_revalidate,
+	.d_delete = v9fs_cached_dentry_delete,
+	.d_release = v9fs_dentry_release,
+};
+
+const struct dentry_operations v9fs_dentry_operations = {
+	.d_delete = always_delete_dentry,
+	.d_release = v9fs_dentry_release,
+};

addons/9p/src/4.4.180/vfs_dir.c

@@ -0,0 +1,248 @@
+/*
+ * linux/fs/9p/vfs_dir.c
+ *
+ * This file contains vfs directory ops for the 9P2000 protocol.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * struct p9_rdir - readdir accounting
+ * @head: start offset of current dirread buffer
+ * @tail: end offset of current dirread buffer
+ * @buf: dirread buffer
+ *
+ * private structure for keeping track of readdir
+ * allocated on demand
+ */
+
+struct p9_rdir {
+	int head;
+	int tail;
+	uint8_t buf[];
+};
+
+/**
+ * dt_type - return file type
+ * @mistat: mistat structure
+ *
+ */
+
+static inline int dt_type(struct p9_wstat *mistat)
+{
+	unsigned long perm = mistat->mode;
+	int rettype = DT_REG;
+
+	if (perm & P9_DMDIR)
+		rettype = DT_DIR;
+	if (perm & P9_DMSYMLINK)
+		rettype = DT_LNK;
+
+	return rettype;
+}
+
+/**
+ * v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir
+ * @filp: opened file structure
+ * @buflen: Length in bytes of buffer to allocate
+ *
+ */
+
+static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen)
+{
+	struct p9_fid *fid = filp->private_data;
+	if (!fid->rdir)
+		fid->rdir = kzalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
+	return fid->rdir;
+}
+
+/**
+ * v9fs_dir_readdir - iterate through a directory
+ * @file: opened file structure
+ * @ctx: actor we feed the entries to
+ *
+ */
+
+static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	bool over;
+	struct p9_wstat st;
+	int err = 0;
+	struct p9_fid *fid;
+	int buflen;
+	struct p9_rdir *rdir;
+	struct kvec kvec;
+
+	p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
+	fid = file->private_data;
+
+	buflen = fid->clnt->msize - P9_IOHDRSZ;
+
+	rdir = v9fs_alloc_rdir_buf(file, buflen);
+	if (!rdir)
+		return -ENOMEM;
+	kvec.iov_base = rdir->buf;
+	kvec.iov_len = buflen;
+
+	while (1) {
+		if (rdir->tail == rdir->head) {
+			struct iov_iter to;
+			int n;
+			iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen);
+			n = p9_client_read(file->private_data, ctx->pos, &to,
+					   &err);
+			if (err)
+				return err;
+			if (n == 0)
+				return 0;
+
+			rdir->head = 0;
+			rdir->tail = n;
+		}
+		while (rdir->head < rdir->tail) {
+			err = p9stat_read(fid->clnt, rdir->buf + rdir->head,
+					  rdir->tail - rdir->head, &st);
+			if (err <= 0) {
+				p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+				return -EIO;
+			}
+
+			over = !dir_emit(ctx, st.name, strlen(st.name),
+					 v9fs_qid2ino(&st.qid), dt_type(&st));
+			p9stat_free(&st);
+			if (over)
+				return 0;
+
+			rdir->head += err;
+			ctx->pos += err;
+		}
+	}
+}
+
+/**
+ * v9fs_dir_readdir_dotl - iterate through a directory
+ * @file: opened file structure
+ * @ctx: actor we feed the entries to
+ *
+ */
+static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx)
+{
+	int err = 0;
+	struct p9_fid *fid;
+	int buflen;
+	struct p9_rdir *rdir;
+	struct p9_dirent curdirent;
+
+	p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
+	fid = file->private_data;
+
+	buflen = fid->clnt->msize - P9_READDIRHDRSZ;
+
+	rdir = v9fs_alloc_rdir_buf(file, buflen);
+	if (!rdir)
+		return -ENOMEM;
+
+	while (1) {
+		if (rdir->tail == rdir->head) {
+			err = p9_client_readdir(fid, rdir->buf, buflen,
+						ctx->pos);
+			if (err <= 0)
+				return err;
+
+			rdir->head = 0;
+			rdir->tail = err;
+		}
+
+		while (rdir->head < rdir->tail) {
+
+			err = p9dirent_read(fid->clnt, rdir->buf + rdir->head,
+					    rdir->tail - rdir->head,
+					    &curdirent);
+			if (err < 0) {
+				p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+				return -EIO;
+			}
+
+			if (!dir_emit(ctx, curdirent.d_name,
+				      strlen(curdirent.d_name),
+				      v9fs_qid2ino(&curdirent.qid),
+				      curdirent.d_type))
+				return 0;
+
+			ctx->pos = curdirent.d_off;
+			rdir->head += err;
+		}
+	}
+}
+
+
+/**
+ * v9fs_dir_release - close a directory
+ * @inode: inode of the directory
+ * @filp: file pointer to a directory
+ *
+ */
+
+int v9fs_dir_release(struct inode *inode, struct file *filp)
+{
+	struct p9_fid *fid;
+
+	fid = filp->private_data;
+	p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n",
+		 inode, filp, fid ? fid->fid : -1);
+	if (fid)
+		p9_client_clunk(fid);
+	return 0;
+}
+
+const struct file_operations v9fs_dir_operations = {
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+	.iterate = v9fs_dir_readdir,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+};
+
+const struct file_operations v9fs_dir_operations_dotl = {
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+	.iterate = v9fs_dir_readdir_dotl,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+        .fsync = v9fs_file_fsync_dotl,
+};

addons/9p/src/4.4.180/vfs_file.c

@@ -0,0 +1,726 @@
+/*
+ *  linux/fs/9p/vfs_file.c
+ *
+ * This file contians vfs file ops for 9P2000.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/utsname.h>
+#include <asm/uaccess.h>
+#include <linux/idr.h>
+#include <linux/uio.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "cache.h"
+
+static const struct vm_operations_struct v9fs_file_vm_ops;
+static const struct vm_operations_struct v9fs_mmap_file_vm_ops;
+
+/**
+ * v9fs_file_open - open a file (or directory)
+ * @inode: inode to be opened
+ * @file: file being opened
+ *
+ */
+
+int v9fs_file_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct v9fs_inode *v9inode;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
+	int omode;
+
+	p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file);
+	v9inode = V9FS_I(inode);
+	v9ses = v9fs_inode2v9ses(inode);
+	if (v9fs_proto_dotl(v9ses))
+		omode = v9fs_open_to_dotl_flags(file->f_flags);
+	else
+		omode = v9fs_uflags2omode(file->f_flags,
+					v9fs_proto_dotu(v9ses));
+	fid = file->private_data;
+	if (!fid) {
+		fid = v9fs_fid_clone(file_dentry(file));
+		if (IS_ERR(fid))
+			return PTR_ERR(fid);
+
+		err = p9_client_open(fid, omode);
+		if (err < 0) {
+			p9_client_clunk(fid);
+			return err;
+		}
+		if ((file->f_flags & O_APPEND) &&
+			(!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)))
+			generic_file_llseek(file, 0, SEEK_END);
+	}
+
+	file->private_data = fid;
+	mutex_lock(&v9inode->v_mutex);
+	if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
+	    !v9inode->writeback_fid &&
+	    ((file->f_flags & O_ACCMODE) != O_RDONLY)) {
+		/*
+		 * clone a fid and add it to writeback_fid
+		 * we do it during open time instead of
+		 * page dirty time via write_begin/page_mkwrite
+		 * because we want write after unlink usecase
+		 * to work.
+		 */
+		fid = v9fs_writeback_fid(file_dentry(file));
+		if (IS_ERR(fid)) {
+			err = PTR_ERR(fid);
+			mutex_unlock(&v9inode->v_mutex);
+			goto out_error;
+		}
+		v9inode->writeback_fid = (void *) fid;
+	}
+	mutex_unlock(&v9inode->v_mutex);
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+		v9fs_cache_inode_set_cookie(inode, file);
+	return 0;
+out_error:
+	p9_client_clunk(file->private_data);
+	file->private_data = NULL;
+	return err;
+}
+
+/**
+ * v9fs_file_lock - lock a file (or directory)
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ * Bugs: this looks like a local only lock, we should extend into 9P
+ *       by using open exclusive
+ */
+
+static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	int res = 0;
+	struct inode *inode = file_inode(filp);
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		return -ENOLCK;
+
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+		filemap_write_and_wait(inode->i_mapping);
+		invalidate_mapping_pages(&inode->i_data, 0, -1);
+	}
+
+	return res;
+}
+
+static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+	struct p9_flock flock;
+	struct p9_fid *fid;
+	uint8_t status = P9_LOCK_ERROR;
+	int res = 0;
+	unsigned char fl_type;
+	struct v9fs_session_info *v9ses;
+
+	fid = filp->private_data;
+	BUG_ON(fid == NULL);
+
+	if ((fl->fl_flags & FL_POSIX) != FL_POSIX)
+		BUG();
+
+	res = locks_lock_file_wait(filp, fl);
+	if (res < 0)
+		goto out;
+
+	/* convert posix lock to p9 tlock args */
+	memset(&flock, 0, sizeof(flock));
+	/* map the lock type */
+	switch (fl->fl_type) {
+	case F_RDLCK:
+		flock.type = P9_LOCK_TYPE_RDLCK;
+		break;
+	case F_WRLCK:
+		flock.type = P9_LOCK_TYPE_WRLCK;
+		break;
+	case F_UNLCK:
+		flock.type = P9_LOCK_TYPE_UNLCK;
+		break;
+	}
+	flock.start = fl->fl_start;
+	if (fl->fl_end == OFFSET_MAX)
+		flock.length = 0;
+	else
+		flock.length = fl->fl_end - fl->fl_start + 1;
+	flock.proc_id = fl->fl_pid;
+	flock.client_id = fid->clnt->name;
+	if (IS_SETLKW(cmd))
+		flock.flags = P9_LOCK_FLAGS_BLOCK;
+
+	v9ses = v9fs_inode2v9ses(file_inode(filp));
+
+	/*
+	 * if its a blocked request and we get P9_LOCK_BLOCKED as the status
+	 * for lock request, keep on trying
+	 */
+	for (;;) {
+		res = p9_client_lock_dotl(fid, &flock, &status);
+		if (res < 0)
+			goto out_unlock;
+
+		if (status != P9_LOCK_BLOCKED)
+			break;
+		if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
+			break;
+		if (schedule_timeout_interruptible(v9ses->session_lock_timeout)
+				!= 0)
+			break;
+		/*
+		 * p9_client_lock_dotl overwrites flock.client_id with the
+		 * server message, free and reuse the client name
+		 */
+		if (flock.client_id != fid->clnt->name) {
+			kfree(flock.client_id);
+			flock.client_id = fid->clnt->name;
+		}
+	}
+
+	/* map 9p status to VFS status */
+	switch (status) {
+	case P9_LOCK_SUCCESS:
+		res = 0;
+		break;
+	case P9_LOCK_BLOCKED:
+		res = -EAGAIN;
+		break;
+	default:
+		WARN_ONCE(1, "unknown lock status code: %d\n", status);
+		/* fallthough */
+	case P9_LOCK_ERROR:
+	case P9_LOCK_GRACE:
+		res = -ENOLCK;
+		break;
+	}
+
+out_unlock:
+	/*
+	 * incase server returned error for lock request, revert
+	 * it locally
+	 */
+	if (res < 0 && fl->fl_type != F_UNLCK) {
+		fl_type = fl->fl_type;
+		fl->fl_type = F_UNLCK;
+		/* Even if this fails we want to return the remote error */
+		locks_lock_file_wait(filp, fl);
+		fl->fl_type = fl_type;
+	}
+	if (flock.client_id != fid->clnt->name)
+		kfree(flock.client_id);
+out:
+	return res;
+}
+
+static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
+{
+	struct p9_getlock glock;
+	struct p9_fid *fid;
+	int res = 0;
+
+	fid = filp->private_data;
+	BUG_ON(fid == NULL);
+
+	posix_test_lock(filp, fl);
+	/*
+	 * if we have a conflicting lock locally, no need to validate
+	 * with server
+	 */
+	if (fl->fl_type != F_UNLCK)
+		return res;
+
+	/* convert posix lock to p9 tgetlock args */
+	memset(&glock, 0, sizeof(glock));
+	glock.type  = P9_LOCK_TYPE_UNLCK;
+	glock.start = fl->fl_start;
+	if (fl->fl_end == OFFSET_MAX)
+		glock.length = 0;
+	else
+		glock.length = fl->fl_end - fl->fl_start + 1;
+	glock.proc_id = fl->fl_pid;
+	glock.client_id = fid->clnt->name;
+
+	res = p9_client_getlock_dotl(fid, &glock);
+	if (res < 0)
+		goto out;
+	/* map 9p lock type to os lock type */
+	switch (glock.type) {
+	case P9_LOCK_TYPE_RDLCK:
+		fl->fl_type = F_RDLCK;
+		break;
+	case P9_LOCK_TYPE_WRLCK:
+		fl->fl_type = F_WRLCK;
+		break;
+	case P9_LOCK_TYPE_UNLCK:
+		fl->fl_type = F_UNLCK;
+		break;
+	}
+	if (glock.type != P9_LOCK_TYPE_UNLCK) {
+		fl->fl_start = glock.start;
+		if (glock.length == 0)
+			fl->fl_end = OFFSET_MAX;
+		else
+			fl->fl_end = glock.start + glock.length - 1;
+		fl->fl_pid = glock.proc_id;
+	}
+out:
+	if (glock.client_id != fid->clnt->name)
+		kfree(glock.client_id);
+	return res;
+}
+
+/**
+ * v9fs_file_lock_dotl - lock a file (or directory)
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ */
+
+static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
+{
+	struct inode *inode = file_inode(filp);
+	int ret = -ENOLCK;
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+		 filp, cmd, fl, filp);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		goto out_err;
+
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+		filemap_write_and_wait(inode->i_mapping);
+		invalidate_mapping_pages(&inode->i_data, 0, -1);
+	}
+
+	if (IS_SETLK(cmd) || IS_SETLKW(cmd))
+		ret = v9fs_file_do_lock(filp, cmd, fl);
+	else if (IS_GETLK(cmd))
+		ret = v9fs_file_getlock(filp, fl);
+	else
+		ret = -EINVAL;
+out_err:
+	return ret;
+}
+
+/**
+ * v9fs_file_flock_dotl - lock a file
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ */
+
+static int v9fs_file_flock_dotl(struct file *filp, int cmd,
+	struct file_lock *fl)
+{
+	struct inode *inode = file_inode(filp);
+	int ret = -ENOLCK;
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+		 filp, cmd, fl, filp);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		goto out_err;
+
+	if (!(fl->fl_flags & FL_FLOCK))
+		goto out_err;
+
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+		filemap_write_and_wait(inode->i_mapping);
+		invalidate_mapping_pages(&inode->i_data, 0, -1);
+	}
+	/* Convert flock to posix lock */
+	fl->fl_flags |= FL_POSIX;
+	fl->fl_flags ^= FL_FLOCK;
+
+	if (IS_SETLK(cmd) | IS_SETLKW(cmd))
+		ret = v9fs_file_do_lock(filp, cmd, fl);
+	else
+		ret = -EINVAL;
+out_err:
+	return ret;
+}
+
+/**
+ * v9fs_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+
+static ssize_t
+v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct p9_fid *fid = iocb->ki_filp->private_data;
+	int ret, err = 0;
+
+	p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n",
+		 iov_iter_count(to), iocb->ki_pos);
+
+	ret = p9_client_read(fid, iocb->ki_pos, to, &err);
+	if (!ret)
+		return err;
+
+	iocb->ki_pos += ret;
+	return ret;
+}
+
+/**
+ * v9fs_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t retval;
+	loff_t origin;
+	int err = 0;
+
+	retval = generic_write_checks(iocb, from);
+	if (retval <= 0)
+		return retval;
+
+	origin = iocb->ki_pos;
+	retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err);
+	if (retval > 0) {
+		struct inode *inode = file_inode(file);
+		loff_t i_size;
+		unsigned long pg_start, pg_end;
+		pg_start = origin >> PAGE_CACHE_SHIFT;
+		pg_end = (origin + retval - 1) >> PAGE_CACHE_SHIFT;
+		if (inode->i_mapping && inode->i_mapping->nrpages)
+			invalidate_inode_pages2_range(inode->i_mapping,
+						      pg_start, pg_end);
+		iocb->ki_pos += retval;
+		i_size = i_size_read(inode);
+		if (iocb->ki_pos > i_size) {
+			inode_add_bytes(inode, iocb->ki_pos - i_size);
+			/*
+			 * Need to serialize against i_size_write() in
+			 * v9fs_stat2inode()
+			 */
+			v9fs_i_size_write(inode, iocb->ki_pos);
+		}
+		return retval;
+	}
+	return err;
+}
+
+static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
+			   int datasync)
+{
+	struct p9_fid *fid;
+	struct inode *inode = filp->f_mapping->host;
+	struct p9_wstat wstat;
+	int retval;
+
+	retval = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (retval)
+		return retval;
+
+	mutex_lock(&inode->i_mutex);
+	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+	fid = filp->private_data;
+	v9fs_blank_wstat(&wstat);
+
+	retval = p9_client_wstat(fid, &wstat);
+	mutex_unlock(&inode->i_mutex);
+
+	return retval;
+}
+
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+			 int datasync)
+{
+	struct p9_fid *fid;
+	struct inode *inode = filp->f_mapping->host;
+	int retval;
+
+	retval = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (retval)
+		return retval;
+
+	mutex_lock(&inode->i_mutex);
+	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+	fid = filp->private_data;
+
+	retval = p9_client_fsync(fid, datasync);
+	mutex_unlock(&inode->i_mutex);
+
+	return retval;
+}
+
+static int
+v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int retval;
+
+
+	retval = generic_file_mmap(filp, vma);
+	if (!retval)
+		vma->vm_ops = &v9fs_file_vm_ops;
+
+	return retval;
+}
+
+static int
+v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int retval;
+	struct inode *inode;
+	struct v9fs_inode *v9inode;
+	struct p9_fid *fid;
+
+	inode = file_inode(filp);
+	v9inode = V9FS_I(inode);
+	mutex_lock(&v9inode->v_mutex);
+	if (!v9inode->writeback_fid &&
+	    (vma->vm_flags & VM_WRITE)) {
+		/*
+		 * clone a fid and add it to writeback_fid
+		 * we do it during mmap instead of
+		 * page dirty time via write_begin/page_mkwrite
+		 * because we want write after unlink usecase
+		 * to work.
+		 */
+		fid = v9fs_writeback_fid(file_dentry(filp));
+		if (IS_ERR(fid)) {
+			retval = PTR_ERR(fid);
+			mutex_unlock(&v9inode->v_mutex);
+			return retval;
+		}
+		v9inode->writeback_fid = (void *) fid;
+	}
+	mutex_unlock(&v9inode->v_mutex);
+
+	retval = generic_file_mmap(filp, vma);
+	if (!retval)
+		vma->vm_ops = &v9fs_mmap_file_vm_ops;
+
+	return retval;
+}
+
+static int
+v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct v9fs_inode *v9inode;
+	struct page *page = vmf->page;
+	struct file *filp = vma->vm_file;
+	struct inode *inode = file_inode(filp);
+
+
+	p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
+		 page, (unsigned long)filp->private_data);
+
+	/* Update file times before taking page lock */
+	file_update_time(filp);
+
+	v9inode = V9FS_I(inode);
+	/* make sure the cache has finished storing the page */
+	v9fs_fscache_wait_on_page_write(inode, page);
+	BUG_ON(!v9inode->writeback_fid);
+	lock_page(page);
+	if (page->mapping != inode->i_mapping)
+		goto out_unlock;
+	wait_for_stable_page(page);
+
+	return VM_FAULT_LOCKED;
+out_unlock:
+	unlock_page(page);
+	return VM_FAULT_NOPAGE;
+}
+
+/**
+ * v9fs_mmap_file_read - read from a file
+ * @filp: file pointer to read
+ * @data: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+static ssize_t
+v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	/* TODO: Check if there are dirty pages */
+	return v9fs_file_read_iter(iocb, to);
+}
+
+/**
+ * v9fs_mmap_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_mmap_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	/*
+	 * TODO: invalidate mmaps on filp's inode between
+	 * offset and offset+count
+	 */
+	return v9fs_file_write_iter(iocb, from);
+}
+
+static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
+{
+	struct inode *inode;
+
+	struct writeback_control wbc = {
+		.nr_to_write = LONG_MAX,
+		.sync_mode = WB_SYNC_ALL,
+		.range_start = vma->vm_pgoff * PAGE_SIZE,
+		 /* absolute end, byte at end included */
+		.range_end = vma->vm_pgoff * PAGE_SIZE +
+			(vma->vm_end - vma->vm_start - 1),
+	};
+
+
+	p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);
+
+	inode = file_inode(vma->vm_file);
+
+	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+		wbc.nr_to_write = 0;
+
+	might_sleep();
+	sync_inode(inode, &wbc);
+}
+
+
+static const struct vm_operations_struct v9fs_file_vm_ops = {
+	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
+	.page_mkwrite = v9fs_vm_page_mkwrite,
+};
+
+static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
+	.close = v9fs_mmap_vm_close,
+	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
+	.page_mkwrite = v9fs_vm_page_mkwrite,
+};
+
+
+const struct file_operations v9fs_cached_file_operations = {
+	.llseek = generic_file_llseek,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = v9fs_file_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_cached_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = v9fs_file_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};
+
+const struct file_operations v9fs_file_operations = {
+	.llseek = generic_file_llseek,
+	.read_iter = v9fs_file_read_iter,
+	.write_iter = v9fs_file_write_iter,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = generic_file_readonly_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read_iter = v9fs_file_read_iter,
+	.write_iter = v9fs_file_write_iter,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = generic_file_readonly_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};
+
+const struct file_operations v9fs_mmap_file_operations = {
+	.llseek = generic_file_llseek,
+	.read_iter = v9fs_mmap_file_read_iter,
+	.write_iter = v9fs_mmap_file_write_iter,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = v9fs_mmap_file_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_mmap_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read_iter = v9fs_mmap_file_read_iter,
+	.write_iter = v9fs_mmap_file_write_iter,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = v9fs_mmap_file_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};

addons/9p/src/4.4.180/vfs_inode_dotl.c

@@ -0,0 +1,999 @@
+/*
+ *  linux/fs/9p/vfs_inode_dotl.c
+ *
+ * This file contains vfs inode ops for the 9P2000.L protocol.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "cache.h"
+#include "xattr.h"
+#include "acl.h"
+
+static int
+v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
+		    dev_t rdev);
+
+/**
+ * v9fs_get_fsgid_for_create - Helper function to get the gid for creating a
+ * new file system object. This checks the S_ISGID to determine the owning
+ * group of the new file system object.
+ */
+
+static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
+{
+	BUG_ON(dir_inode == NULL);
+
+	if (dir_inode->i_mode & S_ISGID) {
+		/* set_gid bit is set.*/
+		return dir_inode->i_gid;
+	}
+	return current_fsgid();
+}
+
+static int v9fs_test_inode_dotl(struct inode *inode, void *data)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+	/* don't match inode of different type */
+	if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT))
+		return 0;
+
+	if (inode->i_generation != st->st_gen)
+		return 0;
+
+	/* compare qid details */
+	if (memcmp(&v9inode->qid.version,
+		   &st->qid.version, sizeof(v9inode->qid.version)))
+		return 0;
+
+	if (v9inode->qid.type != st->qid.type)
+		return 0;
+
+	if (v9inode->qid.path != st->qid.path)
+		return 0;
+	return 1;
+}
+
+/* Always get a new inode */
+static int v9fs_test_new_inode_dotl(struct inode *inode, void *data)
+{
+	return 0;
+}
+
+static int v9fs_set_inode_dotl(struct inode *inode,  void *data)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+	memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+	inode->i_generation = st->st_gen;
+	return 0;
+}
+
+static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
+					struct p9_qid *qid,
+					struct p9_fid *fid,
+					struct p9_stat_dotl *st,
+					int new)
+{
+	int retval;
+	unsigned long i_ino;
+	struct inode *inode;
+	struct v9fs_session_info *v9ses = sb->s_fs_info;
+	int (*test)(struct inode *, void *);
+
+	if (new)
+		test = v9fs_test_new_inode_dotl;
+	else
+		test = v9fs_test_inode_dotl;
+
+	i_ino = v9fs_qid2ino(qid);
+	inode = iget5_locked(sb, i_ino, test, v9fs_set_inode_dotl, st);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+	/*
+	 * initialize the inode with the stat info
+	 * FIXME!! we may need support for stale inodes
+	 * later.
+	 */
+	inode->i_ino = i_ino;
+	retval = v9fs_init_inode(v9ses, inode,
+				 st->st_mode, new_decode_dev(st->st_rdev));
+	if (retval)
+		goto error;
+
+	v9fs_stat2inode_dotl(st, inode, 0);
+	v9fs_cache_inode_get_cookie(inode);
+	retval = v9fs_get_acl(inode, fid);
+	if (retval)
+		goto error;
+
+	unlock_new_inode(inode);
+	return inode;
+error:
+	iget_failed(inode);
+	return ERR_PTR(retval);
+
+}
+
+struct inode *
+v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+			 struct super_block *sb, int new)
+{
+	struct p9_stat_dotl *st;
+	struct inode *inode = NULL;
+
+	st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN);
+	if (IS_ERR(st))
+		return ERR_CAST(st);
+
+	inode = v9fs_qid_iget_dotl(sb, &st->qid, fid, st, new);
+	kfree(st);
+	return inode;
+}
+
+struct dotl_openflag_map {
+	int open_flag;
+	int dotl_flag;
+};
+
+static int v9fs_mapped_dotl_flags(int flags)
+{
+	int i;
+	int rflags = 0;
+	struct dotl_openflag_map dotl_oflag_map[] = {
+		{ O_CREAT,	P9_DOTL_CREATE },
+		{ O_EXCL,	P9_DOTL_EXCL },
+		{ O_NOCTTY,	P9_DOTL_NOCTTY },
+		{ O_APPEND,	P9_DOTL_APPEND },
+		{ O_NONBLOCK,	P9_DOTL_NONBLOCK },
+		{ O_DSYNC,	P9_DOTL_DSYNC },
+		{ FASYNC,	P9_DOTL_FASYNC },
+		{ O_DIRECT,	P9_DOTL_DIRECT },
+		{ O_LARGEFILE,	P9_DOTL_LARGEFILE },
+		{ O_DIRECTORY,	P9_DOTL_DIRECTORY },
+		{ O_NOFOLLOW,	P9_DOTL_NOFOLLOW },
+		{ O_NOATIME,	P9_DOTL_NOATIME },
+		{ O_CLOEXEC,	P9_DOTL_CLOEXEC },
+		{ O_SYNC,	P9_DOTL_SYNC},
+	};
+	for (i = 0; i < ARRAY_SIZE(dotl_oflag_map); i++) {
+		if (flags & dotl_oflag_map[i].open_flag)
+			rflags |= dotl_oflag_map[i].dotl_flag;
+	}
+	return rflags;
+}
+
+/**
+ * v9fs_open_to_dotl_flags- convert Linux specific open flags to
+ * plan 9 open flag.
+ * @flags: flags to convert
+ */
+int v9fs_open_to_dotl_flags(int flags)
+{
+	int rflags = 0;
+
+	/*
+	 * We have same bits for P9_DOTL_READONLY, P9_DOTL_WRONLY
+	 * and P9_DOTL_NOACCESS
+	 */
+	rflags |= flags & O_ACCMODE;
+	rflags |= v9fs_mapped_dotl_flags(flags);
+
+	return rflags;
+}
+
+/**
+ * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol.
+ * @dir: directory inode that is being created
+ * @dentry:  dentry that is being deleted
+ * @omode: create permissions
+ *
+ */
+
+static int
+v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
+		bool excl)
+{
+	return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
+}
+
+static int
+v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
+			  struct file *file, unsigned flags, umode_t omode,
+			  int *opened)
+{
+	int err = 0;
+	kgid_t gid;
+	umode_t mode;
+	char *name = NULL;
+	struct p9_qid qid;
+	struct inode *inode;
+	struct p9_fid *fid = NULL;
+	struct v9fs_inode *v9inode;
+	struct p9_fid *dfid, *ofid, *inode_fid;
+	struct v9fs_session_info *v9ses;
+	struct posix_acl *pacl = NULL, *dacl = NULL;
+	struct dentry *res = NULL;
+
+	if (d_unhashed(dentry)) {
+		res = v9fs_vfs_lookup(dir, dentry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			dentry = res;
+	}
+
+	/* Only creates */
+	if (!(flags & O_CREAT) || d_really_is_positive(dentry))
+		return	finish_no_open(file, res);
+
+	v9ses = v9fs_inode2v9ses(dir);
+
+	name = (char *) dentry->d_name.name;
+	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
+		 name, flags, omode);
+
+	dfid = v9fs_fid_lookup(dentry->d_parent);
+	if (IS_ERR(dfid)) {
+		err = PTR_ERR(dfid);
+		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+		goto out;
+	}
+
+	/* clone a fid to use for creation */
+	ofid = p9_client_walk(dfid, 0, NULL, 1);
+	if (IS_ERR(ofid)) {
+		err = PTR_ERR(ofid);
+		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+		goto out;
+	}
+
+	gid = v9fs_get_fsgid_for_create(dir);
+
+	mode = omode;
+	/* Update mode based on ACL value */
+	err = v9fs_acl_mode(dir, &mode, &dacl, &pacl);
+	if (err) {
+		p9_debug(P9_DEBUG_VFS, "Failed to get acl values in creat %d\n",
+			 err);
+		goto error;
+	}
+	err = p9_client_create_dotl(ofid, name, v9fs_open_to_dotl_flags(flags),
+				    mode, gid, &qid);
+	if (err < 0) {
+		p9_debug(P9_DEBUG_VFS, "p9_client_open_dotl failed in creat %d\n",
+			 err);
+		goto error;
+	}
+	v9fs_invalidate_inode_attr(dir);
+
+	/* instantiate inode and assign the unopened fid to the dentry */
+	fid = p9_client_walk(dfid, 1, &name, 1);
+	if (IS_ERR(fid)) {
+		err = PTR_ERR(fid);
+		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+		fid = NULL;
+		goto error;
+	}
+	inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
+		goto error;
+	}
+	/* Now set the ACL based on the default value */
+	v9fs_set_create_acl(inode, fid, dacl, pacl);
+
+	v9fs_fid_add(dentry, fid);
+	d_instantiate(dentry, inode);
+
+	v9inode = V9FS_I(inode);
+	mutex_lock(&v9inode->v_mutex);
+	if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
+	    !v9inode->writeback_fid &&
+	    ((flags & O_ACCMODE) != O_RDONLY)) {
+		/*
+		 * clone a fid and add it to writeback_fid
+		 * we do it during open time instead of
+		 * page dirty time via write_begin/page_mkwrite
+		 * because we want write after unlink usecase
+		 * to work.
+		 */
+		inode_fid = v9fs_writeback_fid(dentry);
+		if (IS_ERR(inode_fid)) {
+			err = PTR_ERR(inode_fid);
+			mutex_unlock(&v9inode->v_mutex);
+			goto err_clunk_old_fid;
+		}
+		v9inode->writeback_fid = (void *) inode_fid;
+	}
+	mutex_unlock(&v9inode->v_mutex);
+	/* Since we are opening a file, assign the open fid to the file */
+	err = finish_open(file, dentry, generic_file_open, opened);
+	if (err)
+		goto err_clunk_old_fid;
+	file->private_data = ofid;
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+		v9fs_cache_inode_set_cookie(inode, file);
+	*opened |= FILE_CREATED;
+out:
+	v9fs_put_acl(dacl, pacl);
+	dput(res);
+	return err;
+
+error:
+	if (fid)
+		p9_client_clunk(fid);
+err_clunk_old_fid:
+	if (ofid)
+		p9_client_clunk(ofid);
+	goto out;
+}
+
+/**
+ * v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory
+ * @dir:  inode that is being unlinked
+ * @dentry: dentry that is being unlinked
+ * @omode: mode for new directory
+ *
+ */
+
+static int v9fs_vfs_mkdir_dotl(struct inode *dir,
+			       struct dentry *dentry, umode_t omode)
+{
+	int err;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid = NULL, *dfid = NULL;
+	kgid_t gid;
+	char *name;
+	umode_t mode;
+	struct inode *inode;
+	struct p9_qid qid;
+	struct dentry *dir_dentry;
+	struct posix_acl *dacl = NULL, *pacl = NULL;
+
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
+	err = 0;
+	v9ses = v9fs_inode2v9ses(dir);
+
+	omode |= S_IFDIR;
+	if (dir->i_mode & S_ISGID)
+		omode |= S_ISGID;
+
+	dir_dentry = dentry->d_parent;
+	dfid = v9fs_fid_lookup(dir_dentry);
+	if (IS_ERR(dfid)) {
+		err = PTR_ERR(dfid);
+		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+		dfid = NULL;
+		goto error;
+	}
+
+	gid = v9fs_get_fsgid_for_create(dir);
+	mode = omode;
+	/* Update mode based on ACL value */
+	err = v9fs_acl_mode(dir, &mode, &dacl, &pacl);
+	if (err) {
+		p9_debug(P9_DEBUG_VFS, "Failed to get acl values in mkdir %d\n",
+			 err);
+		goto error;
+	}
+	name = (char *) dentry->d_name.name;
+	err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid);
+	if (err < 0)
+		goto error;
+
+	fid = p9_client_walk(dfid, 1, &name, 1);
+	if (IS_ERR(fid)) {
+		err = PTR_ERR(fid);
+		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+			 err);
+		fid = NULL;
+		goto error;
+	}
+
+	/* instantiate inode and assign the unopened fid to the dentry */
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+		if (IS_ERR(inode)) {
+			err = PTR_ERR(inode);
+			p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
+				 err);
+			goto error;
+		}
+		v9fs_fid_add(dentry, fid);
+		v9fs_set_create_acl(inode, fid, dacl, pacl);
+		d_instantiate(dentry, inode);
+		fid = NULL;
+		err = 0;
+	} else {
+		/*
+		 * Not in cached mode. No need to populate
+		 * inode with stat. We need to get an inode
+		 * so that we can set the acl with dentry
+		 */
+		inode = v9fs_get_inode(dir->i_sb, mode, 0);
+		if (IS_ERR(inode)) {
+			err = PTR_ERR(inode);
+			goto error;
+		}
+		v9fs_set_create_acl(inode, fid, dacl, pacl);
+		d_instantiate(dentry, inode);
+	}
+	inc_nlink(dir);
+	v9fs_invalidate_inode_attr(dir);
+error:
+	if (fid)
+		p9_client_clunk(fid);
+	v9fs_put_acl(dacl, pacl);
+	return err;
+}
+
+static int
+v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
+		 struct kstat *stat)
+{
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
+	struct p9_stat_dotl *st;
+
+	p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
+	v9ses = v9fs_dentry2v9ses(dentry);
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+		generic_fillattr(d_inode(dentry), stat);
+		return 0;
+	}
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+
+	/* Ask for all the fields in stat structure. Server will return
+	 * whatever it supports
+	 */
+
+	st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
+	if (IS_ERR(st))
+		return PTR_ERR(st);
+
+	v9fs_stat2inode_dotl(st, d_inode(dentry), 0);
+	generic_fillattr(d_inode(dentry), stat);
+	/* Change block size to what the server returned */
+	stat->blksize = st->st_blksize;
+
+	kfree(st);
+	return 0;
+}
+
+/*
+ * Attribute flags.
+ */
+#define P9_ATTR_MODE		(1 << 0)
+#define P9_ATTR_UID		(1 << 1)
+#define P9_ATTR_GID		(1 << 2)
+#define P9_ATTR_SIZE		(1 << 3)
+#define P9_ATTR_ATIME		(1 << 4)
+#define P9_ATTR_MTIME		(1 << 5)
+#define P9_ATTR_CTIME		(1 << 6)
+#define P9_ATTR_ATIME_SET	(1 << 7)
+#define P9_ATTR_MTIME_SET	(1 << 8)
+
+struct dotl_iattr_map {
+	int iattr_valid;
+	int p9_iattr_valid;
+};
+
+static int v9fs_mapped_iattr_valid(int iattr_valid)
+{
+	int i;
+	int p9_iattr_valid = 0;
+	struct dotl_iattr_map dotl_iattr_map[] = {
+		{ ATTR_MODE,		P9_ATTR_MODE },
+		{ ATTR_UID,		P9_ATTR_UID },
+		{ ATTR_GID,		P9_ATTR_GID },
+		{ ATTR_SIZE,		P9_ATTR_SIZE },
+		{ ATTR_ATIME,		P9_ATTR_ATIME },
+		{ ATTR_MTIME,		P9_ATTR_MTIME },
+		{ ATTR_CTIME,		P9_ATTR_CTIME },
+		{ ATTR_ATIME_SET,	P9_ATTR_ATIME_SET },
+		{ ATTR_MTIME_SET,	P9_ATTR_MTIME_SET },
+	};
+	for (i = 0; i < ARRAY_SIZE(dotl_iattr_map); i++) {
+		if (iattr_valid & dotl_iattr_map[i].iattr_valid)
+			p9_iattr_valid |= dotl_iattr_map[i].p9_iattr_valid;
+	}
+	return p9_iattr_valid;
+}
+
+/**
+ * v9fs_vfs_setattr_dotl - set file metadata
+ * @dentry: file whose metadata to set
+ * @iattr: metadata assignment structure
+ *
+ */
+
+int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
+{
+	int retval;
+	struct p9_fid *fid;
+	struct p9_iattr_dotl p9attr;
+	struct inode *inode = d_inode(dentry);
+
+	p9_debug(P9_DEBUG_VFS, "\n");
+
+	retval = inode_change_ok(inode, iattr);
+	if (retval)
+		return retval;
+
+	p9attr.valid = v9fs_mapped_iattr_valid(iattr->ia_valid);
+	p9attr.mode = iattr->ia_mode;
+	p9attr.uid = iattr->ia_uid;
+	p9attr.gid = iattr->ia_gid;
+	p9attr.size = iattr->ia_size;
+	p9attr.atime_sec = iattr->ia_atime.tv_sec;
+	p9attr.atime_nsec = iattr->ia_atime.tv_nsec;
+	p9attr.mtime_sec = iattr->ia_mtime.tv_sec;
+	p9attr.mtime_nsec = iattr->ia_mtime.tv_nsec;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+
+	/* Write all dirty data */
+	if (S_ISREG(inode->i_mode))
+		filemap_write_and_wait(inode->i_mapping);
+
+	retval = p9_client_setattr(fid, &p9attr);
+	if (retval < 0)
+		return retval;
+
+	if ((iattr->ia_valid & ATTR_SIZE) &&
+	    iattr->ia_size != i_size_read(inode))
+		truncate_setsize(inode, iattr->ia_size);
+
+	v9fs_invalidate_inode_attr(inode);
+	setattr_copy(inode, iattr);
+	mark_inode_dirty(inode);
+	if (iattr->ia_valid & ATTR_MODE) {
+		/* We also want to update ACL when we update mode bits */
+		retval = v9fs_acl_chmod(inode, fid);
+		if (retval < 0)
+			return retval;
+	}
+	return 0;
+}
+
+/**
+ * v9fs_stat2inode_dotl - populate an inode structure with stat info
+ * @stat: stat structure
+ * @inode: inode to populate
+ * @flags: ctrl flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
+ *
+ */
+
+void
+v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
+		      unsigned int flags)
+{
+	umode_t mode;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if ((stat->st_result_mask & P9_STATS_BASIC) == P9_STATS_BASIC) {
+		inode->i_atime.tv_sec = stat->st_atime_sec;
+		inode->i_atime.tv_nsec = stat->st_atime_nsec;
+		inode->i_mtime.tv_sec = stat->st_mtime_sec;
+		inode->i_mtime.tv_nsec = stat->st_mtime_nsec;
+		inode->i_ctime.tv_sec = stat->st_ctime_sec;
+		inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
+		inode->i_uid = stat->st_uid;
+		inode->i_gid = stat->st_gid;
+		set_nlink(inode, stat->st_nlink);
+
+		mode = stat->st_mode & S_IALLUGO;
+		mode |= inode->i_mode & ~S_IALLUGO;
+		inode->i_mode = mode;
+
+		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
+			v9fs_i_size_write(inode, stat->st_size);
+		inode->i_blocks = stat->st_blocks;
+	} else {
+		if (stat->st_result_mask & P9_STATS_ATIME) {
+			inode->i_atime.tv_sec = stat->st_atime_sec;
+			inode->i_atime.tv_nsec = stat->st_atime_nsec;
+		}
+		if (stat->st_result_mask & P9_STATS_MTIME) {
+			inode->i_mtime.tv_sec = stat->st_mtime_sec;
+			inode->i_mtime.tv_nsec = stat->st_mtime_nsec;
+		}
+		if (stat->st_result_mask & P9_STATS_CTIME) {
+			inode->i_ctime.tv_sec = stat->st_ctime_sec;
+			inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
+		}
+		if (stat->st_result_mask & P9_STATS_UID)
+			inode->i_uid = stat->st_uid;
+		if (stat->st_result_mask & P9_STATS_GID)
+			inode->i_gid = stat->st_gid;
+		if (stat->st_result_mask & P9_STATS_NLINK)
+			set_nlink(inode, stat->st_nlink);
+		if (stat->st_result_mask & P9_STATS_MODE) {
+			inode->i_mode = stat->st_mode;
+			if ((S_ISBLK(inode->i_mode)) ||
+						(S_ISCHR(inode->i_mode)))
+				init_special_inode(inode, inode->i_mode,
+								inode->i_rdev);
+		}
+		if (stat->st_result_mask & P9_STATS_RDEV)
+			inode->i_rdev = new_decode_dev(stat->st_rdev);
+		if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
+		    stat->st_result_mask & P9_STATS_SIZE)
+			v9fs_i_size_write(inode, stat->st_size);
+		if (stat->st_result_mask & P9_STATS_BLOCKS)
+			inode->i_blocks = stat->st_blocks;
+	}
+	if (stat->st_result_mask & P9_STATS_GEN)
+		inode->i_generation = stat->st_gen;
+
+	/* Currently we don't support P9_STATS_BTIME and P9_STATS_DATA_VERSION
+	 * because the inode structure does not have fields for them.
+	 */
+	v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
+}
+
+static int
+v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
+		const char *symname)
+{
+	int err;
+	kgid_t gid;
+	char *name;
+	struct p9_qid qid;
+	struct inode *inode;
+	struct p9_fid *dfid;
+	struct p9_fid *fid = NULL;
+	struct v9fs_session_info *v9ses;
+
+	name = (char *) dentry->d_name.name;
+	p9_debug(P9_DEBUG_VFS, "%lu,%s,%s\n", dir->i_ino, name, symname);
+	v9ses = v9fs_inode2v9ses(dir);
+
+	dfid = v9fs_fid_lookup(dentry->d_parent);
+	if (IS_ERR(dfid)) {
+		err = PTR_ERR(dfid);
+		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+		return err;
+	}
+
+	gid = v9fs_get_fsgid_for_create(dir);
+
+	/* Server doesn't alter fid on TSYMLINK. Hence no need to clone it. */
+	err = p9_client_symlink(dfid, name, (char *)symname, gid, &qid);
+
+	if (err < 0) {
+		p9_debug(P9_DEBUG_VFS, "p9_client_symlink failed %d\n", err);
+		goto error;
+	}
+
+	v9fs_invalidate_inode_attr(dir);
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+		/* Now walk from the parent so we can get an unopened fid. */
+		fid = p9_client_walk(dfid, 1, &name, 1);
+		if (IS_ERR(fid)) {
+			err = PTR_ERR(fid);
+			p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+				 err);
+			fid = NULL;
+			goto error;
+		}
+
+		/* instantiate inode and assign the unopened fid to dentry */
+		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+		if (IS_ERR(inode)) {
+			err = PTR_ERR(inode);
+			p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
+				 err);
+			goto error;
+		}
+		v9fs_fid_add(dentry, fid);
+		d_instantiate(dentry, inode);
+		fid = NULL;
+		err = 0;
+	} else {
+		/* Not in cached mode. No need to populate inode with stat */
+		inode = v9fs_get_inode(dir->i_sb, S_IFLNK, 0);
+		if (IS_ERR(inode)) {
+			err = PTR_ERR(inode);
+			goto error;
+		}
+		d_instantiate(dentry, inode);
+	}
+
+error:
+	if (fid)
+		p9_client_clunk(fid);
+
+	return err;
+}
+
+/**
+ * v9fs_vfs_link_dotl - create a hardlink for dotl
+ * @old_dentry: dentry for file to link to
+ * @dir: inode destination for new link
+ * @dentry: dentry for link
+ *
+ */
+
+static int
+v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
+		struct dentry *dentry)
+{
+	int err;
+	struct dentry *dir_dentry;
+	struct p9_fid *dfid, *oldfid;
+	struct v9fs_session_info *v9ses;
+
+	p9_debug(P9_DEBUG_VFS, "dir ino: %lu, old_name: %pd, new_name: %pd\n",
+		 dir->i_ino, old_dentry, dentry);
+
+	v9ses = v9fs_inode2v9ses(dir);
+	dir_dentry = dentry->d_parent;
+	dfid = v9fs_fid_lookup(dir_dentry);
+	if (IS_ERR(dfid))
+		return PTR_ERR(dfid);
+
+	oldfid = v9fs_fid_lookup(old_dentry);
+	if (IS_ERR(oldfid))
+		return PTR_ERR(oldfid);
+
+	err = p9_client_link(dfid, oldfid, (char *)dentry->d_name.name);
+
+	if (err < 0) {
+		p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err);
+		return err;
+	}
+
+	v9fs_invalidate_inode_attr(dir);
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+		/* Get the latest stat info from server. */
+		struct p9_fid *fid;
+		fid = v9fs_fid_lookup(old_dentry);
+		if (IS_ERR(fid))
+			return PTR_ERR(fid);
+
+		v9fs_refresh_inode_dotl(fid, d_inode(old_dentry));
+	}
+	ihold(d_inode(old_dentry));
+	d_instantiate(dentry, d_inode(old_dentry));
+
+	return err;
+}
+
+/**
+ * v9fs_vfs_mknod_dotl - create a special file
+ * @dir: inode destination for new link
+ * @dentry: dentry for file
+ * @omode: mode for creation
+ * @rdev: device associated with special file
+ *
+ */
+static int
+v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
+		dev_t rdev)
+{
+	int err;
+	kgid_t gid;
+	char *name;
+	umode_t mode;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid = NULL, *dfid = NULL;
+	struct inode *inode;
+	struct p9_qid qid;
+	struct dentry *dir_dentry;
+	struct posix_acl *dacl = NULL, *pacl = NULL;
+
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+		 dir->i_ino, dentry, omode,
+		 MAJOR(rdev), MINOR(rdev));
+
+	v9ses = v9fs_inode2v9ses(dir);
+	dir_dentry = dentry->d_parent;
+	dfid = v9fs_fid_lookup(dir_dentry);
+	if (IS_ERR(dfid)) {
+		err = PTR_ERR(dfid);
+		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+		dfid = NULL;
+		goto error;
+	}
+
+	gid = v9fs_get_fsgid_for_create(dir);
+	mode = omode;
+	/* Update mode based on ACL value */
+	err = v9fs_acl_mode(dir, &mode, &dacl, &pacl);
+	if (err) {
+		p9_debug(P9_DEBUG_VFS, "Failed to get acl values in mknod %d\n",
+			 err);
+		goto error;
+	}
+	name = (char *) dentry->d_name.name;
+
+	err = p9_client_mknod_dotl(dfid, name, mode, rdev, gid, &qid);
+	if (err < 0)
+		goto error;
+
+	v9fs_invalidate_inode_attr(dir);
+	fid = p9_client_walk(dfid, 1, &name, 1);
+	if (IS_ERR(fid)) {
+		err = PTR_ERR(fid);
+		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+			 err);
+		fid = NULL;
+		goto error;
+	}
+
+	/* instantiate inode and assign the unopened fid to the dentry */
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+		if (IS_ERR(inode)) {
+			err = PTR_ERR(inode);
+			p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
+				 err);
+			goto error;
+		}
+		v9fs_set_create_acl(inode, fid, dacl, pacl);
+		v9fs_fid_add(dentry, fid);
+		d_instantiate(dentry, inode);
+		fid = NULL;
+		err = 0;
+	} else {
+		/*
+		 * Not in cached mode. No need to populate inode with stat.
+		 * socket syscall returns a fd, so we need instantiate
+		 */
+		inode = v9fs_get_inode(dir->i_sb, mode, rdev);
+		if (IS_ERR(inode)) {
+			err = PTR_ERR(inode);
+			goto error;
+		}
+		v9fs_set_create_acl(inode, fid, dacl, pacl);
+		d_instantiate(dentry, inode);
+	}
+error:
+	if (fid)
+		p9_client_clunk(fid);
+	v9fs_put_acl(dacl, pacl);
+	return err;
+}
+
+/**
+ * v9fs_vfs_follow_link_dotl - follow a symlink path
+ * @dentry: dentry for symlink
+ * @cookie: place to pass the data to put_link()
+ */
+
+static const char *
+v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie)
+{
+	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	char *target;
+	int retval;
+
+	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
+
+	if (IS_ERR(fid))
+		return ERR_CAST(fid);
+	retval = p9_client_readlink(fid, &target);
+	if (retval)
+		return ERR_PTR(retval);
+	return *cookie = target;
+}
+
+int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
+{
+	struct p9_stat_dotl *st;
+	struct v9fs_session_info *v9ses;
+	unsigned int flags;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
+	if (IS_ERR(st))
+		return PTR_ERR(st);
+	/*
+	 * Don't update inode if the file type is different
+	 */
+	if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT))
+		goto out;
+
+	/*
+	 * We don't want to refresh inode->i_size,
+	 * because we may have cached data
+	 */
+	flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
+		V9FS_STAT2INODE_KEEP_ISIZE : 0;
+	v9fs_stat2inode_dotl(st, inode, flags);
+out:
+	kfree(st);
+	return 0;
+}
+
+const struct inode_operations v9fs_dir_inode_operations_dotl = {
+	.create = v9fs_vfs_create_dotl,
+	.atomic_open = v9fs_vfs_atomic_open_dotl,
+	.lookup = v9fs_vfs_lookup,
+	.link = v9fs_vfs_link_dotl,
+	.symlink = v9fs_vfs_symlink_dotl,
+	.unlink = v9fs_vfs_unlink,
+	.mkdir = v9fs_vfs_mkdir_dotl,
+	.rmdir = v9fs_vfs_rmdir,
+	.mknod = v9fs_vfs_mknod_dotl,
+	.rename = v9fs_vfs_rename,
+	.getattr = v9fs_vfs_getattr_dotl,
+	.setattr = v9fs_vfs_setattr_dotl,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.removexattr = generic_removexattr,
+	.listxattr = v9fs_listxattr,
+	.get_acl = v9fs_iop_get_acl,
+};
+
+const struct inode_operations v9fs_file_inode_operations_dotl = {
+	.getattr = v9fs_vfs_getattr_dotl,
+	.setattr = v9fs_vfs_setattr_dotl,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.removexattr = generic_removexattr,
+	.listxattr = v9fs_listxattr,
+	.get_acl = v9fs_iop_get_acl,
+};
+
+const struct inode_operations v9fs_symlink_inode_operations_dotl = {
+	.readlink = generic_readlink,
+	.follow_link = v9fs_vfs_follow_link_dotl,
+	.put_link = kfree_put_link,
+	.getattr = v9fs_vfs_getattr_dotl,
+	.setattr = v9fs_vfs_setattr_dotl,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
+	.removexattr = generic_removexattr,
+	.listxattr = v9fs_listxattr,
+};

addons/9p/src/4.4.180/vfs_super.c

@@ -0,0 +1,366 @@
+/*
+ *  linux/fs/9p/vfs_super.c
+ *
+ * This file contians superblock ops for 9P2000. It is intended that
+ * you mount this file system on directories.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/magic.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "xattr.h"
+#include "acl.h"
+
+static const struct super_operations v9fs_super_ops, v9fs_super_ops_dotl;
+
+/**
+ * v9fs_set_super - set the superblock
+ * @s: super block
+ * @data: file system specific data
+ *
+ */
+
+static int v9fs_set_super(struct super_block *s, void *data)
+{
+	s->s_fs_info = data;
+	return set_anon_super(s, data);
+}
+
+/**
+ * v9fs_fill_super - populate superblock with info
+ * @sb: superblock
+ * @v9ses: session information
+ * @flags: flags propagated from v9fs_mount()
+ *
+ */
+
+static void
+v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
+		int flags, void *data)
+{
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
+	sb->s_blocksize = 1 << sb->s_blocksize_bits;
+	sb->s_magic = V9FS_MAGIC;
+	if (v9fs_proto_dotl(v9ses)) {
+		sb->s_op = &v9fs_super_ops_dotl;
+		sb->s_xattr = v9fs_xattr_handlers;
+	} else
+		sb->s_op = &v9fs_super_ops;
+	sb->s_bdi = &v9ses->bdi;
+	if (v9ses->cache)
+		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE;
+
+	sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
+	if (!v9ses->cache)
+		sb->s_flags |= MS_SYNCHRONOUS;
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+	if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL)
+		sb->s_flags |= MS_POSIXACL;
+#endif
+
+	save_mount_options(sb, data);
+}
+
+/**
+ * v9fs_mount - mount a superblock
+ * @fs_type: file system type
+ * @flags: mount flags
+ * @dev_name: device name that was mounted
+ * @data: mount options
+ *
+ */
+
+static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data)
+{
+	struct super_block *sb = NULL;
+	struct inode *inode = NULL;
+	struct dentry *root = NULL;
+	struct v9fs_session_info *v9ses = NULL;
+	umode_t mode = S_IRWXUGO | S_ISVTX;
+	struct p9_fid *fid;
+	int retval = 0;
+
+	p9_debug(P9_DEBUG_VFS, "\n");
+
+	v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
+	if (!v9ses)
+		return ERR_PTR(-ENOMEM);
+
+	fid = v9fs_session_init(v9ses, dev_name, data);
+	if (IS_ERR(fid)) {
+		retval = PTR_ERR(fid);
+		goto free_session;
+	}
+
+	sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
+	if (IS_ERR(sb)) {
+		retval = PTR_ERR(sb);
+		goto clunk_fid;
+	}
+	v9fs_fill_super(sb, v9ses, flags, data);
+
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+		sb->s_d_op = &v9fs_cached_dentry_operations;
+	else
+		sb->s_d_op = &v9fs_dentry_operations;
+
+	inode = v9fs_get_inode(sb, S_IFDIR | mode, 0);
+	if (IS_ERR(inode)) {
+		retval = PTR_ERR(inode);
+		goto release_sb;
+	}
+
+	root = d_make_root(inode);
+	if (!root) {
+		retval = -ENOMEM;
+		goto release_sb;
+	}
+	sb->s_root = root;
+	if (v9fs_proto_dotl(v9ses)) {
+		struct p9_stat_dotl *st = NULL;
+		st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
+		if (IS_ERR(st)) {
+			retval = PTR_ERR(st);
+			goto release_sb;
+		}
+		d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
+		v9fs_stat2inode_dotl(st, d_inode(root), 0);
+		kfree(st);
+	} else {
+		struct p9_wstat *st = NULL;
+		st = p9_client_stat(fid);
+		if (IS_ERR(st)) {
+			retval = PTR_ERR(st);
+			goto release_sb;
+		}
+
+		d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
+		v9fs_stat2inode(st, d_inode(root), sb, 0);
+
+		p9stat_free(st);
+		kfree(st);
+	}
+	retval = v9fs_get_acl(inode, fid);
+	if (retval)
+		goto release_sb;
+	v9fs_fid_add(root, fid);
+
+	p9_debug(P9_DEBUG_VFS, " simple set mount, return 0\n");
+	return dget(sb->s_root);
+
+clunk_fid:
+	p9_client_clunk(fid);
+	v9fs_session_close(v9ses);
+free_session:
+	kfree(v9ses);
+	return ERR_PTR(retval);
+
+release_sb:
+	/*
+	 * we will do the session_close and root dentry release
+	 * in the below call. But we need to clunk fid, because we haven't
+	 * attached the fid to dentry so it won't get clunked
+	 * automatically.
+	 */
+	p9_client_clunk(fid);
+	deactivate_locked_super(sb);
+	return ERR_PTR(retval);
+}
+
+/**
+ * v9fs_kill_super - Kill Superblock
+ * @s: superblock
+ *
+ */
+
+static void v9fs_kill_super(struct super_block *s)
+{
+	struct v9fs_session_info *v9ses = s->s_fs_info;
+
+	p9_debug(P9_DEBUG_VFS, " %p\n", s);
+
+	kill_anon_super(s);
+
+	v9fs_session_cancel(v9ses);
+	v9fs_session_close(v9ses);
+	kfree(v9ses);
+	s->s_fs_info = NULL;
+	p9_debug(P9_DEBUG_VFS, "exiting kill_super\n");
+}
+
+static void
+v9fs_umount_begin(struct super_block *sb)
+{
+	struct v9fs_session_info *v9ses;
+
+	v9ses = sb->s_fs_info;
+	v9fs_session_begin_cancel(v9ses);
+}
+
+static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid;
+	struct p9_rstatfs rs;
+	int res;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid)) {
+		res = PTR_ERR(fid);
+		goto done;
+	}
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	if (v9fs_proto_dotl(v9ses)) {
+		res = p9_client_statfs(fid, &rs);
+		if (res == 0) {
+			buf->f_type = rs.type;
+			buf->f_bsize = rs.bsize;
+			buf->f_blocks = rs.blocks;
+			buf->f_bfree = rs.bfree;
+			buf->f_bavail = rs.bavail;
+			buf->f_files = rs.files;
+			buf->f_ffree = rs.ffree;
+			buf->f_fsid.val[0] = rs.fsid & 0xFFFFFFFFUL;
+			buf->f_fsid.val[1] = (rs.fsid >> 32) & 0xFFFFFFFFUL;
+			buf->f_namelen = rs.namelen;
+		}
+		if (res != -ENOSYS)
+			goto done;
+	}
+	res = simple_statfs(dentry, buf);
+done:
+	return res;
+}
+
+static int v9fs_drop_inode(struct inode *inode)
+{
+	struct v9fs_session_info *v9ses;
+	v9ses = v9fs_inode2v9ses(inode);
+	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+		return generic_drop_inode(inode);
+	/*
+	 * in case of non cached mode always drop the
+	 * the inode because we want the inode attribute
+	 * to always match that on the server.
+	 */
+	return 1;
+}
+
+static int v9fs_write_inode(struct inode *inode,
+			    struct writeback_control *wbc)
+{
+	int ret;
+	struct p9_wstat wstat;
+	struct v9fs_inode *v9inode;
+	/*
+	 * send an fsync request to server irrespective of
+	 * wbc->sync_mode.
+	 */
+	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
+	v9inode = V9FS_I(inode);
+	if (!v9inode->writeback_fid)
+		return 0;
+	v9fs_blank_wstat(&wstat);
+
+	ret = p9_client_wstat(v9inode->writeback_fid, &wstat);
+	if (ret < 0) {
+		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		return ret;
+	}
+	return 0;
+}
+
+static int v9fs_write_inode_dotl(struct inode *inode,
+				 struct writeback_control *wbc)
+{
+	int ret;
+	struct v9fs_inode *v9inode;
+	/*
+	 * send an fsync request to server irrespective of
+	 * wbc->sync_mode.
+	 */
+	v9inode = V9FS_I(inode);
+	p9_debug(P9_DEBUG_VFS, "%s: inode %p, writeback_fid %p\n",
+		 __func__, inode, v9inode->writeback_fid);
+	if (!v9inode->writeback_fid)
+		return 0;
+
+	ret = p9_client_fsync(v9inode->writeback_fid, 0);
+	if (ret < 0) {
+		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		return ret;
+	}
+	return 0;
+}
+
+static const struct super_operations v9fs_super_ops = {
+	.alloc_inode = v9fs_alloc_inode,
+	.destroy_inode = v9fs_destroy_inode,
+	.statfs = simple_statfs,
+	.evict_inode = v9fs_evict_inode,
+	.show_options = generic_show_options,
+	.umount_begin = v9fs_umount_begin,
+	.write_inode = v9fs_write_inode,
+};
+
+static const struct super_operations v9fs_super_ops_dotl = {
+	.alloc_inode = v9fs_alloc_inode,
+	.destroy_inode = v9fs_destroy_inode,
+	.statfs = v9fs_statfs,
+	.drop_inode = v9fs_drop_inode,
+	.evict_inode = v9fs_evict_inode,
+	.show_options = generic_show_options,
+	.umount_begin = v9fs_umount_begin,
+	.write_inode = v9fs_write_inode_dotl,
+};
+
+struct file_system_type v9fs_fs_type = {
+	.name = "9p",
+	.mount = v9fs_mount,
+	.kill_sb = v9fs_kill_super,
+	.owner = THIS_MODULE,
+	.fs_flags = FS_RENAME_DOES_D_MOVE,
+};
+MODULE_ALIAS_FS("9p");

addons/9p/src/4.4.180/xattr.c

@@ -0,0 +1,195 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/uio.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "fid.h"
+#include "xattr.h"
+
+ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
+			   void *buffer, size_t buffer_size)
+{
+	ssize_t retval;
+	u64 attr_size;
+	struct p9_fid *attr_fid;
+	struct kvec kvec = {.iov_base = buffer, .iov_len = buffer_size};
+	struct iov_iter to;
+	int err;
+
+	iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size);
+
+	attr_fid = p9_client_xattrwalk(fid, name, &attr_size);
+	if (IS_ERR(attr_fid)) {
+		retval = PTR_ERR(attr_fid);
+		p9_debug(P9_DEBUG_VFS, "p9_client_attrwalk failed %zd\n",
+			 retval);
+		return retval;
+	}
+	if (attr_size > buffer_size) {
+		if (!buffer_size) /* request to get the attr_size */
+			retval = attr_size;
+		else
+			retval = -ERANGE;
+	} else {
+		iov_iter_truncate(&to, attr_size);
+		retval = p9_client_read(attr_fid, 0, &to, &err);
+		if (err)
+			retval = err;
+	}
+	p9_client_clunk(attr_fid);
+	return retval;
+}
+
+
+/*
+ * v9fs_xattr_get()
+ *
+ * Copy an extended attribute into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
+		       void *buffer, size_t buffer_size)
+{
+	struct p9_fid *fid;
+
+	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n",
+		 name, buffer_size);
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+
+	return v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
+}
+
+/*
+ * v9fs_xattr_set()
+ *
+ * Create, replace or remove an extended attribute for this inode. Buffer
+ * is NULL to remove an existing extended attribute, and non-NULL to
+ * either replace an existing extended attribute, or create a new extended
+ * attribute. The flags XATTR_REPLACE and XATTR_CREATE
+ * specify that an extended attribute must exist and must not exist
+ * previous to the call, respectively.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int v9fs_xattr_set(struct dentry *dentry, const char *name,
+		   const void *value, size_t value_len, int flags)
+{
+	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+	return v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+}
+
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+		   const void *value, size_t value_len, int flags)
+{
+	struct kvec kvec = {.iov_base = (void *)value, .iov_len = value_len};
+	struct iov_iter from;
+	int retval, err;
+
+	iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len);
+
+	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
+		 name, value_len, flags);
+
+	/* Clone it */
+	fid = p9_client_walk(fid, 0, NULL, 1);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+
+	/*
+	 * On success fid points to xattr
+	 */
+	retval = p9_client_xattrcreate(fid, name, value_len, flags);
+	if (retval < 0)
+		p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n",
+			 retval);
+	else
+		p9_client_write(fid, 0, &from, &retval);
+	err = p9_client_clunk(fid);
+	if (!retval && err)
+		retval = err;
+	return retval;
+}
+
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	return v9fs_xattr_get(dentry, NULL, buffer, buffer_size);
+}
+
+static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
+				  struct dentry *dentry, const char *name,
+				  void *buffer, size_t size)
+{
+	const char *full_name = xattr_full_name(handler, name);
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return v9fs_xattr_get(dentry, full_name, buffer, size);
+}
+
+static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
+				  struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, name);
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return v9fs_xattr_set(dentry, full_name, value, size, flags);
+}
+
+static struct xattr_handler v9fs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.get	= v9fs_xattr_handler_get,
+	.set	= v9fs_xattr_handler_set,
+};
+
+static struct xattr_handler v9fs_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.get	= v9fs_xattr_handler_get,
+	.set	= v9fs_xattr_handler_set,
+};
+
+#ifdef CONFIG_9P_FS_SECURITY
+static struct xattr_handler v9fs_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.get	= v9fs_xattr_handler_get,
+	.set	= v9fs_xattr_handler_set,
+};
+#endif
+
+const struct xattr_handler *v9fs_xattr_handlers[] = {
+	&v9fs_xattr_user_handler,
+	&v9fs_xattr_trusted_handler,
+#ifdef CONFIG_9P_FS_POSIX_ACL
+	&v9fs_xattr_acl_access_handler,
+	&v9fs_xattr_acl_default_handler,
+#endif
+#ifdef CONFIG_9P_FS_SECURITY
+	&v9fs_xattr_security_handler,
+#endif
+	NULL
+};

addons/9p/src/4.4.180/xattr.h

@@ -0,0 +1,34 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+#ifndef FS_9P_XATTR_H
+#define FS_9P_XATTR_H
+
+#include <linux/xattr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+extern const struct xattr_handler *v9fs_xattr_handlers[];
+extern const struct xattr_handler v9fs_xattr_acl_access_handler;
+extern const struct xattr_handler v9fs_xattr_acl_default_handler;
+
+extern ssize_t v9fs_fid_xattr_get(struct p9_fid *, const char *,
+				  void *, size_t);
+extern ssize_t v9fs_xattr_get(struct dentry *, const char *,
+			      void *, size_t);
+extern int v9fs_fid_xattr_set(struct p9_fid *, const char *,
+			  const void *, size_t, int);
+extern int v9fs_xattr_set(struct dentry *, const char *,
+			  const void *, size_t, int);
+extern ssize_t v9fs_listxattr(struct dentry *, char *, size_t);
+#endif /* FS_9P_XATTR_H */

addons/acpid/install.sh

@@ -0,0 +1,12 @@
+if [ "${1}" = "sys" ]; then
+  echo "Installing module and daemon for ACPI button"
+  if [ ! -f /tmpRoot/lib/modules/button.ko ]; then
+    cp /modules/button.ko /tmpRoot/lib/modules/
+  fi
+  tar -zxvf /addons/acpid.tgz -C /tmpRoot/
+  chmod 755 /tmpRoot/usr/sbin/acpid
+  chmod 644 /tmpRoot/etc/acpi/events/power
+  chmod 744 /tmpRoot/etc/acpi/power.sh
+  chmod 744 /tmpRoot/usr/lib/systemd/system/acpid.service
+  ln -sf /usr/lib/systemd/system/acpid.service /tmpRoot/etc/systemd/system/multi-user.target.wants/acpid.service
+fi

addons/acpid/manifest.yml

@@ -0,0 +1,36 @@
+version: 1
+name: acpid
+description: "Flexible and extensible daemon for delivering ACPI events"
+available-for:
+  bromolow-3.10.108:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  apollolake-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  broadwell-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  broadwellnk-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  denverton-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  geminilake-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  v1000-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: true
+  purley-4.4.180:
+    install-script: "install.sh"
+    copy: "all"
+    modules: false

addons/acpid/src/3.10.108/Makefile

@@ -0,0 +1,46 @@
+#
+# Makefile for the Linux ACPI interpreter
+#
+
+#
+# ACPI Boot-Time Table Parsing
+#
+#obj-$(CONFIG_X86)		+= blacklist.o
+
+# Power management related files
+#acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
+
+
+#
+# ACPI Bus and Device Drivers
+#
+#acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
+#acpi-$(CONFIG_X86_INTEL_LPSS)	+= acpi_lpss.o
+#acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
+#acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
+acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
+#acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
+
+# These are (potentially) separate modules
+
+# IPMI may be used by other drivers, so it has to initialise before them
+#obj-$(CONFIG_ACPI_IPMI)		+= acpi_ipmi.o
+
+#obj-$(CONFIG_ACPI_AC) 		+= ac.o
+obj-$(CONFIG_ACPI_BUTTON)	+= button.o
+#obj-$(CONFIG_ACPI_FAN)		+= fan.o
+#obj-$(CONFIG_ACPI_VIDEO)	+= video.o
+#obj-$(CONFIG_ACPI_PCI_SLOT)	+= pci_slot.o
+#obj-$(CONFIG_ACPI_CONTAINER)	+= container.o
+#obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
+#obj-$(CONFIG_ACPI_HOTPLUG_MEMORY) += acpi_memhotplug.o
+#obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
+#obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
+#obj-$(CONFIG_ACPI_SBS)		+= sbs.o
+#obj-$(CONFIG_ACPI_HED)		+= hed.o
+#obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
+#obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
+#obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
+#obj-$(CONFIG_ACPI_I2C)		+= acpi_i2c.o
+
+#obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o

addons/acpid/src/3.10.108/button.c

@@ -0,0 +1,454 @@
+/*
+ *  button.c - ACPI Button Driver
+ *
+ *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
+ *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  This program is distributed in the hope that 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.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/input.h>
+#include <linux/slab.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+#include <acpi/button.h>
+
+#define PREFIX "ACPI: "
+
+#define ACPI_BUTTON_CLASS		"button"
+#define ACPI_BUTTON_FILE_INFO		"info"
+#define ACPI_BUTTON_FILE_STATE		"state"
+#define ACPI_BUTTON_TYPE_UNKNOWN	0x00
+#define ACPI_BUTTON_NOTIFY_STATUS	0x80
+
+#define ACPI_BUTTON_SUBCLASS_POWER	"power"
+#define ACPI_BUTTON_HID_POWER		"PNP0C0C"
+#define ACPI_BUTTON_DEVICE_NAME_POWER	"Power Button"
+#define ACPI_BUTTON_TYPE_POWER		0x01
+
+#define ACPI_BUTTON_SUBCLASS_SLEEP	"sleep"
+#define ACPI_BUTTON_HID_SLEEP		"PNP0C0E"
+#define ACPI_BUTTON_DEVICE_NAME_SLEEP	"Sleep Button"
+#define ACPI_BUTTON_TYPE_SLEEP		0x03
+
+#define ACPI_BUTTON_SUBCLASS_LID	"lid"
+#define ACPI_BUTTON_HID_LID		"PNP0C0D"
+#define ACPI_BUTTON_DEVICE_NAME_LID	"Lid Switch"
+#define ACPI_BUTTON_TYPE_LID		0x05
+
+#define _COMPONENT		ACPI_BUTTON_COMPONENT
+ACPI_MODULE_NAME("button");
+
+MODULE_AUTHOR("Paul Diefenbaugh");
+MODULE_DESCRIPTION("ACPI Button Driver");
+MODULE_LICENSE("GPL");
+
+static const struct acpi_device_id button_device_ids[] = {
+	{ACPI_BUTTON_HID_LID,    0},
+	{ACPI_BUTTON_HID_SLEEP,  0},
+	{ACPI_BUTTON_HID_SLEEPF, 0},
+	{ACPI_BUTTON_HID_POWER,  0},
+	{ACPI_BUTTON_HID_POWERF, 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, button_device_ids);
+
+static int acpi_button_add(struct acpi_device *device);
+static int acpi_button_remove(struct acpi_device *device);
+static void acpi_button_notify(struct acpi_device *device, u32 event);
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_button_resume(struct device *dev);
+#endif
+static SIMPLE_DEV_PM_OPS(acpi_button_pm, NULL, acpi_button_resume);
+
+static struct acpi_driver acpi_button_driver = {
+	.name = "button",
+	.class = ACPI_BUTTON_CLASS,
+	.ids = button_device_ids,
+	.ops = {
+		.add = acpi_button_add,
+		.remove = acpi_button_remove,
+		.notify = acpi_button_notify,
+	},
+	.drv.pm = &acpi_button_pm,
+};
+
+struct acpi_button {
+	unsigned int type;
+	struct input_dev *input;
+	char phys[32];			/* for input device */
+	unsigned long pushed;
+	bool wakeup_enabled;
+};
+
+static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
+static struct acpi_device *lid_device;
+
+/* --------------------------------------------------------------------------
+                              FS Interface (/proc)
+   -------------------------------------------------------------------------- */
+
+static struct proc_dir_entry *acpi_button_dir;
+static struct proc_dir_entry *acpi_lid_dir;
+
+static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
+{
+	struct acpi_device *device = seq->private;
+	acpi_status status;
+	unsigned long long state;
+
+	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &state);
+	seq_printf(seq, "state:      %s\n",
+		   ACPI_FAILURE(status) ? "unsupported" :
+			(state ? "open" : "closed"));
+	return 0;
+}
+
+static int acpi_button_state_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, acpi_button_state_seq_show, PDE_DATA(inode));
+}
+
+static const struct file_operations acpi_button_state_fops = {
+	.owner = THIS_MODULE,
+	.open = acpi_button_state_open_fs,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int acpi_button_add_fs(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	struct proc_dir_entry *entry = NULL;
+	int ret = 0;
+
+	/* procfs I/F for ACPI lid device only */
+	if (button->type != ACPI_BUTTON_TYPE_LID)
+		return 0;
+
+	if (acpi_button_dir || acpi_lid_dir) {
+		printk(KERN_ERR PREFIX "More than one Lid device found!\n");
+		return -EEXIST;
+	}
+
+	/* create /proc/acpi/button */
+	acpi_button_dir = proc_mkdir(ACPI_BUTTON_CLASS, acpi_root_dir);
+	if (!acpi_button_dir)
+		return -ENODEV;
+
+	/* create /proc/acpi/button/lid */
+	acpi_lid_dir = proc_mkdir(ACPI_BUTTON_SUBCLASS_LID, acpi_button_dir);
+	if (!acpi_lid_dir) {
+		ret = -ENODEV;
+		goto remove_button_dir;
+	}
+
+	/* create /proc/acpi/button/lid/LID/ */
+	acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device), acpi_lid_dir);
+	if (!acpi_device_dir(device)) {
+		ret = -ENODEV;
+		goto remove_lid_dir;
+	}
+
+	/* create /proc/acpi/button/lid/LID/state */
+	entry = proc_create_data(ACPI_BUTTON_FILE_STATE,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_button_state_fops, device);
+	if (!entry) {
+		ret = -ENODEV;
+		goto remove_dev_dir;
+	}
+
+done:
+	return ret;
+
+remove_dev_dir:
+	remove_proc_entry(acpi_device_bid(device),
+			  acpi_lid_dir);
+	acpi_device_dir(device) = NULL;
+remove_lid_dir:
+	remove_proc_entry(ACPI_BUTTON_SUBCLASS_LID, acpi_button_dir);
+remove_button_dir:
+	remove_proc_entry(ACPI_BUTTON_CLASS, acpi_root_dir);
+	goto done;
+}
+
+static int acpi_button_remove_fs(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+
+	if (button->type != ACPI_BUTTON_TYPE_LID)
+		return 0;
+
+	remove_proc_entry(ACPI_BUTTON_FILE_STATE,
+			  acpi_device_dir(device));
+	remove_proc_entry(acpi_device_bid(device),
+			  acpi_lid_dir);
+	acpi_device_dir(device) = NULL;
+	remove_proc_entry(ACPI_BUTTON_SUBCLASS_LID, acpi_button_dir);
+	remove_proc_entry(ACPI_BUTTON_CLASS, acpi_root_dir);
+
+	return 0;
+}
+
+/* --------------------------------------------------------------------------
+                                Driver Interface
+   -------------------------------------------------------------------------- */
+int acpi_lid_notifier_register(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&acpi_lid_notifier, nb);
+}
+EXPORT_SYMBOL(acpi_lid_notifier_register);
+
+int acpi_lid_notifier_unregister(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&acpi_lid_notifier, nb);
+}
+EXPORT_SYMBOL(acpi_lid_notifier_unregister);
+
+int acpi_lid_open(void)
+{
+	acpi_status status;
+	unsigned long long state;
+
+	if (!lid_device)
+		return -ENODEV;
+
+	status = acpi_evaluate_integer(lid_device->handle, "_LID", NULL,
+				       &state);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return !!state;
+}
+EXPORT_SYMBOL(acpi_lid_open);
+
+static int acpi_lid_send_state(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	unsigned long long state;
+	acpi_status status;
+	int ret;
+
+	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &state);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	/* input layer checks if event is redundant */
+	input_report_switch(button->input, SW_LID, !state);
+	input_sync(button->input);
+
+	if (state)
+		pm_wakeup_event(&device->dev, 0);
+
+	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
+	if (ret == NOTIFY_DONE)
+		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
+						   device);
+	if (ret == NOTIFY_DONE || ret == NOTIFY_OK) {
+		/*
+		 * It is also regarded as success if the notifier_chain
+		 * returns NOTIFY_OK or NOTIFY_DONE.
+		 */
+		ret = 0;
+	}
+	return ret;
+}
+
+static void acpi_button_notify(struct acpi_device *device, u32 event)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	struct input_dev *input;
+
+	switch (event) {
+	case ACPI_FIXED_HARDWARE_EVENT:
+		event = ACPI_BUTTON_NOTIFY_STATUS;
+		/* fall through */
+	case ACPI_BUTTON_NOTIFY_STATUS:
+		input = button->input;
+		if (button->type == ACPI_BUTTON_TYPE_LID) {
+			acpi_lid_send_state(device);
+		} else {
+			int keycode = test_bit(KEY_SLEEP, input->keybit) ?
+						KEY_SLEEP : KEY_POWER;
+
+			input_report_key(input, keycode, 1);
+			input_sync(input);
+			input_report_key(input, keycode, 0);
+			input_sync(input);
+
+			pm_wakeup_event(&device->dev, 0);
+		}
+
+		acpi_bus_generate_proc_event(device, event, ++button->pushed);
+		break;
+	default:
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+				  "Unsupported event [0x%x]\n", event));
+		break;
+	}
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_button_resume(struct device *dev)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct acpi_button *button = acpi_driver_data(device);
+
+	if (button->type == ACPI_BUTTON_TYPE_LID)
+		return acpi_lid_send_state(device);
+	return 0;
+}
+#endif
+
+static int acpi_button_add(struct acpi_device *device)
+{
+	struct acpi_button *button;
+	struct input_dev *input;
+	const char *hid = acpi_device_hid(device);
+	char *name, *class;
+	int error;
+
+	button = kzalloc(sizeof(struct acpi_button), GFP_KERNEL);
+	if (!button)
+		return -ENOMEM;
+
+	device->driver_data = button;
+
+	button->input = input = input_allocate_device();
+	if (!input) {
+		error = -ENOMEM;
+		goto err_free_button;
+	}
+
+	name = acpi_device_name(device);
+	class = acpi_device_class(device);
+
+	if (!strcmp(hid, ACPI_BUTTON_HID_POWER) ||
+	    !strcmp(hid, ACPI_BUTTON_HID_POWERF)) {
+		button->type = ACPI_BUTTON_TYPE_POWER;
+		strcpy(name, ACPI_BUTTON_DEVICE_NAME_POWER);
+		sprintf(class, "%s/%s",
+			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_POWER);
+	} else if (!strcmp(hid, ACPI_BUTTON_HID_SLEEP) ||
+		   !strcmp(hid, ACPI_BUTTON_HID_SLEEPF)) {
+		button->type = ACPI_BUTTON_TYPE_SLEEP;
+		strcpy(name, ACPI_BUTTON_DEVICE_NAME_SLEEP);
+		sprintf(class, "%s/%s",
+			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_SLEEP);
+	} else if (!strcmp(hid, ACPI_BUTTON_HID_LID)) {
+		button->type = ACPI_BUTTON_TYPE_LID;
+		strcpy(name, ACPI_BUTTON_DEVICE_NAME_LID);
+		sprintf(class, "%s/%s",
+			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_LID);
+	} else {
+		printk(KERN_ERR PREFIX "Unsupported hid [%s]\n", hid);
+		error = -ENODEV;
+		goto err_free_input;
+	}
+
+	error = acpi_button_add_fs(device);
+	if (error)
+		goto err_free_input;
+
+	snprintf(button->phys, sizeof(button->phys), "%s/button/input0", hid);
+
+	input->name = name;
+	input->phys = button->phys;
+	input->id.bustype = BUS_HOST;
+	input->id.product = button->type;
+	input->dev.parent = &device->dev;
+
+	switch (button->type) {
+	case ACPI_BUTTON_TYPE_POWER:
+		input->evbit[0] = BIT_MASK(EV_KEY);
+		set_bit(KEY_POWER, input->keybit);
+		break;
+
+	case ACPI_BUTTON_TYPE_SLEEP:
+		input->evbit[0] = BIT_MASK(EV_KEY);
+		set_bit(KEY_SLEEP, input->keybit);
+		break;
+
+	case ACPI_BUTTON_TYPE_LID:
+		input->evbit[0] = BIT_MASK(EV_SW);
+		set_bit(SW_LID, input->swbit);
+		break;
+	}
+
+	error = input_register_device(input);
+	if (error)
+		goto err_remove_fs;
+	if (button->type == ACPI_BUTTON_TYPE_LID) {
+		acpi_lid_send_state(device);
+		/*
+		 * This assumes there's only one lid device, or if there are
+		 * more we only care about the last one...
+		 */
+		lid_device = device;
+	}
+
+	if (device->wakeup.flags.valid) {
+		/* Button's GPE is run-wake GPE */
+		acpi_enable_gpe(device->wakeup.gpe_device,
+				device->wakeup.gpe_number);
+		if (!device_may_wakeup(&device->dev)) {
+			device_set_wakeup_enable(&device->dev, true);
+			button->wakeup_enabled = true;
+		}
+	}
+
+	printk(KERN_INFO PREFIX "%s [%s]\n", name, acpi_device_bid(device));
+	return 0;
+
+ err_remove_fs:
+	acpi_button_remove_fs(device);
+ err_free_input:
+	input_free_device(input);
+ err_free_button:
+	kfree(button);
+	return error;
+}
+
+static int acpi_button_remove(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+
+	if (device->wakeup.flags.valid) {
+		acpi_disable_gpe(device->wakeup.gpe_device,
+				device->wakeup.gpe_number);
+		if (button->wakeup_enabled)
+			device_set_wakeup_enable(&device->dev, false);
+	}
+
+	acpi_button_remove_fs(device);
+	input_unregister_device(button->input);
+	kfree(button);
+	return 0;
+}
+
+module_acpi_driver(acpi_button_driver);

addons/acpid/src/4.4.180/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_ACPI_BUTTON)	+= button.o

addons/acpid/src/4.4.180/button.c

@@ -0,0 +1,449 @@
+/*
+ *  button.c - ACPI Button Driver
+ *
+ *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
+ *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  This program is distributed in the hope that 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/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/input.h>
+#include <linux/slab.h>
+#include <linux/acpi.h>
+#include <acpi/button.h>
+
+#define PREFIX "ACPI: "
+
+#define ACPI_BUTTON_CLASS		"button"
+#define ACPI_BUTTON_FILE_INFO		"info"
+#define ACPI_BUTTON_FILE_STATE		"state"
+#define ACPI_BUTTON_TYPE_UNKNOWN	0x00
+#define ACPI_BUTTON_NOTIFY_STATUS	0x80
+
+#define ACPI_BUTTON_SUBCLASS_POWER	"power"
+#define ACPI_BUTTON_HID_POWER		"PNP0C0C"
+#define ACPI_BUTTON_DEVICE_NAME_POWER	"Power Button"
+#define ACPI_BUTTON_TYPE_POWER		0x01
+
+#define ACPI_BUTTON_SUBCLASS_SLEEP	"sleep"
+#define ACPI_BUTTON_HID_SLEEP		"PNP0C0E"
+#define ACPI_BUTTON_DEVICE_NAME_SLEEP	"Sleep Button"
+#define ACPI_BUTTON_TYPE_SLEEP		0x03
+
+#define ACPI_BUTTON_SUBCLASS_LID	"lid"
+#define ACPI_BUTTON_HID_LID		"PNP0C0D"
+#define ACPI_BUTTON_DEVICE_NAME_LID	"Lid Switch"
+#define ACPI_BUTTON_TYPE_LID		0x05
+
+#define _COMPONENT		ACPI_BUTTON_COMPONENT
+ACPI_MODULE_NAME("button");
+
+MODULE_AUTHOR("Paul Diefenbaugh");
+MODULE_DESCRIPTION("ACPI Button Driver");
+MODULE_LICENSE("GPL");
+
+static const struct acpi_device_id button_device_ids[] = {
+	{ACPI_BUTTON_HID_LID,    0},
+	{ACPI_BUTTON_HID_SLEEP,  0},
+	{ACPI_BUTTON_HID_SLEEPF, 0},
+	{ACPI_BUTTON_HID_POWER,  0},
+	{ACPI_BUTTON_HID_POWERF, 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, button_device_ids);
+
+static int acpi_button_add(struct acpi_device *device);
+static int acpi_button_remove(struct acpi_device *device);
+static void acpi_button_notify(struct acpi_device *device, u32 event);
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_button_suspend(struct device *dev);
+static int acpi_button_resume(struct device *dev);
+#else
+#define acpi_button_suspend NULL
+#define acpi_button_resume NULL
+#endif
+static SIMPLE_DEV_PM_OPS(acpi_button_pm, acpi_button_suspend, acpi_button_resume);
+
+static struct acpi_driver acpi_button_driver = {
+	.name = "button",
+	.class = ACPI_BUTTON_CLASS,
+	.ids = button_device_ids,
+	.ops = {
+		.add = acpi_button_add,
+		.remove = acpi_button_remove,
+		.notify = acpi_button_notify,
+	},
+	.drv.pm = &acpi_button_pm,
+};
+
+struct acpi_button {
+	unsigned int type;
+	struct input_dev *input;
+	char phys[32];			/* for input device */
+	unsigned long pushed;
+	bool suspended;
+};
+
+static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
+static struct acpi_device *lid_device;
+
+/* --------------------------------------------------------------------------
+                              FS Interface (/proc)
+   -------------------------------------------------------------------------- */
+
+static struct proc_dir_entry *acpi_button_dir;
+static struct proc_dir_entry *acpi_lid_dir;
+
+static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
+{
+	struct acpi_device *device = seq->private;
+	acpi_status status;
+	unsigned long long state;
+
+	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &state);
+	seq_printf(seq, "state:      %s\n",
+		   ACPI_FAILURE(status) ? "unsupported" :
+			(state ? "open" : "closed"));
+	return 0;
+}
+
+static int acpi_button_state_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, acpi_button_state_seq_show, PDE_DATA(inode));
+}
+
+static const struct file_operations acpi_button_state_fops = {
+	.owner = THIS_MODULE,
+	.open = acpi_button_state_open_fs,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int acpi_button_add_fs(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	struct proc_dir_entry *entry = NULL;
+	int ret = 0;
+
+	/* procfs I/F for ACPI lid device only */
+	if (button->type != ACPI_BUTTON_TYPE_LID)
+		return 0;
+
+	if (acpi_button_dir || acpi_lid_dir) {
+		printk(KERN_ERR PREFIX "More than one Lid device found!\n");
+		return -EEXIST;
+	}
+
+	/* create /proc/acpi/button */
+	acpi_button_dir = proc_mkdir(ACPI_BUTTON_CLASS, acpi_root_dir);
+	if (!acpi_button_dir)
+		return -ENODEV;
+
+	/* create /proc/acpi/button/lid */
+	acpi_lid_dir = proc_mkdir(ACPI_BUTTON_SUBCLASS_LID, acpi_button_dir);
+	if (!acpi_lid_dir) {
+		ret = -ENODEV;
+		goto remove_button_dir;
+	}
+
+	/* create /proc/acpi/button/lid/LID/ */
+	acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device), acpi_lid_dir);
+	if (!acpi_device_dir(device)) {
+		ret = -ENODEV;
+		goto remove_lid_dir;
+	}
+
+	/* create /proc/acpi/button/lid/LID/state */
+	entry = proc_create_data(ACPI_BUTTON_FILE_STATE,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_button_state_fops, device);
+	if (!entry) {
+		ret = -ENODEV;
+		goto remove_dev_dir;
+	}
+
+done:
+	return ret;
+
+remove_dev_dir:
+	remove_proc_entry(acpi_device_bid(device),
+			  acpi_lid_dir);
+	acpi_device_dir(device) = NULL;
+remove_lid_dir:
+	remove_proc_entry(ACPI_BUTTON_SUBCLASS_LID, acpi_button_dir);
+remove_button_dir:
+	remove_proc_entry(ACPI_BUTTON_CLASS, acpi_root_dir);
+	goto done;
+}
+
+static int acpi_button_remove_fs(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+
+	if (button->type != ACPI_BUTTON_TYPE_LID)
+		return 0;
+
+	remove_proc_entry(ACPI_BUTTON_FILE_STATE,
+			  acpi_device_dir(device));
+	remove_proc_entry(acpi_device_bid(device),
+			  acpi_lid_dir);
+	acpi_device_dir(device) = NULL;
+	remove_proc_entry(ACPI_BUTTON_SUBCLASS_LID, acpi_button_dir);
+	remove_proc_entry(ACPI_BUTTON_CLASS, acpi_root_dir);
+
+	return 0;
+}
+
+/* --------------------------------------------------------------------------
+                                Driver Interface
+   -------------------------------------------------------------------------- */
+int acpi_lid_notifier_register(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&acpi_lid_notifier, nb);
+}
+EXPORT_SYMBOL(acpi_lid_notifier_register);
+
+int acpi_lid_notifier_unregister(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&acpi_lid_notifier, nb);
+}
+EXPORT_SYMBOL(acpi_lid_notifier_unregister);
+
+int acpi_lid_open(void)
+{
+	acpi_status status;
+	unsigned long long state;
+
+	if (!lid_device)
+		return -ENODEV;
+
+	status = acpi_evaluate_integer(lid_device->handle, "_LID", NULL,
+				       &state);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return !!state;
+}
+EXPORT_SYMBOL(acpi_lid_open);
+
+static int acpi_lid_send_state(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	unsigned long long state;
+	acpi_status status;
+	int ret;
+
+	status = acpi_evaluate_integer(device->handle, "_LID", NULL, &state);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	/* input layer checks if event is redundant */
+	input_report_switch(button->input, SW_LID, !state);
+	input_sync(button->input);
+
+	if (state)
+		pm_wakeup_event(&device->dev, 0);
+
+	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
+	if (ret == NOTIFY_DONE)
+		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
+						   device);
+	if (ret == NOTIFY_DONE || ret == NOTIFY_OK) {
+		/*
+		 * It is also regarded as success if the notifier_chain
+		 * returns NOTIFY_OK or NOTIFY_DONE.
+		 */
+		ret = 0;
+	}
+	return ret;
+}
+
+static void acpi_button_notify(struct acpi_device *device, u32 event)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+	struct input_dev *input;
+
+	switch (event) {
+	case ACPI_FIXED_HARDWARE_EVENT:
+		event = ACPI_BUTTON_NOTIFY_STATUS;
+		/* fall through */
+	case ACPI_BUTTON_NOTIFY_STATUS:
+		input = button->input;
+		if (button->type == ACPI_BUTTON_TYPE_LID) {
+			acpi_lid_send_state(device);
+		} else {
+			int keycode;
+
+			pm_wakeup_event(&device->dev, 0);
+			if (button->suspended)
+				break;
+
+			keycode = test_bit(KEY_SLEEP, input->keybit) ?
+						KEY_SLEEP : KEY_POWER;
+			input_report_key(input, keycode, 1);
+			input_sync(input);
+			input_report_key(input, keycode, 0);
+			input_sync(input);
+
+			acpi_bus_generate_netlink_event(
+					device->pnp.device_class,
+					dev_name(&device->dev),
+					event, ++button->pushed);
+		}
+		break;
+	default:
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+				  "Unsupported event [0x%x]\n", event));
+		break;
+	}
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_button_suspend(struct device *dev)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct acpi_button *button = acpi_driver_data(device);
+
+	button->suspended = true;
+	return 0;
+}
+
+static int acpi_button_resume(struct device *dev)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct acpi_button *button = acpi_driver_data(device);
+
+	button->suspended = false;
+	if (button->type == ACPI_BUTTON_TYPE_LID)
+		return acpi_lid_send_state(device);
+	return 0;
+}
+#endif
+
+static int acpi_button_add(struct acpi_device *device)
+{
+	struct acpi_button *button;
+	struct input_dev *input;
+	const char *hid = acpi_device_hid(device);
+	char *name, *class;
+	int error;
+
+	button = kzalloc(sizeof(struct acpi_button), GFP_KERNEL);
+	if (!button)
+		return -ENOMEM;
+
+	device->driver_data = button;
+
+	button->input = input = input_allocate_device();
+	if (!input) {
+		error = -ENOMEM;
+		goto err_free_button;
+	}
+
+	name = acpi_device_name(device);
+	class = acpi_device_class(device);
+
+	if (!strcmp(hid, ACPI_BUTTON_HID_POWER) ||
+	    !strcmp(hid, ACPI_BUTTON_HID_POWERF)) {
+		button->type = ACPI_BUTTON_TYPE_POWER;
+		strcpy(name, ACPI_BUTTON_DEVICE_NAME_POWER);
+		sprintf(class, "%s/%s",
+			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_POWER);
+	} else if (!strcmp(hid, ACPI_BUTTON_HID_SLEEP) ||
+		   !strcmp(hid, ACPI_BUTTON_HID_SLEEPF)) {
+		button->type = ACPI_BUTTON_TYPE_SLEEP;
+		strcpy(name, ACPI_BUTTON_DEVICE_NAME_SLEEP);
+		sprintf(class, "%s/%s",
+			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_SLEEP);
+	} else if (!strcmp(hid, ACPI_BUTTON_HID_LID)) {
+		button->type = ACPI_BUTTON_TYPE_LID;
+		strcpy(name, ACPI_BUTTON_DEVICE_NAME_LID);
+		sprintf(class, "%s/%s",
+			ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_LID);
+	} else {
+		printk(KERN_ERR PREFIX "Unsupported hid [%s]\n", hid);
+		error = -ENODEV;
+		goto err_free_input;
+	}
+
+	error = acpi_button_add_fs(device);
+	if (error)
+		goto err_free_input;
+
+	snprintf(button->phys, sizeof(button->phys), "%s/button/input0", hid);
+
+	input->name = name;
+	input->phys = button->phys;
+	input->id.bustype = BUS_HOST;
+	input->id.product = button->type;
+	input->dev.parent = &device->dev;
+
+	switch (button->type) {
+	case ACPI_BUTTON_TYPE_POWER:
+		input_set_capability(input, EV_KEY, KEY_POWER);
+		break;
+
+	case ACPI_BUTTON_TYPE_SLEEP:
+		input_set_capability(input, EV_KEY, KEY_SLEEP);
+		break;
+
+	case ACPI_BUTTON_TYPE_LID:
+		input_set_capability(input, EV_SW, SW_LID);
+		break;
+	}
+
+	error = input_register_device(input);
+	if (error)
+		goto err_remove_fs;
+	if (button->type == ACPI_BUTTON_TYPE_LID) {
+		acpi_lid_send_state(device);
+		/*
+		 * This assumes there's only one lid device, or if there are
+		 * more we only care about the last one...
+		 */
+		lid_device = device;
+	}
+
+	printk(KERN_INFO PREFIX "%s [%s]\n", name, acpi_device_bid(device));
+	return 0;
+
+ err_remove_fs:
+	acpi_button_remove_fs(device);
+ err_free_input:
+	input_free_device(input);
+ err_free_button:
+	kfree(button);
+	return error;
+}
+
+static int acpi_button_remove(struct acpi_device *device)
+{
+	struct acpi_button *button = acpi_driver_data(device);
+
+	acpi_button_remove_fs(device);
+	input_unregister_device(button->input);
+	kfree(button);
+	return 0;
+}
+
+module_acpi_driver(acpi_button_driver);

addons/atl1c/install.sh

@@ -0,0 +1,4 @@
+if [ "${1}" = "rd" ]; then
+  echo "Installing module for Atheros L1C Gigabit Ethernet adapter"
+  ${INSMOD} "/modules/atl1c.ko" ${PARAMS}
+fi

addons/atl1c/manifest.yml

@@ -0,0 +1,28 @@
+version: 1
+name: atl1c
+description: "Driver for Atheros L1C Gigabit Ethernet adapters"
+available-for:
+  bromolow-3.10.108:
+    install-script: &script "install.sh"
+    modules: true
+  apollolake-4.4.180:
+    install-script: *script
+    modules: true
+  broadwell-4.4.180:
+    install-script: *script
+    modules: true
+  broadwellnk-4.4.180:
+    install-script: *script
+    modules: true
+  denverton-4.4.180:
+    install-script: *script
+    modules: true
+  geminilake-4.4.180:
+    install-script: *script
+    modules: true
+  v1000-4.4.180:
+    install-script: *script
+    modules: true
+  purley-4.4.180:
+    install-script: *script
+    modules: true

addons/atl1c/src/3.10.108/Makefile

@@ -0,0 +1,2 @@
+obj-m += atl1c.o
+atl1c-objs := atl1c_main.o atl1c_hw.o atl1c_ethtool.o

addons/atl1c/src/3.10.108/atl1c.h

@@ -0,0 +1,606 @@
+/*
+ * Copyright(c) 2008 - 2009 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#ifndef _ATL1C_H_
+#define _ATL1C_H_
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+#include <linux/mii.h>
+#include <linux/io.h>
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <linux/tcp.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/workqueue.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
+
+#include "atl1c_hw.h"
+
+/* Wake Up Filter Control */
+#define AT_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */
+#define AT_WUFC_MAG  0x00000002 /* Magic Packet Wakeup Enable */
+#define AT_WUFC_EX   0x00000004 /* Directed Exact Wakeup Enable */
+#define AT_WUFC_MC   0x00000008 /* Multicast Wakeup Enable */
+#define AT_WUFC_BC   0x00000010 /* Broadcast Wakeup Enable */
+
+#define AT_VLAN_TO_TAG(_vlan, _tag)	   \
+	_tag =  ((((_vlan) >> 8) & 0xFF)  |\
+		 (((_vlan) & 0xFF) << 8))
+
+#define AT_TAG_TO_VLAN(_tag, _vlan) 	 \
+	_vlan = ((((_tag) >> 8) & 0xFF) |\
+		(((_tag) & 0xFF) << 8))
+
+#define SPEED_0		   0xffff
+#define HALF_DUPLEX        1
+#define FULL_DUPLEX        2
+
+#define AT_RX_BUF_SIZE		(ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN)
+#define MAX_JUMBO_FRAME_SIZE	(6*1024)
+
+#define AT_MAX_RECEIVE_QUEUE    4
+#define AT_DEF_RECEIVE_QUEUE	1
+#define AT_MAX_TRANSMIT_QUEUE	2
+
+#define AT_DMA_HI_ADDR_MASK     0xffffffff00000000ULL
+#define AT_DMA_LO_ADDR_MASK     0x00000000ffffffffULL
+
+#define AT_TX_WATCHDOG  (5 * HZ)
+#define AT_MAX_INT_WORK		5
+#define AT_TWSI_EEPROM_TIMEOUT 	100
+#define AT_HW_MAX_IDLE_DELAY 	10
+#define AT_SUSPEND_LINK_TIMEOUT 100
+
+#define AT_ASPM_L0S_TIMER	6
+#define AT_ASPM_L1_TIMER	12
+#define AT_LCKDET_TIMER		12
+
+#define ATL1C_PCIE_L0S_L1_DISABLE 	0x01
+#define ATL1C_PCIE_PHY_RESET		0x02
+
+#define ATL1C_ASPM_L0s_ENABLE		0x0001
+#define ATL1C_ASPM_L1_ENABLE		0x0002
+
+#define AT_REGS_LEN	(74 * sizeof(u32))
+#define AT_EEPROM_LEN 	512
+
+#define ATL1C_GET_DESC(R, i, type)	(&(((type *)((R)->desc))[i]))
+#define ATL1C_RFD_DESC(R, i)	ATL1C_GET_DESC(R, i, struct atl1c_rx_free_desc)
+#define ATL1C_TPD_DESC(R, i)	ATL1C_GET_DESC(R, i, struct atl1c_tpd_desc)
+#define ATL1C_RRD_DESC(R, i)	ATL1C_GET_DESC(R, i, struct atl1c_recv_ret_status)
+
+/* tpd word 1 bit 0:7 General Checksum task offload */
+#define TPD_L4HDR_OFFSET_MASK	0x00FF
+#define TPD_L4HDR_OFFSET_SHIFT	0
+
+/* tpd word 1 bit 0:7 Large Send task offload (IPv4/IPV6) */
+#define TPD_TCPHDR_OFFSET_MASK	0x00FF
+#define TPD_TCPHDR_OFFSET_SHIFT	0
+
+/* tpd word 1 bit 0:7 Custom Checksum task offload */
+#define TPD_PLOADOFFSET_MASK	0x00FF
+#define TPD_PLOADOFFSET_SHIFT	0
+
+/* tpd word 1 bit 8:17 */
+#define TPD_CCSUM_EN_MASK	0x0001
+#define TPD_CCSUM_EN_SHIFT	8
+#define TPD_IP_CSUM_MASK	0x0001
+#define TPD_IP_CSUM_SHIFT	9
+#define TPD_TCP_CSUM_MASK	0x0001
+#define TPD_TCP_CSUM_SHIFT	10
+#define TPD_UDP_CSUM_MASK	0x0001
+#define TPD_UDP_CSUM_SHIFT	11
+#define TPD_LSO_EN_MASK		0x0001	/* TCP Large Send Offload */
+#define TPD_LSO_EN_SHIFT	12
+#define TPD_LSO_VER_MASK	0x0001
+#define TPD_LSO_VER_SHIFT	13 	/* 0 : ipv4; 1 : ipv4/ipv6 */
+#define TPD_CON_VTAG_MASK	0x0001
+#define TPD_CON_VTAG_SHIFT	14
+#define TPD_INS_VTAG_MASK	0x0001
+#define TPD_INS_VTAG_SHIFT	15
+#define TPD_IPV4_PACKET_MASK	0x0001  /* valid when LSO VER  is 1 */
+#define TPD_IPV4_PACKET_SHIFT	16
+#define TPD_ETH_TYPE_MASK	0x0001
+#define TPD_ETH_TYPE_SHIFT	17	/* 0 : 802.3 frame; 1 : Ethernet */
+
+/* tpd word 18:25 Custom Checksum task offload */
+#define TPD_CCSUM_OFFSET_MASK	0x00FF
+#define TPD_CCSUM_OFFSET_SHIFT	18
+#define TPD_CCSUM_EPAD_MASK	0x0001
+#define TPD_CCSUM_EPAD_SHIFT	30
+
+/* tpd word 18:30 Large Send task offload (IPv4/IPV6) */
+#define TPD_MSS_MASK            0x1FFF
+#define TPD_MSS_SHIFT		18
+
+#define TPD_EOP_MASK		0x0001
+#define TPD_EOP_SHIFT		31
+
+struct atl1c_tpd_desc {
+	__le16	buffer_len; /* include 4-byte CRC */
+	__le16	vlan_tag;
+	__le32	word1;
+	__le64	buffer_addr;
+};
+
+struct atl1c_tpd_ext_desc {
+	u32 reservd_0;
+	__le32 word1;
+	__le32 pkt_len;
+	u32 reservd_1;
+};
+/* rrs word 0 bit 0:31 */
+#define RRS_RX_CSUM_MASK	0xFFFF
+#define RRS_RX_CSUM_SHIFT	0
+#define RRS_RX_RFD_CNT_MASK	0x000F
+#define RRS_RX_RFD_CNT_SHIFT	16
+#define RRS_RX_RFD_INDEX_MASK	0x0FFF
+#define RRS_RX_RFD_INDEX_SHIFT	20
+
+/* rrs flag bit 0:16 */
+#define RRS_HEAD_LEN_MASK	0x00FF
+#define RRS_HEAD_LEN_SHIFT	0
+#define RRS_HDS_TYPE_MASK	0x0003
+#define RRS_HDS_TYPE_SHIFT	8
+#define RRS_CPU_NUM_MASK	0x0003
+#define	RRS_CPU_NUM_SHIFT	10
+#define RRS_HASH_FLG_MASK	0x000F
+#define RRS_HASH_FLG_SHIFT	12
+
+#define RRS_HDS_TYPE_HEAD	1
+#define RRS_HDS_TYPE_DATA	2
+
+#define RRS_IS_NO_HDS_TYPE(flag) \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == 0)
+
+#define RRS_IS_HDS_HEAD(flag) \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == \
+			RRS_HDS_TYPE_HEAD)
+
+#define RRS_IS_HDS_DATA(flag) \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == \
+			RRS_HDS_TYPE_DATA)
+
+/* rrs word 3 bit 0:31 */
+#define RRS_PKT_SIZE_MASK	0x3FFF
+#define RRS_PKT_SIZE_SHIFT	0
+#define RRS_ERR_L4_CSUM_MASK	0x0001
+#define RRS_ERR_L4_CSUM_SHIFT	14
+#define RRS_ERR_IP_CSUM_MASK	0x0001
+#define RRS_ERR_IP_CSUM_SHIFT	15
+#define RRS_VLAN_INS_MASK	0x0001
+#define RRS_VLAN_INS_SHIFT	16
+#define RRS_PROT_ID_MASK	0x0007
+#define RRS_PROT_ID_SHIFT	17
+#define RRS_RX_ERR_SUM_MASK	0x0001
+#define RRS_RX_ERR_SUM_SHIFT	20
+#define RRS_RX_ERR_CRC_MASK	0x0001
+#define RRS_RX_ERR_CRC_SHIFT	21
+#define RRS_RX_ERR_FAE_MASK	0x0001
+#define RRS_RX_ERR_FAE_SHIFT	22
+#define RRS_RX_ERR_TRUNC_MASK	0x0001
+#define RRS_RX_ERR_TRUNC_SHIFT	23
+#define RRS_RX_ERR_RUNC_MASK	0x0001
+#define RRS_RX_ERR_RUNC_SHIFT	24
+#define RRS_RX_ERR_ICMP_MASK	0x0001
+#define RRS_RX_ERR_ICMP_SHIFT	25
+#define RRS_PACKET_BCAST_MASK	0x0001
+#define RRS_PACKET_BCAST_SHIFT	26
+#define RRS_PACKET_MCAST_MASK	0x0001
+#define RRS_PACKET_MCAST_SHIFT	27
+#define RRS_PACKET_TYPE_MASK	0x0001
+#define RRS_PACKET_TYPE_SHIFT	28
+#define RRS_FIFO_FULL_MASK	0x0001
+#define RRS_FIFO_FULL_SHIFT	29
+#define RRS_802_3_LEN_ERR_MASK 	0x0001
+#define RRS_802_3_LEN_ERR_SHIFT 30
+#define RRS_RXD_UPDATED_MASK	0x0001
+#define RRS_RXD_UPDATED_SHIFT	31
+
+#define RRS_ERR_L4_CSUM         0x00004000
+#define RRS_ERR_IP_CSUM         0x00008000
+#define RRS_VLAN_INS            0x00010000
+#define RRS_RX_ERR_SUM          0x00100000
+#define RRS_RX_ERR_CRC          0x00200000
+#define RRS_802_3_LEN_ERR	0x40000000
+#define RRS_RXD_UPDATED		0x80000000
+
+#define RRS_PACKET_TYPE_802_3  	1
+#define RRS_PACKET_TYPE_ETH	0
+#define RRS_PACKET_IS_ETH(word) \
+	((((word) >> RRS_PACKET_TYPE_SHIFT) & RRS_PACKET_TYPE_MASK) == \
+			RRS_PACKET_TYPE_ETH)
+#define RRS_RXD_IS_VALID(word) \
+	((((word) >> RRS_RXD_UPDATED_SHIFT) & RRS_RXD_UPDATED_MASK) == 1)
+
+#define RRS_PACKET_PROT_IS_IPV4_ONLY(word) \
+	((((word) >> RRS_PROT_ID_SHIFT) & RRS_PROT_ID_MASK) == 1)
+#define RRS_PACKET_PROT_IS_IPV6_ONLY(word) \
+	((((word) >> RRS_PROT_ID_SHIFT) & RRS_PROT_ID_MASK) == 6)
+
+struct atl1c_recv_ret_status {
+	__le32  word0;
+	__le32	rss_hash;
+	__le16	vlan_tag;
+	__le16	flag;
+	__le32	word3;
+};
+
+/* RFD descriptor */
+struct atl1c_rx_free_desc {
+	__le64	buffer_addr;
+};
+
+/* DMA Order Settings */
+enum atl1c_dma_order {
+	atl1c_dma_ord_in = 1,
+	atl1c_dma_ord_enh = 2,
+	atl1c_dma_ord_out = 4
+};
+
+enum atl1c_dma_rcb {
+	atl1c_rcb_64 = 0,
+	atl1c_rcb_128 = 1
+};
+
+enum atl1c_mac_speed {
+	atl1c_mac_speed_0 = 0,
+	atl1c_mac_speed_10_100 = 1,
+	atl1c_mac_speed_1000 = 2
+};
+
+enum atl1c_dma_req_block {
+	atl1c_dma_req_128 = 0,
+	atl1c_dma_req_256 = 1,
+	atl1c_dma_req_512 = 2,
+	atl1c_dma_req_1024 = 3,
+	atl1c_dma_req_2048 = 4,
+	atl1c_dma_req_4096 = 5
+};
+
+
+enum atl1c_nic_type {
+	athr_l1c = 0,
+	athr_l2c = 1,
+	athr_l2c_b,
+	athr_l2c_b2,
+	athr_l1d,
+	athr_l1d_2,
+};
+
+enum atl1c_trans_queue {
+	atl1c_trans_normal = 0,
+	atl1c_trans_high = 1
+};
+
+struct atl1c_hw_stats {
+	/* rx */
+	unsigned long rx_ok;		/* The number of good packet received. */
+	unsigned long rx_bcast;		/* The number of good broadcast packet received. */
+	unsigned long rx_mcast;		/* The number of good multicast packet received. */
+	unsigned long rx_pause;		/* The number of Pause packet received. */
+	unsigned long rx_ctrl;		/* The number of Control packet received other than Pause frame. */
+	unsigned long rx_fcs_err;	/* The number of packets with bad FCS. */
+	unsigned long rx_len_err;	/* The number of packets with mismatch of length field and actual size. */
+	unsigned long rx_byte_cnt;	/* The number of bytes of good packet received. FCS is NOT included. */
+	unsigned long rx_runt;		/* The number of packets received that are less than 64 byte long and with good FCS. */
+	unsigned long rx_frag;		/* The number of packets received that are less than 64 byte long and with bad FCS. */
+	unsigned long rx_sz_64;		/* The number of good and bad packets received that are 64 byte long. */
+	unsigned long rx_sz_65_127;	/* The number of good and bad packets received that are between 65 and 127-byte long. */
+	unsigned long rx_sz_128_255;	/* The number of good and bad packets received that are between 128 and 255-byte long. */
+	unsigned long rx_sz_256_511;	/* The number of good and bad packets received that are between 256 and 511-byte long. */
+	unsigned long rx_sz_512_1023;	/* The number of good and bad packets received that are between 512 and 1023-byte long. */
+	unsigned long rx_sz_1024_1518;	/* The number of good and bad packets received that are between 1024 and 1518-byte long. */
+	unsigned long rx_sz_1519_max;	/* The number of good and bad packets received that are between 1519-byte and MTU. */
+	unsigned long rx_sz_ov;		/* The number of good and bad packets received that are more than MTU size truncated by Selene. */
+	unsigned long rx_rxf_ov;	/* The number of frame dropped due to occurrence of RX FIFO overflow. */
+	unsigned long rx_rrd_ov;	/* The number of frame dropped due to occurrence of RRD overflow. */
+	unsigned long rx_align_err;	/* Alignment Error */
+	unsigned long rx_bcast_byte_cnt; /* The byte count of broadcast packet received, excluding FCS. */
+	unsigned long rx_mcast_byte_cnt; /* The byte count of multicast packet received, excluding FCS. */
+	unsigned long rx_err_addr;	/* The number of packets dropped due to address filtering. */
+
+	/* tx */
+	unsigned long tx_ok;		/* The number of good packet transmitted. */
+	unsigned long tx_bcast;		/* The number of good broadcast packet transmitted. */
+	unsigned long tx_mcast;		/* The number of good multicast packet transmitted. */
+	unsigned long tx_pause;		/* The number of Pause packet transmitted. */
+	unsigned long tx_exc_defer;	/* The number of packets transmitted with excessive deferral. */
+	unsigned long tx_ctrl;		/* The number of packets transmitted is a control frame, excluding Pause frame. */
+	unsigned long tx_defer;		/* The number of packets transmitted that is deferred. */
+	unsigned long tx_byte_cnt;	/* The number of bytes of data transmitted. FCS is NOT included. */
+	unsigned long tx_sz_64;		/* The number of good and bad packets transmitted that are 64 byte long. */
+	unsigned long tx_sz_65_127;	/* The number of good and bad packets transmitted that are between 65 and 127-byte long. */
+	unsigned long tx_sz_128_255;	/* The number of good and bad packets transmitted that are between 128 and 255-byte long. */
+	unsigned long tx_sz_256_511;	/* The number of good and bad packets transmitted that are between 256 and 511-byte long. */
+	unsigned long tx_sz_512_1023;	/* The number of good and bad packets transmitted that are between 512 and 1023-byte long. */
+	unsigned long tx_sz_1024_1518;	/* The number of good and bad packets transmitted that are between 1024 and 1518-byte long. */
+	unsigned long tx_sz_1519_max;	/* The number of good and bad packets transmitted that are between 1519-byte and MTU. */
+	unsigned long tx_1_col;		/* The number of packets subsequently transmitted successfully with a single prior collision. */
+	unsigned long tx_2_col;		/* The number of packets subsequently transmitted successfully with multiple prior collisions. */
+	unsigned long tx_late_col;	/* The number of packets transmitted with late collisions. */
+	unsigned long tx_abort_col;	/* The number of transmit packets aborted due to excessive collisions. */
+	unsigned long tx_underrun;	/* The number of transmit packets aborted due to transmit FIFO underrun, or TRD FIFO underrun */
+	unsigned long tx_rd_eop;	/* The number of times that read beyond the EOP into the next frame area when TRD was not written timely */
+	unsigned long tx_len_err;	/* The number of transmit packets with length field does NOT match the actual frame size. */
+	unsigned long tx_trunc;		/* The number of transmit packets truncated due to size exceeding MTU. */
+	unsigned long tx_bcast_byte;	/* The byte count of broadcast packet transmitted, excluding FCS. */
+	unsigned long tx_mcast_byte;	/* The byte count of multicast packet transmitted, excluding FCS. */
+};
+
+struct atl1c_hw {
+	u8 __iomem      *hw_addr;            /* inner register address */
+	struct atl1c_adapter *adapter;
+	enum atl1c_nic_type  nic_type;
+	enum atl1c_dma_order dma_order;
+	enum atl1c_dma_rcb   rcb_value;
+	enum atl1c_dma_req_block dmar_block;
+
+	u16 device_id;
+	u16 vendor_id;
+	u16 subsystem_id;
+	u16 subsystem_vendor_id;
+	u8 revision_id;
+	u16 phy_id1;
+	u16 phy_id2;
+
+	u32 intr_mask;
+
+	u8 preamble_len;
+	u16 max_frame_size;
+	u16 min_frame_size;
+
+	enum atl1c_mac_speed mac_speed;
+	bool mac_duplex;
+	bool hibernate;
+	u16 media_type;
+#define MEDIA_TYPE_AUTO_SENSOR  0
+#define MEDIA_TYPE_100M_FULL    1
+#define MEDIA_TYPE_100M_HALF    2
+#define MEDIA_TYPE_10M_FULL     3
+#define MEDIA_TYPE_10M_HALF     4
+
+	u16 autoneg_advertised;
+	u16 mii_autoneg_adv_reg;
+	u16 mii_1000t_ctrl_reg;
+
+	u16 tx_imt;	/* TX Interrupt Moderator timer ( 2us resolution) */
+	u16 rx_imt;	/* RX Interrupt Moderator timer ( 2us resolution) */
+	u16 ict;        /* Interrupt Clear timer (2us resolution) */
+	u16 ctrl_flags;
+#define ATL1C_INTR_CLEAR_ON_READ	0x0001
+#define ATL1C_INTR_MODRT_ENABLE	 	0x0002
+#define ATL1C_CMB_ENABLE		0x0004
+#define ATL1C_SMB_ENABLE		0x0010
+#define ATL1C_TXQ_MODE_ENHANCE		0x0020
+#define ATL1C_RX_IPV6_CHKSUM		0x0040
+#define ATL1C_ASPM_L0S_SUPPORT		0x0080
+#define ATL1C_ASPM_L1_SUPPORT		0x0100
+#define ATL1C_ASPM_CTRL_MON		0x0200
+#define ATL1C_HIB_DISABLE		0x0400
+#define ATL1C_APS_MODE_ENABLE           0x0800
+#define ATL1C_LINK_EXT_SYNC             0x1000
+#define ATL1C_CLK_GATING_EN             0x2000
+#define ATL1C_FPGA_VERSION              0x8000
+	u16 link_cap_flags;
+#define ATL1C_LINK_CAP_1000M		0x0001
+	u32 smb_timer;
+
+	u16 rrd_thresh; /* Threshold of number of RRD produced to trigger
+			  interrupt request */
+	u16 tpd_thresh;
+	u8 tpd_burst;   /* Number of TPD to prefetch in cache-aligned burst. */
+	u8 rfd_burst;
+	u32 base_cpu;
+	u32 indirect_tab;
+	u8 mac_addr[ETH_ALEN];
+	u8 perm_mac_addr[ETH_ALEN];
+
+	bool phy_configured;
+	bool re_autoneg;
+	bool emi_ca;
+	bool msi_lnkpatch;	/* link patch for specific platforms */
+};
+
+/*
+ * atl1c_ring_header represents a single, contiguous block of DMA space
+ * mapped for the three descriptor rings (tpd, rfd, rrd) described below
+ */
+struct atl1c_ring_header {
+	void *desc;		/* virtual address */
+	dma_addr_t dma;		/* physical address*/
+	unsigned int size;	/* length in bytes */
+};
+
+/*
+ * atl1c_buffer is wrapper around a pointer to a socket buffer
+ * so a DMA handle can be stored along with the skb
+ */
+struct atl1c_buffer {
+	struct sk_buff *skb;	/* socket buffer */
+	u16 length;		/* rx buffer length */
+	u16 flags;		/* information of buffer */
+#define ATL1C_BUFFER_FREE		0x0001
+#define ATL1C_BUFFER_BUSY		0x0002
+#define ATL1C_BUFFER_STATE_MASK		0x0003
+
+#define ATL1C_PCIMAP_SINGLE		0x0004
+#define ATL1C_PCIMAP_PAGE		0x0008
+#define ATL1C_PCIMAP_TYPE_MASK		0x000C
+
+#define ATL1C_PCIMAP_TODEVICE		0x0010
+#define ATL1C_PCIMAP_FROMDEVICE		0x0020
+#define ATL1C_PCIMAP_DIRECTION_MASK	0x0030
+	dma_addr_t dma;
+};
+
+#define ATL1C_SET_BUFFER_STATE(buff, state) do {	\
+	((buff)->flags) &= ~ATL1C_BUFFER_STATE_MASK;	\
+	((buff)->flags) |= (state);			\
+	} while (0)
+
+#define ATL1C_SET_PCIMAP_TYPE(buff, type, direction) do {	\
+	((buff)->flags) &= ~ATL1C_PCIMAP_TYPE_MASK;		\
+	((buff)->flags) |= (type);				\
+	((buff)->flags) &= ~ATL1C_PCIMAP_DIRECTION_MASK;	\
+	((buff)->flags) |= (direction);				\
+	} while (0)
+
+/* transimit packet descriptor (tpd) ring */
+struct atl1c_tpd_ring {
+	void *desc;		/* descriptor ring virtual address */
+	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 size;		/* descriptor ring length in bytes */
+	u16 count;		/* number of descriptors in the ring */
+	u16 next_to_use; 	/* this is protectd by adapter->tx_lock */
+	atomic_t next_to_clean;
+	struct atl1c_buffer *buffer_info;
+};
+
+/* receive free descriptor (rfd) ring */
+struct atl1c_rfd_ring {
+	void *desc;		/* descriptor ring virtual address */
+	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 size;		/* descriptor ring length in bytes */
+	u16 count;		/* number of descriptors in the ring */
+	u16 next_to_use;
+	u16 next_to_clean;
+	struct atl1c_buffer *buffer_info;
+};
+
+/* receive return descriptor (rrd) ring */
+struct atl1c_rrd_ring {
+	void *desc;		/* descriptor ring virtual address */
+	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 size;		/* descriptor ring length in bytes */
+	u16 count;		/* number of descriptors in the ring */
+	u16 next_to_use;
+	u16 next_to_clean;
+};
+
+/* board specific private data structure */
+struct atl1c_adapter {
+	struct net_device   *netdev;
+	struct pci_dev      *pdev;
+	struct napi_struct  napi;
+	struct page         *rx_page;
+	unsigned int	    rx_page_offset;
+	unsigned int	    rx_frag_size;
+	struct atl1c_hw        hw;
+	struct atl1c_hw_stats  hw_stats;
+	struct mii_if_info  mii;    /* MII interface info */
+	u16 rx_buffer_len;
+
+	unsigned long flags;
+#define __AT_TESTING        0x0001
+#define __AT_RESETTING      0x0002
+#define __AT_DOWN           0x0003
+	unsigned long work_event;
+#define	ATL1C_WORK_EVENT_RESET		0
+#define	ATL1C_WORK_EVENT_LINK_CHANGE	1
+	u32 msg_enable;
+
+	bool have_msi;
+	u32 wol;
+	u16 link_speed;
+	u16 link_duplex;
+
+	spinlock_t mdio_lock;
+	spinlock_t tx_lock;
+	atomic_t irq_sem;
+
+	struct work_struct common_task;
+	struct timer_list watchdog_timer;
+	struct timer_list phy_config_timer;
+
+	/* All Descriptor memory */
+	struct atl1c_ring_header ring_header;
+	struct atl1c_tpd_ring tpd_ring[AT_MAX_TRANSMIT_QUEUE];
+	struct atl1c_rfd_ring rfd_ring;
+	struct atl1c_rrd_ring rrd_ring;
+	u32 bd_number;     /* board number;*/
+};
+
+#define AT_WRITE_REG(a, reg, value) ( \
+		writel((value), ((a)->hw_addr + reg)))
+
+#define AT_WRITE_FLUSH(a) (\
+		readl((a)->hw_addr))
+
+#define AT_READ_REG(a, reg, pdata) do {					\
+		if (unlikely((a)->hibernate)) {				\
+			readl((a)->hw_addr + reg);			\
+			*(u32 *)pdata = readl((a)->hw_addr + reg);	\
+		} else {						\
+			*(u32 *)pdata = readl((a)->hw_addr + reg);	\
+		}							\
+	} while (0)
+
+#define AT_WRITE_REGB(a, reg, value) (\
+		writeb((value), ((a)->hw_addr + reg)))
+
+#define AT_READ_REGB(a, reg) (\
+		readb((a)->hw_addr + reg))
+
+#define AT_WRITE_REGW(a, reg, value) (\
+		writew((value), ((a)->hw_addr + reg)))
+
+#define AT_READ_REGW(a, reg, pdata) do {				\
+		if (unlikely((a)->hibernate)) {				\
+			readw((a)->hw_addr + reg);			\
+			*(u16 *)pdata = readw((a)->hw_addr + reg);	\
+		} else {						\
+			*(u16 *)pdata = readw((a)->hw_addr + reg);	\
+		}							\
+	} while (0)
+
+#define AT_WRITE_REG_ARRAY(a, reg, offset, value) ( \
+		writel((value), (((a)->hw_addr + reg) + ((offset) << 2))))
+
+#define AT_READ_REG_ARRAY(a, reg, offset) ( \
+		readl(((a)->hw_addr + reg) + ((offset) << 2)))
+
+extern char atl1c_driver_name[];
+extern char atl1c_driver_version[];
+
+extern void atl1c_reinit_locked(struct atl1c_adapter *adapter);
+extern s32 atl1c_reset_hw(struct atl1c_hw *hw);
+extern void atl1c_set_ethtool_ops(struct net_device *netdev);
+#endif /* _ATL1C_H_ */

addons/atl1c/src/3.10.108/atl1c_ethtool.c

@@ -0,0 +1,309 @@
+/*
+ * Copyright(c) 2009 - 2009 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/slab.h>
+
+#include "atl1c.h"
+
+static int atl1c_get_settings(struct net_device *netdev,
+			      struct ethtool_cmd *ecmd)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+
+	ecmd->supported = (SUPPORTED_10baseT_Half  |
+			   SUPPORTED_10baseT_Full  |
+			   SUPPORTED_100baseT_Half |
+			   SUPPORTED_100baseT_Full |
+			   SUPPORTED_Autoneg       |
+			   SUPPORTED_TP);
+	if (hw->link_cap_flags & ATL1C_LINK_CAP_1000M)
+		ecmd->supported |= SUPPORTED_1000baseT_Full;
+
+	ecmd->advertising = ADVERTISED_TP;
+
+	ecmd->advertising |= hw->autoneg_advertised;
+
+	ecmd->port = PORT_TP;
+	ecmd->phy_address = 0;
+	ecmd->transceiver = XCVR_INTERNAL;
+
+	if (adapter->link_speed != SPEED_0) {
+		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+		if (adapter->link_duplex == FULL_DUPLEX)
+			ecmd->duplex = DUPLEX_FULL;
+		else
+			ecmd->duplex = DUPLEX_HALF;
+	} else {
+		ethtool_cmd_speed_set(ecmd, -1);
+		ecmd->duplex = -1;
+	}
+
+	ecmd->autoneg = AUTONEG_ENABLE;
+	return 0;
+}
+
+static int atl1c_set_settings(struct net_device *netdev,
+			      struct ethtool_cmd *ecmd)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+	u16  autoneg_advertised;
+
+	while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
+		msleep(1);
+
+	if (ecmd->autoneg == AUTONEG_ENABLE) {
+		autoneg_advertised = ADVERTISED_Autoneg;
+	} else {
+		u32 speed = ethtool_cmd_speed(ecmd);
+		if (speed == SPEED_1000) {
+			if (ecmd->duplex != DUPLEX_FULL) {
+				if (netif_msg_link(adapter))
+					dev_warn(&adapter->pdev->dev,
+						"1000M half is invalid\n");
+				clear_bit(__AT_RESETTING, &adapter->flags);
+				return -EINVAL;
+			}
+			autoneg_advertised = ADVERTISED_1000baseT_Full;
+		} else if (speed == SPEED_100) {
+			if (ecmd->duplex == DUPLEX_FULL)
+				autoneg_advertised = ADVERTISED_100baseT_Full;
+			else
+				autoneg_advertised = ADVERTISED_100baseT_Half;
+		} else {
+			if (ecmd->duplex == DUPLEX_FULL)
+				autoneg_advertised = ADVERTISED_10baseT_Full;
+			else
+				autoneg_advertised = ADVERTISED_10baseT_Half;
+		}
+	}
+
+	if (hw->autoneg_advertised != autoneg_advertised) {
+		hw->autoneg_advertised = autoneg_advertised;
+		if (atl1c_restart_autoneg(hw) != 0) {
+			if (netif_msg_link(adapter))
+				dev_warn(&adapter->pdev->dev,
+					"ethtool speed/duplex setting failed\n");
+			clear_bit(__AT_RESETTING, &adapter->flags);
+			return -EINVAL;
+		}
+	}
+	clear_bit(__AT_RESETTING, &adapter->flags);
+	return 0;
+}
+
+static u32 atl1c_get_msglevel(struct net_device *netdev)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	return adapter->msg_enable;
+}
+
+static void atl1c_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	adapter->msg_enable = data;
+}
+
+static int atl1c_get_regs_len(struct net_device *netdev)
+{
+	return AT_REGS_LEN;
+}
+
+static void atl1c_get_regs(struct net_device *netdev,
+			   struct ethtool_regs *regs, void *p)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+	u16 phy_data;
+
+	memset(p, 0, AT_REGS_LEN);
+
+	regs->version = 1;
+	AT_READ_REG(hw, REG_PM_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_MAC_HALF_DUPLX_CTRL,  p++);
+	AT_READ_REG(hw, REG_TWSI_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_PCIE_DEV_MISC_CTRL,   p++);
+	AT_READ_REG(hw, REG_MASTER_CTRL, 	  p++);
+	AT_READ_REG(hw, REG_MANUAL_TIMER_INIT,    p++);
+	AT_READ_REG(hw, REG_IRQ_MODRT_TIMER_INIT, p++);
+	AT_READ_REG(hw, REG_GPHY_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_LINK_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_IDLE_STATUS, 	  p++);
+	AT_READ_REG(hw, REG_MDIO_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_SERDES,		  p++);
+	AT_READ_REG(hw, REG_MAC_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_MAC_IPG_IFG, 	  p++);
+	AT_READ_REG(hw, REG_MAC_STA_ADDR, 	  p++);
+	AT_READ_REG(hw, REG_MAC_STA_ADDR+4, 	  p++);
+	AT_READ_REG(hw, REG_RX_HASH_TABLE, 	  p++);
+	AT_READ_REG(hw, REG_RX_HASH_TABLE+4, 	  p++);
+	AT_READ_REG(hw, REG_RXQ_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_TXQ_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_MTU, 		  p++);
+	AT_READ_REG(hw, REG_WOL_CTRL, 		  p++);
+
+	atl1c_read_phy_reg(hw, MII_BMCR, &phy_data);
+	regs_buff[AT_REGS_LEN/sizeof(u32) - 2] = (u32) phy_data;
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	regs_buff[AT_REGS_LEN/sizeof(u32) - 1] = (u32) phy_data;
+}
+
+static int atl1c_get_eeprom_len(struct net_device *netdev)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	if (atl1c_check_eeprom_exist(&adapter->hw))
+		return AT_EEPROM_LEN;
+	else
+		return 0;
+}
+
+static int atl1c_get_eeprom(struct net_device *netdev,
+		struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+	u32 *eeprom_buff;
+	int first_dword, last_dword;
+	int ret_val = 0;
+	int i;
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	if (!atl1c_check_eeprom_exist(hw)) /* not exist */
+		return -EINVAL;
+
+	eeprom->magic = adapter->pdev->vendor |
+			(adapter->pdev->device << 16);
+
+	first_dword = eeprom->offset >> 2;
+	last_dword = (eeprom->offset + eeprom->len - 1) >> 2;
+
+	eeprom_buff = kmalloc(sizeof(u32) *
+			(last_dword - first_dword + 1), GFP_KERNEL);
+	if (eeprom_buff == NULL)
+		return -ENOMEM;
+
+	for (i = first_dword; i < last_dword; i++) {
+		if (!atl1c_read_eeprom(hw, i * 4, &(eeprom_buff[i-first_dword]))) {
+			kfree(eeprom_buff);
+			return -EIO;
+		}
+	}
+
+	memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 3),
+			eeprom->len);
+	kfree(eeprom_buff);
+
+	return ret_val;
+	return 0;
+}
+
+static void atl1c_get_drvinfo(struct net_device *netdev,
+		struct ethtool_drvinfo *drvinfo)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver,  atl1c_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, atl1c_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
+	drvinfo->n_stats = 0;
+	drvinfo->testinfo_len = 0;
+	drvinfo->regdump_len = atl1c_get_regs_len(netdev);
+	drvinfo->eedump_len = atl1c_get_eeprom_len(netdev);
+}
+
+static void atl1c_get_wol(struct net_device *netdev,
+			  struct ethtool_wolinfo *wol)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	wol->supported = WAKE_MAGIC | WAKE_PHY;
+	wol->wolopts = 0;
+
+	if (adapter->wol & AT_WUFC_EX)
+		wol->wolopts |= WAKE_UCAST;
+	if (adapter->wol & AT_WUFC_MC)
+		wol->wolopts |= WAKE_MCAST;
+	if (adapter->wol & AT_WUFC_BC)
+		wol->wolopts |= WAKE_BCAST;
+	if (adapter->wol & AT_WUFC_MAG)
+		wol->wolopts |= WAKE_MAGIC;
+	if (adapter->wol & AT_WUFC_LNKC)
+		wol->wolopts |= WAKE_PHY;
+}
+
+static int atl1c_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE |
+			    WAKE_UCAST | WAKE_BCAST | WAKE_MCAST))
+		return -EOPNOTSUPP;
+	/* these settings will always override what we currently have */
+	adapter->wol = 0;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		adapter->wol |= AT_WUFC_MAG;
+	if (wol->wolopts & WAKE_PHY)
+		adapter->wol |= AT_WUFC_LNKC;
+
+	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
+
+	return 0;
+}
+
+static int atl1c_nway_reset(struct net_device *netdev)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	if (netif_running(netdev))
+		atl1c_reinit_locked(adapter);
+	return 0;
+}
+
+static const struct ethtool_ops atl1c_ethtool_ops = {
+	.get_settings           = atl1c_get_settings,
+	.set_settings           = atl1c_set_settings,
+	.get_drvinfo            = atl1c_get_drvinfo,
+	.get_regs_len           = atl1c_get_regs_len,
+	.get_regs               = atl1c_get_regs,
+	.get_wol                = atl1c_get_wol,
+	.set_wol                = atl1c_set_wol,
+	.get_msglevel           = atl1c_get_msglevel,
+	.set_msglevel           = atl1c_set_msglevel,
+	.nway_reset             = atl1c_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_eeprom_len         = atl1c_get_eeprom_len,
+	.get_eeprom             = atl1c_get_eeprom,
+};
+
+void atl1c_set_ethtool_ops(struct net_device *netdev)
+{
+	SET_ETHTOOL_OPS(netdev, &atl1c_ethtool_ops);
+}

addons/atl1c/src/3.10.108/atl1c_hw.c

@@ -0,0 +1,865 @@
+/*
+ * Copyright(c) 2007 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/mii.h>
+#include <linux/crc32.h>
+
+#include "atl1c.h"
+
+/*
+ * check_eeprom_exist
+ * return 1 if eeprom exist
+ */
+int atl1c_check_eeprom_exist(struct atl1c_hw *hw)
+{
+	u32 data;
+
+	AT_READ_REG(hw, REG_TWSI_DEBUG, &data);
+	if (data & TWSI_DEBUG_DEV_EXIST)
+		return 1;
+
+	AT_READ_REG(hw, REG_MASTER_CTRL, &data);
+	if (data & MASTER_CTRL_OTP_SEL)
+		return 1;
+	return 0;
+}
+
+void atl1c_hw_set_mac_addr(struct atl1c_hw *hw, u8 *mac_addr)
+{
+	u32 value;
+	/*
+	 * 00-0B-6A-F6-00-DC
+	 * 0:  6AF600DC 1: 000B
+	 * low dword
+	 */
+	value = mac_addr[2] << 24 |
+		mac_addr[3] << 16 |
+		mac_addr[4] << 8  |
+		mac_addr[5];
+	AT_WRITE_REG_ARRAY(hw, REG_MAC_STA_ADDR, 0, value);
+	/* hight dword */
+	value = mac_addr[0] << 8 |
+		mac_addr[1];
+	AT_WRITE_REG_ARRAY(hw, REG_MAC_STA_ADDR, 1, value);
+}
+
+/* read mac address from hardware register */
+static bool atl1c_read_current_addr(struct atl1c_hw *hw, u8 *eth_addr)
+{
+	u32 addr[2];
+
+	AT_READ_REG(hw, REG_MAC_STA_ADDR, &addr[0]);
+	AT_READ_REG(hw, REG_MAC_STA_ADDR + 4, &addr[1]);
+
+	*(u32 *) &eth_addr[2] = htonl(addr[0]);
+	*(u16 *) &eth_addr[0] = htons((u16)addr[1]);
+
+	return is_valid_ether_addr(eth_addr);
+}
+
+/*
+ * atl1c_get_permanent_address
+ * return 0 if get valid mac address,
+ */
+static int atl1c_get_permanent_address(struct atl1c_hw *hw)
+{
+	u32 i;
+	u32 otp_ctrl_data;
+	u32 twsi_ctrl_data;
+	u16 phy_data;
+	bool raise_vol = false;
+
+	/* MAC-address from BIOS is the 1st priority */
+	if (atl1c_read_current_addr(hw, hw->perm_mac_addr))
+		return 0;
+
+	/* init */
+	AT_READ_REG(hw, REG_OTP_CTRL, &otp_ctrl_data);
+	if (atl1c_check_eeprom_exist(hw)) {
+		if (hw->nic_type == athr_l1c || hw->nic_type == athr_l2c) {
+			/* Enable OTP CLK */
+			if (!(otp_ctrl_data & OTP_CTRL_CLK_EN)) {
+				otp_ctrl_data |= OTP_CTRL_CLK_EN;
+				AT_WRITE_REG(hw, REG_OTP_CTRL, otp_ctrl_data);
+				AT_WRITE_FLUSH(hw);
+				msleep(1);
+			}
+		}
+		/* raise voltage temporally for l2cb */
+		if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2) {
+			atl1c_read_phy_dbg(hw, MIIDBG_ANACTRL, &phy_data);
+			phy_data &= ~ANACTRL_HB_EN;
+			atl1c_write_phy_dbg(hw, MIIDBG_ANACTRL, phy_data);
+			atl1c_read_phy_dbg(hw, MIIDBG_VOLT_CTRL, &phy_data);
+			phy_data |= VOLT_CTRL_SWLOWEST;
+			atl1c_write_phy_dbg(hw, MIIDBG_VOLT_CTRL, phy_data);
+			udelay(20);
+			raise_vol = true;
+		}
+
+		AT_READ_REG(hw, REG_TWSI_CTRL, &twsi_ctrl_data);
+		twsi_ctrl_data |= TWSI_CTRL_SW_LDSTART;
+		AT_WRITE_REG(hw, REG_TWSI_CTRL, twsi_ctrl_data);
+		for (i = 0; i < AT_TWSI_EEPROM_TIMEOUT; i++) {
+			msleep(10);
+			AT_READ_REG(hw, REG_TWSI_CTRL, &twsi_ctrl_data);
+			if ((twsi_ctrl_data & TWSI_CTRL_SW_LDSTART) == 0)
+				break;
+		}
+		if (i >= AT_TWSI_EEPROM_TIMEOUT)
+			return -1;
+	}
+	/* Disable OTP_CLK */
+	if ((hw->nic_type == athr_l1c || hw->nic_type == athr_l2c)) {
+		otp_ctrl_data &= ~OTP_CTRL_CLK_EN;
+		AT_WRITE_REG(hw, REG_OTP_CTRL, otp_ctrl_data);
+		msleep(1);
+	}
+	if (raise_vol) {
+		atl1c_read_phy_dbg(hw, MIIDBG_ANACTRL, &phy_data);
+		phy_data |= ANACTRL_HB_EN;
+		atl1c_write_phy_dbg(hw, MIIDBG_ANACTRL, phy_data);
+		atl1c_read_phy_dbg(hw, MIIDBG_VOLT_CTRL, &phy_data);
+		phy_data &= ~VOLT_CTRL_SWLOWEST;
+		atl1c_write_phy_dbg(hw, MIIDBG_VOLT_CTRL, phy_data);
+		udelay(20);
+	}
+
+	if (atl1c_read_current_addr(hw, hw->perm_mac_addr))
+		return 0;
+
+	return -1;
+}
+
+bool atl1c_read_eeprom(struct atl1c_hw *hw, u32 offset, u32 *p_value)
+{
+	int i;
+	int ret = false;
+	u32 otp_ctrl_data;
+	u32 control;
+	u32 data;
+
+	if (offset & 3)
+		return ret; /* address do not align */
+
+	AT_READ_REG(hw, REG_OTP_CTRL, &otp_ctrl_data);
+	if (!(otp_ctrl_data & OTP_CTRL_CLK_EN))
+		AT_WRITE_REG(hw, REG_OTP_CTRL,
+				(otp_ctrl_data | OTP_CTRL_CLK_EN));
+
+	AT_WRITE_REG(hw, REG_EEPROM_DATA_LO, 0);
+	control = (offset & EEPROM_CTRL_ADDR_MASK) << EEPROM_CTRL_ADDR_SHIFT;
+	AT_WRITE_REG(hw, REG_EEPROM_CTRL, control);
+
+	for (i = 0; i < 10; i++) {
+		udelay(100);
+		AT_READ_REG(hw, REG_EEPROM_CTRL, &control);
+		if (control & EEPROM_CTRL_RW)
+			break;
+	}
+	if (control & EEPROM_CTRL_RW) {
+		AT_READ_REG(hw, REG_EEPROM_CTRL, &data);
+		AT_READ_REG(hw, REG_EEPROM_DATA_LO, p_value);
+		data = data & 0xFFFF;
+		*p_value = swab32((data << 16) | (*p_value >> 16));
+		ret = true;
+	}
+	if (!(otp_ctrl_data & OTP_CTRL_CLK_EN))
+		AT_WRITE_REG(hw, REG_OTP_CTRL, otp_ctrl_data);
+
+	return ret;
+}
+/*
+ * Reads the adapter's MAC address from the EEPROM
+ *
+ * hw - Struct containing variables accessed by shared code
+ */
+int atl1c_read_mac_addr(struct atl1c_hw *hw)
+{
+	int err = 0;
+
+	err = atl1c_get_permanent_address(hw);
+	if (err)
+		eth_random_addr(hw->perm_mac_addr);
+
+	memcpy(hw->mac_addr, hw->perm_mac_addr, sizeof(hw->perm_mac_addr));
+	return err;
+}
+
+/*
+ * atl1c_hash_mc_addr
+ *  purpose
+ *      set hash value for a multicast address
+ *      hash calcu processing :
+ *          1. calcu 32bit CRC for multicast address
+ *          2. reverse crc with MSB to LSB
+ */
+u32 atl1c_hash_mc_addr(struct atl1c_hw *hw, u8 *mc_addr)
+{
+	u32 crc32;
+	u32 value = 0;
+	int i;
+
+	crc32 = ether_crc_le(6, mc_addr);
+	for (i = 0; i < 32; i++)
+		value |= (((crc32 >> i) & 1) << (31 - i));
+
+	return value;
+}
+
+/*
+ * Sets the bit in the multicast table corresponding to the hash value.
+ * hw - Struct containing variables accessed by shared code
+ * hash_value - Multicast address hash value
+ */
+void atl1c_hash_set(struct atl1c_hw *hw, u32 hash_value)
+{
+	u32 hash_bit, hash_reg;
+	u32 mta;
+
+	/*
+	 * The HASH Table  is a register array of 2 32-bit registers.
+	 * It is treated like an array of 64 bits.  We want to set
+	 * bit BitArray[hash_value]. So we figure out what register
+	 * the bit is in, read it, OR in the new bit, then write
+	 * back the new value.  The register is determined by the
+	 * upper bit of the hash value and the bit within that
+	 * register are determined by the lower 5 bits of the value.
+	 */
+	hash_reg = (hash_value >> 31) & 0x1;
+	hash_bit = (hash_value >> 26) & 0x1F;
+
+	mta = AT_READ_REG_ARRAY(hw, REG_RX_HASH_TABLE, hash_reg);
+
+	mta |= (1 << hash_bit);
+
+	AT_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, hash_reg, mta);
+}
+
+/*
+ * wait mdio module be idle
+ * return true: idle
+ *        false: still busy
+ */
+bool atl1c_wait_mdio_idle(struct atl1c_hw *hw)
+{
+	u32 val;
+	int i;
+
+	for (i = 0; i < MDIO_MAX_AC_TO; i++) {
+		AT_READ_REG(hw, REG_MDIO_CTRL, &val);
+		if (!(val & (MDIO_CTRL_BUSY | MDIO_CTRL_START)))
+			break;
+		udelay(10);
+	}
+
+	return i != MDIO_MAX_AC_TO;
+}
+
+void atl1c_stop_phy_polling(struct atl1c_hw *hw)
+{
+	if (!(hw->ctrl_flags & ATL1C_FPGA_VERSION))
+		return;
+
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, 0);
+	atl1c_wait_mdio_idle(hw);
+}
+
+void atl1c_start_phy_polling(struct atl1c_hw *hw, u16 clk_sel)
+{
+	u32 val;
+
+	if (!(hw->ctrl_flags & ATL1C_FPGA_VERSION))
+		return;
+
+	val = MDIO_CTRL_SPRES_PRMBL |
+		FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+		FIELDX(MDIO_CTRL_REG, 1) |
+		MDIO_CTRL_START |
+		MDIO_CTRL_OP_READ;
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+	atl1c_wait_mdio_idle(hw);
+	val |= MDIO_CTRL_AP_EN;
+	val &= ~MDIO_CTRL_START;
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+	udelay(30);
+}
+
+
+/*
+ * atl1c_read_phy_core
+ * core funtion to read register in PHY via MDIO control regsiter.
+ * ext: extension register (see IEEE 802.3)
+ * dev: device address (see IEEE 802.3 DEVAD, PRTAD is fixed to 0)
+ * reg: reg to read
+ */
+int atl1c_read_phy_core(struct atl1c_hw *hw, bool ext, u8 dev,
+			u16 reg, u16 *phy_data)
+{
+	u32 val;
+	u16 clk_sel = MDIO_CTRL_CLK_25_4;
+
+	atl1c_stop_phy_polling(hw);
+
+	*phy_data = 0;
+
+	/* only l2c_b2 & l1d_2 could use slow clock */
+	if ((hw->nic_type == athr_l2c_b2 || hw->nic_type == athr_l1d_2) &&
+		hw->hibernate)
+		clk_sel = MDIO_CTRL_CLK_25_128;
+	if (ext) {
+		val = FIELDX(MDIO_EXTN_DEVAD, dev) | FIELDX(MDIO_EXTN_REG, reg);
+		AT_WRITE_REG(hw, REG_MDIO_EXTN, val);
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			MDIO_CTRL_START |
+			MDIO_CTRL_MODE_EXT |
+			MDIO_CTRL_OP_READ;
+	} else {
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			FIELDX(MDIO_CTRL_REG, reg) |
+			MDIO_CTRL_START |
+			MDIO_CTRL_OP_READ;
+	}
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+
+	if (!atl1c_wait_mdio_idle(hw))
+		return -1;
+
+	AT_READ_REG(hw, REG_MDIO_CTRL, &val);
+	*phy_data = (u16)FIELD_GETX(val, MDIO_CTRL_DATA);
+
+	atl1c_start_phy_polling(hw, clk_sel);
+
+	return 0;
+}
+
+/*
+ * atl1c_write_phy_core
+ * core funtion to write to register in PHY via MDIO control regsiter.
+ * ext: extension register (see IEEE 802.3)
+ * dev: device address (see IEEE 802.3 DEVAD, PRTAD is fixed to 0)
+ * reg: reg to write
+ */
+int atl1c_write_phy_core(struct atl1c_hw *hw, bool ext, u8 dev,
+			u16 reg, u16 phy_data)
+{
+	u32 val;
+	u16 clk_sel = MDIO_CTRL_CLK_25_4;
+
+	atl1c_stop_phy_polling(hw);
+
+
+	/* only l2c_b2 & l1d_2 could use slow clock */
+	if ((hw->nic_type == athr_l2c_b2 || hw->nic_type == athr_l1d_2) &&
+		hw->hibernate)
+		clk_sel = MDIO_CTRL_CLK_25_128;
+
+	if (ext) {
+		val = FIELDX(MDIO_EXTN_DEVAD, dev) | FIELDX(MDIO_EXTN_REG, reg);
+		AT_WRITE_REG(hw, REG_MDIO_EXTN, val);
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			FIELDX(MDIO_CTRL_DATA, phy_data) |
+			MDIO_CTRL_START |
+			MDIO_CTRL_MODE_EXT;
+	} else {
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			FIELDX(MDIO_CTRL_DATA, phy_data) |
+			FIELDX(MDIO_CTRL_REG, reg) |
+			MDIO_CTRL_START;
+	}
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+
+	if (!atl1c_wait_mdio_idle(hw))
+		return -1;
+
+	atl1c_start_phy_polling(hw, clk_sel);
+
+	return 0;
+}
+
+/*
+ * Reads the value from a PHY register
+ * hw - Struct containing variables accessed by shared code
+ * reg_addr - address of the PHY register to read
+ */
+int atl1c_read_phy_reg(struct atl1c_hw *hw, u16 reg_addr, u16 *phy_data)
+{
+	return atl1c_read_phy_core(hw, false, 0, reg_addr, phy_data);
+}
+
+/*
+ * Writes a value to a PHY register
+ * hw - Struct containing variables accessed by shared code
+ * reg_addr - address of the PHY register to write
+ * data - data to write to the PHY
+ */
+int atl1c_write_phy_reg(struct atl1c_hw *hw, u32 reg_addr, u16 phy_data)
+{
+	return atl1c_write_phy_core(hw, false, 0, reg_addr, phy_data);
+}
+
+/* read from PHY extension register */
+int atl1c_read_phy_ext(struct atl1c_hw *hw, u8 dev_addr,
+			u16 reg_addr, u16 *phy_data)
+{
+	return atl1c_read_phy_core(hw, true, dev_addr, reg_addr, phy_data);
+}
+
+/* write to PHY extension register */
+int atl1c_write_phy_ext(struct atl1c_hw *hw, u8 dev_addr,
+			u16 reg_addr, u16 phy_data)
+{
+	return atl1c_write_phy_core(hw, true, dev_addr, reg_addr, phy_data);
+}
+
+int atl1c_read_phy_dbg(struct atl1c_hw *hw, u16 reg_addr, u16 *phy_data)
+{
+	int err;
+
+	err = atl1c_write_phy_reg(hw, MII_DBG_ADDR, reg_addr);
+	if (unlikely(err))
+		return err;
+	else
+		err = atl1c_read_phy_reg(hw, MII_DBG_DATA, phy_data);
+
+	return err;
+}
+
+int atl1c_write_phy_dbg(struct atl1c_hw *hw, u16 reg_addr, u16 phy_data)
+{
+	int err;
+
+	err = atl1c_write_phy_reg(hw, MII_DBG_ADDR, reg_addr);
+	if (unlikely(err))
+		return err;
+	else
+		err = atl1c_write_phy_reg(hw, MII_DBG_DATA, phy_data);
+
+	return err;
+}
+
+/*
+ * Configures PHY autoneg and flow control advertisement settings
+ *
+ * hw - Struct containing variables accessed by shared code
+ */
+static int atl1c_phy_setup_adv(struct atl1c_hw *hw)
+{
+	u16 mii_adv_data = ADVERTISE_DEFAULT_CAP & ~ADVERTISE_ALL;
+	u16 mii_giga_ctrl_data = GIGA_CR_1000T_DEFAULT_CAP &
+				~GIGA_CR_1000T_SPEED_MASK;
+
+	if (hw->autoneg_advertised & ADVERTISED_10baseT_Half)
+		mii_adv_data |= ADVERTISE_10HALF;
+	if (hw->autoneg_advertised & ADVERTISED_10baseT_Full)
+		mii_adv_data |= ADVERTISE_10FULL;
+	if (hw->autoneg_advertised & ADVERTISED_100baseT_Half)
+		mii_adv_data |= ADVERTISE_100HALF;
+	if (hw->autoneg_advertised & ADVERTISED_100baseT_Full)
+		mii_adv_data |= ADVERTISE_100FULL;
+
+	if (hw->autoneg_advertised & ADVERTISED_Autoneg)
+		mii_adv_data |= ADVERTISE_10HALF  | ADVERTISE_10FULL |
+				ADVERTISE_100HALF | ADVERTISE_100FULL;
+
+	if (hw->link_cap_flags & ATL1C_LINK_CAP_1000M) {
+		if (hw->autoneg_advertised & ADVERTISED_1000baseT_Half)
+			mii_giga_ctrl_data |= ADVERTISE_1000HALF;
+		if (hw->autoneg_advertised & ADVERTISED_1000baseT_Full)
+			mii_giga_ctrl_data |= ADVERTISE_1000FULL;
+		if (hw->autoneg_advertised & ADVERTISED_Autoneg)
+			mii_giga_ctrl_data |= ADVERTISE_1000HALF |
+					ADVERTISE_1000FULL;
+	}
+
+	if (atl1c_write_phy_reg(hw, MII_ADVERTISE, mii_adv_data) != 0 ||
+	    atl1c_write_phy_reg(hw, MII_CTRL1000, mii_giga_ctrl_data) != 0)
+		return -1;
+	return 0;
+}
+
+void atl1c_phy_disable(struct atl1c_hw *hw)
+{
+	atl1c_power_saving(hw, 0);
+}
+
+
+int atl1c_phy_reset(struct atl1c_hw *hw)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	u16 phy_data;
+	u32 phy_ctrl_data, lpi_ctrl;
+	int err;
+
+	/* reset PHY core */
+	AT_READ_REG(hw, REG_GPHY_CTRL, &phy_ctrl_data);
+	phy_ctrl_data &= ~(GPHY_CTRL_EXT_RESET | GPHY_CTRL_PHY_IDDQ |
+		GPHY_CTRL_GATE_25M_EN | GPHY_CTRL_PWDOWN_HW | GPHY_CTRL_CLS);
+	phy_ctrl_data |= GPHY_CTRL_SEL_ANA_RST;
+	if (!(hw->ctrl_flags & ATL1C_HIB_DISABLE))
+		phy_ctrl_data |= (GPHY_CTRL_HIB_EN | GPHY_CTRL_HIB_PULSE);
+	else
+		phy_ctrl_data &= ~(GPHY_CTRL_HIB_EN | GPHY_CTRL_HIB_PULSE);
+	AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl_data);
+	AT_WRITE_FLUSH(hw);
+	udelay(10);
+	AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl_data | GPHY_CTRL_EXT_RESET);
+	AT_WRITE_FLUSH(hw);
+	udelay(10 * GPHY_CTRL_EXT_RST_TO);	/* delay 800us */
+
+	/* switch clock */
+	if (hw->nic_type == athr_l2c_b) {
+		atl1c_read_phy_dbg(hw, MIIDBG_CFGLPSPD, &phy_data);
+		atl1c_write_phy_dbg(hw, MIIDBG_CFGLPSPD,
+			phy_data & ~CFGLPSPD_RSTCNT_CLK125SW);
+	}
+
+	/* tx-half amplitude issue fix */
+	if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2) {
+		atl1c_read_phy_dbg(hw, MIIDBG_CABLE1TH_DET, &phy_data);
+		phy_data |= CABLE1TH_DET_EN;
+		atl1c_write_phy_dbg(hw, MIIDBG_CABLE1TH_DET, phy_data);
+	}
+
+	/* clear bit3 of dbgport 3B to lower voltage */
+	if (!(hw->ctrl_flags & ATL1C_HIB_DISABLE)) {
+		if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2) {
+			atl1c_read_phy_dbg(hw, MIIDBG_VOLT_CTRL, &phy_data);
+			phy_data &= ~VOLT_CTRL_SWLOWEST;
+			atl1c_write_phy_dbg(hw, MIIDBG_VOLT_CTRL, phy_data);
+		}
+		/* power saving config */
+		phy_data =
+			hw->nic_type == athr_l1d || hw->nic_type == athr_l1d_2 ?
+			L1D_LEGCYPS_DEF : L1C_LEGCYPS_DEF;
+		atl1c_write_phy_dbg(hw, MIIDBG_LEGCYPS, phy_data);
+		/* hib */
+		atl1c_write_phy_dbg(hw, MIIDBG_SYSMODCTRL,
+			SYSMODCTRL_IECHOADJ_DEF);
+	} else {
+		/* disable pws */
+		atl1c_read_phy_dbg(hw, MIIDBG_LEGCYPS, &phy_data);
+		atl1c_write_phy_dbg(hw, MIIDBG_LEGCYPS,
+			phy_data & ~LEGCYPS_EN);
+		/* disable hibernate */
+		atl1c_read_phy_dbg(hw, MIIDBG_HIBNEG, &phy_data);
+		atl1c_write_phy_dbg(hw, MIIDBG_HIBNEG,
+			phy_data & HIBNEG_PSHIB_EN);
+	}
+	/* disable AZ(EEE) by default */
+	if (hw->nic_type == athr_l1d || hw->nic_type == athr_l1d_2 ||
+	    hw->nic_type == athr_l2c_b2) {
+		AT_READ_REG(hw, REG_LPI_CTRL, &lpi_ctrl);
+		AT_WRITE_REG(hw, REG_LPI_CTRL, lpi_ctrl & ~LPI_CTRL_EN);
+		atl1c_write_phy_ext(hw, MIIEXT_ANEG, MIIEXT_LOCAL_EEEADV, 0);
+		atl1c_write_phy_ext(hw, MIIEXT_PCS, MIIEXT_CLDCTRL3,
+			L2CB_CLDCTRL3);
+	}
+
+	/* other debug port to set */
+	atl1c_write_phy_dbg(hw, MIIDBG_ANACTRL, ANACTRL_DEF);
+	atl1c_write_phy_dbg(hw, MIIDBG_SRDSYSMOD, SRDSYSMOD_DEF);
+	atl1c_write_phy_dbg(hw, MIIDBG_TST10BTCFG, TST10BTCFG_DEF);
+	/* UNH-IOL test issue, set bit7 */
+	atl1c_write_phy_dbg(hw, MIIDBG_TST100BTCFG,
+		TST100BTCFG_DEF | TST100BTCFG_LITCH_EN);
+
+	/* set phy interrupt mask */
+	phy_data = IER_LINK_UP | IER_LINK_DOWN;
+	err = atl1c_write_phy_reg(hw, MII_IER, phy_data);
+	if (err) {
+		if (netif_msg_hw(adapter))
+			dev_err(&pdev->dev,
+				"Error enable PHY linkChange Interrupt\n");
+		return err;
+	}
+	return 0;
+}
+
+int atl1c_phy_init(struct atl1c_hw *hw)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	int ret_val;
+	u16 mii_bmcr_data = BMCR_RESET;
+
+	if ((atl1c_read_phy_reg(hw, MII_PHYSID1, &hw->phy_id1) != 0) ||
+		(atl1c_read_phy_reg(hw, MII_PHYSID2, &hw->phy_id2) != 0)) {
+		dev_err(&pdev->dev, "Error get phy ID\n");
+		return -1;
+	}
+	switch (hw->media_type) {
+	case MEDIA_TYPE_AUTO_SENSOR:
+		ret_val = atl1c_phy_setup_adv(hw);
+		if (ret_val) {
+			if (netif_msg_link(adapter))
+				dev_err(&pdev->dev,
+					"Error Setting up Auto-Negotiation\n");
+			return ret_val;
+		}
+		mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART;
+		break;
+	case MEDIA_TYPE_100M_FULL:
+		mii_bmcr_data |= BMCR_SPEED100 | BMCR_FULLDPLX;
+		break;
+	case MEDIA_TYPE_100M_HALF:
+		mii_bmcr_data |= BMCR_SPEED100;
+		break;
+	case MEDIA_TYPE_10M_FULL:
+		mii_bmcr_data |= BMCR_FULLDPLX;
+		break;
+	case MEDIA_TYPE_10M_HALF:
+		break;
+	default:
+		if (netif_msg_link(adapter))
+			dev_err(&pdev->dev, "Wrong Media type %d\n",
+				hw->media_type);
+		return -1;
+		break;
+	}
+
+	ret_val = atl1c_write_phy_reg(hw, MII_BMCR, mii_bmcr_data);
+	if (ret_val)
+		return ret_val;
+	hw->phy_configured = true;
+
+	return 0;
+}
+
+/*
+ * Detects the current speed and duplex settings of the hardware.
+ *
+ * hw - Struct containing variables accessed by shared code
+ * speed - Speed of the connection
+ * duplex - Duplex setting of the connection
+ */
+int atl1c_get_speed_and_duplex(struct atl1c_hw *hw, u16 *speed, u16 *duplex)
+{
+	int err;
+	u16 phy_data;
+
+	/* Read   PHY Specific Status Register (17) */
+	err = atl1c_read_phy_reg(hw, MII_GIGA_PSSR, &phy_data);
+	if (err)
+		return err;
+
+	if (!(phy_data & GIGA_PSSR_SPD_DPLX_RESOLVED))
+		return -1;
+
+	switch (phy_data & GIGA_PSSR_SPEED) {
+	case GIGA_PSSR_1000MBS:
+		*speed = SPEED_1000;
+		break;
+	case GIGA_PSSR_100MBS:
+		*speed = SPEED_100;
+		break;
+	case  GIGA_PSSR_10MBS:
+		*speed = SPEED_10;
+		break;
+	default:
+		return -1;
+		break;
+	}
+
+	if (phy_data & GIGA_PSSR_DPLX)
+		*duplex = FULL_DUPLEX;
+	else
+		*duplex = HALF_DUPLEX;
+
+	return 0;
+}
+
+/* select one link mode to get lower power consumption */
+int atl1c_phy_to_ps_link(struct atl1c_hw *hw)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	int ret = 0;
+	u16 autoneg_advertised = ADVERTISED_10baseT_Half;
+	u16 save_autoneg_advertised;
+	u16 phy_data;
+	u16 mii_lpa_data;
+	u16 speed = SPEED_0;
+	u16 duplex = FULL_DUPLEX;
+	int i;
+
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	if (phy_data & BMSR_LSTATUS) {
+		atl1c_read_phy_reg(hw, MII_LPA, &mii_lpa_data);
+		if (mii_lpa_data & LPA_10FULL)
+			autoneg_advertised = ADVERTISED_10baseT_Full;
+		else if (mii_lpa_data & LPA_10HALF)
+			autoneg_advertised = ADVERTISED_10baseT_Half;
+		else if (mii_lpa_data & LPA_100HALF)
+			autoneg_advertised = ADVERTISED_100baseT_Half;
+		else if (mii_lpa_data & LPA_100FULL)
+			autoneg_advertised = ADVERTISED_100baseT_Full;
+
+		save_autoneg_advertised = hw->autoneg_advertised;
+		hw->phy_configured = false;
+		hw->autoneg_advertised = autoneg_advertised;
+		if (atl1c_restart_autoneg(hw) != 0) {
+			dev_dbg(&pdev->dev, "phy autoneg failed\n");
+			ret = -1;
+		}
+		hw->autoneg_advertised = save_autoneg_advertised;
+
+		if (mii_lpa_data) {
+			for (i = 0; i < AT_SUSPEND_LINK_TIMEOUT; i++) {
+				mdelay(100);
+				atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+				atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+				if (phy_data & BMSR_LSTATUS) {
+					if (atl1c_get_speed_and_duplex(hw, &speed,
+									&duplex) != 0)
+						dev_dbg(&pdev->dev,
+							"get speed and duplex failed\n");
+					break;
+				}
+			}
+		}
+	} else {
+		speed = SPEED_10;
+		duplex = HALF_DUPLEX;
+	}
+	adapter->link_speed = speed;
+	adapter->link_duplex = duplex;
+
+	return ret;
+}
+
+int atl1c_restart_autoneg(struct atl1c_hw *hw)
+{
+	int err = 0;
+	u16 mii_bmcr_data = BMCR_RESET;
+
+	err = atl1c_phy_setup_adv(hw);
+	if (err)
+		return err;
+	mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART;
+
+	return atl1c_write_phy_reg(hw, MII_BMCR, mii_bmcr_data);
+}
+
+int atl1c_power_saving(struct atl1c_hw *hw, u32 wufc)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	u32 master_ctrl, mac_ctrl, phy_ctrl;
+	u32 wol_ctrl, speed;
+	u16 phy_data;
+
+	wol_ctrl = 0;
+	speed = adapter->link_speed == SPEED_1000 ?
+		MAC_CTRL_SPEED_1000 : MAC_CTRL_SPEED_10_100;
+
+	AT_READ_REG(hw, REG_MASTER_CTRL, &master_ctrl);
+	AT_READ_REG(hw, REG_MAC_CTRL, &mac_ctrl);
+	AT_READ_REG(hw, REG_GPHY_CTRL, &phy_ctrl);
+
+	master_ctrl &= ~MASTER_CTRL_CLK_SEL_DIS;
+	mac_ctrl = FIELD_SETX(mac_ctrl, MAC_CTRL_SPEED, speed);
+	mac_ctrl &= ~(MAC_CTRL_DUPLX | MAC_CTRL_RX_EN | MAC_CTRL_TX_EN);
+	if (adapter->link_duplex == FULL_DUPLEX)
+		mac_ctrl |= MAC_CTRL_DUPLX;
+	phy_ctrl &= ~(GPHY_CTRL_EXT_RESET | GPHY_CTRL_CLS);
+	phy_ctrl |= GPHY_CTRL_SEL_ANA_RST | GPHY_CTRL_HIB_PULSE |
+		GPHY_CTRL_HIB_EN;
+	if (!wufc) { /* without WoL */
+		master_ctrl |= MASTER_CTRL_CLK_SEL_DIS;
+		phy_ctrl |= GPHY_CTRL_PHY_IDDQ | GPHY_CTRL_PWDOWN_HW;
+		AT_WRITE_REG(hw, REG_MASTER_CTRL, master_ctrl);
+		AT_WRITE_REG(hw, REG_MAC_CTRL, mac_ctrl);
+		AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl);
+		AT_WRITE_REG(hw, REG_WOL_CTRL, 0);
+		hw->phy_configured = false; /* re-init PHY when resume */
+		return 0;
+	}
+	phy_ctrl |= GPHY_CTRL_EXT_RESET;
+	if (wufc & AT_WUFC_MAG) {
+		mac_ctrl |= MAC_CTRL_RX_EN | MAC_CTRL_BC_EN;
+		wol_ctrl |= WOL_MAGIC_EN | WOL_MAGIC_PME_EN;
+		if (hw->nic_type == athr_l2c_b && hw->revision_id == L2CB_V11)
+			wol_ctrl |= WOL_PATTERN_EN | WOL_PATTERN_PME_EN;
+	}
+	if (wufc & AT_WUFC_LNKC) {
+		wol_ctrl |= WOL_LINK_CHG_EN | WOL_LINK_CHG_PME_EN;
+		if (atl1c_write_phy_reg(hw, MII_IER, IER_LINK_UP) != 0) {
+			dev_dbg(&pdev->dev, "%s: write phy MII_IER failed.\n",
+				atl1c_driver_name);
+		}
+	}
+	/* clear PHY interrupt */
+	atl1c_read_phy_reg(hw, MII_ISR, &phy_data);
+
+	dev_dbg(&pdev->dev, "%s: suspend MAC=%x,MASTER=%x,PHY=0x%x,WOL=%x\n",
+		atl1c_driver_name, mac_ctrl, master_ctrl, phy_ctrl, wol_ctrl);
+	AT_WRITE_REG(hw, REG_MASTER_CTRL, master_ctrl);
+	AT_WRITE_REG(hw, REG_MAC_CTRL, mac_ctrl);
+	AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl);
+	AT_WRITE_REG(hw, REG_WOL_CTRL, wol_ctrl);
+
+	return 0;
+}
+
+
+/* configure phy after Link change Event */
+void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed)
+{
+	u16 phy_val;
+	bool adj_thresh = false;
+
+	if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2 ||
+	    hw->nic_type == athr_l1d || hw->nic_type == athr_l1d_2)
+		adj_thresh = true;
+
+	if (link_speed != SPEED_0) { /* link up */
+		/* az with brcm, half-amp */
+		if (hw->nic_type == athr_l1d_2) {
+			atl1c_read_phy_ext(hw, MIIEXT_PCS, MIIEXT_CLDCTRL6,
+				&phy_val);
+			phy_val = FIELD_GETX(phy_val, CLDCTRL6_CAB_LEN);
+			phy_val = phy_val > CLDCTRL6_CAB_LEN_SHORT ?
+				AZ_ANADECT_LONG : AZ_ANADECT_DEF;
+			atl1c_write_phy_dbg(hw, MIIDBG_AZ_ANADECT, phy_val);
+		}
+		/* threshold adjust */
+		if (adj_thresh && link_speed == SPEED_100 && hw->msi_lnkpatch) {
+			atl1c_write_phy_dbg(hw, MIIDBG_MSE16DB, L1D_MSE16DB_UP);
+			atl1c_write_phy_dbg(hw, MIIDBG_SYSMODCTRL,
+				L1D_SYSMODCTRL_IECHOADJ_DEF);
+		}
+	} else { /* link down */
+		if (adj_thresh && hw->msi_lnkpatch) {
+			atl1c_write_phy_dbg(hw, MIIDBG_SYSMODCTRL,
+				SYSMODCTRL_IECHOADJ_DEF);
+			atl1c_write_phy_dbg(hw, MIIDBG_MSE16DB,
+				L1D_MSE16DB_DOWN);
+		}
+	}
+}

addons/atl1c/src/4.4.180/Makefile

@@ -0,0 +1,2 @@
+obj-m += atl1c.o
+atl1c-objs := atl1c_main.o atl1c_hw.o atl1c_ethtool.o

addons/atl1c/src/4.4.180/atl1c.h

@@ -0,0 +1,605 @@
+/*
+ * Copyright(c) 2008 - 2009 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#ifndef _ATL1C_H_
+#define _ATL1C_H_
+
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+#include <linux/mii.h>
+#include <linux/io.h>
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <linux/tcp.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/workqueue.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
+
+#include "atl1c_hw.h"
+
+/* Wake Up Filter Control */
+#define AT_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */
+#define AT_WUFC_MAG  0x00000002 /* Magic Packet Wakeup Enable */
+#define AT_WUFC_EX   0x00000004 /* Directed Exact Wakeup Enable */
+#define AT_WUFC_MC   0x00000008 /* Multicast Wakeup Enable */
+#define AT_WUFC_BC   0x00000010 /* Broadcast Wakeup Enable */
+
+#define AT_VLAN_TO_TAG(_vlan, _tag)	   \
+	_tag =  ((((_vlan) >> 8) & 0xFF)  |\
+		 (((_vlan) & 0xFF) << 8))
+
+#define AT_TAG_TO_VLAN(_tag, _vlan) 	 \
+	_vlan = ((((_tag) >> 8) & 0xFF) |\
+		(((_tag) & 0xFF) << 8))
+
+#define SPEED_0		   0xffff
+#define HALF_DUPLEX        1
+#define FULL_DUPLEX        2
+
+#define AT_RX_BUF_SIZE		(ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN)
+#define MAX_JUMBO_FRAME_SIZE	(6*1024)
+
+#define AT_MAX_RECEIVE_QUEUE    4
+#define AT_DEF_RECEIVE_QUEUE	1
+#define AT_MAX_TRANSMIT_QUEUE	2
+
+#define AT_DMA_HI_ADDR_MASK     0xffffffff00000000ULL
+#define AT_DMA_LO_ADDR_MASK     0x00000000ffffffffULL
+
+#define AT_TX_WATCHDOG  (5 * HZ)
+#define AT_MAX_INT_WORK		5
+#define AT_TWSI_EEPROM_TIMEOUT 	100
+#define AT_HW_MAX_IDLE_DELAY 	10
+#define AT_SUSPEND_LINK_TIMEOUT 100
+
+#define AT_ASPM_L0S_TIMER	6
+#define AT_ASPM_L1_TIMER	12
+#define AT_LCKDET_TIMER		12
+
+#define ATL1C_PCIE_L0S_L1_DISABLE 	0x01
+#define ATL1C_PCIE_PHY_RESET		0x02
+
+#define ATL1C_ASPM_L0s_ENABLE		0x0001
+#define ATL1C_ASPM_L1_ENABLE		0x0002
+
+#define AT_REGS_LEN	(74 * sizeof(u32))
+#define AT_EEPROM_LEN 	512
+
+#define ATL1C_GET_DESC(R, i, type)	(&(((type *)((R)->desc))[i]))
+#define ATL1C_RFD_DESC(R, i)	ATL1C_GET_DESC(R, i, struct atl1c_rx_free_desc)
+#define ATL1C_TPD_DESC(R, i)	ATL1C_GET_DESC(R, i, struct atl1c_tpd_desc)
+#define ATL1C_RRD_DESC(R, i)	ATL1C_GET_DESC(R, i, struct atl1c_recv_ret_status)
+
+/* tpd word 1 bit 0:7 General Checksum task offload */
+#define TPD_L4HDR_OFFSET_MASK	0x00FF
+#define TPD_L4HDR_OFFSET_SHIFT	0
+
+/* tpd word 1 bit 0:7 Large Send task offload (IPv4/IPV6) */
+#define TPD_TCPHDR_OFFSET_MASK	0x00FF
+#define TPD_TCPHDR_OFFSET_SHIFT	0
+
+/* tpd word 1 bit 0:7 Custom Checksum task offload */
+#define TPD_PLOADOFFSET_MASK	0x00FF
+#define TPD_PLOADOFFSET_SHIFT	0
+
+/* tpd word 1 bit 8:17 */
+#define TPD_CCSUM_EN_MASK	0x0001
+#define TPD_CCSUM_EN_SHIFT	8
+#define TPD_IP_CSUM_MASK	0x0001
+#define TPD_IP_CSUM_SHIFT	9
+#define TPD_TCP_CSUM_MASK	0x0001
+#define TPD_TCP_CSUM_SHIFT	10
+#define TPD_UDP_CSUM_MASK	0x0001
+#define TPD_UDP_CSUM_SHIFT	11
+#define TPD_LSO_EN_MASK		0x0001	/* TCP Large Send Offload */
+#define TPD_LSO_EN_SHIFT	12
+#define TPD_LSO_VER_MASK	0x0001
+#define TPD_LSO_VER_SHIFT	13 	/* 0 : ipv4; 1 : ipv4/ipv6 */
+#define TPD_CON_VTAG_MASK	0x0001
+#define TPD_CON_VTAG_SHIFT	14
+#define TPD_INS_VTAG_MASK	0x0001
+#define TPD_INS_VTAG_SHIFT	15
+#define TPD_IPV4_PACKET_MASK	0x0001  /* valid when LSO VER  is 1 */
+#define TPD_IPV4_PACKET_SHIFT	16
+#define TPD_ETH_TYPE_MASK	0x0001
+#define TPD_ETH_TYPE_SHIFT	17	/* 0 : 802.3 frame; 1 : Ethernet */
+
+/* tpd word 18:25 Custom Checksum task offload */
+#define TPD_CCSUM_OFFSET_MASK	0x00FF
+#define TPD_CCSUM_OFFSET_SHIFT	18
+#define TPD_CCSUM_EPAD_MASK	0x0001
+#define TPD_CCSUM_EPAD_SHIFT	30
+
+/* tpd word 18:30 Large Send task offload (IPv4/IPV6) */
+#define TPD_MSS_MASK            0x1FFF
+#define TPD_MSS_SHIFT		18
+
+#define TPD_EOP_MASK		0x0001
+#define TPD_EOP_SHIFT		31
+
+struct atl1c_tpd_desc {
+	__le16	buffer_len; /* include 4-byte CRC */
+	__le16	vlan_tag;
+	__le32	word1;
+	__le64	buffer_addr;
+};
+
+struct atl1c_tpd_ext_desc {
+	u32 reservd_0;
+	__le32 word1;
+	__le32 pkt_len;
+	u32 reservd_1;
+};
+/* rrs word 0 bit 0:31 */
+#define RRS_RX_CSUM_MASK	0xFFFF
+#define RRS_RX_CSUM_SHIFT	0
+#define RRS_RX_RFD_CNT_MASK	0x000F
+#define RRS_RX_RFD_CNT_SHIFT	16
+#define RRS_RX_RFD_INDEX_MASK	0x0FFF
+#define RRS_RX_RFD_INDEX_SHIFT	20
+
+/* rrs flag bit 0:16 */
+#define RRS_HEAD_LEN_MASK	0x00FF
+#define RRS_HEAD_LEN_SHIFT	0
+#define RRS_HDS_TYPE_MASK	0x0003
+#define RRS_HDS_TYPE_SHIFT	8
+#define RRS_CPU_NUM_MASK	0x0003
+#define	RRS_CPU_NUM_SHIFT	10
+#define RRS_HASH_FLG_MASK	0x000F
+#define RRS_HASH_FLG_SHIFT	12
+
+#define RRS_HDS_TYPE_HEAD	1
+#define RRS_HDS_TYPE_DATA	2
+
+#define RRS_IS_NO_HDS_TYPE(flag) \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == 0)
+
+#define RRS_IS_HDS_HEAD(flag) \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == \
+			RRS_HDS_TYPE_HEAD)
+
+#define RRS_IS_HDS_DATA(flag) \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == \
+			RRS_HDS_TYPE_DATA)
+
+/* rrs word 3 bit 0:31 */
+#define RRS_PKT_SIZE_MASK	0x3FFF
+#define RRS_PKT_SIZE_SHIFT	0
+#define RRS_ERR_L4_CSUM_MASK	0x0001
+#define RRS_ERR_L4_CSUM_SHIFT	14
+#define RRS_ERR_IP_CSUM_MASK	0x0001
+#define RRS_ERR_IP_CSUM_SHIFT	15
+#define RRS_VLAN_INS_MASK	0x0001
+#define RRS_VLAN_INS_SHIFT	16
+#define RRS_PROT_ID_MASK	0x0007
+#define RRS_PROT_ID_SHIFT	17
+#define RRS_RX_ERR_SUM_MASK	0x0001
+#define RRS_RX_ERR_SUM_SHIFT	20
+#define RRS_RX_ERR_CRC_MASK	0x0001
+#define RRS_RX_ERR_CRC_SHIFT	21
+#define RRS_RX_ERR_FAE_MASK	0x0001
+#define RRS_RX_ERR_FAE_SHIFT	22
+#define RRS_RX_ERR_TRUNC_MASK	0x0001
+#define RRS_RX_ERR_TRUNC_SHIFT	23
+#define RRS_RX_ERR_RUNC_MASK	0x0001
+#define RRS_RX_ERR_RUNC_SHIFT	24
+#define RRS_RX_ERR_ICMP_MASK	0x0001
+#define RRS_RX_ERR_ICMP_SHIFT	25
+#define RRS_PACKET_BCAST_MASK	0x0001
+#define RRS_PACKET_BCAST_SHIFT	26
+#define RRS_PACKET_MCAST_MASK	0x0001
+#define RRS_PACKET_MCAST_SHIFT	27
+#define RRS_PACKET_TYPE_MASK	0x0001
+#define RRS_PACKET_TYPE_SHIFT	28
+#define RRS_FIFO_FULL_MASK	0x0001
+#define RRS_FIFO_FULL_SHIFT	29
+#define RRS_802_3_LEN_ERR_MASK 	0x0001
+#define RRS_802_3_LEN_ERR_SHIFT 30
+#define RRS_RXD_UPDATED_MASK	0x0001
+#define RRS_RXD_UPDATED_SHIFT	31
+
+#define RRS_ERR_L4_CSUM         0x00004000
+#define RRS_ERR_IP_CSUM         0x00008000
+#define RRS_VLAN_INS            0x00010000
+#define RRS_RX_ERR_SUM          0x00100000
+#define RRS_RX_ERR_CRC          0x00200000
+#define RRS_802_3_LEN_ERR	0x40000000
+#define RRS_RXD_UPDATED		0x80000000
+
+#define RRS_PACKET_TYPE_802_3  	1
+#define RRS_PACKET_TYPE_ETH	0
+#define RRS_PACKET_IS_ETH(word) \
+	((((word) >> RRS_PACKET_TYPE_SHIFT) & RRS_PACKET_TYPE_MASK) == \
+			RRS_PACKET_TYPE_ETH)
+#define RRS_RXD_IS_VALID(word) \
+	((((word) >> RRS_RXD_UPDATED_SHIFT) & RRS_RXD_UPDATED_MASK) == 1)
+
+#define RRS_PACKET_PROT_IS_IPV4_ONLY(word) \
+	((((word) >> RRS_PROT_ID_SHIFT) & RRS_PROT_ID_MASK) == 1)
+#define RRS_PACKET_PROT_IS_IPV6_ONLY(word) \
+	((((word) >> RRS_PROT_ID_SHIFT) & RRS_PROT_ID_MASK) == 6)
+
+struct atl1c_recv_ret_status {
+	__le32  word0;
+	__le32	rss_hash;
+	__le16	vlan_tag;
+	__le16	flag;
+	__le32	word3;
+};
+
+/* RFD descriptor */
+struct atl1c_rx_free_desc {
+	__le64	buffer_addr;
+};
+
+/* DMA Order Settings */
+enum atl1c_dma_order {
+	atl1c_dma_ord_in = 1,
+	atl1c_dma_ord_enh = 2,
+	atl1c_dma_ord_out = 4
+};
+
+enum atl1c_dma_rcb {
+	atl1c_rcb_64 = 0,
+	atl1c_rcb_128 = 1
+};
+
+enum atl1c_mac_speed {
+	atl1c_mac_speed_0 = 0,
+	atl1c_mac_speed_10_100 = 1,
+	atl1c_mac_speed_1000 = 2
+};
+
+enum atl1c_dma_req_block {
+	atl1c_dma_req_128 = 0,
+	atl1c_dma_req_256 = 1,
+	atl1c_dma_req_512 = 2,
+	atl1c_dma_req_1024 = 3,
+	atl1c_dma_req_2048 = 4,
+	atl1c_dma_req_4096 = 5
+};
+
+
+enum atl1c_nic_type {
+	athr_l1c = 0,
+	athr_l2c = 1,
+	athr_l2c_b,
+	athr_l2c_b2,
+	athr_l1d,
+	athr_l1d_2,
+};
+
+enum atl1c_trans_queue {
+	atl1c_trans_normal = 0,
+	atl1c_trans_high = 1
+};
+
+struct atl1c_hw_stats {
+	/* rx */
+	unsigned long rx_ok;		/* The number of good packet received. */
+	unsigned long rx_bcast;		/* The number of good broadcast packet received. */
+	unsigned long rx_mcast;		/* The number of good multicast packet received. */
+	unsigned long rx_pause;		/* The number of Pause packet received. */
+	unsigned long rx_ctrl;		/* The number of Control packet received other than Pause frame. */
+	unsigned long rx_fcs_err;	/* The number of packets with bad FCS. */
+	unsigned long rx_len_err;	/* The number of packets with mismatch of length field and actual size. */
+	unsigned long rx_byte_cnt;	/* The number of bytes of good packet received. FCS is NOT included. */
+	unsigned long rx_runt;		/* The number of packets received that are less than 64 byte long and with good FCS. */
+	unsigned long rx_frag;		/* The number of packets received that are less than 64 byte long and with bad FCS. */
+	unsigned long rx_sz_64;		/* The number of good and bad packets received that are 64 byte long. */
+	unsigned long rx_sz_65_127;	/* The number of good and bad packets received that are between 65 and 127-byte long. */
+	unsigned long rx_sz_128_255;	/* The number of good and bad packets received that are between 128 and 255-byte long. */
+	unsigned long rx_sz_256_511;	/* The number of good and bad packets received that are between 256 and 511-byte long. */
+	unsigned long rx_sz_512_1023;	/* The number of good and bad packets received that are between 512 and 1023-byte long. */
+	unsigned long rx_sz_1024_1518;	/* The number of good and bad packets received that are between 1024 and 1518-byte long. */
+	unsigned long rx_sz_1519_max;	/* The number of good and bad packets received that are between 1519-byte and MTU. */
+	unsigned long rx_sz_ov;		/* The number of good and bad packets received that are more than MTU size truncated by Selene. */
+	unsigned long rx_rxf_ov;	/* The number of frame dropped due to occurrence of RX FIFO overflow. */
+	unsigned long rx_rrd_ov;	/* The number of frame dropped due to occurrence of RRD overflow. */
+	unsigned long rx_align_err;	/* Alignment Error */
+	unsigned long rx_bcast_byte_cnt; /* The byte count of broadcast packet received, excluding FCS. */
+	unsigned long rx_mcast_byte_cnt; /* The byte count of multicast packet received, excluding FCS. */
+	unsigned long rx_err_addr;	/* The number of packets dropped due to address filtering. */
+
+	/* tx */
+	unsigned long tx_ok;		/* The number of good packet transmitted. */
+	unsigned long tx_bcast;		/* The number of good broadcast packet transmitted. */
+	unsigned long tx_mcast;		/* The number of good multicast packet transmitted. */
+	unsigned long tx_pause;		/* The number of Pause packet transmitted. */
+	unsigned long tx_exc_defer;	/* The number of packets transmitted with excessive deferral. */
+	unsigned long tx_ctrl;		/* The number of packets transmitted is a control frame, excluding Pause frame. */
+	unsigned long tx_defer;		/* The number of packets transmitted that is deferred. */
+	unsigned long tx_byte_cnt;	/* The number of bytes of data transmitted. FCS is NOT included. */
+	unsigned long tx_sz_64;		/* The number of good and bad packets transmitted that are 64 byte long. */
+	unsigned long tx_sz_65_127;	/* The number of good and bad packets transmitted that are between 65 and 127-byte long. */
+	unsigned long tx_sz_128_255;	/* The number of good and bad packets transmitted that are between 128 and 255-byte long. */
+	unsigned long tx_sz_256_511;	/* The number of good and bad packets transmitted that are between 256 and 511-byte long. */
+	unsigned long tx_sz_512_1023;	/* The number of good and bad packets transmitted that are between 512 and 1023-byte long. */
+	unsigned long tx_sz_1024_1518;	/* The number of good and bad packets transmitted that are between 1024 and 1518-byte long. */
+	unsigned long tx_sz_1519_max;	/* The number of good and bad packets transmitted that are between 1519-byte and MTU. */
+	unsigned long tx_1_col;		/* The number of packets subsequently transmitted successfully with a single prior collision. */
+	unsigned long tx_2_col;		/* The number of packets subsequently transmitted successfully with multiple prior collisions. */
+	unsigned long tx_late_col;	/* The number of packets transmitted with late collisions. */
+	unsigned long tx_abort_col;	/* The number of transmit packets aborted due to excessive collisions. */
+	unsigned long tx_underrun;	/* The number of transmit packets aborted due to transmit FIFO underrun, or TRD FIFO underrun */
+	unsigned long tx_rd_eop;	/* The number of times that read beyond the EOP into the next frame area when TRD was not written timely */
+	unsigned long tx_len_err;	/* The number of transmit packets with length field does NOT match the actual frame size. */
+	unsigned long tx_trunc;		/* The number of transmit packets truncated due to size exceeding MTU. */
+	unsigned long tx_bcast_byte;	/* The byte count of broadcast packet transmitted, excluding FCS. */
+	unsigned long tx_mcast_byte;	/* The byte count of multicast packet transmitted, excluding FCS. */
+};
+
+struct atl1c_hw {
+	u8 __iomem      *hw_addr;            /* inner register address */
+	struct atl1c_adapter *adapter;
+	enum atl1c_nic_type  nic_type;
+	enum atl1c_dma_order dma_order;
+	enum atl1c_dma_rcb   rcb_value;
+	enum atl1c_dma_req_block dmar_block;
+
+	u16 device_id;
+	u16 vendor_id;
+	u16 subsystem_id;
+	u16 subsystem_vendor_id;
+	u8 revision_id;
+	u16 phy_id1;
+	u16 phy_id2;
+
+	u32 intr_mask;
+
+	u8 preamble_len;
+	u16 max_frame_size;
+	u16 min_frame_size;
+
+	enum atl1c_mac_speed mac_speed;
+	bool mac_duplex;
+	bool hibernate;
+	u16 media_type;
+#define MEDIA_TYPE_AUTO_SENSOR  0
+#define MEDIA_TYPE_100M_FULL    1
+#define MEDIA_TYPE_100M_HALF    2
+#define MEDIA_TYPE_10M_FULL     3
+#define MEDIA_TYPE_10M_HALF     4
+
+	u16 autoneg_advertised;
+	u16 mii_autoneg_adv_reg;
+	u16 mii_1000t_ctrl_reg;
+
+	u16 tx_imt;	/* TX Interrupt Moderator timer ( 2us resolution) */
+	u16 rx_imt;	/* RX Interrupt Moderator timer ( 2us resolution) */
+	u16 ict;        /* Interrupt Clear timer (2us resolution) */
+	u16 ctrl_flags;
+#define ATL1C_INTR_CLEAR_ON_READ	0x0001
+#define ATL1C_INTR_MODRT_ENABLE	 	0x0002
+#define ATL1C_CMB_ENABLE		0x0004
+#define ATL1C_SMB_ENABLE		0x0010
+#define ATL1C_TXQ_MODE_ENHANCE		0x0020
+#define ATL1C_RX_IPV6_CHKSUM		0x0040
+#define ATL1C_ASPM_L0S_SUPPORT		0x0080
+#define ATL1C_ASPM_L1_SUPPORT		0x0100
+#define ATL1C_ASPM_CTRL_MON		0x0200
+#define ATL1C_HIB_DISABLE		0x0400
+#define ATL1C_APS_MODE_ENABLE           0x0800
+#define ATL1C_LINK_EXT_SYNC             0x1000
+#define ATL1C_CLK_GATING_EN             0x2000
+#define ATL1C_FPGA_VERSION              0x8000
+	u16 link_cap_flags;
+#define ATL1C_LINK_CAP_1000M		0x0001
+	u32 smb_timer;
+
+	u16 rrd_thresh; /* Threshold of number of RRD produced to trigger
+			  interrupt request */
+	u16 tpd_thresh;
+	u8 tpd_burst;   /* Number of TPD to prefetch in cache-aligned burst. */
+	u8 rfd_burst;
+	u32 base_cpu;
+	u32 indirect_tab;
+	u8 mac_addr[ETH_ALEN];
+	u8 perm_mac_addr[ETH_ALEN];
+
+	bool phy_configured;
+	bool re_autoneg;
+	bool emi_ca;
+	bool msi_lnkpatch;	/* link patch for specific platforms */
+};
+
+/*
+ * atl1c_ring_header represents a single, contiguous block of DMA space
+ * mapped for the three descriptor rings (tpd, rfd, rrd) described below
+ */
+struct atl1c_ring_header {
+	void *desc;		/* virtual address */
+	dma_addr_t dma;		/* physical address*/
+	unsigned int size;	/* length in bytes */
+};
+
+/*
+ * atl1c_buffer is wrapper around a pointer to a socket buffer
+ * so a DMA handle can be stored along with the skb
+ */
+struct atl1c_buffer {
+	struct sk_buff *skb;	/* socket buffer */
+	u16 length;		/* rx buffer length */
+	u16 flags;		/* information of buffer */
+#define ATL1C_BUFFER_FREE		0x0001
+#define ATL1C_BUFFER_BUSY		0x0002
+#define ATL1C_BUFFER_STATE_MASK		0x0003
+
+#define ATL1C_PCIMAP_SINGLE		0x0004
+#define ATL1C_PCIMAP_PAGE		0x0008
+#define ATL1C_PCIMAP_TYPE_MASK		0x000C
+
+#define ATL1C_PCIMAP_TODEVICE		0x0010
+#define ATL1C_PCIMAP_FROMDEVICE		0x0020
+#define ATL1C_PCIMAP_DIRECTION_MASK	0x0030
+	dma_addr_t dma;
+};
+
+#define ATL1C_SET_BUFFER_STATE(buff, state) do {	\
+	((buff)->flags) &= ~ATL1C_BUFFER_STATE_MASK;	\
+	((buff)->flags) |= (state);			\
+	} while (0)
+
+#define ATL1C_SET_PCIMAP_TYPE(buff, type, direction) do {	\
+	((buff)->flags) &= ~ATL1C_PCIMAP_TYPE_MASK;		\
+	((buff)->flags) |= (type);				\
+	((buff)->flags) &= ~ATL1C_PCIMAP_DIRECTION_MASK;	\
+	((buff)->flags) |= (direction);				\
+	} while (0)
+
+/* transimit packet descriptor (tpd) ring */
+struct atl1c_tpd_ring {
+	void *desc;		/* descriptor ring virtual address */
+	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 size;		/* descriptor ring length in bytes */
+	u16 count;		/* number of descriptors in the ring */
+	u16 next_to_use; 	/* this is protectd by adapter->tx_lock */
+	atomic_t next_to_clean;
+	struct atl1c_buffer *buffer_info;
+};
+
+/* receive free descriptor (rfd) ring */
+struct atl1c_rfd_ring {
+	void *desc;		/* descriptor ring virtual address */
+	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 size;		/* descriptor ring length in bytes */
+	u16 count;		/* number of descriptors in the ring */
+	u16 next_to_use;
+	u16 next_to_clean;
+	struct atl1c_buffer *buffer_info;
+};
+
+/* receive return descriptor (rrd) ring */
+struct atl1c_rrd_ring {
+	void *desc;		/* descriptor ring virtual address */
+	dma_addr_t dma;		/* descriptor ring physical address */
+	u16 size;		/* descriptor ring length in bytes */
+	u16 count;		/* number of descriptors in the ring */
+	u16 next_to_use;
+	u16 next_to_clean;
+};
+
+/* board specific private data structure */
+struct atl1c_adapter {
+	struct net_device   *netdev;
+	struct pci_dev      *pdev;
+	struct napi_struct  napi;
+	struct page         *rx_page;
+	unsigned int	    rx_page_offset;
+	unsigned int	    rx_frag_size;
+	struct atl1c_hw        hw;
+	struct atl1c_hw_stats  hw_stats;
+	struct mii_if_info  mii;    /* MII interface info */
+	u16 rx_buffer_len;
+
+	unsigned long flags;
+#define __AT_TESTING        0x0001
+#define __AT_RESETTING      0x0002
+#define __AT_DOWN           0x0003
+	unsigned long work_event;
+#define	ATL1C_WORK_EVENT_RESET		0
+#define	ATL1C_WORK_EVENT_LINK_CHANGE	1
+	u32 msg_enable;
+
+	bool have_msi;
+	u32 wol;
+	u16 link_speed;
+	u16 link_duplex;
+
+	spinlock_t mdio_lock;
+	spinlock_t tx_lock;
+	atomic_t irq_sem;
+
+	struct work_struct common_task;
+	struct timer_list watchdog_timer;
+	struct timer_list phy_config_timer;
+
+	/* All Descriptor memory */
+	struct atl1c_ring_header ring_header;
+	struct atl1c_tpd_ring tpd_ring[AT_MAX_TRANSMIT_QUEUE];
+	struct atl1c_rfd_ring rfd_ring;
+	struct atl1c_rrd_ring rrd_ring;
+	u32 bd_number;     /* board number;*/
+};
+
+#define AT_WRITE_REG(a, reg, value) ( \
+		writel((value), ((a)->hw_addr + reg)))
+
+#define AT_WRITE_FLUSH(a) (\
+		readl((a)->hw_addr))
+
+#define AT_READ_REG(a, reg, pdata) do {					\
+		if (unlikely((a)->hibernate)) {				\
+			readl((a)->hw_addr + reg);			\
+			*(u32 *)pdata = readl((a)->hw_addr + reg);	\
+		} else {						\
+			*(u32 *)pdata = readl((a)->hw_addr + reg);	\
+		}							\
+	} while (0)
+
+#define AT_WRITE_REGB(a, reg, value) (\
+		writeb((value), ((a)->hw_addr + reg)))
+
+#define AT_READ_REGB(a, reg) (\
+		readb((a)->hw_addr + reg))
+
+#define AT_WRITE_REGW(a, reg, value) (\
+		writew((value), ((a)->hw_addr + reg)))
+
+#define AT_READ_REGW(a, reg, pdata) do {				\
+		if (unlikely((a)->hibernate)) {				\
+			readw((a)->hw_addr + reg);			\
+			*(u16 *)pdata = readw((a)->hw_addr + reg);	\
+		} else {						\
+			*(u16 *)pdata = readw((a)->hw_addr + reg);	\
+		}							\
+	} while (0)
+
+#define AT_WRITE_REG_ARRAY(a, reg, offset, value) ( \
+		writel((value), (((a)->hw_addr + reg) + ((offset) << 2))))
+
+#define AT_READ_REG_ARRAY(a, reg, offset) ( \
+		readl(((a)->hw_addr + reg) + ((offset) << 2)))
+
+extern char atl1c_driver_name[];
+extern char atl1c_driver_version[];
+
+void atl1c_reinit_locked(struct atl1c_adapter *adapter);
+s32 atl1c_reset_hw(struct atl1c_hw *hw);
+void atl1c_set_ethtool_ops(struct net_device *netdev);
+#endif /* _ATL1C_H_ */

addons/atl1c/src/4.4.180/atl1c_ethtool.c

@@ -0,0 +1,305 @@
+/*
+ * Copyright(c) 2009 - 2009 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/slab.h>
+
+#include "atl1c.h"
+
+static int atl1c_get_settings(struct net_device *netdev,
+			      struct ethtool_cmd *ecmd)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+
+	ecmd->supported = (SUPPORTED_10baseT_Half  |
+			   SUPPORTED_10baseT_Full  |
+			   SUPPORTED_100baseT_Half |
+			   SUPPORTED_100baseT_Full |
+			   SUPPORTED_Autoneg       |
+			   SUPPORTED_TP);
+	if (hw->link_cap_flags & ATL1C_LINK_CAP_1000M)
+		ecmd->supported |= SUPPORTED_1000baseT_Full;
+
+	ecmd->advertising = ADVERTISED_TP;
+
+	ecmd->advertising |= hw->autoneg_advertised;
+
+	ecmd->port = PORT_TP;
+	ecmd->phy_address = 0;
+	ecmd->transceiver = XCVR_INTERNAL;
+
+	if (adapter->link_speed != SPEED_0) {
+		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+		if (adapter->link_duplex == FULL_DUPLEX)
+			ecmd->duplex = DUPLEX_FULL;
+		else
+			ecmd->duplex = DUPLEX_HALF;
+	} else {
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
+	}
+
+	ecmd->autoneg = AUTONEG_ENABLE;
+	return 0;
+}
+
+static int atl1c_set_settings(struct net_device *netdev,
+			      struct ethtool_cmd *ecmd)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+	u16  autoneg_advertised;
+
+	while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
+		msleep(1);
+
+	if (ecmd->autoneg == AUTONEG_ENABLE) {
+		autoneg_advertised = ADVERTISED_Autoneg;
+	} else {
+		u32 speed = ethtool_cmd_speed(ecmd);
+		if (speed == SPEED_1000) {
+			if (ecmd->duplex != DUPLEX_FULL) {
+				if (netif_msg_link(adapter))
+					dev_warn(&adapter->pdev->dev,
+						"1000M half is invalid\n");
+				clear_bit(__AT_RESETTING, &adapter->flags);
+				return -EINVAL;
+			}
+			autoneg_advertised = ADVERTISED_1000baseT_Full;
+		} else if (speed == SPEED_100) {
+			if (ecmd->duplex == DUPLEX_FULL)
+				autoneg_advertised = ADVERTISED_100baseT_Full;
+			else
+				autoneg_advertised = ADVERTISED_100baseT_Half;
+		} else {
+			if (ecmd->duplex == DUPLEX_FULL)
+				autoneg_advertised = ADVERTISED_10baseT_Full;
+			else
+				autoneg_advertised = ADVERTISED_10baseT_Half;
+		}
+	}
+
+	if (hw->autoneg_advertised != autoneg_advertised) {
+		hw->autoneg_advertised = autoneg_advertised;
+		if (atl1c_restart_autoneg(hw) != 0) {
+			if (netif_msg_link(adapter))
+				dev_warn(&adapter->pdev->dev,
+					"ethtool speed/duplex setting failed\n");
+			clear_bit(__AT_RESETTING, &adapter->flags);
+			return -EINVAL;
+		}
+	}
+	clear_bit(__AT_RESETTING, &adapter->flags);
+	return 0;
+}
+
+static u32 atl1c_get_msglevel(struct net_device *netdev)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	return adapter->msg_enable;
+}
+
+static void atl1c_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	adapter->msg_enable = data;
+}
+
+static int atl1c_get_regs_len(struct net_device *netdev)
+{
+	return AT_REGS_LEN;
+}
+
+static void atl1c_get_regs(struct net_device *netdev,
+			   struct ethtool_regs *regs, void *p)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+	u16 phy_data;
+
+	memset(p, 0, AT_REGS_LEN);
+
+	regs->version = 1;
+	AT_READ_REG(hw, REG_PM_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_MAC_HALF_DUPLX_CTRL,  p++);
+	AT_READ_REG(hw, REG_TWSI_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_PCIE_DEV_MISC_CTRL,   p++);
+	AT_READ_REG(hw, REG_MASTER_CTRL, 	  p++);
+	AT_READ_REG(hw, REG_MANUAL_TIMER_INIT,    p++);
+	AT_READ_REG(hw, REG_IRQ_MODRT_TIMER_INIT, p++);
+	AT_READ_REG(hw, REG_GPHY_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_LINK_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_IDLE_STATUS, 	  p++);
+	AT_READ_REG(hw, REG_MDIO_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_SERDES,		  p++);
+	AT_READ_REG(hw, REG_MAC_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_MAC_IPG_IFG, 	  p++);
+	AT_READ_REG(hw, REG_MAC_STA_ADDR, 	  p++);
+	AT_READ_REG(hw, REG_MAC_STA_ADDR+4, 	  p++);
+	AT_READ_REG(hw, REG_RX_HASH_TABLE, 	  p++);
+	AT_READ_REG(hw, REG_RX_HASH_TABLE+4, 	  p++);
+	AT_READ_REG(hw, REG_RXQ_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_TXQ_CTRL, 		  p++);
+	AT_READ_REG(hw, REG_MTU, 		  p++);
+	AT_READ_REG(hw, REG_WOL_CTRL, 		  p++);
+
+	atl1c_read_phy_reg(hw, MII_BMCR, &phy_data);
+	regs_buff[AT_REGS_LEN/sizeof(u32) - 2] = (u32) phy_data;
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	regs_buff[AT_REGS_LEN/sizeof(u32) - 1] = (u32) phy_data;
+}
+
+static int atl1c_get_eeprom_len(struct net_device *netdev)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	if (atl1c_check_eeprom_exist(&adapter->hw))
+		return AT_EEPROM_LEN;
+	else
+		return 0;
+}
+
+static int atl1c_get_eeprom(struct net_device *netdev,
+		struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	struct atl1c_hw *hw = &adapter->hw;
+	u32 *eeprom_buff;
+	int first_dword, last_dword;
+	int ret_val = 0;
+	int i;
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	if (!atl1c_check_eeprom_exist(hw)) /* not exist */
+		return -EINVAL;
+
+	eeprom->magic = adapter->pdev->vendor |
+			(adapter->pdev->device << 16);
+
+	first_dword = eeprom->offset >> 2;
+	last_dword = (eeprom->offset + eeprom->len - 1) >> 2;
+
+	eeprom_buff = kmalloc(sizeof(u32) *
+			(last_dword - first_dword + 1), GFP_KERNEL);
+	if (eeprom_buff == NULL)
+		return -ENOMEM;
+
+	for (i = first_dword; i < last_dword; i++) {
+		if (!atl1c_read_eeprom(hw, i * 4, &(eeprom_buff[i-first_dword]))) {
+			kfree(eeprom_buff);
+			return -EIO;
+		}
+	}
+
+	memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 3),
+			eeprom->len);
+	kfree(eeprom_buff);
+
+	return ret_val;
+	return 0;
+}
+
+static void atl1c_get_drvinfo(struct net_device *netdev,
+		struct ethtool_drvinfo *drvinfo)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver,  atl1c_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, atl1c_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
+}
+
+static void atl1c_get_wol(struct net_device *netdev,
+			  struct ethtool_wolinfo *wol)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	wol->supported = WAKE_MAGIC | WAKE_PHY;
+	wol->wolopts = 0;
+
+	if (adapter->wol & AT_WUFC_EX)
+		wol->wolopts |= WAKE_UCAST;
+	if (adapter->wol & AT_WUFC_MC)
+		wol->wolopts |= WAKE_MCAST;
+	if (adapter->wol & AT_WUFC_BC)
+		wol->wolopts |= WAKE_BCAST;
+	if (adapter->wol & AT_WUFC_MAG)
+		wol->wolopts |= WAKE_MAGIC;
+	if (adapter->wol & AT_WUFC_LNKC)
+		wol->wolopts |= WAKE_PHY;
+}
+
+static int atl1c_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+
+	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE |
+			    WAKE_UCAST | WAKE_BCAST | WAKE_MCAST))
+		return -EOPNOTSUPP;
+	/* these settings will always override what we currently have */
+	adapter->wol = 0;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		adapter->wol |= AT_WUFC_MAG;
+	if (wol->wolopts & WAKE_PHY)
+		adapter->wol |= AT_WUFC_LNKC;
+
+	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
+
+	return 0;
+}
+
+static int atl1c_nway_reset(struct net_device *netdev)
+{
+	struct atl1c_adapter *adapter = netdev_priv(netdev);
+	if (netif_running(netdev))
+		atl1c_reinit_locked(adapter);
+	return 0;
+}
+
+static const struct ethtool_ops atl1c_ethtool_ops = {
+	.get_settings           = atl1c_get_settings,
+	.set_settings           = atl1c_set_settings,
+	.get_drvinfo            = atl1c_get_drvinfo,
+	.get_regs_len           = atl1c_get_regs_len,
+	.get_regs               = atl1c_get_regs,
+	.get_wol                = atl1c_get_wol,
+	.set_wol                = atl1c_set_wol,
+	.get_msglevel           = atl1c_get_msglevel,
+	.set_msglevel           = atl1c_set_msglevel,
+	.nway_reset             = atl1c_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_eeprom_len         = atl1c_get_eeprom_len,
+	.get_eeprom             = atl1c_get_eeprom,
+};
+
+void atl1c_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &atl1c_ethtool_ops;
+}

addons/atl1c/src/4.4.180/atl1c_hw.c

@@ -0,0 +1,863 @@
+/*
+ * Copyright(c) 2007 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/mii.h>
+#include <linux/crc32.h>
+
+#include "atl1c.h"
+
+/*
+ * check_eeprom_exist
+ * return 1 if eeprom exist
+ */
+int atl1c_check_eeprom_exist(struct atl1c_hw *hw)
+{
+	u32 data;
+
+	AT_READ_REG(hw, REG_TWSI_DEBUG, &data);
+	if (data & TWSI_DEBUG_DEV_EXIST)
+		return 1;
+
+	AT_READ_REG(hw, REG_MASTER_CTRL, &data);
+	if (data & MASTER_CTRL_OTP_SEL)
+		return 1;
+	return 0;
+}
+
+void atl1c_hw_set_mac_addr(struct atl1c_hw *hw, u8 *mac_addr)
+{
+	u32 value;
+	/*
+	 * 00-0B-6A-F6-00-DC
+	 * 0:  6AF600DC 1: 000B
+	 * low dword
+	 */
+	value = mac_addr[2] << 24 |
+		mac_addr[3] << 16 |
+		mac_addr[4] << 8  |
+		mac_addr[5];
+	AT_WRITE_REG_ARRAY(hw, REG_MAC_STA_ADDR, 0, value);
+	/* hight dword */
+	value = mac_addr[0] << 8 |
+		mac_addr[1];
+	AT_WRITE_REG_ARRAY(hw, REG_MAC_STA_ADDR, 1, value);
+}
+
+/* read mac address from hardware register */
+static bool atl1c_read_current_addr(struct atl1c_hw *hw, u8 *eth_addr)
+{
+	u32 addr[2];
+
+	AT_READ_REG(hw, REG_MAC_STA_ADDR, &addr[0]);
+	AT_READ_REG(hw, REG_MAC_STA_ADDR + 4, &addr[1]);
+
+	*(u32 *) &eth_addr[2] = htonl(addr[0]);
+	*(u16 *) &eth_addr[0] = htons((u16)addr[1]);
+
+	return is_valid_ether_addr(eth_addr);
+}
+
+/*
+ * atl1c_get_permanent_address
+ * return 0 if get valid mac address,
+ */
+static int atl1c_get_permanent_address(struct atl1c_hw *hw)
+{
+	u32 i;
+	u32 otp_ctrl_data;
+	u32 twsi_ctrl_data;
+	u16 phy_data;
+	bool raise_vol = false;
+
+	/* MAC-address from BIOS is the 1st priority */
+	if (atl1c_read_current_addr(hw, hw->perm_mac_addr))
+		return 0;
+
+	/* init */
+	AT_READ_REG(hw, REG_OTP_CTRL, &otp_ctrl_data);
+	if (atl1c_check_eeprom_exist(hw)) {
+		if (hw->nic_type == athr_l1c || hw->nic_type == athr_l2c) {
+			/* Enable OTP CLK */
+			if (!(otp_ctrl_data & OTP_CTRL_CLK_EN)) {
+				otp_ctrl_data |= OTP_CTRL_CLK_EN;
+				AT_WRITE_REG(hw, REG_OTP_CTRL, otp_ctrl_data);
+				AT_WRITE_FLUSH(hw);
+				msleep(1);
+			}
+		}
+		/* raise voltage temporally for l2cb */
+		if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2) {
+			atl1c_read_phy_dbg(hw, MIIDBG_ANACTRL, &phy_data);
+			phy_data &= ~ANACTRL_HB_EN;
+			atl1c_write_phy_dbg(hw, MIIDBG_ANACTRL, phy_data);
+			atl1c_read_phy_dbg(hw, MIIDBG_VOLT_CTRL, &phy_data);
+			phy_data |= VOLT_CTRL_SWLOWEST;
+			atl1c_write_phy_dbg(hw, MIIDBG_VOLT_CTRL, phy_data);
+			udelay(20);
+			raise_vol = true;
+		}
+
+		AT_READ_REG(hw, REG_TWSI_CTRL, &twsi_ctrl_data);
+		twsi_ctrl_data |= TWSI_CTRL_SW_LDSTART;
+		AT_WRITE_REG(hw, REG_TWSI_CTRL, twsi_ctrl_data);
+		for (i = 0; i < AT_TWSI_EEPROM_TIMEOUT; i++) {
+			msleep(10);
+			AT_READ_REG(hw, REG_TWSI_CTRL, &twsi_ctrl_data);
+			if ((twsi_ctrl_data & TWSI_CTRL_SW_LDSTART) == 0)
+				break;
+		}
+		if (i >= AT_TWSI_EEPROM_TIMEOUT)
+			return -1;
+	}
+	/* Disable OTP_CLK */
+	if ((hw->nic_type == athr_l1c || hw->nic_type == athr_l2c)) {
+		otp_ctrl_data &= ~OTP_CTRL_CLK_EN;
+		AT_WRITE_REG(hw, REG_OTP_CTRL, otp_ctrl_data);
+		msleep(1);
+	}
+	if (raise_vol) {
+		atl1c_read_phy_dbg(hw, MIIDBG_ANACTRL, &phy_data);
+		phy_data |= ANACTRL_HB_EN;
+		atl1c_write_phy_dbg(hw, MIIDBG_ANACTRL, phy_data);
+		atl1c_read_phy_dbg(hw, MIIDBG_VOLT_CTRL, &phy_data);
+		phy_data &= ~VOLT_CTRL_SWLOWEST;
+		atl1c_write_phy_dbg(hw, MIIDBG_VOLT_CTRL, phy_data);
+		udelay(20);
+	}
+
+	if (atl1c_read_current_addr(hw, hw->perm_mac_addr))
+		return 0;
+
+	return -1;
+}
+
+bool atl1c_read_eeprom(struct atl1c_hw *hw, u32 offset, u32 *p_value)
+{
+	int i;
+	bool ret = false;
+	u32 otp_ctrl_data;
+	u32 control;
+	u32 data;
+
+	if (offset & 3)
+		return ret; /* address do not align */
+
+	AT_READ_REG(hw, REG_OTP_CTRL, &otp_ctrl_data);
+	if (!(otp_ctrl_data & OTP_CTRL_CLK_EN))
+		AT_WRITE_REG(hw, REG_OTP_CTRL,
+				(otp_ctrl_data | OTP_CTRL_CLK_EN));
+
+	AT_WRITE_REG(hw, REG_EEPROM_DATA_LO, 0);
+	control = (offset & EEPROM_CTRL_ADDR_MASK) << EEPROM_CTRL_ADDR_SHIFT;
+	AT_WRITE_REG(hw, REG_EEPROM_CTRL, control);
+
+	for (i = 0; i < 10; i++) {
+		udelay(100);
+		AT_READ_REG(hw, REG_EEPROM_CTRL, &control);
+		if (control & EEPROM_CTRL_RW)
+			break;
+	}
+	if (control & EEPROM_CTRL_RW) {
+		AT_READ_REG(hw, REG_EEPROM_CTRL, &data);
+		AT_READ_REG(hw, REG_EEPROM_DATA_LO, p_value);
+		data = data & 0xFFFF;
+		*p_value = swab32((data << 16) | (*p_value >> 16));
+		ret = true;
+	}
+	if (!(otp_ctrl_data & OTP_CTRL_CLK_EN))
+		AT_WRITE_REG(hw, REG_OTP_CTRL, otp_ctrl_data);
+
+	return ret;
+}
+/*
+ * Reads the adapter's MAC address from the EEPROM
+ *
+ * hw - Struct containing variables accessed by shared code
+ */
+int atl1c_read_mac_addr(struct atl1c_hw *hw)
+{
+	int err = 0;
+
+	err = atl1c_get_permanent_address(hw);
+	if (err)
+		eth_random_addr(hw->perm_mac_addr);
+
+	memcpy(hw->mac_addr, hw->perm_mac_addr, sizeof(hw->perm_mac_addr));
+	return err;
+}
+
+/*
+ * atl1c_hash_mc_addr
+ *  purpose
+ *      set hash value for a multicast address
+ *      hash calcu processing :
+ *          1. calcu 32bit CRC for multicast address
+ *          2. reverse crc with MSB to LSB
+ */
+u32 atl1c_hash_mc_addr(struct atl1c_hw *hw, u8 *mc_addr)
+{
+	u32 crc32;
+	u32 value = 0;
+	int i;
+
+	crc32 = ether_crc_le(6, mc_addr);
+	for (i = 0; i < 32; i++)
+		value |= (((crc32 >> i) & 1) << (31 - i));
+
+	return value;
+}
+
+/*
+ * Sets the bit in the multicast table corresponding to the hash value.
+ * hw - Struct containing variables accessed by shared code
+ * hash_value - Multicast address hash value
+ */
+void atl1c_hash_set(struct atl1c_hw *hw, u32 hash_value)
+{
+	u32 hash_bit, hash_reg;
+	u32 mta;
+
+	/*
+	 * The HASH Table  is a register array of 2 32-bit registers.
+	 * It is treated like an array of 64 bits.  We want to set
+	 * bit BitArray[hash_value]. So we figure out what register
+	 * the bit is in, read it, OR in the new bit, then write
+	 * back the new value.  The register is determined by the
+	 * upper bit of the hash value and the bit within that
+	 * register are determined by the lower 5 bits of the value.
+	 */
+	hash_reg = (hash_value >> 31) & 0x1;
+	hash_bit = (hash_value >> 26) & 0x1F;
+
+	mta = AT_READ_REG_ARRAY(hw, REG_RX_HASH_TABLE, hash_reg);
+
+	mta |= (1 << hash_bit);
+
+	AT_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, hash_reg, mta);
+}
+
+/*
+ * wait mdio module be idle
+ * return true: idle
+ *        false: still busy
+ */
+bool atl1c_wait_mdio_idle(struct atl1c_hw *hw)
+{
+	u32 val;
+	int i;
+
+	for (i = 0; i < MDIO_MAX_AC_TO; i++) {
+		AT_READ_REG(hw, REG_MDIO_CTRL, &val);
+		if (!(val & (MDIO_CTRL_BUSY | MDIO_CTRL_START)))
+			break;
+		udelay(10);
+	}
+
+	return i != MDIO_MAX_AC_TO;
+}
+
+void atl1c_stop_phy_polling(struct atl1c_hw *hw)
+{
+	if (!(hw->ctrl_flags & ATL1C_FPGA_VERSION))
+		return;
+
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, 0);
+	atl1c_wait_mdio_idle(hw);
+}
+
+void atl1c_start_phy_polling(struct atl1c_hw *hw, u16 clk_sel)
+{
+	u32 val;
+
+	if (!(hw->ctrl_flags & ATL1C_FPGA_VERSION))
+		return;
+
+	val = MDIO_CTRL_SPRES_PRMBL |
+		FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+		FIELDX(MDIO_CTRL_REG, 1) |
+		MDIO_CTRL_START |
+		MDIO_CTRL_OP_READ;
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+	atl1c_wait_mdio_idle(hw);
+	val |= MDIO_CTRL_AP_EN;
+	val &= ~MDIO_CTRL_START;
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+	udelay(30);
+}
+
+
+/*
+ * atl1c_read_phy_core
+ * core function to read register in PHY via MDIO control regsiter.
+ * ext: extension register (see IEEE 802.3)
+ * dev: device address (see IEEE 802.3 DEVAD, PRTAD is fixed to 0)
+ * reg: reg to read
+ */
+int atl1c_read_phy_core(struct atl1c_hw *hw, bool ext, u8 dev,
+			u16 reg, u16 *phy_data)
+{
+	u32 val;
+	u16 clk_sel = MDIO_CTRL_CLK_25_4;
+
+	atl1c_stop_phy_polling(hw);
+
+	*phy_data = 0;
+
+	/* only l2c_b2 & l1d_2 could use slow clock */
+	if ((hw->nic_type == athr_l2c_b2 || hw->nic_type == athr_l1d_2) &&
+		hw->hibernate)
+		clk_sel = MDIO_CTRL_CLK_25_128;
+	if (ext) {
+		val = FIELDX(MDIO_EXTN_DEVAD, dev) | FIELDX(MDIO_EXTN_REG, reg);
+		AT_WRITE_REG(hw, REG_MDIO_EXTN, val);
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			MDIO_CTRL_START |
+			MDIO_CTRL_MODE_EXT |
+			MDIO_CTRL_OP_READ;
+	} else {
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			FIELDX(MDIO_CTRL_REG, reg) |
+			MDIO_CTRL_START |
+			MDIO_CTRL_OP_READ;
+	}
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+
+	if (!atl1c_wait_mdio_idle(hw))
+		return -1;
+
+	AT_READ_REG(hw, REG_MDIO_CTRL, &val);
+	*phy_data = (u16)FIELD_GETX(val, MDIO_CTRL_DATA);
+
+	atl1c_start_phy_polling(hw, clk_sel);
+
+	return 0;
+}
+
+/*
+ * atl1c_write_phy_core
+ * core function to write to register in PHY via MDIO control register.
+ * ext: extension register (see IEEE 802.3)
+ * dev: device address (see IEEE 802.3 DEVAD, PRTAD is fixed to 0)
+ * reg: reg to write
+ */
+int atl1c_write_phy_core(struct atl1c_hw *hw, bool ext, u8 dev,
+			u16 reg, u16 phy_data)
+{
+	u32 val;
+	u16 clk_sel = MDIO_CTRL_CLK_25_4;
+
+	atl1c_stop_phy_polling(hw);
+
+
+	/* only l2c_b2 & l1d_2 could use slow clock */
+	if ((hw->nic_type == athr_l2c_b2 || hw->nic_type == athr_l1d_2) &&
+		hw->hibernate)
+		clk_sel = MDIO_CTRL_CLK_25_128;
+
+	if (ext) {
+		val = FIELDX(MDIO_EXTN_DEVAD, dev) | FIELDX(MDIO_EXTN_REG, reg);
+		AT_WRITE_REG(hw, REG_MDIO_EXTN, val);
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			FIELDX(MDIO_CTRL_DATA, phy_data) |
+			MDIO_CTRL_START |
+			MDIO_CTRL_MODE_EXT;
+	} else {
+		val = MDIO_CTRL_SPRES_PRMBL |
+			FIELDX(MDIO_CTRL_CLK_SEL, clk_sel) |
+			FIELDX(MDIO_CTRL_DATA, phy_data) |
+			FIELDX(MDIO_CTRL_REG, reg) |
+			MDIO_CTRL_START;
+	}
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+
+	if (!atl1c_wait_mdio_idle(hw))
+		return -1;
+
+	atl1c_start_phy_polling(hw, clk_sel);
+
+	return 0;
+}
+
+/*
+ * Reads the value from a PHY register
+ * hw - Struct containing variables accessed by shared code
+ * reg_addr - address of the PHY register to read
+ */
+int atl1c_read_phy_reg(struct atl1c_hw *hw, u16 reg_addr, u16 *phy_data)
+{
+	return atl1c_read_phy_core(hw, false, 0, reg_addr, phy_data);
+}
+
+/*
+ * Writes a value to a PHY register
+ * hw - Struct containing variables accessed by shared code
+ * reg_addr - address of the PHY register to write
+ * data - data to write to the PHY
+ */
+int atl1c_write_phy_reg(struct atl1c_hw *hw, u32 reg_addr, u16 phy_data)
+{
+	return atl1c_write_phy_core(hw, false, 0, reg_addr, phy_data);
+}
+
+/* read from PHY extension register */
+int atl1c_read_phy_ext(struct atl1c_hw *hw, u8 dev_addr,
+			u16 reg_addr, u16 *phy_data)
+{
+	return atl1c_read_phy_core(hw, true, dev_addr, reg_addr, phy_data);
+}
+
+/* write to PHY extension register */
+int atl1c_write_phy_ext(struct atl1c_hw *hw, u8 dev_addr,
+			u16 reg_addr, u16 phy_data)
+{
+	return atl1c_write_phy_core(hw, true, dev_addr, reg_addr, phy_data);
+}
+
+int atl1c_read_phy_dbg(struct atl1c_hw *hw, u16 reg_addr, u16 *phy_data)
+{
+	int err;
+
+	err = atl1c_write_phy_reg(hw, MII_DBG_ADDR, reg_addr);
+	if (unlikely(err))
+		return err;
+	else
+		err = atl1c_read_phy_reg(hw, MII_DBG_DATA, phy_data);
+
+	return err;
+}
+
+int atl1c_write_phy_dbg(struct atl1c_hw *hw, u16 reg_addr, u16 phy_data)
+{
+	int err;
+
+	err = atl1c_write_phy_reg(hw, MII_DBG_ADDR, reg_addr);
+	if (unlikely(err))
+		return err;
+	else
+		err = atl1c_write_phy_reg(hw, MII_DBG_DATA, phy_data);
+
+	return err;
+}
+
+/*
+ * Configures PHY autoneg and flow control advertisement settings
+ *
+ * hw - Struct containing variables accessed by shared code
+ */
+static int atl1c_phy_setup_adv(struct atl1c_hw *hw)
+{
+	u16 mii_adv_data = ADVERTISE_DEFAULT_CAP & ~ADVERTISE_ALL;
+	u16 mii_giga_ctrl_data = GIGA_CR_1000T_DEFAULT_CAP &
+				~GIGA_CR_1000T_SPEED_MASK;
+
+	if (hw->autoneg_advertised & ADVERTISED_10baseT_Half)
+		mii_adv_data |= ADVERTISE_10HALF;
+	if (hw->autoneg_advertised & ADVERTISED_10baseT_Full)
+		mii_adv_data |= ADVERTISE_10FULL;
+	if (hw->autoneg_advertised & ADVERTISED_100baseT_Half)
+		mii_adv_data |= ADVERTISE_100HALF;
+	if (hw->autoneg_advertised & ADVERTISED_100baseT_Full)
+		mii_adv_data |= ADVERTISE_100FULL;
+
+	if (hw->autoneg_advertised & ADVERTISED_Autoneg)
+		mii_adv_data |= ADVERTISE_10HALF  | ADVERTISE_10FULL |
+				ADVERTISE_100HALF | ADVERTISE_100FULL;
+
+	if (hw->link_cap_flags & ATL1C_LINK_CAP_1000M) {
+		if (hw->autoneg_advertised & ADVERTISED_1000baseT_Half)
+			mii_giga_ctrl_data |= ADVERTISE_1000HALF;
+		if (hw->autoneg_advertised & ADVERTISED_1000baseT_Full)
+			mii_giga_ctrl_data |= ADVERTISE_1000FULL;
+		if (hw->autoneg_advertised & ADVERTISED_Autoneg)
+			mii_giga_ctrl_data |= ADVERTISE_1000HALF |
+					ADVERTISE_1000FULL;
+	}
+
+	if (atl1c_write_phy_reg(hw, MII_ADVERTISE, mii_adv_data) != 0 ||
+	    atl1c_write_phy_reg(hw, MII_CTRL1000, mii_giga_ctrl_data) != 0)
+		return -1;
+	return 0;
+}
+
+void atl1c_phy_disable(struct atl1c_hw *hw)
+{
+	atl1c_power_saving(hw, 0);
+}
+
+
+int atl1c_phy_reset(struct atl1c_hw *hw)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	u16 phy_data;
+	u32 phy_ctrl_data, lpi_ctrl;
+	int err;
+
+	/* reset PHY core */
+	AT_READ_REG(hw, REG_GPHY_CTRL, &phy_ctrl_data);
+	phy_ctrl_data &= ~(GPHY_CTRL_EXT_RESET | GPHY_CTRL_PHY_IDDQ |
+		GPHY_CTRL_GATE_25M_EN | GPHY_CTRL_PWDOWN_HW | GPHY_CTRL_CLS);
+	phy_ctrl_data |= GPHY_CTRL_SEL_ANA_RST;
+	if (!(hw->ctrl_flags & ATL1C_HIB_DISABLE))
+		phy_ctrl_data |= (GPHY_CTRL_HIB_EN | GPHY_CTRL_HIB_PULSE);
+	else
+		phy_ctrl_data &= ~(GPHY_CTRL_HIB_EN | GPHY_CTRL_HIB_PULSE);
+	AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl_data);
+	AT_WRITE_FLUSH(hw);
+	udelay(10);
+	AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl_data | GPHY_CTRL_EXT_RESET);
+	AT_WRITE_FLUSH(hw);
+	udelay(10 * GPHY_CTRL_EXT_RST_TO);	/* delay 800us */
+
+	/* switch clock */
+	if (hw->nic_type == athr_l2c_b) {
+		atl1c_read_phy_dbg(hw, MIIDBG_CFGLPSPD, &phy_data);
+		atl1c_write_phy_dbg(hw, MIIDBG_CFGLPSPD,
+			phy_data & ~CFGLPSPD_RSTCNT_CLK125SW);
+	}
+
+	/* tx-half amplitude issue fix */
+	if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2) {
+		atl1c_read_phy_dbg(hw, MIIDBG_CABLE1TH_DET, &phy_data);
+		phy_data |= CABLE1TH_DET_EN;
+		atl1c_write_phy_dbg(hw, MIIDBG_CABLE1TH_DET, phy_data);
+	}
+
+	/* clear bit3 of dbgport 3B to lower voltage */
+	if (!(hw->ctrl_flags & ATL1C_HIB_DISABLE)) {
+		if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2) {
+			atl1c_read_phy_dbg(hw, MIIDBG_VOLT_CTRL, &phy_data);
+			phy_data &= ~VOLT_CTRL_SWLOWEST;
+			atl1c_write_phy_dbg(hw, MIIDBG_VOLT_CTRL, phy_data);
+		}
+		/* power saving config */
+		phy_data =
+			hw->nic_type == athr_l1d || hw->nic_type == athr_l1d_2 ?
+			L1D_LEGCYPS_DEF : L1C_LEGCYPS_DEF;
+		atl1c_write_phy_dbg(hw, MIIDBG_LEGCYPS, phy_data);
+		/* hib */
+		atl1c_write_phy_dbg(hw, MIIDBG_SYSMODCTRL,
+			SYSMODCTRL_IECHOADJ_DEF);
+	} else {
+		/* disable pws */
+		atl1c_read_phy_dbg(hw, MIIDBG_LEGCYPS, &phy_data);
+		atl1c_write_phy_dbg(hw, MIIDBG_LEGCYPS,
+			phy_data & ~LEGCYPS_EN);
+		/* disable hibernate */
+		atl1c_read_phy_dbg(hw, MIIDBG_HIBNEG, &phy_data);
+		atl1c_write_phy_dbg(hw, MIIDBG_HIBNEG,
+			phy_data & HIBNEG_PSHIB_EN);
+	}
+	/* disable AZ(EEE) by default */
+	if (hw->nic_type == athr_l1d || hw->nic_type == athr_l1d_2 ||
+	    hw->nic_type == athr_l2c_b2) {
+		AT_READ_REG(hw, REG_LPI_CTRL, &lpi_ctrl);
+		AT_WRITE_REG(hw, REG_LPI_CTRL, lpi_ctrl & ~LPI_CTRL_EN);
+		atl1c_write_phy_ext(hw, MIIEXT_ANEG, MIIEXT_LOCAL_EEEADV, 0);
+		atl1c_write_phy_ext(hw, MIIEXT_PCS, MIIEXT_CLDCTRL3,
+			L2CB_CLDCTRL3);
+	}
+
+	/* other debug port to set */
+	atl1c_write_phy_dbg(hw, MIIDBG_ANACTRL, ANACTRL_DEF);
+	atl1c_write_phy_dbg(hw, MIIDBG_SRDSYSMOD, SRDSYSMOD_DEF);
+	atl1c_write_phy_dbg(hw, MIIDBG_TST10BTCFG, TST10BTCFG_DEF);
+	/* UNH-IOL test issue, set bit7 */
+	atl1c_write_phy_dbg(hw, MIIDBG_TST100BTCFG,
+		TST100BTCFG_DEF | TST100BTCFG_LITCH_EN);
+
+	/* set phy interrupt mask */
+	phy_data = IER_LINK_UP | IER_LINK_DOWN;
+	err = atl1c_write_phy_reg(hw, MII_IER, phy_data);
+	if (err) {
+		if (netif_msg_hw(adapter))
+			dev_err(&pdev->dev,
+				"Error enable PHY linkChange Interrupt\n");
+		return err;
+	}
+	return 0;
+}
+
+int atl1c_phy_init(struct atl1c_hw *hw)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	int ret_val;
+	u16 mii_bmcr_data = BMCR_RESET;
+
+	if ((atl1c_read_phy_reg(hw, MII_PHYSID1, &hw->phy_id1) != 0) ||
+		(atl1c_read_phy_reg(hw, MII_PHYSID2, &hw->phy_id2) != 0)) {
+		dev_err(&pdev->dev, "Error get phy ID\n");
+		return -1;
+	}
+	switch (hw->media_type) {
+	case MEDIA_TYPE_AUTO_SENSOR:
+		ret_val = atl1c_phy_setup_adv(hw);
+		if (ret_val) {
+			if (netif_msg_link(adapter))
+				dev_err(&pdev->dev,
+					"Error Setting up Auto-Negotiation\n");
+			return ret_val;
+		}
+		mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART;
+		break;
+	case MEDIA_TYPE_100M_FULL:
+		mii_bmcr_data |= BMCR_SPEED100 | BMCR_FULLDPLX;
+		break;
+	case MEDIA_TYPE_100M_HALF:
+		mii_bmcr_data |= BMCR_SPEED100;
+		break;
+	case MEDIA_TYPE_10M_FULL:
+		mii_bmcr_data |= BMCR_FULLDPLX;
+		break;
+	case MEDIA_TYPE_10M_HALF:
+		break;
+	default:
+		if (netif_msg_link(adapter))
+			dev_err(&pdev->dev, "Wrong Media type %d\n",
+				hw->media_type);
+		return -1;
+	}
+
+	ret_val = atl1c_write_phy_reg(hw, MII_BMCR, mii_bmcr_data);
+	if (ret_val)
+		return ret_val;
+	hw->phy_configured = true;
+
+	return 0;
+}
+
+/*
+ * Detects the current speed and duplex settings of the hardware.
+ *
+ * hw - Struct containing variables accessed by shared code
+ * speed - Speed of the connection
+ * duplex - Duplex setting of the connection
+ */
+int atl1c_get_speed_and_duplex(struct atl1c_hw *hw, u16 *speed, u16 *duplex)
+{
+	int err;
+	u16 phy_data;
+
+	/* Read   PHY Specific Status Register (17) */
+	err = atl1c_read_phy_reg(hw, MII_GIGA_PSSR, &phy_data);
+	if (err)
+		return err;
+
+	if (!(phy_data & GIGA_PSSR_SPD_DPLX_RESOLVED))
+		return -1;
+
+	switch (phy_data & GIGA_PSSR_SPEED) {
+	case GIGA_PSSR_1000MBS:
+		*speed = SPEED_1000;
+		break;
+	case GIGA_PSSR_100MBS:
+		*speed = SPEED_100;
+		break;
+	case  GIGA_PSSR_10MBS:
+		*speed = SPEED_10;
+		break;
+	default:
+		return -1;
+	}
+
+	if (phy_data & GIGA_PSSR_DPLX)
+		*duplex = FULL_DUPLEX;
+	else
+		*duplex = HALF_DUPLEX;
+
+	return 0;
+}
+
+/* select one link mode to get lower power consumption */
+int atl1c_phy_to_ps_link(struct atl1c_hw *hw)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	int ret = 0;
+	u16 autoneg_advertised = ADVERTISED_10baseT_Half;
+	u16 save_autoneg_advertised;
+	u16 phy_data;
+	u16 mii_lpa_data;
+	u16 speed = SPEED_0;
+	u16 duplex = FULL_DUPLEX;
+	int i;
+
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+	if (phy_data & BMSR_LSTATUS) {
+		atl1c_read_phy_reg(hw, MII_LPA, &mii_lpa_data);
+		if (mii_lpa_data & LPA_10FULL)
+			autoneg_advertised = ADVERTISED_10baseT_Full;
+		else if (mii_lpa_data & LPA_10HALF)
+			autoneg_advertised = ADVERTISED_10baseT_Half;
+		else if (mii_lpa_data & LPA_100HALF)
+			autoneg_advertised = ADVERTISED_100baseT_Half;
+		else if (mii_lpa_data & LPA_100FULL)
+			autoneg_advertised = ADVERTISED_100baseT_Full;
+
+		save_autoneg_advertised = hw->autoneg_advertised;
+		hw->phy_configured = false;
+		hw->autoneg_advertised = autoneg_advertised;
+		if (atl1c_restart_autoneg(hw) != 0) {
+			dev_dbg(&pdev->dev, "phy autoneg failed\n");
+			ret = -1;
+		}
+		hw->autoneg_advertised = save_autoneg_advertised;
+
+		if (mii_lpa_data) {
+			for (i = 0; i < AT_SUSPEND_LINK_TIMEOUT; i++) {
+				mdelay(100);
+				atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+				atl1c_read_phy_reg(hw, MII_BMSR, &phy_data);
+				if (phy_data & BMSR_LSTATUS) {
+					if (atl1c_get_speed_and_duplex(hw, &speed,
+									&duplex) != 0)
+						dev_dbg(&pdev->dev,
+							"get speed and duplex failed\n");
+					break;
+				}
+			}
+		}
+	} else {
+		speed = SPEED_10;
+		duplex = HALF_DUPLEX;
+	}
+	adapter->link_speed = speed;
+	adapter->link_duplex = duplex;
+
+	return ret;
+}
+
+int atl1c_restart_autoneg(struct atl1c_hw *hw)
+{
+	int err = 0;
+	u16 mii_bmcr_data = BMCR_RESET;
+
+	err = atl1c_phy_setup_adv(hw);
+	if (err)
+		return err;
+	mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART;
+
+	return atl1c_write_phy_reg(hw, MII_BMCR, mii_bmcr_data);
+}
+
+int atl1c_power_saving(struct atl1c_hw *hw, u32 wufc)
+{
+	struct atl1c_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	u32 master_ctrl, mac_ctrl, phy_ctrl;
+	u32 wol_ctrl, speed;
+	u16 phy_data;
+
+	wol_ctrl = 0;
+	speed = adapter->link_speed == SPEED_1000 ?
+		MAC_CTRL_SPEED_1000 : MAC_CTRL_SPEED_10_100;
+
+	AT_READ_REG(hw, REG_MASTER_CTRL, &master_ctrl);
+	AT_READ_REG(hw, REG_MAC_CTRL, &mac_ctrl);
+	AT_READ_REG(hw, REG_GPHY_CTRL, &phy_ctrl);
+
+	master_ctrl &= ~MASTER_CTRL_CLK_SEL_DIS;
+	mac_ctrl = FIELD_SETX(mac_ctrl, MAC_CTRL_SPEED, speed);
+	mac_ctrl &= ~(MAC_CTRL_DUPLX | MAC_CTRL_RX_EN | MAC_CTRL_TX_EN);
+	if (adapter->link_duplex == FULL_DUPLEX)
+		mac_ctrl |= MAC_CTRL_DUPLX;
+	phy_ctrl &= ~(GPHY_CTRL_EXT_RESET | GPHY_CTRL_CLS);
+	phy_ctrl |= GPHY_CTRL_SEL_ANA_RST | GPHY_CTRL_HIB_PULSE |
+		GPHY_CTRL_HIB_EN;
+	if (!wufc) { /* without WoL */
+		master_ctrl |= MASTER_CTRL_CLK_SEL_DIS;
+		phy_ctrl |= GPHY_CTRL_PHY_IDDQ | GPHY_CTRL_PWDOWN_HW;
+		AT_WRITE_REG(hw, REG_MASTER_CTRL, master_ctrl);
+		AT_WRITE_REG(hw, REG_MAC_CTRL, mac_ctrl);
+		AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl);
+		AT_WRITE_REG(hw, REG_WOL_CTRL, 0);
+		hw->phy_configured = false; /* re-init PHY when resume */
+		return 0;
+	}
+	phy_ctrl |= GPHY_CTRL_EXT_RESET;
+	if (wufc & AT_WUFC_MAG) {
+		mac_ctrl |= MAC_CTRL_RX_EN | MAC_CTRL_BC_EN;
+		wol_ctrl |= WOL_MAGIC_EN | WOL_MAGIC_PME_EN;
+		if (hw->nic_type == athr_l2c_b && hw->revision_id == L2CB_V11)
+			wol_ctrl |= WOL_PATTERN_EN | WOL_PATTERN_PME_EN;
+	}
+	if (wufc & AT_WUFC_LNKC) {
+		wol_ctrl |= WOL_LINK_CHG_EN | WOL_LINK_CHG_PME_EN;
+		if (atl1c_write_phy_reg(hw, MII_IER, IER_LINK_UP) != 0) {
+			dev_dbg(&pdev->dev, "%s: write phy MII_IER failed.\n",
+				atl1c_driver_name);
+		}
+	}
+	/* clear PHY interrupt */
+	atl1c_read_phy_reg(hw, MII_ISR, &phy_data);
+
+	dev_dbg(&pdev->dev, "%s: suspend MAC=%x,MASTER=%x,PHY=0x%x,WOL=%x\n",
+		atl1c_driver_name, mac_ctrl, master_ctrl, phy_ctrl, wol_ctrl);
+	AT_WRITE_REG(hw, REG_MASTER_CTRL, master_ctrl);
+	AT_WRITE_REG(hw, REG_MAC_CTRL, mac_ctrl);
+	AT_WRITE_REG(hw, REG_GPHY_CTRL, phy_ctrl);
+	AT_WRITE_REG(hw, REG_WOL_CTRL, wol_ctrl);
+
+	return 0;
+}
+
+
+/* configure phy after Link change Event */
+void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed)
+{
+	u16 phy_val;
+	bool adj_thresh = false;
+
+	if (hw->nic_type == athr_l2c_b || hw->nic_type == athr_l2c_b2 ||
+	    hw->nic_type == athr_l1d || hw->nic_type == athr_l1d_2)
+		adj_thresh = true;
+
+	if (link_speed != SPEED_0) { /* link up */
+		/* az with brcm, half-amp */
+		if (hw->nic_type == athr_l1d_2) {
+			atl1c_read_phy_ext(hw, MIIEXT_PCS, MIIEXT_CLDCTRL6,
+				&phy_val);
+			phy_val = FIELD_GETX(phy_val, CLDCTRL6_CAB_LEN);
+			phy_val = phy_val > CLDCTRL6_CAB_LEN_SHORT ?
+				AZ_ANADECT_LONG : AZ_ANADECT_DEF;
+			atl1c_write_phy_dbg(hw, MIIDBG_AZ_ANADECT, phy_val);
+		}
+		/* threshold adjust */
+		if (adj_thresh && link_speed == SPEED_100 && hw->msi_lnkpatch) {
+			atl1c_write_phy_dbg(hw, MIIDBG_MSE16DB, L1D_MSE16DB_UP);
+			atl1c_write_phy_dbg(hw, MIIDBG_SYSMODCTRL,
+				L1D_SYSMODCTRL_IECHOADJ_DEF);
+		}
+	} else { /* link down */
+		if (adj_thresh && hw->msi_lnkpatch) {
+			atl1c_write_phy_dbg(hw, MIIDBG_SYSMODCTRL,
+				SYSMODCTRL_IECHOADJ_DEF);
+			atl1c_write_phy_dbg(hw, MIIDBG_MSE16DB,
+				L1D_MSE16DB_DOWN);
+		}
+	}
+}

addons/atl1e/install.sh

@@ -0,0 +1,4 @@
+if [ "${1}" = "rd" ]; then
+  echo "Installing module for Atheros L1E Gigabit Ethernet adapter"
+  ${INSMOD} "/modules/atl1e.ko" ${PARAMS}
+fi

addons/atl1e/manifest.yml

@@ -0,0 +1,28 @@
+version: 1
+name: atl1e
+description: "Driver for Atheros L1E Gigabit Ethernet adapters"
+available-for:
+  bromolow-3.10.108:
+    install-script: &script "install.sh"
+    modules: true
+  apollolake-4.4.180:
+    install-script: *script
+    modules: true
+  broadwell-4.4.180:
+    install-script: *script
+    modules: true
+  broadwellnk-4.4.180:
+    install-script: *script
+    modules: true
+  denverton-4.4.180:
+    install-script: *script
+    modules: true
+  geminilake-4.4.180:
+    install-script: *script
+    modules: true
+  v1000-4.4.180:
+    install-script: *script
+    modules: true
+  purley-4.4.180:
+    install-script: *script
+    modules: true

addons/atl1e/src/3.10.108/Makefile

@@ -0,0 +1,2 @@
+obj-m	+= atl1e.o
+atl1e-objs		+= atl1e_main.o atl1e_hw.o atl1e_ethtool.o atl1e_param.o

addons/atl1e/src/3.10.108/atl1e.h

@@ -0,0 +1,508 @@
+/*
+ * Copyright(c) 2007 Atheros Corporation. All rights reserved.
+ * Copyright(c) 2007 xiong huang <xiong.huang@atheros.com>
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#ifndef _ATL1E_H_
+#define _ATL1E_H_
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+#include <linux/mii.h>
+#include <linux/io.h>
+#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
+#include <linux/tcp.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/workqueue.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
+
+#include "atl1e_hw.h"
+
+#define PCI_REG_COMMAND	 0x04    /* PCI Command Register */
+#define CMD_IO_SPACE	 0x0001
+#define CMD_MEMORY_SPACE 0x0002
+#define CMD_BUS_MASTER   0x0004
+
+#define BAR_0   0
+#define BAR_1   1
+#define BAR_5   5
+
+/* Wake Up Filter Control */
+#define AT_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */
+#define AT_WUFC_MAG  0x00000002 /* Magic Packet Wakeup Enable */
+#define AT_WUFC_EX   0x00000004 /* Directed Exact Wakeup Enable */
+#define AT_WUFC_MC   0x00000008 /* Multicast Wakeup Enable */
+#define AT_WUFC_BC   0x00000010 /* Broadcast Wakeup Enable */
+
+#define SPEED_0		   0xffff
+#define HALF_DUPLEX        1
+#define FULL_DUPLEX        2
+
+/* Error Codes */
+#define AT_ERR_EEPROM      1
+#define AT_ERR_PHY         2
+#define AT_ERR_CONFIG      3
+#define AT_ERR_PARAM       4
+#define AT_ERR_MAC_TYPE    5
+#define AT_ERR_PHY_TYPE    6
+#define AT_ERR_PHY_SPEED   7
+#define AT_ERR_PHY_RES     8
+#define AT_ERR_TIMEOUT     9
+
+#define MAX_JUMBO_FRAME_SIZE 0x2000
+
+#define AT_VLAN_TAG_TO_TPD_TAG(_vlan, _tpd)    \
+	_tpd = (((_vlan) << (4)) | (((_vlan) >> 13) & 7) |\
+		 (((_vlan) >> 9) & 8))
+
+#define AT_TPD_TAG_TO_VLAN_TAG(_tpd, _vlan)    \
+	_vlan = (((_tpd) >> 8) | (((_tpd) & 0x77) << 9) |\
+		   (((_tdp) & 0x88) << 5))
+
+#define AT_MAX_RECEIVE_QUEUE    4
+#define AT_PAGE_NUM_PER_QUEUE   2
+
+#define AT_DMA_HI_ADDR_MASK     0xffffffff00000000ULL
+#define AT_DMA_LO_ADDR_MASK     0x00000000ffffffffULL
+
+#define AT_TX_WATCHDOG  (5 * HZ)
+#define AT_MAX_INT_WORK		10
+#define AT_TWSI_EEPROM_TIMEOUT 	100
+#define AT_HW_MAX_IDLE_DELAY 	10
+#define AT_SUSPEND_LINK_TIMEOUT 28
+
+#define AT_REGS_LEN	75
+#define AT_EEPROM_LEN 	512
+#define AT_ADV_MASK	(ADVERTISE_10_HALF  |\
+			 ADVERTISE_10_FULL  |\
+			 ADVERTISE_100_HALF |\
+			 ADVERTISE_100_FULL |\
+			 ADVERTISE_1000_FULL)
+
+/* tpd word 2 */
+#define TPD_BUFLEN_MASK 	0x3FFF
+#define TPD_BUFLEN_SHIFT        0
+#define TPD_DMAINT_MASK		0x0001
+#define TPD_DMAINT_SHIFT        14
+#define TPD_PKTNT_MASK          0x0001
+#define TPD_PKTINT_SHIFT        15
+#define TPD_VLANTAG_MASK        0xFFFF
+#define TPD_VLAN_SHIFT          16
+
+/* tpd word 3 bits 0:4 */
+#define TPD_EOP_MASK            0x0001
+#define TPD_EOP_SHIFT           0
+#define TPD_IP_VERSION_MASK	0x0001
+#define TPD_IP_VERSION_SHIFT	1	/* 0 : IPV4, 1 : IPV6 */
+#define TPD_INS_VL_TAG_MASK	0x0001
+#define TPD_INS_VL_TAG_SHIFT	2
+#define TPD_CC_SEGMENT_EN_MASK	0x0001
+#define TPD_CC_SEGMENT_EN_SHIFT	3
+#define TPD_SEGMENT_EN_MASK     0x0001
+#define TPD_SEGMENT_EN_SHIFT    4
+
+/* tdp word 3 bits 5:7 if ip version is 0 */
+#define TPD_IP_CSUM_MASK        0x0001
+#define TPD_IP_CSUM_SHIFT       5
+#define TPD_TCP_CSUM_MASK       0x0001
+#define TPD_TCP_CSUM_SHIFT      6
+#define TPD_UDP_CSUM_MASK       0x0001
+#define TPD_UDP_CSUM_SHIFT      7
+
+/* tdp word 3 bits 5:7 if ip version is 1 */
+#define TPD_V6_IPHLLO_MASK	0x0007
+#define TPD_V6_IPHLLO_SHIFT	7
+
+/* tpd word 3 bits 8:9 bit */
+#define TPD_VL_TAGGED_MASK      0x0001
+#define TPD_VL_TAGGED_SHIFT     8
+#define TPD_ETHTYPE_MASK        0x0001
+#define TPD_ETHTYPE_SHIFT       9
+
+/* tdp word 3 bits 10:13 if ip version is 0 */
+#define TDP_V4_IPHL_MASK	0x000F
+#define TPD_V4_IPHL_SHIFT	10
+
+/* tdp word 3 bits 10:13 if ip version is 1 */
+#define TPD_V6_IPHLHI_MASK	0x000F
+#define TPD_V6_IPHLHI_SHIFT	10
+
+/* tpd word 3 bit 14:31 if segment enabled */
+#define TPD_TCPHDRLEN_MASK      0x000F
+#define TPD_TCPHDRLEN_SHIFT     14
+#define TPD_HDRFLAG_MASK        0x0001
+#define TPD_HDRFLAG_SHIFT       18
+#define TPD_MSS_MASK            0x1FFF
+#define TPD_MSS_SHIFT           19
+
+/* tdp word 3 bit 16:31 if custom csum enabled */
+#define TPD_PLOADOFFSET_MASK    0x00FF
+#define TPD_PLOADOFFSET_SHIFT   16
+#define TPD_CCSUMOFFSET_MASK    0x00FF
+#define TPD_CCSUMOFFSET_SHIFT   24
+
+struct atl1e_tpd_desc {
+	__le64 buffer_addr;
+	__le32 word2;
+	__le32 word3;
+};
+
+/* how about 0x2000 */
+#define MAX_TX_BUF_LEN      0x2000
+#define MAX_TX_BUF_SHIFT    13
+#define MAX_TSO_SEG_SIZE    0x3c00
+
+/* rrs word 1 bit 0:31 */
+#define RRS_RX_CSUM_MASK	0xFFFF
+#define RRS_RX_CSUM_SHIFT	0
+#define RRS_PKT_SIZE_MASK	0x3FFF
+#define RRS_PKT_SIZE_SHIFT	16
+#define RRS_CPU_NUM_MASK	0x0003
+#define	RRS_CPU_NUM_SHIFT	30
+
+#define	RRS_IS_RSS_IPV4		0x0001
+#define RRS_IS_RSS_IPV4_TCP	0x0002
+#define RRS_IS_RSS_IPV6		0x0004
+#define RRS_IS_RSS_IPV6_TCP	0x0008
+#define RRS_IS_IPV6		0x0010
+#define RRS_IS_IP_FRAG		0x0020
+#define RRS_IS_IP_DF		0x0040
+#define RRS_IS_802_3		0x0080
+#define RRS_IS_VLAN_TAG		0x0100
+#define RRS_IS_ERR_FRAME	0x0200
+#define RRS_IS_IPV4		0x0400
+#define RRS_IS_UDP		0x0800
+#define RRS_IS_TCP		0x1000
+#define RRS_IS_BCAST		0x2000
+#define RRS_IS_MCAST		0x4000
+#define RRS_IS_PAUSE		0x8000
+
+#define RRS_ERR_BAD_CRC		0x0001
+#define RRS_ERR_CODE		0x0002
+#define RRS_ERR_DRIBBLE		0x0004
+#define RRS_ERR_RUNT		0x0008
+#define RRS_ERR_RX_OVERFLOW	0x0010
+#define RRS_ERR_TRUNC		0x0020
+#define RRS_ERR_IP_CSUM		0x0040
+#define RRS_ERR_L4_CSUM		0x0080
+#define RRS_ERR_LENGTH		0x0100
+#define RRS_ERR_DES_ADDR	0x0200
+
+struct atl1e_recv_ret_status {
+	u16 seq_num;
+	u16 hash_lo;
+	__le32	word1;
+	u16 pkt_flag;
+	u16 err_flag;
+	u16 hash_hi;
+	u16 vtag;
+};
+
+enum atl1e_dma_req_block {
+	atl1e_dma_req_128 = 0,
+	atl1e_dma_req_256 = 1,
+	atl1e_dma_req_512 = 2,
+	atl1e_dma_req_1024 = 3,
+	atl1e_dma_req_2048 = 4,
+	atl1e_dma_req_4096 = 5
+};
+
+enum atl1e_rrs_type {
+	atl1e_rrs_disable = 0,
+	atl1e_rrs_ipv4 = 1,
+	atl1e_rrs_ipv4_tcp = 2,
+	atl1e_rrs_ipv6 = 4,
+	atl1e_rrs_ipv6_tcp = 8
+};
+
+enum atl1e_nic_type {
+	athr_l1e = 0,
+	athr_l2e_revA = 1,
+	athr_l2e_revB = 2
+};
+
+struct atl1e_hw_stats {
+	/* rx */
+	unsigned long rx_ok;	      /* The number of good packet received. */
+	unsigned long rx_bcast;       /* The number of good broadcast packet received. */
+	unsigned long rx_mcast;       /* The number of good multicast packet received. */
+	unsigned long rx_pause;       /* The number of Pause packet received. */
+	unsigned long rx_ctrl;        /* The number of Control packet received other than Pause frame. */
+	unsigned long rx_fcs_err;     /* The number of packets with bad FCS. */
+	unsigned long rx_len_err;     /* The number of packets with mismatch of length field and actual size. */
+	unsigned long rx_byte_cnt;    /* The number of bytes of good packet received. FCS is NOT included. */
+	unsigned long rx_runt;        /* The number of packets received that are less than 64 byte long and with good FCS. */
+	unsigned long rx_frag;        /* The number of packets received that are less than 64 byte long and with bad FCS. */
+	unsigned long rx_sz_64;       /* The number of good and bad packets received that are 64 byte long. */
+	unsigned long rx_sz_65_127;   /* The number of good and bad packets received that are between 65 and 127-byte long. */
+	unsigned long rx_sz_128_255;  /* The number of good and bad packets received that are between 128 and 255-byte long. */
+	unsigned long rx_sz_256_511;  /* The number of good and bad packets received that are between 256 and 511-byte long. */
+	unsigned long rx_sz_512_1023; /* The number of good and bad packets received that are between 512 and 1023-byte long. */
+	unsigned long rx_sz_1024_1518;    /* The number of good and bad packets received that are between 1024 and 1518-byte long. */
+	unsigned long rx_sz_1519_max; /* The number of good and bad packets received that are between 1519-byte and MTU. */
+	unsigned long rx_sz_ov;       /* The number of good and bad packets received that are more than MTU size truncated by Selene. */
+	unsigned long rx_rxf_ov;      /* The number of frame dropped due to occurrence of RX FIFO overflow. */
+	unsigned long rx_rrd_ov;      /* The number of frame dropped due to occurrence of RRD overflow. */
+	unsigned long rx_align_err;   /* Alignment Error */
+	unsigned long rx_bcast_byte_cnt;  /* The byte count of broadcast packet received, excluding FCS. */
+	unsigned long rx_mcast_byte_cnt;  /* The byte count of multicast packet received, excluding FCS. */
+	unsigned long rx_err_addr;    /* The number of packets dropped due to address filtering. */
+
+	/* tx */
+	unsigned long tx_ok;      /* The number of good packet transmitted. */
+	unsigned long tx_bcast;       /* The number of good broadcast packet transmitted. */
+	unsigned long tx_mcast;       /* The number of good multicast packet transmitted. */
+	unsigned long tx_pause;       /* The number of Pause packet transmitted. */
+	unsigned long tx_exc_defer;   /* The number of packets transmitted with excessive deferral. */
+	unsigned long tx_ctrl;        /* The number of packets transmitted is a control frame, excluding Pause frame. */
+	unsigned long tx_defer;       /* The number of packets transmitted that is deferred. */
+	unsigned long tx_byte_cnt;    /* The number of bytes of data transmitted. FCS is NOT included. */
+	unsigned long tx_sz_64;       /* The number of good and bad packets transmitted that are 64 byte long. */
+	unsigned long tx_sz_65_127;   /* The number of good and bad packets transmitted that are between 65 and 127-byte long. */
+	unsigned long tx_sz_128_255;  /* The number of good and bad packets transmitted that are between 128 and 255-byte long. */
+	unsigned long tx_sz_256_511;  /* The number of good and bad packets transmitted that are between 256 and 511-byte long. */
+	unsigned long tx_sz_512_1023; /* The number of good and bad packets transmitted that are between 512 and 1023-byte long. */
+	unsigned long tx_sz_1024_1518;    /* The number of good and bad packets transmitted that are between 1024 and 1518-byte long. */
+	unsigned long tx_sz_1519_max; /* The number of good and bad packets transmitted that are between 1519-byte and MTU. */
+	unsigned long tx_1_col;       /* The number of packets subsequently transmitted successfully with a single prior collision. */
+	unsigned long tx_2_col;       /* The number of packets subsequently transmitted successfully with multiple prior collisions. */
+	unsigned long tx_late_col;    /* The number of packets transmitted with late collisions. */
+	unsigned long tx_abort_col;   /* The number of transmit packets aborted due to excessive collisions. */
+	unsigned long tx_underrun;    /* The number of transmit packets aborted due to transmit FIFO underrun, or TRD FIFO underrun */
+	unsigned long tx_rd_eop;      /* The number of times that read beyond the EOP into the next frame area when TRD was not written timely */
+	unsigned long tx_len_err;     /* The number of transmit packets with length field does NOT match the actual frame size. */
+	unsigned long tx_trunc;       /* The number of transmit packets truncated due to size exceeding MTU. */
+	unsigned long tx_bcast_byte;  /* The byte count of broadcast packet transmitted, excluding FCS. */
+	unsigned long tx_mcast_byte;  /* The byte count of multicast packet transmitted, excluding FCS. */
+};
+
+struct atl1e_hw {
+	u8 __iomem      *hw_addr;            /* inner register address */
+	resource_size_t mem_rang;
+	struct atl1e_adapter *adapter;
+	enum atl1e_nic_type  nic_type;
+	u16 device_id;
+	u16 vendor_id;
+	u16 subsystem_id;
+	u16 subsystem_vendor_id;
+	u8  revision_id;
+	u16 pci_cmd_word;
+	u8 mac_addr[ETH_ALEN];
+	u8 perm_mac_addr[ETH_ALEN];
+	u8 preamble_len;
+	u16 max_frame_size;
+	u16 rx_jumbo_th;
+	u16 tx_jumbo_th;
+
+	u16 media_type;
+#define MEDIA_TYPE_AUTO_SENSOR  0
+#define MEDIA_TYPE_100M_FULL    1
+#define MEDIA_TYPE_100M_HALF    2
+#define MEDIA_TYPE_10M_FULL     3
+#define MEDIA_TYPE_10M_HALF     4
+
+	u16 autoneg_advertised;
+#define ADVERTISE_10_HALF               0x0001
+#define ADVERTISE_10_FULL               0x0002
+#define ADVERTISE_100_HALF              0x0004
+#define ADVERTISE_100_FULL              0x0008
+#define ADVERTISE_1000_HALF             0x0010 /* Not used, just FYI */
+#define ADVERTISE_1000_FULL             0x0020
+	u16 mii_autoneg_adv_reg;
+	u16 mii_1000t_ctrl_reg;
+
+	u16 imt;        /* Interrupt Moderator timer ( 2us resolution) */
+	u16 ict;        /* Interrupt Clear timer (2us resolution) */
+	u32 smb_timer;
+	u16 rrd_thresh; /* Threshold of number of RRD produced to trigger
+			  interrupt request */
+	u16 tpd_thresh;
+	u16 rx_count_down; /* 2us resolution */
+	u16 tx_count_down;
+
+	u8 tpd_burst;   /* Number of TPD to prefetch in cache-aligned burst. */
+	enum atl1e_rrs_type rrs_type;
+	u32 base_cpu;
+	u32 indirect_tab;
+
+	enum atl1e_dma_req_block dmar_block;
+	enum atl1e_dma_req_block dmaw_block;
+	u8 dmaw_dly_cnt;
+	u8 dmar_dly_cnt;
+
+	bool phy_configured;
+	bool re_autoneg;
+	bool emi_ca;
+};
+
+/*
+ * wrapper around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer
+ */
+struct atl1e_tx_buffer {
+	struct sk_buff *skb;
+	u16 flags;
+#define ATL1E_TX_PCIMAP_SINGLE		0x0001
+#define ATL1E_TX_PCIMAP_PAGE		0x0002
+#define ATL1E_TX_PCIMAP_TYPE_MASK	0x0003
+	u16 length;
+	dma_addr_t dma;
+};
+
+#define ATL1E_SET_PCIMAP_TYPE(tx_buff, type) do {		\
+	((tx_buff)->flags) &= ~ATL1E_TX_PCIMAP_TYPE_MASK;	\
+	((tx_buff)->flags) |= (type);				\
+	} while (0)
+
+struct atl1e_rx_page {
+	dma_addr_t	dma;    /* receive rage DMA address */
+	u8		*addr;   /* receive rage virtual address */
+	dma_addr_t	write_offset_dma;  /* the DMA address which contain the
+					      receive data offset in the page */
+	u32		*write_offset_addr; /* the virtaul address which contain
+					     the receive data offset in the page */
+	u32		read_offset;       /* the offset where we have read */
+};
+
+struct atl1e_rx_page_desc {
+	struct atl1e_rx_page   rx_page[AT_PAGE_NUM_PER_QUEUE];
+	u8  rx_using;
+	u16 rx_nxseq;
+};
+
+/* transmit packet descriptor (tpd) ring */
+struct atl1e_tx_ring {
+	struct atl1e_tpd_desc *desc;  /* descriptor ring virtual address  */
+	dma_addr_t	   dma;    /* descriptor ring physical address */
+	u16       	   count;  /* the count of transmit rings  */
+	rwlock_t	   tx_lock;
+	u16		   next_to_use;
+	atomic_t	   next_to_clean;
+	struct atl1e_tx_buffer *tx_buffer;
+	dma_addr_t	   cmb_dma;
+	u32		   *cmb;
+};
+
+/* receive packet descriptor ring */
+struct atl1e_rx_ring {
+	void        	*desc;
+	dma_addr_t  	dma;
+	int         	size;
+	u32	    	page_size; /* bytes length of rxf page */
+	u32		real_page_size; /* real_page_size = page_size + jumbo + aliagn */
+	struct atl1e_rx_page_desc	rx_page_desc[AT_MAX_RECEIVE_QUEUE];
+};
+
+/* board specific private data structure */
+struct atl1e_adapter {
+	struct net_device   *netdev;
+	struct pci_dev      *pdev;
+	struct napi_struct  napi;
+	struct mii_if_info  mii;    /* MII interface info */
+	struct atl1e_hw        hw;
+	struct atl1e_hw_stats  hw_stats;
+
+	u32 wol;
+	u16 link_speed;
+	u16 link_duplex;
+
+	spinlock_t mdio_lock;
+	spinlock_t tx_lock;
+	atomic_t irq_sem;
+
+	struct work_struct reset_task;
+	struct work_struct link_chg_task;
+	struct timer_list watchdog_timer;
+	struct timer_list phy_config_timer;
+
+	/* All Descriptor memory */
+	dma_addr_t  	ring_dma;
+	void     	*ring_vir_addr;
+	u32             ring_size;
+
+	struct atl1e_tx_ring tx_ring;
+	struct atl1e_rx_ring rx_ring;
+	int num_rx_queues;
+	unsigned long flags;
+#define __AT_TESTING        0x0001
+#define __AT_RESETTING      0x0002
+#define __AT_DOWN           0x0003
+
+	u32 bd_number;     /* board number;*/
+	u32 pci_state[16];
+	u32 *config_space;
+};
+
+#define AT_WRITE_REG(a, reg, value) ( \
+		writel((value), ((a)->hw_addr + reg)))
+
+#define AT_WRITE_FLUSH(a) (\
+		readl((a)->hw_addr))
+
+#define AT_READ_REG(a, reg) ( \
+		readl((a)->hw_addr + reg))
+
+#define AT_WRITE_REGB(a, reg, value) (\
+		writeb((value), ((a)->hw_addr + reg)))
+
+#define AT_READ_REGB(a, reg) (\
+		readb((a)->hw_addr + reg))
+
+#define AT_WRITE_REGW(a, reg, value) (\
+		writew((value), ((a)->hw_addr + reg)))
+
+#define AT_READ_REGW(a, reg) (\
+		readw((a)->hw_addr + reg))
+
+#define AT_WRITE_REG_ARRAY(a, reg, offset, value) ( \
+		writel((value), (((a)->hw_addr + reg) + ((offset) << 2))))
+
+#define AT_READ_REG_ARRAY(a, reg, offset) ( \
+		readl(((a)->hw_addr + reg) + ((offset) << 2)))
+
+extern char atl1e_driver_name[];
+extern char atl1e_driver_version[];
+
+extern void atl1e_check_options(struct atl1e_adapter *adapter);
+extern int atl1e_up(struct atl1e_adapter *adapter);
+extern void atl1e_down(struct atl1e_adapter *adapter);
+extern void atl1e_reinit_locked(struct atl1e_adapter *adapter);
+extern s32 atl1e_reset_hw(struct atl1e_hw *hw);
+extern void atl1e_set_ethtool_ops(struct net_device *netdev);
+#endif /* _ATL1_E_H_ */

addons/atl1e/src/3.10.108/atl1e_ethtool.c

@@ -0,0 +1,392 @@
+/*
+ * Copyright(c) 2007 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/slab.h>
+
+#include "atl1e.h"
+
+static int atl1e_get_settings(struct net_device *netdev,
+			      struct ethtool_cmd *ecmd)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+	struct atl1e_hw *hw = &adapter->hw;
+
+	ecmd->supported = (SUPPORTED_10baseT_Half  |
+			   SUPPORTED_10baseT_Full  |
+			   SUPPORTED_100baseT_Half |
+			   SUPPORTED_100baseT_Full |
+			   SUPPORTED_Autoneg       |
+			   SUPPORTED_TP);
+	if (hw->nic_type == athr_l1e)
+		ecmd->supported |= SUPPORTED_1000baseT_Full;
+
+	ecmd->advertising = ADVERTISED_TP;
+
+	ecmd->advertising |= ADVERTISED_Autoneg;
+	ecmd->advertising |= hw->autoneg_advertised;
+
+	ecmd->port = PORT_TP;
+	ecmd->phy_address = 0;
+	ecmd->transceiver = XCVR_INTERNAL;
+
+	if (adapter->link_speed != SPEED_0) {
+		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+		if (adapter->link_duplex == FULL_DUPLEX)
+			ecmd->duplex = DUPLEX_FULL;
+		else
+			ecmd->duplex = DUPLEX_HALF;
+	} else {
+		ethtool_cmd_speed_set(ecmd, -1);
+		ecmd->duplex = -1;
+	}
+
+	ecmd->autoneg = AUTONEG_ENABLE;
+	return 0;
+}
+
+static int atl1e_set_settings(struct net_device *netdev,
+			      struct ethtool_cmd *ecmd)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+	struct atl1e_hw *hw = &adapter->hw;
+
+	while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
+		msleep(1);
+
+	if (ecmd->autoneg == AUTONEG_ENABLE) {
+		u16 adv4, adv9;
+
+		if ((ecmd->advertising&ADVERTISE_1000_FULL)) {
+			if (hw->nic_type == athr_l1e) {
+				hw->autoneg_advertised =
+					ecmd->advertising & AT_ADV_MASK;
+			} else {
+				clear_bit(__AT_RESETTING, &adapter->flags);
+				return -EINVAL;
+			}
+		} else if (ecmd->advertising&ADVERTISE_1000_HALF) {
+			clear_bit(__AT_RESETTING, &adapter->flags);
+			return -EINVAL;
+		} else {
+			hw->autoneg_advertised =
+				ecmd->advertising & AT_ADV_MASK;
+		}
+		ecmd->advertising = hw->autoneg_advertised |
+				    ADVERTISED_TP | ADVERTISED_Autoneg;
+
+		adv4 = hw->mii_autoneg_adv_reg & ~ADVERTISE_ALL;
+		adv9 = hw->mii_1000t_ctrl_reg & ~MII_AT001_CR_1000T_SPEED_MASK;
+		if (hw->autoneg_advertised & ADVERTISE_10_HALF)
+			adv4 |= ADVERTISE_10HALF;
+		if (hw->autoneg_advertised & ADVERTISE_10_FULL)
+			adv4 |= ADVERTISE_10FULL;
+		if (hw->autoneg_advertised & ADVERTISE_100_HALF)
+			adv4 |= ADVERTISE_100HALF;
+		if (hw->autoneg_advertised & ADVERTISE_100_FULL)
+			adv4 |= ADVERTISE_100FULL;
+		if (hw->autoneg_advertised & ADVERTISE_1000_FULL)
+			adv9 |= ADVERTISE_1000FULL;
+
+		if (adv4 != hw->mii_autoneg_adv_reg ||
+				adv9 != hw->mii_1000t_ctrl_reg) {
+			hw->mii_autoneg_adv_reg = adv4;
+			hw->mii_1000t_ctrl_reg = adv9;
+			hw->re_autoneg = true;
+		}
+
+	} else {
+		clear_bit(__AT_RESETTING, &adapter->flags);
+		return -EINVAL;
+	}
+
+	/* reset the link */
+
+	if (netif_running(adapter->netdev)) {
+		atl1e_down(adapter);
+		atl1e_up(adapter);
+	} else
+		atl1e_reset_hw(&adapter->hw);
+
+	clear_bit(__AT_RESETTING, &adapter->flags);
+	return 0;
+}
+
+static u32 atl1e_get_msglevel(struct net_device *netdev)
+{
+#ifdef DBG
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+static int atl1e_get_regs_len(struct net_device *netdev)
+{
+	return AT_REGS_LEN * sizeof(u32);
+}
+
+static void atl1e_get_regs(struct net_device *netdev,
+			   struct ethtool_regs *regs, void *p)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+	struct atl1e_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+	u16 phy_data;
+
+	memset(p, 0, AT_REGS_LEN * sizeof(u32));
+
+	regs->version = (1 << 24) | (hw->revision_id << 16) | hw->device_id;
+
+	regs_buff[0]  = AT_READ_REG(hw, REG_VPD_CAP);
+	regs_buff[1]  = AT_READ_REG(hw, REG_SPI_FLASH_CTRL);
+	regs_buff[2]  = AT_READ_REG(hw, REG_SPI_FLASH_CONFIG);
+	regs_buff[3]  = AT_READ_REG(hw, REG_TWSI_CTRL);
+	regs_buff[4]  = AT_READ_REG(hw, REG_PCIE_DEV_MISC_CTRL);
+	regs_buff[5]  = AT_READ_REG(hw, REG_MASTER_CTRL);
+	regs_buff[6]  = AT_READ_REG(hw, REG_MANUAL_TIMER_INIT);
+	regs_buff[7]  = AT_READ_REG(hw, REG_IRQ_MODU_TIMER_INIT);
+	regs_buff[8]  = AT_READ_REG(hw, REG_GPHY_CTRL);
+	regs_buff[9]  = AT_READ_REG(hw, REG_CMBDISDMA_TIMER);
+	regs_buff[10] = AT_READ_REG(hw, REG_IDLE_STATUS);
+	regs_buff[11] = AT_READ_REG(hw, REG_MDIO_CTRL);
+	regs_buff[12] = AT_READ_REG(hw, REG_SERDES_LOCK);
+	regs_buff[13] = AT_READ_REG(hw, REG_MAC_CTRL);
+	regs_buff[14] = AT_READ_REG(hw, REG_MAC_IPG_IFG);
+	regs_buff[15] = AT_READ_REG(hw, REG_MAC_STA_ADDR);
+	regs_buff[16] = AT_READ_REG(hw, REG_MAC_STA_ADDR+4);
+	regs_buff[17] = AT_READ_REG(hw, REG_RX_HASH_TABLE);
+	regs_buff[18] = AT_READ_REG(hw, REG_RX_HASH_TABLE+4);
+	regs_buff[19] = AT_READ_REG(hw, REG_MAC_HALF_DUPLX_CTRL);
+	regs_buff[20] = AT_READ_REG(hw, REG_MTU);
+	regs_buff[21] = AT_READ_REG(hw, REG_WOL_CTRL);
+	regs_buff[22] = AT_READ_REG(hw, REG_SRAM_TRD_ADDR);
+	regs_buff[23] = AT_READ_REG(hw, REG_SRAM_TRD_LEN);
+	regs_buff[24] = AT_READ_REG(hw, REG_SRAM_RXF_ADDR);
+	regs_buff[25] = AT_READ_REG(hw, REG_SRAM_RXF_LEN);
+	regs_buff[26] = AT_READ_REG(hw, REG_SRAM_TXF_ADDR);
+	regs_buff[27] = AT_READ_REG(hw, REG_SRAM_TXF_LEN);
+	regs_buff[28] = AT_READ_REG(hw, REG_SRAM_TCPH_ADDR);
+	regs_buff[29] = AT_READ_REG(hw, REG_SRAM_PKTH_ADDR);
+
+	atl1e_read_phy_reg(hw, MII_BMCR, &phy_data);
+	regs_buff[73] = (u32)phy_data;
+	atl1e_read_phy_reg(hw, MII_BMSR, &phy_data);
+	regs_buff[74] = (u32)phy_data;
+}
+
+static int atl1e_get_eeprom_len(struct net_device *netdev)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+
+	if (!atl1e_check_eeprom_exist(&adapter->hw))
+		return AT_EEPROM_LEN;
+	else
+		return 0;
+}
+
+static int atl1e_get_eeprom(struct net_device *netdev,
+		struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+	struct atl1e_hw *hw = &adapter->hw;
+	u32 *eeprom_buff;
+	int first_dword, last_dword;
+	int ret_val = 0;
+	int i;
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	if (atl1e_check_eeprom_exist(hw)) /* not exist */
+		return -EINVAL;
+
+	eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+	first_dword = eeprom->offset >> 2;
+	last_dword = (eeprom->offset + eeprom->len - 1) >> 2;
+
+	eeprom_buff = kmalloc(sizeof(u32) *
+			(last_dword - first_dword + 1), GFP_KERNEL);
+	if (eeprom_buff == NULL)
+		return -ENOMEM;
+
+	for (i = first_dword; i < last_dword; i++) {
+		if (!atl1e_read_eeprom(hw, i * 4, &(eeprom_buff[i-first_dword]))) {
+			kfree(eeprom_buff);
+			return -EIO;
+		}
+	}
+
+	memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 3),
+			eeprom->len);
+	kfree(eeprom_buff);
+
+	return ret_val;
+}
+
+static int atl1e_set_eeprom(struct net_device *netdev,
+			    struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+	struct atl1e_hw *hw = &adapter->hw;
+	u32 *eeprom_buff;
+	u32 *ptr;
+	int first_dword, last_dword;
+	int ret_val = 0;
+	int i;
+
+	if (eeprom->len == 0)
+		return -EOPNOTSUPP;
+
+	if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16)))
+		return -EINVAL;
+
+	first_dword = eeprom->offset >> 2;
+	last_dword = (eeprom->offset + eeprom->len - 1) >> 2;
+	eeprom_buff = kmalloc(AT_EEPROM_LEN, GFP_KERNEL);
+	if (eeprom_buff == NULL)
+		return -ENOMEM;
+
+	ptr = eeprom_buff;
+
+	if (eeprom->offset & 3) {
+		/* need read/modify/write of first changed EEPROM word */
+		/* only the second byte of the word is being modified */
+		if (!atl1e_read_eeprom(hw, first_dword * 4, &(eeprom_buff[0]))) {
+			ret_val = -EIO;
+			goto out;
+		}
+		ptr++;
+	}
+	if (((eeprom->offset + eeprom->len) & 3)) {
+		/* need read/modify/write of last changed EEPROM word */
+		/* only the first byte of the word is being modified */
+
+		if (!atl1e_read_eeprom(hw, last_dword * 4,
+				&(eeprom_buff[last_dword - first_dword]))) {
+			ret_val = -EIO;
+			goto out;
+		}
+	}
+
+	/* Device's eeprom is always little-endian, word addressable */
+	memcpy(ptr, bytes, eeprom->len);
+
+	for (i = 0; i < last_dword - first_dword + 1; i++) {
+		if (!atl1e_write_eeprom(hw, ((first_dword + i) * 4),
+				  eeprom_buff[i])) {
+			ret_val = -EIO;
+			goto out;
+		}
+	}
+out:
+	kfree(eeprom_buff);
+	return ret_val;
+}
+
+static void atl1e_get_drvinfo(struct net_device *netdev,
+		struct ethtool_drvinfo *drvinfo)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver,  atl1e_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, atl1e_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->fw_version, "L1e", sizeof(drvinfo->fw_version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
+	drvinfo->n_stats = 0;
+	drvinfo->testinfo_len = 0;
+	drvinfo->regdump_len = atl1e_get_regs_len(netdev);
+	drvinfo->eedump_len = atl1e_get_eeprom_len(netdev);
+}
+
+static void atl1e_get_wol(struct net_device *netdev,
+			  struct ethtool_wolinfo *wol)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+
+	wol->supported = WAKE_MAGIC | WAKE_PHY;
+	wol->wolopts = 0;
+
+	if (adapter->wol & AT_WUFC_EX)
+		wol->wolopts |= WAKE_UCAST;
+	if (adapter->wol & AT_WUFC_MC)
+		wol->wolopts |= WAKE_MCAST;
+	if (adapter->wol & AT_WUFC_BC)
+		wol->wolopts |= WAKE_BCAST;
+	if (adapter->wol & AT_WUFC_MAG)
+		wol->wolopts |= WAKE_MAGIC;
+	if (adapter->wol & AT_WUFC_LNKC)
+		wol->wolopts |= WAKE_PHY;
+}
+
+static int atl1e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+
+	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE |
+			    WAKE_UCAST | WAKE_MCAST | WAKE_BCAST))
+		return -EOPNOTSUPP;
+	/* these settings will always override what we currently have */
+	adapter->wol = 0;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		adapter->wol |= AT_WUFC_MAG;
+	if (wol->wolopts & WAKE_PHY)
+		adapter->wol |= AT_WUFC_LNKC;
+
+	device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol);
+
+	return 0;
+}
+
+static int atl1e_nway_reset(struct net_device *netdev)
+{
+	struct atl1e_adapter *adapter = netdev_priv(netdev);
+	if (netif_running(netdev))
+		atl1e_reinit_locked(adapter);
+	return 0;
+}
+
+static const struct ethtool_ops atl1e_ethtool_ops = {
+	.get_settings           = atl1e_get_settings,
+	.set_settings           = atl1e_set_settings,
+	.get_drvinfo            = atl1e_get_drvinfo,
+	.get_regs_len           = atl1e_get_regs_len,
+	.get_regs               = atl1e_get_regs,
+	.get_wol                = atl1e_get_wol,
+	.set_wol                = atl1e_set_wol,
+	.get_msglevel           = atl1e_get_msglevel,
+	.nway_reset             = atl1e_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_eeprom_len         = atl1e_get_eeprom_len,
+	.get_eeprom             = atl1e_get_eeprom,
+	.set_eeprom             = atl1e_set_eeprom,
+};
+
+void atl1e_set_ethtool_ops(struct net_device *netdev)
+{
+	SET_ETHTOOL_OPS(netdev, &atl1e_ethtool_ops);
+}

addons/atl1e/src/3.10.108/atl1e_hw.c

@@ -0,0 +1,651 @@
+/*
+ * Copyright(c) 2007 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/mii.h>
+#include <linux/crc32.h>
+
+#include "atl1e.h"
+
+/*
+ * check_eeprom_exist
+ * return 0 if eeprom exist
+ */
+int atl1e_check_eeprom_exist(struct atl1e_hw *hw)
+{
+	u32 value;
+
+	value = AT_READ_REG(hw, REG_SPI_FLASH_CTRL);
+	if (value & SPI_FLASH_CTRL_EN_VPD) {
+		value &= ~SPI_FLASH_CTRL_EN_VPD;
+		AT_WRITE_REG(hw, REG_SPI_FLASH_CTRL, value);
+	}
+	value = AT_READ_REGW(hw, REG_PCIE_CAP_LIST);
+	return ((value & 0xFF00) == 0x6C00) ? 0 : 1;
+}
+
+void atl1e_hw_set_mac_addr(struct atl1e_hw *hw)
+{
+	u32 value;
+	/*
+	 * 00-0B-6A-F6-00-DC
+	 * 0:  6AF600DC 1: 000B
+	 * low dword
+	 */
+	value = (((u32)hw->mac_addr[2]) << 24) |
+		(((u32)hw->mac_addr[3]) << 16) |
+		(((u32)hw->mac_addr[4]) << 8)  |
+		(((u32)hw->mac_addr[5])) ;
+	AT_WRITE_REG_ARRAY(hw, REG_MAC_STA_ADDR, 0, value);
+	/* hight dword */
+	value = (((u32)hw->mac_addr[0]) << 8) |
+		(((u32)hw->mac_addr[1])) ;
+	AT_WRITE_REG_ARRAY(hw, REG_MAC_STA_ADDR, 1, value);
+}
+
+/*
+ * atl1e_get_permanent_address
+ * return 0 if get valid mac address,
+ */
+static int atl1e_get_permanent_address(struct atl1e_hw *hw)
+{
+	u32 addr[2];
+	u32 i;
+	u32 twsi_ctrl_data;
+	u8  eth_addr[ETH_ALEN];
+
+	if (is_valid_ether_addr(hw->perm_mac_addr))
+		return 0;
+
+	/* init */
+	addr[0] = addr[1] = 0;
+
+	if (!atl1e_check_eeprom_exist(hw)) {
+		/* eeprom exist */
+		twsi_ctrl_data = AT_READ_REG(hw, REG_TWSI_CTRL);
+		twsi_ctrl_data |= TWSI_CTRL_SW_LDSTART;
+		AT_WRITE_REG(hw, REG_TWSI_CTRL, twsi_ctrl_data);
+		for (i = 0; i < AT_TWSI_EEPROM_TIMEOUT; i++) {
+			msleep(10);
+			twsi_ctrl_data = AT_READ_REG(hw, REG_TWSI_CTRL);
+			if ((twsi_ctrl_data & TWSI_CTRL_SW_LDSTART) == 0)
+				break;
+		}
+		if (i >= AT_TWSI_EEPROM_TIMEOUT)
+			return AT_ERR_TIMEOUT;
+	}
+
+	/* maybe MAC-address is from BIOS */
+	addr[0] = AT_READ_REG(hw, REG_MAC_STA_ADDR);
+	addr[1] = AT_READ_REG(hw, REG_MAC_STA_ADDR + 4);
+	*(u32 *) &eth_addr[2] = swab32(addr[0]);
+	*(u16 *) &eth_addr[0] = swab16(*(u16 *)&addr[1]);
+
+	if (is_valid_ether_addr(eth_addr)) {
+		memcpy(hw->perm_mac_addr, eth_addr, ETH_ALEN);
+		return 0;
+	}
+
+	return AT_ERR_EEPROM;
+}
+
+bool atl1e_write_eeprom(struct atl1e_hw *hw, u32 offset, u32 value)
+{
+	return true;
+}
+
+bool atl1e_read_eeprom(struct atl1e_hw *hw, u32 offset, u32 *p_value)
+{
+	int i;
+	u32 control;
+
+	if (offset & 3)
+		return false; /* address do not align */
+
+	AT_WRITE_REG(hw, REG_VPD_DATA, 0);
+	control = (offset & VPD_CAP_VPD_ADDR_MASK) << VPD_CAP_VPD_ADDR_SHIFT;
+	AT_WRITE_REG(hw, REG_VPD_CAP, control);
+
+	for (i = 0; i < 10; i++) {
+		msleep(2);
+		control = AT_READ_REG(hw, REG_VPD_CAP);
+		if (control & VPD_CAP_VPD_FLAG)
+			break;
+	}
+	if (control & VPD_CAP_VPD_FLAG) {
+		*p_value = AT_READ_REG(hw, REG_VPD_DATA);
+		return true;
+	}
+	return false; /* timeout */
+}
+
+void atl1e_force_ps(struct atl1e_hw *hw)
+{
+	AT_WRITE_REGW(hw, REG_GPHY_CTRL,
+			GPHY_CTRL_PW_WOL_DIS | GPHY_CTRL_EXT_RESET);
+}
+
+/*
+ * Reads the adapter's MAC address from the EEPROM
+ *
+ * hw - Struct containing variables accessed by shared code
+ */
+int atl1e_read_mac_addr(struct atl1e_hw *hw)
+{
+	int err = 0;
+
+	err = atl1e_get_permanent_address(hw);
+	if (err)
+		return AT_ERR_EEPROM;
+	memcpy(hw->mac_addr, hw->perm_mac_addr, sizeof(hw->perm_mac_addr));
+	return 0;
+}
+
+/*
+ * atl1e_hash_mc_addr
+ *  purpose
+ *      set hash value for a multicast address
+ */
+u32 atl1e_hash_mc_addr(struct atl1e_hw *hw, u8 *mc_addr)
+{
+	u32 crc32;
+	u32 value = 0;
+	int i;
+
+	crc32 = ether_crc_le(6, mc_addr);
+	for (i = 0; i < 32; i++)
+		value |= (((crc32 >> i) & 1) << (31 - i));
+
+	return value;
+}
+
+/*
+ * Sets the bit in the multicast table corresponding to the hash value.
+ * hw - Struct containing variables accessed by shared code
+ * hash_value - Multicast address hash value
+ */
+void atl1e_hash_set(struct atl1e_hw *hw, u32 hash_value)
+{
+	u32 hash_bit, hash_reg;
+	u32 mta;
+
+	/*
+	 * The HASH Table  is a register array of 2 32-bit registers.
+	 * It is treated like an array of 64 bits.  We want to set
+	 * bit BitArray[hash_value]. So we figure out what register
+	 * the bit is in, read it, OR in the new bit, then write
+	 * back the new value.  The register is determined by the
+	 * upper 7 bits of the hash value and the bit within that
+	 * register are determined by the lower 5 bits of the value.
+	 */
+	hash_reg = (hash_value >> 31) & 0x1;
+	hash_bit = (hash_value >> 26) & 0x1F;
+
+	mta = AT_READ_REG_ARRAY(hw, REG_RX_HASH_TABLE, hash_reg);
+
+	mta |= (1 << hash_bit);
+
+	AT_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, hash_reg, mta);
+}
+/*
+ * Reads the value from a PHY register
+ * hw - Struct containing variables accessed by shared code
+ * reg_addr - address of the PHY register to read
+ */
+int atl1e_read_phy_reg(struct atl1e_hw *hw, u16 reg_addr, u16 *phy_data)
+{
+	u32 val;
+	int i;
+
+	val = ((u32)(reg_addr & MDIO_REG_ADDR_MASK)) << MDIO_REG_ADDR_SHIFT |
+		MDIO_START | MDIO_SUP_PREAMBLE | MDIO_RW |
+		MDIO_CLK_25_4 << MDIO_CLK_SEL_SHIFT;
+
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+
+	wmb();
+
+	for (i = 0; i < MDIO_WAIT_TIMES; i++) {
+		udelay(2);
+		val = AT_READ_REG(hw, REG_MDIO_CTRL);
+		if (!(val & (MDIO_START | MDIO_BUSY)))
+			break;
+		wmb();
+	}
+	if (!(val & (MDIO_START | MDIO_BUSY))) {
+		*phy_data = (u16)val;
+		return 0;
+	}
+
+	return AT_ERR_PHY;
+}
+
+/*
+ * Writes a value to a PHY register
+ * hw - Struct containing variables accessed by shared code
+ * reg_addr - address of the PHY register to write
+ * data - data to write to the PHY
+ */
+int atl1e_write_phy_reg(struct atl1e_hw *hw, u32 reg_addr, u16 phy_data)
+{
+	int i;
+	u32 val;
+
+	val = ((u32)(phy_data & MDIO_DATA_MASK)) << MDIO_DATA_SHIFT |
+	       (reg_addr&MDIO_REG_ADDR_MASK) << MDIO_REG_ADDR_SHIFT |
+	       MDIO_SUP_PREAMBLE |
+	       MDIO_START |
+	       MDIO_CLK_25_4 << MDIO_CLK_SEL_SHIFT;
+
+	AT_WRITE_REG(hw, REG_MDIO_CTRL, val);
+	wmb();
+
+	for (i = 0; i < MDIO_WAIT_TIMES; i++) {
+		udelay(2);
+		val = AT_READ_REG(hw, REG_MDIO_CTRL);
+		if (!(val & (MDIO_START | MDIO_BUSY)))
+			break;
+		wmb();
+	}
+
+	if (!(val & (MDIO_START | MDIO_BUSY)))
+		return 0;
+
+	return AT_ERR_PHY;
+}
+
+/*
+ * atl1e_init_pcie - init PCIE module
+ */
+static void atl1e_init_pcie(struct atl1e_hw *hw)
+{
+	u32 value;
+	/* comment 2lines below to save more power when sususpend
+	   value = LTSSM_TEST_MODE_DEF;
+	   AT_WRITE_REG(hw, REG_LTSSM_TEST_MODE, value);
+	 */
+
+	/* pcie flow control mode change */
+	value = AT_READ_REG(hw, 0x1008);
+	value |= 0x8000;
+	AT_WRITE_REG(hw, 0x1008, value);
+}
+/*
+ * Configures PHY autoneg and flow control advertisement settings
+ *
+ * hw - Struct containing variables accessed by shared code
+ */
+static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw)
+{
+	s32 ret_val;
+	u16 mii_autoneg_adv_reg;
+	u16 mii_1000t_ctrl_reg;
+
+	if (0 != hw->mii_autoneg_adv_reg)
+		return 0;
+	/* Read the MII Auto-Neg Advertisement Register (Address 4/9). */
+	mii_autoneg_adv_reg = MII_AR_DEFAULT_CAP_MASK;
+	mii_1000t_ctrl_reg  = MII_AT001_CR_1000T_DEFAULT_CAP_MASK;
+
+	/*
+	 * Need to parse autoneg_advertised  and set up
+	 * the appropriate PHY registers.  First we will parse for
+	 * autoneg_advertised software override.  Since we can advertise
+	 * a plethora of combinations, we need to check each bit
+	 * individually.
+	 */
+
+	/*
+	 * First we clear all the 10/100 mb speed bits in the Auto-Neg
+	 * Advertisement Register (Address 4) and the 1000 mb speed bits in
+	 * the  1000Base-T control Register (Address 9).
+	 */
+	mii_autoneg_adv_reg &= ~ADVERTISE_ALL;
+	mii_1000t_ctrl_reg  &= ~MII_AT001_CR_1000T_SPEED_MASK;
+
+	/*
+	 * Need to parse MediaType and setup the
+	 * appropriate PHY registers.
+	 */
+	switch (hw->media_type) {
+	case MEDIA_TYPE_AUTO_SENSOR:
+		mii_autoneg_adv_reg |= ADVERTISE_ALL;
+		hw->autoneg_advertised = ADVERTISE_ALL;
+		if (hw->nic_type == athr_l1e) {
+			mii_1000t_ctrl_reg |= ADVERTISE_1000FULL;
+			hw->autoneg_advertised |= ADVERTISE_1000_FULL;
+		}
+		break;
+
+	case MEDIA_TYPE_100M_FULL:
+		mii_autoneg_adv_reg   |= ADVERTISE_100FULL;
+		hw->autoneg_advertised = ADVERTISE_100_FULL;
+		break;
+
+	case MEDIA_TYPE_100M_HALF:
+		mii_autoneg_adv_reg   |= ADVERTISE_100_HALF;
+		hw->autoneg_advertised = ADVERTISE_100_HALF;
+		break;
+
+	case MEDIA_TYPE_10M_FULL:
+		mii_autoneg_adv_reg   |= ADVERTISE_10_FULL;
+		hw->autoneg_advertised = ADVERTISE_10_FULL;
+		break;
+
+	default:
+		mii_autoneg_adv_reg   |= ADVERTISE_10_HALF;
+		hw->autoneg_advertised = ADVERTISE_10_HALF;
+		break;
+	}
+
+	/* flow control fixed to enable all */
+	mii_autoneg_adv_reg |= (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP);
+
+	hw->mii_autoneg_adv_reg = mii_autoneg_adv_reg;
+	hw->mii_1000t_ctrl_reg  = mii_1000t_ctrl_reg;
+
+	ret_val = atl1e_write_phy_reg(hw, MII_ADVERTISE, mii_autoneg_adv_reg);
+	if (ret_val)
+		return ret_val;
+
+	if (hw->nic_type == athr_l1e || hw->nic_type == athr_l2e_revA) {
+		ret_val = atl1e_write_phy_reg(hw, MII_CTRL1000,
+					   mii_1000t_ctrl_reg);
+		if (ret_val)
+			return ret_val;
+	}
+
+	return 0;
+}
+
+
+/*
+ * Resets the PHY and make all config validate
+ *
+ * hw - Struct containing variables accessed by shared code
+ *
+ * Sets bit 15 and 12 of the MII control regiser (for F001 bug)
+ */
+int atl1e_phy_commit(struct atl1e_hw *hw)
+{
+	struct atl1e_adapter *adapter = hw->adapter;
+	int ret_val;
+	u16 phy_data;
+
+	phy_data = BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART;
+
+	ret_val = atl1e_write_phy_reg(hw, MII_BMCR, phy_data);
+	if (ret_val) {
+		u32 val;
+		int i;
+		/**************************************
+		 * pcie serdes link may be down !
+		 **************************************/
+		for (i = 0; i < 25; i++) {
+			msleep(1);
+			val = AT_READ_REG(hw, REG_MDIO_CTRL);
+			if (!(val & (MDIO_START | MDIO_BUSY)))
+				break;
+		}
+
+		if (0 != (val & (MDIO_START | MDIO_BUSY))) {
+			netdev_err(adapter->netdev,
+				   "pcie linkdown at least for 25ms\n");
+			return ret_val;
+		}
+
+		netdev_err(adapter->netdev, "pcie linkup after %d ms\n", i);
+	}
+	return 0;
+}
+
+int atl1e_phy_init(struct atl1e_hw *hw)
+{
+	struct atl1e_adapter *adapter = hw->adapter;
+	s32 ret_val;
+	u16 phy_val;
+
+	if (hw->phy_configured) {
+		if (hw->re_autoneg) {
+			hw->re_autoneg = false;
+			return atl1e_restart_autoneg(hw);
+		}
+		return 0;
+	}
+
+	/* RESET GPHY Core */
+	AT_WRITE_REGW(hw, REG_GPHY_CTRL, GPHY_CTRL_DEFAULT);
+	msleep(2);
+	AT_WRITE_REGW(hw, REG_GPHY_CTRL, GPHY_CTRL_DEFAULT |
+		      GPHY_CTRL_EXT_RESET);
+	msleep(2);
+
+	/* patches */
+	/* p1. eable hibernation mode */
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_ADDR, 0xB);
+	if (ret_val)
+		return ret_val;
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_DATA, 0xBC00);
+	if (ret_val)
+		return ret_val;
+	/* p2. set Class A/B for all modes */
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_ADDR, 0);
+	if (ret_val)
+		return ret_val;
+	phy_val = 0x02ef;
+	/* remove Class AB */
+	/* phy_val = hw->emi_ca ? 0x02ef : 0x02df; */
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_DATA, phy_val);
+	if (ret_val)
+		return ret_val;
+	/* p3. 10B ??? */
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_ADDR, 0x12);
+	if (ret_val)
+		return ret_val;
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_DATA, 0x4C04);
+	if (ret_val)
+		return ret_val;
+	/* p4. 1000T power */
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_ADDR, 0x4);
+	if (ret_val)
+		return ret_val;
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_DATA, 0x8BBB);
+	if (ret_val)
+		return ret_val;
+
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_ADDR, 0x5);
+	if (ret_val)
+		return ret_val;
+	ret_val = atl1e_write_phy_reg(hw, MII_DBG_DATA, 0x2C46);
+	if (ret_val)
+		return ret_val;
+
+	msleep(1);
+
+	/*Enable PHY LinkChange Interrupt */
+	ret_val = atl1e_write_phy_reg(hw, MII_INT_CTRL, 0xC00);
+	if (ret_val) {
+		netdev_err(adapter->netdev,
+			   "Error enable PHY linkChange Interrupt\n");
+		return ret_val;
+	}
+	/* setup AutoNeg parameters */
+	ret_val = atl1e_phy_setup_autoneg_adv(hw);
+	if (ret_val) {
+		netdev_err(adapter->netdev,
+			   "Error Setting up Auto-Negotiation\n");
+		return ret_val;
+	}
+	/* SW.Reset & En-Auto-Neg to restart Auto-Neg*/
+	netdev_dbg(adapter->netdev, "Restarting Auto-Negotiation\n");
+	ret_val = atl1e_phy_commit(hw);
+	if (ret_val) {
+		netdev_err(adapter->netdev, "Error resetting the phy\n");
+		return ret_val;
+	}
+
+	hw->phy_configured = true;
+
+	return 0;
+}
+
+/*
+ * Reset the transmit and receive units; mask and clear all interrupts.
+ * hw - Struct containing variables accessed by shared code
+ * return : 0  or  idle status (if error)
+ */
+int atl1e_reset_hw(struct atl1e_hw *hw)
+{
+	struct atl1e_adapter *adapter = hw->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+
+	u32 idle_status_data = 0;
+	u16 pci_cfg_cmd_word = 0;
+	int timeout = 0;
+
+	/* Workaround for PCI problem when BIOS sets MMRBC incorrectly. */
+	pci_read_config_word(pdev, PCI_REG_COMMAND, &pci_cfg_cmd_word);
+	if ((pci_cfg_cmd_word & (CMD_IO_SPACE |
+				CMD_MEMORY_SPACE | CMD_BUS_MASTER))
+			!= (CMD_IO_SPACE | CMD_MEMORY_SPACE | CMD_BUS_MASTER)) {
+		pci_cfg_cmd_word |= (CMD_IO_SPACE |
+				     CMD_MEMORY_SPACE | CMD_BUS_MASTER);
+		pci_write_config_word(pdev, PCI_REG_COMMAND, pci_cfg_cmd_word);
+	}
+
+	/*
+	 * Issue Soft Reset to the MAC.  This will reset the chip's
+	 * transmit, receive, DMA.  It will not effect
+	 * the current PCI configuration.  The global reset bit is self-
+	 * clearing, and should clear within a microsecond.
+	 */
+	AT_WRITE_REG(hw, REG_MASTER_CTRL,
+			MASTER_CTRL_LED_MODE | MASTER_CTRL_SOFT_RST);
+	wmb();
+	msleep(1);
+
+	/* Wait at least 10ms for All module to be Idle */
+	for (timeout = 0; timeout < AT_HW_MAX_IDLE_DELAY; timeout++) {
+		idle_status_data = AT_READ_REG(hw, REG_IDLE_STATUS);
+		if (idle_status_data == 0)
+			break;
+		msleep(1);
+		cpu_relax();
+	}
+
+	if (timeout >= AT_HW_MAX_IDLE_DELAY) {
+		netdev_err(adapter->netdev,
+			   "MAC state machine can't be idle since disabled for 10ms second\n");
+		return AT_ERR_TIMEOUT;
+	}
+
+	return 0;
+}
+
+
+/*
+ * Performs basic configuration of the adapter.
+ *
+ * hw - Struct containing variables accessed by shared code
+ * Assumes that the controller has previously been reset and is in a
+ * post-reset uninitialized state. Initializes multicast table,
+ * and  Calls routines to setup link
+ * Leaves the transmit and receive units disabled and uninitialized.
+ */
+int atl1e_init_hw(struct atl1e_hw *hw)
+{
+	s32 ret_val = 0;
+
+	atl1e_init_pcie(hw);
+
+	/* Zero out the Multicast HASH table */
+	/* clear the old settings from the multicast hash table */
+	AT_WRITE_REG(hw, REG_RX_HASH_TABLE, 0);
+	AT_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, 1, 0);
+
+	ret_val = atl1e_phy_init(hw);
+
+	return ret_val;
+}
+
+/*
+ * Detects the current speed and duplex settings of the hardware.
+ *
+ * hw - Struct containing variables accessed by shared code
+ * speed - Speed of the connection
+ * duplex - Duplex setting of the connection
+ */
+int atl1e_get_speed_and_duplex(struct atl1e_hw *hw, u16 *speed, u16 *duplex)
+{
+	int err;
+	u16 phy_data;
+
+	/* Read   PHY Specific Status Register (17) */
+	err = atl1e_read_phy_reg(hw, MII_AT001_PSSR, &phy_data);
+	if (err)
+		return err;
+
+	if (!(phy_data & MII_AT001_PSSR_SPD_DPLX_RESOLVED))
+		return AT_ERR_PHY_RES;
+
+	switch (phy_data & MII_AT001_PSSR_SPEED) {
+	case MII_AT001_PSSR_1000MBS:
+		*speed = SPEED_1000;
+		break;
+	case MII_AT001_PSSR_100MBS:
+		*speed = SPEED_100;
+		break;
+	case MII_AT001_PSSR_10MBS:
+		*speed = SPEED_10;
+		break;
+	default:
+		return AT_ERR_PHY_SPEED;
+		break;
+	}
+
+	if (phy_data & MII_AT001_PSSR_DPLX)
+		*duplex = FULL_DUPLEX;
+	else
+		*duplex = HALF_DUPLEX;
+
+	return 0;
+}
+
+int atl1e_restart_autoneg(struct atl1e_hw *hw)
+{
+	int err = 0;
+
+	err = atl1e_write_phy_reg(hw, MII_ADVERTISE, hw->mii_autoneg_adv_reg);
+	if (err)
+		return err;
+
+	if (hw->nic_type == athr_l1e || hw->nic_type == athr_l2e_revA) {
+		err = atl1e_write_phy_reg(hw, MII_CTRL1000,
+				       hw->mii_1000t_ctrl_reg);
+		if (err)
+			return err;
+	}
+
+	err = atl1e_write_phy_reg(hw, MII_BMCR,
+			BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART);
+	return err;
+}
+

addons/atl1e/src/3.10.108/atl1e_hw.h

@@ -0,0 +1,690 @@
+/*
+ * Copyright(c) 2007 Atheros Corporation. All rights reserved.
+ *
+ * Derived from Intel e1000 driver
+ * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#ifndef _ATHL1E_HW_H_
+#define _ATHL1E_HW_H_
+
+#include <linux/types.h>
+#include <linux/mii.h>
+
+struct atl1e_adapter;
+struct atl1e_hw;
+
+/* function prototype */
+s32 atl1e_reset_hw(struct atl1e_hw *hw);
+s32 atl1e_read_mac_addr(struct atl1e_hw *hw);
+s32 atl1e_init_hw(struct atl1e_hw *hw);
+s32 atl1e_phy_commit(struct atl1e_hw *hw);
+s32 atl1e_get_speed_and_duplex(struct atl1e_hw *hw, u16 *speed, u16 *duplex);
+u32 atl1e_auto_get_fc(struct atl1e_adapter *adapter, u16 duplex);
+u32 atl1e_hash_mc_addr(struct atl1e_hw *hw, u8 *mc_addr);
+void atl1e_hash_set(struct atl1e_hw *hw, u32 hash_value);
+s32 atl1e_read_phy_reg(struct atl1e_hw *hw, u16 reg_addr, u16 *phy_data);
+s32 atl1e_write_phy_reg(struct atl1e_hw *hw, u32 reg_addr, u16 phy_data);
+s32 atl1e_validate_mdi_setting(struct atl1e_hw *hw);
+void atl1e_hw_set_mac_addr(struct atl1e_hw *hw);
+bool atl1e_read_eeprom(struct atl1e_hw *hw, u32 offset, u32 *p_value);
+bool atl1e_write_eeprom(struct atl1e_hw *hw, u32 offset, u32 value);
+s32 atl1e_phy_enter_power_saving(struct atl1e_hw *hw);
+s32 atl1e_phy_leave_power_saving(struct atl1e_hw *hw);
+s32 atl1e_phy_init(struct atl1e_hw *hw);
+int atl1e_check_eeprom_exist(struct atl1e_hw *hw);
+void atl1e_force_ps(struct atl1e_hw *hw);
+s32 atl1e_restart_autoneg(struct atl1e_hw *hw);
+
+/* register definition */
+#define REG_PM_CTRLSTAT             0x44
+
+#define REG_PCIE_CAP_LIST           0x58
+
+#define REG_DEVICE_CAP              0x5C
+#define     DEVICE_CAP_MAX_PAYLOAD_MASK     0x7
+#define     DEVICE_CAP_MAX_PAYLOAD_SHIFT    0
+
+#define REG_DEVICE_CTRL             0x60
+#define     DEVICE_CTRL_MAX_PAYLOAD_MASK    0x7
+#define     DEVICE_CTRL_MAX_PAYLOAD_SHIFT   5
+#define     DEVICE_CTRL_MAX_RREQ_SZ_MASK    0x7
+#define     DEVICE_CTRL_MAX_RREQ_SZ_SHIFT   12
+
+#define REG_VPD_CAP                 0x6C
+#define     VPD_CAP_ID_MASK                 0xff
+#define     VPD_CAP_ID_SHIFT                0
+#define     VPD_CAP_NEXT_PTR_MASK           0xFF
+#define     VPD_CAP_NEXT_PTR_SHIFT          8
+#define     VPD_CAP_VPD_ADDR_MASK           0x7FFF
+#define     VPD_CAP_VPD_ADDR_SHIFT          16
+#define     VPD_CAP_VPD_FLAG                0x80000000
+
+#define REG_VPD_DATA                0x70
+
+#define REG_SPI_FLASH_CTRL          0x200
+#define     SPI_FLASH_CTRL_STS_NON_RDY      0x1
+#define     SPI_FLASH_CTRL_STS_WEN          0x2
+#define     SPI_FLASH_CTRL_STS_WPEN         0x80
+#define     SPI_FLASH_CTRL_DEV_STS_MASK     0xFF
+#define     SPI_FLASH_CTRL_DEV_STS_SHIFT    0
+#define     SPI_FLASH_CTRL_INS_MASK         0x7
+#define     SPI_FLASH_CTRL_INS_SHIFT        8
+#define     SPI_FLASH_CTRL_START            0x800
+#define     SPI_FLASH_CTRL_EN_VPD           0x2000
+#define     SPI_FLASH_CTRL_LDSTART          0x8000
+#define     SPI_FLASH_CTRL_CS_HI_MASK       0x3
+#define     SPI_FLASH_CTRL_CS_HI_SHIFT      16
+#define     SPI_FLASH_CTRL_CS_HOLD_MASK     0x3
+#define     SPI_FLASH_CTRL_CS_HOLD_SHIFT    18
+#define     SPI_FLASH_CTRL_CLK_LO_MASK      0x3
+#define     SPI_FLASH_CTRL_CLK_LO_SHIFT     20
+#define     SPI_FLASH_CTRL_CLK_HI_MASK      0x3
+#define     SPI_FLASH_CTRL_CLK_HI_SHIFT     22
+#define     SPI_FLASH_CTRL_CS_SETUP_MASK    0x3
+#define     SPI_FLASH_CTRL_CS_SETUP_SHIFT   24
+#define     SPI_FLASH_CTRL_EROM_PGSZ_MASK   0x3
+#define     SPI_FLASH_CTRL_EROM_PGSZ_SHIFT  26
+#define     SPI_FLASH_CTRL_WAIT_READY       0x10000000
+
+#define REG_SPI_ADDR                0x204
+
+#define REG_SPI_DATA                0x208
+
+#define REG_SPI_FLASH_CONFIG        0x20C
+#define     SPI_FLASH_CONFIG_LD_ADDR_MASK   0xFFFFFF
+#define     SPI_FLASH_CONFIG_LD_ADDR_SHIFT  0
+#define     SPI_FLASH_CONFIG_VPD_ADDR_MASK  0x3
+#define     SPI_FLASH_CONFIG_VPD_ADDR_SHIFT 24
+#define     SPI_FLASH_CONFIG_LD_EXIST       0x4000000
+
+
+#define REG_SPI_FLASH_OP_PROGRAM    0x210
+#define REG_SPI_FLASH_OP_SC_ERASE   0x211
+#define REG_SPI_FLASH_OP_CHIP_ERASE 0x212
+#define REG_SPI_FLASH_OP_RDID       0x213
+#define REG_SPI_FLASH_OP_WREN       0x214
+#define REG_SPI_FLASH_OP_RDSR       0x215
+#define REG_SPI_FLASH_OP_WRSR       0x216
+#define REG_SPI_FLASH_OP_READ       0x217
+
+#define REG_TWSI_CTRL               0x218
+#define     TWSI_CTRL_LD_OFFSET_MASK        0xFF
+#define     TWSI_CTRL_LD_OFFSET_SHIFT       0
+#define     TWSI_CTRL_LD_SLV_ADDR_MASK      0x7
+#define     TWSI_CTRL_LD_SLV_ADDR_SHIFT     8
+#define     TWSI_CTRL_SW_LDSTART            0x800
+#define     TWSI_CTRL_HW_LDSTART            0x1000
+#define     TWSI_CTRL_SMB_SLV_ADDR_MASK     0x0x7F
+#define     TWSI_CTRL_SMB_SLV_ADDR_SHIFT    15
+#define     TWSI_CTRL_LD_EXIST              0x400000
+#define     TWSI_CTRL_READ_FREQ_SEL_MASK    0x3
+#define     TWSI_CTRL_READ_FREQ_SEL_SHIFT   23
+#define     TWSI_CTRL_FREQ_SEL_100K         0
+#define     TWSI_CTRL_FREQ_SEL_200K         1
+#define     TWSI_CTRL_FREQ_SEL_300K         2
+#define     TWSI_CTRL_FREQ_SEL_400K         3
+#define     TWSI_CTRL_SMB_SLV_ADDR
+#define     TWSI_CTRL_WRITE_FREQ_SEL_MASK   0x3
+#define     TWSI_CTRL_WRITE_FREQ_SEL_SHIFT  24
+
+
+#define REG_PCIE_DEV_MISC_CTRL      0x21C
+#define     PCIE_DEV_MISC_CTRL_EXT_PIPE     0x2
+#define     PCIE_DEV_MISC_CTRL_RETRY_BUFDIS 0x1
+#define     PCIE_DEV_MISC_CTRL_SPIROM_EXIST 0x4
+#define     PCIE_DEV_MISC_CTRL_SERDES_ENDIAN    0x8
+#define     PCIE_DEV_MISC_CTRL_SERDES_SEL_DIN   0x10
+
+#define REG_PCIE_PHYMISC	    0x1000
+#define PCIE_PHYMISC_FORCE_RCV_DET	0x4
+
+#define REG_LTSSM_TEST_MODE         0x12FC
+#define         LTSSM_TEST_MODE_DEF     0xE000
+
+/* Selene Master Control Register */
+#define REG_MASTER_CTRL             0x1400
+#define     MASTER_CTRL_SOFT_RST            0x1
+#define     MASTER_CTRL_MTIMER_EN           0x2
+#define     MASTER_CTRL_ITIMER_EN           0x4
+#define     MASTER_CTRL_MANUAL_INT          0x8
+#define     MASTER_CTRL_ITIMER2_EN          0x20
+#define     MASTER_CTRL_INT_RDCLR           0x40
+#define     MASTER_CTRL_LED_MODE	    0x200
+#define     MASTER_CTRL_REV_NUM_SHIFT       16
+#define     MASTER_CTRL_REV_NUM_MASK        0xff
+#define     MASTER_CTRL_DEV_ID_SHIFT        24
+#define     MASTER_CTRL_DEV_ID_MASK         0xff
+
+/* Timer Initial Value Register */
+#define REG_MANUAL_TIMER_INIT       0x1404
+
+
+/* IRQ ModeratorTimer Initial Value Register */
+#define REG_IRQ_MODU_TIMER_INIT     0x1408   /* w */
+#define REG_IRQ_MODU_TIMER2_INIT    0x140A   /* w */
+
+
+#define REG_GPHY_CTRL               0x140C
+#define     GPHY_CTRL_EXT_RESET         1
+#define     GPHY_CTRL_PIPE_MOD          2
+#define     GPHY_CTRL_TEST_MODE_MASK    3
+#define     GPHY_CTRL_TEST_MODE_SHIFT   2
+#define     GPHY_CTRL_BERT_START        0x10
+#define     GPHY_CTRL_GATE_25M_EN       0x20
+#define     GPHY_CTRL_LPW_EXIT          0x40
+#define     GPHY_CTRL_PHY_IDDQ          0x80
+#define     GPHY_CTRL_PHY_IDDQ_DIS      0x100
+#define     GPHY_CTRL_PCLK_SEL_DIS      0x200
+#define     GPHY_CTRL_HIB_EN            0x400
+#define     GPHY_CTRL_HIB_PULSE         0x800
+#define     GPHY_CTRL_SEL_ANA_RST       0x1000
+#define     GPHY_CTRL_PHY_PLL_ON        0x2000
+#define     GPHY_CTRL_PWDOWN_HW		0x4000
+#define     GPHY_CTRL_DEFAULT (\
+		GPHY_CTRL_PHY_PLL_ON	|\
+		GPHY_CTRL_SEL_ANA_RST	|\
+		GPHY_CTRL_HIB_PULSE	|\
+		GPHY_CTRL_HIB_EN)
+
+#define     GPHY_CTRL_PW_WOL_DIS (\
+		GPHY_CTRL_PHY_PLL_ON	|\
+		GPHY_CTRL_SEL_ANA_RST	|\
+		GPHY_CTRL_HIB_PULSE	|\
+		GPHY_CTRL_HIB_EN	|\
+		GPHY_CTRL_PWDOWN_HW	|\
+		GPHY_CTRL_PCLK_SEL_DIS	|\
+		GPHY_CTRL_PHY_IDDQ)
+
+/* IRQ Anti-Lost Timer Initial Value Register */
+#define REG_CMBDISDMA_TIMER         0x140E
+
+
+/* Block IDLE Status Register */
+#define REG_IDLE_STATUS  	0x1410
+#define     IDLE_STATUS_RXMAC       1    /* 1: RXMAC state machine is in non-IDLE state. 0: RXMAC is idling */
+#define     IDLE_STATUS_TXMAC       2    /* 1: TXMAC state machine is in non-IDLE state. 0: TXMAC is idling */
+#define     IDLE_STATUS_RXQ         4    /* 1: RXQ state machine is in non-IDLE state.   0: RXQ is idling   */
+#define     IDLE_STATUS_TXQ         8    /* 1: TXQ state machine is in non-IDLE state.   0: TXQ is idling   */
+#define     IDLE_STATUS_DMAR        0x10 /* 1: DMAR state machine is in non-IDLE state.  0: DMAR is idling  */
+#define     IDLE_STATUS_DMAW        0x20 /* 1: DMAW state machine is in non-IDLE state.  0: DMAW is idling  */
+#define     IDLE_STATUS_SMB         0x40 /* 1: SMB state machine is in non-IDLE state.   0: SMB is idling   */
+#define     IDLE_STATUS_CMB         0x80 /* 1: CMB state machine is in non-IDLE state.   0: CMB is idling   */
+
+/* MDIO Control Register */
+#define REG_MDIO_CTRL           0x1414
+#define     MDIO_DATA_MASK          0xffff  /* On MDIO write, the 16-bit control data to write to PHY MII management register */
+#define     MDIO_DATA_SHIFT         0       /* On MDIO read, the 16-bit status data that was read from the PHY MII management register*/
+#define     MDIO_REG_ADDR_MASK      0x1f    /* MDIO register address */
+#define     MDIO_REG_ADDR_SHIFT     16
+#define     MDIO_RW                 0x200000      /* 1: read, 0: write */
+#define     MDIO_SUP_PREAMBLE       0x400000      /* Suppress preamble */
+#define     MDIO_START              0x800000      /* Write 1 to initiate the MDIO master. And this bit is self cleared after one cycle*/
+#define     MDIO_CLK_SEL_SHIFT      24
+#define     MDIO_CLK_25_4           0
+#define     MDIO_CLK_25_6           2
+#define     MDIO_CLK_25_8           3
+#define     MDIO_CLK_25_10          4
+#define     MDIO_CLK_25_14          5
+#define     MDIO_CLK_25_20          6
+#define     MDIO_CLK_25_28          7
+#define     MDIO_BUSY               0x8000000
+#define     MDIO_AP_EN              0x10000000
+#define MDIO_WAIT_TIMES         10
+
+/* MII PHY Status Register */
+#define REG_PHY_STATUS           0x1418
+#define     PHY_STATUS_100M	      0x20000
+#define     PHY_STATUS_EMI_CA	      0x40000
+
+/* BIST Control and Status Register0 (for the Packet Memory) */
+#define REG_BIST0_CTRL              0x141c
+#define     BIST0_NOW                   0x1 /* 1: To trigger BIST0 logic. This bit stays high during the */
+/* BIST process and reset to zero when BIST is done */
+#define     BIST0_SRAM_FAIL             0x2 /* 1: The SRAM failure is un-repairable because it has address */
+/* decoder failure or more than 1 cell stuck-to-x failure */
+#define     BIST0_FUSE_FLAG             0x4 /* 1: Indicating one cell has been fixed */
+
+/* BIST Control and Status Register1(for the retry buffer of PCI Express) */
+#define REG_BIST1_CTRL              0x1420
+#define     BIST1_NOW                   0x1 /* 1: To trigger BIST0 logic. This bit stays high during the */
+/* BIST process and reset to zero when BIST is done */
+#define     BIST1_SRAM_FAIL             0x2 /* 1: The SRAM failure is un-repairable because it has address */
+/* decoder failure or more than 1 cell stuck-to-x failure.*/
+#define     BIST1_FUSE_FLAG             0x4
+
+/* SerDes Lock Detect Control and Status Register */
+#define REG_SERDES_LOCK             0x1424
+#define     SERDES_LOCK_DETECT          1  /* 1: SerDes lock detected . This signal comes from Analog SerDes */
+#define     SERDES_LOCK_DETECT_EN       2  /* 1: Enable SerDes Lock detect function */
+
+/* MAC Control Register  */
+#define REG_MAC_CTRL                0x1480
+#define     MAC_CTRL_TX_EN              1  /* 1: Transmit Enable */
+#define     MAC_CTRL_RX_EN              2  /* 1: Receive Enable */
+#define     MAC_CTRL_TX_FLOW            4  /* 1: Transmit Flow Control Enable */
+#define     MAC_CTRL_RX_FLOW            8  /* 1: Receive Flow Control Enable */
+#define     MAC_CTRL_LOOPBACK           0x10      /* 1: Loop back at G/MII Interface */
+#define     MAC_CTRL_DUPLX              0x20      /* 1: Full-duplex mode  0: Half-duplex mode */
+#define     MAC_CTRL_ADD_CRC            0x40      /* 1: Instruct MAC to attach CRC on all egress Ethernet frames */
+#define     MAC_CTRL_PAD                0x80      /* 1: Instruct MAC to pad short frames to 60-bytes, and then attach CRC. This bit has higher priority over CRC_EN */
+#define     MAC_CTRL_LENCHK             0x100     /* 1: Instruct MAC to check if length field matches the real packet length */
+#define     MAC_CTRL_HUGE_EN            0x200     /* 1: receive Jumbo frame enable */
+#define     MAC_CTRL_PRMLEN_SHIFT       10        /* Preamble length */
+#define     MAC_CTRL_PRMLEN_MASK        0xf
+#define     MAC_CTRL_RMV_VLAN           0x4000    /* 1: to remove VLAN Tag automatically from all receive packets */
+#define     MAC_CTRL_PROMIS_EN          0x8000    /* 1: Promiscuous Mode Enable */
+#define     MAC_CTRL_TX_PAUSE           0x10000   /* 1: transmit test pause */
+#define     MAC_CTRL_SCNT               0x20000   /* 1: shortcut slot time counter */
+#define     MAC_CTRL_SRST_TX            0x40000   /* 1: synchronized reset Transmit MAC module */
+#define     MAC_CTRL_TX_SIMURST         0x80000   /* 1: transmit simulation reset */
+#define     MAC_CTRL_SPEED_SHIFT        20        /* 10: gigabit 01:10M/100M */
+#define     MAC_CTRL_SPEED_MASK         0x300000
+#define     MAC_CTRL_SPEED_1000         2
+#define     MAC_CTRL_SPEED_10_100       1
+#define     MAC_CTRL_DBG_TX_BKPRESURE   0x400000  /* 1: transmit maximum backoff (half-duplex test bit) */
+#define     MAC_CTRL_TX_HUGE            0x800000  /* 1: transmit huge enable */
+#define     MAC_CTRL_RX_CHKSUM_EN       0x1000000 /* 1: RX checksum enable */
+#define     MAC_CTRL_MC_ALL_EN          0x2000000 /* 1: upload all multicast frame without error to system */
+#define     MAC_CTRL_BC_EN              0x4000000 /* 1: upload all broadcast frame without error to system */
+#define     MAC_CTRL_DBG                0x8000000 /* 1: upload all received frame to system (Debug Mode) */
+
+/* MAC IPG/IFG Control Register  */
+#define REG_MAC_IPG_IFG             0x1484
+#define     MAC_IPG_IFG_IPGT_SHIFT      0     /* Desired back to back inter-packet gap. The default is 96-bit time */
+#define     MAC_IPG_IFG_IPGT_MASK       0x7f
+#define     MAC_IPG_IFG_MIFG_SHIFT      8     /* Minimum number of IFG to enforce in between RX frames */
+#define     MAC_IPG_IFG_MIFG_MASK       0xff  /* Frame gap below such IFP is dropped */
+#define     MAC_IPG_IFG_IPGR1_SHIFT     16    /* 64bit Carrier-Sense window */
+#define     MAC_IPG_IFG_IPGR1_MASK      0x7f
+#define     MAC_IPG_IFG_IPGR2_SHIFT     24    /* 96-bit IPG window */
+#define     MAC_IPG_IFG_IPGR2_MASK      0x7f
+
+/* MAC STATION ADDRESS  */
+#define REG_MAC_STA_ADDR            0x1488
+
+/* Hash table for multicast address */
+#define REG_RX_HASH_TABLE           0x1490
+
+
+/* MAC Half-Duplex Control Register */
+#define REG_MAC_HALF_DUPLX_CTRL     0x1498
+#define     MAC_HALF_DUPLX_CTRL_LCOL_SHIFT   0      /* Collision Window */
+#define     MAC_HALF_DUPLX_CTRL_LCOL_MASK    0x3ff
+#define     MAC_HALF_DUPLX_CTRL_RETRY_SHIFT  12     /* Retransmission maximum, afterwards the packet will be discarded */
+#define     MAC_HALF_DUPLX_CTRL_RETRY_MASK   0xf
+#define     MAC_HALF_DUPLX_CTRL_EXC_DEF_EN   0x10000 /* 1: Allow the transmission of a packet which has been excessively deferred */
+#define     MAC_HALF_DUPLX_CTRL_NO_BACK_C    0x20000 /* 1: No back-off on collision, immediately start the retransmission */
+#define     MAC_HALF_DUPLX_CTRL_NO_BACK_P    0x40000 /* 1: No back-off on backpressure, immediately start the transmission after back pressure */
+#define     MAC_HALF_DUPLX_CTRL_ABEBE        0x80000 /* 1: Alternative Binary Exponential Back-off Enabled */
+#define     MAC_HALF_DUPLX_CTRL_ABEBT_SHIFT  20      /* Maximum binary exponential number */
+#define     MAC_HALF_DUPLX_CTRL_ABEBT_MASK   0xf
+#define     MAC_HALF_DUPLX_CTRL_JAMIPG_SHIFT 24      /* IPG to start JAM for collision based flow control in half-duplex */
+#define     MAC_HALF_DUPLX_CTRL_JAMIPG_MASK  0xf     /* mode. In unit of 8-bit time */
+
+/* Maximum Frame Length Control Register   */
+#define REG_MTU                     0x149c
+
+/* Wake-On-Lan control register */
+#define REG_WOL_CTRL                0x14a0
+#define     WOL_PATTERN_EN                  0x00000001
+#define     WOL_PATTERN_PME_EN              0x00000002
+#define     WOL_MAGIC_EN                    0x00000004
+#define     WOL_MAGIC_PME_EN                0x00000008
+#define     WOL_LINK_CHG_EN                 0x00000010
+#define     WOL_LINK_CHG_PME_EN             0x00000020
+#define     WOL_PATTERN_ST                  0x00000100
+#define     WOL_MAGIC_ST                    0x00000200
+#define     WOL_LINKCHG_ST                  0x00000400
+#define     WOL_CLK_SWITCH_EN               0x00008000
+#define     WOL_PT0_EN                      0x00010000
+#define     WOL_PT1_EN                      0x00020000
+#define     WOL_PT2_EN                      0x00040000
+#define     WOL_PT3_EN                      0x00080000
+#define     WOL_PT4_EN                      0x00100000
+#define     WOL_PT5_EN                      0x00200000
+#define     WOL_PT6_EN                      0x00400000
+/* WOL Length ( 2 DWORD ) */
+#define REG_WOL_PATTERN_LEN         0x14a4
+#define     WOL_PT_LEN_MASK                 0x7f
+#define     WOL_PT0_LEN_SHIFT               0
+#define     WOL_PT1_LEN_SHIFT               8
+#define     WOL_PT2_LEN_SHIFT               16
+#define     WOL_PT3_LEN_SHIFT               24
+#define     WOL_PT4_LEN_SHIFT               0
+#define     WOL_PT5_LEN_SHIFT               8
+#define     WOL_PT6_LEN_SHIFT               16
+
+/* Internal SRAM Partition Register */
+#define REG_SRAM_TRD_ADDR           0x1518
+#define REG_SRAM_TRD_LEN            0x151C
+#define REG_SRAM_RXF_ADDR           0x1520
+#define REG_SRAM_RXF_LEN            0x1524
+#define REG_SRAM_TXF_ADDR           0x1528
+#define REG_SRAM_TXF_LEN            0x152C
+#define REG_SRAM_TCPH_ADDR          0x1530
+#define REG_SRAM_PKTH_ADDR          0x1532
+
+/* Load Ptr Register */
+#define REG_LOAD_PTR                0x1534  /* Software sets this bit after the initialization of the head and tail */
+
+/*
+ * addresses of all descriptors, as well as the following descriptor
+ * control register, which triggers each function block to load the head
+ * pointer to prepare for the operation. This bit is then self-cleared
+ * after one cycle.
+ */
+
+/* Descriptor Control register  */
+#define REG_RXF3_BASE_ADDR_HI           0x153C
+#define REG_DESC_BASE_ADDR_HI           0x1540
+#define REG_RXF0_BASE_ADDR_HI           0x1540 /* share with DESC BASE ADDR HI */
+#define REG_HOST_RXF0_PAGE0_LO          0x1544
+#define REG_HOST_RXF0_PAGE1_LO          0x1548
+#define REG_TPD_BASE_ADDR_LO            0x154C
+#define REG_RXF1_BASE_ADDR_HI           0x1550
+#define REG_RXF2_BASE_ADDR_HI           0x1554
+#define REG_HOST_RXFPAGE_SIZE           0x1558
+#define REG_TPD_RING_SIZE               0x155C
+/* RSS about */
+#define REG_RSS_KEY0                    0x14B0
+#define REG_RSS_KEY1                    0x14B4
+#define REG_RSS_KEY2                    0x14B8
+#define REG_RSS_KEY3                    0x14BC
+#define REG_RSS_KEY4                    0x14C0
+#define REG_RSS_KEY5                    0x14C4
+#define REG_RSS_KEY6                    0x14C8
+#define REG_RSS_KEY7                    0x14CC
+#define REG_RSS_KEY8                    0x14D0
+#define REG_RSS_KEY9                    0x14D4
+#define REG_IDT_TABLE4                  0x14E0
+#define REG_IDT_TABLE5                  0x14E4
+#define REG_IDT_TABLE6                  0x14E8
+#define REG_IDT_TABLE7                  0x14EC
+#define REG_IDT_TABLE0                  0x1560
+#define REG_IDT_TABLE1                  0x1564
+#define REG_IDT_TABLE2                  0x1568
+#define REG_IDT_TABLE3                  0x156C
+#define REG_IDT_TABLE                   REG_IDT_TABLE0
+#define REG_RSS_HASH_VALUE              0x1570
+#define REG_RSS_HASH_FLAG               0x1574
+#define REG_BASE_CPU_NUMBER             0x157C
+
+
+/* TXQ Control Register */
+#define REG_TXQ_CTRL                0x1580
+#define     TXQ_CTRL_NUM_TPD_BURST_MASK     0xF
+#define     TXQ_CTRL_NUM_TPD_BURST_SHIFT    0
+#define     TXQ_CTRL_EN                     0x20  /* 1: Enable TXQ */
+#define     TXQ_CTRL_ENH_MODE               0x40  /* Performance enhancement mode, in which up to two back-to-back DMA read commands might be dispatched. */
+#define     TXQ_CTRL_TXF_BURST_NUM_SHIFT    16    /* Number of data byte to read in a cache-aligned burst. Each SRAM entry is 8-byte in length. */
+#define     TXQ_CTRL_TXF_BURST_NUM_MASK     0xffff
+
+/* Jumbo packet Threshold for task offload */
+#define REG_TX_EARLY_TH                     0x1584 /* Jumbo frame threshold in QWORD unit. Packet greater than */
+/* JUMBO_TASK_OFFLOAD_THRESHOLD will not be task offloaded. */
+#define     TX_TX_EARLY_TH_MASK             0x7ff
+#define     TX_TX_EARLY_TH_SHIFT            0
+
+
+/* RXQ Control Register */
+#define REG_RXQ_CTRL                0x15A0
+#define         RXQ_CTRL_PBA_ALIGN_32                   0   /* rx-packet alignment */
+#define         RXQ_CTRL_PBA_ALIGN_64                   1
+#define         RXQ_CTRL_PBA_ALIGN_128                  2
+#define         RXQ_CTRL_PBA_ALIGN_256                  3
+#define         RXQ_CTRL_Q1_EN				0x10
+#define         RXQ_CTRL_Q2_EN				0x20
+#define         RXQ_CTRL_Q3_EN				0x40
+#define         RXQ_CTRL_IPV6_XSUM_VERIFY_EN		0x80
+#define         RXQ_CTRL_HASH_TLEN_SHIFT                8
+#define         RXQ_CTRL_HASH_TLEN_MASK                 0xFF
+#define         RXQ_CTRL_HASH_TYPE_IPV4                 0x10000
+#define         RXQ_CTRL_HASH_TYPE_IPV4_TCP             0x20000
+#define         RXQ_CTRL_HASH_TYPE_IPV6                 0x40000
+#define         RXQ_CTRL_HASH_TYPE_IPV6_TCP             0x80000
+#define         RXQ_CTRL_RSS_MODE_DISABLE               0
+#define         RXQ_CTRL_RSS_MODE_SQSINT                0x4000000
+#define         RXQ_CTRL_RSS_MODE_MQUESINT              0x8000000
+#define         RXQ_CTRL_RSS_MODE_MQUEMINT              0xC000000
+#define         RXQ_CTRL_NIP_QUEUE_SEL_TBL              0x10000000
+#define         RXQ_CTRL_HASH_ENABLE                    0x20000000
+#define         RXQ_CTRL_CUT_THRU_EN                    0x40000000
+#define         RXQ_CTRL_EN                             0x80000000
+
+/* Rx jumbo packet threshold and rrd  retirement timer  */
+#define REG_RXQ_JMBOSZ_RRDTIM       0x15A4
+/*
+ * Jumbo packet threshold for non-VLAN packet, in QWORD (64-bit) unit.
+ * When the packet length greater than or equal to this value, RXQ
+ * shall start cut-through forwarding of the received packet.
+ */
+#define         RXQ_JMBOSZ_TH_MASK      0x7ff
+#define         RXQ_JMBOSZ_TH_SHIFT         0  /* RRD retirement timer. Decrement by 1 after every 512ns passes*/
+#define         RXQ_JMBO_LKAH_MASK          0xf
+#define         RXQ_JMBO_LKAH_SHIFT         11
+
+/* RXF flow control register */
+#define REG_RXQ_RXF_PAUSE_THRESH    0x15A8
+#define     RXQ_RXF_PAUSE_TH_HI_SHIFT       0
+#define     RXQ_RXF_PAUSE_TH_HI_MASK        0xfff
+#define     RXQ_RXF_PAUSE_TH_LO_SHIFT       16
+#define     RXQ_RXF_PAUSE_TH_LO_MASK        0xfff
+
+
+/* DMA Engine Control Register */
+#define REG_DMA_CTRL                0x15C0
+#define     DMA_CTRL_DMAR_IN_ORDER          0x1
+#define     DMA_CTRL_DMAR_ENH_ORDER         0x2
+#define     DMA_CTRL_DMAR_OUT_ORDER         0x4
+#define     DMA_CTRL_RCB_VALUE              0x8
+#define     DMA_CTRL_DMAR_BURST_LEN_SHIFT   4
+#define     DMA_CTRL_DMAR_BURST_LEN_MASK    7
+#define     DMA_CTRL_DMAW_BURST_LEN_SHIFT   7
+#define     DMA_CTRL_DMAW_BURST_LEN_MASK    7
+#define     DMA_CTRL_DMAR_REQ_PRI           0x400
+#define     DMA_CTRL_DMAR_DLY_CNT_MASK      0x1F
+#define     DMA_CTRL_DMAR_DLY_CNT_SHIFT     11
+#define     DMA_CTRL_DMAW_DLY_CNT_MASK      0xF
+#define     DMA_CTRL_DMAW_DLY_CNT_SHIFT     16
+#define     DMA_CTRL_TXCMB_EN               0x100000
+#define     DMA_CTRL_RXCMB_EN				0x200000
+
+
+/* CMB/SMB Control Register */
+#define REG_SMB_STAT_TIMER                      0x15C4
+#define REG_TRIG_RRD_THRESH                     0x15CA
+#define REG_TRIG_TPD_THRESH                     0x15C8
+#define REG_TRIG_TXTIMER                        0x15CC
+#define REG_TRIG_RXTIMER                        0x15CE
+
+/* HOST RXF Page 1,2,3 address */
+#define REG_HOST_RXF1_PAGE0_LO                  0x15D0
+#define REG_HOST_RXF1_PAGE1_LO                  0x15D4
+#define REG_HOST_RXF2_PAGE0_LO                  0x15D8
+#define REG_HOST_RXF2_PAGE1_LO                  0x15DC
+#define REG_HOST_RXF3_PAGE0_LO                  0x15E0
+#define REG_HOST_RXF3_PAGE1_LO                  0x15E4
+
+/* Mail box */
+#define REG_MB_RXF1_RADDR                       0x15B4
+#define REG_MB_RXF2_RADDR                       0x15B8
+#define REG_MB_RXF3_RADDR                       0x15BC
+#define REG_MB_TPD_PROD_IDX                     0x15F0
+
+/* RXF-Page 0-3  PageNo & Valid bit */
+#define REG_HOST_RXF0_PAGE0_VLD     0x15F4
+#define     HOST_RXF_VALID              1
+#define     HOST_RXF_PAGENO_SHIFT       1
+#define     HOST_RXF_PAGENO_MASK        0x7F
+#define REG_HOST_RXF0_PAGE1_VLD     0x15F5
+#define REG_HOST_RXF1_PAGE0_VLD     0x15F6
+#define REG_HOST_RXF1_PAGE1_VLD     0x15F7
+#define REG_HOST_RXF2_PAGE0_VLD     0x15F8
+#define REG_HOST_RXF2_PAGE1_VLD     0x15F9
+#define REG_HOST_RXF3_PAGE0_VLD     0x15FA
+#define REG_HOST_RXF3_PAGE1_VLD     0x15FB
+
+/* Interrupt Status Register */
+#define REG_ISR    0x1600
+#define  ISR_SMB   		1
+#define  ISR_TIMER		2       /* Interrupt when Timer is counted down to zero */
+/*
+ * Software manual interrupt, for debug. Set when SW_MAN_INT_EN is set
+ * in Table 51 Selene Master Control Register (Offset 0x1400).
+ */
+#define  ISR_MANUAL         	4
+#define  ISR_HW_RXF_OV          8        /* RXF overflow interrupt */
+#define  ISR_HOST_RXF0_OV       0x10
+#define  ISR_HOST_RXF1_OV       0x20
+#define  ISR_HOST_RXF2_OV       0x40
+#define  ISR_HOST_RXF3_OV       0x80
+#define  ISR_TXF_UN             0x100
+#define  ISR_RX0_PAGE_FULL      0x200
+#define  ISR_DMAR_TO_RST        0x400
+#define  ISR_DMAW_TO_RST        0x800
+#define  ISR_GPHY               0x1000
+#define  ISR_TX_CREDIT          0x2000
+#define  ISR_GPHY_LPW           0x4000    /* GPHY low power state interrupt */
+#define  ISR_RX_PKT             0x10000   /* One packet received, triggered by RFD */
+#define  ISR_TX_PKT             0x20000   /* One packet transmitted, triggered by TPD */
+#define  ISR_TX_DMA             0x40000
+#define  ISR_RX_PKT_1           0x80000
+#define  ISR_RX_PKT_2           0x100000
+#define  ISR_RX_PKT_3           0x200000
+#define  ISR_MAC_RX             0x400000
+#define  ISR_MAC_TX             0x800000
+#define  ISR_UR_DETECTED        0x1000000
+#define  ISR_FERR_DETECTED      0x2000000
+#define  ISR_NFERR_DETECTED     0x4000000
+#define  ISR_CERR_DETECTED      0x8000000
+#define  ISR_PHY_LINKDOWN       0x10000000
+#define  ISR_DIS_INT            0x80000000
+
+
+/* Interrupt Mask Register */
+#define REG_IMR 0x1604
+
+
+#define IMR_NORMAL_MASK (\
+		ISR_SMB	        |\
+		ISR_TXF_UN      |\
+		ISR_HW_RXF_OV   |\
+		ISR_HOST_RXF0_OV|\
+		ISR_MANUAL      |\
+		ISR_GPHY        |\
+		ISR_GPHY_LPW    |\
+		ISR_DMAR_TO_RST |\
+		ISR_DMAW_TO_RST |\
+		ISR_PHY_LINKDOWN|\
+		ISR_RX_PKT      |\
+		ISR_TX_PKT)
+
+#define ISR_TX_EVENT (ISR_TXF_UN | ISR_TX_PKT)
+#define ISR_RX_EVENT (ISR_HOST_RXF0_OV | ISR_HW_RXF_OV | ISR_RX_PKT)
+
+#define REG_MAC_RX_STATUS_BIN 0x1700
+#define REG_MAC_RX_STATUS_END 0x175c
+#define REG_MAC_TX_STATUS_BIN 0x1760
+#define REG_MAC_TX_STATUS_END 0x17c0
+
+/* Hardware Offset Register */
+#define REG_HOST_RXF0_PAGEOFF 0x1800
+#define REG_TPD_CONS_IDX      0x1804
+#define REG_HOST_RXF1_PAGEOFF 0x1808
+#define REG_HOST_RXF2_PAGEOFF 0x180C
+#define REG_HOST_RXF3_PAGEOFF 0x1810
+
+/* RXF-Page 0-3 Offset DMA Address */
+#define REG_HOST_RXF0_MB0_LO  0x1820
+#define REG_HOST_RXF0_MB1_LO  0x1824
+#define REG_HOST_RXF1_MB0_LO  0x1828
+#define REG_HOST_RXF1_MB1_LO  0x182C
+#define REG_HOST_RXF2_MB0_LO  0x1830
+#define REG_HOST_RXF2_MB1_LO  0x1834
+#define REG_HOST_RXF3_MB0_LO  0x1838
+#define REG_HOST_RXF3_MB1_LO  0x183C
+
+/* Tpd CMB DMA Address */
+#define REG_HOST_TX_CMB_LO    0x1840
+#define REG_HOST_SMB_ADDR_LO  0x1844
+
+/* DEBUG ADDR */
+#define REG_DEBUG_DATA0 0x1900
+#define REG_DEBUG_DATA1 0x1904
+
+/***************************** MII definition ***************************************/
+/* PHY Common Register */
+#define MII_AT001_PSCR                  0x10
+#define MII_AT001_PSSR                  0x11
+#define MII_INT_CTRL                    0x12
+#define MII_INT_STATUS                  0x13
+#define MII_SMARTSPEED                  0x14
+#define MII_LBRERROR                    0x18
+#define MII_RESV2                       0x1a
+
+#define MII_DBG_ADDR			0x1D
+#define MII_DBG_DATA			0x1E
+
+/* Autoneg Advertisement Register */
+#define MII_AR_DEFAULT_CAP_MASK                 0
+
+/* 1000BASE-T Control Register */
+#define MII_AT001_CR_1000T_SPEED_MASK \
+	(ADVERTISE_1000FULL | ADVERTISE_1000HALF)
+#define MII_AT001_CR_1000T_DEFAULT_CAP_MASK	MII_AT001_CR_1000T_SPEED_MASK
+
+/* AT001 PHY Specific Control Register */
+#define MII_AT001_PSCR_JABBER_DISABLE           0x0001  /* 1=Jabber Function disabled */
+#define MII_AT001_PSCR_POLARITY_REVERSAL        0x0002  /* 1=Polarity Reversal enabled */
+#define MII_AT001_PSCR_SQE_TEST                 0x0004  /* 1=SQE Test enabled */
+#define MII_AT001_PSCR_MAC_POWERDOWN            0x0008
+#define MII_AT001_PSCR_CLK125_DISABLE           0x0010  /* 1=CLK125 low,
+							 * 0=CLK125 toggling
+							 */
+#define MII_AT001_PSCR_MDI_MANUAL_MODE          0x0000  /* MDI Crossover Mode bits 6:5 */
+/* Manual MDI configuration */
+#define MII_AT001_PSCR_MDIX_MANUAL_MODE         0x0020  /* Manual MDIX configuration */
+#define MII_AT001_PSCR_AUTO_X_1000T             0x0040  /* 1000BASE-T: Auto crossover,
+							 *  100BASE-TX/10BASE-T:
+							 *  MDI Mode
+							 */
+#define MII_AT001_PSCR_AUTO_X_MODE              0x0060  /* Auto crossover enabled
+							 * all speeds.
+							 */
+#define MII_AT001_PSCR_10BT_EXT_DIST_ENABLE     0x0080
+/* 1=Enable Extended 10BASE-T distance
+ * (Lower 10BASE-T RX Threshold)
+ * 0=Normal 10BASE-T RX Threshold */
+#define MII_AT001_PSCR_MII_5BIT_ENABLE          0x0100
+/* 1=5-Bit interface in 100BASE-TX
+ * 0=MII interface in 100BASE-TX */
+#define MII_AT001_PSCR_SCRAMBLER_DISABLE        0x0200  /* 1=Scrambler disable */
+#define MII_AT001_PSCR_FORCE_LINK_GOOD          0x0400  /* 1=Force link good */
+#define MII_AT001_PSCR_ASSERT_CRS_ON_TX         0x0800  /* 1=Assert CRS on Transmit */
+#define MII_AT001_PSCR_POLARITY_REVERSAL_SHIFT    1
+#define MII_AT001_PSCR_AUTO_X_MODE_SHIFT          5
+#define MII_AT001_PSCR_10BT_EXT_DIST_ENABLE_SHIFT 7
+/* AT001 PHY Specific Status Register */
+#define MII_AT001_PSSR_SPD_DPLX_RESOLVED        0x0800  /* 1=Speed & Duplex resolved */
+#define MII_AT001_PSSR_DPLX                     0x2000  /* 1=Duplex 0=Half Duplex */
+#define MII_AT001_PSSR_SPEED                    0xC000  /* Speed, bits 14:15 */
+#define MII_AT001_PSSR_10MBS                    0x0000  /* 00=10Mbs */
+#define MII_AT001_PSSR_100MBS                   0x4000  /* 01=100Mbs */
+#define MII_AT001_PSSR_1000MBS                  0x8000  /* 10=1000Mbs */
+
+#endif /*_ATHL1E_HW_H_*/