* Re: [PATCH 0/6] VSOCK for Linux upstreaming
From: David Miller @ 2012-11-05 18:09 UTC (permalink / raw)
To: georgezhang
Cc: pv-drivers, netdev, linux-kernel, virtualization, gregkh,
vm-crosstalk
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
The big and only question is whether anyone can actually use any of
this stuff without your proprietary bits?
^ permalink raw reply
* [PATCH 6/6] VSOCK: header and config files.
From: George Zhang @ 2012-11-05 18:01 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
VSOCK header files, Makefiles and Kconfig systems for Linux VSocket module.
Signed-off-by: George Zhang <georgezhang@vmware.com>
---
include/linux/socket.h | 4
net/Kconfig | 1
net/Makefile | 1
net/vmw_vsock/Kconfig | 14 +
net/vmw_vsock/Makefile | 4
net/vmw_vsock/notify_qstate.c | 627 +++++++++++++++++++++++++++++++++++
net/vmw_vsock/vmci_sockets.h | 517 +++++++++++++++++++++++++++++
net/vmw_vsock/vmci_sockets_packet.h | 106 ++++++
net/vmw_vsock/vsock_common.h | 130 +++++++
net/vmw_vsock/vsock_packet.h | 131 +++++++
net/vmw_vsock/vsock_version.h | 29 ++
11 files changed, 1563 insertions(+), 1 deletions(-)
create mode 100644 net/vmw_vsock/Kconfig
create mode 100644 net/vmw_vsock/Makefile
create mode 100644 net/vmw_vsock/notify_qstate.c
create mode 100644 net/vmw_vsock/vmci_sockets.h
create mode 100644 net/vmw_vsock/vmci_sockets_packet.h
create mode 100644 net/vmw_vsock/vsock_common.h
create mode 100644 net/vmw_vsock/vsock_packet.h
create mode 100644 net/vmw_vsock/vsock_version.h
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 25d6322..57bc85e 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -195,7 +195,8 @@ struct ucred {
#define AF_CAIF 37 /* CAIF sockets */
#define AF_ALG 38 /* Algorithm sockets */
#define AF_NFC 39 /* NFC sockets */
-#define AF_MAX 40 /* For now.. */
+#define AF_VSOCK 40 /* VMCI sockets */
+#define AF_MAX 41 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
@@ -238,6 +239,7 @@ struct ucred {
#define PF_CAIF AF_CAIF
#define PF_ALG AF_ALG
#define PF_NFC AF_NFC
+#define PF_VSOCK AF_VSOCK
#define PF_MAX AF_MAX
/* Maximum queue length specifiable by listen. */
diff --git a/net/Kconfig b/net/Kconfig
index 245831b..75b8d5e 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -216,6 +216,7 @@ source "net/dcb/Kconfig"
source "net/dns_resolver/Kconfig"
source "net/batman-adv/Kconfig"
source "net/openvswitch/Kconfig"
+source "net/vmw_vsock/Kconfig"
config RPS
boolean
diff --git a/net/Makefile b/net/Makefile
index 4f4ee08..cae59f4 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -70,3 +70,4 @@ obj-$(CONFIG_CEPH_LIB) += ceph/
obj-$(CONFIG_BATMAN_ADV) += batman-adv/
obj-$(CONFIG_NFC) += nfc/
obj-$(CONFIG_OPENVSWITCH) += openvswitch/
+obj-$(CONFIG_VMWARE_VSOCK) += vmw_vsock/
diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig
new file mode 100644
index 0000000..95e2568
--- /dev/null
+++ b/net/vmw_vsock/Kconfig
@@ -0,0 +1,14 @@
+#
+# Vsock protocol
+#
+
+config VMWARE_VSOCK
+ tristate "Virtual Socket protocol"
+ depends on VMWARE_VMCI
+ help
+ Virtual Socket Protocol is a socket protocol similar to TCP/IP
+ allowing comunication between Virtual Machines and VMware
+ hypervisor.
+
+ To compile this driver as a module, choose M here: the module
+ will be called vsock. If unsure, say N.
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
new file mode 100644
index 0000000..4e940fe
--- /dev/null
+++ b/net/vmw_vsock/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_VMWARE_VSOCK) += vmw_vsock.o
+
+vmw_vsock-y += af_vsock.o notify.o notify_qstate.o stats.o util.o \
+ vsock_addr.o
diff --git a/net/vmw_vsock/notify_qstate.c b/net/vmw_vsock/notify_qstate.c
new file mode 100644
index 0000000..9cc4b58
--- /dev/null
+++ b/net/vmw_vsock/notify_qstate.c
@@ -0,0 +1,627 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2009-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * notifyQState.c --
+ *
+ * Linux control notifications based on Queuepair state for the VMCI Stream
+ * Sockets protocol.
+ */
+
+#include <linux/types.h>
+
+#include <linux/socket.h>
+
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+
+#include "notify.h"
+#include "af_vsock.h"
+
+#define PKT_FIELD(vsk, field_name) \
+ (vsk)->notify.pkt_q_state.field_name
+
+/*
+ *
+ * vsock_vmci_notify_waiting_write --
+ *
+ * Determines if the conditions have been met to notify a waiting writer.
+ *
+ * Results: true if a notification should be sent, false otherwise.
+ *
+ * Side effects: None.
+ */
+
+static bool vsock_vmci_notify_waiting_write(vsock_vmci_sock *vsk)
+{
+ bool retval;
+ u64 notify_limit;
+
+ if (!PKT_FIELD(vsk, peer_waiting_write))
+ return false;
+
+ /*
+ * When the sender blocks, we take that as a sign that the sender is
+ * faster than the receiver. To reduce the transmit rate of the sender,
+ * we delay the sending of the read notification by decreasing the
+ * write_notify_window. The notification is delayed until the number of
+ * bytes used in the queue drops below the write_notify_window.
+ */
+
+ if (!PKT_FIELD(vsk, peer_waiting_write_detected)) {
+ PKT_FIELD(vsk, peer_waiting_write_detected) = true;
+ if (PKT_FIELD(vsk, write_notify_window) < PAGE_SIZE) {
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+ } else {
+ PKT_FIELD(vsk, write_notify_window) -= PAGE_SIZE;
+ if (PKT_FIELD(vsk, write_notify_window) <
+ PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+
+ }
+ }
+ notify_limit = vsk->consume_size - PKT_FIELD(vsk, write_notify_window);
+
+ /*
+ * The notify_limit is used to delay notifications in the case where
+ * flow control is enabled. Below the test is expressed in terms of
+ * free space in the queue: if free_space > ConsumeSize -
+ * write_notify_window then notify An alternate way of expressing this
+ * is to rewrite the expression to use the data ready in the receive
+ * queue: if write_notify_window > bufferReady then notify as
+ * free_space == ConsumeSize - bufferReady.
+ */
+
+ retval = vmci_qpair_consume_free_space(vsk->qpair) > notify_limit;
+
+ if (retval) {
+ /*
+ * Once we notify the peer, we reset the detected flag so the
+ * next wait will again cause a decrease in the window size.
+ */
+
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+ }
+ return retval;
+}
+
+/*
+ *
+ * vsock_vmci_handle_read --
+ *
+ * Handles an incoming read message.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void
+vsock_vmci_handle_read(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+
+ sk->sk_write_space(sk);
+}
+
+/*
+ *
+ * vsock_vmci_handle_wrote --
+ *
+ * Handles an incoming wrote message.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void
+vsock_vmci_handle_wrote(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+ sk->sk_data_ready(sk, 0);
+}
+
+/*
+ *
+ * vsock_vmci_block_update_write_window --
+ *
+ * Updates the write window when we are blocking for data.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_block_update_write_window(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+
+ if (PKT_FIELD(vsk, write_notify_window) < vsk->consume_size)
+ PKT_FIELD(vsk, write_notify_window) =
+ min(PKT_FIELD(vsk, write_notify_window) + PAGE_SIZE,
+ vsk->consume_size);
+
+}
+
+/*
+ *
+ * vsock_vmci_send_read_notification --
+ *
+ * Sends a read notification to this socket's peer.
+ *
+ * Results: >= 0 if the datagram is sent successfully, negative error value
+ * otherwise.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_send_read_notification(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+ bool sent_read;
+ unsigned int retries;
+ int err;
+
+ vsk = vsock_sk(sk);
+ sent_read = false;
+ retries = 0;
+ err = 0;
+
+ if (vsock_vmci_notify_waiting_write(vsk)) {
+ /*
+ * Notify the peer that we have read, retrying the send on
+ * failure up to our maximum value. XXX For now we just log
+ * the failure, but later we should schedule a work item to
+ * handle the resend until it succeeds. That would require
+ * keeping track of work items in the vsk and cleaning them up
+ * upon socket close.
+ */
+ while (!(vsk->peer_shutdown & RCV_SHUTDOWN) &&
+ !sent_read && retries < VSOCK_MAX_DGRAM_RESENDS) {
+ err = VSOCK_SEND_READ(sk);
+ if (err >= 0)
+ sent_read = true;
+
+ retries++;
+ }
+
+ if (retries >= VSOCK_MAX_DGRAM_RESENDS && !sent_read)
+ printk
+ ("%p unable to send read notification to peer.\n",
+ sk);
+ else
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+
+ }
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_socket_init --
+ *
+ * Function that is called after a socket is created and before any notify ops
+ * are used.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_socket_init(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_socket_destruct --
+ *
+ * Function that is called when the socket is being released.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_socket_destruct(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_poll_in --
+ *
+ * Called by the poll function to figure out if there is data to read and to
+ * setup future notifications if needed. Only called on sockets that aren't
+ * shutdown for recv.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_poll_in(struct sock *sk,
+ size_t target, bool *data_ready_now)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ if (vsock_vmci_stream_has_data(vsk)) {
+ *data_ready_now = true;
+ } else {
+ /*
+ * We can't read right now because there is nothing in the
+ * queue. Ask for notifications when there is something to
+ * read.
+ */
+ if (sk->sk_state == SS_CONNECTED)
+ vsock_vmci_block_update_write_window(sk);
+
+ *data_ready_now = false;
+ }
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_poll_out
+ *
+ * Called by the poll function to figure out if there is space to write and to
+ * setup future notifications if needed. Only called on a connected socket that
+ * isn't shutdown for send.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_poll_out(struct sock *sk,
+ size_t target, bool *space_avail_now)
+{
+ s64 produce_q_free_space;
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ produce_q_free_space = vsock_vmci_stream_has_space(vsk);
+ if (produce_q_free_space > 0) {
+ *space_avail_now = true;
+ return 0;
+ } else if (produce_q_free_space == 0) {
+ /*
+ * This is a connected socket but we can't currently send data.
+ * Nothing else to do.
+ */
+ *space_avail_now = false;
+ }
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_init --
+ *
+ * Called at the start of a stream recv call with the socket lock held.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_init(struct sock *sk,
+ size_t target,
+ vsock_vmci_recv_notify_data *data)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ data->consume_head = 0;
+ data->produce_tail = 0;
+ data->notify_on_block = false;
+
+ if (PKT_FIELD(vsk, write_notify_min_window) < target + 1) {
+ ASSERT(target < vsk->consume_size);
+ PKT_FIELD(vsk, write_notify_min_window) = target + 1;
+ if (PKT_FIELD(vsk, write_notify_window) <
+ PKT_FIELD(vsk, write_notify_min_window)) {
+ /*
+ * If the current window is smaller than the new
+ * minimal window size, we need to reevaluate whether
+ * we need to notify the sender. If the number of ready
+ * bytes are smaller than the new window, we need to
+ * send a notification to the sender before we block.
+ */
+
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+ data->notify_on_block = true;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_pre_block --
+ *
+ * Called right before a socket is about to block with the socket lock held.
+ * The socket lock may have been released between the entry function and the
+ * preblock call.
+ *
+ * Note: This function may be called multiple times before the post block
+ * function is called.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_pre_block(struct sock *sk,
+ size_t target,
+ vsock_vmci_recv_notify_data *data)
+{
+ int err = 0;
+
+ vsock_vmci_block_update_write_window(sk);
+
+ if (data->notify_on_block) {
+ err = vsock_vmci_send_read_notification(sk);
+ if (err < 0)
+ return err;
+
+ data->notify_on_block = false;
+ }
+
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_post_dequeue --
+ *
+ * Called right after we dequeue / peek data from a socket.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_post_dequeue(struct sock *sk,
+ size_t target,
+ ssize_t copied,
+ bool data_read,
+ vsock_vmci_recv_notify_data *data)
+{
+ vsock_vmci_sock *vsk;
+ int err;
+ bool was_full = false;
+ u64 free_space;
+
+ vsk = vsock_sk(sk);
+ err = 0;
+
+ if (data_read) {
+ smp_mb();
+
+ free_space = vmci_qpair_consume_free_space(vsk->qpair);
+ was_full = free_space == copied;
+
+ if (was_full)
+ PKT_FIELD(vsk, peer_waiting_write) = true;
+
+ err = vsock_vmci_send_read_notification(sk);
+ if (err < 0)
+ return err;
+
+ /* See the comment in vsock_vmci_notify_pkt_send_post_enqueue */
+ sk->sk_data_ready(sk, 0);
+ }
+
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_send_init --
+ *
+ * Called at the start of a stream send call with the socket lock held.
+ *
+ * Results: 0 on success. A negative error code on failure.
+ *
+ * Side effects:
+ */
+
+static int
+vsock_vmci_notify_pkt_send_init(struct sock *sk,
+ vsock_vmci_send_notify_data *data)
+{
+ data->consume_head = 0;
+ data->produce_tail = 0;
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notifySendPostEnqueue --
+ *
+ * Called right after we enqueue data to a socket.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_send_post_enqueue(struct sock *sk,
+ ssize_t written,
+ vsock_vmci_send_notify_data *data)
+{
+ int err = 0;
+ vsock_vmci_sock *vsk;
+ bool sent_wrote = false;
+ bool was_empty;
+ int retries = 0;
+
+ vsk = vsock_sk(sk);
+
+ smp_mb();
+
+ was_empty = (vmci_qpair_produce_buf_ready(vsk->qpair) == written);
+ if (was_empty) {
+ while (!(vsk->peer_shutdown & RCV_SHUTDOWN) &&
+ !sent_wrote && retries < VSOCK_MAX_DGRAM_RESENDS) {
+ err = VSOCK_SEND_WROTE(sk);
+ if (err >= 0)
+ sent_wrote = true;
+
+ retries++;
+ }
+ }
+
+ if (retries >= VSOCK_MAX_DGRAM_RESENDS && !sent_wrote) {
+ printk
+ ("%p unable to send wrote notification to peer.\n",
+ sk);
+ return err;
+ }
+
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_handle_pkt
+ *
+ * Called when a notify packet is recieved for a socket in the connected state.
+ * Note this might be called from a bottom half.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void
+vsock_vmci_notify_pkt_handle_pkt(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst,
+ struct sockaddr_vm *src, bool *pkt_processed)
+{
+ bool processed = false;
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_WROTE:
+ vsock_vmci_handle_wrote(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ case VSOCK_PACKET_TYPE_READ:
+ vsock_vmci_handle_read(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ }
+
+ if (pkt_processed)
+ *pkt_processed = processed;
+
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_process_request
+ *
+ * Called near the end of process request.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_process_request(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = vsk->consume_size;
+ if (vsk->consume_size < PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_min_window) = vsk->consume_size;
+
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_process_negotiate
+ *
+ * Called near the end of process negotiate.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_process_negotiate(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = vsk->consume_size;
+ if (vsk->consume_size < PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_min_window) = vsk->consume_size;
+
+}
+
+/* Socket always on control packet based operations. */
+vsock_vmci_notify_ops vsock_vmci_notify_pkt_q_state_ops = {
+ vsock_vmci_notify_pkt_socket_init,
+ vsock_vmci_notify_pkt_socket_destruct,
+ vsock_vmci_notify_pkt_poll_in,
+ vsock_vmci_notify_pkt_poll_out,
+ vsock_vmci_notify_pkt_handle_pkt,
+ vsock_vmci_notify_pkt_recv_init,
+ vsock_vmci_notify_pkt_recv_pre_block,
+ NULL, /* recv_pre_dequeue */
+ vsock_vmci_notify_pkt_recv_post_dequeue,
+ vsock_vmci_notify_pkt_send_init,
+ NULL, /* send_pre_block */
+ NULL, /* send_pre_enqueue */
+ vsock_vmci_notify_pkt_send_post_enqueue,
+ vsock_vmci_notify_pkt_process_request,
+ vsock_vmci_notify_pkt_process_negotiate,
+};
diff --git a/net/vmw_vsock/vmci_sockets.h b/net/vmw_vsock/vmci_sockets.h
new file mode 100644
index 0000000..6e6fd98
--- /dev/null
+++ b/net/vmw_vsock/vmci_sockets.h
@@ -0,0 +1,517 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vmci_sockets.h --
+ *
+ * VMCI sockets public constants and types.
+ */
+
+#ifndef _VMCI_SOCKETS_H_
+#define _VMCI_SOCKETS_H_
+
+#if !defined(__KERNEL__)
+#include <sys/socket.h>
+#endif
+
+/*
+ * \brief Option name for STREAM socket buffer size.
+ *
+ * Use as the option name in \c setsockopt(3) or \c getsockopt(3) to set or get
+ * an \c unsigned \c long \c long that specifies the size of the buffer
+ * underlying a vSockets STREAM socket.
+ *
+ * \note Value is clamped to the MIN and MAX.
+ *
+ * \see vmci_sock_get_af_value_fd() \see SO_VMCI_BUFFER_MIN_SIZE \see
+ * SO_VMCI_BUFFER_MAX_SIZE
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); unsigned long
+ * long val = 0x1000; int fd = socket(af, SOCK_STREAM, 0); setsockopt(fd, af,
+ * SO_VMCI_BUFFER_SIZE, &val, sizeof val); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_BUFFER_SIZE 0
+
+/*
+ * \brief Option name for STREAM socket minimum buffer size.
+ *
+ * Use as the option name in \c setsockopt(3) or \c getsockopt(3) to set or get
+ * an \c unsigned \c long \c long that specifies the minimum size allowed for
+ * the buffer underlying a vSockets STREAM socket.
+ *
+ * \see vmci_sock_get_af_value_fd() \see SO_VMCI_BUFFER_SIZE \see
+ * SO_VMCI_BUFFER_MAX_SIZE
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); unsigned long
+ * long val = 0x500; int fd = socket(af, SOCK_STREAM, 0); setsockopt(fd, af,
+ * SO_VMCI_BUFFER_MIN_SIZE, &val, sizeof val); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_BUFFER_MIN_SIZE 1
+
+/*
+ * \brief Option name for STREAM socket maximum buffer size.
+ *
+ * Use as the option name in \c setsockopt(3) or \c getsockopt(3) to set or get
+ * an unsigned long long that specifies the maximum size allowed for the buffer
+ * underlying a vSockets STREAM socket.
+ *
+ * \see vmci_sock_get_af_value_fd() \see SO_VMCI_BUFFER_SIZE \see
+ * SO_VMCI_BUFFER_MIN_SIZE
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); unsigned long
+ * long val = 0x4000; int fd = socket(af, SOCK_STREAM, 0); setsockopt(fd, af,
+ * SO_VMCI_BUFFER_MAX_SIZE, &val, sizeof val); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_BUFFER_MAX_SIZE 2
+
+/*
+ * \brief Option name for socket peer's host-specific VM ID.
+ *
+ * Use as the option name in \c getsockopt(3) to get a host-specific identifier
+ * for the peer endpoint's VM. The identifier is a signed integer.
+ *
+ * \note Only available for ESX (VMKernel/userworld) endpoints.
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); int id;
+ * socklen_t len = sizeof id; int fd = socket(af, SOCK_DGRAM, 0); getsockopt(fd,
+ * af, SO_VMCI_PEER_HOST_VM_ID, &id, &len); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_PEER_HOST_VM_ID 3
+
+/*
+ * \brief Option name for socket's service label.
+ *
+ * Use as the option name in \c setsockopt(3) or \c getsockopt(3) to set or get
+ * the service label for a socket. The service label is a C-style
+ * NUL-terminated string.
+ *
+ * \note Only available for ESX (VMkernel/userworld) endpoints.
+ */
+
+#define SO_VMCI_SERVICE_LABEL 4
+
+/*
+ * \brief Option name for determining if a socket is trusted.
+ *
+ * Use as the option name in \c getsockopt(3) to determine if a socket is
+ * trusted. The value is a signed integer.
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); int trusted;
+ * socklen_t len = sizeof trusted; int fd = socket(af, SOCK_DGRAM, 0);
+ * getsockopt(fd, af, SO_VMCI_TRUSTED, &trusted, &len); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_TRUSTED 5
+
+/*
+ * \brief Option name for STREAM socket connection timeout.
+ *
+ * Use as the option name in \c setsockopt(3) or \c getsockopt(3) to set or get
+ * the connection timeout for a STREAM socket. The value is platform
+ * dependent. On ESX, Linux and Mac OS, it is a \c struct \c timeval. On
+ * Windows, it is a \c DWORD.
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); struct
+ * timeval t = { 5, 100000 }; int fd = socket(af, SOCK_STREAM, 0);
+ * setsockopt(fd, af, SO_VMCI_CONNECT_TIMEOUT, &t, sizeof t); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_CONNECT_TIMEOUT 6
+
+/*
+ * \brief Option name for using non-blocking send/receive.
+ *
+ * Use as the option name for \c setsockopt(3) or \c getsockopt(3) to set or
+ * get the non-blocking transmit/receive flag for a STREAM socket. This flag
+ * determines whether \c send() and \c recv() can be called in non-blocking
+ * contexts for the given socket. The value is a signed integer.
+ *
+ * This option is only relevant to kernel endpoints, where descheduling the
+ * thread of execution is not allowed, for example, while holding a spinlock.
+ * It is not to be confused with conventional non-blocking socket operations.
+ *
+ * \note Only available for VMKernel endpoints.
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); int nonblock;
+ * socklen_t len = sizeof nonblock; int fd = socket(af, SOCK_STREAM, 0);
+ * getsockopt(fd, af, SO_VMCI_NONBLOCK_TXRX, &nonblock, &len); ... close(fd);
+ * vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define SO_VMCI_NONBLOCK_TXRX 7
+
+/*
+ * \brief The vSocket equivalent of INADDR_ANY.
+ *
+ * This works for the \c svm_cid field of sockaddr_vm and indicates the context
+ * ID of the current endpoint.
+ *
+ * \see sockaddr_vm
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); struct
+ * sockaddr_vm addr; int fd = socket(af, SOCK_DGRAM, 0); addr.svm_family = af;
+ * addr.svm_cid = VMADDR_CID_ANY; addr.svm_port = 2000; bind(fd, &addr, sizeof
+ * addr); ... close(fd); vmci_sock_release_af_value_fd(vmciFd); \endcode
+ */
+
+#define VMADDR_CID_ANY ((unsigned int)-1)
+
+/*
+ * \brief Bind to any available port.
+ *
+ * Works for the \c svm_port field of sockaddr_vm.
+ *
+ * \see sockaddr_vm
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); struct
+ * sockaddr_vm addr; int fd = socket(af, SOCK_DGRAM, 0); addr.svm_family = af;
+ * addr.svm_cid = VMADDR_CID_ANY; addr.svm_port = VMADDR_PORT_ANY; bind(fd,
+ * &addr, sizeof addr); ... close(fd); vmci_sock_release_af_value_fd(vmciFd);
+ * \endcode
+ */
+
+#define VMADDR_PORT_ANY ((unsigned int)-1)
+
+/*
+ * \brief Invalid vSockets version.
+ *
+ * \see VMCISock_Version()
+ */
+
+#define VMCI_SOCKETS_INVALID_VERSION ((unsigned int)-1)
+
+/*
+ * \brief The epoch (first) component of the vSockets version.
+ *
+ * A single byte representing the epoch component of the vSockets version.
+ *
+ * \see VMCISock_Version()
+ *
+ * An example is given below.
+ *
+ * \code unsigned int ver = VMCISock_Version(); unsigned char epoch =
+ * VMCI_SOCKETS_VERSION_EPOCH(ver); \endcode
+ */
+
+#define VMCI_SOCKETS_VERSION_EPOCH(_v) (((_v) & 0xFF000000) >> 24)
+
+/*
+ * \brief The major (second) component of the vSockets version.
+ *
+ * A single byte representing the major component of the vSockets version.
+ * Typically changes for every major release of a product.
+ *
+ * \see VMCISock_Version()
+ *
+ * An example is given below.
+ *
+ * \code unsigned int ver = VMCISock_Version(); unsigned char major =
+ * VMCI_SOCKETS_VERSION_MAJOR(ver); \endcode
+ */
+
+#define VMCI_SOCKETS_VERSION_MAJOR(_v) (((_v) & 0x00FF0000) >> 16)
+
+/*
+ * \brief The minor (third) component of the vSockets version.
+ *
+ * Two bytes representing the minor component of the vSockets version.
+ *
+ * \see VMCISock_Version()
+ *
+ * An example is given below.
+ *
+ * \code unsigned int ver = VMCISock_Version(); unsigned short minor =
+ * VMCI_SOCKETS_VERSION_MINOR(ver); \endcode
+ */
+
+#define VMCI_SOCKETS_VERSION_MINOR(_v) (((_v) & 0x0000FFFF))
+
+/** \cond PRIVATE */
+
+/** \endcond */
+
+/*
+ * \brief Address structure for vSockets.
+ *
+ * The address family should be set to whatever vmci_sock_get_af_value_fd()
+ * returns. The structure members should all align on their natural boundaries
+ * without resorting to compiler packing directives. The total size of this
+ * structure should be exactly the same as that of \c struct \c sockaddr.
+ *
+ * \see vmci_sock_get_af_value_fd()
+ */
+
+struct sockaddr_vm {
+
+ /** \brief Address family. \see vmci_sock_get_af_value_fd() */
+ sa_family_t svm_family;
+
+ /** \cond PRIVATE */
+ unsigned short svm_reserved1;
+ /** \endcond */
+
+ /** \brief Port. \see VMADDR_PORT_ANY */
+ unsigned int svm_port;
+
+ /** \brief Context ID. \see VMADDR_CID_ANY */
+ unsigned int svm_cid;
+
+ /** \cond PRIVATE */
+ unsigned char svm_zero[sizeof(struct sockaddr) -
+ sizeof(sa_family_t) -
+ sizeof(unsigned short) -
+ sizeof(unsigned int) - sizeof(unsigned int)];
+ /** \endcond */
+};
+
+#if defined(linux) && defined(__KERNEL__)
+int vmci_sock_get_local_c_id(void);
+#else
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+
+#include <stdio.h>
+
+/** \cond PRIVATE */
+#define VMCI_SOCKETS_DEFAULT_DEVICE "/dev/vsock"
+#define VMCI_SOCKETS_CLASSIC_ESX_DEVICE "/vmfs/devices/char/vsock/vsock"
+#define VMCI_SOCKETS_VERSION 1972
+#define VMCI_SOCKETS_GET_AF_VALUE 1976
+#define VMCI_SOCKETS_GET_LOCAL_CID 1977
+/** \endcond */
+
+ /*
+ * VMCISock_Version
+ *
+ * \brief Retrieve the vSockets version.
+ *
+ * Returns the current version of vSockets. The version is a 32-bit
+ * unsigned integer that consist of three components: the epoch, the major
+ * version, and the minor version. Use the \c VMCI_SOCKETS_VERSION macros
+ * to extract the components.
+ *
+ * \see VMCI_SOCKETS_VERSION_EPOCH() \see VMCI_SOCKETS_VERSION_MAJOR() \see
+ * VMCI_SOCKETS_VERSION_MINOR()
+ *
+ * \retval VMCI_SOCKETS_INVALID_VERSION Not available. \retval other The
+ * current version.
+ *
+ * An example is given below.
+ *
+ * \code unsigned int ver = VMCISock_Version(); if (ver !=
+ * VMCI_SOCKETS_INVALID_VERSION) { printf("vSockets version=%d.%d.%d\n",
+ * VMCI_SOCKETS_VERSION_EPOCH(ver), VMCI_SOCKETS_VERSION_MAJOR(ver),
+ * VMCI_SOCKETS_VERSION_MINOR(ver)); } \endcode
+ */
+
+static inline unsigned int VMCISock_Version(void)
+{
+ int fd;
+ unsigned int version;
+
+ fd = open(VMCI_SOCKETS_DEFAULT_DEVICE, O_RDWR);
+ if (fd < 0) {
+ fd = open(VMCI_SOCKETS_CLASSIC_ESX_DEVICE, O_RDWR);
+ if (fd < 0)
+ return VMCI_SOCKETS_INVALID_VERSION;
+
+ }
+
+ if (ioctl(fd, VMCI_SOCKETS_VERSION, &version) < 0)
+ version = VMCI_SOCKETS_INVALID_VERSION;
+
+ close(fd);
+ return version;
+}
+
+ /*
+ * vmci_sock_get_af_value_fd
+ *
+ * \brief Retrieve the address family value for vSockets.
+ *
+ * Returns the value to be used for the VMCI Sockets address family. This
+ * value should be used as the domain argument to \c socket(2) (when you
+ * might otherwise use \c AF_INET). For VMCI Socket-specific options, this
+ * value should also be used for the level argument to \c setsockopt(2)
+ * (when you might otherwise use \c SOL_TCP).
+ *
+ * \see vmci_sock_release_af_value_fd() \see sockaddr_vm
+ *
+ * \param[out] out_fd File descriptor to the VMCI device. The address
+ * family value is valid until this descriptor is closed. This parameter is
+ * only valid if the return value is not -1. Call
+ * vmci_sock_release_af_value_fd() to close this descriptor.
+ *
+ * \retval -1 Not available. \retval other The address family value.
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); if (af !=
+ * -1) { int fd = socket(af, SOCK_STREAM, 0); ... close(fd); close(vmciFd); }
+ * \endcode
+ */
+
+static inline int vmci_sock_get_af_value_fd(int *out_fd)
+{
+ int fd;
+ int family;
+
+ fd = open(VMCI_SOCKETS_DEFAULT_DEVICE, O_RDWR);
+ if (fd < 0) {
+ fd = open(VMCI_SOCKETS_CLASSIC_ESX_DEVICE, O_RDWR);
+ if (fd < 0)
+ return -1;
+
+ }
+
+ if (ioctl(fd, VMCI_SOCKETS_GET_AF_VALUE, &family) < 0)
+ family = -1;
+
+ if (family < 0)
+ close(fd);
+ else if (out_fd)
+ *out_fd = fd;
+
+ return family;
+}
+
+ /** \cond PRIVATE */
+ /*
+ * vmci_sock_get_af_value
+ *
+ * \brief Retrieve the address family value for vSockets.
+ *
+ * Returns the value to be used for the VMCI Sockets address family. This
+ * value should be used as the domain argument to \c socket(2) (when you
+ * might otherwise use \c AF_INET). For VMCI Socket-specific options, this
+ * value should also be used for the level argument to \c setsockopt(2)
+ * (when you might otherwise use \c SOL_TCP).
+ *
+ * \note This function leaves its descriptor to the vsock device open so
+ * that the socket implementation knows that the socket family is still in
+ * use. This is done because the address family is registered with the
+ * kernel on-demand and a notification is needed to unregister the address
+ * family. Use of this function is thus discouraged; please use
+ * vmci_sock_get_af_value_fd() instead.
+ *
+ * \see vmci_sock_get_af_value_fd() \see sockaddr_vm
+ *
+ * \retval -1 Not available. \retval other The address family value.
+ *
+ * An example is given below.
+ *
+ * \code int af = vmci_sock_get_af_value(); if (af != -1) { int fd =
+ * socket(af, SOCK_STREAM, 0); ... close(fd); } \endcode
+ */
+
+static inline int vmci_sock_get_af_value(void)
+{
+ return vmci_sock_get_af_value_fd(NULL);
+}
+
+ /** \endcond PRIVATE */
+
+ /*
+ * vmci_sock_release_af_value_fd
+ *
+ * \brief Release the file descriptor obtained when retrieving the address
+ * family value.
+ *
+ * Use this to release the file descriptor obtained by calling
+ * vmci_sock_get_af_value_fd().
+ *
+ * \see vmci_sock_get_af_value_fd()
+ *
+ * \param[in] fd File descriptor to the VMCI device.
+ */
+
+static inline void vmci_sock_release_af_value_fd(int fd)
+{
+ if (fd >= 0)
+ close(fd);
+
+}
+
+ /*
+ * vmci_sock_get_local_c_id
+ *
+ * \brief Retrieve the current context ID.
+ *
+ * \see VMADDR_CID_ANY
+ *
+ * \retval VMADDR_CID_ANY Not available. \retval other The current context
+ * ID.
+ *
+ * An example is given below.
+ *
+ * \code int vmciFd; int af = vmci_sock_get_af_value_fd(&vmciFd); struct
+ * sockaddr_vm addr; addr.svm_family = af; addr.svm_cid =
+ * vmci_sock_get_local_c_id(); vmci_sock_release_af_value_fd(vmciFd);
+ * \endcode
+ */
+
+static inline unsigned int vmci_sock_get_local_c_id(void)
+{
+ int fd;
+ unsigned int context_id;
+
+ fd = open(VMCI_SOCKETS_DEFAULT_DEVICE, O_RDWR);
+ if (fd < 0) {
+ fd = open(VMCI_SOCKETS_CLASSIC_ESX_DEVICE, O_RDWR);
+ if (fd < 0)
+ return VMADDR_CID_ANY;
+
+ }
+
+ if (ioctl(fd, VMCI_SOCKETS_GET_LOCAL_CID, &context_id) < 0)
+ context_id = VMADDR_CID_ANY;
+
+ close(fd);
+ return context_id;
+}
+#endif
+
+#endif
diff --git a/net/vmw_vsock/vmci_sockets_packet.h b/net/vmw_vsock/vmci_sockets_packet.h
new file mode 100644
index 0000000..fc9f434
--- /dev/null
+++ b/net/vmw_vsock/vmci_sockets_packet.h
@@ -0,0 +1,106 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vmci_sockets_packet.h --
+ *
+ * Definition of VMCI Sockets packet format, constants, and types.
+ */
+
+#ifndef _VMCI_SOCKETS_PACKET_H_
+#define _VMCI_SOCKETS_PACKET_H_
+
+#include <linux/vmw_vmci_defs.h>
+#include <linux/vmw_vmci_api.h>
+
+/*
+ * STREAM control packets.
+ */
+
+/* If the packet format changes in a release then this should change too. */
+#define VSOCK_PACKET_VERSION 1
+
+/* The resource ID on which control packets are sent. */
+#define VSOCK_PACKET_RID 1
+
+/*
+ * Assert that the given packet is valid. We check that the two original
+ * reserved fields equal zero because the version of the common code that
+ * shipped with ESX 4.0 and WS 6.5 did so and will return a RST packet if they
+ * aren't set that way. For newer packet types added after that release we
+ * don't do this.
+ */
+#define VSOCK_PACKET_ASSERT(_p) \
+ do { \
+ ASSERT((_p)->type < VSOCK_PACKET_TYPE_MAX); \
+ if ((_p)->type < VSOCK_PACKET_TYPE_REQUEST2) { \
+ ASSERT(0 == (_p)->proto); \
+ ASSERT(0 == (_p)->_reserved2); \
+ } \
+ } while (0)
+
+typedef enum vsock_packet_type {
+ VSOCK_PACKET_TYPE_INVALID = 0,
+ VSOCK_PACKET_TYPE_REQUEST,
+ VSOCK_PACKET_TYPE_NEGOTIATE,
+ VSOCK_PACKET_TYPE_OFFER,
+ VSOCK_PACKET_TYPE_ATTACH,
+ VSOCK_PACKET_TYPE_WROTE,
+ VSOCK_PACKET_TYPE_READ,
+ VSOCK_PACKET_TYPE_RST,
+ VSOCK_PACKET_TYPE_SHUTDOWN,
+ VSOCK_PACKET_TYPE_WAITING_WRITE,
+ VSOCK_PACKET_TYPE_WAITING_READ,
+ VSOCK_PACKET_TYPE_REQUEST2,
+ VSOCK_PACKET_TYPE_NEGOTIATE2,
+ VSOCK_PACKET_TYPE_MAX
+} vsock_packet_type;
+
+typedef u16 vsock_proto_version;
+#define VSOCK_PROTO_INVALID 0
+#define VSOCK_PROTO_PKT_ON_NOTIFY (1 << 0)
+
+#define VSOCK_PROTO_ALL_SUPPORTED (VSOCK_PROTO_PKT_ON_NOTIFY)
+
+typedef struct vsock_waiting_info {
+ u64 generation;
+ u64 offset;
+} vsock_waiting_info;
+
+/*
+ * Control packet type for STREAM sockets. DGRAMs have no control packets nor
+ * special packet header for data packets, they are just raw VMCI DGRAM
+ * messages. For STREAMs, control packets are sent over the control channel
+ * while data is written and read directly from queue pairs with no packet
+ * format.
+ */
+typedef struct vsock_packet {
+ struct vmci_datagram dg;
+ u8 version;
+ u8 type;
+ vsock_proto_version proto;
+
+ u32 src_port;
+ u32 dst_port;
+ u32 _reserved2;
+ union {
+ u64 size;
+ u64 mode;
+ struct vmci_handle handle;
+ vsock_waiting_info wait;
+ } u;
+} vsock_packet;
+
+#endif
diff --git a/net/vmw_vsock/vsock_common.h b/net/vmw_vsock/vsock_common.h
new file mode 100644
index 0000000..fd7f2cd
--- /dev/null
+++ b/net/vmw_vsock/vsock_common.h
@@ -0,0 +1,130 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vsockCommon.h --
+ *
+ * VSockets common constants, types and functions.
+ */
+
+#ifndef _VSOCK_COMMON_H_
+#define _VSOCK_COMMON_H_
+
+/*
+ * vmci_sock_get_af_value_int is defined separately from vmci_sock_get_af_value
+ * because it is used in several different contexts. In particular it is called
+ * from vsock_addr.c which gets compiled into both our kernel modules as well
+ * as the user level vsock library. In the linux kernel we need different
+ * behavior than external kernel modules using VMCI Sockets api inside the
+ * kernel. FIXME
+ */
+
+#if defined __KERNEL__
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <asm/page.h>
+#else
+/* In userland, just use the normal exported userlevel api. */
+#define vmci_sock_get_af_value_int() vmci_sock_get_af_value()
+#endif
+
+#include <linux/vmw_vmci_defs.h>
+#include <linux/vmw_vmci_api.h>
+
+#include "vmci_sockets.h"
+#include "vsock_addr.h"
+
+#define ASSERT(cond) BUG_ON(!(cond))
+#define ASSERT_ON_COMPILE(cond) BUILD_BUG_ON(!(cond))
+
+#ifdef __x86_64__
+#define FMT64 "ll"
+#else
+#define FMT64 "L"
+#endif
+
+#ifndef PAGE_SHIFT
+#if defined __i386__
+#define PAGE_SHIFT 12
+#elif defined __arm__
+#define PAGE_SHIFT 12
+#else
+#error
+#endif
+#endif
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE (1<<PAGE_SHIFT)
+#endif
+
+#define MAX_UINT32 ((u32)0xffffffff)
+
+#ifndef ESYSNOTREADY
+#define ESYSNOTREADY EOPNOTSUPP
+#endif
+
+#define sockerr() errno
+#define sockerr2err(_e) (((_e) > 0) ? -(_e) : (_e))
+#define SS_LISTEN 255
+
+extern vmci_id vmci_get_context_id(void);
+
+/*
+ * Helper function to determine if the given handle points to the local context.
+ * Returns TRUE if the given handle is for the local context, FALSE otherwise.
+ */
+
+static inline bool vsock_vmci_is_local(struct vmci_handle handle)
+{
+ return vmci_get_context_id() == VMCI_HANDLE_TO_CONTEXT_ID(handle);
+}
+
+/*
+ * Helper function to convert from a VMCI error code to a VSock error code.
+ */
+
+static inline s32 vsock_vmci_error_to_vsock_error(s32 vmci_error)
+{
+ int err;
+
+ switch (vmci_error) {
+ case VMCI_ERROR_NO_MEM:
+ err = ENOMEM;
+ break;
+ case VMCI_ERROR_DUPLICATE_ENTRY:
+ case VMCI_ERROR_ALREADY_EXISTS:
+ err = EADDRINUSE;
+ break;
+ case VMCI_ERROR_NO_ACCESS:
+ err = EPERM;
+ break;
+ case VMCI_ERROR_NO_RESOURCES:
+ err = ENOBUFS;
+ break;
+ case VMCI_ERROR_INVALID_RESOURCE:
+ err = EHOSTUNREACH;
+ break;
+ case VMCI_ERROR_MODULE_NOT_LOADED:
+ err = ESYSNOTREADY;
+ break;
+ case VMCI_ERROR_INVALID_ARGS:
+ default:
+ err = EINVAL;
+ }
+
+ return sockerr2err(err);
+}
+
+#endif
diff --git a/net/vmw_vsock/vsock_packet.h b/net/vmw_vsock/vsock_packet.h
new file mode 100644
index 0000000..76bcac0
--- /dev/null
+++ b/net/vmw_vsock/vsock_packet.h
@@ -0,0 +1,131 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vsockPacket.h --
+ *
+ * Packet constants, types and functions.
+ */
+
+#ifndef _VSOCK_PACKET_H_
+#define _VSOCK_PACKET_H_
+
+#include "vmci_sockets_packet.h"
+
+/*
+ *
+ * vsock_packet_init --
+ *
+ * Initialize the given packet. The packet version is set and the fields are
+ * filled out. Reserved fields are cleared.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void
+vsock_packet_init(vsock_packet *pkt,
+ struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ u8 type,
+ u64 size,
+ u64 mode,
+ vsock_waiting_info *wait,
+ vsock_proto_version proto, struct vmci_handle handle)
+{
+ BUG_ON(!pkt);
+ BUG_ON(vsock_addr_validate(src) != 0);
+ BUG_ON(vsock_addr_validate(dst) != 0);
+
+ /*
+ * We register the stream control handler as an any cid handle so we
+ * must always send from a source address of VMADDR_CID_ANY
+ */
+ pkt->dg.src = VMCI_MAKE_HANDLE(VMADDR_CID_ANY, VSOCK_PACKET_RID);
+ pkt->dg.dst = VMCI_MAKE_HANDLE(dst->svm_cid, VSOCK_PACKET_RID);
+ pkt->dg.payload_size = sizeof *pkt - sizeof pkt->dg;
+ pkt->version = VSOCK_PACKET_VERSION;
+ pkt->type = type;
+ pkt->src_port = src->svm_port;
+ pkt->dst_port = dst->svm_port;
+ memset(&pkt->proto, 0, sizeof pkt->proto);
+ memset(&pkt->_reserved2, 0, sizeof pkt->_reserved2);
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_INVALID:
+ pkt->u.size = 0;
+ break;
+
+ case VSOCK_PACKET_TYPE_REQUEST:
+ case VSOCK_PACKET_TYPE_NEGOTIATE:
+ pkt->u.size = size;
+ break;
+
+ case VSOCK_PACKET_TYPE_OFFER:
+ case VSOCK_PACKET_TYPE_ATTACH:
+ pkt->u.handle = handle;
+ break;
+
+ case VSOCK_PACKET_TYPE_WROTE:
+ case VSOCK_PACKET_TYPE_READ:
+ case VSOCK_PACKET_TYPE_RST:
+ pkt->u.size = 0;
+ break;
+
+ case VSOCK_PACKET_TYPE_SHUTDOWN:
+ pkt->u.mode = mode;
+ break;
+
+ case VSOCK_PACKET_TYPE_WAITING_READ:
+ case VSOCK_PACKET_TYPE_WAITING_WRITE:
+ ASSERT(wait);
+ memcpy(&pkt->u.wait, wait, sizeof pkt->u.wait);
+ break;
+
+ case VSOCK_PACKET_TYPE_REQUEST2:
+ case VSOCK_PACKET_TYPE_NEGOTIATE2:
+ pkt->u.size = size;
+ pkt->proto = proto;
+ break;
+ }
+
+ VSOCK_PACKET_ASSERT(pkt);
+}
+
+/*
+ *
+ * vsock_packet_get_addresses --
+ *
+ * Get the local and remote addresses from the given packet.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void
+vsock_packet_get_addresses(vsock_packet *pkt,
+ struct sockaddr_vm *local,
+ struct sockaddr_vm *remote)
+{
+ VSOCK_PACKET_ASSERT(pkt);
+ vsock_addr_init(local, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.dst),
+ pkt->dst_port);
+ vsock_addr_init(remote, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src),
+ pkt->src_port);
+}
+
+#endif
diff --git a/net/vmw_vsock/vsock_version.h b/net/vmw_vsock/vsock_version.h
new file mode 100644
index 0000000..9a6a63b
--- /dev/null
+++ b/net/vmw_vsock/vsock_version.h
@@ -0,0 +1,29 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2011-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vsock_version.h --
+ *
+ * Version definitions for the Linux vsock driver.
+ */
+
+#ifndef _VSOCK_VERSION_H_
+#define _VSOCK_VERSION_H_
+
+#define VSOCK_DRIVER_VERSION 1.0.0.0-k
+#define VSOCK_DRIVER_VERSION_COMMAS 1,0,0,0
+#define VSOCK_DRIVER_VERSION_STRING "1.0.0.0-k"
+
+#endif /* _VSOCK_VERSION_H_ */
^ permalink raw reply related
* [PATCH 5/6] VSOCK: utility functions.
From: George Zhang @ 2012-11-05 18:01 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
VSOCK utility functions for Linux VSocket module.
Signed-off-by: George Zhang <georgezhang@vmware.com>
---
net/vmw_vsock/util.c | 626 ++++++++++++++++++++++++++++++++++++++++++++++++++
net/vmw_vsock/util.h | 312 +++++++++++++++++++++++++
2 files changed, 938 insertions(+), 0 deletions(-)
create mode 100644 net/vmw_vsock/util.c
create mode 100644 net/vmw_vsock/util.h
diff --git a/net/vmw_vsock/util.c b/net/vmw_vsock/util.c
new file mode 100644
index 0000000..1c42b23
--- /dev/null
+++ b/net/vmw_vsock/util.c
@@ -0,0 +1,626 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * util.c --
+ *
+ * Utility functions for Linux VSocket module.
+ */
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/socket.h>
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+
+#include "af_vsock.h"
+#include "util.h"
+
+struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
+struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
+
+DEFINE_SPINLOCK(vsock_table_lock);
+
+/*
+ *
+ * vsock_vmci_log_pkt --
+ *
+ * Logs the provided packet.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+void vsock_vmci_log_pkt(char const *function, u32 line, vsock_packet *pkt)
+{
+ char buf[256];
+ char *cur = buf;
+ int left = sizeof buf;
+ int written = 0;
+ char *type_strings[] = {
+ [VSOCK_PACKET_TYPE_INVALID] = "INVALID",
+ [VSOCK_PACKET_TYPE_REQUEST] = "REQUEST",
+ [VSOCK_PACKET_TYPE_NEGOTIATE] = "NEGOTIATE",
+ [VSOCK_PACKET_TYPE_OFFER] = "OFFER",
+ [VSOCK_PACKET_TYPE_ATTACH] = "ATTACH",
+ [VSOCK_PACKET_TYPE_WROTE] = "WROTE",
+ [VSOCK_PACKET_TYPE_READ] = "READ",
+ [VSOCK_PACKET_TYPE_RST] = "RST",
+ [VSOCK_PACKET_TYPE_SHUTDOWN] = "SHUTDOWN",
+ [VSOCK_PACKET_TYPE_WAITING_WRITE] = "WAITING_WRITE",
+ [VSOCK_PACKET_TYPE_WAITING_READ] = "WAITING_READ",
+ [VSOCK_PACKET_TYPE_REQUEST2] = "REQUEST2",
+ [VSOCK_PACKET_TYPE_NEGOTIATE2] = "NEGOTIATE2",
+ };
+
+ written = snprintf(cur, left, "PKT: %u:%u -> %u:%u",
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src),
+ pkt->src_port,
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.dst),
+ pkt->dst_port);
+ if (written >= left)
+ goto error;
+
+ left -= written;
+ cur += written;
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_REQUEST:
+ case VSOCK_PACKET_TYPE_NEGOTIATE:
+ written = snprintf(cur, left, ", %s, size = %" FMT64 "u",
+ type_strings[pkt->type], pkt->u.size);
+ break;
+
+ case VSOCK_PACKET_TYPE_OFFER:
+ case VSOCK_PACKET_TYPE_ATTACH:
+ written = snprintf(cur, left, ", %s, handle = %u:%u",
+ type_strings[pkt->type],
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->u.handle),
+ VMCI_HANDLE_TO_RESOURCE_ID(pkt->u.handle));
+ break;
+
+ case VSOCK_PACKET_TYPE_WROTE:
+ case VSOCK_PACKET_TYPE_READ:
+ case VSOCK_PACKET_TYPE_RST:
+ written = snprintf(cur, left, ", %s", type_strings[pkt->type]);
+ break;
+ case VSOCK_PACKET_TYPE_SHUTDOWN: {
+ bool recv;
+ bool send;
+
+ recv = pkt->u.mode & RCV_SHUTDOWN;
+ send = pkt->u.mode & SEND_SHUTDOWN;
+ written = snprintf(cur, left, ", %s, mode = %c%c",
+ type_strings[pkt->type],
+ recv ? 'R' : ' ', send ? 'S' : ' ');
+ }
+ break;
+
+ case VSOCK_PACKET_TYPE_WAITING_WRITE:
+ case VSOCK_PACKET_TYPE_WAITING_READ:
+ written = snprintf(cur, left, ", %s, generation = %" FMT64 "u, "
+ "offset = %" FMT64 "u",
+ type_strings[pkt->type],
+ pkt->u.wait.generation, pkt->u.wait.offset);
+
+ break;
+
+ case VSOCK_PACKET_TYPE_REQUEST2:
+ case VSOCK_PACKET_TYPE_NEGOTIATE2:
+ written = snprintf(cur, left, ", %s, size = %" FMT64 "u, "
+ "proto = %u",
+ type_strings[pkt->type], pkt->u.size,
+ pkt->proto);
+ break;
+
+ default:
+ written = snprintf(cur, left, ", unrecognized type");
+ }
+
+ if (written >= left)
+ goto error;
+
+ left -= written;
+ cur += written;
+
+ written = snprintf(cur, left, " [%s:%u]\n", function, line);
+ if (written >= left)
+ goto error;
+
+ return;
+
+error:
+ pr_err("could not log packet\n");
+}
+
+/*
+ *
+ * vsock_vmci_init_tables --
+ *
+ * Initializes the tables used for socket lookup.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+void vsock_vmci_init_tables(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++)
+ INIT_LIST_HEAD(&vsock_bind_table[i]);
+
+ for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
+ INIT_LIST_HEAD(&vsock_connected_table[i]);
+}
+
+/*
+ *
+ * __vsock_vmci_insert_bound --
+ *
+ * Inserts socket into the bound table.
+ *
+ * Note that this assumes any necessary locks are held.
+ *
+ * Results: None.
+ *
+ * Side effects: The reference count for sk is incremented.
+ */
+
+void __vsock_vmci_insert_bound(struct list_head *list, struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ sock_hold(sk);
+ list_add(&vsk->bound_table, list);
+}
+
+/*
+ *
+ * __vsock_vmci_insert_connected --
+ *
+ * Inserts socket into the connected table.
+ *
+ * Note that this assumes any necessary locks are held.
+ *
+ * Results: None.
+ *
+ * Side effects: The reference count for sk is incremented.
+ */
+
+void __vsock_vmci_insert_connected(struct list_head *list, struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ sock_hold(sk);
+ list_add(&vsk->connected_table, list);
+}
+
+/*
+ *
+ * __vsock_vmci_remove_bound --
+ *
+ * Removes socket from the bound table.
+ *
+ * Note that this assumes any necessary locks are held.
+ *
+ * Results: None.
+ *
+ * Side effects: The reference count for sk is decremented.
+ */
+
+void __vsock_vmci_remove_bound(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+
+ ASSERT(__vsock_vmci_in_bound_table(sk));
+
+ vsk = vsock_sk(sk);
+
+ list_del_init(&vsk->bound_table);
+ sock_put(sk);
+}
+
+/*
+ *
+ * __vsock_vmci_remove_connected --
+ *
+ * Removes socket from the connected table.
+ *
+ * Note that this assumes any necessary locks are held.
+ *
+ * Results: None.
+ *
+ * Side effects: The reference count for sk is decremented.
+ */
+
+void __vsock_vmci_remove_connected(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+
+ ASSERT(__vsock_vmci_in_connected_table(sk));
+
+ vsk = vsock_sk(sk);
+
+ list_del_init(&vsk->connected_table);
+ sock_put(sk);
+}
+
+/*
+ *
+ * __vsock_vmci_find_bound_socket --
+ *
+ * Finds the socket corresponding to the provided address in the bound sockets
+ * hash table.
+ *
+ * Note that this assumes any necessary locks are held.
+ *
+ * Results: The sock structure if found, NULL if not found.
+ *
+ * Side effects: None.
+ */
+
+struct sock *__vsock_vmci_find_bound_socket(struct sockaddr_vm *addr)
+{
+ vsock_vmci_sock *vsk;
+
+ list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
+ if (vsock_addr_equals_addr_any(addr, &vsk->local_addr)) {
+ return sk_vsock(vsk);
+ }
+ }
+
+ return NULL;
+}
+
+/*
+ *
+ * __vsock_vmci_find_connected_socket --
+ *
+ * Finds the socket corresponding to the provided addresses in the connected
+ * sockets hash table.
+ *
+ * Note that this assumes any necessary locks are held.
+ *
+ * Results: The sock structure if found, NULL if not found.
+ *
+ * Side effects: None.
+ */
+
+struct sock *__vsock_vmci_find_connected_socket(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst)
+{
+ vsock_vmci_sock *vsk;
+
+ list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
+ connected_table) {
+ if (vsock_addr_equals_addr(src, &vsk->remote_addr)
+ && vsock_addr_equals_addr(dst, &vsk->local_addr)) {
+ return sk_vsock(vsk);
+ }
+ }
+
+ return NULL;
+}
+
+/*
+ *
+ * __vsock_vmci_in_bound_table --
+ *
+ * Determines whether the provided socket is in the bound table.
+ *
+ * Results: TRUE is socket is in bound table, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool __vsock_vmci_in_bound_table(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ return !list_empty(&vsk->bound_table);
+}
+
+/*
+ *
+ * __vsock_vmci_in_connected_table --
+ *
+ * Determines whether the provided socket is in the connected table.
+ *
+ * Results: TRUE is socket is in connected table, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool __vsock_vmci_in_connected_table(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ return !list_empty(&vsk->connected_table);
+}
+
+/*
+ *
+ * vsock_vmci_get_pending --
+ *
+ * Retrieves a pending connection that matches the addresses specified in the
+ * provided packet.
+ *
+ * Assumes the socket lock is held for listener.
+ *
+ * Results: Socket of the pending connection on success, NULL if not found.
+ *
+ * Side effects: A reference is held on the socket until the release function
+ * is called.
+ */
+
+struct sock *vsock_vmci_get_pending(struct sock *listener, vsock_packet *pkt)
+{
+ vsock_vmci_sock *vlistener;
+ vsock_vmci_sock *vpending;
+ struct sock *pending;
+
+ vlistener = vsock_sk(listener);
+
+ list_for_each_entry(vpending, &vlistener->pending_links,
+ pending_links) {
+ struct sockaddr_vm src;
+ struct sockaddr_vm dst;
+
+ vsock_addr_init(&src, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src),
+ pkt->src_port);
+ vsock_addr_init(&dst, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.dst),
+ pkt->dst_port);
+
+ if (vsock_addr_equals_addr(&src, &vpending->remote_addr) &&
+ vsock_addr_equals_addr(&dst, &vpending->local_addr)) {
+ pending = sk_vsock(vpending);
+ sock_hold(pending);
+ goto found;
+ }
+ }
+
+ pending = NULL;
+found:
+ return pending;
+
+}
+
+/*
+ *
+ * vsock_vmci_release_pending --
+ *
+ * Releases the reference on a socket previously obtained by a call to
+ * vsock_vmci_get_pending().
+ *
+ * Results: None.
+ *
+ * Side effects: The socket may be freed if this was the last reference.
+ */
+
+void vsock_vmci_release_pending(struct sock *pending)
+{
+ sock_put(pending);
+}
+
+/*
+ *
+ * vsock_vmci_add_pending --
+ *
+ * Adds a pending connection on listener's pending list.
+ *
+ * Assumes the socket lock is held for listener. Assumes the socket lock is
+ * held for pending.
+ *
+ * Results: None.
+ *
+ * Side effects: The reference count of the sockets is incremented.
+ */
+
+void vsock_vmci_add_pending(struct sock *listener, struct sock *pending)
+{
+ vsock_vmci_sock *vlistener;
+ vsock_vmci_sock *vpending;
+
+ vlistener = vsock_sk(listener);
+ vpending = vsock_sk(pending);
+
+ sock_hold(pending);
+ sock_hold(listener);
+ list_add_tail(&vpending->pending_links, &vlistener->pending_links);
+}
+
+/*
+ *
+ * vsock_vmci_remove_pending --
+ *
+ * Removes a pending connection from the listener's pending list.
+ *
+ * Assumes the socket lock is held for listener. Assumes the socket lock is
+ * held for pending.
+ *
+ * Results: None.
+ *
+ * Side effects: The reference count of the sockets is decremented.
+ */
+
+void vsock_vmci_remove_pending(struct sock *listener, struct sock *pending)
+{
+ vsock_vmci_sock *vpending = vsock_sk(pending);
+
+ list_del_init(&vpending->pending_links);
+ sock_put(listener);
+ sock_put(pending);
+}
+
+/*
+ *
+ * vsock_vmci_enqueue_accept --
+ *
+ * Enqueues the connected socket on the listening socket's accepting queue.
+ *
+ * Assumes the socket lock is held for listener. Assumes the socket lock is
+ * held for connected.
+ *
+ * Results: None.
+ *
+ * Side effects: The sockets' reference counts are incremented.
+ */
+
+void vsock_vmci_enqueue_accept(struct sock *listener, struct sock *connected)
+{
+ vsock_vmci_sock *vlistener;
+ vsock_vmci_sock *vconnected;
+
+ vlistener = vsock_sk(listener);
+ vconnected = vsock_sk(connected);
+
+ sock_hold(connected);
+ sock_hold(listener);
+ list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue);
+}
+
+/*
+ *
+ * vsock_vmci_dequeue_accept --
+ *
+ * Dequeues the next connected socket from the listening socket's accept queue.
+ *
+ * Assumes the socket lock is held for listener.
+ *
+ * Note that the caller must call sock_put() on the returned socket once it is
+ * done with the socket.
+ *
+ * Results: The next socket from the queue, or NULL if the queue is empty.
+ *
+ * Side effects: The reference count of the listener is decremented.
+ */
+
+struct sock *vsock_vmci_dequeue_accept(struct sock *listener)
+{
+ vsock_vmci_sock *vlistener;
+ vsock_vmci_sock *vconnected;
+
+ vlistener = vsock_sk(listener);
+
+ if (list_empty(&vlistener->accept_queue))
+ return NULL;
+
+ vconnected = list_entry(vlistener->accept_queue.next,
+ vsock_vmci_sock, accept_queue);
+ ASSERT(vconnected);
+
+ list_del_init(&vconnected->accept_queue);
+ sock_put(listener);
+ /*
+ * The caller will need a reference on the connected socket so we let
+ * it call sock_put().
+ */
+
+ ASSERT(sk_vsock(vconnected));
+ return sk_vsock(vconnected);
+}
+
+/*
+ *
+ * vsock_vmci_remove_accept --
+ *
+ * Removes a socket from the accept queue of a listening socket.
+ *
+ * Assumes the socket lock is held for listener. Assumes the socket lock is
+ * held for connected.
+ *
+ * Results: None.
+ *
+ * Side effects: The sockets' reference counts are decremented.
+ */
+
+void vsock_vmci_remove_accept(struct sock *listener, struct sock *connected)
+{
+ vsock_vmci_sock *vconnected;
+
+ if (!vsock_vmci_in_accept_queue(connected))
+ return;
+
+ vconnected = vsock_sk(connected);
+ ASSERT(vconnected->listener == listener);
+
+ list_del_init(&vconnected->accept_queue);
+ sock_put(listener);
+ sock_put(connected);
+}
+
+/*
+ *
+ * vsock_vmci_in_accept_queue --
+ *
+ * Determines whether a socket is on an accept queue.
+ *
+ * Assumes the socket lock is held for sk.
+ *
+ * Results: TRUE if the socket is in an accept queue, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_vmci_in_accept_queue(struct sock *sk)
+{
+ /*
+ * If our accept queue isn't empty, it means we're linked into some
+ * listener socket's accept queue.
+ */
+ return !vsock_vmci_is_accept_queue_empty(sk);
+}
+
+/*
+ *
+ * vsock_vmci_is_accept_queue_empty --
+ *
+ * Determines whether the provided socket's accept queue is empty.
+ *
+ * Assumes the socket lock is held for sk.
+ *
+ * Results: TRUE if the socket's accept queue is empty, FALSE otherwsise.
+ *
+ * Side effects: None.
+ *
+ */
+
+bool vsock_vmci_is_accept_queue_empty(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+ return list_empty(&vsk->accept_queue);
+}
+
+/*
+ *
+ * vsock_vmci_is_pending --
+ *
+ * Determines whether a socket is pending.
+ *
+ * Assumes the socket lock is held for sk.
+ *
+ * Results: TRUE if the socket is pending, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_vmci_is_pending(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+ return !list_empty(&vsk->pending_links);
+}
diff --git a/net/vmw_vsock/util.h b/net/vmw_vsock/util.h
new file mode 100644
index 0000000..50ed6c8
--- /dev/null
+++ b/net/vmw_vsock/util.h
@@ -0,0 +1,312 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * util.h --
+ *
+ * Utility functions for Linux VSocket module.
+ */
+
+#ifndef __UTIL_H__
+#define __UTIL_H__
+
+#include <linux/types.h>
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+#include <linux/spinlock.h>
+
+#include "vsock_common.h"
+#include "vsock_packet.h"
+
+/*
+ * Each bound VSocket is stored in the bind hash table and each connected
+ * VSocket is stored in the connected hash table.
+ *
+ * Unbound sockets are all put on the same list attached to the end of the hash
+ * table (vsock_unbound_sockets). Bound sockets are added to the hash table in
+ * the bucket that their local address hashes to (vsock_bound_sockets(addr)
+ * represents the list that addr hashes to).
+ *
+ * Specifically, we initialize the vsock_bind_table array to a size of
+ * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through
+ * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and
+ * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function
+ * mods with VSOCK_HASH_SIZE - 1 to ensure this.
+ */
+#define VSOCK_HASH_SIZE 251
+#define LAST_RESERVED_PORT 1023
+#define MAX_PORT_RETRIES 24
+
+extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
+extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
+
+extern spinlock_t vsock_table_lock;
+
+#define VSOCK_HASH(addr) ((addr)->svm_port % (VSOCK_HASH_SIZE - 1))
+#define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)])
+#define vsock_unbound_sockets (&vsock_bind_table[VSOCK_HASH_SIZE])
+
+/* XXX This can probably be implemented in a better way. */
+#define VSOCK_CONN_HASH(src, dst) \
+ (((src)->svm_cid ^ (dst)->svm_port) % (VSOCK_HASH_SIZE - 1))
+#define vsock_connected_sockets(src, dst) \
+ (&vsock_connected_table[VSOCK_CONN_HASH(src, dst)])
+#define vsock_connected_sockets_vsk(vsk) \
+ vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr)
+
+/*
+ * Prototypes.
+ */
+
+void vsock_vmci_log_pkt(char const *function, u32 line, vsock_packet *pkt);
+
+void vsock_vmci_init_tables(void);
+void __vsock_vmci_insert_bound(struct list_head *list, struct sock *sk);
+void __vsock_vmci_insert_connected(struct list_head *list, struct sock *sk);
+void __vsock_vmci_remove_bound(struct sock *sk);
+void __vsock_vmci_remove_connected(struct sock *sk);
+struct sock *__vsock_vmci_find_bound_socket(struct sockaddr_vm *addr);
+struct sock *__vsock_vmci_find_connected_socket(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst);
+bool __vsock_vmci_in_bound_table(struct sock *sk);
+bool __vsock_vmci_in_connected_table(struct sock *sk);
+
+struct sock *vsock_vmci_get_pending(struct sock *listener, vsock_packet *pkt);
+void vsock_vmci_release_pending(struct sock *pending);
+void vsock_vmci_add_pending(struct sock *listener, struct sock *pending);
+void vsock_vmci_remove_pending(struct sock *listener, struct sock *pending);
+void vsock_vmci_enqueue_accept(struct sock *listener, struct sock *connected);
+struct sock *vsock_vmci_dequeue_accept(struct sock *listener);
+void vsock_vmci_remove_accept(struct sock *listener, struct sock *connected);
+bool vsock_vmci_in_accept_queue(struct sock *sk);
+bool vsock_vmci_is_accept_queue_empty(struct sock *sk);
+bool vsock_vmci_is_pending(struct sock *sk);
+
+static inline void vsock_vmci_insert_bound(struct list_head *list,
+ struct sock *sk);
+static inline void vsock_vmci_insert_connected(struct list_head *list,
+ struct sock *sk);
+static inline void vsock_vmci_remove_bound(struct sock *sk);
+static inline void vsock_vmci_remove_connected(struct sock *sk);
+static inline struct sock *vsock_vmci_find_bound_socket(struct sockaddr_vm
+ *addr);
+static inline struct sock *vsock_vmci_find_connected_socket(struct sockaddr_vm
+ *src,
+ struct sockaddr_vm
+ *dst);
+static inline bool vsock_vmci_in_bound_table(struct sock *sk);
+static inline bool vsock_vmci_in_connected_table(struct sock *sk);
+
+/*
+ *
+ * vsock_vmci_insert_bound --
+ *
+ * Inserts socket into the bound table.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these may be called from tasklets.
+ *
+ * Results: None.
+ *
+ * Side effects: vsock_table_lock is acquired and released.
+ */
+
+static inline void
+vsock_vmci_insert_bound(struct list_head *list, struct sock *sk)
+{
+ spin_lock_bh(&vsock_table_lock);
+ __vsock_vmci_insert_bound(list, sk);
+ spin_unlock_bh(&vsock_table_lock);
+}
+
+/*
+ *
+ * vsock_vmci_insert_connected --
+ *
+ * Inserts socket into the connected table.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these may be called from tasklets.
+ *
+ * Results: None.
+ *
+ * Side effects: vsock_table_lock is acquired and released.
+ */
+
+static inline void
+vsock_vmci_insert_connected(struct list_head *list, struct sock *sk)
+{
+ spin_lock_bh(&vsock_table_lock);
+ __vsock_vmci_insert_connected(list, sk);
+ spin_unlock_bh(&vsock_table_lock);
+}
+
+/*
+ *
+ * vsock_vmci_remove_bound --
+ *
+ * Removes socket from the bound list.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these may be called from tasklets.
+ *
+ * Results: None.
+ *
+ * Side effects: vsock_table_lock is acquired and released.
+ */
+
+static inline void vsock_vmci_remove_bound(struct sock *sk)
+{
+ spin_lock_bh(&vsock_table_lock);
+ __vsock_vmci_remove_bound(sk);
+ spin_unlock_bh(&vsock_table_lock);
+}
+
+/*
+ *
+ * vsock_vmci_remove_connected --
+ *
+ * Removes socket from the connected list.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these may be called from tasklets.
+ *
+ * Results: None.
+ *
+ * Side effects: vsock_table_lock is acquired and released.
+ */
+
+static inline void vsock_vmci_remove_connected(struct sock *sk)
+{
+ spin_lock_bh(&vsock_table_lock);
+ __vsock_vmci_remove_connected(sk);
+ spin_unlock_bh(&vsock_table_lock);
+}
+
+/*
+ *
+ * vsock_vmci_find_bound_socket --
+ *
+ * Finds the socket corresponding to the provided address in the bound sockets
+ * hash table.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these are called from tasklets.
+ *
+ * Results: The sock structure if found, NULL on failure.
+ *
+ * Side effects: vsock_table_lock is acquired and released. The socket's
+ * reference count is increased.
+ */
+
+static inline struct sock *vsock_vmci_find_bound_socket(struct sockaddr_vm
+ *addr)
+{
+ struct sock *sk;
+
+ spin_lock_bh(&vsock_table_lock);
+ sk = __vsock_vmci_find_bound_socket(addr);
+ if (sk)
+ sock_hold(sk);
+
+ spin_unlock_bh(&vsock_table_lock);
+
+ return sk;
+}
+
+/*
+ *
+ * vsock_vmci_find_connected_socket --
+ *
+ * Finds the socket corresponding to the provided address in the connected
+ * sockets hash table.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these are called from tasklets.
+ *
+ * Results: The sock structure if found, NULL on failure.
+ *
+ * Side effects: vsock_table_lock is acquired and released. The socket's
+ * reference count is increased.
+ */
+
+static inline struct sock *vsock_vmci_find_connected_socket(struct sockaddr_vm
+ *src,
+ struct sockaddr_vm
+ *dst)
+{
+ struct sock *sk;
+
+ spin_lock_bh(&vsock_table_lock);
+ sk = __vsock_vmci_find_connected_socket(src, dst);
+ if (sk)
+ sock_hold(sk);
+
+ spin_unlock_bh(&vsock_table_lock);
+
+ return sk;
+}
+
+/*
+ *
+ * vsock_vmci_in_bound_table --
+ *
+ * Determines whether the provided socket is in the bound table.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these may be called from tasklets.
+ *
+ * Results: TRUE is socket is in bound table, FALSE otherwise.
+ *
+ * Side effects: vsock_table_lock is acquired and released.
+ */
+
+static inline bool vsock_vmci_in_bound_table(struct sock *sk)
+{
+ bool ret;
+
+ spin_lock_bh(&vsock_table_lock);
+ ret = __vsock_vmci_in_bound_table(sk);
+ spin_unlock_bh(&vsock_table_lock);
+
+ return ret;
+}
+
+/*
+ *
+ * vsock_vmci_in_connected_table --
+ *
+ * Determines whether the provided socket is in the connected table.
+ *
+ * Note that it is important to invoke the bottom-half versions of the spinlock
+ * functions since these may be called from tasklets.
+ *
+ * Results: TRUE is socket is in connected table, FALSE otherwise.
+ *
+ * Side effects: vsock_table_lock is acquired and released.
+ */
+
+static inline bool vsock_vmci_in_connected_table(struct sock *sk)
+{
+ bool ret;
+
+ spin_lock_bh(&vsock_table_lock);
+ ret = __vsock_vmci_in_connected_table(sk);
+ spin_unlock_bh(&vsock_table_lock);
+
+ return ret;
+}
+
+#endif /* __UTIL_H__ */
^ permalink raw reply related
* [PATCH 4/6] VSOCK: statistics implementation.
From: George Zhang @ 2012-11-05 18:01 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
VSOCK stats for VMCI Stream Sockets protocol.
Signed-off-by: George Zhang <georgezhang@vmware.com>
---
net/vmw_vsock/stats.c | 37 ++++++++
net/vmw_vsock/stats.h | 219 +++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 256 insertions(+), 0 deletions(-)
create mode 100644 net/vmw_vsock/stats.c
create mode 100644 net/vmw_vsock/stats.h
diff --git a/net/vmw_vsock/stats.c b/net/vmw_vsock/stats.c
new file mode 100644
index 0000000..2d172d5
--- /dev/null
+++ b/net/vmw_vsock/stats.c
@@ -0,0 +1,37 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2009-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * stats.c --
+ *
+ * Linux stats for the VMCI Stream Sockets protocol.
+ */
+
+#include <linux/types.h>
+
+#include <linux/socket.h>
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+
+#include "af_vsock.h"
+#include "stats.h"
+
+#ifdef VSOCK_GATHER_STATISTICS
+u64 vsock_stats_ctl_pkt_count[VSOCK_PACKET_TYPE_MAX];
+u64 vsock_stats_consume_queue_hist[VSOCK_NUM_QUEUE_LEVEL_BUCKETS];
+u64 vsock_stats_produce_queue_hist[VSOCK_NUM_QUEUE_LEVEL_BUCKETS];
+atomic64_t vsock_stats_consume_total;
+atomic64_t vsock_stats_produce_total;
+#endif
diff --git a/net/vmw_vsock/stats.h b/net/vmw_vsock/stats.h
new file mode 100644
index 0000000..2f9d44c
--- /dev/null
+++ b/net/vmw_vsock/stats.h
@@ -0,0 +1,219 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2009-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * stats.h --
+ *
+ * Stats functions for Linux vsock module.
+ */
+
+#ifndef __STATS_H__
+#define __STATS_H__
+
+#include <linux/types.h>
+
+#include "vsock_common.h"
+#include "vsock_packet.h"
+
+/*
+ * Define VSOCK_GATHER_STATISTICS to turn on statistics gathering. Currently
+ * this consists of 3 types of stats: 1. The number of control datagram
+ * messages sent. 2. The level of queuepair fullness (in 10% buckets) whenever
+ * data is about to be enqueued or dequeued from the queuepair. 3. The total
+ * number of bytes enqueued/dequeued.
+ */
+
+#ifdef VSOCK_GATHER_STATISTICS
+
+#define VSOCK_NUM_QUEUE_LEVEL_BUCKETS 10
+extern u64 vsock_stats_ctl_pkt_count[VSOCK_PACKET_TYPE_MAX];
+extern u64 vsock_stats_consume_queue_hist[VSOCK_NUM_QUEUE_LEVEL_BUCKETS];
+extern u64 vsock_stats_produce_queue_hist[VSOCK_NUM_QUEUE_LEVEL_BUCKETS];
+extern atomic64_t vsock_stats_consume_total;
+extern atomic64_t vsock_stats_produce_total;
+
+#define VSOCK_STATS_STREAM_CONSUME_HIST(vsk) \
+ vsock_vmci_stats_update_queue_bucket_count((vsk)->qpair, \
+ (vsk)->consume_size, \
+ vmci_qpair_consume_buf_ready((vsk)->qpair), \
+ vsock_stats_consume_queue_hist)
+#define VSOCK_STATS_STREAM_PRODUCE_HIST(vsk) \
+ vsock_vmci_stats_update_queue_bucket_count((vsk)->qpair, \
+ (vsk)->produce_size, \
+ vmci_qpair_produce_buf_ready((vsk)->qpair), \
+ vsock_stats_produce_queue_hist)
+#define VSOCK_STATS_CTLPKT_LOG(pkt_type) \
+ do { \
+ ++vsock_stats_ctl_pkt_count[pkt_type]; \
+ } while (0)
+#define VSOCK_STATS_STREAM_CONSUME(bytes) \
+ atomic64_add(&vsock_stats_consume_total, bytes)
+#define VSOCK_STATS_STREAM_PRODUCE(bytes) \
+ atomic64_add(&vsock_stats_produce_total, bytes)
+#define VSOCK_STATS_CTLPKT_DUMP_ALL() vsock_vmci_stats_ctl_pkt_dump_all()
+#define VSOCK_STATS_HIST_DUMP_ALL() vsock_vmci_stats_hist_dump_all()
+#define VSOCK_STATS_TOTALS_DUMP_ALL() vsock_vmci_stats_totals_dump_all()
+#define VSOCK_STATS_RESET() vsock_vmci_stats_reset()
+
+/*
+ *
+ * vsock_vmci_stats_update_queue_bucket_count --
+ *
+ * Given a queue, determine how much data is enqueued and add that to the
+ * specified queue level statistic bucket.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void
+vsock_vmci_stats_update_queue_bucket_count(vmci_qpair *qpair,
+ u64 queue_size,
+ u64 data_ready,
+ u64 queue_hist[])
+{
+ u64 bucket = 0;
+ u32 remainder = 0;
+
+ /*
+ * We can't do 64 / 64 = 64 bit divides on linux because it requires a
+ * libgcc which is not linked into the kernel module. Since this code
+ * is only used by developers we just limit the queue_size to be less
+ * than MAX_UINT for now.
+ */
+ ASSERT(queue_size <= MAX_UINT32);
+ Div643264(data_ready * 10, queue_size, &bucket, &remainder);
+ ASSERT(bucket < VSOCK_NUM_QUEUE_LEVEL_BUCKETS);
+ ++queue_hist[bucket];
+}
+
+/*
+ *
+ * vsock_vmci_stats_ctl_pkt_dump_all --
+ *
+ * Prints all stream control packet counts out to the console using the
+ * appropriate platform logging.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void vsock_vmci_stats_ctl_pkt_dump_all(void)
+{
+ int index;
+
+ ASSERT_ON_COMPILE(VSOCK_PACKET_TYPE_MAX ==
+ ARRAY_SIZE(vsock_stats_ctl_pkt_count));
+
+ for (index = 0; index < ARRAY_SIZE(vsock_stats_ctl_pkt_count);
+ index++) {
+ pr_info("Control packet: Type = %u, Count = %" FMT64
+ "u\n", index, vsock_stats_ctl_pkt_count[index]);
+ }
+}
+
+/*
+ *
+ * vsock_vmci_stats_hist_dump_all --
+ *
+ * Prints the produce and consume queue histograms to the console.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void vsock_vmci_stats_hist_dump_all(void)
+{
+ int index;
+
+#define VSOCK_DUMP_HIST(strname, name) do { \
+ for (index = 0; index < ARRAY_SIZE(name); index++) { \
+ printk(strname " Bucket count %u = %"FMT64"u\n", \
+ index, name[index]); \
+ } \
+ } while (0)
+
+ VSOCK_DUMP_HIST("Produce Queue", vsock_stats_produce_queue_hist);
+ VSOCK_DUMP_HIST("Consume Queue", vsock_stats_consume_queue_hist);
+
+#undef VSOCK_DUMP_HIST
+}
+
+/*
+ *
+ * vsock_vmci_stats_totals_dump_all --
+ *
+ * Prints the produce and consume totals.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void vsock_vmci_stats_totals_dump_all(void)
+{
+ pr_info("Produced %" FMT64 "u total bytes\n",
+ atomic64_read(&vsock_stats_produce_total));
+ pr_info("Consumed %" FMT64 "u total bytes\n",
+ atomic64_read(&vsock_stats_consume_total));
+}
+
+/*
+ *
+ * vsock_vmci_stats_reset --
+ *
+ * Reset all VSock statistics.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static inline void vsock_vmci_stats_reset(void)
+{
+ int index;
+
+#define VSOCK_RESET_ARRAY(name) do { \
+ for (index = 0; index < ARRAY_SIZE(name); index++) { \
+ name[index] = 0; \
+ } \
+ } while (0)
+
+ VSOCK_RESET_ARRAY(vsock_stats_ctl_pkt_count);
+ VSOCK_RESET_ARRAY(vsock_stats_produce_queue_hist);
+ VSOCK_RESET_ARRAY(vsock_stats_consume_queue_hist);
+
+#undef VSOCK_RESET_ARRAY
+
+ atomic64_set(&vsock_stats_consume_total, 0);
+ atomic64_set(&vsock_stats_produce_total, 0);
+}
+
+#else
+#define VSOCK_STATS_STREAM_CONSUME_HIST(vsk)
+#define VSOCK_STATS_STREAM_PRODUCE_HIST(vsk)
+#define VSOCK_STATS_STREAM_PRODUCE(bytes)
+#define VSOCK_STATS_STREAM_CONSUME(bytes)
+#define VSOCK_STATS_CTLPKT_LOG(pkt_type)
+#define VSOCK_STATS_CTLPKT_DUMP_ALL()
+#define VSOCK_STATS_HIST_DUMP_ALL()
+#define VSOCK_STATS_TOTALS_DUMP_ALL()
+#define VSOCK_STATS_RESET()
+#endif
+
+#endif
^ permalink raw reply related
* [PATCH 3/6] VSOCK: notification implementation.
From: George Zhang @ 2012-11-05 18:01 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
VSOCK control notifications for VMCI Stream Sockets protocol.
Signed-off-by: George Zhang <georgezhang@vmware.com>
---
net/vmw_vsock/notify.c | 984 ++++++++++++++++++++++++++++++++++++++++++++++++
net/vmw_vsock/notify.h | 130 ++++++
2 files changed, 1114 insertions(+), 0 deletions(-)
create mode 100644 net/vmw_vsock/notify.c
create mode 100644 net/vmw_vsock/notify.h
diff --git a/net/vmw_vsock/notify.c b/net/vmw_vsock/notify.c
new file mode 100644
index 0000000..5c69c7c
--- /dev/null
+++ b/net/vmw_vsock/notify.c
@@ -0,0 +1,984 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2009-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * notify.c --
+ *
+ * Linux control notifications for the VMCI Stream Sockets protocol.
+ */
+
+#include <linux/types.h>
+
+#include <linux/socket.h>
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+
+#include "notify.h"
+#include "af_vsock.h"
+
+#define PKT_FIELD(vsk, field_name) \
+ (vsk)->notify.pkt.field_name
+
+#define VSOCK_MAX_DGRAM_RESENDS 10
+
+/*
+ *
+ * vsock_vmci_notify_waiting_write --
+ *
+ * Determines if the conditions have been met to notify a waiting writer.
+ *
+ * Results: true if a notification should be sent, false otherwise.
+ *
+ * Side effects: None.
+ */
+
+static bool vsock_vmci_notify_waiting_write(vsock_vmci_sock *vsk)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ bool retval;
+ u64 notify_limit;
+
+ if (!PKT_FIELD(vsk, peer_waiting_write))
+ return false;
+
+#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL
+ /*
+ * When the sender blocks, we take that as a sign that the sender is
+ * faster than the receiver. To reduce the transmit rate of the sender,
+ * we delay the sending of the read notification by decreasing the
+ * write_notify_window. The notification is delayed until the number of
+ * bytes used in the queue drops below the write_notify_window.
+ */
+
+ if (!PKT_FIELD(vsk, peer_waiting_write_detected)) {
+ PKT_FIELD(vsk, peer_waiting_write_detected) = true;
+ if (PKT_FIELD(vsk, write_notify_window) < PAGE_SIZE) {
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+ } else {
+ PKT_FIELD(vsk, write_notify_window) -= PAGE_SIZE;
+ if (PKT_FIELD(vsk, write_notify_window) <
+ PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+
+ }
+ }
+ notify_limit = vsk->consume_size - PKT_FIELD(vsk, write_notify_window);
+#else
+ notify_limit = 0;
+#endif
+
+ /*
+ * For now we ignore the wait information and just see if the free
+ * space exceeds the notify limit. Note that improving this function
+ * to be more intelligent will not require a protocol change and will
+ * retain compatibility between endpoints with mixed versions of this
+ * function.
+ *
+ * The notify_limit is used to delay notifications in the case where
+ * flow control is enabled. Below the test is expressed in terms of
+ * free space in the queue: if free_space > ConsumeSize -
+ * write_notify_window then notify An alternate way of expressing this
+ * is to rewrite the expression to use the data ready in the receive
+ * queue: if write_notify_window > bufferReady then notify as
+ * free_space == ConsumeSize - bufferReady.
+ */
+ retval = vmci_qpair_consume_free_space(vsk->qpair) > notify_limit;
+#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL
+ if (retval) {
+ /*
+ * Once we notify the peer, we reset the detected flag so the
+ * next wait will again cause a decrease in the window size.
+ */
+
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+ }
+#endif
+ return retval;
+#else
+ return true;
+#endif
+}
+
+/*
+ *
+ * vsock_vmci_notify_waiting_read --
+ *
+ * Determines if the conditions have been met to notify a waiting reader.
+ *
+ * Results: true if a notification should be sent, false otherwise.
+ *
+ * Side effects: None.
+ */
+
+static bool vsock_vmci_notify_waiting_read(vsock_vmci_sock *vsk)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ if (!PKT_FIELD(vsk, peer_waiting_read))
+ return false;
+
+ /*
+ * For now we ignore the wait information and just see if there is any
+ * data for our peer to read. Note that improving this function to be
+ * more intelligent will not require a protocol change and will retain
+ * compatibility between endpoints with mixed versions of this
+ * function.
+ */
+ return vmci_qpair_produce_buf_ready(vsk->qpair) > 0;
+#else
+ return true;
+#endif
+}
+
+/*
+ *
+ * vsock_vmci_handle_waiting_read --
+ *
+ * Handles an incoming waiting read message.
+ *
+ * Results: None.
+ *
+ * Side effects: May send a notification to the peer, may update socket's wait
+ * info structure.
+ */
+
+static void
+vsock_vmci_handle_waiting_read(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, peer_waiting_read) = true;
+ memcpy(&PKT_FIELD(vsk, peer_waiting_read_info), &pkt->u.wait,
+ sizeof PKT_FIELD(vsk, peer_waiting_read_info));
+
+ if (vsock_vmci_notify_waiting_read(vsk)) {
+ bool sent;
+
+ if (bottom_half)
+ sent = VSOCK_SEND_WROTE_BH(dst, src) > 0;
+ else
+ sent = VSOCK_SEND_WROTE(sk) > 0;
+
+ if (sent)
+ PKT_FIELD(vsk, peer_waiting_read) = false;
+
+ }
+#endif
+}
+
+/*
+ *
+ * vsock_vmci_handle_waiting_write --
+ *
+ * Handles an incoming waiting write message.
+ *
+ * Results: None.
+ *
+ * Side effects: May send a notification to the peer, may update socket's wait
+ * info structure.
+ */
+
+static void
+vsock_vmci_handle_waiting_write(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst,
+ struct sockaddr_vm *src)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, peer_waiting_write) = true;
+ memcpy(&PKT_FIELD(vsk, peer_waiting_write_info), &pkt->u.wait,
+ sizeof PKT_FIELD(vsk, peer_waiting_write_info));
+
+ if (vsock_vmci_notify_waiting_write(vsk)) {
+ bool sent;
+
+ if (bottom_half)
+ sent = VSOCK_SEND_READ_BH(dst, src) > 0;
+ else
+ sent = VSOCK_SEND_READ(sk) > 0;
+
+ if (sent)
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+
+ }
+#endif
+}
+
+/*
+ *
+ * vsock_vmci_handle_read --
+ *
+ * Handles an incoming read message.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void
+vsock_vmci_handle_read(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+ PKT_FIELD(vsk, sent_waiting_write) = false;
+#endif
+
+ sk->sk_write_space(sk);
+}
+
+/*
+ *
+ * vsock_vmci_send_waiting_read --
+ *
+ * Sends a waiting read notification to this socket's peer.
+ *
+ * Results: true if the datagram is sent successfully, false otherwise.
+ *
+ * Side effects: Our peer will notify us when there is data to read from our
+ * consume queue.
+ */
+
+static bool vsock_vmci_send_waiting_read(struct sock *sk, u64 room_needed)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vsock_vmci_sock *vsk;
+ vsock_waiting_info waiting_info;
+ u64 tail;
+ u64 head;
+ u64 room_left;
+ bool ret;
+
+ vsk = vsock_sk(sk);
+
+ if (PKT_FIELD(vsk, sent_waiting_read))
+ return true;
+
+ if (PKT_FIELD(vsk, write_notify_window) < vsk->consume_size)
+ PKT_FIELD(vsk, write_notify_window) =
+ min(PKT_FIELD(vsk, write_notify_window) + PAGE_SIZE,
+ vsk->consume_size);
+
+ vmci_qpair_get_consume_indexes(vsk->qpair, &tail, &head);
+ room_left = vsk->consume_size - head;
+ if (room_needed >= room_left) {
+ waiting_info.offset = room_needed - room_left;
+ waiting_info.generation =
+ PKT_FIELD(vsk, consume_q_generation) + 1;
+ } else {
+ waiting_info.offset = head + room_needed;
+ waiting_info.generation = PKT_FIELD(vsk, consume_q_generation);
+ }
+
+ ret = VSOCK_SEND_WAITING_READ(sk, &waiting_info) > 0;
+ if (ret)
+ PKT_FIELD(vsk, sent_waiting_read) = true;
+
+ return ret;
+#else
+ return true;
+#endif
+}
+
+/*
+ *
+ * vsock_vmci_send_waiting_write --
+ *
+ * Sends a waiting write notification to this socket's peer.
+ *
+ * Results: true if the datagram is sent successfully or does not need to be
+ * sent. false otherwise.
+ *
+ * Side effects: Our peer will notify us when there is room to write in to our
+ * produce queue.
+ */
+
+static bool vsock_vmci_send_waiting_write(struct sock *sk, u64 room_needed)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vsock_vmci_sock *vsk;
+ vsock_waiting_info waiting_info;
+ u64 tail;
+ u64 head;
+ u64 room_left;
+ bool ret;
+
+ vsk = vsock_sk(sk);
+
+ if (PKT_FIELD(vsk, sent_waiting_write))
+ return true;
+
+ vmci_qpair_get_produce_indexes(vsk->qpair, &tail, &head);
+ room_left = vsk->produce_size - tail;
+ if (room_needed + 1 >= room_left) {
+ /* Wraps around to current generation. */
+ waiting_info.offset = room_needed + 1 - room_left;
+ waiting_info.generation = PKT_FIELD(vsk, produce_q_generation);
+ } else {
+ waiting_info.offset = tail + room_needed + 1;
+ waiting_info.generation =
+ PKT_FIELD(vsk, produce_q_generation) - 1;
+ }
+
+ ret = VSOCK_SEND_WAITING_WRITE(sk, &waiting_info) > 0;
+ if (ret)
+ PKT_FIELD(vsk, sent_waiting_write) = true;
+
+ return ret;
+#else
+ return true;
+#endif
+}
+
+/*
+ *
+ * vsock_vmci_send_read_notification --
+ *
+ * Sends a read notification to this socket's peer.
+ *
+ * Results: >= 0 if the datagram is sent successfully, negative error value
+ * otherwise.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_send_read_notification(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+ bool sent_read;
+ unsigned int retries;
+ int err;
+
+ vsk = vsock_sk(sk);
+ sent_read = false;
+ retries = 0;
+ err = 0;
+
+ if (vsock_vmci_notify_waiting_write(vsk)) {
+ /*
+ * Notify the peer that we have read, retrying the send on
+ * failure up to our maximum value. XXX For now we just log
+ * the failure, but later we should schedule a work item to
+ * handle the resend until it succeeds. That would require
+ * keeping track of work items in the vsk and cleaning them up
+ * upon socket close.
+ */
+ while (!(vsk->peer_shutdown & RCV_SHUTDOWN) &&
+ !sent_read && retries < VSOCK_MAX_DGRAM_RESENDS) {
+ err = VSOCK_SEND_READ(sk);
+ if (err >= 0)
+ sent_read = true;
+
+ retries++;
+ }
+
+ if (retries >= VSOCK_MAX_DGRAM_RESENDS)
+ printk
+ ("%p unable to send read notify to peer.\n",
+ sk);
+ else
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+#endif
+
+ }
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_handle_wrote --
+ *
+ * Handles an incoming wrote message.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void
+vsock_vmci_handle_wrote(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst, struct sockaddr_vm *src)
+{
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+ PKT_FIELD(vsk, sent_waiting_read) = false;
+#endif
+
+ sk->sk_data_ready(sk, 0);
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_socket_init --
+ *
+ * Function that is called after a socket is created and before any notify ops
+ * are used.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_socket_init(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+ vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE;
+ PKT_FIELD(vsk, peer_waiting_read) = false;
+ PKT_FIELD(vsk, peer_waiting_write) = false;
+ PKT_FIELD(vsk, peer_waiting_write_detected) = false;
+ PKT_FIELD(vsk, sent_waiting_read) = false;
+ PKT_FIELD(vsk, sent_waiting_write) = false;
+ PKT_FIELD(vsk, produce_q_generation) = 0;
+ PKT_FIELD(vsk, consume_q_generation) = 0;
+
+ memset(&PKT_FIELD(vsk, peer_waiting_read_info), 0,
+ sizeof PKT_FIELD(vsk, peer_waiting_read_info));
+ memset(&PKT_FIELD(vsk, peer_waiting_write_info), 0,
+ sizeof PKT_FIELD(vsk, peer_waiting_write_info));
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_socket_destruct --
+ *
+ * Function that is called when the socket is being released.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_socket_destruct(struct sock *sk)
+{
+ return;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_poll_in --
+ *
+ * Called by the poll function to figure out if there is data to read and to
+ * setup future notifications if needed. Only called on sockets that aren't
+ * shutdown for recv.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_poll_in(struct sock *sk,
+ size_t target, bool *data_ready_now)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ if (vsock_vmci_stream_has_data(vsk)) {
+ *data_ready_now = true;
+ } else {
+ /*
+ * We can't read right now because there is nothing in the
+ * queue. Ask for notifications when there is something to
+ * read.
+ */
+ if (sk->sk_state == SS_CONNECTED) {
+ if (!vsock_vmci_send_waiting_read(sk, 1))
+ return -1;
+
+ }
+ *data_ready_now = false;
+ }
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_poll_out
+ *
+ * Called by the poll function to figure out if there is space to write and to
+ * setup future notifications if needed. Only called on a connected socket that
+ * isn't shutdown for send.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_poll_out(struct sock *sk,
+ size_t target, bool *space_avail_now)
+{
+ s64 produce_q_free_space;
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ produce_q_free_space = vsock_vmci_stream_has_space(vsk);
+ if (produce_q_free_space > 0) {
+ *space_avail_now = true;
+ return 0;
+ } else if (produce_q_free_space == 0) {
+ /*
+ * This is a connected socket but we can't currently send data.
+ * Notify the peer that we are waiting if the queue is full. We
+ * only send a waiting write if the queue is full because
+ * otherwise we end up in an infinite WAITING_WRITE, READ,
+ * WAITING_WRITE, READ, etc. loop. Treat failing to send the
+ * notification as a socket error, passing that back through
+ * the mask.
+ */
+ if (!vsock_vmci_send_waiting_write(sk, 1))
+ return -1;
+
+ *space_avail_now = false;
+ }
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_init --
+ *
+ * Called at the start of a stream recv call with the socket lock held.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_init(struct sock *sk,
+ size_t target,
+ vsock_vmci_recv_notify_data *data)
+{
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+
+#ifdef VSOCK_OPTIMIZATION_WAITING_NOTIFY
+ data->consume_head = 0;
+ data->produce_tail = 0;
+#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL
+ data->notify_on_block = false;
+
+ if (PKT_FIELD(vsk, write_notify_min_window) < target + 1) {
+ ASSERT(target < vsk->consume_size);
+ PKT_FIELD(vsk, write_notify_min_window) = target + 1;
+ if (PKT_FIELD(vsk, write_notify_window) <
+ PKT_FIELD(vsk, write_notify_min_window)) {
+ /*
+ * If the current window is smaller than the new
+ * minimal window size, we need to reevaluate whether
+ * we need to notify the sender. If the number of ready
+ * bytes are smaller than the new window, we need to
+ * send a notification to the sender before we block.
+ */
+
+ PKT_FIELD(vsk, write_notify_window) =
+ PKT_FIELD(vsk, write_notify_min_window);
+ data->notify_on_block = true;
+ }
+ }
+#endif
+#endif
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_pre_block --
+ *
+ * Called right before a socket is about to block with the socket lock held.
+ * The socket lock may have been released between the entry function and the
+ * preblock call.
+ *
+ * Note: This function may be called multiple times before the post block
+ * function is called.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_pre_block(struct sock *sk,
+ size_t target,
+ vsock_vmci_recv_notify_data *data)
+{
+ int err = 0;
+
+ /* Notify our peer that we are waiting for data to read. */
+ if (!vsock_vmci_send_waiting_read(sk, target)) {
+ err = -EHOSTUNREACH;
+ return err;
+ }
+#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL
+ if (data->notify_on_block) {
+ err = vsock_vmci_send_read_notification(sk);
+ if (err < 0)
+ return err;
+
+ data->notify_on_block = false;
+ }
+#endif
+
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_pre_dequeue --
+ *
+ * Called right before we dequeue / peek data from a socket.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_pre_dequeue(struct sock *sk,
+ size_t target,
+ vsock_vmci_recv_notify_data *data)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ /*
+ * Now consume up to len bytes from the queue. Note that since we have
+ * the socket locked we should copy at least ready bytes.
+ */
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vmci_qpair_get_consume_indexes(vsk->qpair,
+ &data->produce_tail,
+ &data->consume_head);
+#endif
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_recv_post_dequeue --
+ *
+ * Called right after we dequeue / peek data from a socket.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_recv_post_dequeue(struct sock *sk,
+ size_t target,
+ ssize_t copied,
+ bool data_read,
+ vsock_vmci_recv_notify_data *data)
+{
+ vsock_vmci_sock *vsk;
+ int err;
+
+ vsk = vsock_sk(sk);
+ err = 0;
+
+ if (data_read) {
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ /*
+ * Detect a wrap-around to maintain queue generation. Note
+ * that this is safe since we hold the socket lock across the
+ * two queue pair operations.
+ */
+ if (copied >= vsk->consume_size - data->consume_head)
+ PKT_FIELD(vsk, consume_q_generation)++;
+
+#endif
+
+ err = vsock_vmci_send_read_notification(sk);
+ if (err < 0)
+ return err;
+
+ }
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_send_init --
+ *
+ * Called at the start of a stream send call with the socket lock held.
+ *
+ * Results: 0 on success. A negative error code on failure.
+ *
+ * Side effects:
+ */
+
+static int
+vsock_vmci_notify_pkt_send_init(struct sock *sk,
+ vsock_vmci_send_notify_data *data)
+{
+#ifdef VSOCK_OPTIMIZATION_WAITING_NOTIFY
+ data->consume_head = 0;
+ data->produce_tail = 0;
+#endif
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_send_pre_block --
+ *
+ * Called right before a socket is about to block with the socket lock held.
+ * The socket lock may have been released between the entry function and the
+ * preblock call.
+ *
+ * Note: This function may be called multiple times before the post block
+ * function is called.
+ *
+ * Results. 0 on success. A negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_send_pre_block(struct sock *sk,
+ vsock_vmci_send_notify_data *data)
+{
+ /* Notify our peer that we are waiting for room to write. */
+ if (!vsock_vmci_send_waiting_write(sk, 1))
+ return -EHOSTUNREACH;
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notifySendPreEnqueue --
+ *
+ * Called right before we Enqueue to a socket.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_send_pre_enqueue(struct sock *sk,
+ vsock_vmci_send_notify_data *data)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ vmci_qpair_get_produce_indexes(vsk->qpair,
+ &data->produce_tail,
+ &data->consume_head);
+#endif
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_vmci_notifySendPostEnqueue --
+ *
+ * Called right after we enqueue data to a socket.
+ *
+ * Results: 0 on success. Negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_notify_pkt_send_post_enqueue(struct sock *sk,
+ ssize_t written,
+ vsock_vmci_send_notify_data *data)
+{
+ int err = 0;
+ vsock_vmci_sock *vsk;
+ bool sent_wrote = false;
+ int retries = 0;
+
+ vsk = vsock_sk(sk);
+
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ /*
+ * Detect a wrap-around to maintain queue generation. Note that this
+ * is safe since we hold the socket lock across the two queue pair
+ * operations.
+ */
+ if (written >= vsk->produce_size - data->produce_tail)
+ PKT_FIELD(vsk, produce_q_generation)++;
+
+#endif
+
+ if (vsock_vmci_notify_waiting_read(vsk)) {
+ /*
+ * Notify the peer that we have written, retrying the send on
+ * failure up to our maximum value. See the XXX comment for the
+ * corresponding piece of code in StreamRecvmsg() for potential
+ * improvements.
+ */
+ while (!(vsk->peer_shutdown & RCV_SHUTDOWN) &&
+ !sent_wrote && retries < VSOCK_MAX_DGRAM_RESENDS) {
+ err = VSOCK_SEND_WROTE(sk);
+ if (err >= 0)
+ sent_wrote = true;
+
+ retries++;
+ }
+
+ if (retries >= VSOCK_MAX_DGRAM_RESENDS) {
+ printk
+ (" %p unable to send wrote notify to peer.\n",
+ sk);
+ return err;
+ } else {
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+ PKT_FIELD(vsk, peer_waiting_read) = false;
+#endif
+ }
+ }
+ return err;
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_handle_pkt
+ *
+ * Called when a notify packet is recieved for a socket in the connected state.
+ * Note this might be called from a bottom half.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void
+vsock_vmci_notify_pkt_handle_pkt(struct sock *sk,
+ vsock_packet *pkt,
+ bool bottom_half,
+ struct sockaddr_vm *dst,
+ struct sockaddr_vm *src, bool *pkt_processed)
+{
+ bool processed = false;
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_WROTE:
+ vsock_vmci_handle_wrote(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ case VSOCK_PACKET_TYPE_READ:
+ vsock_vmci_handle_read(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ case VSOCK_PACKET_TYPE_WAITING_WRITE:
+ vsock_vmci_handle_waiting_write(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+
+ case VSOCK_PACKET_TYPE_WAITING_READ:
+ vsock_vmci_handle_waiting_read(sk, pkt, bottom_half, dst, src);
+ processed = true;
+ break;
+ }
+
+ if (pkt_processed)
+ *pkt_processed = processed;
+
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_process_request
+ *
+ * Called near the end of process request.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_process_request(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = vsk->consume_size;
+ if (vsk->consume_size < PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_min_window) = vsk->consume_size;
+
+}
+
+/*
+ *
+ * vsock_vmci_notify_pkt_process_negotiate
+ *
+ * Called near the end of process negotiate.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+static void vsock_vmci_notify_pkt_process_negotiate(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ PKT_FIELD(vsk, write_notify_window) = vsk->consume_size;
+ if (vsk->consume_size < PKT_FIELD(vsk, write_notify_min_window))
+ PKT_FIELD(vsk, write_notify_min_window) = vsk->consume_size;
+
+}
+
+/* Socket control packet based operations. */
+vsock_vmci_notify_ops vsock_vmci_notify_pkt_ops = {
+ vsock_vmci_notify_pkt_socket_init,
+ vsock_vmci_notify_pkt_socket_destruct,
+ vsock_vmci_notify_pkt_poll_in,
+ vsock_vmci_notify_pkt_poll_out,
+ vsock_vmci_notify_pkt_handle_pkt,
+ vsock_vmci_notify_pkt_recv_init,
+ vsock_vmci_notify_pkt_recv_pre_block,
+ vsock_vmci_notify_pkt_recv_pre_dequeue,
+ vsock_vmci_notify_pkt_recv_post_dequeue,
+ vsock_vmci_notify_pkt_send_init,
+ vsock_vmci_notify_pkt_send_pre_block,
+ vsock_vmci_notify_pkt_send_pre_enqueue,
+ vsock_vmci_notify_pkt_send_post_enqueue,
+ vsock_vmci_notify_pkt_process_request,
+ vsock_vmci_notify_pkt_process_negotiate,
+};
diff --git a/net/vmw_vsock/notify.h b/net/vmw_vsock/notify.h
new file mode 100644
index 0000000..fe39442
--- /dev/null
+++ b/net/vmw_vsock/notify.h
@@ -0,0 +1,130 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2009-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * notify.h --
+ *
+ * Notify functions for Linux VSocket module.
+ */
+
+#ifndef __NOTIFY_H__
+#define __NOTIFY_H__
+
+#include <linux/types.h>
+
+#include "vsock_common.h"
+#include "vsock_packet.h"
+
+/* Comment this out to compare with old protocol. */
+#define VSOCK_OPTIMIZATION_WAITING_NOTIFY 1
+#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY)
+/* Comment this out to remove flow control for "new" protocol */
+#define VSOCK_OPTIMIZATION_FLOW_CONTROL 1
+#endif
+
+#define VSOCK_MAX_DGRAM_RESENDS 10
+
+#define NOTIFYCALLRET(vsk, rv, mod_fn, args...) \
+ do { \
+ if (vsk->notify_ops && \
+ vsk->notify_ops->mod_fn != NULL) \
+ rv = (vsk->notify_ops->mod_fn)(args); \
+ else \
+ rv = 0; \
+ \
+ } while (0)
+
+#define NOTIFYCALL(vsk, mod_fn, args...) \
+ do { \
+ if (vsk->notify_ops && \
+ vsk->notify_ops->mod_fn != NULL) \
+ (vsk->notify_ops->mod_fn)(args); \
+ \
+ } while (0)
+
+typedef struct vsock_vmci_notify_pkt {
+ u64 write_notify_window;
+ u64 write_notify_min_window;
+ bool peer_waiting_read;
+ bool peer_waiting_write;
+ bool peer_waiting_write_detected;
+ bool sent_waiting_read;
+ bool sent_waiting_write;
+ vsock_waiting_info peer_waiting_read_info;
+ vsock_waiting_info peer_waiting_write_info;
+ u64 produce_q_generation;
+ u64 consume_q_generation;
+} vsock_vmci_notify_pkt;
+
+typedef struct vsock_vmci_notify_pkt_q_state {
+ u64 write_notify_window;
+ u64 write_notify_min_window;
+ bool peer_waiting_write;
+ bool peer_waiting_write_detected;
+} vsock_vmci_notify_pkt_q_state;
+
+typedef union vsock_vmci_notify {
+ vsock_vmci_notify_pkt pkt;
+ vsock_vmci_notify_pkt_q_state pkt_q_state;
+} vsock_vmci_notify;
+
+typedef struct vsock_vmci_recv_notify_data {
+ u64 consume_head;
+ u64 produce_tail;
+ bool notify_on_block;
+} vsock_vmci_recv_notify_data;
+
+typedef struct vsock_vmci_send_notify_data {
+ u64 consume_head;
+ u64 produce_tail;
+} vsock_vmci_send_notify_data;
+
+/* Socket notification callbacks. */
+typedef struct vsock_vmci_notify_ops {
+ void (*socket_init) (struct sock *sk);
+ void (*socket_destruct) (struct sock *sk);
+ int (*poll_in) (struct sock *sk, size_t target,
+ bool *data_ready_now);
+ int (*poll_out) (struct sock *sk, size_t target,
+ bool *space_avail_now);
+ void (*handle_notify_pkt) (struct sock *sk, vsock_packet *pkt,
+ bool bottom_half, struct sockaddr_vm *dst,
+ struct sockaddr_vm *src,
+ bool *pkt_processed);
+ int (*recv_init) (struct sock *sk, size_t target,
+ vsock_vmci_recv_notify_data *data);
+ int (*recv_pre_block) (struct sock *sk, size_t target,
+ vsock_vmci_recv_notify_data *data);
+ int (*recv_pre_dequeue) (struct sock *sk, size_t target,
+ vsock_vmci_recv_notify_data *data);
+ int (*recv_post_dequeue) (struct sock *sk, size_t target,
+ ssize_t copied, bool data_read,
+ vsock_vmci_recv_notify_data *data);
+ int (*send_init) (struct sock *sk,
+ vsock_vmci_send_notify_data *data);
+ int (*send_pre_block) (struct sock *sk,
+ vsock_vmci_send_notify_data *data);
+ int (*send_pre_enqueue) (struct sock *sk,
+ vsock_vmci_send_notify_data *data);
+ int (*send_post_enqueue) (struct sock *sk, ssize_t written,
+ vsock_vmci_send_notify_data *data);
+ void (*process_request) (struct sock *sk);
+ void (*process_negotiate) (struct sock *sk);
+} vsock_vmci_notify_ops;
+
+extern vsock_vmci_notify_ops vsock_vmci_notify_pkt_ops;
+extern vsock_vmci_notify_ops vsock_vmci_notify_pkt_q_state_ops;
+
+#endif /* __NOTIFY_H__ */
^ permalink raw reply related
* [PATCH 2/6] VSOCK: vsock address implementaion.
From: George Zhang @ 2012-11-05 18:01 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
VSOCK linux address code implementation.
Signed-off-by: George Zhang <georgezhang@vmware.com>
---
net/vmw_vsock/vsock_addr.c | 264 ++++++++++++++++++++++++++++++++++++++++++++
net/vmw_vsock/vsock_addr.h | 40 +++++++
2 files changed, 304 insertions(+), 0 deletions(-)
create mode 100644 net/vmw_vsock/vsock_addr.c
create mode 100644 net/vmw_vsock/vsock_addr.h
diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c
new file mode 100644
index 0000000..c93a174
--- /dev/null
+++ b/net/vmw_vsock/vsock_addr.c
@@ -0,0 +1,264 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vsockAddr.c --
+ *
+ * VSockets address implementation.
+ */
+
+/*
+ * These includes come before vsockCommon.h to ensure that VMware's ASSERT
+ * macro is used instead of Linux's irda.h definition.
+ */
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+
+#include "vsock_common.h"
+
+/*
+ *
+ * vsock_addr_init --
+ *
+ * Initialize the given address with the given context id and port. This will
+ * clear the address, set the correct family, and add the given values.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port)
+{
+ memset(addr, 0, sizeof *addr);
+
+ addr->svm_family = AF_VSOCK;
+ addr->svm_cid = cid;
+ addr->svm_port = port;
+
+ BUG_ON(vsock_addr_validate(addr) != 0);
+}
+
+/*
+ *
+ * vsock_addr_validate --
+ *
+ * Try to validate the given address. The address must not be null and must
+ * have the correct address family. Any reserved fields must be zero.
+ *
+ * Results: 0 on success, EFAULT if the address is null, EAFNOSUPPORT if the
+ * address is of the wrong family, and EINVAL if the reserved fields are not
+ * zero.
+ *
+ * Side effects: None.
+ */
+
+int vsock_addr_validate(const struct sockaddr_vm *addr)
+{
+ if (!addr)
+ return -EFAULT;
+
+ if (addr->svm_family != AF_VSOCK)
+ return -EAFNOSUPPORT;
+
+ if (addr->svm_zero[0] != 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+/*
+ *
+ * vsock_addr_bound --
+ *
+ * Determines whether the provided address is bound.
+ *
+ * Results: TRUE if the address structure is bound, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_addr_bound(const struct sockaddr_vm *addr)
+{
+ BUG_ON(!addr);
+
+ return addr->svm_port != VMADDR_PORT_ANY;
+}
+
+/*
+ *
+ * vsock_addr_unbind --
+ *
+ * Unbind the given addresss.
+ *
+ * Results: None.
+ *
+ * Side effects: None.
+ */
+
+void vsock_addr_unbind(struct sockaddr_vm *addr)
+{
+ vsock_addr_init(addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+}
+
+/*
+ *
+ * vsock_addr_equals_addr --
+ *
+ * Determine if the given addresses are equal.
+ *
+ * Results: TRUE if the addresses are equal, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_addr_equals_addr(const struct sockaddr_vm *addr,
+ const struct sockaddr_vm *other)
+{
+ BUG_ON(vsock_addr_validate(addr) != 0);
+ BUG_ON(vsock_addr_validate(other) != 0);
+
+ return addr->svm_cid == other->svm_cid &&
+ addr->svm_port == other->svm_port;
+}
+
+/*
+ *
+ * vsock_addr_equals_addr_any --
+ *
+ * Determine if the given addresses are equal. Will accept either an exact
+ * match or one where the rids match and that either the cids match or are set
+ * to VMADDR_CID_ANY.
+ *
+ * Results: TRUE if the addresses are equal, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr,
+ const struct sockaddr_vm *other)
+{
+ BUG_ON(vsock_addr_validate(addr) != 0);
+ BUG_ON(vsock_addr_validate(other) != 0);
+
+ return (addr->svm_cid == VMADDR_CID_ANY ||
+ other->svm_cid == VMADDR_CID_ANY ||
+ addr->svm_cid == other->svm_cid) &&
+ addr->svm_port == other->svm_port;
+}
+
+/*
+ *
+ * vsock_addr_equals_handle_port --
+ *
+ * Determines if the given address matches the given handle and port.
+ *
+ * Results: TRUE if the address matches the handle and port, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_addr_equals_handle_port(const struct sockaddr_vm *addr,
+ struct vmci_handle handle, u32 port)
+{
+ BUG_ON(vsock_addr_validate(addr) != 0);
+
+ return addr->svm_cid == VMCI_HANDLE_TO_CONTEXT_ID(handle) &&
+ addr->svm_port == port;
+}
+
+/*
+ *
+ * vsock_addr_cast --
+ *
+ * Try to cast the given generic address to a VM address. The given length
+ * must match that of a VM address and the address must be valid. The
+ * "out_addr" parameter contains the address if successful.
+ *
+ * Results: 0 on success, EFAULT if the length is too small. See
+ * vsock_addr_validate() for other possible return codes.
+ *
+ * Side effects: None.
+ */
+
+int vsock_addr_cast(const struct sockaddr *addr,
+ size_t len, struct sockaddr_vm **out_addr)
+{
+ BUG_ON(!out_addr);
+
+ if (len < sizeof **out_addr)
+ return -EFAULT;
+
+ *out_addr = (struct sockaddr_vm *)addr;
+ return vsock_addr_validate(*out_addr);
+}
+
+/*
+ *
+ * vsock_addr_socket_context_stream --
+ *
+ * Determines whether the provided context id represents a context that
+ * contains a stream socket endpoints.
+ *
+ * Results: TRUE if the context does have socket endpoints, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_addr_socket_context_stream(u32 cid)
+{
+ static const vmci_id non_socket_contexts[] = {
+ VMCI_HYPERVISOR_CONTEXT_ID,
+ VMCI_WELL_KNOWN_CONTEXT_ID,
+ };
+ int i;
+
+ BUILD_BUG_ON(sizeof cid != sizeof *non_socket_contexts);
+
+ for (i = 0; i < ARRAY_SIZE(non_socket_contexts); i++) {
+ if (cid == non_socket_contexts[i])
+ return false;
+
+ }
+
+ return true;
+}
+
+/*
+ *
+ * vsock_addr_socket_context_dgram --
+ *
+ * Determines whether the provided <context id, resource id> represent a
+ * protected datagram endpoint.
+ *
+ * Results: TRUE if the context does have socket endpoints, FALSE otherwise.
+ *
+ * Side effects: None.
+ */
+
+bool vsock_addr_socket_context_dgram(u32 cid, u32 rid)
+{
+ if (cid == VMCI_HYPERVISOR_CONTEXT_ID) {
+ /*
+ * Registrations of PBRPC Servers do not modify VMX/Hypervisor
+ * state and are allowed.
+ */
+ return rid == VMCI_UNITY_PBRPC_REGISTER;
+ }
+
+ return true;
+}
diff --git a/net/vmw_vsock/vsock_addr.h b/net/vmw_vsock/vsock_addr.h
new file mode 100644
index 0000000..18f023d
--- /dev/null
+++ b/net/vmw_vsock/vsock_addr.h
@@ -0,0 +1,40 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * vsockAddr.h --
+ *
+ * VSockets address constants, types and functions.
+ */
+
+#ifndef _VSOCK_ADDR_H_
+#define _VSOCK_ADDR_H_
+
+void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port);
+int vsock_addr_validate(const struct sockaddr_vm *addr);
+bool vsock_addr_bound(const struct sockaddr_vm *addr);
+void vsock_addr_unbind(struct sockaddr_vm *addr);
+bool vsock_addr_equals_addr(const struct sockaddr_vm *addr,
+ const struct sockaddr_vm *other);
+bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr,
+ const struct sockaddr_vm *other);
+bool vsock_addr_equals_handle_port(const struct sockaddr_vm *addr,
+ struct vmci_handle handle, u32 port);
+int vsock_addr_cast(const struct sockaddr *addr, size_t len,
+ struct sockaddr_vm **out_addr);
+bool vsock_addr_socket_context_stream(u32 cid);
+bool vsock_addr_socket_context_dgram(u32 cid, u32 rid);
+
+#endif
^ permalink raw reply related
* [PATCH 1/6] VSOCK: vsock protocol implementation.
From: George Zhang @ 2012-11-05 18:00 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
In-Reply-To: <20121105175730.21472.99155.stgit@promb-2n-dhcp175.eng.vmware.com>
VSOCK linux socket module for VMCI Sockets protocol family.
Signed-off-by: George Zhang <georgezhang@vmware.com>
---
net/vmw_vsock/af_vsock.c | 4165 ++++++++++++++++++++++++++++++++++++++++++++++
net/vmw_vsock/af_vsock.h | 179 ++
2 files changed, 4344 insertions(+), 0 deletions(-)
create mode 100644 net/vmw_vsock/af_vsock.c
create mode 100644 net/vmw_vsock/af_vsock.h
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
new file mode 100644
index 0000000..00c2050
--- /dev/null
+++ b/net/vmw_vsock/af_vsock.c
@@ -0,0 +1,4165 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * af_vsock.c --
+ *
+ * Linux socket module for the VMCI Sockets protocol family.
+ */
+
+/*
+ * Implementation notes:
+ *
+ * - There are two kinds of sockets: those created by user action (such as
+ * calling socket(2)) and those created by incoming connection request packets.
+ *
+ * - There are two "global" tables, one for bound sockets (sockets that have
+ * specified an address that they are responsible for) and one for connected
+ * sockets (sockets that have established a connection with another socket).
+ * These tables are "global" in that all sockets on the system are placed
+ * within them. - Note, though, that the bound table contains an extra entry
+ * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in
+ * that list. The bound table is used solely for lookup of sockets when packets
+ * are received and that's not necessary for SOCK_DGRAM sockets since we create
+ * a datagram handle for each and need not perform a lookup. Keeping SOCK_DGRAM
+ * sockets out of the bound hash buckets will reduce the chance of collisions
+ * when looking for SOCK_STREAM sockets and prevents us from having to check the
+ * socket type in the hash table lookups.
+ *
+ * - Sockets created by user action will either be "client" sockets that
+ * initiate a connection or "server" sockets that listen for connections; we do
+ * not support simultaneous connects (two "client" sockets connecting).
+ *
+ * - "Server" sockets are referred to as listener sockets throughout this
+ * implementation because they are in the SS_LISTEN state. When a connection
+ * request is received (the second kind of socket mentioned above), we create a
+ * new socket and refer to it as a pending socket. These pending sockets are
+ * placed on the pending connection list of the listener socket. When future
+ * packets are received for the address the listener socket is bound to, we
+ * check if the source of the packet is from one that has an existing pending
+ * connection. If it does, we process the packet for the pending socket. When
+ * that socket reaches the connected state, it is removed from the listener
+ * socket's pending list and enqueued in the listener socket's accept queue.
+ * Callers of accept(2) will accept connected sockets from the listener socket's
+ * accept queue. If the socket cannot be accepted for some reason then it is
+ * marked rejected. Once the connection is accepted, it is owned by the user
+ * process and the responsibility for cleanup falls with that user process.
+ *
+ * - It is possible that these pending sockets will never reach the connected
+ * state; in fact, we may never receive another packet after the connection
+ * request. Because of this, we must schedule a cleanup function to run in the
+ * future, after some amount of time passes where a connection should have been
+ * established. This function ensures that the socket is off all lists so it
+ * cannot be retrieved, then drops all references to the socket so it is cleaned
+ * up (sock_put() -> sk_free() -> our sk_destruct implementation). Note this
+ * function will also cleanup rejected sockets, those that reach the connected
+ * state but leave it before they have been accepted.
+ *
+ * - Sockets created by user action will be cleaned up when the user process
+ * calls close(2), causing our release implementation to be called. Our release
+ * implementation will perform some cleanup then drop the last reference so our
+ * sk_destruct implementation is invoked. Our sk_destruct implementation will
+ * perform additional cleanup that's common for both types of sockets.
+ *
+ * - A socket's reference count is what ensures that the structure won't be
+ * freed. Each entry in a list (such as the "global" bound and connected tables
+ * and the listener socket's pending list and connected queue) ensures a
+ * reference. When we defer work until process context and pass a socket as our
+ * argument, we must ensure the reference count is increased to ensure the
+ * socket isn't freed before the function is run; the deferred function will
+ * then drop the reference.
+ */
+
+#include <linux/types.h>
+
+#define EXPORT_SYMTAB
+#include <linux/kmod.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/miscdevice.h>
+#include <linux/poll.h>
+#include <linux/smp.h>
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+#include <linux/init.h>
+#include <linux/io.h>
+
+#include <linux/module.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h> /* for NULL */
+#include <net/sock.h>
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
+/*
+ * Include linux/cred.h via linux/sched.h - it is not nice, but as cpp does not
+ * have #ifexist...
+ */
+#include <linux/sched.h>
+
+#if !defined(cap_set_full)
+/* cap_set_full was removed in kernel version 3.0-rc4. */
+#define cap_set_full(_c) do { (_c) = CAP_FULL_SET; } while (0)
+#endif
+
+#include "af_vsock.h"
+#include "stats.h"
+#include "util.h"
+#include "vsock_version.h"
+
+/*
+ * All kernels above 2.6.33 have the kern parameter for the create call in
+ * struct net_proto_family.
+ */
+
+#define VSOCK_INVALID_FAMILY NPROTO
+#define VSOCK_AF_IS_REGISTERED(val) ((val) >= 0 && (val) < NPROTO)
+
+/*
+ * Prototypes
+ */
+
+/* Internal functions. */
+static bool vsock_vmci_proto_to_notify_struct(struct sock *sk,
+ vsock_proto_version * proto,
+ bool old_pkt_proto);
+static int vsock_vmci_recv_dgram_cb(void *data, struct vmci_datagram *dg);
+static int vsock_vmci_recv_stream_cb(void *data, struct vmci_datagram *dg);
+static void vsock_vmci_peer_attach_cb(vmci_id sub_id,
+ const struct vmci_event_data *ed,
+ void *client_data);
+static void vsock_vmci_peer_detach_cb(vmci_id sub_id,
+ const struct vmci_event_data *ed,
+ void *client_data);
+static void vsock_vmci_recv_pkt_work(struct work_struct *work);
+static int vsock_vmci_recv_listen(struct sock *sk, vsock_packet *pkt);
+static int vsock_vmci_recv_connecting_server(struct sock *sk,
+ struct sock *pending,
+ vsock_packet *pkt);
+static int vsock_vmci_recv_connecting_client(struct sock *sk,
+ vsock_packet *pkt);
+static int vsock_vmci_recv_connecting_client_negotiate(struct sock *sk,
+ vsock_packet *pkt);
+static int vsock_vmci_recv_connecting_client_invalid(struct sock *sk,
+ vsock_packet *pkt);
+static int vsock_vmci_recv_connected(struct sock *sk, vsock_packet *pkt);
+static int __vsock_vmci_bind(struct sock *sk, struct sockaddr_vm *addr);
+static struct sock *__vsock_vmci_create(struct net *net,
+ struct socket *sock,
+ struct sock *parent, gfp_t priority,
+ unsigned short type);
+static int vsock_vmci_register_with_vmci(void);
+static void vsock_vmci_unregister_with_vmci(void);
+
+/* Socket operations. */
+static void vsock_vmci_sk_destruct(struct sock *sk);
+static int vsock_vmci_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+static int vsock_vmci_release(struct socket *sock);
+static int vsock_vmci_bind(struct socket *sock,
+ struct sockaddr *addr, int addr_len);
+static int vsock_vmci_dgram_connect(struct socket *sock,
+ struct sockaddr *addr, int addr_len,
+ int flags);
+static int vsock_vmci_stream_connect(struct socket *sock, struct sockaddr *addr,
+ int addr_len, int flags);
+static int vsock_vmci_accept(struct socket *sock, struct socket *newsock,
+ int flags);
+static int vsock_vmci_getname(struct socket *sock, struct sockaddr *addr,
+ int *addr_len, int peer);
+static unsigned int vsock_vmci_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
+static int vsock_vmci_listen(struct socket *sock, int backlog);
+static int vsock_vmci_shutdown(struct socket *sock, int mode);
+
+typedef unsigned int vsock_setsockopt_len_type;
+static int vsock_vmci_stream_setsockopt(struct socket *sock, int level,
+ int optname, char __user *optval,
+ vsock_setsockopt_len_type optlen);
+
+static int vsock_vmci_stream_getsockopt(struct socket *sock, int level,
+ int optname, char __user *optval,
+ int __user *optlen);
+
+static int vsock_vmci_dgram_sendmsg(struct kiocb *kiocb,
+ struct socket *sock, struct msghdr *msg,
+ size_t len);
+static int vsock_vmci_dgram_recvmsg(struct kiocb *kiocb, struct socket *sock,
+ struct msghdr *msg, size_t len, int flags);
+static int vsock_vmci_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
+ struct msghdr *msg, size_t len);
+static int vsock_vmci_stream_recvmsg(struct kiocb *kiocb, struct socket *sock,
+ struct msghdr *msg, size_t len, int flags);
+
+static int vsock_vmci_create(struct net *net,
+ struct socket *sock, int protocol, int kern);
+
+/*
+ * Variables.
+ */
+
+/* Protocol family. */
+static struct proto vsock_vmci_proto = {
+ .name = "AF_VMCI",
+ /* Added in 2.6.10. */
+ .owner = THIS_MODULE,
+ /*
+ * From 2.6.9 until 2.6.11, these address families called
+ * sk_alloc_slab() and the allocated slab was assigned to the slab
+ * variable in the proto struct and was created of size slab_obj_size.
+ * As of 2.6.12 and later, this slab allocation was moved into
+ * proto_register() and only done if you specified a non-zero value for
+ * the second argument (alloc_slab); the size of the slab element was
+ * changed to obj_size.
+ */
+ .obj_size = sizeof(vsock_vmci_sock),
+};
+
+static const struct net_proto_family vsock_vmci_family_ops = {
+ .family = AF_VSOCK,
+ .create = vsock_vmci_create,
+ .owner = THIS_MODULE,
+};
+
+/* Socket operations, split for DGRAM and STREAM sockets. */
+static const struct proto_ops vsock_vmci_dgram_ops = {
+ .family = PF_VSOCK,
+ .owner = THIS_MODULE,
+ .release = vsock_vmci_release,
+ .bind = vsock_vmci_bind,
+ .connect = vsock_vmci_dgram_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = vsock_vmci_getname,
+ .poll = vsock_vmci_poll,
+ .ioctl = sock_no_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = vsock_vmci_shutdown,
+ .setsockopt = sock_no_setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .sendmsg = vsock_vmci_dgram_sendmsg,
+ .recvmsg = vsock_vmci_dgram_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = sock_no_sendpage,
+};
+
+static const struct proto_ops vsock_vmci_stream_ops = {
+ .family = PF_VSOCK,
+ .owner = THIS_MODULE,
+ .release = vsock_vmci_release,
+ .bind = vsock_vmci_bind,
+ .connect = vsock_vmci_stream_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = vsock_vmci_accept,
+ .getname = vsock_vmci_getname,
+ .poll = vsock_vmci_poll,
+ .ioctl = sock_no_ioctl,
+ .listen = vsock_vmci_listen,
+ .shutdown = vsock_vmci_shutdown,
+ .setsockopt = vsock_vmci_stream_setsockopt,
+ .getsockopt = vsock_vmci_stream_getsockopt,
+ .sendmsg = vsock_vmci_stream_sendmsg,
+ .recvmsg = vsock_vmci_stream_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = sock_no_sendpage,
+};
+
+typedef struct vsock_recv_pkt_info {
+ struct work_struct work;
+ struct sock *sk;
+ vsock_packet pkt;
+} vsock_recv_pkt_info;
+
+static struct vmci_handle vmci_stream_handle = { VMCI_INVALID_ID,
+ VMCI_INVALID_ID };
+
+static vmci_id qp_resumed_sub_id = VMCI_INVALID_ID;
+
+static int PROTOCOL_OVERRIDE = -1;
+
+/*
+ * Netperf benchmarks have shown significant throughput improvements when the
+ * QP size is bumped from 64k to 256k. These measurements were taken during the
+ * K/L.next timeframe. Give users better performance by default.
+ */
+#define VSOCK_DEFAULT_QP_SIZE_MIN 128
+#define VSOCK_DEFAULT_QP_SIZE 262144
+#define VSOCK_DEFAULT_QP_SIZE_MAX 262144
+
+/*
+ * The default peer timeout indicates how long we will wait for a peer response
+ * to a control message.
+ */
+#define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ)
+
+#define LOG_PACKET(_pkt)
+
+/**
+ * vsock_vmci_old_proto_override --
+ *
+ * Check to see if the user has asked us to override all sockets to use the
+ * vsock notify protocol.
+ *
+ * Results: true if there is a protocol override in effect. - old_pkt_proto is
+ * true the original protocol should be used. False if there is no override in
+ * effect.
+ *
+ * Side effects: None.
+ */
+
+static bool vsock_vmci_old_proto_override(bool *old_pkt_proto)
+{
+ if (PROTOCOL_OVERRIDE != -1) {
+ if (PROTOCOL_OVERRIDE == 0)
+ *old_pkt_proto = true;
+ else
+ *old_pkt_proto = false;
+
+ pr_info("Proto override in use.\n");
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * vsock_vmci_proto_to_notify_struct --
+ *
+ * Given a particular notify protocol version, setup the socket's notify struct
+ * correctly.
+ *
+ * Results: true on success, false otherwise.
+ *
+ * Side effects: None.
+ */
+
+static bool
+vsock_vmci_proto_to_notify_struct(struct sock *sk,
+ vsock_proto_version *proto,
+ bool old_pkt_proto)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ if (old_pkt_proto) {
+ if (*proto != VSOCK_PROTO_INVALID) {
+ pr_err("Can't set both an old and new protocol\n");
+ return false;
+ }
+ vsk->notify_ops = &vsock_vmci_notify_pkt_ops;
+ goto exit;
+ }
+
+ switch (*proto) {
+ case VSOCK_PROTO_PKT_ON_NOTIFY:
+ vsk->notify_ops = &vsock_vmci_notify_pkt_q_state_ops;
+ break;
+ default:
+ pr_err("Unknown notify protocol version\n");
+ return false;
+ }
+
+exit:
+ NOTIFYCALL(vsk, socket_init, sk);
+ return true;
+}
+
+/*
+ * vsock_vmci_new_proto_supported_versions
+ *
+ * Gets the supported REQUEST2/NEGOTIATE2 vsock protocol versions.
+ *
+ * Results: Either 1 specific protocol version (override mode) or
+ * VSOCK_PROTO_ALL_SUPPORTED.
+ *
+ * Side effects: None.
+ */
+
+static vsock_proto_version vsock_vmci_new_proto_supported_versions(void)
+{
+ if (PROTOCOL_OVERRIDE != -1)
+ return PROTOCOL_OVERRIDE;
+
+ return VSOCK_PROTO_ALL_SUPPORTED;
+}
+
+/*
+ * VSockSocket_Trusted --
+ *
+ * We allow two kinds of sockets to communicate with a restricted VM: 1)
+ * trusted sockets 2) sockets from applications running as the same user as the
+ * VM (this is only true for the host side and only when using hosted products)
+ *
+ * Results: true if trusted communication is allowed to peer_cid, false
+ * otherwise.
+ *
+ * Side effects: None.
+ */
+
+static bool vsock_vmci_trusted(vsock_vmci_sock *vsock, vmci_id peer_cid)
+{
+ return vsock->trusted ||
+ vmci_is_context_owner(peer_cid, vsock->owner->uid);
+}
+
+/*
+ * VSockSocket_AllowDgram --
+ *
+ * We allow sending datagrams to and receiving datagrams from a restricted VM
+ * only if it is trusted as described in vsock_vmci_trusted.
+ *
+ * Results: true if datagram communication is allowed to peer_cid, false
+ * otherwise.
+ *
+ * Side effects: None.
+ */
+
+static bool vsock_vmci_allow_dgram(vsock_vmci_sock *vsock, vmci_id peer_cid)
+{
+ if (vsock->cached_peer != peer_cid) {
+ vsock->cached_peer = peer_cid;
+ if (!vsock_vmci_trusted(vsock, peer_cid) &&
+ (vmci_context_get_priv_flags(peer_cid) &
+ VMCI_PRIVILEGE_FLAG_RESTRICTED)) {
+ vsock->cached_peer_allow_dgram = false;
+ } else {
+ vsock->cached_peer_allow_dgram = true;
+ }
+ }
+
+ return vsock->cached_peer_allow_dgram;
+}
+
+/*
+ * vmci_sock_get_local_c_id --
+ *
+ * Kernel interface that allows external kernel modules to get the current VMCI
+ * context id. This version of the function is exported to kernel clients and
+ * should not change.
+ *
+ * Results: The context id on success, a negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+int vmci_sock_get_local_c_id(void)
+{
+ /* FIXME: needed? */
+ return vmci_get_context_id();
+}
+EXPORT_SYMBOL_GPL(vmci_sock_get_local_c_id);
+
+/*
+ * Helper functions.
+ */
+
+/*
+ * vsock_vmci_queue_pair_alloc --
+ *
+ * Allocates or attaches to a queue pair. Tries to register with trusted status
+ * if requested but does not fail if the queuepair could not be allocate as
+ * trusted (running in the guest)
+ *
+ * Results: 0 on success. A VSock error on error.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_queue_pair_alloc(struct vmci_qp **qpair,
+ struct vmci_handle *handle,
+ u64 produce_size,
+ u64 consume_size,
+ vmci_id peer, u32 flags, bool trusted)
+{
+ int err = 0;
+
+ if (trusted) {
+ /*
+ * Try to allocate our queue pair as trusted. This will only
+ * work if vsock is running in the host.
+ */
+
+ err = vmci_qpair_alloc(qpair, handle, produce_size,
+ consume_size,
+ peer, flags,
+ VMCI_PRIVILEGE_FLAG_TRUSTED);
+ if (err != VMCI_ERROR_NO_ACCESS)
+ goto out;
+
+ }
+
+ err = vmci_qpair_alloc(qpair, handle, produce_size, consume_size,
+ peer, flags, VMCI_NO_PRIVILEGE_FLAGS);
+out:
+ if (err < 0) {
+ pr_err("Could not attach to queue pair with %d\n",
+ err);
+ err = vsock_vmci_error_to_vsock_error(err);
+ }
+
+ return err;
+}
+
+/*
+ * vsock_vmci_datagram_create_hnd --
+ *
+ * Creates a datagram handle. Tries to register with trusted status but does
+ * not fail if the handler could not be allocated as trusted (running in the
+ * guest).
+ *
+ * Results: 0 on success. A VMCI error on error.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_datagram_create_hnd(vmci_id resource_id,
+ u32 flags,
+ vmci_datagram_recv_cb recv_cb,
+ void *client_data,
+ struct vmci_handle *out_handle)
+{
+ int err = 0;
+
+ /*
+ * Try to allocate our datagram handler as trusted. This will only work
+ * if vsock is running in the host.
+ */
+
+ err = vmci_datagram_create_handle_priv(resource_id, flags,
+ VMCI_PRIVILEGE_FLAG_TRUSTED,
+ recv_cb,
+ client_data, out_handle);
+
+ if (err == VMCI_ERROR_NO_ACCESS)
+ err = vmci_datagram_create_handle(resource_id, flags,
+ recv_cb, client_data,
+ out_handle);
+
+ return err;
+}
+
+/*
+ * vsock_vmci_recv_dgram_cb --
+ *
+ * VMCI Datagram receive callback. This function is used specifically for
+ * SOCK_DGRAM sockets.
+ *
+ * This is invoked as part of a tasklet that's scheduled when the VMCI
+ * interrupt fires. This is run in bottom-half context and if it ever needs to
+ * sleep it should defer that work to a work queue.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: An sk_buff is created and queued with this socket.
+ */
+
+static int vsock_vmci_recv_dgram_cb(void *data, struct vmci_datagram *dg)
+{
+ struct sock *sk;
+ size_t size;
+ struct sk_buff *skb;
+ vsock_vmci_sock *vsk;
+
+ ASSERT(dg->payload_size <= VMCI_MAX_DG_PAYLOAD_SIZE);
+
+ sk = (struct sock *)data;
+
+ /*
+ * This handler is privileged when this module is running on the host.
+ * We will get datagrams from all endpoints (even VMs that are in a
+ * restricted context). If we get one from a restricted context then
+ * the destination socket must be trusted.
+ *
+ * NOTE: We access the socket struct without holding the lock here.
+ * This is ok because the field we are interested is never modified
+ * outside of the create and destruct socket functions.
+ */
+ vsk = vsock_sk(sk);
+ if (!vsock_vmci_allow_dgram(vsk, VMCI_HANDLE_TO_CONTEXT_ID(dg->src)))
+ return VMCI_ERROR_NO_ACCESS;
+
+ size = VMCI_DG_SIZE(dg);
+
+ /*
+ * Attach the packet to the socket's receive queue as an sk_buff.
+ */
+ skb = alloc_skb(size, GFP_ATOMIC);
+ if (skb) {
+ /* sk_receive_skb() will do a sock_put(), so hold here. */
+ sock_hold(sk);
+ skb_put(skb, size);
+ memcpy(skb->data, dg, size);
+ sk_receive_skb(sk, skb, 0);
+ }
+
+ return VMCI_SUCCESS;
+}
+
+/*
+ * vsock_vmci_recv_stream_cb --
+ *
+ * VMCI stream receive callback for control datagrams. This function is used
+ * specifically for SOCK_STREAM sockets.
+ *
+ * This is invoked as part of a tasklet that's scheduled when the VMCI
+ * interrupt fires. This is run in bottom-half context but it defers most of
+ * its work to the packet handling work queue.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_recv_stream_cb(void *data, struct vmci_datagram *dg)
+{
+ struct sock *sk;
+ struct sockaddr_vm dst;
+ struct sockaddr_vm src;
+ vsock_packet *pkt;
+ vsock_vmci_sock *vsk;
+ bool bh_process_pkt;
+ int err;
+
+ ASSERT(dg->payload_size <= VMCI_MAX_DG_PAYLOAD_SIZE);
+
+ sk = NULL;
+ err = VMCI_SUCCESS;
+ bh_process_pkt = false;
+
+ /*
+ * Ignore incoming packets from contexts without sockets, or resources
+ * that aren't vsock implementations.
+ */
+
+ if (!vsock_addr_socket_context_stream
+ (VMCI_HANDLE_TO_CONTEXT_ID(dg->src))
+ || VSOCK_PACKET_RID != VMCI_HANDLE_TO_RESOURCE_ID(dg->src)) {
+ return VMCI_ERROR_NO_ACCESS;
+ }
+
+ if (VMCI_DG_SIZE(dg) < sizeof *pkt)
+ /* Drop datagrams that do not contain full VSock packets. */
+ return VMCI_ERROR_INVALID_ARGS;
+
+ pkt = (vsock_packet *) dg;
+
+ LOG_PACKET(pkt);
+
+ /*
+ * Find the socket that should handle this packet. First we look for a
+ * connected socket and if there is none we look for a socket bound to
+ * the destintation address.
+ */
+ vsock_addr_init(&src, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src),
+ pkt->src_port);
+
+ vsock_addr_init(&dst, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.dst),
+ pkt->dst_port);
+
+ sk = vsock_vmci_find_connected_socket(&src, &dst);
+ if (!sk) {
+ sk = vsock_vmci_find_bound_socket(&dst);
+ if (!sk) {
+ /*
+ * We could not find a socket for this specified
+ * address. If this packet is a RST, we just drop it.
+ * If it is another packet, we send a RST. Note that
+ * we do not send a RST reply to RSTs so that we do not
+ * continually send RSTs between two endpoints.
+ *
+ * Note that since this is a reply, dst is src and src
+ * is dst.
+ */
+ if (VSOCK_SEND_RESET_BH(&dst, &src, pkt) < 0)
+ pr_err("unable to send reset.\n");
+
+ err = VMCI_ERROR_NOT_FOUND;
+ goto out;
+ }
+ }
+
+ /*
+ * If the received packet type is beyond all types known to this
+ * implementation, reply with an invalid message. Hopefully this will
+ * help when implementing backwards compatibility in the future.
+ */
+ if (pkt->type >= VSOCK_PACKET_TYPE_MAX) {
+ VSOCK_SEND_INVALID_BH(&dst, &src);
+ err = VMCI_ERROR_INVALID_ARGS;
+ goto out;
+ }
+
+ /*
+ * This handler is privileged when this module is running on the host.
+ * We will get datagram connect requests from all endpoints (even VMs
+ * that are in a restricted context). If we get one from a restricted
+ * context then the destination socket must be trusted.
+ *
+ * NOTE: We access the socket struct without holding the lock here.
+ * This is ok because the field we are interested is never modified
+ * outside of the create and destruct socket functions.
+ */
+ vsk = vsock_sk(sk);
+ if (!vsock_vmci_allow_dgram
+ (vsk, VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src))) {
+ err = VMCI_ERROR_NO_ACCESS;
+ goto out;
+ }
+
+ /*
+ * We do most everything in a work queue, but let's fast path the
+ * notification of reads and writes to help data transfer performance.
+ * We can only do this if there is no process context code executing
+ * for this socket since that may change the state.
+ */
+ bh_lock_sock(sk);
+
+ if (!sock_owned_by_user(sk) && sk->sk_state == SS_CONNECTED)
+ NOTIFYCALL(vsk, handle_notify_pkt, sk, pkt, true, &dst, &src,
+ &bh_process_pkt);
+
+ bh_unlock_sock(sk);
+
+ if (!bh_process_pkt) {
+ vsock_recv_pkt_info *recv_pkt_info;
+
+ recv_pkt_info = kmalloc(sizeof *recv_pkt_info, GFP_ATOMIC);
+ if (!recv_pkt_info) {
+ if (VSOCK_SEND_RESET_BH(&dst, &src, pkt) < 0)
+ pr_err("unable to send reset\n");
+
+ err = VMCI_ERROR_NO_MEM;
+ goto out;
+ }
+
+ recv_pkt_info->sk = sk;
+ memcpy(&recv_pkt_info->pkt, pkt, sizeof recv_pkt_info->pkt);
+ INIT_WORK(&recv_pkt_info->work, vsock_vmci_recv_pkt_work);
+
+ schedule_work(&recv_pkt_info->work);
+ /*
+ * Clear sk so that the reference count incremented by one of
+ * the Find functions above is not decremented below. We need
+ * that reference count for the packet handler we've scheduled
+ * to run.
+ */
+ sk = NULL;
+ }
+
+out:
+ if (sk)
+ sock_put(sk);
+
+ return err;
+}
+
+/*
+ * vsock_vmci_peer_attach_cb --
+ *
+ * Invoked when a peer attaches to a queue pair.
+ *
+ * Right now this does not do anything.
+ *
+ * Results: None.
+ *
+ * Side effects: May modify socket state and signal socket.
+ */
+
+static void vsock_vmci_peer_attach_cb(vmci_id sub_id,
+ const struct vmci_event_data *e_data,
+ void *client_data)
+{
+ struct sock *sk = client_data;
+ const struct vmci_event_payload_qp *e_payload;
+ vsock_vmci_sock *vsk;
+
+ e_payload = vmci_event_data_const_payload(e_data);
+
+ vsk = vsock_sk(sk);
+
+ /*
+ * We don't ask for delayed CBs when we subscribe to this event (we
+ * pass 0 as flags to vmci_event_subscribe()). VMCI makes no
+ * guarantees in that case about what context we might be running in,
+ * so it could be BH or process, blockable or non-blockable. So we
+ * need to account for all possible contexts here.
+ */
+ local_bh_disable();
+ bh_lock_sock(sk);
+
+ /*
+ * XXX This is lame, we should provide a way to lookup sockets by
+ * qp_handle.
+ */
+ if (VMCI_HANDLE_EQUAL(vsk->qp_handle, e_payload->handle)) {
+ /*
+ * XXX This doesn't do anything, but in the future we may want
+ * to set a flag here to verify the attach really did occur and
+ * we weren't just sent a datagram claiming it was.
+ */
+ goto out;
+ }
+
+out:
+ bh_unlock_sock(sk);
+ local_bh_enable();
+}
+
+/*
+ *
+ * vsock_vmci_handle_detach --
+ *
+ * Perform the work necessary when the peer has detached.
+ *
+ * Note that this assumes the socket lock is held.
+ *
+ * Results: None.
+ *
+ * Side effects: The socket's and its peer's shutdown mask will be set
+ * appropriately, and any callers waiting on this socket will be awoken.
+ */
+
+static void vsock_vmci_handle_detach(struct sock *sk)
+{
+ vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+ if (!VMCI_HANDLE_INVALID(vsk->qp_handle)) {
+ sock_set_flag(sk, SOCK_DONE);
+
+ /*
+ * On a detach the peer will not be sending or receiving
+ * anymore.
+ */
+ vsk->peer_shutdown = SHUTDOWN_MASK;
+
+ /*
+ * We should not be sending anymore since the peer won't be
+ * there to receive, but we can still receive if there is data
+ * left in our consume queue.
+ */
+ if (vsock_vmci_stream_has_data(vsk) <= 0) {
+ if (sk->sk_state == SS_CONNECTING) {
+ /*
+ * The peer may detach from a queue pair while
+ * we are still in the connecting state, i.e.,
+ * if the peer VM is killed after attaching to
+ * a queue pair, but before we complete the
+ * handshake. In that case, we treat the detach
+ * event like a reset.
+ */
+
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = ECONNRESET;
+ sk->sk_error_report(sk);
+ return;
+ }
+ sk->sk_state = SS_UNCONNECTED;
+ }
+ sk->sk_state_change(sk);
+ }
+}
+
+/*
+ * vsock_vmci_peer_detach_cb --
+ *
+ * Invoked when a peer detaches from a queue pair.
+ *
+ * Results: None.
+ *
+ * Side effects: May modify socket state and signal socket.
+ */
+
+static void vsock_vmci_peer_detach_cb(vmci_id sub_id,
+ const struct vmci_event_data *e_data,
+ void *client_data)
+{
+ struct sock *sk = client_data;
+ const struct vmci_event_payload_qp *e_payload;
+ vsock_vmci_sock *vsk;
+
+ e_payload = vmci_event_data_const_payload(e_data);
+ vsk = vsock_sk(sk);
+ if (VMCI_HANDLE_INVALID(e_payload->handle))
+ return;
+
+ /* Same rules for locking as for peer_attach_cb(). */
+ local_bh_disable();
+ bh_lock_sock(sk);
+
+ /*
+ * XXX This is lame, we should provide a way to lookup sockets by
+ * qp_handle.
+ */
+ if (VMCI_HANDLE_EQUAL(vsk->qp_handle, e_payload->handle))
+ vsock_vmci_handle_detach(sk);
+
+ bh_unlock_sock(sk);
+ local_bh_enable();
+}
+
+/*
+ * vsock_vmci_qp_resumed_cb --
+ *
+ * Invoked when a VM is resumed. We must mark all connected stream sockets as
+ * detached.
+ *
+ * Results: None.
+ *
+ * Side effects: May modify socket state and signal socket.
+ */
+
+static void vsock_vmci_qp_resumed_cb(vmci_id sub_id,
+ const struct vmci_event_data *e_data,
+ void *client_data)
+{
+ int i;
+
+ spin_lock_bh(&vsock_table_lock);
+
+ /*
+ * XXX This loop should probably be provided by util.{h,c}, but that's
+ * for another day.
+ */
+ for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) {
+ vsock_vmci_sock *vsk;
+
+ list_for_each_entry(vsk, &vsock_connected_table[i],
+ connected_table) {
+ struct sock *sk = sk_vsock(vsk);
+
+ /*
+ * XXX Technically this is racy but the resulting
+ * outcome from such a race is relatively harmless. My
+ * next change will be a fix to this.
+ */
+ vsock_vmci_handle_detach(sk);
+ }
+ }
+
+ spin_unlock_bh(&vsock_table_lock);
+}
+
+/*
+ * vsock_vmci_pending_work --
+ *
+ * Releases the resources for a pending socket if it has not reached the
+ * connected state and been accepted by a user process.
+ *
+ * Results: None.
+ *
+ * Side effects: The socket may be removed from the connected list and all its
+ * resources freed.
+ */
+
+static void vsock_vmci_pending_work(struct work_struct *work)
+{
+ struct sock *sk;
+ struct sock *listener;
+ vsock_vmci_sock *vsk;
+ bool cleanup;
+
+ vsk = container_of(work, vsock_vmci_sock, dwork.work);
+ sk = sk_vsock(vsk);
+ listener = vsk->listener;
+ cleanup = true;
+
+ lock_sock(listener);
+ lock_sock(sk);
+
+ /*
+ * The socket should be on the pending list or the accept queue, but
+ * not both. It's also possible that the socket isn't on either.
+ */
+ ASSERT((vsock_vmci_is_pending(sk) && !vsock_vmci_in_accept_queue(sk))
+ || (!vsock_vmci_is_pending(sk) && vsock_vmci_in_accept_queue(sk))
+ || (!vsock_vmci_is_pending(sk)
+ && !vsock_vmci_in_accept_queue(sk)));
+
+ if (vsock_vmci_is_pending(sk)) {
+ vsock_vmci_remove_pending(listener, sk);
+ } else if (!vsk->rejected) {
+ /*
+ * We are not on the pending list and accept() did not reject
+ * us, so we must have been accepted by our user process. We
+ * just need to drop our references to the sockets and be on
+ * our way.
+ */
+ cleanup = false;
+ goto out;
+ }
+
+ listener->sk_ack_backlog--;
+
+ /*
+ * We need to remove ourself from the global connected sockets list so
+ * incoming packets can't find this socket, and to reduce the reference
+ * count.
+ */
+ if (vsock_vmci_in_connected_table(sk))
+ vsock_vmci_remove_connected(sk);
+
+ sk->sk_state = SS_FREE;
+
+out:
+ release_sock(sk);
+ release_sock(listener);
+ if (cleanup)
+ sock_put(sk);
+
+ sock_put(sk);
+ sock_put(listener);
+}
+
+/*
+ * vsock_vmci_recv_pkt_work --
+ *
+ * Handles an incoming control packet for the provided socket. This is the
+ * state machine for our stream sockets.
+ *
+ * Results: None.
+ *
+ * Side effects: May set state and wakeup threads waiting for socket state to
+ * change.
+ */
+
+static void vsock_vmci_recv_pkt_work(struct work_struct *work)
+{
+ vsock_recv_pkt_info *recv_pkt_info;
+ vsock_packet *pkt;
+ struct sock *sk;
+
+ recv_pkt_info = container_of(work, vsock_recv_pkt_info, work);
+ sk = recv_pkt_info->sk;
+ pkt = &recv_pkt_info->pkt;
+
+ ASSERT(pkt->type < VSOCK_PACKET_TYPE_MAX);
+
+ lock_sock(sk);
+
+ switch (sk->sk_state) {
+ case SS_LISTEN:
+ vsock_vmci_recv_listen(sk, pkt);
+ break;
+ case SS_CONNECTING:
+ /*
+ * Processing of pending connections for servers goes through
+ * the listening socket, so see vsock_vmci_recv_listen() for
+ * that path.
+ */
+ vsock_vmci_recv_connecting_client(sk, pkt);
+ break;
+ case SS_CONNECTED:
+ vsock_vmci_recv_connected(sk, pkt);
+ break;
+ default:
+ /*
+ * Because this function does not run in the same context as
+ * vsock_vmci_recv_stream_cb it is possible that the socket has
+ * closed. We need to let the other side know or it could be
+ * sitting in a connect and hang forever. Send a reset to
+ * prevent that.
+ */
+ VSOCK_SEND_RESET(sk, pkt);
+ goto out;
+ }
+
+out:
+ release_sock(sk);
+ kfree(recv_pkt_info);
+ /*
+ * Release reference obtained in the stream callback when we fetched
+ * this socket out of the bound or connected list.
+ */
+ sock_put(sk);
+}
+
+/*
+ * vsock_vmci_recv_listen --
+ *
+ * Receives packets for sockets in the listen state.
+ *
+ * Note that this assumes the socket lock is held.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: A new socket may be created and a negotiate control packet is
+ * sent.
+ */
+
+static int vsock_vmci_recv_listen(struct sock *sk, vsock_packet *pkt)
+{
+ struct sock *pending;
+ vsock_vmci_sock *vpending;
+ int err;
+ u64 qp_size;
+ bool old_request = false;
+ bool old_pkt_proto = false;
+
+ ASSERT(sk->sk_state == SS_LISTEN);
+
+ err = 0;
+
+ /*
+ * Because we are in the listen state, we could be receiving a packet
+ * for ourself or any previous connection requests that we received.
+ * If it's the latter, we try to find a socket in our list of pending
+ * connections and, if we do, call the appropriate handler for the
+ * state that that socket is in. Otherwise we try to service the
+ * connection request.
+ */
+ pending = vsock_vmci_get_pending(sk, pkt);
+ if (pending) {
+ lock_sock(pending);
+ switch (pending->sk_state) {
+ case SS_CONNECTING:
+ err =
+ vsock_vmci_recv_connecting_server(sk, pending, pkt);
+ break;
+ default:
+ VSOCK_SEND_RESET(pending, pkt);
+ err = -EINVAL;
+ }
+
+ if (err < 0)
+ vsock_vmci_remove_pending(sk, pending);
+
+ release_sock(pending);
+ vsock_vmci_release_pending(pending);
+
+ return err;
+ }
+
+ /*
+ * The listen state only accepts connection requests. Reply with a
+ * reset unless we received a reset.
+ */
+
+ if (!(pkt->type == VSOCK_PACKET_TYPE_REQUEST ||
+ pkt->type == VSOCK_PACKET_TYPE_REQUEST2)) {
+ VSOCK_REPLY_RESET(pkt);
+ return -EINVAL;
+ }
+
+ if (pkt->u.size == 0) {
+ VSOCK_REPLY_RESET(pkt);
+ return -EINVAL;
+ }
+
+ /*
+ * If this socket can't accommodate this connection request, we send a
+ * reset. Otherwise we create and initialize a child socket and reply
+ * with a connection negotiation.
+ */
+ if (sk->sk_ack_backlog >= sk->sk_max_ack_backlog) {
+ VSOCK_REPLY_RESET(pkt);
+ return -ECONNREFUSED;
+ }
+
+ pending = __vsock_vmci_create(sock_net(sk), NULL, sk, GFP_KERNEL,
+ sk->sk_type);
+ if (!pending) {
+ VSOCK_SEND_RESET(sk, pkt);
+ return -ENOMEM;
+ }
+
+ vpending = vsock_sk(pending);
+ ASSERT(vsock_sk(sk)->local_addr.svm_port == pkt->dst_port);
+
+ vsock_addr_init(&vpending->local_addr,
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.dst), pkt->dst_port);
+ vsock_addr_init(&vpending->remote_addr,
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src), pkt->src_port);
+
+ /*
+ * If the proposed size fits within our min/max, accept it. Otherwise
+ * propose our own size.
+ */
+ if (pkt->u.size >= vpending->queue_pair_min_size &&
+ pkt->u.size <= vpending->queue_pair_max_size) {
+ qp_size = pkt->u.size;
+ } else {
+ qp_size = vpending->queue_pair_size;
+ }
+
+ /*
+ * Figure out if we are using old or new requests based on the
+ * overrides pkt types sent by our peer.
+ */
+ if (vsock_vmci_old_proto_override(&old_pkt_proto)) {
+ old_request = old_pkt_proto;
+ } else {
+ if (pkt->type == VSOCK_PACKET_TYPE_REQUEST)
+ old_request = true;
+ else if (pkt->type == VSOCK_PACKET_TYPE_REQUEST2)
+ old_request = false;
+
+ }
+
+ if (old_request) {
+ /* Handle a REQUEST (or override) */
+ vsock_proto_version version = VSOCK_PROTO_INVALID;
+ if (vsock_vmci_proto_to_notify_struct(pending, &version, true))
+ err = VSOCK_SEND_NEGOTIATE(pending, qp_size);
+ else
+ err = -EINVAL;
+
+ } else {
+ /* Handle a REQUEST2 (or override) */
+ int proto_int = pkt->proto;
+ int pos;
+ u16 active_proto_version = 0;
+
+ /*
+ * The list of possible protocols is the intersection of all
+ * protocols the client supports ... plus all the protocols we
+ * support.
+ */
+ proto_int &= vsock_vmci_new_proto_supported_versions();
+
+ /* We choose the highest possible protocol version and use that
+ * one. */
+ pos = fls(proto_int);
+ if (pos) {
+ active_proto_version = (1 << (pos - 1));
+ if (vsock_vmci_proto_to_notify_struct
+ (pending, &active_proto_version, false))
+ err =
+ VSOCK_SEND_NEGOTIATE2(pending, qp_size,
+ active_proto_version);
+ else
+ err = -EINVAL;
+
+ } else {
+ err = -EINVAL;
+ }
+ }
+
+ if (err < 0) {
+ VSOCK_SEND_RESET(sk, pkt);
+ sock_put(pending);
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto out;
+ }
+
+ vsock_vmci_add_pending(sk, pending);
+ sk->sk_ack_backlog++;
+
+ pending->sk_state = SS_CONNECTING;
+ vpending->produce_size = vpending->consume_size = qp_size;
+ vpending->queue_pair_size = qp_size;
+
+ NOTIFYCALL(vpending, process_request, pending);
+
+ /*
+ * We might never receive another message for this socket and it's not
+ * connected to any process, so we have to ensure it gets cleaned up
+ * ourself. Our delayed work function will take care of that. Note
+ * that we do not ever cancel this function since we have few
+ * guarantees about its state when calling cancel_delayed_work().
+ * Instead we hold a reference on the socket for that function and make
+ * it capable of handling cases where it needs to do nothing but
+ * release that reference.
+ */
+ vpending->listener = sk;
+ sock_hold(sk);
+ sock_hold(pending);
+ INIT_DELAYED_WORK(&vpending->dwork, vsock_vmci_pending_work);
+ schedule_delayed_work(&vpending->dwork, HZ);
+
+out:
+ return err;
+}
+
+/*
+ * vsock_vmci_recv_connecting_server --
+ *
+ * Receives packets for sockets in the connecting state on the server side.
+ *
+ * Connecting sockets on the server side can only receive queue pair offer
+ * packets. All others should be treated as cause for closing the connection.
+ *
+ * Note that this assumes the socket lock is held for both sk and pending.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: A queue pair may be created, an attach control packet may be
+ * sent, the socket may transition to the connected state, and a pending caller
+ * in accept() may be woken up.
+ */
+
+static int
+vsock_vmci_recv_connecting_server(struct sock *listener,
+ struct sock *pending, vsock_packet *pkt)
+{
+ vsock_vmci_sock *vpending;
+ struct vmci_handle handle;
+ struct vmci_qp *qpair;
+ bool is_local;
+ u32 flags;
+ vmci_id detach_sub_id;
+ int err;
+ int skerr;
+
+ ASSERT(listener->sk_state == SS_LISTEN);
+ ASSERT(pending->sk_state == SS_CONNECTING);
+
+ vpending = vsock_sk(pending);
+ detach_sub_id = VMCI_INVALID_ID;
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_OFFER:
+ if (VMCI_HANDLE_INVALID(pkt->u.handle)) {
+ VSOCK_SEND_RESET(pending, pkt);
+ skerr = EPROTO;
+ err = -EINVAL;
+ goto destroy;
+ }
+ break;
+ default:
+ /* Close and cleanup the connection. */
+ VSOCK_SEND_RESET(pending, pkt);
+ skerr = EPROTO;
+ err = pkt->type == VSOCK_PACKET_TYPE_RST ? 0 : -EINVAL;
+ goto destroy;
+ }
+
+ ASSERT(pkt->type == VSOCK_PACKET_TYPE_OFFER);
+
+ /*
+ * In order to complete the connection we need to attach to the offered
+ * queue pair and send an attach notification. We also subscribe to the
+ * detach event so we know when our peer goes away, and we do that
+ * before attaching so we don't miss an event. If all this succeeds,
+ * we update our state and wakeup anything waiting in accept() for a
+ * connection.
+ */
+
+ /*
+ * We don't care about attach since we ensure the other side has
+ * attached by specifying the ATTACH_ONLY flag below.
+ */
+ err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH,
+ vsock_vmci_peer_detach_cb,
+ pending, &detach_sub_id);
+ if (err < VMCI_SUCCESS) {
+ VSOCK_SEND_RESET(pending, pkt);
+ err = vsock_vmci_error_to_vsock_error(err);
+ skerr = -err;
+ goto destroy;
+ }
+
+ vpending->detach_sub_id = detach_sub_id;
+
+ /* Now attach to the queue pair the client created. */
+ handle = pkt->u.handle;
+
+ /*
+ * vpending->local_addr always has a context id so we do not need to
+ * worry about VMADDR_CID_ANY in this case.
+ */
+ is_local =
+ vpending->remote_addr.svm_cid == vpending->local_addr.svm_cid;
+ flags = VMCI_QPFLAG_ATTACH_ONLY;
+ flags |= is_local ? VMCI_QPFLAG_LOCAL : 0;
+
+ err = vsock_vmci_queue_pair_alloc(&qpair,
+ &handle,
+ vpending->produce_size,
+ vpending->consume_size,
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->
+ dg.src),
+ flags,
+ vsock_vmci_trusted(
+ vpending,
+ vpending->remote_addr.svm_cid));
+ if (err < 0) {
+ VSOCK_SEND_RESET(pending, pkt);
+ skerr = -err;
+ goto destroy;
+ }
+
+ ASSERT(VMCI_HANDLE_EQUAL(handle, pkt->u.handle));
+ vpending->qp_handle = handle;
+ vpending->qpair = qpair;
+
+ /*
+ * When we send the attach message, we must be ready to handle incoming
+ * control messages on the newly connected socket. So we move the
+ * pending socket to the connected state before sending the attach
+ * message. Otherwise, an incoming packet triggered by the attach being
+ * received by the peer may be processed concurrently with what happens
+ * below after sending the attach message, and that incoming packet
+ * will find the listening socket instead of the (currently) pending
+ * socket. Note that enqueueing the socket increments the reference
+ * count, so even if a reset comes before the connection is accepted,
+ * the socket will be valid until it is removed from the queue.
+ *
+ * If we fail sending the attach below, we remove the socket from the
+ * connected list and move the socket to SS_UNCONNECTED before
+ * releasing the lock, so a pending slow path processing of an incoming
+ * packet will not see the socket in the connected state in that case.
+ */
+ pending->sk_state = SS_CONNECTED;
+
+ vsock_vmci_insert_connected(vsock_connected_sockets_vsk(vpending),
+ pending);
+
+ /* Notify our peer of our attach. */
+ err = VSOCK_SEND_ATTACH(pending, handle);
+ if (err < 0) {
+ vsock_vmci_remove_connected(pending);
+ pr_err("Could not send attach\n");
+ VSOCK_SEND_RESET(pending, pkt);
+ err = vsock_vmci_error_to_vsock_error(err);
+ skerr = -err;
+ goto destroy;
+ }
+
+ /*
+ * We have a connection. Move the now connected socket from the
+ * listener's pending list to the accept queue so callers of accept()
+ * can find it.
+ */
+ vsock_vmci_remove_pending(listener, pending);
+ vsock_vmci_enqueue_accept(listener, pending);
+
+ /*
+ * Callers of accept() will be be waiting on the listening socket, not
+ * the pending socket.
+ */
+ listener->sk_state_change(listener);
+
+ return 0;
+
+destroy:
+ pending->sk_err = skerr;
+ pending->sk_state = SS_UNCONNECTED;
+ /*
+ * As long as we drop our reference, all necessary cleanup will handle
+ * when the cleanup function drops its reference and our destruct
+ * implementation is called. Note that since the listen handler will
+ * remove pending from the pending list upon our failure, the cleanup
+ * function won't drop the additional reference, which is why we do it
+ * here.
+ */
+ sock_put(pending);
+
+ return err;
+}
+
+/*
+ * vsock_vmci_recv_connecting_client --
+ *
+ * Receives packets for sockets in the connecting state on the client side.
+ *
+ * Connecting sockets on the client side should only receive attach packets.
+ * All others should be treated as cause for closing the connection.
+ *
+ * Note that this assumes the socket lock is held for both sk and pending.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: The socket may transition to the connected state and wakeup
+ * the pending caller of connect().
+ */
+
+static int
+vsock_vmci_recv_connecting_client(struct sock *sk, vsock_packet *pkt)
+{
+ vsock_vmci_sock *vsk;
+ int err;
+ int skerr;
+
+ ASSERT(sk->sk_state == SS_CONNECTING);
+
+ vsk = vsock_sk(sk);
+
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_ATTACH:
+ if (VMCI_HANDLE_INVALID(pkt->u.handle) ||
+ !VMCI_HANDLE_EQUAL(pkt->u.handle, vsk->qp_handle)) {
+ skerr = EPROTO;
+ err = -EINVAL;
+ goto destroy;
+ }
+
+ /*
+ * Signify the socket is connected and wakeup the waiter in
+ * connect(). Also place the socket in the connected table for
+ * accounting (it can already be found since it's in the bound
+ * table).
+ */
+ sk->sk_state = SS_CONNECTED;
+ sk->sk_socket->state = SS_CONNECTED;
+ vsock_vmci_insert_connected(vsock_connected_sockets_vsk(vsk),
+ sk);
+ sk->sk_state_change(sk);
+
+ break;
+ case VSOCK_PACKET_TYPE_NEGOTIATE:
+ case VSOCK_PACKET_TYPE_NEGOTIATE2:
+ if (pkt->u.size == 0 ||
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src) !=
+ vsk->remote_addr.svm_cid
+ || pkt->src_port != vsk->remote_addr.svm_port
+ || !VMCI_HANDLE_INVALID(vsk->qp_handle) || vsk->qpair
+ || vsk->produce_size != 0 || vsk->consume_size != 0
+ || vsk->attach_sub_id != VMCI_INVALID_ID
+ || vsk->detach_sub_id != VMCI_INVALID_ID) {
+ skerr = EPROTO;
+ err = -EINVAL;
+
+ goto destroy;
+ }
+
+ err = vsock_vmci_recv_connecting_client_negotiate(sk, pkt);
+ if (err) {
+ skerr = -err;
+ goto destroy;
+ }
+
+ break;
+ case VSOCK_PACKET_TYPE_INVALID:
+ err = vsock_vmci_recv_connecting_client_invalid(sk, pkt);
+ if (err) {
+ skerr = -err;
+ goto destroy;
+ }
+
+ break;
+ case VSOCK_PACKET_TYPE_RST:
+ /*
+ * Older versions of the linux code (WS 6.5 / ESX 4.0) used to
+ * continue processing here after they sent an INVALID packet.
+ * This meant that we got a RST after the INVALID. We ignore a
+ * RST after an INVALID. The common code doesn't send the RST
+ * ... so we can hang if an old version of the common code
+ * fails between getting a REQUEST and sending an OFFER back.
+ * Not much we can do about it... except hope that it doesn't
+ * happen.
+ */
+ if (vsk->ignore_connecting_rst) {
+ vsk->ignore_connecting_rst = false;
+ } else {
+ skerr = ECONNRESET;
+ err = 0;
+ goto destroy;
+ }
+
+ break;
+ default:
+ /* Close and cleanup the connection. */
+ skerr = EPROTO;
+ err = -EINVAL;
+ goto destroy;
+ }
+
+ ASSERT(pkt->type == VSOCK_PACKET_TYPE_ATTACH ||
+ pkt->type == VSOCK_PACKET_TYPE_NEGOTIATE ||
+ pkt->type == VSOCK_PACKET_TYPE_NEGOTIATE2 ||
+ pkt->type == VSOCK_PACKET_TYPE_INVALID ||
+ pkt->type == VSOCK_PACKET_TYPE_RST);
+
+ return 0;
+
+destroy:
+ VSOCK_SEND_RESET(sk, pkt);
+
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = skerr;
+ sk->sk_error_report(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_recv_connecting_client_negotiate --
+ *
+ * Handles a negotiate packet for a client in the connecting state.
+ *
+ * Note that this assumes the socket lock is held for both sk and pending.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: The socket may transition to the connected state and wakeup
+ * the pending caller of connect().
+ */
+
+static int
+vsock_vmci_recv_connecting_client_negotiate(struct sock *sk, vsock_packet *pkt)
+{
+ int err;
+ vsock_vmci_sock *vsk;
+ struct vmci_handle handle;
+ struct vmci_qp *qpair;
+ vmci_id attach_sub_id;
+ vmci_id detach_sub_id;
+ bool is_local;
+ u32 flags;
+ bool old_proto = true;
+ bool old_pkt_proto;
+ vsock_proto_version version;
+
+ vsk = vsock_sk(sk);
+ handle = VMCI_INVALID_HANDLE;
+ attach_sub_id = VMCI_INVALID_ID;
+ detach_sub_id = VMCI_INVALID_ID;
+
+ ASSERT(pkt->u.size > 0);
+ ASSERT(vsk->remote_addr.svm_cid ==
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.src));
+ ASSERT(vsk->remote_addr.svm_port == pkt->src_port);
+ ASSERT(VMCI_HANDLE_INVALID(vsk->qp_handle));
+ ASSERT(vsk->qpair == NULL);
+ ASSERT(vsk->produce_size == 0);
+ ASSERT(vsk->consume_size == 0);
+ ASSERT(vsk->attach_sub_id == VMCI_INVALID_ID);
+ ASSERT(vsk->detach_sub_id == VMCI_INVALID_ID);
+
+ /*
+ * If we have gotten here then we should be past the point where old
+ * linux vsock could have sent the bogus rst.
+ */
+ vsk->sent_request = false;
+ vsk->ignore_connecting_rst = false;
+
+ /* Verify that we're OK with the proposed queue pair size */
+ if (pkt->u.size < vsk->queue_pair_min_size ||
+ pkt->u.size > vsk->queue_pair_max_size) {
+ err = -EINVAL;
+ goto destroy;
+ }
+
+ /*
+ * At this point we know the CID the peer is using to talk to us.
+ */
+
+ if (vsk->local_addr.svm_cid == VMADDR_CID_ANY)
+ vsk->local_addr.svm_cid =
+ VMCI_HANDLE_TO_CONTEXT_ID(pkt->dg.dst);
+
+ /*
+ * Setup the notify ops to be the highest supported version that both
+ * the server and the client support.
+ */
+
+ if (vsock_vmci_old_proto_override(&old_pkt_proto)) {
+ old_proto = old_pkt_proto;
+ } else {
+ if (pkt->type == VSOCK_PACKET_TYPE_NEGOTIATE)
+ old_proto = true;
+ else if (pkt->type == VSOCK_PACKET_TYPE_NEGOTIATE2)
+ old_proto = false;
+
+ }
+
+ if (old_proto)
+ version = VSOCK_PROTO_INVALID;
+ else
+ version = pkt->proto;
+
+ if (!vsock_vmci_proto_to_notify_struct(sk, &version, old_proto)) {
+ err = -EINVAL;
+ goto destroy;
+ }
+
+ /*
+ * Subscribe to attach and detach events first.
+ *
+ * XXX We attach once for each queue pair created for now so it is easy
+ * to find the socket (it's provided), but later we should only
+ * subscribe once and add a way to lookup sockets by queue pair handle.
+ */
+ err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_ATTACH,
+ vsock_vmci_peer_attach_cb,
+ sk, &attach_sub_id);
+ if (err < VMCI_SUCCESS) {
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto destroy;
+ }
+
+ err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH,
+ vsock_vmci_peer_detach_cb,
+ sk, &detach_sub_id);
+ if (err < VMCI_SUCCESS) {
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto destroy;
+ }
+
+ /* Make VMCI select the handle for us. */
+ handle = VMCI_INVALID_HANDLE;
+ is_local = vsk->remote_addr.svm_cid == vsk->local_addr.svm_cid;
+ flags = is_local ? VMCI_QPFLAG_LOCAL : 0;
+
+ err = vsock_vmci_queue_pair_alloc(&qpair,
+ &handle,
+ pkt->u.size,
+ pkt->u.size,
+ vsk->remote_addr.svm_cid,
+ flags,
+ vsock_vmci_trusted(
+ vsk,
+ vsk->
+ remote_addr.svm_cid));
+ if (err < 0)
+ goto destroy;
+
+ err = VSOCK_SEND_QP_OFFER(sk, handle);
+ if (err < 0) {
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto destroy;
+ }
+
+ vsk->qp_handle = handle;
+ vsk->qpair = qpair;
+
+ vsk->produce_size = vsk->consume_size = pkt->u.size;
+
+ vsk->attach_sub_id = attach_sub_id;
+ vsk->detach_sub_id = detach_sub_id;
+
+ NOTIFYCALL(vsk, process_negotiate, sk);
+
+ return 0;
+
+destroy:
+ if (attach_sub_id != VMCI_INVALID_ID) {
+ vmci_event_unsubscribe(attach_sub_id);
+ ASSERT(vsk->attach_sub_id == VMCI_INVALID_ID);
+ }
+
+ if (detach_sub_id != VMCI_INVALID_ID) {
+ vmci_event_unsubscribe(detach_sub_id);
+ ASSERT(vsk->detach_sub_id == VMCI_INVALID_ID);
+ }
+
+ if (!VMCI_HANDLE_INVALID(handle)) {
+ vmci_qpair_detach(&qpair);
+ ASSERT(VMCI_HANDLE_INVALID(vsk->qp_handle));
+ }
+
+ return err;
+}
+
+/*
+ * vsock_vmci_recv_connecting_client_invalid --
+ *
+ * Handles an invalid packet for a client in the connecting state.
+ *
+ * Note that this assumes the socket lock is held for both sk and pending.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_recv_connecting_client_invalid(struct sock *sk, vsock_packet *pkt)
+{
+ int err = 0;
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ if (vsk->sent_request) {
+ vsk->sent_request = false;
+ vsk->ignore_connecting_rst = true;
+
+ err = VSOCK_SEND_CONN_REQUEST(sk, vsk->queue_pair_size);
+ if (err < 0)
+ err = vsock_vmci_error_to_vsock_error(err);
+ else
+ err = 0;
+
+ }
+
+ return err;
+}
+
+/*
+ * vsock_vmci_recv_connected --
+ *
+ * Receives packets for sockets in the connected state.
+ *
+ * Connected sockets should only ever receive detach, wrote, read, or reset
+ * control messages. Others are treated as errors that are ignored.
+ *
+ * Wrote and read signify that the peer has produced or consumed, respectively.
+ *
+ * Detach messages signify that the connection is being closed cleanly and
+ * reset messages signify that the connection is being closed in error.
+ *
+ * Note that this assumes the socket lock is held.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: A queue pair may be created, an offer control packet sent, and
+ * the socket may transition to the connecting state.
+ *
+ */
+
+static int vsock_vmci_recv_connected(struct sock *sk, vsock_packet *pkt)
+{
+ vsock_vmci_sock *vsk;
+ bool pkt_processed = false;
+
+ ASSERT(sk->sk_state == SS_CONNECTED);
+
+ /*
+ * In cases where we are closing the connection, it's sufficient to
+ * mark the state change (and maybe error) and wake up any waiting
+ * threads. Since this is a connected socket, it's owned by a user
+ * process and will be cleaned up when the failure is passed back on
+ * the current or next system call. Our system call implementations
+ * must therefore check for error and state changes on entry and when
+ * being awoken.
+ */
+ switch (pkt->type) {
+ case VSOCK_PACKET_TYPE_SHUTDOWN:
+ if (pkt->u.mode) {
+ vsk = vsock_sk(sk);
+
+ vsk->peer_shutdown |= pkt->u.mode;
+ sk->sk_state_change(sk);
+ }
+ break;
+
+ case VSOCK_PACKET_TYPE_RST:
+ vsk = vsock_sk(sk);
+ /*
+ * It is possible that we sent our peer a message (e.g a
+ * WAITING_READ) right before we got notified that the peer had
+ * detached. If that happens then we can get a RST pkt back
+ * from our peer even though there is data available for us to
+ * read. In that case, don't shutdown the socket completely but
+ * instead allow the local client to finish reading data off
+ * the queuepair. Always treat a RST pkt in connected mode like
+ * a clean shutdown.
+ */
+ sock_set_flag(sk, SOCK_DONE);
+ vsk->peer_shutdown = SHUTDOWN_MASK;
+ if (vsock_vmci_stream_has_data(vsk) <= 0)
+ sk->sk_state = SS_DISCONNECTING;
+
+ sk->sk_state_change(sk);
+ break;
+
+ default:
+ vsk = vsock_sk(sk);
+ NOTIFYCALL(vsk, handle_notify_pkt, sk, pkt, false, NULL, NULL,
+ &pkt_processed);
+ if (!pkt_processed)
+ return -EINVAL;
+
+ break;
+ }
+
+ return 0;
+}
+
+/*
+ * __vsock_vmci_send_control_pkt --
+ *
+ * Common code to send a control packet.
+ *
+ * Results: Size of datagram sent on success, negative error code otherwise. If
+ * convert_error is true, error code is a vsock error, otherwise, result is a
+ * VMCI error code.
+ *
+ * Side effects: None.
+ */
+
+static int
+__vsock_vmci_send_control_pkt(vsock_packet *pkt,
+ struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ vsock_packet_type type,
+ u64 size,
+ u64 mode,
+ vsock_waiting_info *wait,
+ vsock_proto_version proto,
+ struct vmci_handle handle, bool convert_error)
+{
+ int err;
+
+ BUG_ON(vsock_addr_validate(src) != 0);
+ BUG_ON(vsock_addr_validate(dst) != 0);
+
+ vsock_packet_init(pkt, src, dst, type, size, mode, wait, proto, handle);
+ LOG_PACKET(pkt);
+ VSOCK_STATS_CTLPKT_LOG(pkt->type);
+ err = vmci_datagram_send(&pkt->dg);
+ if (convert_error && (err < 0))
+ return vsock_vmci_error_to_vsock_error(err);
+
+ return err;
+}
+
+/*
+ * vsock_vmci_reply_control_pkt_fast --
+ *
+ * Sends a control packet back to the source of an incoming packet. The control
+ * packet is allocated in the stack.
+ *
+ * Results: Size of datagram sent on success, negative error code otherwise.
+ *
+ * Side effects: None.
+ */
+
+int
+vsock_vmci_reply_control_pkt_fast(vsock_packet *pkt,
+ vsock_packet_type type,
+ u64 size,
+ u64 mode,
+ vsock_waiting_info *wait,
+ struct vmci_handle handle)
+{
+ vsock_packet reply;
+ struct sockaddr_vm src, dst;
+
+ if (pkt->type == VSOCK_PACKET_TYPE_RST) {
+ return 0;
+ } else {
+ vsock_packet_get_addresses(pkt, &src, &dst);
+ return __vsock_vmci_send_control_pkt(&reply, &src, &dst, type,
+ size, mode, wait,
+ VSOCK_PROTO_INVALID,
+ handle, true);
+ }
+}
+
+/*
+ * vsock_vmci_send_control_pkt_bh --
+ *
+ * Sends a control packet from bottom-half context. The control packet is
+ * static data to minimize the resource cost.
+ *
+ * Results: Size of datagram sent on success, negative error code otherwise.
+ * Note that we return a VMCI error message since that's what callers will need
+ * to provide.
+ *
+ * Side effects: None.
+ */
+
+int
+vsock_vmci_send_control_pkt_bh(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ vsock_packet_type type,
+ u64 size,
+ u64 mode,
+ vsock_waiting_info *wait,
+ struct vmci_handle handle)
+{
+ /*
+ * Note that it is safe to use a single packet across all CPUs since
+ * two tasklets of the same type are guaranteed to not ever run
+ * simultaneously. If that ever changes, or VMCI stops using tasklets,
+ * we can use per-cpu packets.
+ */
+ static vsock_packet pkt;
+
+ return __vsock_vmci_send_control_pkt(&pkt, src, dst, type,
+ size, mode, wait,
+ VSOCK_PROTO_INVALID, handle,
+ false);
+}
+
+/*
+ * vsock_vmci_send_control_pkt --
+ *
+ * Sends a control packet.
+ *
+ * Results: Size of datagram sent on success, negative error on failure.
+ *
+ * Side effects: None.
+ */
+
+int
+vsock_vmci_send_control_pkt(struct sock *sk,
+ vsock_packet_type type,
+ u64 size,
+ u64 mode,
+ vsock_waiting_info *wait,
+ vsock_proto_version proto,
+ struct vmci_handle handle)
+{
+ vsock_packet *pkt;
+ vsock_vmci_sock *vsk;
+ int err;
+
+ vsk = vsock_sk(sk);
+
+ if (!vsock_addr_bound(&vsk->local_addr))
+ return -EINVAL;
+
+ if (!vsock_addr_bound(&vsk->remote_addr))
+ return -EINVAL;
+
+ pkt = kmalloc(sizeof *pkt, GFP_KERNEL);
+ if (!pkt)
+ return -ENOMEM;
+
+ err =
+ __vsock_vmci_send_control_pkt(pkt, &vsk->local_addr,
+ &vsk->remote_addr, type, size, mode,
+ wait, proto, handle, true);
+ kfree(pkt);
+
+ return err;
+}
+
+/*
+ * __vsock_vmci_bind --
+ *
+ * Common functionality needed to bind the specified address to the VSocket.
+ * If VMADDR_CID_ANY or VMADDR_PORT_ANY are specified, the context ID or port
+ * are selected automatically.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: On success, a new datagram handle is created.
+ */
+
+static int __vsock_vmci_bind(struct sock *sk, struct sockaddr_vm *addr)
+{
+ static unsigned int port = LAST_RESERVED_PORT + 1;
+ struct sockaddr_vm new_addr;
+ vsock_vmci_sock *vsk;
+ vmci_id cid;
+ int err;
+
+ vsk = vsock_sk(sk);
+
+ /* First ensure this socket isn't already bound. */
+ if (vsock_addr_bound(&vsk->local_addr))
+ return -EINVAL;
+
+ /*
+ * Now bind to the provided address or select appropriate values if
+ * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY). Note that
+ * like AF_INET prevents binding to a non-local IP address (in most
+ * cases), we only allow binding to the local CID.
+ */
+ vsock_addr_init(&new_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+
+ cid = vmci_get_context_id();
+ if (addr->svm_cid != cid && addr->svm_cid != VMADDR_CID_ANY)
+ return -EADDRNOTAVAIL;
+
+ new_addr.svm_cid = addr->svm_cid;
+
+ switch (sk->sk_socket->type) {
+ case SOCK_STREAM:
+ spin_lock_bh(&vsock_table_lock);
+
+ if (addr->svm_port == VMADDR_PORT_ANY) {
+ bool found = false;
+ unsigned int i;
+
+ for (i = 0; i < MAX_PORT_RETRIES; i++) {
+ if (port <= LAST_RESERVED_PORT)
+ port = LAST_RESERVED_PORT + 1;
+
+ new_addr.svm_port = port++;
+
+ if (!__vsock_vmci_find_bound_socket
+ (&new_addr)) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ err = -EADDRNOTAVAIL;
+ goto out;
+ }
+ } else {
+ /*
+ * If port is in reserved range, ensure caller
+ * has necessary privileges.
+ */
+ if (addr->svm_port <= LAST_RESERVED_PORT &&
+ !capable(CAP_NET_BIND_SERVICE)) {
+ err = -EACCES;
+ goto out;
+ }
+
+ new_addr.svm_port = addr->svm_port;
+ if (__vsock_vmci_find_bound_socket(&new_addr)) {
+ err = -EADDRINUSE;
+ goto out;
+ }
+
+ }
+ break;
+ case SOCK_DGRAM: {
+ u32 flags = 0;
+
+ /*
+ * VMCI will select a resource ID for us if we provide
+ * VMCI_INVALID_ID.i
+ */
+ new_addr.svm_port = addr->svm_port == VMADDR_PORT_ANY ?
+ VMCI_INVALID_ID : addr->svm_port;
+
+ if (new_addr.svm_port <= LAST_RESERVED_PORT &&
+ !capable(CAP_NET_BIND_SERVICE)) {
+ err = -EACCES;
+ goto out;
+ }
+
+ if (new_addr.svm_cid == VMADDR_CID_ANY)
+ flags = VMCI_FLAG_ANYCID_DG_HND;
+
+ err = vsock_vmci_datagram_create_hnd(new_addr.svm_port,
+ flags,
+ vsock_vmci_recv_dgram_cb,
+ sk, &vsk->dg_handle);
+ if (err < VMCI_SUCCESS) {
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto out;
+ }
+
+ new_addr.svm_port = VMCI_HANDLE_TO_RESOURCE_ID(vsk->dg_handle);
+ break;
+ }
+ default:
+ err = -EINVAL;
+ goto out;
+ }
+
+ vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port);
+
+ /*
+ * Remove stream sockets from the unbound list and add them to the hash
+ * table for easy lookup by its address. The unbound list is simply an
+ * extra entry at the end of the hash table, a trick used by AF_UNIX.
+ */
+ if (sk->sk_socket->type == SOCK_STREAM) {
+ __vsock_vmci_remove_bound(sk);
+ __vsock_vmci_insert_bound(vsock_bound_sockets(&vsk->local_addr),
+ sk);
+ spin_unlock_bh(&vsock_table_lock);
+ }
+
+ BUG_ON(vsock_addr_validate(&vsk->local_addr) != 0);
+ return 0;
+
+out:
+ if (sk->sk_socket->type == SOCK_STREAM)
+ spin_unlock_bh(&vsock_table_lock);
+
+ return err;
+}
+
+/*
+ * __vsock_vmci_create --
+ *
+ * Does the work to create the sock structure. Note: If sock is NULL then the
+ * type field must be non-zero. Otherwise, sock is non-NULL and the type of
+ * sock is used in the newly created socket.
+ *
+ * Results: sock structure on success, NULL on failure.
+ *
+ * Side effects: Allocated sk is added to the unbound sockets list iff it is
+ * owned by a struct socket.
+ */
+
+static struct sock *__vsock_vmci_create(struct net *net,
+ struct socket *sock,
+ struct sock *parent,
+ gfp_t priority, unsigned short type)
+{
+ struct sock *sk;
+ vsock_vmci_sock *psk;
+ vsock_vmci_sock *vsk;
+
+ ASSERT((sock && !type) || (!sock && type));
+
+ vsk = NULL;
+
+ /*
+ * From 2.6.9 to until 2.6.12 sk_alloc() used a cache in the protocol
+ * structure, but you still had to specify the size and cache yourself.
+ * Most recently (in 2.6.24), sk_alloc() was changed to expect the
+ * network namespace, and the option to zero the sock was dropped.
+ */
+ sk = sk_alloc(net, vsock_vmci_family_ops.family, priority,
+ &vsock_vmci_proto);
+ if (!sk)
+ return NULL;
+
+ sock_init_data(sock, sk);
+
+ /*
+ * sk->sk_type is normally set in sock_init_data, but only if sock is
+ * non-NULL. We make sure that our sockets always have a type by
+ * setting it here if needed.
+ */
+ if (!sock)
+ sk->sk_type = type;
+
+ vsk = vsock_sk(sk);
+ vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+ vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+
+ sk->sk_destruct = vsock_vmci_sk_destruct;
+ sk->sk_backlog_rcv = vsock_vmci_queue_rcv_skb;
+ sk->sk_state = 0;
+ sock_reset_flag(sk, SOCK_DONE);
+
+ INIT_LIST_HEAD(&vsk->bound_table);
+ INIT_LIST_HEAD(&vsk->connected_table);
+ vsk->dg_handle = VMCI_INVALID_HANDLE;
+ vsk->qp_handle = VMCI_INVALID_HANDLE;
+ vsk->qpair = NULL;
+ vsk->produce_size = vsk->consume_size = 0;
+ vsk->listener = NULL;
+ INIT_LIST_HEAD(&vsk->pending_links);
+ INIT_LIST_HEAD(&vsk->accept_queue);
+ vsk->rejected = false;
+ vsk->sent_request = false;
+ vsk->ignore_connecting_rst = false;
+ vsk->attach_sub_id = vsk->detach_sub_id = VMCI_INVALID_ID;
+ vsk->peer_shutdown = 0;
+
+ if (parent) {
+ psk = vsock_sk(parent);
+ vsk->trusted = psk->trusted;
+ vsk->owner = get_cred(psk->owner);
+ vsk->queue_pair_size = psk->queue_pair_size;
+ vsk->queue_pair_min_size = psk->queue_pair_min_size;
+ vsk->queue_pair_max_size = psk->queue_pair_max_size;
+ vsk->connect_timeout = psk->connect_timeout;
+ } else {
+ vsk->trusted = capable(CAP_NET_ADMIN);
+ vsk->owner = get_current_cred();
+ vsk->queue_pair_size = VSOCK_DEFAULT_QP_SIZE;
+ vsk->queue_pair_min_size = VSOCK_DEFAULT_QP_SIZE_MIN;
+ vsk->queue_pair_max_size = VSOCK_DEFAULT_QP_SIZE_MAX;
+ vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
+ }
+
+ vsk->notify_ops = NULL;
+
+ if (sock)
+ vsock_vmci_insert_bound(vsock_unbound_sockets, sk);
+
+ return sk;
+}
+
+/*
+ * __vsock_vmci_release --
+ *
+ * Releases the provided socket.
+ *
+ * Results: None.
+ *
+ * Side effects: Any pending sockets are also released.
+ */
+
+static void __vsock_vmci_release(struct sock *sk)
+{
+ if (sk) {
+ struct sk_buff *skb;
+ struct sock *pending;
+ struct vsock_vmci_sock *vsk;
+
+ vsk = vsock_sk(sk);
+ pending = NULL; /* Compiler warning. */
+
+ if (vsock_vmci_in_bound_table(sk))
+ vsock_vmci_remove_bound(sk);
+
+ if (vsock_vmci_in_connected_table(sk))
+ vsock_vmci_remove_connected(sk);
+
+ if (!VMCI_HANDLE_INVALID(vsk->dg_handle)) {
+ vmci_datagram_destroy_handle(vsk->dg_handle);
+ vsk->dg_handle = VMCI_INVALID_HANDLE;
+ }
+
+ lock_sock(sk);
+ sock_orphan(sk);
+ sk->sk_shutdown = SHUTDOWN_MASK;
+
+ while ((skb = skb_dequeue(&sk->sk_receive_queue)))
+ kfree_skb(skb);
+
+ /* Clean up any sockets that never were accepted. */
+ while ((pending = vsock_vmci_dequeue_accept(sk)) != NULL) {
+ __vsock_vmci_release(pending);
+ sock_put(pending);
+ }
+
+ release_sock(sk);
+ sock_put(sk);
+ }
+}
+
+/*
+ * Sock operations.
+ */
+
+/*
+ * vsock_vmci_sk_destruct --
+ *
+ * Destroys the provided socket. This is called by sk_free(), which is invoke
+ * when the reference count of the socket drops to zero.
+ *
+ * Results: None.
+ *
+ * Side effects: Socket count is decremented.
+ */
+
+static void vsock_vmci_sk_destruct(struct sock *sk)
+{
+ vsock_vmci_sock *vsk = vsock_sk(sk);
+
+ if (vsk->attach_sub_id != VMCI_INVALID_ID) {
+ vmci_event_unsubscribe(vsk->attach_sub_id);
+ vsk->attach_sub_id = VMCI_INVALID_ID;
+ }
+
+ if (vsk->detach_sub_id != VMCI_INVALID_ID) {
+ vmci_event_unsubscribe(vsk->detach_sub_id);
+ vsk->detach_sub_id = VMCI_INVALID_ID;
+ }
+
+ if (!VMCI_HANDLE_INVALID(vsk->qp_handle)) {
+ vmci_qpair_detach(&vsk->qpair);
+ vsk->qp_handle = VMCI_INVALID_HANDLE;
+ vsk->produce_size = vsk->consume_size = 0;
+ }
+
+ /*
+ * Each list entry holds a reference on the socket, so we should not
+ * even be here if the socket is in one of our lists. If we are we
+ * have a stray sock_put() that needs to go away.
+ */
+ ASSERT(!vsock_vmci_in_bound_table(sk));
+ ASSERT(!vsock_vmci_in_connected_table(sk));
+ ASSERT(!vsock_vmci_is_pending(sk));
+ ASSERT(!vsock_vmci_in_accept_queue(sk));
+
+ /*
+ * When clearing these addresses, there's no need to set the family and
+ * possibly register the address family with the kernel.
+ */
+ vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+ vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+
+ NOTIFYCALL(vsk, socket_destruct, sk);
+
+ put_cred(vsk->owner);
+
+ VSOCK_STATS_CTLPKT_DUMP_ALL();
+ VSOCK_STATS_HIST_DUMP_ALL();
+ VSOCK_STATS_TOTALS_DUMP_ALL();
+}
+
+/*
+ * vsock_vmci_queue_rcv_skb --
+ *
+ * Receives skb on the socket's receive queue.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ int err;
+
+ err = sock_queue_rcv_skb(sk, skb);
+ if (err)
+ kfree_skb(skb);
+
+ return err;
+}
+
+/*
+ * vsock_vmci_register_with_vmci --
+ *
+ * Registers with the VMCI device, and creates control message and event
+ * handlers.
+ *
+ * Results: Zero on success, error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_register_with_vmci(void)
+{
+ int err = 0;
+
+ /*
+ * Create the datagram handle that we will use to send and receive all
+ * VSocket control messages for this context.
+ */
+ err = vsock_vmci_datagram_create_hnd(VSOCK_PACKET_RID,
+ VMCI_FLAG_ANYCID_DG_HND,
+ vsock_vmci_recv_stream_cb, NULL,
+ &vmci_stream_handle);
+ if (err < VMCI_SUCCESS) {
+ pr_err("Unable to create datagram handle. (%d)\n",
+ err);
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto out;
+ }
+
+ err = vmci_event_subscribe(VMCI_EVENT_QP_RESUMED,
+ vsock_vmci_qp_resumed_cb,
+ NULL, &qp_resumed_sub_id);
+ if (err < VMCI_SUCCESS) {
+ pr_err("Unable to subscribe to resumed event. (%d)\n",
+ err);
+ err = vsock_vmci_error_to_vsock_error(err);
+ qp_resumed_sub_id = VMCI_INVALID_ID;
+ goto out;
+ }
+
+out:
+ if (err != 0)
+ vsock_vmci_unregister_with_vmci();
+
+ return err;
+}
+
+/*
+ * vsock_vmci_unregister_with_vmci --
+ *
+ * Destroys control message and event handlers, and unregisters with the VMCI
+ * device
+ *
+ * Results: None.
+ *
+ * Side effects: Our socket implementation is no longer accessible.
+ */
+
+static void vsock_vmci_unregister_with_vmci(void)
+{
+ if (!VMCI_HANDLE_INVALID(vmci_stream_handle)) {
+ if (vmci_datagram_destroy_handle(vmci_stream_handle) !=
+ VMCI_SUCCESS)
+ pr_err("Couldn't destroy datagram handle.\n");
+
+ vmci_stream_handle = VMCI_INVALID_HANDLE;
+ }
+
+ if (qp_resumed_sub_id != VMCI_INVALID_ID) {
+ vmci_event_unsubscribe(qp_resumed_sub_id);
+ qp_resumed_sub_id = VMCI_INVALID_ID;
+ }
+}
+
+/*
+ * vsock_vmci_stream_has_data --
+ *
+ * Gets the amount of data available for a given stream socket's consume queue.
+ *
+ * Note that this assumes the socket lock is held.
+ *
+ * Results: The amount of data available or a VMCI error code on failure.
+ *
+ * Side effects: None.
+ */
+
+s64 vsock_vmci_stream_has_data(vsock_vmci_sock *vsk)
+{
+ return vmci_qpair_consume_buf_ready(vsk->qpair);
+}
+
+/*
+ * vsock_vmci_stream_has_space --
+ *
+ * Gets the amount of space available for a give stream socket's produce queue.
+ *
+ * Note that this assumes the socket lock is held.
+ *
+ * Results: The amount of space available or a VMCI error code on failure.
+ *
+ * Side effects: None.
+ */
+
+s64 vsock_vmci_stream_has_space(vsock_vmci_sock *vsk)
+{
+ return vmci_qpair_produce_free_space(vsk->qpair);
+}
+
+/*
+ * Socket operations.
+ */
+
+/*
+ *
+ * vsock_vmci_release --
+ *
+ * Releases the provided socket by freeing the contents of its queue. This is
+ * called when a user process calls close(2) on the socket.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_release(struct socket *sock)
+{
+ __vsock_vmci_release(sock->sk);
+ sock->sk = NULL;
+ sock->state = SS_FREE;
+
+ return 0;
+}
+
+/*
+ * vsock_vmci_bind --
+ *
+ * Binds the provided address to the provided socket.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
+{
+ int err;
+ struct sock *sk;
+ struct sockaddr_vm *vmci_addr;
+
+ sk = sock->sk;
+
+ if (vsock_addr_cast(addr, addr_len, &vmci_addr) != 0)
+ return -EINVAL;
+
+ lock_sock(sk);
+ err = __vsock_vmci_bind(sk, vmci_addr);
+ release_sock(sk);
+
+ return err;
+}
+
+/*
+ * vsock_vmci_dgram_connect --
+ *
+ * Connects a datagram socket. This can be called multiple times to change the
+ * socket's association and can be called with a sockaddr whose family is set
+ * to AF_UNSPEC to dissolve any existing association.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_dgram_connect(struct socket *sock,
+ struct sockaddr *addr, int addr_len, int flags)
+{
+ int err;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ struct sockaddr_vm *remote_addr;
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ err = vsock_addr_cast(addr, addr_len, &remote_addr);
+ if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) {
+ lock_sock(sk);
+ vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY,
+ VMADDR_PORT_ANY);
+ sock->state = SS_UNCONNECTED;
+ release_sock(sk);
+ return 0;
+ } else if (err != 0)
+ return -EINVAL;
+
+ lock_sock(sk);
+
+ if (!vsock_addr_bound(&vsk->local_addr)) {
+ struct sockaddr_vm local_addr;
+
+ vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+ err = __vsock_vmci_bind(sk, &local_addr);
+ if (err != 0)
+ goto out;
+
+ }
+
+ if (!vsock_addr_socket_context_dgram(remote_addr->svm_cid,
+ remote_addr->svm_port)) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ memcpy(&vsk->remote_addr, remote_addr, sizeof vsk->remote_addr);
+ sock->state = SS_CONNECTED;
+
+out:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_connect_timeout --
+ *
+ * Asynchronous connection attempts schedule this timeout function to notify
+ * the connector of an unsuccessfull connection attempt. If the socket is still
+ * in the connecting state and hasn't been closed, we mark the socket as timed
+ * out. Otherwise, we do nothing.
+ *
+ * Results: None.
+ *
+ * Side effects: May destroy the socket.
+ */
+
+static void vsock_vmci_connect_timeout(struct work_struct *work)
+{
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+
+ vsk = container_of(work, vsock_vmci_sock, dwork.work);
+ sk = sk_vsock(vsk);
+
+ lock_sock(sk);
+ if (sk->sk_state == SS_CONNECTING &&
+ (sk->sk_shutdown != SHUTDOWN_MASK)) {
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = ETIMEDOUT;
+ sk->sk_error_report(sk);
+ }
+ release_sock(sk);
+
+ sock_put(sk);
+}
+
+/*
+ * vsock_vmci_stream_connect --
+ *
+ * Connects a stream socket.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_stream_connect(struct socket *sock,
+ struct sockaddr *addr, int addr_len, int flags)
+{
+ int err;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ struct sockaddr_vm *remote_addr;
+ long timeout;
+ bool old_pkt_proto = false;
+ DEFINE_WAIT(wait);
+
+ err = 0;
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ lock_sock(sk);
+
+ /* XXX AF_UNSPEC should make us disconnect like AF_INET. */
+ switch (sock->state) {
+ case SS_CONNECTED:
+ err = -EISCONN;
+ goto out;
+ case SS_DISCONNECTING:
+ err = -EINVAL;
+ goto out;
+ case SS_CONNECTING:
+ /*
+ * This continues on so we can move sock into the SS_CONNECTED
+ * state once the connection has completed (at which point err
+ * will be set to zero also). Otherwise, we will either wait
+ * for the connection or return -EALREADY should this be a
+ * non-blocking call.
+ */
+ err = -EALREADY;
+ break;
+ default:
+ ASSERT(sk->sk_state == SS_FREE ||
+ sk->sk_state == SS_UNCONNECTED ||
+ sk->sk_state == SS_LISTEN);
+ if ((sk->sk_state == SS_LISTEN) ||
+ vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * The hypervisor and well-known contexts do not have socket
+ * endpoints.
+ */
+ if (!vsock_addr_socket_context_stream(remote_addr->svm_cid)) {
+ err = -ENETUNREACH;
+ goto out;
+ }
+
+ /* Set the remote address that we are connecting to. */
+ memcpy(&vsk->remote_addr, remote_addr, sizeof vsk->remote_addr);
+
+ /* Autobind this socket to the local address if necessary. */
+ if (!vsock_addr_bound(&vsk->local_addr)) {
+ struct sockaddr_vm local_addr;
+
+ vsock_addr_init(&local_addr, VMADDR_CID_ANY,
+ VMADDR_PORT_ANY);
+ err = __vsock_vmci_bind(sk, &local_addr);
+ if (err != 0)
+ goto out;
+
+ }
+
+ sk->sk_state = SS_CONNECTING;
+
+ if (vsock_vmci_old_proto_override(&old_pkt_proto)
+ && old_pkt_proto) {
+ err = VSOCK_SEND_CONN_REQUEST(sk, vsk->queue_pair_size);
+ if (err < 0) {
+ sk->sk_state = SS_UNCONNECTED;
+ goto out;
+ }
+ } else {
+ int supported_proto_versions =
+ vsock_vmci_new_proto_supported_versions();
+ err =
+ VSOCK_SEND_CONN_REQUEST2(sk, vsk->queue_pair_size,
+ supported_proto_versions);
+ if (err < 0) {
+ sk->sk_state = SS_UNCONNECTED;
+ goto out;
+ }
+
+ vsk->sent_request = true;
+ }
+
+ /*
+ * Mark sock as connecting and set the error code to in
+ * progress in case this is a non-blocking connect.
+ */
+ sock->state = SS_CONNECTING;
+ err = -EINPROGRESS;
+ }
+
+ /*
+ * The receive path will handle all communication until we are able to
+ * enter the connected state. Here we wait for the connection to be
+ * completed or a notification of an error.
+ */
+ timeout = vsk->connect_timeout;
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+
+ while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
+ if (flags & O_NONBLOCK) {
+ /*
+ * If we're not going to block, we schedule a timeout
+ * function to generate a timeout on the connection
+ * attempt, in case the peer doesn't respond in a
+ * timely manner. We hold on to the socket until the
+ * timeout fires.
+ */
+ sock_hold(sk);
+ INIT_DELAYED_WORK(&vsk->dwork,
+ vsock_vmci_connect_timeout);
+ schedule_delayed_work(&vsk->dwork, timeout);
+
+ /* Skip ahead to preserve error code set above. */
+ goto out_wait;
+ }
+
+ release_sock(sk);
+ timeout = schedule_timeout(timeout);
+ lock_sock(sk);
+
+ if (signal_pending(current)) {
+ err = sock_intr_errno(timeout);
+ goto out_wait_error;
+ } else if (timeout == 0) {
+ err = -ETIMEDOUT;
+ goto out_wait_error;
+ }
+
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ }
+
+ if (sk->sk_err) {
+ err = -sk->sk_err;
+ goto out_wait_error;
+ } else {
+ ASSERT(sk->sk_state == SS_CONNECTED);
+ err = 0;
+ }
+
+out_wait:
+ finish_wait(sk_sleep(sk), &wait);
+out:
+ release_sock(sk);
+ return err;
+
+out_wait_error:
+ sk->sk_state = SS_UNCONNECTED;
+ sock->state = SS_UNCONNECTED;
+ goto out_wait;
+}
+
+/*
+ * vsock_vmci_accept --
+ *
+ * Accepts next available connection request for this socket.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_accept(struct socket *sock, struct socket *newsock, int flags)
+{
+ struct sock *listener;
+ int err;
+ struct sock *connected;
+ vsock_vmci_sock *vconnected;
+ long timeout;
+ DEFINE_WAIT(wait);
+
+ err = 0;
+ listener = sock->sk;
+
+ lock_sock(listener);
+
+ if (sock->type != SOCK_STREAM) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ if (listener->sk_state != SS_LISTEN) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Wait for children sockets to appear; these are the new sockets
+ * created upon connection establishment.
+ */
+ timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
+ prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
+
+ while ((connected = vsock_vmci_dequeue_accept(listener)) == NULL &&
+ listener->sk_err == 0) {
+ release_sock(listener);
+ timeout = schedule_timeout(timeout);
+ lock_sock(listener);
+
+ if (signal_pending(current)) {
+ err = sock_intr_errno(timeout);
+ goto out_wait;
+ } else if (timeout == 0) {
+ err = -EAGAIN;
+ goto out_wait;
+ }
+
+ prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
+ }
+
+ if (listener->sk_err)
+ err = -listener->sk_err;
+
+ if (connected) {
+ listener->sk_ack_backlog--;
+
+ lock_sock(connected);
+ vconnected = vsock_sk(connected);
+
+ /*
+ * If the listener socket has received an error, then we should
+ * reject this socket and return. Note that we simply mark the
+ * socket rejected, drop our reference, and let the cleanup
+ * function handle the cleanup; the fact that we found it in
+ * the listener's accept queue guarantees that the cleanup
+ * function hasn't run yet.
+ */
+ if (err) {
+ vconnected->rejected = true;
+ release_sock(connected);
+ sock_put(connected);
+ goto out_wait;
+ }
+
+ newsock->state = SS_CONNECTED;
+ sock_graft(connected, newsock);
+ release_sock(connected);
+ sock_put(connected);
+ }
+
+out_wait:
+ finish_wait(sk_sleep(listener), &wait);
+out:
+ release_sock(listener);
+ return err;
+}
+
+/*
+ * vsock_vmci_getname --
+ *
+ * Provides the local or remote address for the socket.
+ *
+ * Results: Zero on success, negative error code otherwise.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_getname(struct socket *sock,
+ struct sockaddr *addr, int *addr_len, int peer)
+{
+ int err;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ struct sockaddr_vm *vmci_addr;
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+ err = 0;
+
+ lock_sock(sk);
+
+ if (peer) {
+ if (sock->state != SS_CONNECTED) {
+ err = -ENOTCONN;
+ goto out;
+ }
+ vmci_addr = &vsk->remote_addr;
+ } else {
+ vmci_addr = &vsk->local_addr;
+ }
+
+ if (!vmci_addr) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * sys_getsockname() and sys_getpeername() pass us a
+ * MAX_SOCK_ADDR-sized buffer and don't set addr_len. Unfortunately
+ * that macro is defined in socket.c instead of .h, so we hardcode its
+ * value here.
+ */
+ ASSERT_ON_COMPILE(sizeof *vmci_addr <= 128);
+ memcpy(addr, vmci_addr, sizeof *vmci_addr);
+ *addr_len = sizeof *vmci_addr;
+
+out:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_poll --
+ *
+ * Waits on file for activity then provides mask indicating state of socket.
+ *
+ * Results: Mask of flags containing socket state.
+ *
+ * Side effects: None.
+ */
+
+static unsigned int
+vsock_vmci_poll(struct file *file, struct socket *sock, poll_table *wait)
+{
+ struct sock *sk;
+ unsigned int mask;
+ vsock_vmci_sock *vsk;
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
+
+ if (sk->sk_err)
+ /* Signify that there has been an error on this socket. */
+ mask |= POLLERR;
+
+ /*
+ * INET sockets treat local write shutdown and peer write shutdown as a
+ * case of POLLHUP set.
+ */
+ if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
+ ((sk->sk_shutdown & SEND_SHUTDOWN) &&
+ (vsk->peer_shutdown & SEND_SHUTDOWN))) {
+ mask |= POLLHUP;
+ }
+
+ /* POLLRDHUP wasn't added until 2.6.17. */
+ if (sk->sk_shutdown & RCV_SHUTDOWN ||
+ vsk->peer_shutdown & SEND_SHUTDOWN) {
+ mask |= POLLRDHUP;
+ }
+
+ if (sock->type == SOCK_DGRAM) {
+ /*
+ * For datagram sockets we can read if there is something in
+ * the queue and write as long as the socket isn't shutdown for
+ * sending.
+ */
+ if (!skb_queue_empty(&sk->sk_receive_queue) ||
+ (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ mask |= POLLIN | POLLRDNORM;
+ }
+
+ if (!(sk->sk_shutdown & SEND_SHUTDOWN))
+ mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+
+ } else if (sock->type == SOCK_STREAM) {
+ lock_sock(sk);
+
+ /*
+ * Listening sockets that have connections in their accept
+ * queue can be read.
+ */
+ if (sk->sk_state == SS_LISTEN
+ && !vsock_vmci_is_accept_queue_empty(sk))
+ mask |= POLLIN | POLLRDNORM;
+
+ /*
+ * If there is something in the queue then we can read.
+ */
+ if (!VMCI_HANDLE_INVALID(vsk->qp_handle) &&
+ !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+ bool data_ready_now = false;
+ int ret = 0;
+ NOTIFYCALLRET(vsk, ret, poll_in, sk, 1,
+ &data_ready_now);
+ if (ret < 0) {
+ mask |= POLLERR;
+ } else {
+ if (data_ready_now)
+ mask |= POLLIN | POLLRDNORM;
+
+ }
+ }
+
+ /*
+ * Sockets whose connections have been closed, reset, or
+ * terminated should also be considered read, and we check the
+ * shutdown flag for that.
+ */
+ if (sk->sk_shutdown & RCV_SHUTDOWN ||
+ vsk->peer_shutdown & SEND_SHUTDOWN) {
+ mask |= POLLIN | POLLRDNORM;
+ }
+
+ /*
+ * Connected sockets that can produce data can be written.
+ */
+ if (sk->sk_state == SS_CONNECTED) {
+ if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+ bool space_avail_now = false;
+ int ret = 0;
+
+ NOTIFYCALLRET(vsk, ret, poll_out, sk, 1,
+ &space_avail_now);
+ if (ret < 0) {
+ mask |= POLLERR;
+ } else {
+ if (space_avail_now)
+ /*
+ * Remove POLLWRBAND since INET
+ * sockets are not setting it.
+ */
+ mask |= POLLOUT | POLLWRNORM;
+
+ }
+ }
+ }
+
+ /*
+ * Simulate INET socket poll behaviors, which sets
+ * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
+ * but local send is not shutdown.
+ */
+ if (sk->sk_state == SS_UNCONNECTED) {
+ if (!(sk->sk_shutdown & SEND_SHUTDOWN))
+ mask |= POLLOUT | POLLWRNORM;
+
+ }
+
+ release_sock(sk);
+ }
+
+ return mask;
+}
+
+/*
+ * vsock_vmci_listen --
+ *
+ * Signify that this socket is listening for connection requests.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_listen(struct socket *sock, int backlog)
+{
+ int err;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+
+ sk = sock->sk;
+
+ lock_sock(sk);
+
+ if (sock->type != SOCK_STREAM) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ if (sock->state != SS_UNCONNECTED) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ vsk = vsock_sk(sk);
+
+ if (!vsock_addr_bound(&vsk->local_addr)) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ sk->sk_max_ack_backlog = backlog;
+ sk->sk_state = SS_LISTEN;
+
+ err = 0;
+
+out:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_shutdown --
+ *
+ * Shuts down the provided socket in the provided method.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_shutdown(struct socket *sock, int mode)
+{
+ int err;
+ struct sock *sk;
+
+ /*
+ * User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses
+ * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode
+ * here like the other address families do. Note also that the
+ * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3),
+ * which is what we want.
+ */
+ mode++;
+
+ if ((mode & ~SHUTDOWN_MASK) || !mode)
+ return -EINVAL;
+
+ /*
+ * If this is a STREAM socket and it is not connected then bail out
+ * immediately. If it is a DGRAM socket then we must first kick the socket
+ * so that it wakes up from any sleeping calls, for example recv(), and then
+ * afterwards return the error.
+ */
+
+ sk = sock->sk;
+ if (sock->state == SS_UNCONNECTED) {
+ err = -ENOTCONN;
+ if (sk->sk_type == SOCK_STREAM)
+ return err;
+ } else {
+ sock->state = SS_DISCONNECTING;
+ err = 0;
+ }
+
+ /* Receive and send shutdowns are treated alike. */
+ mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN);
+ if (mode) {
+ lock_sock(sk);
+ sk->sk_shutdown |= mode;
+ sk->sk_state_change(sk);
+ release_sock(sk);
+
+ if (sk->sk_type == SOCK_STREAM) {
+ sock_reset_flag(sk, SOCK_DONE);
+ VSOCK_SEND_SHUTDOWN(sk, mode);
+ }
+ }
+
+ return err;
+}
+
+/*
+ * vsock_vmci_dgram_sendmsg --
+ *
+ * Sends a datagram.
+ *
+ * Results: Number of bytes sent on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_dgram_sendmsg(struct kiocb *kiocb,
+ struct socket *sock, struct msghdr *msg, size_t len)
+{
+ int err;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ struct sockaddr_vm *remote_addr;
+ struct vmci_datagram *dg;
+
+ if (msg->msg_flags & MSG_OOB)
+ return -EOPNOTSUPP;
+
+ if (len > VMCI_MAX_DG_PAYLOAD_SIZE)
+ return -EMSGSIZE;
+
+ /* For now, MSG_DONTWAIT is always assumed... */
+ err = 0;
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ lock_sock(sk);
+
+ if (!vsock_addr_bound(&vsk->local_addr)) {
+ struct sockaddr_vm local_addr;
+
+ vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+ err = __vsock_vmci_bind(sk, &local_addr);
+ if (err != 0)
+ goto out;
+
+ }
+
+ /*
+ * If the provided message contains an address, use that. Otherwise
+ * fall back on the socket's remote handle (if it has been connected).
+ */
+ if (msg->msg_name &&
+ vsock_addr_cast(msg->msg_name, msg->msg_namelen,
+ &remote_addr) == 0) {
+ /* Ensure this address is of the right type and is a valid
+ * destination. */
+
+ if (remote_addr->svm_cid == VMADDR_CID_ANY)
+ remote_addr->svm_cid = vmci_get_context_id();
+
+ if (!vsock_addr_bound(remote_addr)) {
+ err = -EINVAL;
+ goto out;
+ }
+ } else if (sock->state == SS_CONNECTED) {
+ remote_addr = &vsk->remote_addr;
+
+ if (remote_addr->svm_cid == VMADDR_CID_ANY)
+ remote_addr->svm_cid = vmci_get_context_id();
+
+ /* XXX Should connect() or this function ensure remote_addr is
+ * bound? */
+ if (!vsock_addr_bound(&vsk->remote_addr)) {
+ err = -EINVAL;
+ goto out;
+ }
+ } else {
+ err = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Make sure that we don't allow a userlevel app to send datagrams to
+ * the hypervisor that modify VMCI device state.
+ */
+ if (!vsock_addr_socket_context_dgram(remote_addr->svm_cid,
+ remote_addr->svm_port)) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (!vsock_vmci_allow_dgram(vsk, remote_addr->svm_cid)) {
+ err = -EPERM;
+ goto out;
+ }
+
+ /*
+ * Allocate a buffer for the user's message and our packet header.
+ */
+ dg = kmalloc(len + sizeof *dg, GFP_KERNEL);
+ if (!dg) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ memcpy_fromiovec(VMCI_DG_PAYLOAD(dg), msg->msg_iov, len);
+
+ dg->dst = VMCI_MAKE_HANDLE(remote_addr->svm_cid, remote_addr->svm_port);
+ dg->src =
+ VMCI_MAKE_HANDLE(vsk->local_addr.svm_cid, vsk->local_addr.svm_port);
+
+ dg->payload_size = len;
+
+ err = vmci_datagram_send(dg);
+ kfree(dg);
+ if (err < 0) {
+ err = vsock_vmci_error_to_vsock_error(err);
+ goto out;
+ }
+
+ err -= sizeof *dg;
+
+out:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_stream_setsockopt --
+ *
+ * Set a socket option on a stream socket
+ *
+ * Results: 0 on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_stream_setsockopt(struct socket *sock,
+ int level,
+ int optname,
+ char __user *optval,
+ vsock_setsockopt_len_type optlen)
+{
+ int err;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ u64 val;
+
+ if (level != AF_VSOCK)
+ return -ENOPROTOOPT;
+
+#define COPY_IN(_v) \
+ do { \
+ if (optlen < sizeof _v) { \
+ err = -EINVAL; \
+ goto exit; \
+ } \
+ if (copy_from_user(&_v, optval, sizeof _v) != 0) { \
+ err = -EFAULT; \
+ goto exit; \
+ } \
+ } while (0)
+
+ err = 0;
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ ASSERT(vsk->queue_pair_min_size <= vsk->queue_pair_size &&
+ vsk->queue_pair_size <= vsk->queue_pair_max_size);
+
+ lock_sock(sk);
+
+ switch (optname) {
+ case SO_VMCI_BUFFER_SIZE:
+ COPY_IN(val);
+ if (val < vsk->queue_pair_min_size)
+ vsk->queue_pair_min_size = val;
+
+ if (val > vsk->queue_pair_max_size)
+ vsk->queue_pair_max_size = val;
+
+ vsk->queue_pair_size = val;
+ break;
+
+ case SO_VMCI_BUFFER_MAX_SIZE:
+ COPY_IN(val);
+ if (val < vsk->queue_pair_size)
+ vsk->queue_pair_size = val;
+
+ vsk->queue_pair_max_size = val;
+ break;
+
+ case SO_VMCI_BUFFER_MIN_SIZE:
+ COPY_IN(val);
+ if (val > vsk->queue_pair_size)
+ vsk->queue_pair_size = val;
+
+ vsk->queue_pair_min_size = val;
+ break;
+
+ case SO_VMCI_CONNECT_TIMEOUT: {
+ struct timeval tv;
+ COPY_IN(tv);
+ if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC &&
+ tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) {
+ vsk->connect_timeout = tv.tv_sec * HZ +
+ DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ));
+ if (vsk->connect_timeout == 0)
+ vsk->connect_timeout =
+ VSOCK_DEFAULT_CONNECT_TIMEOUT;
+
+ } else {
+ err = -ERANGE;
+ }
+ break;
+ }
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+#undef COPY_IN
+
+ ASSERT(vsk->queue_pair_min_size <= vsk->queue_pair_size &&
+ vsk->queue_pair_size <= vsk->queue_pair_max_size);
+exit:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_stream_getsockopt --
+ *
+ * Get a socket option for a stream socket
+ *
+ * Results: 0 on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int vsock_vmci_stream_getsockopt(struct socket *sock,
+ int level, int optname,
+ char __user *optval,
+ int __user *optlen)
+{
+ int err;
+ int len;
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+
+ if (level != AF_VSOCK)
+ return -ENOPROTOOPT;
+
+ err = get_user(len, optlen);
+ if (err != 0)
+ return err;
+
+#define COPY_OUT(_v) \
+ do { \
+ if (len < sizeof _v) \
+ return -EINVAL; \
+ \
+ len = sizeof _v; \
+ if (copy_to_user(optval, &_v, len) != 0) \
+ return -EFAULT; \
+ \
+ } while (0)
+
+ err = 0;
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+
+ switch (optname) {
+ case SO_VMCI_BUFFER_SIZE:
+ COPY_OUT(vsk->queue_pair_size);
+ break;
+
+ case SO_VMCI_BUFFER_MAX_SIZE:
+ COPY_OUT(vsk->queue_pair_max_size);
+ break;
+
+ case SO_VMCI_BUFFER_MIN_SIZE:
+ COPY_OUT(vsk->queue_pair_min_size);
+ break;
+
+ case SO_VMCI_CONNECT_TIMEOUT: {
+ struct timeval tv;
+ tv.tv_sec = vsk->connect_timeout / HZ;
+ tv.tv_usec =
+ (vsk->connect_timeout -
+ tv.tv_sec * HZ) * (1000000 / HZ);
+ COPY_OUT(tv);
+ break;
+ }
+ default:
+ return -ENOPROTOOPT;
+ }
+
+ err = put_user(len, optlen);
+ if (err != 0)
+ return -EFAULT;
+
+#undef COPY_OUT
+
+ return 0;
+}
+
+/*
+ * vsock_vmci_stream_sendmsg --
+ *
+ * Sends a message on the socket.
+ *
+ * Results: Number of bytes sent on success, negative error code on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_stream_sendmsg(struct kiocb *kiocb,
+ struct socket *sock, struct msghdr *msg, size_t len)
+{
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ ssize_t total_written;
+ long timeout;
+ int err;
+ vsock_vmci_send_notify_data send_data;
+
+ DEFINE_WAIT(wait);
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+ total_written = 0;
+ err = 0;
+
+ if (msg->msg_flags & MSG_OOB)
+ return -EOPNOTSUPP;
+
+ lock_sock(sk);
+
+ /* Callers should not provide a destination with stream sockets. */
+ if (msg->msg_namelen) {
+ err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP;
+ goto out;
+ }
+
+ /* Send data only if both sides are not shutdown in the direction. */
+ if (sk->sk_shutdown & SEND_SHUTDOWN ||
+ vsk->peer_shutdown & RCV_SHUTDOWN) {
+ err = -EPIPE;
+ goto out;
+ }
+
+ if (sk->sk_state != SS_CONNECTED ||
+ !vsock_addr_bound(&vsk->local_addr)) {
+ err = -ENOTCONN;
+ goto out;
+ }
+
+ if (!vsock_addr_bound(&vsk->remote_addr)) {
+ err = -EDESTADDRREQ;
+ goto out;
+ }
+
+ /*
+ * Wait for room in the produce queue to enqueue our user's data.
+ */
+ timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+
+ NOTIFYCALLRET(vsk, err, send_init, sk, &send_data);
+ if (err < 0)
+ goto out;
+
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+
+ while (total_written < len) {
+ ssize_t written;
+
+ while (vsock_vmci_stream_has_space(vsk) == 0 &&
+ sk->sk_err == 0 &&
+ !(sk->sk_shutdown & SEND_SHUTDOWN) &&
+ !(vsk->peer_shutdown & RCV_SHUTDOWN)) {
+
+ /* Don't wait for non-blocking sockets. */
+ if (timeout == 0) {
+ err = -EAGAIN;
+ goto out_wait;
+ }
+
+ NOTIFYCALLRET(vsk, err, send_pre_block, sk, &send_data);
+
+ if (err < 0)
+ goto out_wait;
+
+ release_sock(sk);
+ timeout = schedule_timeout(timeout);
+ lock_sock(sk);
+ if (signal_pending(current)) {
+ err = sock_intr_errno(timeout);
+ goto out_wait;
+ } else if (timeout == 0) {
+ err = -EAGAIN;
+ goto out_wait;
+ }
+
+ prepare_to_wait(sk_sleep(sk), &wait,
+ TASK_INTERRUPTIBLE);
+ }
+
+ /*
+ * These checks occur both as part of and after the loop
+ * conditional since we need to check before and after
+ * sleeping.
+ */
+ if (sk->sk_err) {
+ err = -sk->sk_err;
+ goto out_wait;
+ } else if ((sk->sk_shutdown & SEND_SHUTDOWN) ||
+ (vsk->peer_shutdown & RCV_SHUTDOWN)) {
+ err = -EPIPE;
+ goto out_wait;
+ }
+
+ VSOCK_STATS_STREAM_PRODUCE_HIST(vsk);
+
+ NOTIFYCALLRET(vsk, err, send_pre_enqueue, sk, &send_data);
+ if (err < 0)
+ goto out_wait;
+
+ /*
+ * Note that enqueue will only write as many bytes as are free
+ * in the produce queue, so we don't need to ensure len is
+ * smaller than the queue size. It is the caller's
+ * responsibility to check how many bytes we were able to send.
+ */
+
+ written = vmci_qpair_enquev(vsk->qpair, msg->msg_iov,
+ len - total_written, 0);
+ if (written < 0) {
+ err = -ENOMEM;
+ goto out_wait;
+ }
+
+ total_written += written;
+
+ NOTIFYCALLRET(vsk, err, send_post_enqueue, sk, written,
+ &send_data);
+ if (err < 0)
+ goto out_wait;
+
+ }
+
+ ASSERT(total_written <= INT_MAX);
+
+out_wait:
+ if (total_written > 0) {
+ VSOCK_STATS_STREAM_PRODUCE(total_written);
+ err = total_written;
+ }
+ finish_wait(sk_sleep(sk), &wait);
+out:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * vsock_vmci_dgram_recvmsg --
+ *
+ * Receives a datagram and places it in the caller's msg.
+ *
+ * Results: The size of the payload on success, negative value on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_dgram_recvmsg(struct kiocb *kiocb,
+ struct socket *sock,
+ struct msghdr *msg, size_t len, int flags)
+{
+ int err;
+ int noblock;
+ struct sock *sk;
+ struct vmci_datagram *dg;
+ size_t payload_len;
+ struct sk_buff *skb;
+
+ sk = sock->sk;
+ noblock = flags & MSG_DONTWAIT;
+
+ if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
+ return -EOPNOTSUPP;
+
+ /* Retrieve the head sk_buff from the socket's receive queue. */
+ err = 0;
+ skb = skb_recv_datagram(sk, flags, noblock, &err);
+ if (err)
+ return err;
+
+ if (!skb)
+ return -EAGAIN;
+
+ dg = (struct vmci_datagram *) skb->data;
+ if (!dg)
+ /* err is 0, meaning we read zero bytes. */
+ goto out;
+
+ payload_len = dg->payload_size;
+ /* Ensure the sk_buff matches the payload size claimed in the packet. */
+ if (payload_len != skb->len - sizeof *dg) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (payload_len > len) {
+ payload_len = len;
+ msg->msg_flags |= MSG_TRUNC;
+ }
+
+ /* Place the datagram payload in the user's iovec. */
+ err =
+ skb_copy_datagram_iovec(skb, sizeof *dg, msg->msg_iov, payload_len);
+ if (err)
+ goto out;
+
+ msg->msg_namelen = 0;
+ if (msg->msg_name) {
+ struct sockaddr_vm *vmci_addr;
+
+ /* Provide the address of the sender. */
+ vmci_addr = (struct sockaddr_vm *)msg->msg_name;
+ vsock_addr_init(vmci_addr,
+ VMCI_HANDLE_TO_CONTEXT_ID(dg->src),
+ VMCI_HANDLE_TO_RESOURCE_ID(dg->src));
+ msg->msg_namelen = sizeof *vmci_addr;
+ }
+ err = payload_len;
+
+out:
+ skb_free_datagram(sk, skb);
+ return err;
+}
+
+/*
+ * vsock_vmci_stream_recvmsg --
+ *
+ * Receives a datagram and places it in the caller's msg.
+ *
+ * Results: The size of the payload on success, negative value on failure.
+ *
+ * Side effects: None.
+ */
+
+static int
+vsock_vmci_stream_recvmsg(struct kiocb *kiocb,
+ struct socket *sock,
+ struct msghdr *msg, size_t len, int flags)
+{
+ struct sock *sk;
+ vsock_vmci_sock *vsk;
+ int err;
+ size_t target;
+ ssize_t copied;
+ long timeout;
+
+ vsock_vmci_recv_notify_data recv_data;
+
+ DEFINE_WAIT(wait);
+
+ sk = sock->sk;
+ vsk = vsock_sk(sk);
+ err = 0;
+
+ lock_sock(sk);
+
+ if (sk->sk_state != SS_CONNECTED) {
+ /*
+ * Recvmsg is supposed to return 0 if a peer performs an
+ * orderly shutdown. Differentiate between that case and when a
+ * peer has not connected or a local shutdown occured with the
+ * SOCK_DONE flag.
+ */
+ if (sock_flag(sk, SOCK_DONE))
+ err = 0;
+ else
+ err = -ENOTCONN;
+
+ goto out;
+ }
+
+ if (flags & MSG_OOB) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ /*
+ * We don't check peer_shutdown flag here since peer may actually shut
+ * down, but there can be data in the VMCI queue that local socket can
+ * receive.
+ */
+ if (sk->sk_shutdown & RCV_SHUTDOWN) {
+ err = 0;
+ goto out;
+ }
+
+ /*
+ * It is valid on Linux to pass in a zero-length receive buffer. This
+ * is not an error. We may as well bail out now. Note that if we
+ * don't, we will fail "ASSERT(copied >= target)" after we dequeue,
+ * because the minimum target is always 1 byte.
+ */
+ if (!len) {
+ err = 0;
+ goto out;
+ }
+
+ /*
+ * We must not copy less than target bytes into the user's buffer
+ * before returning successfully, so we wait for the consume queue to
+ * have that much data to consume before dequeueing. Note that this
+ * makes it impossible to handle cases where target is greater than the
+ * queue size.
+ */
+ target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
+ if (target >= vsk->consume_size) {
+ err = -ENOMEM;
+ goto out;
+ }
+ timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+ copied = 0;
+
+ NOTIFYCALLRET(vsk, err, recv_init, sk, target, &recv_data);
+ if (err < 0)
+ goto out;
+
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+
+ while (1) {
+ s64 ready = vsock_vmci_stream_has_data(vsk);
+
+ if (ready < 0) {
+ /*
+ * Invalid queue pair content. XXX This should be
+ * changed to a connection reset in a later change.
+ */
+
+ err = -ENOMEM;
+ goto out_wait;
+ } else if (ready > 0) {
+ ssize_t read;
+
+ VSOCK_STATS_STREAM_CONSUME_HIST(vsk);
+
+ NOTIFYCALLRET(vsk, err, recv_pre_dequeue, sk, target,
+ &recv_data);
+ if (err < 0)
+ break;
+
+ if (flags & MSG_PEEK)
+ read =
+ vmci_qpair_peekv(vsk->qpair, msg->msg_iov,
+ len - copied, 0);
+ else
+ read =
+ vmci_qpair_dequev(vsk->qpair, msg->msg_iov,
+ len - copied, 0);
+
+ if (read < 0) {
+ err = -ENOMEM;
+ break;
+ }
+
+ ASSERT(read <= INT_MAX);
+ copied += read;
+
+ NOTIFYCALLRET(vsk, err, recv_post_dequeue, sk, target,
+ read, !(flags & MSG_PEEK), &recv_data);
+ if (err < 0)
+ goto out_wait;
+
+ if (read >= target || flags & MSG_PEEK)
+ break;
+
+ target -= read;
+ } else {
+ if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN)
+ || (vsk->peer_shutdown & SEND_SHUTDOWN)) {
+ break;
+ }
+ /* Don't wait for non-blocking sockets. */
+ if (timeout == 0) {
+ err = -EAGAIN;
+ break;
+ }
+
+ NOTIFYCALLRET(vsk, err, recv_pre_block, sk, target,
+ &recv_data);
+ if (err < 0)
+ break;
+
+ release_sock(sk);
+ timeout = schedule_timeout(timeout);
+ lock_sock(sk);
+
+ if (signal_pending(current)) {
+ err = sock_intr_errno(timeout);
+ break;
+ } else if (timeout == 0) {
+ err = -EAGAIN;
+ break;
+ }
+
+ prepare_to_wait(sk_sleep(sk), &wait,
+ TASK_INTERRUPTIBLE);
+ }
+ }
+
+ if (sk->sk_err)
+ err = -sk->sk_err;
+ else if (sk->sk_shutdown & RCV_SHUTDOWN)
+ err = 0;
+
+ if (copied > 0) {
+ /*
+ * We only do these additional bookkeeping/notification steps
+ * if we actually copied something out of the queue pair
+ * instead of just peeking ahead.
+ */
+
+ if (!(flags & MSG_PEEK)) {
+ VSOCK_STATS_STREAM_CONSUME(copied);
+
+ /*
+ * If the other side has shutdown for sending and there
+ * is nothing more to read, then modify the socket
+ * state.
+ */
+ if (vsk->peer_shutdown & SEND_SHUTDOWN) {
+ if (vsock_vmci_stream_has_data(vsk) <= 0) {
+ sk->sk_state = SS_UNCONNECTED;
+ sock_set_flag(sk, SOCK_DONE);
+ sk->sk_state_change(sk);
+ }
+ }
+ }
+ err = copied;
+ }
+
+out_wait:
+ finish_wait(sk_sleep(sk), &wait);
+out:
+ release_sock(sk);
+ return err;
+}
+
+/*
+ * Protocol operation.
+ */
+
+/*
+ * vsock_vmci_create --
+ *
+ * Creates a VSocket socket.
+ *
+ * Results: Zero on success, negative error code on failure.
+ *
+ * Side effects: Socket count is incremented.
+ */
+
+static int
+vsock_vmci_create(struct net *net, struct socket *sock, int protocol, int kern)
+{
+ if (!sock)
+ return -EINVAL;
+
+ if (protocol)
+ return -EPROTONOSUPPORT;
+
+ switch (sock->type) {
+ case SOCK_DGRAM:
+ sock->ops = &vsock_vmci_dgram_ops;
+ break;
+ case SOCK_STREAM:
+ sock->ops = &vsock_vmci_stream_ops;
+ break;
+ default:
+ return -ESOCKTNOSUPPORT;
+ }
+
+ sock->state = SS_UNCONNECTED;
+
+ return __vsock_vmci_create(net, sock, NULL, GFP_KERNEL,
+ 0) ? 0 : -ENOMEM;
+}
+
+/*
+ * Device operations.
+ */
+
+static long vsock_vmci_dev_do_ioctl(struct file *filp,
+ unsigned int cmd, void __user *ptr)
+{
+ static const u16 parts[4] = { VSOCK_DRIVER_VERSION_COMMAS };
+ u32 __user *p = ptr;
+ int retval = 0;
+ u32 version;
+
+ switch (cmd) {
+ case IOCTL_VMCI_SOCKETS_VERSION:
+ version = VMCI_SOCKETS_MAKE_VERSION(parts);
+ if (put_user(version, p) != 0)
+ retval = -EFAULT;
+ break;
+
+ case IOCTL_VMCI_SOCKETS_GET_AF_VALUE:
+ if (put_user(AF_VSOCK, p) != 0)
+ retval = -EFAULT;
+
+ break;
+
+ case IOCTL_VMCI_SOCKETS_GET_LOCAL_CID:
+ if (put_user(vmci_get_context_id(), p) != 0)
+ retval = -EFAULT;
+
+ break;
+
+ default:
+ pr_err("Unknown ioctl %d\n", cmd);
+ retval = -EINVAL;
+ }
+
+ return retval;
+}
+
+static long vsock_vmci_dev_ioctl(struct file *filp,
+ unsigned int cmd, unsigned long arg)
+{
+ return vsock_vmci_dev_do_ioctl(filp, cmd, (void __user *)arg);
+}
+
+#ifdef CONFIG_COMPAT
+static long vsock_vmci_dev_compat_ioctl(struct file *filp,
+ unsigned int cmd, unsigned long arg)
+{
+ return vsock_vmci_dev_do_ioctl(filp, cmd, compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations vsock_vmci_device_ops = {
+ .owner = THIS_MODULE,
+ .unlocked_ioctl = vsock_vmci_dev_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = vsock_vmci_dev_compat_ioctl,
+#endif
+ .open = nonseekable_open,
+};
+
+static struct miscdevice vsock_vmci_device = {
+ .name = "vsock",
+ .minor = MISC_DYNAMIC_MINOR,
+ .fops = &vsock_vmci_device_ops,
+};
+
+
+/*
+ * Module operations.
+ */
+
+/*
+ * vsock_vmci_init --
+ *
+ * Initialization routine for the VSockets module.
+ *
+ * Results: Zero on success, error code on failure.
+ *
+ * Side effects: The VSocket protocol family and socket operations are
+ * registered.
+ */
+
+static int __init vsock_vmci_init(void)
+{
+ int err;
+
+ request_module("vmci");
+
+ err = misc_register(&vsock_vmci_device);
+ if (err) {
+ pr_err("Failed to register misc device\n");
+ return -ENOENT;
+ }
+
+ err = vsock_vmci_register_with_vmci();
+ if (err) {
+ pr_err("Cannot register with VMCI device.\n");
+ goto err_misc_deregister;
+ }
+
+ err = proto_register(&vsock_vmci_proto, 1); /* we want our slab */
+ if (err) {
+ pr_err("Cannot register vsock protocol.\n");
+ goto err_unregister_with_vmci;
+ }
+
+ err = sock_register(&vsock_vmci_family_ops);
+ if (err) {
+ pr_err("could not register af_vsock (%d) address family: %d\n",
+ AF_VSOCK, err);
+ goto err_unregister_proto;
+ }
+
+ vsock_vmci_init_tables();
+ return 0;
+
+err_unregister_proto:
+ proto_unregister(&vsock_vmci_proto);
+err_unregister_with_vmci:
+ vsock_vmci_unregister_with_vmci();
+err_misc_deregister:
+ misc_deregister(&vsock_vmci_device);
+ return err;
+}
+
+/*
+ * VSocketVmciExit --
+ *
+ * VSockets module exit routine.
+ *
+ * Results: None.
+ *
+ * Side effects: Unregisters VSocket protocol family and socket operations.
+ */
+
+static void __exit vsock_vmci_exit(void)
+{
+ misc_deregister(&vsock_vmci_device);
+ sock_unregister(AF_VSOCK);
+ proto_unregister(&vsock_vmci_proto);
+ /* Need reset ? */
+ VSOCK_STATS_RESET();
+ vsock_vmci_unregister_with_vmci();
+}
+
+module_init(vsock_vmci_init);
+module_exit(vsock_vmci_exit);
+
+MODULE_AUTHOR("VMware, Inc.");
+MODULE_DESCRIPTION("VMware Virtual Socket Family");
+MODULE_VERSION(VSOCK_DRIVER_VERSION_STRING);
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("vmware_vsock");
diff --git a/net/vmw_vsock/af_vsock.h b/net/vmw_vsock/af_vsock.h
new file mode 100644
index 0000000..c434afc
--- /dev/null
+++ b/net/vmw_vsock/af_vsock.h
@@ -0,0 +1,179 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2012 VMware, Inc. 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 version 2 and no 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.
+ */
+
+/*
+ * af_vsock.h --
+ *
+ * Definitions for Linux VSockets module.
+ */
+
+#ifndef __AF_VSOCK_H__
+#define __AF_VSOCK_H__
+
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+#include <linux/vmw_vmci_defs.h>
+#include <linux/vmw_vmci_api.h>
+
+#include "vsock_common.h"
+#include "vsock_packet.h"
+#include "notify.h"
+
+#define vsock_sk(__sk) ((vsock_vmci_sock *)__sk)
+#define sk_vsock(__vsk) (&(__vsk)->sk)
+
+typedef struct vsock_vmci_sock {
+ /* sk must be the first member. */
+ struct sock sk;
+ struct sockaddr_vm local_addr;
+ struct sockaddr_vm remote_addr;
+ /* Links for the global tables of bound and connected sockets. */
+ struct list_head bound_table;
+ struct list_head connected_table;
+ /*
+ * Accessed without the socket lock held. This means it can never be
+ * modified outsided of socket create or destruct.
+ */
+ bool trusted;
+ bool cached_peer_allow_dgram; /* Dgram communication allowed to
+ * cached peer? */
+ vmci_id cached_peer; /* Context ID of last dgram destination check. */
+ const struct cred *owner;
+ struct vmci_handle dg_handle; /* For SOCK_DGRAM only. */
+ /* Rest are SOCK_STREAM only. */
+ struct vmci_handle qp_handle;
+ struct vmci_qp *qpair;
+ u64 produce_size;
+ u64 consume_size;
+ u64 queue_pair_size;
+ u64 queue_pair_min_size;
+ u64 queue_pair_max_size;
+ long connect_timeout;
+ vsock_vmci_notify notify;
+ vsock_vmci_notify_ops *notify_ops;
+ vmci_id attach_sub_id;
+ vmci_id detach_sub_id;
+ /* Listening socket that this came from. */
+ struct sock *listener;
+ /*
+ * Used for pending list and accept queue during connection handshake.
+ * The listening socket is the head for both lists. Sockets created
+ * for connection requests are placed in the pending list until they
+ * are connected, at which point they are put in the accept queue list
+ * so they can be accepted in accept(). If accept() cannot accept the
+ * connection, it is marked as rejected so the cleanup function knows
+ * to clean up the socket.
+ */
+ struct list_head pending_links;
+ struct list_head accept_queue;
+ bool rejected;
+ struct delayed_work dwork;
+ u32 peer_shutdown;
+ bool sent_request;
+ bool ignore_connecting_rst;
+} vsock_vmci_sock;
+
+int vsock_vmci_send_control_pkt_bh(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ vsock_packet_type type,
+ u64 size,
+ u64 mode,
+ vsock_waiting_info *wait,
+ struct vmci_handle handle);
+int vsock_vmci_reply_control_pkt_fast(vsock_packet *pkt,
+ vsock_packet_type type, u64 size,
+ u64 mode, vsock_waiting_info *wait,
+ struct vmci_handle handle);
+int vsock_vmci_send_control_pkt(struct sock *sk, vsock_packet_type type,
+ u64 size, u64 mode,
+ vsock_waiting_info *wait,
+ vsock_proto_version version,
+ struct vmci_handle handle);
+
+s64 vsock_vmci_stream_has_data(vsock_vmci_sock *vsk);
+s64 vsock_vmci_stream_has_space(vsock_vmci_sock *vsk);
+
+#define VSOCK_SEND_RESET_BH(_dst, _src, _pkt) \
+ ((_pkt)->type == VSOCK_PACKET_TYPE_RST) ? \
+ 0 : \
+ vsock_vmci_send_control_pkt_bh( \
+ _dst, _src, \
+ VSOCK_PACKET_TYPE_RST, 0, \
+ 0, NULL, VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_INVALID_BH(_dst, _src) \
+ vsock_vmci_send_control_pkt_bh(_dst, _src, \
+ VSOCK_PACKET_TYPE_INVALID, 0, \
+ 0, NULL, VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_WROTE_BH(_dst, _src) \
+ vsock_vmci_send_control_pkt_bh(_dst, _src, VSOCK_PACKET_TYPE_WROTE, 0, \
+ 0, NULL, VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_READ_BH(_dst, _src) \
+ vsock_vmci_send_control_pkt_bh((_dst), (_src), \
+ VSOCK_PACKET_TYPE_READ, 0, \
+ 0, NULL, VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_RESET(_sk, _pkt) \
+ ((_pkt)->type == VSOCK_PACKET_TYPE_RST) ? \
+ 0 : \
+ vsock_vmci_send_control_pkt( \
+ _sk, VSOCK_PACKET_TYPE_RST, \
+ 0, 0, NULL, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_NEGOTIATE(_sk, _size) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_NEGOTIATE, \
+ _size, 0, NULL, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_NEGOTIATE2(_sk, _size, signal_proto) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_NEGOTIATE2, \
+ _size, 0, NULL, signal_proto, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_QP_OFFER(_sk, _handle) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_OFFER, \
+ 0, 0, NULL, VSOCK_PROTO_INVALID, _handle)
+#define VSOCK_SEND_CONN_REQUEST(_sk, _size) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_REQUEST, \
+ _size, 0, NULL, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_CONN_REQUEST2(_sk, _size, signal_proto) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_REQUEST2, \
+ _size, 0, NULL, signal_proto, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_ATTACH(_sk, _handle) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_ATTACH, \
+ 0, 0, NULL, VSOCK_PROTO_INVALID, _handle)
+#define VSOCK_SEND_WROTE(_sk) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_WROTE, \
+ 0, 0, NULL, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_READ(_sk) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_READ, \
+ 0, 0, NULL, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_SHUTDOWN(_sk, _mode) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_SHUTDOWN, \
+ 0, _mode, NULL, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_WAITING_WRITE(_sk, _wait_info) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_WAITING_WRITE, \
+ 0, 0, _wait_info, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_SEND_WAITING_READ(_sk, _wait_info) \
+ vsock_vmci_send_control_pkt(_sk, VSOCK_PACKET_TYPE_WAITING_READ, \
+ 0, 0, _wait_info, VSOCK_PROTO_INVALID, \
+ VMCI_INVALID_HANDLE)
+#define VSOCK_REPLY_RESET(_pkt) \
+ vsock_vmci_reply_control_pkt_fast(_pkt, VSOCK_PACKET_TYPE_RST, \
+ 0, 0, NULL, VMCI_INVALID_HANDLE)
+
+#endif /* __AF_VSOCK_H__ */
^ permalink raw reply related
* [PATCH 0/6] VSOCK for Linux upstreaming
From: George Zhang @ 2012-11-05 18:00 UTC (permalink / raw)
To: netdev, linux-kernel, georgezhang, virtualization
Cc: pv-drivers, vm-crosstalk, davem, gregkh
* * *
This series of VSOCK linux upstreaming patches include latest udpate from
VMware.
Summary of changes:
- Add include/linux/socket.h for AF_VSOCK.
- Cleanup some comments.
- Cleanup makefiles.
* * *
In an effort to improve the out-of-the-box experience with Linux
kernels for VMware users, VMware is working on readying the Virtual
Machine Communication Interface (vmw_vmci) and VMCI Sockets (VSOCK)
(vmw_vsock) kernel modules for inclusion in the Linux kernel. The
purpose of this post is to acquire feedback on the vmw_vsock kernel
module. The vmw_vmci kernel module has been presented in an early post.
* * *
VMCI Sockets allows virtual machines to communicate with host kernel
modules and the VMware hypervisors. VMCI Sockets kernel module has
dependency on VMCI kernel module. User level applications both in
a virtual machine and on the host can use vmw_vmci through VMCI
Sockets API which facilitates fast and efficient communication
between guest virtual machines and their host. A socket
address family designed to be compatible with UDP and TCP at the
interface level. Today, VMCI and VMCI Sockets are used by the VMware
shared folders (HGFS) and various VMware Tools components inside the
guest for zero-config, network-less access to VMware host services. In
addition to this, VMware's users are using VMCI Sockets for various
applications, where network access of the virtual machine is
restricted or non-existent. Examples of this are VMs communicating
with device proxies for proprietary hardware running as host
applications and automated testing of applications running within
virtual machines.
The VMware VMCI Sockets are similar to other socket types, like
Berkeley UNIX socket interface. The VMCI sockets module supports
both connection-oriented stream sockets like TCP, and connectionless
datagram sockets like UDP. The VSOCK protocol family is defined as
"AF_VSOCK" and the socket operations split for SOCK_DGRAM and
SOCK_STREAM.
For additional information about the use of VMCI and in particular
VMCI Sockets, please refer to the VMCI Socket Programming Guide
available at https://www.vmware.com/support/developer/vmci-sdk/.
---
George Zhang (6):
VSOCK: vsock protocol implementation.
VSOCK: vsock address implementaion.
VSOCK: notification implementation.
VSOCK: statistics implementation.
VSOCK: utility functions.
VSOCK: header and config files.
include/linux/socket.h | 4
net/Kconfig | 1
net/Makefile | 1
net/vmw_vsock/Kconfig | 14
net/vmw_vsock/Makefile | 4
net/vmw_vsock/af_vsock.c | 4165 +++++++++++++++++++++++++++++++++++
net/vmw_vsock/af_vsock.h | 179 ++
net/vmw_vsock/notify.c | 984 ++++++++
net/vmw_vsock/notify.h | 130 +
net/vmw_vsock/notify_qstate.c | 627 +++++
net/vmw_vsock/stats.c | 37
net/vmw_vsock/stats.h | 219 ++
net/vmw_vsock/util.c | 626 +++++
net/vmw_vsock/util.h | 312 +++
net/vmw_vsock/vmci_sockets.h | 517 ++++
net/vmw_vsock/vmci_sockets_packet.h | 106 +
net/vmw_vsock/vsock_addr.c | 264 ++
net/vmw_vsock/vsock_addr.h | 40
net/vmw_vsock/vsock_common.h | 130 +
net/vmw_vsock/vsock_packet.h | 131 +
net/vmw_vsock/vsock_version.h | 29
21 files changed, 8519 insertions(+), 1 deletions(-)
create mode 100644 net/vmw_vsock/Kconfig
create mode 100644 net/vmw_vsock/Makefile
create mode 100644 net/vmw_vsock/af_vsock.c
create mode 100644 net/vmw_vsock/af_vsock.h
create mode 100644 net/vmw_vsock/notify.c
create mode 100644 net/vmw_vsock/notify.h
create mode 100644 net/vmw_vsock/notify_qstate.c
create mode 100644 net/vmw_vsock/stats.c
create mode 100644 net/vmw_vsock/stats.h
create mode 100644 net/vmw_vsock/util.c
create mode 100644 net/vmw_vsock/util.h
create mode 100644 net/vmw_vsock/vmci_sockets.h
create mode 100644 net/vmw_vsock/vmci_sockets_packet.h
create mode 100644 net/vmw_vsock/vsock_addr.c
create mode 100644 net/vmw_vsock/vsock_addr.h
create mode 100644 net/vmw_vsock/vsock_common.h
create mode 100644 net/vmw_vsock/vsock_packet.h
create mode 100644 net/vmw_vsock/vsock_version.h
--
Signature
^ permalink raw reply
* how to disable automatic route addition for an ipv6 address
From: devendra.aaru @ 2012-11-05 17:52 UTC (permalink / raw)
To: netdev
while adding the ipv6 address to interface ,
ifconfig eth0 add 2001:8800:10fb:4444::ae/64
i am seeing the route addition automatically
route -n -A inet6 shows that one of the route from the above added address.
how to disable the automatic route addition?
or is it something that ipv6 protocol itself does?
thanks,
^ permalink raw reply
* Re: [PATCH net-next] ipv6: export IP6_RT_PRIO_* to userland
From: David Miller @ 2012-11-05 17:43 UTC (permalink / raw)
To: nicolas.dichtel; +Cc: netdev
In-Reply-To: <5097F5DF.7040507@6wind.com>
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 05 Nov 2012 18:22:39 +0100
> Le 05/11/2012 18:00, David Miller a écrit :
>> From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
>> Date: Mon, 5 Nov 2012 16:28:18 +0100
>>
>>> The kernel uses some default metric when routes are managed. For
>>> example, a
>>> static route added with a metric set to 0 is inserted in the kernel
>>> with
>>> metric 1024 (IP6_RT_PRIO_USER).
>>> It is useful for routing daemons to know these values, to be able to
>>> set routes
>>> without interfering with what the kernel does.
>>>
>>> Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
>>
>> But these belong in the libc headers anyways.
>>
>> If we haven't provided them for so long, there's no real value of
>> adding them now.
>>
> But how can a daemon know which default values are used? If it wants
> to add a route with metric = default + x, it should first add it with
> metric = 0, check the result and then change the metric.
What do we do on the ipv4 side and how do daemons cope in that situation?
^ permalink raw reply
* RE: [PATCH] drivers: ethernet: qlogic: netxen_nic_ethtool.c: Fixed a coding style issue
From: Rajesh Borundia @ 2012-11-05 17:24 UTC (permalink / raw)
To: Kumar Amit Mehta, Sony Chacko
Cc: netdev, linux-kernel, kernel-janitors@vger.kernel.org
In-Reply-To: <1352094368-5037-1-git-send-email-gmate.amit@gmail.com>
>-----Original Message-----
>From: Kumar Amit Mehta [mailto:gmate.amit@gmail.com]
>Sent: Monday, November 05, 2012 11:16 AM
>To: Sony Chacko
>Cc: Rajesh Borundia; netdev; linux-kernel; kernel-
>janitors@vger.kernel.org
>Subject: [PATCH] drivers: ethernet: qlogic: netxen_nic_ethtool.c: Fixed
>a coding style issue
>
>Fixed some coding style issues.
>
>Signed-off-by: Kumar Amit Mehta <gmate.amit@gmail.com>
>---
> .../ethernet/qlogic/netxen/netxen_nic_ethtool.c | 86 ++++++++++---
>-------
> 1 file changed, 43 insertions(+), 43 deletions(-)
Amit,
Thanks for taking care of this.
Acked-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
^ permalink raw reply
* Re: [PATCH net-next] ipv6: export IP6_RT_PRIO_* to userland
From: Nicolas Dichtel @ 2012-11-05 17:22 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20121105.120017.1189906314924845791.davem@davemloft.net>
Le 05/11/2012 18:00, David Miller a écrit :
> From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
> Date: Mon, 5 Nov 2012 16:28:18 +0100
>
>> The kernel uses some default metric when routes are managed. For example, a
>> static route added with a metric set to 0 is inserted in the kernel with
>> metric 1024 (IP6_RT_PRIO_USER).
>> It is useful for routing daemons to know these values, to be able to set routes
>> without interfering with what the kernel does.
>>
>> Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
>
> But these belong in the libc headers anyways.
>
> If we haven't provided them for so long, there's no real value of
> adding them now.
>
But how can a daemon know which default values are used? If it wants to add a
route with metric = default + x, it should first add it with metric = 0, check
the result and then change the metric.
^ permalink raw reply
* Re: [PATCH net-next] ipv6: export IP6_RT_PRIO_* to userland
From: David Miller @ 2012-11-05 17:00 UTC (permalink / raw)
To: nicolas.dichtel; +Cc: netdev
In-Reply-To: <1352129298-1104-1-git-send-email-nicolas.dichtel@6wind.com>
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 5 Nov 2012 16:28:18 +0100
> The kernel uses some default metric when routes are managed. For example, a
> static route added with a metric set to 0 is inserted in the kernel with
> metric 1024 (IP6_RT_PRIO_USER).
> It is useful for routing daemons to know these values, to be able to set routes
> without interfering with what the kernel does.
>
> Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
But these belong in the libc headers anyways.
If we haven't provided them for so long, there's no real value of
adding them now.
^ permalink raw reply
* Re: [PATCH net-next V3] htb: improved accuracy at high rates
From: Eric Dumazet @ 2012-11-05 16:58 UTC (permalink / raw)
To: Vimalkumar; +Cc: davem, Jamal Hadi Salim, netdev
In-Reply-To: <1351699451-79317-1-git-send-email-j.vimal@gmail.com>
On Wed, 2012-10-31 at 09:04 -0700, Vimalkumar wrote:
> Current HTB (and TBF) uses rate table computed by the "tc"
> userspace program, which has the following issue:
>
> The rate table has 256 entries to map packet lengths
> to token (time units). With TSO sized packets, the
> 256 entry granularity leads to loss/gain of rate,
> making the token bucket inaccurate.
>
> Thus, instead of relying on rate table, this patch
> explicitly computes the time and accounts for packet
> transmission times with nanosecond granularity.
>
> This greatly improves accuracy of HTB with a wide
> range of packet sizes.
>
> Example:
>
> tc qdisc add dev $dev root handle 1: \
> htb default 1
>
> tc class add dev $dev classid 1:1 parent 1: \
> rate 5Gbit mtu 64k
>
> Here is an example of inaccuracy:
>
> $ iperf -c host -t 10 -i 1
>
> With old htb:
> eth4: 34.76 Mb/s In 5827.98 Mb/s Out - 65836.0 p/s In 481273.0 p/s Out
> [SUM] 9.0-10.0 sec 669 MBytes 5.61 Gbits/sec
> [SUM] 0.0-10.0 sec 6.50 GBytes 5.58 Gbits/sec
>
> With new htb:
> eth4: 28.36 Mb/s In 5208.06 Mb/s Out - 53704.0 p/s In 430076.0 p/s Out
> [SUM] 9.0-10.0 sec 594 MBytes 4.98 Gbits/sec
> [SUM] 0.0-10.0 sec 5.80 GBytes 4.98 Gbits/sec
>
> The bits per second on the wire is still 5200Mb/s with new HTB
> because qdisc accounts for packet length using skb->len, which
> is smaller than total bytes on the wire if GSO is used. But
> that is for another patch regardless of how time is accounted.
>
> Many thanks to Eric Dumazet for review and feedback.
>
> Signed-off-by: Vimalkumar <j.vimal@gmail.com>
> ---
> net/sched/sch_htb.c | 128 ++++++++++++++++++++++++++++++++++++---------------
> 1 files changed, 90 insertions(+), 38 deletions(-)
>
> @@ -684,7 +729,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level,
> return cl->pq_key;
>
> htb_safe_rb_erase(p, q->wait_pq + level);
> - diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
> + diff = min_t(s64, q->now - cl->t_c, cl->mbuffer);
> htb_change_class_mode(q, cl, &diff);
> if (cl->cmode != HTB_CAN_SEND)
> htb_add_to_wait_tree(q, cl, diff);
> @@ -834,7 +879,6 @@ next:
> } while (cl != start);
>
> if (likely(skb != NULL)) {
> - bstats_update(&cl->bstats, skb);
> cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb);
> if (cl->un.leaf.deficit[level] < 0) {
> cl->un.leaf.deficit[level] += cl->quantum;
> @@ -871,10 +915,10 @@ ok:
>
Why this bstats_update() call was removed ?
^ permalink raw reply
* Re: [PATCH v3 6/6] net: calxedaxgmac: ip align receive buffers
From: Eric Dumazet @ 2012-11-05 16:53 UTC (permalink / raw)
To: Rob Herring; +Cc: netdev, davem, Rob Herring
In-Reply-To: <1352132544-15809-7-git-send-email-robherring2@gmail.com>
On Mon, 2012-11-05 at 10:22 -0600, Rob Herring wrote:
> From: Rob Herring <rob.herring@calxeda.com>
>
> On gcc 4.7, we will get alignment traps in the ip stack if we don't align
> the ip headers on receive. The h/w can support this, so use ip aligned
> allocations.
>
> Cut down the unnecessary padding on the allocation. The buffer can start on
> any byte alignment, but the size including the begining offset must be 8
> byte aligned. So the h/w buffer size must include the NET_IP_ALIGN offset.
>
> Thanks to Eric Dumazet for the initial patch highlighting the padding issues.
>
> Signed-off-by: Rob Herring <rob.herring@calxeda.com>
> ---
Acked-by: Eric Dumazet <edumazet@google.com>
^ permalink raw reply
* Re: [PATCH v1 0/5] usbnet: avoiding access auto-suspended device
From: David Miller @ 2012-11-05 16:50 UTC (permalink / raw)
To: oneukum-l3A5Bk7waGM
Cc: ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw,
gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r,
netdev-u79uwXL29TY76Z2rM5mHXA, linux-usb-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <9016904.gHGBncEQ14-ugxBuEnWX9yG/4A2pS7c2Q@public.gmane.org>
From: Oliver Neukum <oneukum-l3A5Bk7waGM@public.gmane.org>
Date: Mon, 05 Nov 2012 10:24:57 +0100
> On Sunday 04 November 2012 09:29:49 Ming Lei wrote:
>> Thip patchset avoids accessing auto-suspended device in ioctl path,
>> which is generally triggered by some network utility(ethtool, ifconfig,
>> ...)
>>
>> Most of network devices have the problem, but as discussed in the
>> thread:
>>
>> http://marc.info/?t=135054860600003&r=1&w=2
>>
>> the problem should be solved inside driver.
>>
>> Considered that only smsc75xx and smsc95xx calls usbnet_read_cmd()
>> and usbnet_write_cmd() inside its resume and suspend callback, the
>> patcheset introduce the nopm version of the two functions which
>> should be called only in the resume and suspend callback. So we
>> can solve the problem by runtime resuming device before doing
>> control message things.
>
> Hi,
>
> I am happy with these patches.
> Dave, do you have a principal objection regarding these patches, too?
There were review comments and the most recently posted series
needs to be reposted with that feedback incorporated.
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 8/9] isdn: Remove unused variable causing a compile build warning
From: David Miller @ 2012-11-05 16:46 UTC (permalink / raw)
To: lee.jones; +Cc: pebolle, linux-kernel, isdn, netdev
In-Reply-To: <20121105084419.GC2699@gmail.com>
From: Lee Jones <lee.jones@linaro.org>
Date: Mon, 5 Nov 2012 09:44:19 +0100
> On Sun, 04 Nov 2012, David Miller wrote:
>
>> From: Lee Jones <lee.jones@linaro.org>
>> Date: Sun, 4 Nov 2012 11:53:32 +0100
>>
>> > On Sun, 04 Nov 2012, Paul Bolle wrote:
>> >
>> >> On Sat, 2012-11-03 at 23:48 +0100, Lee Jones wrote:
>> >> > On Sat, 03 Nov 2012, Paul Bolle wrote:
>> >> > > On Sat, 2012-11-03 at 23:02 +0100, Lee Jones wrote:
>> >> > > > This patch fixes:
>> >> > > > drivers/isdn/i4l/isdn_common.c: In function ‘isdn_ioctl’:
>> >> > > > drivers/isdn/i4l/isdn_common.c:1278:8: warning: unused variable ‘s’ [-Wunused-variable]
>> >> > >
>> >> > > Did you have CONFIG_NETDEVICES not set in this build?
>> >> >
>> >> > Ah yes, I see it. The function went down further than I thought
>> >> > it did. So the real fix is to ensure 's' is defined inside of
>> >> > some ifdef CONFIG_NETDEVICES guards.
>> >>
>> >> What puzzles me is that we only find these "#ifdef CONFIG_NETDEVICES"
>> >> guards in this file and not in isdn_net.c, were all the ioctl commands
>> >> guarded that way seem to be calling into. On first glance that doesn't
>> >> make much sense.
>> >>
>> >> (Actually the idea of having ISDN without NETDEVICES is a bit puzzling
>> >> too. But there are too many parts of the isdn subsystem that I'm
>> >> unfamiliar with to say whether that can make sense.)
>> >
>> > I'm in the same position as you Paul. I just noticed the warning so
>> > fixed it following the current way of doing things. Any, more
>> > substantial changes requiring greater knowledge of the subsystem
>> > would have to be done by someone else.
>>
>> I think the most appropriate thing to do is make CONFIG_ISDN depend
>> upon CONFIG_NETDEVICES in the Kconfig file.
>
> ... and then remove the CONFIG_NETDEVICES guards in isdn_common.c?
>
> If that's suitable more suitable I can do that instead?
>
> Just need a yay or nay and I'll make it happen.
"yay"
^ permalink raw reply
* Re: [PATCH RFC] pkt_sched: enable QFQ to support TSO/GSO
From: David Miller @ 2012-11-05 16:46 UTC (permalink / raw)
To: xiyou.wangcong
Cc: shemminger, paolo.valente, jhs, linux-kernel, netdev, rizzo,
fchecconi
In-Reply-To: <CAM_iQpUbru0EiO8yJYO2Uke_Y5v7047PEijkBHHpBn5DUbke5Q@mail.gmail.com>
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 5 Nov 2012 16:41:49 +0800
> On Tue, Oct 30, 2012 at 10:24 PM, Stephen Hemminger
> <shemminger@vyatta.com> wrote:
>> On Tue, 30 Oct 2012 07:00:56 +0100
>> Paolo Valente <paolo.valente@unimore.it> wrote:
>>
>>> Hi,
>>> if the max packet size for some class (configured through tc) is
>>> violated by the actual size of the packets of that class, then QFQ
>>> would not schedule classes correctly, and the data structures
>>> implementing the bucket lists may get corrupted. This problem occurs
>>> with TSO/GSO even if the max packet size is set to the MTU, and is,
>>> e.g., the cause of the failure reported in [1]. Two patches have been
>>> proposed to solve this problem in [2], one of them is a preliminary
>>> version of this patch.
>>>
>>> This patch addresses the above issues by: 1) setting QFQ parameters to
>>> proper values for supporting TSO/GSO (in particular, setting the
>>> maximum possible packet size to 64KB), 2) automatically increasing the
>>> max packet size for a class, lmax, when a packet with a larger size
>>> than the current value of lmax arrives.
>>>
>>> The drawback of the first point is that the maximum weight for a class
>>> is now limited to 4096, which is equal to 1/16 of the maximum weight
>>> sum.
>>>
>>> Finally, this patch also forcibly caps the timestamps of a class if
>>> they are too high to be stored in the bucket list. This capping, taken
>>> from QFQ+ [3], handles the unfrequent case described in the comment to
>>> the function slot_insert.
>>>
>>> [1] http://marc.info/?l=linux-netdev&m=134968777902077&w=2
>>> [2] http://marc.info/?l=linux-netdev&m=135096573507936&w=2
>>> [3] http://marc.info/?l=linux-netdev&m=134902691421670&w=2
>>>
>>> Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
>>> Tested-by: Cong Wang <amwang@redhat.com>
>>
>> Acked-by: Stephen Hemminger <shemminger@vyatta.com>
>
>
> David, could you take this patch? Stephen acked it.
It's "RFC" so it needs to be explicitly reposted.
^ permalink raw reply
* Re: [PATCH] wireless: iwlwifi - add dma_mapping_error() checks to avoid warnings
From: Shuah Khan @ 2012-11-05 16:44 UTC (permalink / raw)
To: Johannes Berg
Cc: wey-yi.w.guy, linville, ilw, emmanuel.grumbach, donald.h.fry,
linux-wireless, netdev, LKML, shuahkhan
In-Reply-To: <1352132992.9466.27.camel@jlt4.sipsolutions.net>
On Mon, 2012-11-05 at 17:29 +0100, Johannes Berg wrote:
> On Mon, 2012-11-05 at 09:26 -0700, Shuah Khan wrote:
>
> > > Thanks for the report. Since I think doing BUG_ON() in such a scenario
> > > is a really bad idea, I've applied a different patch with your
> > > Reported-by.
> >
> > Yeah. I wasn't sure about BUS() either. Did you notice the other cases
> > of BUG_ON() in this path in iwl_rx_allocate()? I would think those need
> > fixing as well.
> >
> > rxb->page_dma =
> > dma_map_page(trans->dev, page, 0,
> > PAGE_SIZE <<
> > trans_pcie->rx_page_order,
> > DMA_FROM_DEVICE);
> > /* dma address must be no more than 36 bits */
> > BUG_ON(rxb->page_dma & ~DMA_BIT_MASK(36));
> > /* and also 256 byte aligned! */
> > BUG_ON(rxb->page_dma & DMA_BIT_MASK(8));
>
> Well, yes, we could convert them, but we can leave them as they are
> because these are assertions that the DMA mapping API guarantees. If
> this breaks, it's a bug in the DMA mapping code.
>
> In contrast, if it fails to map, it's not a bug in the code, it's just
> running out of memory or IO space or whatever.
Right.
>
> > Could you please send me commitID for the patch you did. I am interested
> > in seeing the failure handling in your patch?
>
> It's here:
> http://git.kernel.org/?p=linux/kernel/git/iwlwifi/iwlwifi-fixes.git;a=commit;h=7c34158231b2eda8dcbd297be2bb1559e69cb433
>
Thanks.
^ permalink raw reply
* 3.6 routing cache regression, multicast loopback broken
From: Maxime Bizon @ 2012-11-05 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Hi David & all,
kernel 3.6 to 3.6.5 (3.5 is working fine)
I have a "sender" sample app that does:
- socket(dgram)
- setsockopt mcast ttl 8
- setsockopt mcast loopback
- sendto() to 239.0.0.x
and a "receiver" sample app:
- socket(dgram)
- bind(239.0.0.x)
- add membership (239.0.0.x)
- loop on recv()
My setup: no default route, "ip route add 239.0.0.0/8 dev eth0", sender
& receiver running on same host.
If I first start one sender app (on 239.0.0.1), and after a receiver app
on 239.0.0.1 => no problem
If I first start two or more sender apps (239.0.0.1/239.0.0.2/...), then
assuming I don't start as many matching receivers, receivers sometimes
get all data or nothing at all.
After digging in __mkroute_output(), I found that unless I'm using a
default route (fi != NULL), rtable is cached and shared by all senders
(even those with different mcast addresses)
Since ip_check_mc_rcu() returns different results depending on whether
fl->daddr is present in device mc_list or not, I don't think we can
cache this.
The random working/not working effect I get is because add_membership
flushes the rt_cache, so depending on which sender does sendto() first
after flush, the cached entry will either use ip_mc_output() or
ip_output().
--
Maxime
^ permalink raw reply
* Re: [PATCH] wireless: iwlwifi - add dma_mapping_error() checks to avoid warnings
From: Johannes Berg @ 2012-11-05 16:29 UTC (permalink / raw)
To: shuah.khan
Cc: wey-yi.w.guy, linville, ilw, emmanuel.grumbach, donald.h.fry,
linux-wireless, netdev, LKML, shuahkhan
In-Reply-To: <1352132785.2606.14.camel@lorien2>
On Mon, 2012-11-05 at 09:26 -0700, Shuah Khan wrote:
> > Thanks for the report. Since I think doing BUG_ON() in such a scenario
> > is a really bad idea, I've applied a different patch with your
> > Reported-by.
>
> Yeah. I wasn't sure about BUS() either. Did you notice the other cases
> of BUG_ON() in this path in iwl_rx_allocate()? I would think those need
> fixing as well.
>
> rxb->page_dma =
> dma_map_page(trans->dev, page, 0,
> PAGE_SIZE <<
> trans_pcie->rx_page_order,
> DMA_FROM_DEVICE);
> /* dma address must be no more than 36 bits */
> BUG_ON(rxb->page_dma & ~DMA_BIT_MASK(36));
> /* and also 256 byte aligned! */
> BUG_ON(rxb->page_dma & DMA_BIT_MASK(8));
Well, yes, we could convert them, but we can leave them as they are
because these are assertions that the DMA mapping API guarantees. If
this breaks, it's a bug in the DMA mapping code.
In contrast, if it fails to map, it's not a bug in the code, it's just
running out of memory or IO space or whatever.
> Could you please send me commitID for the patch you did. I am interested
> in seeing the failure handling in your patch?
It's here:
http://git.kernel.org/?p=linux/kernel/git/iwlwifi/iwlwifi-fixes.git;a=commit;h=7c34158231b2eda8dcbd297be2bb1559e69cb433
johannes
^ permalink raw reply
* Re: [PATCH] wireless: iwlwifi - add dma_mapping_error() checks to avoid warnings
From: Shuah Khan @ 2012-11-05 16:26 UTC (permalink / raw)
To: Johannes Berg
Cc: johannes.berg, wey-yi.w.guy, linville, ilw, emmanuel.grumbach,
donald.h.fry, linux-wireless, netdev, LKML, shuahkhan
In-Reply-To: <1352020617.10072.0.camel@jlt4.sipsolutions.net>
On Sun, 2012-11-04 at 10:16 +0100, Johannes Berg wrote:
> On Sat, 2012-11-03 at 19:40 -0600, Shuah Khan wrote:
> > Add missing dma_mapping_error() checks to validate dma addresses returned by
> > dma_map_page() calls to avoid the following warning:
> >
> > [ 28.475686] WARNING: at lib/dma-debug.c:933 check_unmap+0x459/0x8a0()
> > [ 28.475688] Hardware name: HP EliteBook 6930p
> > [ 28.475690] iwlwifi 0000:03:00.0: DMA-API: device driver failed to check map error[device address=0x00000000ffffa000] [size=8192 bytes] [mapped as page]
> > [ 28.475691] Modules linked in: arc4 bnep rfcomm iwldvm mac80211 snd_hda_codec_analog radeon snd_hda_intel snd_hda_codec coretemp kvm_intel snd_hwdep snd_pcm iwlwifi kvm btusb bluetooth snd_seq_midi snd_rawmidi ttm cfg80211 snd_seq_midi_event drm_kms_helper pata_pcmcia drm snd_seq binfmt_misc pcmcia snd_timer snd_seq_device tpm_infineon snd dm_multipath yenta_socket joydev pcmcia_rsrc pcmcia_core hp_wmi psmouse hp_accel microcode soundcore i2c_algo_bit sparse_keymap wmi ppdev lpc_ich lis3lv02d snd_page_alloc video tpm_tis serio_raw parport_pc input_polldev mac_hid lp parport firewire_ohci firewire_core crc_itu_t sdhci_pci sdhci e1000e
>
> Thanks for the report. Since I think doing BUG_ON() in such a scenario
> is a really bad idea, I've applied a different patch with your
> Reported-by.
Yeah. I wasn't sure about BUS() either. Did you notice the other cases
of BUG_ON() in this path in iwl_rx_allocate()? I would think those need
fixing as well.
rxb->page_dma =
dma_map_page(trans->dev, page, 0,
PAGE_SIZE <<
trans_pcie->rx_page_order,
DMA_FROM_DEVICE);
/* dma address must be no more than 36 bits */
BUG_ON(rxb->page_dma & ~DMA_BIT_MASK(36));
/* and also 256 byte aligned! */
BUG_ON(rxb->page_dma & DMA_BIT_MASK(8));
Could you please send me commitID for the patch you did. I am interested
in seeing the failure handling in your patch?
-- Shuah
^ permalink raw reply
* Re: linux-next: Tree for Nov 5 (oki_semi/pch_gbe)
From: Randy Dunlap @ 2012-11-05 16:23 UTC (permalink / raw)
To: Stephen Rothwell
Cc: linux-next, linux-kernel, netdev@vger.kernel.org,
LAPIS SEMICONDUCTOR
In-Reply-To: <20121105164910.792cfe7d08761860acffe305@canb.auug.org.au>
[-- Attachment #1: Type: text/plain, Size: 880 bytes --]
On 11/04/2012 09:49 PM, Stephen Rothwell wrote:
> Hi all,
>
> Changes since 20121102:
>
on x86_64:
ERROR: "pch_set_station_address" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_tx_snap_read" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_src_uuid_lo_read" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_ch_event_read" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_ch_event_write" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_src_uuid_hi_read" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_ch_control_write" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
ERROR: "pch_rx_snap_read" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!
Full randconfig file is attached.
--
~Randy
[-- Attachment #2: config-r8555 --]
[-- Type: text/plain, Size: 60314 bytes --]
#
# Automatically generated file; DO NOT EDIT.
# Linux/x86_64 3.7.0-rc4 Kernel Configuration
#
CONFIG_64BIT=y
CONFIG_X86_64=y
CONFIG_X86=y
CONFIG_INSTRUCTION_DECODER=y
CONFIG_OUTPUT_FORMAT="elf64-x86-64"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig"
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_HAVE_LATENCYTOP_SUPPORT=y
CONFIG_MMU=y
CONFIG_NEED_DMA_MAP_STATE=y
CONFIG_NEED_SG_DMA_LENGTH=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_DEFAULT_IDLE=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_ARCH_HAS_CPU_AUTOPROBE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
CONFIG_ZONE_DMA32=y
CONFIG_AUDIT_ARCH=y
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_ARCH_HWEIGHT_CFLAGS="-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11"
CONFIG_ARCH_SUPPORTS_UPROBES=y
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
CONFIG_HAVE_IRQ_WORK=y
CONFIG_IRQ_WORK=y
CONFIG_BUILDTIME_EXTABLE_SORT=y
#
# General setup
#
CONFIG_EXPERIMENTAL=y
CONFIG_BROKEN_ON_SMP=y
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_CROSS_COMPILE=""
CONFIG_LOCALVERSION=""
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_HAVE_KERNEL_XZ=y
CONFIG_HAVE_KERNEL_LZO=y
# CONFIG_KERNEL_GZIP is not set
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
CONFIG_KERNEL_XZ=y
# CONFIG_KERNEL_LZO is not set
CONFIG_DEFAULT_HOSTNAME="(none)"
CONFIG_SWAP=y
# CONFIG_SYSVIPC is not set
# CONFIG_POSIX_MQUEUE is not set
CONFIG_FHANDLE=y
CONFIG_AUDIT=y
# CONFIG_AUDITSYSCALL is not set
# CONFIG_AUDIT_LOGINUID_IMMUTABLE is not set
CONFIG_HAVE_GENERIC_HARDIRQS=y
#
# IRQ subsystem
#
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_IRQ_DOMAIN=y
# CONFIG_IRQ_DOMAIN_DEBUG is not set
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_SPARSE_IRQ=y
CONFIG_CLOCKSOURCE_WATCHDOG=y
CONFIG_ARCH_CLOCKSOURCE_DATA=y
CONFIG_GENERIC_TIME_VSYSCALL=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
CONFIG_GENERIC_CMOS_UPDATE=y
#
# Timers subsystem
#
# CONFIG_NO_HZ is not set
# CONFIG_HIGH_RES_TIMERS is not set
#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_IRQ_TIME_ACCOUNTING is not set
# CONFIG_BSD_PROCESS_ACCT is not set
CONFIG_TASKSTATS=y
# CONFIG_TASK_DELAY_ACCT is not set
CONFIG_TASK_XACCT=y
# CONFIG_TASK_IO_ACCOUNTING is not set
#
# RCU Subsystem
#
CONFIG_TINY_PREEMPT_RCU=y
CONFIG_PREEMPT_RCU=y
# CONFIG_TREE_RCU_TRACE is not set
# CONFIG_RCU_BOOST is not set
CONFIG_IKCONFIG=m
# CONFIG_IKCONFIG_PROC is not set
CONFIG_LOG_BUF_SHIFT=17
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
CONFIG_CGROUPS=y
# CONFIG_CGROUP_DEBUG is not set
# CONFIG_CGROUP_FREEZER is not set
CONFIG_CGROUP_DEVICE=y
# CONFIG_CPUSETS is not set
CONFIG_CGROUP_CPUACCT=y
# CONFIG_RESOURCE_COUNTERS is not set
# CONFIG_CGROUP_PERF is not set
CONFIG_CGROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_CFS_BANDWIDTH=y
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_BLK_CGROUP=y
# CONFIG_DEBUG_BLK_CGROUP is not set
# CONFIG_CHECKPOINT_RESTORE is not set
CONFIG_NAMESPACES=y
# CONFIG_UTS_NS is not set
# CONFIG_PID_NS is not set
CONFIG_NET_NS=y
CONFIG_SCHED_AUTOGROUP=y
# CONFIG_SYSFS_DEPRECATED is not set
CONFIG_RELAY=y
# CONFIG_BLK_DEV_INITRD is not set
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
CONFIG_ANON_INODES=y
CONFIG_EXPERT=y
CONFIG_HAVE_UID16=y
CONFIG_UID16=y
CONFIG_SYSCTL_EXCEPTION_TRACE=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
# CONFIG_BUG is not set
# CONFIG_ELF_CORE is not set
CONFIG_PCSPKR_PLATFORM=y
CONFIG_HAVE_PCSPKR_PLATFORM=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
# CONFIG_EPOLL is not set
# CONFIG_SIGNALFD is not set
CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
CONFIG_SHMEM=y
# CONFIG_AIO is not set
# CONFIG_EMBEDDED is not set
CONFIG_HAVE_PERF_EVENTS=y
CONFIG_PERF_USE_VMALLOC=y
#
# Kernel Performance Events And Counters
#
CONFIG_PERF_EVENTS=y
CONFIG_DEBUG_PERF_USE_VMALLOC=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_PCI_QUIRKS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
# CONFIG_SLAB is not set
CONFIG_SLUB=y
# CONFIG_SLOB is not set
# CONFIG_PROFILING is not set
CONFIG_TRACEPOINTS=y
CONFIG_HAVE_OPROFILE=y
CONFIG_OPROFILE_NMI_TIMER=y
# CONFIG_KPROBES is not set
# CONFIG_JUMP_LABEL is not set
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_OPTPROBES=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_ATTRS=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
CONFIG_HAVE_DMA_API_DEBUG=y
CONFIG_HAVE_HW_BREAKPOINT=y
CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
CONFIG_HAVE_USER_RETURN_NOTIFIER=y
CONFIG_HAVE_PERF_EVENTS_NMI=y
CONFIG_HAVE_PERF_REGS=y
CONFIG_HAVE_PERF_USER_STACK_DUMP=y
CONFIG_HAVE_ARCH_JUMP_LABEL=y
CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
CONFIG_HAVE_ALIGNED_STRUCT_PAGE=y
CONFIG_HAVE_CMPXCHG_LOCAL=y
CONFIG_HAVE_CMPXCHG_DOUBLE=y
CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION=y
CONFIG_ARCH_WANT_OLD_COMPAT_IPC=y
CONFIG_GENERIC_KERNEL_THREAD=y
CONFIG_GENERIC_KERNEL_EXECVE=y
CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
CONFIG_HAVE_RCU_USER_QS=y
CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
CONFIG_MODULES_USE_ELF_RELA=y
#
# GCOV-based kernel profiling
#
# CONFIG_GCOV_KERNEL is not set
# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
CONFIG_RT_MUTEXES=y
CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_MODULE_FORCE_UNLOAD is not set
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_MODULE_SIG=y
CONFIG_MODULE_SIG_FORCE=y
# CONFIG_MODULE_SIG_SHA1 is not set
# CONFIG_MODULE_SIG_SHA224 is not set
# CONFIG_MODULE_SIG_SHA256 is not set
# CONFIG_MODULE_SIG_SHA384 is not set
CONFIG_MODULE_SIG_SHA512=y
CONFIG_BLOCK=y
CONFIG_BLK_DEV_BSG=y
CONFIG_BLK_DEV_BSGLIB=y
CONFIG_BLK_DEV_INTEGRITY=y
# CONFIG_BLK_DEV_THROTTLING is not set
#
# Partition Types
#
# CONFIG_PARTITION_ADVANCED is not set
CONFIG_MSDOS_PARTITION=y
CONFIG_BLOCK_COMPAT=y
#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
# CONFIG_IOSCHED_DEADLINE is not set
# CONFIG_IOSCHED_CFQ is not set
CONFIG_DEFAULT_NOOP=y
CONFIG_DEFAULT_IOSCHED="noop"
CONFIG_ASN1=y
CONFIG_UNINLINE_SPIN_UNLOCK=y
CONFIG_FREEZER=y
#
# Processor type and features
#
CONFIG_ZONE_DMA=y
# CONFIG_SMP is not set
# CONFIG_X86_MPPARSE is not set
# CONFIG_X86_EXTENDED_PLATFORM is not set
CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y
# CONFIG_SCHED_OMIT_FRAME_POINTER is not set
# CONFIG_KVMTOOL_TEST_ENABLE is not set
CONFIG_PARAVIRT_GUEST=y
CONFIG_PARAVIRT_TIME_ACCOUNTING=y
# CONFIG_XEN is not set
# CONFIG_XEN_PRIVILEGED_GUEST is not set
# CONFIG_KVM_GUEST is not set
CONFIG_PARAVIRT=y
# CONFIG_PARAVIRT_DEBUG is not set
CONFIG_NO_BOOTMEM=y
# CONFIG_MEMTEST is not set
# CONFIG_MK8 is not set
# CONFIG_MPSC is not set
# CONFIG_MCORE2 is not set
# CONFIG_MATOM is not set
CONFIG_GENERIC_CPU=y
CONFIG_X86_INTERNODE_CACHE_SHIFT=6
CONFIG_X86_CMPXCHG=y
CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_XADD=y
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_CMOV=y
CONFIG_X86_MINIMUM_CPU_FAMILY=64
CONFIG_X86_DEBUGCTLMSR=y
# CONFIG_PROCESSOR_SELECT is not set
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR=y
CONFIG_HPET_TIMER=y
CONFIG_DMI=y
# CONFIG_GART_IOMMU is not set
CONFIG_CALGARY_IOMMU=y
CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT=y
CONFIG_SWIOTLB=y
CONFIG_IOMMU_HELPER=y
CONFIG_NR_CPUS=1
# CONFIG_PREEMPT_NONE is not set
# CONFIG_PREEMPT_VOLUNTARY is not set
CONFIG_PREEMPT=y
CONFIG_PREEMPT_COUNT=y
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
# CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS is not set
CONFIG_X86_MCE=y
CONFIG_X86_MCE_INTEL=y
CONFIG_X86_MCE_AMD=y
CONFIG_X86_MCE_THRESHOLD=y
CONFIG_X86_MCE_INJECT=m
CONFIG_X86_THERMAL_VECTOR=y
# CONFIG_I8K is not set
# CONFIG_MICROCODE is not set
# CONFIG_X86_MSR is not set
# CONFIG_X86_CPUID is not set
CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
CONFIG_ARCH_DMA_ADDR_T_64BIT=y
CONFIG_DIRECT_GBPAGES=y
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SPARSEMEM_DEFAULT=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_SPARSEMEM_MANUAL=y
CONFIG_SPARSEMEM=y
CONFIG_HAVE_MEMORY_PRESENT=y
CONFIG_SPARSEMEM_EXTREME=y
CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER=y
# CONFIG_SPARSEMEM_VMEMMAP is not set
CONFIG_HAVE_MEMBLOCK=y
CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
CONFIG_ARCH_DISCARD_MEMBLOCK=y
# CONFIG_MEMORY_HOTPLUG is not set
CONFIG_PAGEFLAGS_EXTENDED=y
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_COMPACTION=y
CONFIG_MIGRATION=y
CONFIG_PHYS_ADDR_T_64BIT=y
CONFIG_ZONE_DMA_FLAG=1
CONFIG_BOUNCE=y
CONFIG_VIRT_TO_BUS=y
CONFIG_KSM=y
CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y
# CONFIG_MEMORY_FAILURE is not set
# CONFIG_TRANSPARENT_HUGEPAGE is not set
CONFIG_CROSS_MEMORY_ATTACH=y
CONFIG_NEED_PER_CPU_KM=y
# CONFIG_CLEANCACHE is not set
# CONFIG_FRONTSWAP is not set
# CONFIG_X86_CHECK_BIOS_CORRUPTION is not set
CONFIG_X86_RESERVE_LOW=64
CONFIG_MTRR=y
# CONFIG_MTRR_SANITIZER is not set
# CONFIG_X86_PAT is not set
CONFIG_ARCH_RANDOM=y
CONFIG_X86_SMAP=y
CONFIG_EFI=y
# CONFIG_EFI_STUB is not set
# CONFIG_SECCOMP is not set
# CONFIG_CC_STACKPROTECTOR is not set
# CONFIG_HZ_100 is not set
CONFIG_HZ_250=y
# CONFIG_HZ_300 is not set
# CONFIG_HZ_1000 is not set
CONFIG_HZ=250
# CONFIG_SCHED_HRTICK is not set
# CONFIG_KEXEC is not set
# CONFIG_CRASH_DUMP is not set
CONFIG_PHYSICAL_START=0x1000000
CONFIG_RELOCATABLE=y
CONFIG_PHYSICAL_ALIGN=0x1000000
# CONFIG_COMPAT_VDSO is not set
# CONFIG_CMDLINE_BOOL is not set
CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
#
# Power management and ACPI options
#
CONFIG_ARCH_HIBERNATION_HEADER=y
CONFIG_SUSPEND=y
CONFIG_SUSPEND_FREEZER=y
CONFIG_HIBERNATE_CALLBACKS=y
CONFIG_HIBERNATION=y
CONFIG_PM_STD_PARTITION=""
CONFIG_PM_SLEEP=y
CONFIG_PM_AUTOSLEEP=y
CONFIG_PM_WAKELOCKS=y
CONFIG_PM_WAKELOCKS_LIMIT=100
CONFIG_PM_WAKELOCKS_GC=y
# CONFIG_PM_RUNTIME is not set
CONFIG_PM=y
# CONFIG_PM_DEBUG is not set
CONFIG_ACPI=y
CONFIG_ACPI_SLEEP=y
CONFIG_ACPI_PROCFS=y
CONFIG_ACPI_PROCFS_POWER=y
CONFIG_ACPI_EC_DEBUGFS=m
# CONFIG_ACPI_PROC_EVENT is not set
# CONFIG_ACPI_AC is not set
CONFIG_ACPI_BATTERY=m
CONFIG_ACPI_FAN=m
# CONFIG_ACPI_DOCK is not set
CONFIG_ACPI_PROCESSOR=m
# CONFIG_ACPI_PROCESSOR_AGGREGATOR is not set
# CONFIG_ACPI_THERMAL is not set
# CONFIG_ACPI_CUSTOM_DSDT is not set
# CONFIG_ACPI_INITRD_TABLE_OVERRIDE is not set
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
CONFIG_ACPI_PCI_SLOT=m
CONFIG_X86_PM_TIMER=y
# CONFIG_ACPI_CONTAINER is not set
CONFIG_ACPI_SBS=m
# CONFIG_ACPI_HED is not set
# CONFIG_ACPI_CUSTOM_METHOD is not set
CONFIG_ACPI_BGRT=y
# CONFIG_ACPI_APEI is not set
# CONFIG_SFI is not set
#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set
CONFIG_CPU_IDLE=y
# CONFIG_CPU_IDLE_MULTIPLE_DRIVERS is not set
CONFIG_CPU_IDLE_GOV_LADDER=y
# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
CONFIG_INTEL_IDLE=y
#
# Memory power savings
#
CONFIG_I7300_IDLE_IOAT_CHANNEL=y
CONFIG_I7300_IDLE=m
#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
CONFIG_PCI_DOMAINS=y
CONFIG_PCI_CNB20LE_QUIRK=y
# CONFIG_PCIEPORTBUS is not set
CONFIG_ARCH_SUPPORTS_MSI=y
# CONFIG_PCI_MSI is not set
CONFIG_PCI_DEBUG=y
# CONFIG_PCI_REALLOC_ENABLE_AUTO is not set
CONFIG_PCI_STUB=m
# CONFIG_HT_IRQ is not set
CONFIG_PCI_ATS=y
# CONFIG_PCI_IOV is not set
CONFIG_PCI_PRI=y
# CONFIG_PCI_PASID is not set
# CONFIG_PCI_IOAPIC is not set
CONFIG_PCI_LABEL=y
CONFIG_ISA_DMA_API=y
CONFIG_AMD_NB=y
CONFIG_PCCARD=m
CONFIG_PCMCIA=m
CONFIG_PCMCIA_LOAD_CIS=y
CONFIG_CARDBUS=y
#
# PC-card bridges
#
# CONFIG_YENTA is not set
CONFIG_PD6729=m
CONFIG_I82092=m
CONFIG_PCCARD_NONSTATIC=y
# CONFIG_HOTPLUG_PCI is not set
# CONFIG_RAPIDIO is not set
#
# Executable file formats / Emulations
#
CONFIG_BINFMT_ELF=y
CONFIG_COMPAT_BINFMT_ELF=y
CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE=y
# CONFIG_HAVE_AOUT is not set
CONFIG_BINFMT_MISC=m
CONFIG_COREDUMP=y
CONFIG_IA32_EMULATION=y
CONFIG_IA32_AOUT=m
CONFIG_X86_X32=y
CONFIG_COMPAT=y
CONFIG_COMPAT_FOR_U64_ALIGNMENT=y
CONFIG_KEYS_COMPAT=y
CONFIG_HAVE_TEXT_POKE_SMP=y
CONFIG_X86_DEV_DMA_OPS=y
CONFIG_NET=y
CONFIG_COMPAT_NETLINK_MESSAGES=y
#
# Networking options
#
# CONFIG_PACKET is not set
# CONFIG_UNIX is not set
CONFIG_XFRM=y
CONFIG_XFRM_ALGO=m
# CONFIG_XFRM_SUB_POLICY is not set
CONFIG_XFRM_MIGRATE=y
CONFIG_NET_KEY=m
CONFIG_NET_KEY_MIGRATE=y
# CONFIG_INET is not set
# CONFIG_NETWORK_SECMARK is not set
# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
# CONFIG_NETFILTER is not set
CONFIG_ATM=m
CONFIG_ATM_LANE=m
# CONFIG_BRIDGE is not set
# CONFIG_NET_DSA is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
CONFIG_LLC=m
CONFIG_LLC2=m
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
# CONFIG_WAN_ROUTER is not set
# CONFIG_PHONET is not set
CONFIG_IEEE802154=m
CONFIG_MAC802154=m
CONFIG_NET_SCHED=y
#
# Queueing/Scheduling
#
CONFIG_NET_SCH_CBQ=m
# CONFIG_NET_SCH_HTB is not set
# CONFIG_NET_SCH_HFSC is not set
# CONFIG_NET_SCH_ATM is not set
# CONFIG_NET_SCH_PRIO is not set
CONFIG_NET_SCH_MULTIQ=m
CONFIG_NET_SCH_RED=m
# CONFIG_NET_SCH_SFB is not set
CONFIG_NET_SCH_SFQ=m
CONFIG_NET_SCH_TEQL=m
# CONFIG_NET_SCH_TBF is not set
# CONFIG_NET_SCH_GRED is not set
CONFIG_NET_SCH_DSMARK=m
CONFIG_NET_SCH_NETEM=m
# CONFIG_NET_SCH_DRR is not set
# CONFIG_NET_SCH_MQPRIO is not set
# CONFIG_NET_SCH_CHOKE is not set
# CONFIG_NET_SCH_QFQ is not set
CONFIG_NET_SCH_CODEL=m
# CONFIG_NET_SCH_FQ_CODEL is not set
CONFIG_NET_SCH_INGRESS=m
# CONFIG_NET_SCH_PLUG is not set
#
# Classification
#
CONFIG_NET_CLS=y
CONFIG_NET_CLS_BASIC=m
# CONFIG_NET_CLS_TCINDEX is not set
CONFIG_NET_CLS_FW=m
# CONFIG_NET_CLS_U32 is not set
# CONFIG_NET_CLS_RSVP is not set
# CONFIG_NET_CLS_RSVP6 is not set
CONFIG_NET_CLS_FLOW=m
CONFIG_NET_CLS_CGROUP=m
CONFIG_NET_EMATCH=y
CONFIG_NET_EMATCH_STACK=32
CONFIG_NET_EMATCH_CMP=m
# CONFIG_NET_EMATCH_NBYTE is not set
# CONFIG_NET_EMATCH_U32 is not set
# CONFIG_NET_EMATCH_META is not set
CONFIG_NET_EMATCH_TEXT=m
CONFIG_NET_CLS_ACT=y
# CONFIG_NET_ACT_POLICE is not set
# CONFIG_NET_ACT_GACT is not set
# CONFIG_NET_ACT_MIRRED is not set
CONFIG_NET_ACT_NAT=m
CONFIG_NET_ACT_PEDIT=m
# CONFIG_NET_ACT_SIMP is not set
# CONFIG_NET_ACT_SKBEDIT is not set
CONFIG_NET_CLS_IND=y
CONFIG_NET_SCH_FIFO=y
# CONFIG_DCB is not set
# CONFIG_DNS_RESOLVER is not set
# CONFIG_BATMAN_ADV is not set
# CONFIG_OPENVSWITCH is not set
CONFIG_NETPRIO_CGROUP=m
CONFIG_BQL=y
# CONFIG_BPF_JIT is not set
#
# Network testing
#
CONFIG_NET_PKTGEN=m
CONFIG_HAMRADIO=y
#
# Packet Radio protocols
#
CONFIG_AX25=m
CONFIG_AX25_DAMA_SLAVE=y
CONFIG_NETROM=m
# CONFIG_ROSE is not set
#
# AX.25 network device drivers
#
CONFIG_MKISS=m
CONFIG_6PACK=m
CONFIG_BPQETHER=m
# CONFIG_BAYCOM_SER_FDX is not set
CONFIG_BAYCOM_SER_HDX=m
# CONFIG_YAM is not set
# CONFIG_CAN is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
CONFIG_WIRELESS=y
CONFIG_WIRELESS_EXT=y
CONFIG_WEXT_CORE=y
CONFIG_WEXT_PROC=y
CONFIG_WEXT_SPY=y
CONFIG_WEXT_PRIV=y
# CONFIG_CFG80211 is not set
CONFIG_LIB80211=m
CONFIG_LIB80211_CRYPT_WEP=m
CONFIG_LIB80211_CRYPT_CCMP=m
CONFIG_LIB80211_CRYPT_TKIP=m
CONFIG_LIB80211_DEBUG=y
#
# CFG80211 needs to be enabled for MAC80211
#
# CONFIG_WIMAX is not set
CONFIG_RFKILL=m
CONFIG_RFKILL_LEDS=y
CONFIG_RFKILL_REGULATOR=m
CONFIG_NET_9P=m
# CONFIG_NET_9P_VIRTIO is not set
# CONFIG_NET_9P_DEBUG is not set
# CONFIG_CAIF is not set
# CONFIG_NFC is not set
CONFIG_HAVE_BPF_JIT=y
#
# Device Drivers
#
#
# Generic Driver Options
#
CONFIG_UEVENT_HELPER_PATH=""
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
CONFIG_FW_LOADER=m
# CONFIG_FIRMWARE_IN_KERNEL is not set
CONFIG_EXTRA_FIRMWARE=""
# CONFIG_DEBUG_DRIVER is not set
# CONFIG_DEBUG_DEVRES is not set
# CONFIG_SYS_HYPERVISOR is not set
# CONFIG_GENERIC_CPU_DEVICES is not set
# CONFIG_DMA_SHARED_BUFFER is not set
#
# Bus devices
#
# CONFIG_OMAP_OCP2SCP is not set
# CONFIG_CONNECTOR is not set
CONFIG_MTD=m
# CONFIG_MTD_TESTS is not set
CONFIG_MTD_REDBOOT_PARTS=m
CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1
# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set
# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set
CONFIG_MTD_AR7_PARTS=m
#
# User Modules And Translation Layers
#
# CONFIG_MTD_CHAR is not set
CONFIG_HAVE_MTD_OTP=y
CONFIG_MTD_BLKDEVS=m
CONFIG_MTD_BLOCK=m
# CONFIG_MTD_BLOCK_RO is not set
CONFIG_FTL=m
CONFIG_NFTL=m
# CONFIG_NFTL_RW is not set
CONFIG_INFTL=m
CONFIG_RFD_FTL=m
# CONFIG_SSFDC is not set
CONFIG_SM_FTL=m
# CONFIG_MTD_OOPS is not set
CONFIG_MTD_SWAP=m
#
# RAM/ROM/Flash chip drivers
#
# CONFIG_MTD_CFI is not set
CONFIG_MTD_JEDECPROBE=m
CONFIG_MTD_GEN_PROBE=m
CONFIG_MTD_CFI_ADV_OPTIONS=y
CONFIG_MTD_CFI_NOSWAP=y
# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set
# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set
# CONFIG_MTD_CFI_GEOMETRY is not set
CONFIG_MTD_MAP_BANK_WIDTH_1=y
CONFIG_MTD_MAP_BANK_WIDTH_2=y
CONFIG_MTD_MAP_BANK_WIDTH_4=y
# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
CONFIG_MTD_CFI_I1=y
CONFIG_MTD_CFI_I2=y
# CONFIG_MTD_CFI_I4 is not set
# CONFIG_MTD_CFI_I8 is not set
CONFIG_MTD_OTP=y
CONFIG_MTD_CFI_INTELEXT=m
CONFIG_MTD_CFI_AMDSTD=m
# CONFIG_MTD_CFI_STAA is not set
CONFIG_MTD_CFI_UTIL=m
CONFIG_MTD_RAM=m
# CONFIG_MTD_ROM is not set
# CONFIG_MTD_ABSENT is not set
#
# Mapping drivers for chip access
#
# CONFIG_MTD_COMPLEX_MAPPINGS is not set
CONFIG_MTD_PHYSMAP=m
# CONFIG_MTD_PHYSMAP_COMPAT is not set
CONFIG_MTD_TS5500=m
# CONFIG_MTD_AMD76XROM is not set
# CONFIG_MTD_ICHXROM is not set
CONFIG_MTD_ESB2ROM=m
# CONFIG_MTD_CK804XROM is not set
# CONFIG_MTD_SCB2_FLASH is not set
CONFIG_MTD_NETtel=m
CONFIG_MTD_L440GX=m
CONFIG_MTD_INTEL_VR_NOR=m
CONFIG_MTD_PLATRAM=m
#
# Self-contained MTD device drivers
#
CONFIG_MTD_PMC551=m
# CONFIG_MTD_PMC551_BUGFIX is not set
# CONFIG_MTD_PMC551_DEBUG is not set
# CONFIG_MTD_SLRAM is not set
# CONFIG_MTD_PHRAM is not set
CONFIG_MTD_MTDRAM=m
CONFIG_MTDRAM_TOTAL_SIZE=4096
CONFIG_MTDRAM_ERASE_SIZE=128
CONFIG_MTD_BLOCK2MTD=m
#
# Disk-On-Chip Device Drivers
#
# CONFIG_MTD_DOCG3 is not set
CONFIG_MTD_NAND_ECC=m
# CONFIG_MTD_NAND_ECC_SMC is not set
# CONFIG_MTD_NAND is not set
CONFIG_MTD_ONENAND=m
CONFIG_MTD_ONENAND_VERIFY_WRITE=y
# CONFIG_MTD_ONENAND_GENERIC is not set
CONFIG_MTD_ONENAND_OTP=y
# CONFIG_MTD_ONENAND_2X_PROGRAM is not set
# CONFIG_MTD_ONENAND_SIM is not set
#
# LPDDR flash memory drivers
#
CONFIG_MTD_LPDDR=m
CONFIG_MTD_QINFO_PROBE=m
CONFIG_MTD_UBI=m
CONFIG_MTD_UBI_WL_THRESHOLD=4096
CONFIG_MTD_UBI_BEB_LIMIT=20
# CONFIG_MTD_UBI_FASTMAP is not set
CONFIG_MTD_UBI_GLUEBI=m
# CONFIG_PARPORT is not set
CONFIG_PNP=y
# CONFIG_PNP_DEBUG_MESSAGES is not set
#
# Protocols
#
CONFIG_PNPACPI=y
# CONFIG_BLK_DEV is not set
#
# Misc devices
#
CONFIG_PHANTOM=m
CONFIG_INTEL_MID_PTI=m
# CONFIG_SGI_IOC4 is not set
CONFIG_TIFM_CORE=m
# CONFIG_TIFM_7XX1 is not set
CONFIG_ENCLOSURE_SERVICES=m
CONFIG_HP_ILO=m
CONFIG_VMWARE_BALLOON=m
# CONFIG_PCH_PHUB is not set
CONFIG_C2PORT=m
CONFIG_C2PORT_DURAMAR_2150=m
#
# EEPROM support
#
CONFIG_EEPROM_93CX6=m
CONFIG_CB710_CORE=m
# CONFIG_CB710_DEBUG is not set
CONFIG_CB710_DEBUG_ASSUMPTIONS=y
#
# Texas Instruments shared transport line discipline
#
#
# Altera FPGA firmware download module
#
CONFIG_HAVE_IDE=y
# CONFIG_IDE is not set
#
# SCSI device support
#
CONFIG_SCSI_MOD=m
CONFIG_RAID_ATTRS=m
CONFIG_SCSI=m
CONFIG_SCSI_DMA=y
CONFIG_SCSI_TGT=m
CONFIG_SCSI_NETLINK=y
CONFIG_SCSI_PROC_FS=y
#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=m
CONFIG_CHR_DEV_ST=m
# CONFIG_CHR_DEV_OSST is not set
# CONFIG_BLK_DEV_SR is not set
# CONFIG_CHR_DEV_SG is not set
# CONFIG_CHR_DEV_SCH is not set
# CONFIG_SCSI_ENCLOSURE is not set
CONFIG_SCSI_MULTI_LUN=y
# CONFIG_SCSI_CONSTANTS is not set
CONFIG_SCSI_LOGGING=y
# CONFIG_SCSI_SCAN_ASYNC is not set
#
# SCSI Transports
#
CONFIG_SCSI_SPI_ATTRS=m
CONFIG_SCSI_FC_ATTRS=m
CONFIG_SCSI_FC_TGT_ATTRS=y
CONFIG_SCSI_ISCSI_ATTRS=m
CONFIG_SCSI_SAS_ATTRS=m
CONFIG_SCSI_SAS_LIBSAS=m
# CONFIG_SCSI_SAS_ATA is not set
# CONFIG_SCSI_SAS_HOST_SMP is not set
CONFIG_SCSI_SRP_ATTRS=m
# CONFIG_SCSI_SRP_TGT_ATTRS is not set
CONFIG_SCSI_LOWLEVEL=y
CONFIG_ISCSI_BOOT_SYSFS=m
# CONFIG_SCSI_BNX2_ISCSI is not set
CONFIG_SCSI_BNX2X_FCOE=m
# CONFIG_BE2ISCSI is not set
CONFIG_BLK_DEV_3W_XXXX_RAID=m
# CONFIG_SCSI_HPSA is not set
# CONFIG_SCSI_3W_9XXX is not set
CONFIG_SCSI_3W_SAS=m
# CONFIG_SCSI_ACARD is not set
CONFIG_SCSI_AACRAID=m
# CONFIG_SCSI_AIC7XXX is not set
CONFIG_SCSI_AIC7XXX_OLD=m
CONFIG_SCSI_AIC79XX=m
CONFIG_AIC79XX_CMDS_PER_DEVICE=32
CONFIG_AIC79XX_RESET_DELAY_MS=5000
CONFIG_AIC79XX_DEBUG_ENABLE=y
CONFIG_AIC79XX_DEBUG_MASK=0
# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set
# CONFIG_SCSI_AIC94XX is not set
CONFIG_SCSI_MVSAS=m
CONFIG_SCSI_MVSAS_DEBUG=y
# CONFIG_SCSI_MVSAS_TASKLET is not set
# CONFIG_SCSI_MVUMI is not set
CONFIG_SCSI_DPT_I2O=m
# CONFIG_SCSI_ADVANSYS is not set
CONFIG_SCSI_ARCMSR=m
# CONFIG_MEGARAID_NEWGEN is not set
CONFIG_MEGARAID_LEGACY=m
CONFIG_MEGARAID_SAS=m
# CONFIG_SCSI_MPT2SAS is not set
CONFIG_SCSI_UFSHCD=m
CONFIG_SCSI_HPTIOP=m
CONFIG_SCSI_BUSLOGIC=m
CONFIG_VMWARE_PVSCSI=m
CONFIG_LIBFC=m
CONFIG_LIBFCOE=m
CONFIG_FCOE=m
# CONFIG_FCOE_FNIC is not set
CONFIG_SCSI_DMX3191D=m
CONFIG_SCSI_EATA=m
# CONFIG_SCSI_EATA_TAGGED_QUEUE is not set
CONFIG_SCSI_EATA_LINKED_COMMANDS=y
CONFIG_SCSI_EATA_MAX_TAGS=16
# CONFIG_SCSI_FUTURE_DOMAIN is not set
CONFIG_SCSI_GDTH=m
# CONFIG_SCSI_ISCI is not set
# CONFIG_SCSI_IPS is not set
# CONFIG_SCSI_INITIO is not set
CONFIG_SCSI_INIA100=m
CONFIG_SCSI_STEX=m
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
# CONFIG_SCSI_QLA_FC is not set
CONFIG_SCSI_QLA_ISCSI=m
# CONFIG_SCSI_LPFC is not set
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_DC390T is not set
CONFIG_SCSI_DEBUG=m
# CONFIG_SCSI_PMCRAID is not set
CONFIG_SCSI_PM8001=m
CONFIG_SCSI_SRP=m
# CONFIG_SCSI_BFA_FC is not set
# CONFIG_SCSI_VIRTIO is not set
# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
CONFIG_SCSI_DH=m
# CONFIG_SCSI_DH_RDAC is not set
# CONFIG_SCSI_DH_HP_SW is not set
CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
CONFIG_SCSI_OSD_INITIATOR=m
# CONFIG_SCSI_OSD_ULD is not set
CONFIG_SCSI_OSD_DPRINT_SENSE=1
CONFIG_SCSI_OSD_DEBUG=y
CONFIG_ATA=m
# CONFIG_ATA_NONSTANDARD is not set
CONFIG_ATA_VERBOSE_ERROR=y
CONFIG_ATA_ACPI=y
CONFIG_SATA_PMP=y
#
# Controllers with non-SFF native interface
#
# CONFIG_SATA_AHCI is not set
CONFIG_SATA_AHCI_PLATFORM=m
# CONFIG_SATA_INIC162X is not set
CONFIG_SATA_ACARD_AHCI=m
CONFIG_SATA_SIL24=m
CONFIG_ATA_SFF=y
#
# SFF controllers with custom DMA interface
#
CONFIG_PDC_ADMA=m
CONFIG_SATA_QSTOR=m
# CONFIG_SATA_SX4 is not set
# CONFIG_ATA_BMDMA is not set
#
# PIO-only SFF controllers
#
CONFIG_PATA_CMD640_PCI=m
# CONFIG_PATA_MPIIX is not set
CONFIG_PATA_NS87410=m
CONFIG_PATA_OPTI=m
# CONFIG_PATA_PCMCIA is not set
CONFIG_PATA_PLATFORM=m
# CONFIG_PATA_RZ1000 is not set
#
# Generic fallback / legacy drivers
#
CONFIG_PATA_LEGACY=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=m
# CONFIG_MD_LINEAR is not set
CONFIG_MD_RAID0=m
# CONFIG_MD_RAID1 is not set
# CONFIG_MD_RAID10 is not set
CONFIG_MD_RAID456=m
# CONFIG_MD_MULTIPATH is not set
# CONFIG_MD_FAULTY is not set
# CONFIG_BLK_DEV_DM is not set
# CONFIG_TARGET_CORE is not set
CONFIG_FUSION=y
# CONFIG_FUSION_SPI is not set
# CONFIG_FUSION_FC is not set
# CONFIG_FUSION_SAS is not set
CONFIG_FUSION_MAX_SGE=128
# CONFIG_FUSION_LOGGING is not set
#
# IEEE 1394 (FireWire) support
#
CONFIG_FIREWIRE=m
CONFIG_FIREWIRE_OHCI=m
# CONFIG_FIREWIRE_SBP2 is not set
# CONFIG_FIREWIRE_NOSY is not set
CONFIG_I2O=m
# CONFIG_I2O_LCT_NOTIFY_ON_CHANGES is not set
# CONFIG_I2O_EXT_ADAPTEC is not set
CONFIG_I2O_CONFIG=m
CONFIG_I2O_CONFIG_OLD_IOCTL=y
CONFIG_I2O_BUS=m
CONFIG_I2O_BLOCK=m
CONFIG_I2O_SCSI=m
# CONFIG_I2O_PROC is not set
CONFIG_MACINTOSH_DRIVERS=y
CONFIG_NETDEVICES=y
CONFIG_NET_CORE=y
CONFIG_DUMMY=m
# CONFIG_EQUALIZER is not set
CONFIG_NET_FC=y
CONFIG_MII=m
# CONFIG_IFB is not set
# CONFIG_NET_TEAM is not set
# CONFIG_MACVLAN is not set
# CONFIG_NETCONSOLE is not set
# CONFIG_NETPOLL is not set
# CONFIG_NET_POLL_CONTROLLER is not set
CONFIG_TUN=m
# CONFIG_VETH is not set
CONFIG_VIRTIO_NET=m
# CONFIG_ARCNET is not set
CONFIG_ATM_DRIVERS=y
# CONFIG_ATM_DUMMY is not set
# CONFIG_ATM_LANAI is not set
CONFIG_ATM_ENI=m
# CONFIG_ATM_ENI_DEBUG is not set
# CONFIG_ATM_ENI_TUNE_BURST is not set
# CONFIG_ATM_FIRESTREAM is not set
# CONFIG_ATM_ZATM is not set
CONFIG_ATM_NICSTAR=m
CONFIG_ATM_NICSTAR_USE_SUNI=y
CONFIG_ATM_NICSTAR_USE_IDT77105=y
CONFIG_ATM_IDT77252=m
# CONFIG_ATM_IDT77252_DEBUG is not set
CONFIG_ATM_IDT77252_RCV_ALL=y
CONFIG_ATM_IDT77252_USE_SUNI=y
# CONFIG_ATM_AMBASSADOR is not set
CONFIG_ATM_HORIZON=m
# CONFIG_ATM_HORIZON_DEBUG is not set
# CONFIG_ATM_IA is not set
# CONFIG_ATM_FORE200E is not set
# CONFIG_ATM_HE is not set
# CONFIG_ATM_SOLOS is not set
#
# CAIF transport drivers
#
CONFIG_ETHERNET=y
CONFIG_MDIO=m
# CONFIG_NET_VENDOR_3COM is not set
# CONFIG_NET_VENDOR_ADAPTEC is not set
# CONFIG_NET_VENDOR_ALTEON is not set
# CONFIG_NET_VENDOR_AMD is not set
# CONFIG_NET_VENDOR_ATHEROS is not set
CONFIG_NET_CADENCE=y
# CONFIG_ARM_AT91_ETHER is not set
# CONFIG_MACB is not set
CONFIG_NET_VENDOR_BROADCOM=y
CONFIG_B44=m
CONFIG_B44_PCI_AUTOSELECT=y
CONFIG_B44_PCICORE_AUTOSELECT=y
CONFIG_B44_PCI=y
CONFIG_BNX2=m
CONFIG_CNIC=m
CONFIG_TIGON3=m
CONFIG_BNX2X=m
# CONFIG_NET_VENDOR_BROCADE is not set
CONFIG_NET_CALXEDA_XGMAC=m
# CONFIG_NET_VENDOR_CHELSIO is not set
# CONFIG_DNET is not set
CONFIG_NET_VENDOR_DEC=y
# CONFIG_NET_TULIP is not set
# CONFIG_NET_VENDOR_DLINK is not set
CONFIG_NET_VENDOR_EMULEX=y
CONFIG_BE2NET=m
# CONFIG_NET_VENDOR_EXAR is not set
CONFIG_NET_VENDOR_FUJITSU=y
CONFIG_PCMCIA_FMVJ18X=m
# CONFIG_NET_VENDOR_HP is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_IP1000 is not set
CONFIG_JME=m
CONFIG_NET_VENDOR_MARVELL=y
# CONFIG_SKGE is not set
CONFIG_SKY2=m
CONFIG_SKY2_DEBUG=y
CONFIG_NET_VENDOR_MELLANOX=y
CONFIG_MLX4_CORE=m
CONFIG_MLX4_DEBUG=y
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_FEALNX is not set
CONFIG_NET_VENDOR_NATSEMI=y
CONFIG_NATSEMI=m
# CONFIG_NS83820 is not set
CONFIG_NET_VENDOR_8390=y
CONFIG_PCMCIA_AXNET=m
# CONFIG_NE2K_PCI is not set
CONFIG_PCMCIA_PCNET=m
CONFIG_NET_VENDOR_NVIDIA=y
CONFIG_FORCEDETH=m
CONFIG_NET_VENDOR_OKI=y
CONFIG_PCH_GBE=m
CONFIG_ETHOC=m
CONFIG_NET_PACKET_ENGINE=y
# CONFIG_HAMACHI is not set
CONFIG_YELLOWFIN=m
CONFIG_NET_VENDOR_QLOGIC=y
CONFIG_QLA3XXX=m
# CONFIG_QLCNIC is not set
# CONFIG_QLGE is not set
# CONFIG_NETXEN_NIC is not set
# CONFIG_NET_VENDOR_REALTEK is not set
CONFIG_NET_VENDOR_RDC=y
CONFIG_R6040=m
# CONFIG_NET_VENDOR_SEEQ is not set
CONFIG_NET_VENDOR_SILAN=y
CONFIG_SC92031=m
# CONFIG_NET_VENDOR_SIS is not set
CONFIG_NET_VENDOR_SMSC=y
CONFIG_PCMCIA_SMC91C92=m
CONFIG_EPIC100=m
# CONFIG_SMSC9420 is not set
# CONFIG_NET_VENDOR_STMICRO is not set
# CONFIG_NET_VENDOR_SUN is not set
CONFIG_NET_VENDOR_TEHUTI=y
CONFIG_TEHUTI=m
# CONFIG_NET_VENDOR_TI is not set
# CONFIG_NET_VENDOR_VIA is not set
CONFIG_NET_VENDOR_WIZNET=y
# CONFIG_WIZNET_W5100 is not set
# CONFIG_WIZNET_W5300 is not set
CONFIG_NET_VENDOR_XIRCOM=y
CONFIG_PCMCIA_XIRC2PS=m
# CONFIG_FDDI is not set
# CONFIG_NET_SB1000 is not set
CONFIG_PHYLIB=m
#
# MII PHY device drivers
#
# CONFIG_AT803X_PHY is not set
CONFIG_AMD_PHY=m
# CONFIG_MARVELL_PHY is not set
# CONFIG_DAVICOM_PHY is not set
CONFIG_QSEMI_PHY=m
# CONFIG_LXT_PHY is not set
# CONFIG_CICADA_PHY is not set
CONFIG_VITESSE_PHY=m
CONFIG_SMSC_PHY=m
CONFIG_BROADCOM_PHY=m
CONFIG_BCM87XX_PHY=m
CONFIG_ICPLUS_PHY=m
CONFIG_REALTEK_PHY=m
# CONFIG_NATIONAL_PHY is not set
# CONFIG_STE10XP is not set
CONFIG_LSI_ET1011C_PHY=m
# CONFIG_MICREL_PHY is not set
CONFIG_MDIO_BITBANG=m
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
# CONFIG_PPP_DEFLATE is not set
# CONFIG_PPP_FILTER is not set
# CONFIG_PPP_MPPE is not set
CONFIG_PPP_MULTILINK=y
# CONFIG_PPPOATM is not set
# CONFIG_PPPOE is not set
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
CONFIG_SLIP=m
CONFIG_SLHC=m
# CONFIG_SLIP_COMPRESSED is not set
# CONFIG_SLIP_SMART is not set
# CONFIG_SLIP_MODE_SLIP6 is not set
#
# USB Network Adapters
#
# CONFIG_USB_CATC is not set
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
CONFIG_USB_RTL8150=m
# CONFIG_USB_USBNET is not set
CONFIG_USB_HSO=m
CONFIG_USB_IPHETH=m
CONFIG_WLAN=y
CONFIG_PCMCIA_RAYCS=m
# CONFIG_AIRO is not set
CONFIG_ATMEL=m
# CONFIG_PCI_ATMEL is not set
CONFIG_PCMCIA_ATMEL=m
CONFIG_AIRO_CS=m
CONFIG_PCMCIA_WL3501=m
# CONFIG_PRISM54 is not set
CONFIG_USB_ZD1201=m
CONFIG_HOSTAP=m
# CONFIG_HOSTAP_FIRMWARE is not set
CONFIG_HOSTAP_PLX=m
# CONFIG_HOSTAP_PCI is not set
# CONFIG_HOSTAP_CS is not set
# CONFIG_WL_TI is not set
#
# Enable WiMAX (Networking options) to see the WiMAX drivers
#
# CONFIG_WAN is not set
# CONFIG_IEEE802154_DRIVERS is not set
CONFIG_ISDN=y
CONFIG_ISDN_I4L=m
CONFIG_ISDN_AUDIO=y
# CONFIG_ISDN_TTY_FAX is not set
#
# ISDN feature submodules
#
CONFIG_ISDN_DRV_LOOP=m
CONFIG_ISDN_DIVERSION=m
#
# ISDN4Linux hardware drivers
#
#
# Passive cards
#
CONFIG_ISDN_DRV_HISAX=m
#
# D-channel protocol features
#
CONFIG_HISAX_EURO=y
CONFIG_DE_AOC=y
# CONFIG_HISAX_NO_SENDCOMPLETE is not set
# CONFIG_HISAX_NO_LLC is not set
CONFIG_HISAX_NO_KEYPAD=y
CONFIG_HISAX_1TR6=y
CONFIG_HISAX_NI1=y
CONFIG_HISAX_MAX_CARDS=8
#
# HiSax supported cards
#
# CONFIG_HISAX_16_3 is not set
CONFIG_HISAX_TELESPCI=y
CONFIG_HISAX_S0BOX=y
CONFIG_HISAX_FRITZPCI=y
# CONFIG_HISAX_AVM_A1_PCMCIA is not set
# CONFIG_HISAX_ELSA is not set
CONFIG_HISAX_DIEHLDIVA=y
CONFIG_HISAX_SEDLBAUER=y
# CONFIG_HISAX_NETJET is not set
CONFIG_HISAX_NETJET_U=y
# CONFIG_HISAX_NICCY is not set
# CONFIG_HISAX_BKM_A4T is not set
# CONFIG_HISAX_SCT_QUADRO is not set
# CONFIG_HISAX_GAZEL is not set
# CONFIG_HISAX_HFC_PCI is not set
# CONFIG_HISAX_W6692 is not set
CONFIG_HISAX_HFC_SX=y
CONFIG_HISAX_DEBUG=y
#
# HiSax PCMCIA card service modules
#
# CONFIG_HISAX_SEDLBAUER_CS is not set
# CONFIG_HISAX_AVM_A1_CS is not set
#
# HiSax sub driver modules
#
CONFIG_HISAX_ST5481=m
# CONFIG_HISAX_HFCUSB is not set
CONFIG_HISAX_HFC4S8S=m
# CONFIG_HISAX_FRITZ_PCIPNP is not set
#
# Active cards
#
# CONFIG_ISDN_CAPI is not set
# CONFIG_ISDN_DRV_GIGASET is not set
# CONFIG_HYSDN is not set
# CONFIG_MISDN is not set
CONFIG_ISDN_HDLC=m
#
# Input device support
#
# CONFIG_INPUT is not set
#
# Hardware I/O ports
#
# CONFIG_SERIO is not set
# CONFIG_GAMEPORT is not set
#
# Character devices
#
# CONFIG_VT is not set
CONFIG_UNIX98_PTYS=y
CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
CONFIG_LEGACY_PTYS=y
CONFIG_LEGACY_PTY_COUNT=256
CONFIG_SERIAL_NONSTANDARD=y
# CONFIG_ROCKETPORT is not set
# CONFIG_CYCLADES is not set
# CONFIG_MOXA_INTELLIO is not set
# CONFIG_MOXA_SMARTIO is not set
CONFIG_SYNCLINK=m
# CONFIG_SYNCLINKMP is not set
CONFIG_SYNCLINK_GT=m
CONFIG_NOZOMI=m
CONFIG_ISI=m
# CONFIG_N_HDLC is not set
# CONFIG_N_GSM is not set
# CONFIG_TRACE_SINK is not set
# CONFIG_DEVKMEM is not set
# CONFIG_STALDRV is not set
#
# Serial drivers
#
# CONFIG_SERIAL_8250 is not set
CONFIG_FIX_EARLYCON_MEM=y
#
# Non-8250 serial port support
#
# CONFIG_SERIAL_MFD_HSU is not set
CONFIG_SERIAL_CORE=m
CONFIG_SERIAL_JSM=m
# CONFIG_SERIAL_SCCNXP is not set
# CONFIG_SERIAL_TIMBERDALE is not set
# CONFIG_SERIAL_ALTERA_JTAGUART is not set
# CONFIG_SERIAL_ALTERA_UART is not set
# CONFIG_SERIAL_PCH_UART is not set
# CONFIG_SERIAL_XILINX_PS_UART is not set
CONFIG_SERIAL_ARC=m
CONFIG_SERIAL_ARC_NR_PORTS=1
CONFIG_TTY_PRINTK=y
# CONFIG_VIRTIO_CONSOLE is not set
# CONFIG_IPMI_HANDLER is not set
# CONFIG_HW_RANDOM is not set
# CONFIG_NVRAM is not set
CONFIG_R3964=m
CONFIG_APPLICOM=m
#
# PCMCIA character devices
#
# CONFIG_SYNCLINK_CS is not set
# CONFIG_CARDMAN_4000 is not set
# CONFIG_CARDMAN_4040 is not set
CONFIG_IPWIRELESS=m
# CONFIG_MWAVE is not set
# CONFIG_RAW_DRIVER is not set
# CONFIG_HPET is not set
# CONFIG_HANGCHECK_TIMER is not set
# CONFIG_TCG_TPM is not set
CONFIG_TELCLOCK=m
CONFIG_DEVPORT=y
# CONFIG_I2C is not set
# CONFIG_SPI is not set
CONFIG_HSI=m
CONFIG_HSI_BOARDINFO=y
#
# HSI clients
#
CONFIG_HSI_CHAR=m
#
# PPS support
#
CONFIG_PPS=m
CONFIG_PPS_DEBUG=y
# CONFIG_NTP_PPS is not set
#
# PPS clients support
#
# CONFIG_PPS_CLIENT_KTIMER is not set
CONFIG_PPS_CLIENT_LDISC=m
# CONFIG_PPS_CLIENT_GPIO is not set
#
# PPS generators support
#
#
# PTP clock support
#
CONFIG_PTP_1588_CLOCK=m
#
# Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
#
# CONFIG_PTP_1588_CLOCK_PCH is not set
CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
# CONFIG_GPIOLIB is not set
CONFIG_W1=m
#
# 1-wire Bus Masters
#
# CONFIG_W1_MASTER_MATROX is not set
CONFIG_W1_MASTER_DS2490=m
# CONFIG_W1_MASTER_DS1WM is not set
# CONFIG_HDQ_MASTER_OMAP is not set
#
# 1-wire Slaves
#
# CONFIG_W1_SLAVE_THERM is not set
CONFIG_W1_SLAVE_SMEM=m
# CONFIG_W1_SLAVE_DS2408 is not set
# CONFIG_W1_SLAVE_DS2423 is not set
# CONFIG_W1_SLAVE_DS2431 is not set
CONFIG_W1_SLAVE_DS2433=m
CONFIG_W1_SLAVE_DS2433_CRC=y
CONFIG_W1_SLAVE_DS2760=m
# CONFIG_W1_SLAVE_DS2780 is not set
# CONFIG_W1_SLAVE_DS2781 is not set
# CONFIG_W1_SLAVE_DS28E04 is not set
# CONFIG_W1_SLAVE_BQ27000 is not set
CONFIG_POWER_SUPPLY=y
# CONFIG_POWER_SUPPLY_DEBUG is not set
CONFIG_PDA_POWER=m
# CONFIG_GENERIC_ADC_BATTERY is not set
# CONFIG_TEST_POWER is not set
CONFIG_BATTERY_DS2760=m
# CONFIG_BATTERY_DS2780 is not set
# CONFIG_BATTERY_DS2781 is not set
CONFIG_BATTERY_BQ27x00=m
# CONFIG_BATTERY_BQ27X00_PLATFORM is not set
CONFIG_CHARGER_ISP1704=m
CONFIG_CHARGER_MAX8903=m
CONFIG_CHARGER_MANAGER=y
# CONFIG_POWER_AVS is not set
CONFIG_HWMON=m
CONFIG_HWMON_VID=m
# CONFIG_HWMON_DEBUG_CHIP is not set
#
# Native drivers
#
# CONFIG_SENSORS_ABITUGURU is not set
# CONFIG_SENSORS_ABITUGURU3 is not set
CONFIG_SENSORS_K8TEMP=m
CONFIG_SENSORS_K10TEMP=m
# CONFIG_SENSORS_FAM15H_POWER is not set
# CONFIG_SENSORS_I5K_AMB is not set
# CONFIG_SENSORS_F71805F is not set
CONFIG_SENSORS_F71882FG=m
CONFIG_SENSORS_CORETEMP=m
CONFIG_SENSORS_IT87=m
CONFIG_SENSORS_MAX197=m
CONFIG_SENSORS_NTC_THERMISTOR=m
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_PC87427 is not set
CONFIG_SENSORS_SIS5595=m
CONFIG_SENSORS_SMSC47M1=m
# CONFIG_SENSORS_SMSC47B397 is not set
# CONFIG_SENSORS_SCH56XX_COMMON is not set
CONFIG_SENSORS_VIA_CPUTEMP=m
CONFIG_SENSORS_VIA686A=m
# CONFIG_SENSORS_VT1211 is not set
# CONFIG_SENSORS_VT8231 is not set
CONFIG_SENSORS_W83627HF=m
# CONFIG_SENSORS_W83627EHF is not set
#
# ACPI drivers
#
CONFIG_SENSORS_ACPI_POWER=m
CONFIG_SENSORS_ATK0110=m
CONFIG_THERMAL=m
CONFIG_THERMAL_HWMON=y
# CONFIG_FAIR_SHARE is not set
# CONFIG_STEP_WISE is not set
CONFIG_USER_SPACE=y
# CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE is not set
# CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE is not set
CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE=y
# CONFIG_WATCHDOG is not set
CONFIG_SSB_POSSIBLE=y
#
# Sonics Silicon Backplane
#
CONFIG_SSB=m
CONFIG_SSB_SPROM=y
CONFIG_SSB_PCIHOST_POSSIBLE=y
CONFIG_SSB_PCIHOST=y
# CONFIG_SSB_B43_PCI_BRIDGE is not set
CONFIG_SSB_PCMCIAHOST_POSSIBLE=y
# CONFIG_SSB_PCMCIAHOST is not set
# CONFIG_SSB_SILENT is not set
# CONFIG_SSB_DEBUG is not set
CONFIG_SSB_DRIVER_PCICORE_POSSIBLE=y
CONFIG_SSB_DRIVER_PCICORE=y
CONFIG_BCMA_POSSIBLE=y
#
# Broadcom specific AMBA
#
# CONFIG_BCMA is not set
#
# Multifunction device drivers
#
CONFIG_MFD_CORE=m
CONFIG_MFD_SM501=m
# CONFIG_HTC_PASIC3 is not set
# CONFIG_MFD_TMIO is not set
CONFIG_ABX500_CORE=y
# CONFIG_MFD_CS5535 is not set
CONFIG_LPC_SCH=m
CONFIG_LPC_ICH=m
CONFIG_MFD_RDC321X=m
CONFIG_MFD_JANZ_CMODIO=m
# CONFIG_MFD_VX855 is not set
CONFIG_REGULATOR=y
# CONFIG_REGULATOR_DEBUG is not set
# CONFIG_REGULATOR_DUMMY is not set
CONFIG_REGULATOR_FIXED_VOLTAGE=m
# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set
# CONFIG_REGULATOR_USERSPACE_CONSUMER is not set
CONFIG_MEDIA_SUPPORT=m
#
# Multimedia core support
#
CONFIG_MEDIA_CAMERA_SUPPORT=y
CONFIG_MEDIA_ANALOG_TV_SUPPORT=y
# CONFIG_MEDIA_DIGITAL_TV_SUPPORT is not set
CONFIG_MEDIA_RADIO_SUPPORT=y
# CONFIG_MEDIA_CONTROLLER is not set
CONFIG_VIDEO_DEV=m
CONFIG_VIDEO_V4L2=m
CONFIG_VIDEO_ADV_DEBUG=y
# CONFIG_VIDEO_FIXED_MINOR_RANGES is not set
#
# Media drivers
#
# CONFIG_MEDIA_USB_SUPPORT is not set
# CONFIG_MEDIA_PCI_SUPPORT is not set
CONFIG_V4L_PLATFORM_DRIVERS=y
# CONFIG_V4L_MEM2MEM_DRIVERS is not set
# CONFIG_V4L_TEST_DRIVERS is not set
#
# Supported MMC/SDIO adapters
#
# CONFIG_RADIO_ADAPTERS is not set
CONFIG_MEDIA_SUBDRV_AUTOSELECT=y
#
# Media ancillary drivers (tuners, sensors, i2c, frontends)
#
#
# Audio decoders, processors and mixers
#
#
# RDS decoders
#
#
# Video decoders
#
#
# Video and audio decoders
#
#
# MPEG video encoders
#
#
# Video encoders
#
#
# Camera sensor devices
#
#
# Flash devices
#
#
# Video improvement chips
#
#
# Miscelaneous helper chips
#
#
# Sensors used on soc_camera driver
#
CONFIG_MEDIA_ATTACH=y
#
# Tools to develop new frontends
#
# CONFIG_DVB_DUMMY_FE is not set
#
# Graphics support
#
# CONFIG_AGP is not set
CONFIG_VGA_ARB=y
CONFIG_VGA_ARB_MAX_GPUS=16
# CONFIG_VGA_SWITCHEROO is not set
# CONFIG_DRM is not set
# CONFIG_STUB_POULSBO is not set
# CONFIG_VGASTATE is not set
# CONFIG_VIDEO_OUTPUT_CONTROL is not set
# CONFIG_FB is not set
CONFIG_EXYNOS_VIDEO=y
# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
CONFIG_SOUND=m
# CONFIG_SOUND_OSS_CORE is not set
# CONFIG_SND is not set
# CONFIG_SOUND_PRIME is not set
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB_ARCH_HAS_EHCI=y
CONFIG_USB_ARCH_HAS_XHCI=y
CONFIG_USB_SUPPORT=y
CONFIG_USB_COMMON=m
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB=m
CONFIG_USB_DEBUG=y
# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
#
# Miscellaneous USB options
#
# CONFIG_USB_DYNAMIC_MINORS is not set
# CONFIG_USB_OTG_WHITELIST is not set
CONFIG_USB_OTG_BLACKLIST_HUB=y
CONFIG_USB_MON=m
CONFIG_USB_WUSB=m
# CONFIG_USB_WUSB_CBAF is not set
#
# USB Host Controller Drivers
#
CONFIG_USB_C67X00_HCD=m
CONFIG_USB_XHCI_HCD=m
CONFIG_USB_XHCI_HCD_DEBUGGING=y
# CONFIG_USB_EHCI_HCD is not set
CONFIG_USB_OXU210HP_HCD=m
CONFIG_USB_ISP116X_HCD=m
# CONFIG_USB_ISP1760_HCD is not set
# CONFIG_USB_ISP1362_HCD is not set
CONFIG_USB_OHCI_HCD=m
CONFIG_USB_OHCI_HCD_SSB=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
CONFIG_USB_OHCI_LITTLE_ENDIAN=y
CONFIG_USB_UHCI_HCD=m
# CONFIG_USB_SL811_HCD is not set
CONFIG_USB_R8A66597_HCD=m
CONFIG_USB_WHCI_HCD=m
CONFIG_USB_HWA_HCD=m
CONFIG_USB_HCD_SSB=m
# CONFIG_USB_CHIPIDEA is not set
#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set
CONFIG_USB_WDM=m
# CONFIG_USB_TMC is not set
#
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
#
#
# also be needed; see USB_STORAGE Help for more info
#
CONFIG_USB_STORAGE=m
# CONFIG_USB_STORAGE_DEBUG is not set
CONFIG_USB_STORAGE_REALTEK=m
CONFIG_USB_STORAGE_DATAFAB=m
# CONFIG_USB_STORAGE_FREECOM is not set
CONFIG_USB_STORAGE_ISD200=m
# CONFIG_USB_STORAGE_USBAT is not set
CONFIG_USB_STORAGE_SDDR09=m
# CONFIG_USB_STORAGE_SDDR55 is not set
CONFIG_USB_STORAGE_JUMPSHOT=m
# CONFIG_USB_STORAGE_ALAUDA is not set
CONFIG_USB_STORAGE_KARMA=m
# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
CONFIG_USB_STORAGE_ENE_UB6250=m
CONFIG_USB_UAS=m
#
# USB Imaging devices
#
CONFIG_USB_MDC800=m
CONFIG_USB_MICROTEK=m
#
# USB port drivers
#
# CONFIG_USB_SERIAL is not set
#
# USB Miscellaneous drivers
#
CONFIG_USB_EMI62=m
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_ADUTUX is not set
CONFIG_USB_SEVSEG=m
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
CONFIG_USB_IDMOUSE=m
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
CONFIG_USB_LD=m
CONFIG_USB_TRANCEVIBRATOR=m
# CONFIG_USB_IOWARRIOR is not set
# CONFIG_USB_TEST is not set
# CONFIG_USB_ISIGHTFW is not set
# CONFIG_USB_YUREX is not set
# CONFIG_USB_EZUSB_FX2 is not set
#
# USB Physical Layer drivers
#
CONFIG_OMAP_USB2=m
CONFIG_USB_ATM=m
# CONFIG_USB_SPEEDTOUCH is not set
# CONFIG_USB_CXACRU is not set
CONFIG_USB_UEAGLEATM=m
CONFIG_USB_XUSBATM=m
# CONFIG_USB_GADGET is not set
#
# OTG and related infrastructure
#
CONFIG_USB_OTG_UTILS=y
# CONFIG_NOP_USB_XCEIV is not set
CONFIG_UWB=m
CONFIG_UWB_HWA=m
CONFIG_UWB_WHCI=m
CONFIG_UWB_I1480U=m
# CONFIG_MMC is not set
CONFIG_MEMSTICK=m
# CONFIG_MEMSTICK_DEBUG is not set
#
# MemoryStick drivers
#
CONFIG_MEMSTICK_UNSAFE_RESUME=y
# CONFIG_MSPRO_BLOCK is not set
CONFIG_MS_BLOCK=m
#
# MemoryStick Host Controller Drivers
#
CONFIG_MEMSTICK_TIFM_MS=m
# CONFIG_MEMSTICK_JMICRON_38X is not set
# CONFIG_MEMSTICK_R592 is not set
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=m
#
# LED drivers
#
CONFIG_LEDS_REGULATOR=m
CONFIG_LEDS_INTEL_SS4200=m
CONFIG_LEDS_OT200=m
CONFIG_LEDS_TRIGGERS=y
#
# LED Triggers
#
# CONFIG_LEDS_TRIGGER_TIMER is not set
CONFIG_LEDS_TRIGGER_ONESHOT=m
# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
CONFIG_LEDS_TRIGGER_BACKLIGHT=m
CONFIG_LEDS_TRIGGER_CPU=y
# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
#
# iptables trigger is under Netfilter config (LED target)
#
CONFIG_LEDS_TRIGGER_TRANSIENT=m
# CONFIG_ACCESSIBILITY is not set
CONFIG_INFINIBAND=m
CONFIG_INFINIBAND_USER_MAD=m
CONFIG_INFINIBAND_USER_ACCESS=m
CONFIG_INFINIBAND_USER_MEM=y
CONFIG_INFINIBAND_MTHCA=m
# CONFIG_INFINIBAND_MTHCA_DEBUG is not set
# CONFIG_INFINIBAND_QIB is not set
CONFIG_MLX4_INFINIBAND=m
CONFIG_INFINIBAND_OCRDMA=m
CONFIG_INFINIBAND_SRP=m
# CONFIG_EDAC is not set
CONFIG_RTC_LIB=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_RTC_DEBUG=y
#
# RTC interfaces
#
CONFIG_RTC_INTF_SYSFS=y
CONFIG_RTC_INTF_PROC=y
# CONFIG_RTC_INTF_DEV is not set
CONFIG_RTC_DRV_TEST=m
#
# SPI RTC drivers
#
#
# Platform RTC drivers
#
# CONFIG_RTC_DRV_CMOS is not set
CONFIG_RTC_DRV_DS1286=m
CONFIG_RTC_DRV_DS1511=m
# CONFIG_RTC_DRV_DS1553 is not set
# CONFIG_RTC_DRV_DS1742 is not set
CONFIG_RTC_DRV_STK17TA8=m
CONFIG_RTC_DRV_M48T86=m
CONFIG_RTC_DRV_M48T35=m
CONFIG_RTC_DRV_M48T59=m
CONFIG_RTC_DRV_MSM6242=m
# CONFIG_RTC_DRV_BQ4802 is not set
CONFIG_RTC_DRV_RP5C01=m
# CONFIG_RTC_DRV_V3020 is not set
# CONFIG_RTC_DRV_DS2404 is not set
#
# on-CPU RTC drivers
#
# CONFIG_DMADEVICES is not set
# CONFIG_AUXDISPLAY is not set
CONFIG_UIO=m
# CONFIG_UIO_CIF is not set
# CONFIG_UIO_PDRV is not set
# CONFIG_UIO_PDRV_GENIRQ is not set
CONFIG_UIO_DMEM_GENIRQ=m
# CONFIG_UIO_AEC is not set
# CONFIG_UIO_SERCOS3 is not set
CONFIG_UIO_PCI_GENERIC=m
CONFIG_UIO_NETX=m
CONFIG_VIRTIO=m
#
# Virtio drivers
#
CONFIG_VIRTIO_PCI=m
# CONFIG_VIRTIO_BALLOON is not set
# CONFIG_VIRTIO_MMIO is not set
#
# Microsoft Hyper-V guest support
#
# CONFIG_HYPERV is not set
CONFIG_STAGING=y
# CONFIG_ET131X is not set
CONFIG_SLICOSS=m
# CONFIG_USBIP_CORE is not set
CONFIG_ECHO=m
CONFIG_COMEDI=m
# CONFIG_COMEDI_DEBUG is not set
CONFIG_COMEDI_DEFAULT_BUF_SIZE_KB=2048
CONFIG_COMEDI_DEFAULT_BUF_MAXSIZE_KB=20480
# CONFIG_COMEDI_MISC_DRIVERS is not set
# CONFIG_COMEDI_PCI_DRIVERS is not set
CONFIG_COMEDI_PCMCIA_DRIVERS=y
CONFIG_COMEDI_CB_DAS16_CS=m
CONFIG_COMEDI_DAS08_CS=m
CONFIG_COMEDI_NI_DAQ_700_CS=m
CONFIG_COMEDI_NI_DAQ_DIO24_CS=m
# CONFIG_COMEDI_NI_MIO_CS is not set
# CONFIG_COMEDI_QUATECH_DAQP_CS is not set
CONFIG_COMEDI_USB_DRIVERS=y
CONFIG_COMEDI_DT9812=m
# CONFIG_COMEDI_USBDUX is not set
# CONFIG_COMEDI_USBDUXFAST is not set
CONFIG_COMEDI_USBDUXSIGMA=m
# CONFIG_COMEDI_VMK80XX is not set
CONFIG_COMEDI_8255=m
CONFIG_COMEDI_FC=m
CONFIG_COMEDI_DAS08=m
# CONFIG_ASUS_OLED is not set
# CONFIG_R8187SE is not set
CONFIG_RTL8192U=m
# CONFIG_RTLLIB is not set
# CONFIG_R8712U is not set
# CONFIG_RTS5139 is not set
# CONFIG_TRANZPORT is not set
CONFIG_VT6655=m
# CONFIG_VT6656 is not set
CONFIG_DX_SEP=m
#
# IIO staging drivers
#
# CONFIG_IIO_ST_HWMON is not set
#
# Accelerometers
#
#
# Analog to digital converters
#
#
# Analog digital bi-direction converters
#
#
# Capacitance to digital converters
#
#
# Direct Digital Synthesis
#
#
# Digital gyroscope sensors
#
#
# Network Analyzer, Impedance Converters
#
#
# Inertial measurement units
#
#
# Light sensors
#
#
# Magnetometer sensors
#
#
# Active energy metering IC
#
#
# Resolver to digital converters
#
#
# Triggers - standalone
#
CONFIG_IIO_PERIODIC_RTC_TRIGGER=m
CONFIG_IIO_SYSFS_TRIGGER=m
# CONFIG_IIO_SIMPLE_DUMMY is not set
# CONFIG_ZRAM is not set
CONFIG_ZSMALLOC=m
# CONFIG_WLAGS49_H2 is not set
CONFIG_WLAGS49_H25=m
CONFIG_CRYSTALHD=m
CONFIG_USB_ENESTORAGE=m
# CONFIG_BCM_WIMAX is not set
CONFIG_FT1000=m
CONFIG_FT1000_USB=m
CONFIG_FT1000_PCMCIA=m
#
# Speakup console speech
#
CONFIG_STAGING_MEDIA=y
# CONFIG_VIDEO_DT3155 is not set
#
# Android
#
# CONFIG_ANDROID is not set
# CONFIG_USB_WPAN_HCD is not set
CONFIG_IPACK_BUS=m
CONFIG_BOARD_TPCI200=m
# CONFIG_SERIAL_IPOCTAL is not set
CONFIG_WIMAX_GDM72XX=m
CONFIG_WIMAX_GDM72XX_QOS=y
# CONFIG_WIMAX_GDM72XX_K_MODE is not set
# CONFIG_WIMAX_GDM72XX_WIMAX2 is not set
CONFIG_WIMAX_GDM72XX_USB=y
CONFIG_NET_VENDOR_SILICOM=y
CONFIG_SBYPASS=m
CONFIG_BPCTL=m
CONFIG_CED1401=m
# CONFIG_DGRP is not set
# CONFIG_X86_PLATFORM_DEVICES is not set
#
# Hardware Spinlock drivers
#
CONFIG_CLKEVT_I8253=y
CONFIG_I8253_LOCK=y
CONFIG_CLKBLD_I8253=y
CONFIG_IOMMU_SUPPORT=y
# CONFIG_AMD_IOMMU is not set
#
# Remoteproc drivers (EXPERIMENTAL)
#
# CONFIG_STE_MODEM_RPROC is not set
#
# Rpmsg drivers
#
CONFIG_VIRT_DRIVERS=y
CONFIG_PM_DEVFREQ=y
#
# DEVFREQ Governors
#
# CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND is not set
CONFIG_DEVFREQ_GOV_PERFORMANCE=y
# CONFIG_DEVFREQ_GOV_POWERSAVE is not set
CONFIG_DEVFREQ_GOV_USERSPACE=y
#
# DEVFREQ Drivers
#
CONFIG_EXTCON=y
#
# Extcon Device Drivers
#
CONFIG_EXTCON_ADC_JACK=m
CONFIG_MEMORY=y
CONFIG_IIO=m
# CONFIG_IIO_BUFFER is not set
CONFIG_IIO_TRIGGER=y
CONFIG_IIO_CONSUMERS_PER_TRIGGER=2
#
# Accelerometers
#
#
# Analog to digital converters
#
#
# Amplifiers
#
#
# Light sensors
#
#
# Frequency Synthesizers DDS/PLL
#
#
# Clock Generator/Distribution
#
#
# Phase-Locked Loop (PLL) frequency synthesizers
#
#
# Digital to analog converters
#
#
# Hid Sensor IIO Common
#
#
# Digital gyroscope sensors
#
#
# Magnetometer sensors
#
# CONFIG_VME_BUS is not set
CONFIG_PWM=y
#
# Firmware Drivers
#
# CONFIG_EDD is not set
# CONFIG_FIRMWARE_MEMMAP is not set
# CONFIG_EFI_VARS is not set
# CONFIG_DELL_RBU is not set
# CONFIG_DCDBAS is not set
# CONFIG_DMIID is not set
# CONFIG_DMI_SYSFS is not set
# CONFIG_ISCSI_IBFT_FIND is not set
CONFIG_GOOGLE_FIRMWARE=y
#
# Google Firmware Drivers
#
# CONFIG_GOOGLE_SMI is not set
CONFIG_GOOGLE_MEMCONSOLE=m
#
# File systems
#
CONFIG_DCACHE_WORD_ACCESS=y
# CONFIG_EXT2_FS is not set
CONFIG_EXT3_FS=m
# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
# CONFIG_EXT3_FS_XATTR is not set
# CONFIG_EXT4_FS is not set
CONFIG_JBD=m
CONFIG_JBD_DEBUG=y
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
CONFIG_XFS_FS=m
CONFIG_XFS_QUOTA=y
CONFIG_XFS_POSIX_ACL=y
# CONFIG_XFS_RT is not set
CONFIG_XFS_DEBUG=y
CONFIG_GFS2_FS=m
# CONFIG_BTRFS_FS is not set
CONFIG_NILFS2_FS=m
CONFIG_FS_POSIX_ACL=y
CONFIG_EXPORTFS=y
# CONFIG_FILE_LOCKING is not set
CONFIG_FSNOTIFY=y
CONFIG_DNOTIFY=y
# CONFIG_INOTIFY_USER is not set
CONFIG_FANOTIFY=y
CONFIG_QUOTA=y
# CONFIG_QUOTA_NETLINK_INTERFACE is not set
CONFIG_PRINT_QUOTA_WARNING=y
CONFIG_QUOTA_DEBUG=y
CONFIG_QUOTA_TREE=m
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
CONFIG_QUOTACTL=y
CONFIG_QUOTACTL_COMPAT=y
# CONFIG_AUTOFS4_FS is not set
# CONFIG_FUSE_FS is not set
#
# Caches
#
CONFIG_FSCACHE=m
# CONFIG_FSCACHE_STATS is not set
CONFIG_FSCACHE_HISTOGRAM=y
CONFIG_FSCACHE_DEBUG=y
# CONFIG_FSCACHE_OBJECT_LIST is not set
CONFIG_CACHEFILES=m
CONFIG_CACHEFILES_DEBUG=y
# CONFIG_CACHEFILES_HISTOGRAM is not set
#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=m
# CONFIG_JOLIET is not set
CONFIG_ZISOFS=y
CONFIG_UDF_FS=m
CONFIG_UDF_NLS=y
#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=m
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
CONFIG_NTFS_FS=m
# CONFIG_NTFS_DEBUG is not set
CONFIG_NTFS_RW=y
#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
# CONFIG_PROC_KCORE is not set
# CONFIG_PROC_SYSCTL is not set
# CONFIG_PROC_PAGE_MONITOR is not set
CONFIG_SYSFS=y
# CONFIG_TMPFS is not set
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
# CONFIG_CONFIGFS_FS is not set
CONFIG_MISC_FILESYSTEMS=y
CONFIG_ADFS_FS=m
CONFIG_ADFS_FS_RW=y
# CONFIG_AFFS_FS is not set
CONFIG_ECRYPT_FS=m
CONFIG_HFS_FS=m
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
CONFIG_BFS_FS=m
CONFIG_EFS_FS=m
# CONFIG_JFFS2_FS is not set
# CONFIG_UBIFS_FS is not set
CONFIG_LOGFS=m
# CONFIG_CRAMFS is not set
# CONFIG_SQUASHFS is not set
CONFIG_VXFS_FS=m
CONFIG_MINIX_FS=m
CONFIG_OMFS_FS=m
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_QNX6FS_FS is not set
CONFIG_ROMFS_FS=m
# CONFIG_ROMFS_BACKED_BY_BLOCK is not set
CONFIG_ROMFS_BACKED_BY_MTD=y
# CONFIG_ROMFS_BACKED_BY_BOTH is not set
CONFIG_ROMFS_ON_MTD=y
CONFIG_PSTORE=y
CONFIG_PSTORE_CONSOLE=y
CONFIG_PSTORE_FTRACE=y
CONFIG_PSTORE_RAM=m
CONFIG_SYSV_FS=m
CONFIG_UFS_FS=m
# CONFIG_UFS_FS_WRITE is not set
CONFIG_UFS_DEBUG=y
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
# CONFIG_NLS_CODEPAGE_437 is not set
CONFIG_NLS_CODEPAGE_737=m
CONFIG_NLS_CODEPAGE_775=m
# CONFIG_NLS_CODEPAGE_850 is not set
# CONFIG_NLS_CODEPAGE_852 is not set
# CONFIG_NLS_CODEPAGE_855 is not set
# CONFIG_NLS_CODEPAGE_857 is not set
# CONFIG_NLS_CODEPAGE_860 is not set
CONFIG_NLS_CODEPAGE_861=m
CONFIG_NLS_CODEPAGE_862=m
# CONFIG_NLS_CODEPAGE_863 is not set
CONFIG_NLS_CODEPAGE_864=m
CONFIG_NLS_CODEPAGE_865=m
CONFIG_NLS_CODEPAGE_866=m
# CONFIG_NLS_CODEPAGE_869 is not set
CONFIG_NLS_CODEPAGE_936=m
CONFIG_NLS_CODEPAGE_950=m
# CONFIG_NLS_CODEPAGE_932 is not set
CONFIG_NLS_CODEPAGE_949=m
# CONFIG_NLS_CODEPAGE_874 is not set
CONFIG_NLS_ISO8859_8=m
# CONFIG_NLS_CODEPAGE_1250 is not set
CONFIG_NLS_CODEPAGE_1251=m
CONFIG_NLS_ASCII=m
# CONFIG_NLS_ISO8859_1 is not set
# CONFIG_NLS_ISO8859_2 is not set
CONFIG_NLS_ISO8859_3=m
CONFIG_NLS_ISO8859_4=m
CONFIG_NLS_ISO8859_5=m
CONFIG_NLS_ISO8859_6=m
CONFIG_NLS_ISO8859_7=m
# CONFIG_NLS_ISO8859_9 is not set
# CONFIG_NLS_ISO8859_13 is not set
CONFIG_NLS_ISO8859_14=m
CONFIG_NLS_ISO8859_15=m
# CONFIG_NLS_KOI8_R is not set
CONFIG_NLS_KOI8_U=m
CONFIG_NLS_MAC_ROMAN=m
# CONFIG_NLS_MAC_CELTIC is not set
CONFIG_NLS_MAC_CENTEURO=m
# CONFIG_NLS_MAC_CROATIAN is not set
# CONFIG_NLS_MAC_CYRILLIC is not set
# CONFIG_NLS_MAC_GAELIC is not set
# CONFIG_NLS_MAC_GREEK is not set
# CONFIG_NLS_MAC_ICELAND is not set
# CONFIG_NLS_MAC_INUIT is not set
CONFIG_NLS_MAC_ROMANIAN=m
CONFIG_NLS_MAC_TURKISH=m
# CONFIG_NLS_UTF8 is not set
#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
# CONFIG_PRINTK_TIME is not set
CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4
CONFIG_ENABLE_WARN_DEPRECATED=y
# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FRAME_WARN=2048
# CONFIG_MAGIC_SYSRQ is not set
# CONFIG_STRIP_ASM_SYMS is not set
CONFIG_READABLE_ASM=y
# CONFIG_UNUSED_SYMBOLS is not set
CONFIG_DEBUG_FS=y
CONFIG_HEADERS_CHECK=y
# CONFIG_DEBUG_SECTION_MISMATCH is not set
CONFIG_DEBUG_KERNEL=y
# CONFIG_DEBUG_SHIRQ is not set
# CONFIG_LOCKUP_DETECTOR is not set
# CONFIG_PANIC_ON_OOPS is not set
CONFIG_PANIC_ON_OOPS_VALUE=0
# CONFIG_DETECT_HUNG_TASK is not set
CONFIG_SCHED_DEBUG=y
CONFIG_SCHEDSTATS=y
# CONFIG_TIMER_STATS is not set
# CONFIG_DEBUG_OBJECTS is not set
CONFIG_SLUB_STATS=y
CONFIG_HAVE_DEBUG_KMEMLEAK=y
# CONFIG_DEBUG_KMEMLEAK is not set
# CONFIG_DEBUG_PREEMPT is not set
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_DEBUG_PI_LIST=y
# CONFIG_RT_MUTEX_TESTER is not set
# CONFIG_DEBUG_SPINLOCK is not set
CONFIG_DEBUG_MUTEXES=y
# CONFIG_DEBUG_LOCK_ALLOC is not set
# CONFIG_PROVE_LOCKING is not set
CONFIG_PROVE_RCU_DELAY=y
# CONFIG_SPARSE_RCU_POINTER is not set
# CONFIG_LOCK_STAT is not set
CONFIG_TRACE_IRQFLAGS=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
CONFIG_STACKTRACE=y
CONFIG_DEBUG_STACK_USAGE=y
CONFIG_DEBUG_KOBJECT=y
# CONFIG_DEBUG_INFO is not set
CONFIG_DEBUG_VM=y
CONFIG_DEBUG_VM_RB=y
CONFIG_DEBUG_VIRTUAL=y
CONFIG_DEBUG_WRITECOUNT=y
# CONFIG_DEBUG_MEMORY_INIT is not set
# CONFIG_DEBUG_LIST is not set
CONFIG_TEST_LIST_SORT=y
# CONFIG_DEBUG_SG is not set
# CONFIG_DEBUG_NOTIFIERS is not set
CONFIG_DEBUG_CREDENTIALS=y
CONFIG_ARCH_WANT_FRAME_POINTERS=y
CONFIG_FRAME_POINTER=y
# CONFIG_BOOT_PRINTK_DELAY is not set
# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=21
CONFIG_RCU_TRACE=y
# CONFIG_BACKTRACE_SELF_TEST is not set
CONFIG_DEBUG_BLOCK_EXT_DEVT=y
# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
CONFIG_LKDTM=m
# CONFIG_NOTIFIER_ERROR_INJECTION is not set
# CONFIG_FAULT_INJECTION is not set
CONFIG_LATENCYTOP=y
CONFIG_DEBUG_PAGEALLOC=y
CONFIG_WANT_PAGE_DEBUG_FLAGS=y
CONFIG_PAGE_GUARD=y
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_NOP_TRACER=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST=y
CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
CONFIG_HAVE_FENTRY=y
CONFIG_HAVE_C_RECORDMCOUNT=y
CONFIG_TRACER_MAX_TRACE=y
CONFIG_TRACE_CLOCK=y
CONFIG_RING_BUFFER=y
CONFIG_EVENT_TRACING=y
# CONFIG_EVENT_POWER_TRACING_DEPRECATED is not set
CONFIG_CONTEXT_SWITCH_TRACER=y
CONFIG_RING_BUFFER_ALLOW_SWAP=y
CONFIG_TRACING=y
CONFIG_GENERIC_TRACER=y
CONFIG_TRACING_SUPPORT=y
CONFIG_FTRACE=y
CONFIG_FUNCTION_TRACER=y
CONFIG_FUNCTION_GRAPH_TRACER=y
CONFIG_IRQSOFF_TRACER=y
# CONFIG_PREEMPT_TRACER is not set
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_TRACE_BRANCH_PROFILING=y
# CONFIG_BRANCH_PROFILE_NONE is not set
CONFIG_PROFILE_ANNOTATED_BRANCHES=y
# CONFIG_PROFILE_ALL_BRANCHES is not set
CONFIG_TRACING_BRANCHES=y
CONFIG_BRANCH_TRACER=y
CONFIG_STACK_TRACER=y
# CONFIG_BLK_DEV_IO_TRACE is not set
# CONFIG_UPROBE_EVENT is not set
# CONFIG_PROBE_EVENTS is not set
CONFIG_DYNAMIC_FTRACE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_FTRACE_MCOUNT_RECORD=y
CONFIG_FTRACE_SELFTEST=y
CONFIG_FTRACE_STARTUP_TEST=y
CONFIG_EVENT_TRACE_TEST_SYSCALLS=y
CONFIG_MMIOTRACE=y
# CONFIG_MMIOTRACE_TEST is not set
# CONFIG_RING_BUFFER_BENCHMARK is not set
CONFIG_RBTREE_TEST=m
# CONFIG_INTERVAL_TREE_TEST is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
# CONFIG_FIREWIRE_OHCI_REMOTE_DMA is not set
# CONFIG_BUILD_DOCSRC is not set
# CONFIG_DYNAMIC_DEBUG is not set
# CONFIG_DMA_API_DEBUG is not set
# CONFIG_ATOMIC64_SELFTEST is not set
CONFIG_ASYNC_RAID6_TEST=m
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
CONFIG_HAVE_ARCH_KMEMCHECK=y
# CONFIG_TEST_KSTRTOX is not set
CONFIG_STRICT_DEVMEM=y
# CONFIG_X86_VERBOSE_BOOTUP is not set
CONFIG_EARLY_PRINTK=y
# CONFIG_EARLY_PRINTK_DBGP is not set
# CONFIG_DEBUG_STACKOVERFLOW is not set
CONFIG_X86_PTDUMP=y
# CONFIG_DEBUG_RODATA is not set
CONFIG_DEBUG_SET_MODULE_RONX=y
# CONFIG_DEBUG_NX_TEST is not set
# CONFIG_DEBUG_TLBFLUSH is not set
CONFIG_IOMMU_STRESS=y
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
CONFIG_IO_DELAY_TYPE_NONE=3
# CONFIG_IO_DELAY_0X80 is not set
# CONFIG_IO_DELAY_0XED is not set
# CONFIG_IO_DELAY_UDELAY is not set
CONFIG_IO_DELAY_NONE=y
CONFIG_DEFAULT_IO_DELAY_TYPE=3
# CONFIG_DEBUG_BOOT_PARAMS is not set
CONFIG_CPA_DEBUG=y
CONFIG_OPTIMIZE_INLINING=y
# CONFIG_DEBUG_NMI_SELFTEST is not set
#
# Security options
#
CONFIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
# CONFIG_KEYS_DEBUG_PROC_KEYS is not set
# CONFIG_SECURITY_DMESG_RESTRICT is not set
# CONFIG_SECURITY is not set
# CONFIG_SECURITYFS is not set
CONFIG_DEFAULT_SECURITY_DAC=y
CONFIG_DEFAULT_SECURITY=""
CONFIG_XOR_BLOCKS=m
CONFIG_ASYNC_CORE=m
CONFIG_ASYNC_MEMCPY=m
CONFIG_ASYNC_XOR=m
CONFIG_ASYNC_PQ=m
CONFIG_ASYNC_RAID6_RECOV=m
CONFIG_CRYPTO=y
#
# Crypto core or helper
#
CONFIG_CRYPTO_ALGAPI=y
CONFIG_CRYPTO_ALGAPI2=y
CONFIG_CRYPTO_AEAD=m
CONFIG_CRYPTO_AEAD2=y
CONFIG_CRYPTO_BLKCIPHER=m
CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG=m
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_PCOMP=m
CONFIG_CRYPTO_PCOMP2=y
CONFIG_CRYPTO_MANAGER=m
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_USER is not set
CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
CONFIG_CRYPTO_GF128MUL=m
CONFIG_CRYPTO_NULL=m
CONFIG_CRYPTO_WORKQUEUE=y
CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_AUTHENC=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_ABLK_HELPER_X86=m
CONFIG_CRYPTO_GLUE_HELPER_X86=m
#
# Authenticated Encryption with Associated Data
#
# CONFIG_CRYPTO_CCM is not set
CONFIG_CRYPTO_GCM=m
CONFIG_CRYPTO_SEQIV=m
#
# Block modes
#
CONFIG_CRYPTO_CBC=m
CONFIG_CRYPTO_CTR=m
# CONFIG_CRYPTO_CTS is not set
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_LRW=m
# CONFIG_CRYPTO_PCBC is not set
CONFIG_CRYPTO_XTS=m
#
# Hash modes
#
CONFIG_CRYPTO_HMAC=m
# CONFIG_CRYPTO_XCBC is not set
# CONFIG_CRYPTO_VMAC is not set
#
# Digest
#
CONFIG_CRYPTO_CRC32C=m
CONFIG_CRYPTO_CRC32C_X86_64=y
CONFIG_CRYPTO_CRC32C_INTEL=m
CONFIG_CRYPTO_GHASH=m
CONFIG_CRYPTO_MD4=m
CONFIG_CRYPTO_MD5=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD128=m
# CONFIG_CRYPTO_RMD160 is not set
# CONFIG_CRYPTO_RMD256 is not set
# CONFIG_CRYPTO_RMD320 is not set
CONFIG_CRYPTO_SHA1=m
CONFIG_CRYPTO_SHA1_SSSE3=m
CONFIG_CRYPTO_SHA256=m
CONFIG_CRYPTO_SHA512=y
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL=m
#
# Ciphers
#
CONFIG_CRYPTO_AES=m
CONFIG_CRYPTO_AES_X86_64=m
CONFIG_CRYPTO_AES_NI_INTEL=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_ARC4=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_BLOWFISH_COMMON=m
# CONFIG_CRYPTO_BLOWFISH_X86_64 is not set
# CONFIG_CRYPTO_CAMELLIA is not set
CONFIG_CRYPTO_CAMELLIA_X86_64=m
# CONFIG_CRYPTO_CAST5 is not set
# CONFIG_CRYPTO_CAST5_AVX_X86_64 is not set
CONFIG_CRYPTO_CAST6=m
# CONFIG_CRYPTO_CAST6_AVX_X86_64 is not set
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
# CONFIG_CRYPTO_KHAZAD is not set
CONFIG_CRYPTO_SALSA20=m
# CONFIG_CRYPTO_SALSA20_X86_64 is not set
# CONFIG_CRYPTO_SEED is not set
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SERPENT_SSE2_X86_64=m
# CONFIG_CRYPTO_SERPENT_AVX_X86_64 is not set
# CONFIG_CRYPTO_TEA is not set
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_TWOFISH_COMMON=m
CONFIG_CRYPTO_TWOFISH_X86_64=m
CONFIG_CRYPTO_TWOFISH_X86_64_3WAY=m
CONFIG_CRYPTO_TWOFISH_AVX_X86_64=m
#
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
CONFIG_CRYPTO_ZLIB=m
CONFIG_CRYPTO_LZO=m
#
# Random Number Generation
#
CONFIG_CRYPTO_ANSI_CPRNG=m
# CONFIG_CRYPTO_USER_API_HASH is not set
# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
CONFIG_CRYPTO_HW=y
CONFIG_CRYPTO_DEV_PADLOCK=m
CONFIG_CRYPTO_DEV_PADLOCK_AES=m
# CONFIG_CRYPTO_DEV_PADLOCK_SHA is not set
CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
CONFIG_PUBLIC_KEY_ALGO_RSA=y
CONFIG_X509_CERTIFICATE_PARSER=y
CONFIG_HAVE_KVM=y
CONFIG_VIRTUALIZATION=y
CONFIG_VHOST_NET=m
CONFIG_BINARY_PRINTF=y
#
# Library routines
#
CONFIG_RAID6_PQ=m
CONFIG_BITREVERSE=y
CONFIG_GENERIC_STRNCPY_FROM_USER=y
CONFIG_GENERIC_STRNLEN_USER=y
CONFIG_GENERIC_FIND_FIRST_BIT=y
CONFIG_GENERIC_PCI_IOMAP=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_IO=y
CONFIG_CRC_CCITT=m
CONFIG_CRC16=m
CONFIG_CRC_T10DIF=m
CONFIG_CRC_ITU_T=m
CONFIG_CRC32=y
CONFIG_CRC32_SELFTEST=y
# CONFIG_CRC32_SLICEBY8 is not set
# CONFIG_CRC32_SLICEBY4 is not set
# CONFIG_CRC32_SARWATE is not set
CONFIG_CRC32_BIT=y
# CONFIG_CRC7 is not set
CONFIG_LIBCRC32C=m
CONFIG_CRC8=m
CONFIG_ZLIB_INFLATE=m
CONFIG_ZLIB_DEFLATE=m
CONFIG_LZO_COMPRESS=y
CONFIG_LZO_DECOMPRESS=y
CONFIG_XZ_DEC=m
# CONFIG_XZ_DEC_X86 is not set
CONFIG_XZ_DEC_POWERPC=y
CONFIG_XZ_DEC_IA64=y
CONFIG_XZ_DEC_ARM=y
# CONFIG_XZ_DEC_ARMTHUMB is not set
CONFIG_XZ_DEC_SPARC=y
CONFIG_XZ_DEC_BCJ=y
CONFIG_XZ_DEC_TEST=m
CONFIG_REED_SOLOMON=m
CONFIG_REED_SOLOMON_ENC8=y
CONFIG_REED_SOLOMON_DEC8=y
CONFIG_TEXTSEARCH=y
CONFIG_TEXTSEARCH_KMP=m
CONFIG_TEXTSEARCH_BM=m
CONFIG_TEXTSEARCH_FSM=m
CONFIG_BTREE=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT=y
CONFIG_HAS_DMA=y
CONFIG_DQL=y
CONFIG_NLATTR=y
CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE=y
# CONFIG_AVERAGE is not set
CONFIG_CLZ_TAB=y
# CONFIG_CORDIC is not set
# CONFIG_DDR is not set
CONFIG_MPILIB=y
CONFIG_OID_REGISTRY=y
^ permalink raw reply
* [PATCH v3 6/6] net: calxedaxgmac: ip align receive buffers
From: Rob Herring @ 2012-11-05 16:22 UTC (permalink / raw)
To: netdev, davem; +Cc: eric.dumazet, Rob Herring
In-Reply-To: <1352132544-15809-1-git-send-email-robherring2@gmail.com>
From: Rob Herring <rob.herring@calxeda.com>
On gcc 4.7, we will get alignment traps in the ip stack if we don't align
the ip headers on receive. The h/w can support this, so use ip aligned
allocations.
Cut down the unnecessary padding on the allocation. The buffer can start on
any byte alignment, but the size including the begining offset must be 8
byte aligned. So the h/w buffer size must include the NET_IP_ALIGN offset.
Thanks to Eric Dumazet for the initial patch highlighting the padding issues.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
---
drivers/net/ethernet/calxeda/xgmac.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 362b35e..b407043 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -665,6 +665,7 @@ static void xgmac_rx_refill(struct xgmac_priv *priv)
{
struct xgmac_dma_desc *p;
dma_addr_t paddr;
+ int bufsz = priv->dev->mtu + ETH_HLEN + ETH_FCS_LEN;
while (dma_ring_space(priv->rx_head, priv->rx_tail, DMA_RX_RING_SZ) > 1) {
int entry = priv->rx_head;
@@ -673,13 +674,13 @@ static void xgmac_rx_refill(struct xgmac_priv *priv)
p = priv->dma_rx + entry;
if (priv->rx_skbuff[entry] == NULL) {
- skb = netdev_alloc_skb(priv->dev, priv->dma_buf_sz);
+ skb = netdev_alloc_skb_ip_align(priv->dev, bufsz);
if (unlikely(skb == NULL))
break;
priv->rx_skbuff[entry] = skb;
paddr = dma_map_single(priv->device, skb->data,
- priv->dma_buf_sz, DMA_FROM_DEVICE);
+ bufsz, DMA_FROM_DEVICE);
desc_set_buf_addr(p, paddr, priv->dma_buf_sz);
}
@@ -703,10 +704,10 @@ static int xgmac_dma_desc_rings_init(struct net_device *dev)
unsigned int bfsize;
/* Set the Buffer size according to the MTU;
- * indeed, in case of jumbo we need to bump-up the buffer sizes.
+ * The total buffer size including any IP offset must be a multiple
+ * of 8 bytes.
*/
- bfsize = ALIGN(dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN + 64,
- 64);
+ bfsize = ALIGN(dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN, 8);
netdev_dbg(priv->dev, "mtu [%d] bfsize [%d]\n", dev->mtu, bfsize);
--
1.7.10.4
^ permalink raw reply related
* [PATCH v3 5/6] net: calxedaxgmac: rework transmit ring handling
From: Rob Herring @ 2012-11-05 16:22 UTC (permalink / raw)
To: netdev, davem; +Cc: eric.dumazet, Rob Herring
In-Reply-To: <1352132544-15809-1-git-send-email-robherring2@gmail.com>
From: Rob Herring <rob.herring@calxeda.com>
Only generate tx interrupts on every ring size / 4 descriptors. Move the
netif_stop_queue call to the end of the xmit function rather than
checking at the beginning.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
---
drivers/net/ethernet/calxeda/xgmac.c | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 8263219..362b35e 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -211,7 +211,7 @@
#define DMA_INTR_ENA_TIE 0x00000001 /* Transmit Interrupt */
#define DMA_INTR_NORMAL (DMA_INTR_ENA_NIE | DMA_INTR_ENA_RIE | \
- DMA_INTR_ENA_TUE)
+ DMA_INTR_ENA_TUE | DMA_INTR_ENA_TIE)
#define DMA_INTR_ABNORMAL (DMA_INTR_ENA_AIE | DMA_INTR_ENA_FBE | \
DMA_INTR_ENA_RWE | DMA_INTR_ENA_RSE | \
@@ -374,6 +374,7 @@ struct xgmac_priv {
struct sk_buff **tx_skbuff;
unsigned int tx_head;
unsigned int tx_tail;
+ int tx_irq_cnt;
void __iomem *base;
unsigned int dma_buf_sz;
@@ -886,7 +887,7 @@ static void xgmac_tx_complete(struct xgmac_priv *priv)
}
if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) >
- TX_THRESH)
+ MAX_SKB_FRAGS)
netif_wake_queue(priv->dev);
}
@@ -1057,19 +1058,15 @@ static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev)
struct xgmac_priv *priv = netdev_priv(dev);
unsigned int entry;
int i;
+ u32 irq_flag;
int nfrags = skb_shinfo(skb)->nr_frags;
struct xgmac_dma_desc *desc, *first;
unsigned int desc_flags;
unsigned int len;
dma_addr_t paddr;
- if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) <
- (nfrags + 1)) {
- writel(DMA_INTR_DEFAULT_MASK | DMA_INTR_ENA_TIE,
- priv->base + XGMAC_DMA_INTR_ENA);
- netif_stop_queue(dev);
- return NETDEV_TX_BUSY;
- }
+ priv->tx_irq_cnt = (priv->tx_irq_cnt + 1) & (DMA_TX_RING_SZ/4 - 1);
+ irq_flag = priv->tx_irq_cnt ? 0 : TXDESC_INTERRUPT;
desc_flags = (skb->ip_summed == CHECKSUM_PARTIAL) ?
TXDESC_CSUM_ALL : 0;
@@ -1110,9 +1107,9 @@ static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev)
/* Interrupt on completition only for the latest segment */
if (desc != first)
desc_set_tx_owner(desc, desc_flags |
- TXDESC_LAST_SEG | TXDESC_INTERRUPT);
+ TXDESC_LAST_SEG | irq_flag);
else
- desc_flags |= TXDESC_LAST_SEG | TXDESC_INTERRUPT;
+ desc_flags |= TXDESC_LAST_SEG | irq_flag;
/* Set owner on first desc last to avoid race condition */
wmb();
@@ -1121,6 +1118,9 @@ static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev)
priv->tx_head = dma_ring_incr(entry, DMA_TX_RING_SZ);
writel(1, priv->base + XGMAC_DMA_TX_POLL);
+ if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) <
+ MAX_SKB_FRAGS)
+ netif_stop_queue(dev);
return NETDEV_TX_OK;
}
@@ -1397,7 +1397,7 @@ static irqreturn_t xgmac_interrupt(int irq, void *dev_id)
}
/* TX/RX NORMAL interrupts */
- if (intr_status & (DMA_STATUS_RI | DMA_STATUS_TU)) {
+ if (intr_status & (DMA_STATUS_RI | DMA_STATUS_TU | DMA_STATUS_TI)) {
__raw_writel(DMA_INTR_ABNORMAL, priv->base + XGMAC_DMA_INTR_ENA);
napi_schedule(&priv->napi);
}
--
1.7.10.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).