aboutsummaryrefslogtreecommitdiff
path: root/fs/9p/mux.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/9p/mux.c')
-rw-r--r--fs/9p/mux.c1033
1 files changed, 0 insertions, 1033 deletions
diff --git a/fs/9p/mux.c b/fs/9p/mux.c
deleted file mode 100644
index f4407eb276c..00000000000
--- a/fs/9p/mux.c
+++ /dev/null
@@ -1,1033 +0,0 @@
-/*
- * linux/fs/9p/mux.c
- *
- * Protocol Multiplexer
- *
- * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
- * Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to:
- * Free Software Foundation
- * 51 Franklin Street, Fifth Floor
- * Boston, MA 02111-1301 USA
- *
- */
-
-#include <linux/config.h>
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/poll.h>
-#include <linux/kthread.h>
-#include <linux/idr.h>
-#include <linux/mutex.h>
-
-#include "debug.h"
-#include "v9fs.h"
-#include "9p.h"
-#include "conv.h"
-#include "transport.h"
-#include "mux.h"
-
-#define ERREQFLUSH 1
-#define SCHED_TIMEOUT 10
-#define MAXPOLLWADDR 2
-
-enum {
- Rworksched = 1, /* read work scheduled or running */
- Rpending = 2, /* can read */
- Wworksched = 4, /* write work scheduled or running */
- Wpending = 8, /* can write */
-};
-
-enum {
- None,
- Flushing,
- Flushed,
-};
-
-struct v9fs_mux_poll_task;
-
-struct v9fs_req {
- spinlock_t lock;
- int tag;
- struct v9fs_fcall *tcall;
- struct v9fs_fcall *rcall;
- int err;
- v9fs_mux_req_callback cb;
- void *cba;
- int flush;
- struct list_head req_list;
-};
-
-struct v9fs_mux_data {
- spinlock_t lock;
- struct list_head mux_list;
- struct v9fs_mux_poll_task *poll_task;
- int msize;
- unsigned char *extended;
- struct v9fs_transport *trans;
- struct v9fs_idpool tagpool;
- int err;
- wait_queue_head_t equeue;
- struct list_head req_list;
- struct list_head unsent_req_list;
- struct v9fs_fcall *rcall;
- int rpos;
- char *rbuf;
- int wpos;
- int wsize;
- char *wbuf;
- wait_queue_t poll_wait[MAXPOLLWADDR];
- wait_queue_head_t *poll_waddr[MAXPOLLWADDR];
- poll_table pt;
- struct work_struct rq;
- struct work_struct wq;
- unsigned long wsched;
-};
-
-struct v9fs_mux_poll_task {
- struct task_struct *task;
- struct list_head mux_list;
- int muxnum;
-};
-
-struct v9fs_mux_rpc {
- struct v9fs_mux_data *m;
- int err;
- struct v9fs_fcall *tcall;
- struct v9fs_fcall *rcall;
- wait_queue_head_t wqueue;
-};
-
-static int v9fs_poll_proc(void *);
-static void v9fs_read_work(void *);
-static void v9fs_write_work(void *);
-static void v9fs_pollwait(struct file *filp, wait_queue_head_t * wait_address,
- poll_table * p);
-static u16 v9fs_mux_get_tag(struct v9fs_mux_data *);
-static void v9fs_mux_put_tag(struct v9fs_mux_data *, u16);
-
-static DEFINE_MUTEX(v9fs_mux_task_lock);
-static struct workqueue_struct *v9fs_mux_wq;
-
-static int v9fs_mux_num;
-static int v9fs_mux_poll_task_num;
-static struct v9fs_mux_poll_task v9fs_mux_poll_tasks[100];
-
-int v9fs_mux_global_init(void)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(v9fs_mux_poll_tasks); i++)
- v9fs_mux_poll_tasks[i].task = NULL;
-
- v9fs_mux_wq = create_workqueue("v9fs");
- if (!v9fs_mux_wq)
- return -ENOMEM;
-
- return 0;
-}
-
-void v9fs_mux_global_exit(void)
-{
- destroy_workqueue(v9fs_mux_wq);
-}
-
-/**
- * v9fs_mux_calc_poll_procs - calculates the number of polling procs
- * based on the number of mounted v9fs filesystems.
- *
- * The current implementation returns sqrt of the number of mounts.
- */
-static int v9fs_mux_calc_poll_procs(int muxnum)
-{
- int n;
-
- if (v9fs_mux_poll_task_num)
- n = muxnum / v9fs_mux_poll_task_num +
- (muxnum % v9fs_mux_poll_task_num ? 1 : 0);
- else
- n = 1;
-
- if (n > ARRAY_SIZE(v9fs_mux_poll_tasks))
- n = ARRAY_SIZE(v9fs_mux_poll_tasks);
-
- return n;
-}
-
-static int v9fs_mux_poll_start(struct v9fs_mux_data *m)
-{
- int i, n;
- struct v9fs_mux_poll_task *vpt, *vptlast;
- struct task_struct *pproc;
-
- dprintk(DEBUG_MUX, "mux %p muxnum %d procnum %d\n", m, v9fs_mux_num,
- v9fs_mux_poll_task_num);
- mutex_lock(&v9fs_mux_task_lock);
-
- n = v9fs_mux_calc_poll_procs(v9fs_mux_num + 1);
- if (n > v9fs_mux_poll_task_num) {
- for (i = 0; i < ARRAY_SIZE(v9fs_mux_poll_tasks); i++) {
- if (v9fs_mux_poll_tasks[i].task == NULL) {
- vpt = &v9fs_mux_poll_tasks[i];
- dprintk(DEBUG_MUX, "create proc %p\n", vpt);
- pproc = kthread_create(v9fs_poll_proc, vpt,
- "v9fs-poll");
-
- if (!IS_ERR(pproc)) {
- vpt->task = pproc;
- INIT_LIST_HEAD(&vpt->mux_list);
- vpt->muxnum = 0;
- v9fs_mux_poll_task_num++;
- wake_up_process(vpt->task);
- }
- break;
- }
- }
-
- if (i >= ARRAY_SIZE(v9fs_mux_poll_tasks))
- dprintk(DEBUG_ERROR, "warning: no free poll slots\n");
- }
-
- n = (v9fs_mux_num + 1) / v9fs_mux_poll_task_num +
- ((v9fs_mux_num + 1) % v9fs_mux_poll_task_num ? 1 : 0);
-
- vptlast = NULL;
- for (i = 0; i < ARRAY_SIZE(v9fs_mux_poll_tasks); i++) {
- vpt = &v9fs_mux_poll_tasks[i];
- if (vpt->task != NULL) {
- vptlast = vpt;
- if (vpt->muxnum < n) {
- dprintk(DEBUG_MUX, "put in proc %d\n", i);
- list_add(&m->mux_list, &vpt->mux_list);
- vpt->muxnum++;
- m->poll_task = vpt;
- memset(&m->poll_waddr, 0, sizeof(m->poll_waddr));
- init_poll_funcptr(&m->pt, v9fs_pollwait);
- break;
- }
- }
- }
-
- if (i >= ARRAY_SIZE(v9fs_mux_poll_tasks)) {
- if (vptlast == NULL)
- return -ENOMEM;
-
- dprintk(DEBUG_MUX, "put in proc %d\n", i);
- list_add(&m->mux_list, &vptlast->mux_list);
- vptlast->muxnum++;
- m->poll_task = vptlast;
- memset(&m->poll_waddr, 0, sizeof(m->poll_waddr));
- init_poll_funcptr(&m->pt, v9fs_pollwait);
- }
-
- v9fs_mux_num++;
- mutex_unlock(&v9fs_mux_task_lock);
-
- return 0;
-}
-
-static void v9fs_mux_poll_stop(struct v9fs_mux_data *m)
-{
- int i;
- struct v9fs_mux_poll_task *vpt;
-
- mutex_lock(&v9fs_mux_task_lock);
- vpt = m->poll_task;
- list_del(&m->mux_list);
- for(i = 0; i < ARRAY_SIZE(m->poll_waddr); i++) {
- if (m->poll_waddr[i] != NULL) {
- remove_wait_queue(m->poll_waddr[i], &m->poll_wait[i]);
- m->poll_waddr[i] = NULL;
- }
- }
- vpt->muxnum--;
- if (!vpt->muxnum) {
- dprintk(DEBUG_MUX, "destroy proc %p\n", vpt);
- send_sig(SIGKILL, vpt->task, 1);
- vpt->task = NULL;
- v9fs_mux_poll_task_num--;
- }
- v9fs_mux_num--;
- mutex_unlock(&v9fs_mux_task_lock);
-}
-
-/**
- * v9fs_mux_init - allocate and initialize the per-session mux data
- * Creates the polling task if this is the first session.
- *
- * @trans - transport structure
- * @msize - maximum message size
- * @extended - pointer to the extended flag
- */
-struct v9fs_mux_data *v9fs_mux_init(struct v9fs_transport *trans, int msize,
- unsigned char *extended)
-{
- int i, n;
- struct v9fs_mux_data *m, *mtmp;
-
- dprintk(DEBUG_MUX, "transport %p msize %d\n", trans, msize);
- m = kmalloc(sizeof(struct v9fs_mux_data), GFP_KERNEL);
- if (!m)
- return ERR_PTR(-ENOMEM);
-
- spin_lock_init(&m->lock);
- INIT_LIST_HEAD(&m->mux_list);
- m->msize = msize;
- m->extended = extended;
- m->trans = trans;
- idr_init(&m->tagpool.pool);
- init_MUTEX(&m->tagpool.lock);
- m->err = 0;
- init_waitqueue_head(&m->equeue);
- INIT_LIST_HEAD(&m->req_list);
- INIT_LIST_HEAD(&m->unsent_req_list);
- m->rcall = NULL;
- m->rpos = 0;
- m->rbuf = NULL;
- m->wpos = m->wsize = 0;
- m->wbuf = NULL;
- INIT_WORK(&m->rq, v9fs_read_work, m);
- INIT_WORK(&m->wq, v9fs_write_work, m);
- m->wsched = 0;
- memset(&m->poll_waddr, 0, sizeof(m->poll_waddr));
- m->poll_task = NULL;
- n = v9fs_mux_poll_start(m);
- if (n)
- return ERR_PTR(n);
-
- n = trans->poll(trans, &m->pt);
- if (n & POLLIN) {
- dprintk(DEBUG_MUX, "mux %p can read\n", m);
- set_bit(Rpending, &m->wsched);
- }
-
- if (n & POLLOUT) {
- dprintk(DEBUG_MUX, "mux %p can write\n", m);
- set_bit(Wpending, &m->wsched);
- }
-
- for(i = 0; i < ARRAY_SIZE(m->poll_waddr); i++) {
- if (IS_ERR(m->poll_waddr[i])) {
- v9fs_mux_poll_stop(m);
- mtmp = (void *)m->poll_waddr; /* the error code */
- kfree(m);
- m = mtmp;
- break;
- }
- }
-
- return m;
-}
-
-/**
- * v9fs_mux_destroy - cancels all pending requests and frees mux resources
- */
-void v9fs_mux_destroy(struct v9fs_mux_data *m)
-{
- dprintk(DEBUG_MUX, "mux %p prev %p next %p\n", m,
- m->mux_list.prev, m->mux_list.next);
- v9fs_mux_cancel(m, -ECONNRESET);
-
- if (!list_empty(&m->req_list)) {
- /* wait until all processes waiting on this session exit */
- dprintk(DEBUG_MUX, "mux %p waiting for empty request queue\n",
- m);
- wait_event_timeout(m->equeue, (list_empty(&m->req_list)), 5000);
- dprintk(DEBUG_MUX, "mux %p request queue empty: %d\n", m,
- list_empty(&m->req_list));
- }
-
- v9fs_mux_poll_stop(m);
- m->trans = NULL;
-
- kfree(m);
-}
-
-/**
- * v9fs_pollwait - called by files poll operation to add v9fs-poll task
- * to files wait queue
- */
-static void
-v9fs_pollwait(struct file *filp, wait_queue_head_t * wait_address,
- poll_table * p)
-{
- int i;
- struct v9fs_mux_data *m;
-
- m = container_of(p, struct v9fs_mux_data, pt);
- for(i = 0; i < ARRAY_SIZE(m->poll_waddr); i++)
- if (m->poll_waddr[i] == NULL)
- break;
-
- if (i >= ARRAY_SIZE(m->poll_waddr)) {
- dprintk(DEBUG_ERROR, "not enough wait_address slots\n");
- return;
- }
-
- m->poll_waddr[i] = wait_address;
-
- if (!wait_address) {
- dprintk(DEBUG_ERROR, "no wait_address\n");
- m->poll_waddr[i] = ERR_PTR(-EIO);
- return;
- }
-
- init_waitqueue_entry(&m->poll_wait[i], m->poll_task->task);
- add_wait_queue(wait_address, &m->poll_wait[i]);
-}
-
-/**
- * v9fs_poll_mux - polls a mux and schedules read or write works if necessary
- */
-static void v9fs_poll_mux(struct v9fs_mux_data *m)
-{
- int n;
-
- if (m->err < 0)
- return;
-
- n = m->trans->poll(m->trans, NULL);
- if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) {
- dprintk(DEBUG_MUX, "error mux %p err %d\n", m, n);
- if (n >= 0)
- n = -ECONNRESET;
- v9fs_mux_cancel(m, n);
- }
-
- if (n & POLLIN) {
- set_bit(Rpending, &m->wsched);
- dprintk(DEBUG_MUX, "mux %p can read\n", m);
- if (!test_and_set_bit(Rworksched, &m->wsched)) {
- dprintk(DEBUG_MUX, "schedule read work mux %p\n", m);
- queue_work(v9fs_mux_wq, &m->rq);
- }
- }
-
- if (n & POLLOUT) {
- set_bit(Wpending, &m->wsched);
- dprintk(DEBUG_MUX, "mux %p can write\n", m);
- if ((m->wsize || !list_empty(&m->unsent_req_list))
- && !test_and_set_bit(Wworksched, &m->wsched)) {
- dprintk(DEBUG_MUX, "schedule write work mux %p\n", m);
- queue_work(v9fs_mux_wq, &m->wq);
- }
- }
-}
-
-/**
- * v9fs_poll_proc - polls all v9fs transports for new events and queues
- * the appropriate work to the work queue
- */
-static int v9fs_poll_proc(void *a)
-{
- struct v9fs_mux_data *m, *mtmp;
- struct v9fs_mux_poll_task *vpt;
-
- vpt = a;
- dprintk(DEBUG_MUX, "start %p %p\n", current, vpt);
- allow_signal(SIGKILL);
- while (!kthread_should_stop()) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (signal_pending(current))
- break;
-
- list_for_each_entry_safe(m, mtmp, &vpt->mux_list, mux_list) {
- v9fs_poll_mux(m);
- }
-
- dprintk(DEBUG_MUX, "sleeping...\n");
- schedule_timeout(SCHED_TIMEOUT * HZ);
- }
-
- __set_current_state(TASK_RUNNING);
- dprintk(DEBUG_MUX, "finish\n");
- return 0;
-}
-
-/**
- * v9fs_write_work - called when a transport can send some data
- */
-static void v9fs_write_work(void *a)
-{
- int n, err;
- struct v9fs_mux_data *m;
- struct v9fs_req *req;
-
- m = a;
-
- if (m->err < 0) {
- clear_bit(Wworksched, &m->wsched);
- return;
- }
-
- if (!m->wsize) {
- if (list_empty(&m->unsent_req_list)) {
- clear_bit(Wworksched, &m->wsched);
- return;
- }
-
- spin_lock(&m->lock);
-again:
- req = list_entry(m->unsent_req_list.next, struct v9fs_req,
- req_list);
- list_move_tail(&req->req_list, &m->req_list);
- if (req->err == ERREQFLUSH)
- goto again;
-
- m->wbuf = req->tcall->sdata;
- m->wsize = req->tcall->size;
- m->wpos = 0;
- dump_data(m->wbuf, m->wsize);
- spin_unlock(&m->lock);
- }
-
- dprintk(DEBUG_MUX, "mux %p pos %d size %d\n", m, m->wpos, m->wsize);
- clear_bit(Wpending, &m->wsched);
- err = m->trans->write(m->trans, m->wbuf + m->wpos, m->wsize - m->wpos);
- dprintk(DEBUG_MUX, "mux %p sent %d bytes\n", m, err);
- if (err == -EAGAIN) {
- clear_bit(Wworksched, &m->wsched);
- return;
- }
-
- if (err <= 0)
- goto error;
-
- m->wpos += err;
- if (m->wpos == m->wsize)
- m->wpos = m->wsize = 0;
-
- if (m->wsize == 0 && !list_empty(&m->unsent_req_list)) {
- if (test_and_clear_bit(Wpending, &m->wsched))
- n = POLLOUT;
- else
- n = m->trans->poll(m->trans, NULL);
-
- if (n & POLLOUT) {
- dprintk(DEBUG_MUX, "schedule write work mux %p\n", m);
- queue_work(v9fs_mux_wq, &m->wq);
- } else
- clear_bit(Wworksched, &m->wsched);
- } else
- clear_bit(Wworksched, &m->wsched);
-
- return;
-
- error:
- v9fs_mux_cancel(m, err);
- clear_bit(Wworksched, &m->wsched);
-}
-
-static void process_request(struct v9fs_mux_data *m, struct v9fs_req *req)
-{
- int ecode;
- struct v9fs_str *ename;
-
- if (!req->err && req->rcall->id == RERROR) {
- ecode = req->rcall->params.rerror.errno;
- ename = &req->rcall->params.rerror.error;
-
- dprintk(DEBUG_MUX, "Rerror %.*s\n", ename->len, ename->str);
-
- if (*m->extended)
- req->err = -ecode;
-
- if (!req->err) {
- req->err = v9fs_errstr2errno(ename->str, ename->len);
-
- if (!req->err) { /* string match failed */
- PRINT_FCALL_ERROR("unknown error", req->rcall);
- }
-
- if (!req->err)
- req->err = -ESERVERFAULT;
- }
- } else if (req->tcall && req->rcall->id != req->tcall->id + 1) {
- dprintk(DEBUG_ERROR, "fcall mismatch: expected %d, got %d\n",
- req->tcall->id + 1, req->rcall->id);
- if (!req->err)
- req->err = -EIO;
- }
-}
-
-/**
- * v9fs_read_work - called when there is some data to be read from a transport
- */
-static void v9fs_read_work(void *a)
-{
- int n, err;
- struct v9fs_mux_data *m;
- struct v9fs_req *req, *rptr, *rreq;
- struct v9fs_fcall *rcall;
- char *rbuf;
-
- m = a;
-
- if (m->err < 0)
- return;
-
- rcall = NULL;
- dprintk(DEBUG_MUX, "start mux %p pos %d\n", m, m->rpos);
-
- if (!m->rcall) {
- m->rcall =
- kmalloc(sizeof(struct v9fs_fcall) + m->msize, GFP_KERNEL);
- if (!m->rcall) {
- err = -ENOMEM;
- goto error;
- }
-
- m->rbuf = (char *)m->rcall + sizeof(struct v9fs_fcall);
- m->rpos = 0;
- }
-
- clear_bit(Rpending, &m->wsched);
- err = m->trans->read(m->trans, m->rbuf + m->rpos, m->msize - m->rpos);
- dprintk(DEBUG_MUX, "mux %p got %d bytes\n", m, err);
- if (err == -EAGAIN) {
- clear_bit(Rworksched, &m->wsched);
- return;
- }
-
- if (err <= 0)
- goto error;
-
- m->rpos += err;
- while (m->rpos > 4) {
- n = le32_to_cpu(*(__le32 *) m->rbuf);
- if (n >= m->msize) {
- dprintk(DEBUG_ERROR,
- "requested packet size too big: %d\n", n);
- err = -EIO;
- goto error;
- }
-
- if (m->rpos < n)
- break;
-
- dump_data(m->rbuf, n);
- err =
- v9fs_deserialize_fcall(m->rbuf, n, m->rcall, *m->extended);
- if (err < 0) {
- goto error;
- }
-
- if ((v9fs_debug_level&DEBUG_FCALL) == DEBUG_FCALL) {
- char buf[150];
-
- v9fs_printfcall(buf, sizeof(buf), m->rcall,
- *m->extended);
- printk(KERN_NOTICE ">>> %p %s\n", m, buf);
- }
-
- rcall = m->rcall;
- rbuf = m->rbuf;
- if (m->rpos > n) {
- m->rcall = kmalloc(sizeof(struct v9fs_fcall) + m->msize,
- GFP_KERNEL);
- if (!m->rcall) {
- err = -ENOMEM;
- goto error;
- }
-
- m->rbuf = (char *)m->rcall + sizeof(struct v9fs_fcall);
- memmove(m->rbuf, rbuf + n, m->rpos - n);
- m->rpos -= n;
- } else {
- m->rcall = NULL;
- m->rbuf = NULL;
- m->rpos = 0;
- }
-
- dprintk(DEBUG_MUX, "mux %p fcall id %d tag %d\n", m, rcall->id,
- rcall->tag);
-
- req = NULL;
- spin_lock(&m->lock);
- list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) {
- if (rreq->tag == rcall->tag) {
- req = rreq;
- if (req->flush != Flushing)
- list_del(&req->req_list);
- break;
- }
- }
- spin_unlock(&m->lock);
-
- if (req) {
- req->rcall = rcall;
- process_request(m, req);
-
- if (req->flush != Flushing) {
- if (req->cb)
- (*req->cb) (req, req->cba);
- else
- kfree(req->rcall);
-
- wake_up(&m->equeue);
- }
- } else {
- if (err >= 0 && rcall->id != RFLUSH)
- dprintk(DEBUG_ERROR,
- "unexpected response mux %p id %d tag %d\n",
- m, rcall->id, rcall->tag);
- kfree(rcall);
- }
- }
-
- if (!list_empty(&m->req_list)) {
- if (test_and_clear_bit(Rpending, &m->wsched))
- n = POLLIN;
- else
- n = m->trans->poll(m->trans, NULL);
-
- if (n & POLLIN) {
- dprintk(DEBUG_MUX, "schedule read work mux %p\n", m);
- queue_work(v9fs_mux_wq, &m->rq);
- } else
- clear_bit(Rworksched, &m->wsched);
- } else
- clear_bit(Rworksched, &m->wsched);
-
- return;
-
- error:
- v9fs_mux_cancel(m, err);
- clear_bit(Rworksched, &m->wsched);
-}
-
-/**
- * v9fs_send_request - send 9P request
- * The function can sleep until the request is scheduled for sending.
- * The function can be interrupted. Return from the function is not
- * a guarantee that the request is sent succesfully. Can return errors
- * that can be retrieved by PTR_ERR macros.
- *
- * @m: mux data
- * @tc: request to be sent
- * @cb: callback function to call when response is received
- * @cba: parameter to pass to the callback function
- */
-static struct v9fs_req *v9fs_send_request(struct v9fs_mux_data *m,
- struct v9fs_fcall *tc,
- v9fs_mux_req_callback cb, void *cba)
-{
- int n;
- struct v9fs_req *req;
-
- dprintk(DEBUG_MUX, "mux %p task %p tcall %p id %d\n", m, current,
- tc, tc->id);
- if (m->err < 0)
- return ERR_PTR(m->err);
-
- req = kmalloc(sizeof(struct v9fs_req), GFP_KERNEL);
- if (!req)
- return ERR_PTR(-ENOMEM);
-
- if (tc->id == TVERSION)
- n = V9FS_NOTAG;
- else
- n = v9fs_mux_get_tag(m);
-
- if (n < 0)
- return ERR_PTR(-ENOMEM);
-
- v9fs_set_tag(tc, n);
- if ((v9fs_debug_level&DEBUG_FCALL) == DEBUG_FCALL) {
- char buf[150];
-
- v9fs_printfcall(buf, sizeof(buf), tc, *m->extended);
- printk(KERN_NOTICE "<<< %p %s\n", m, buf);
- }
-
- spin_lock_init(&req->lock);
- req->tag = n;
- req->tcall = tc;
- req->rcall = NULL;
- req->err = 0;
- req->cb = cb;
- req->cba = cba;
- req->flush = None;
-
- spin_lock(&m->lock);
- list_add_tail(&req->req_list, &m->unsent_req_list);
- spin_unlock(&m->lock);
-
- if (test_and_clear_bit(Wpending, &m->wsched))
- n = POLLOUT;
- else
- n = m->trans->poll(m->trans, NULL);
-
- if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
- queue_work(v9fs_mux_wq, &m->wq);
-
- return req;
-}
-
-static void v9fs_mux_free_request(struct v9fs_mux_data *m, struct v9fs_req *req)
-{
- v9fs_mux_put_tag(m, req->tag);
- kfree(req);
-}
-
-static void v9fs_mux_flush_cb(struct v9fs_req *freq, void *a)
-{
- v9fs_mux_req_callback cb;
- int tag;
- struct v9fs_mux_data *m;
- struct v9fs_req *req, *rreq, *rptr;
-
- m = a;
- dprintk(DEBUG_MUX, "mux %p tc %p rc %p err %d oldtag %d\n", m,
- freq->tcall, freq->rcall, freq->err,
- freq->tcall->params.tflush.oldtag);
-
- spin_lock(&m->lock);
- cb = NULL;
- tag = freq->tcall->params.tflush.oldtag;
- req = NULL;
- list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) {
- if (rreq->tag == tag) {
- req = rreq;
- list_del(&req->req_list);
- break;
- }
- }
- spin_unlock(&m->lock);
-
- if (req) {
- spin_lock(&req->lock);
- req->flush = Flushed;
- spin_unlock(&req->lock);
-
- if (req->cb)
- (*req->cb) (req, req->cba);
- else
- kfree(req->rcall);
-
- wake_up(&m->equeue);
- }
-
- kfree(freq->tcall);
- kfree(freq->rcall);
- v9fs_mux_free_request(m, freq);
-}
-
-static int
-v9fs_mux_flush_request(struct v9fs_mux_data *m, struct v9fs_req *req)
-{
- struct v9fs_fcall *fc;
- struct v9fs_req *rreq, *rptr;
-
- dprintk(DEBUG_MUX, "mux %p req %p tag %d\n", m, req, req->tag);
-
- /* if a response was received for a request, do nothing */
- spin_lock(&req->lock);
- if (req->rcall || req->err) {
- spin_unlock(&req->lock);
- dprintk(DEBUG_MUX, "mux %p req %p response already received\n", m, req);
- return 0;
- }
-
- req->flush = Flushing;
- spin_unlock(&req->lock);
-
- spin_lock(&m->lock);
- /* if the request is not sent yet, just remove it from the list */
- list_for_each_entry_safe(rreq, rptr, &m->unsent_req_list, req_list) {
- if (rreq->tag == req->tag) {
- dprintk(DEBUG_MUX, "mux %p req %p request is not sent yet\n", m, req);
- list_del(&rreq->req_list);
- req->flush = Flushed;
- spin_unlock(&m->lock);
- if (req->cb)
- (*req->cb) (req, req->cba);
- return 0;
- }
- }
- spin_unlock(&m->lock);
-
- clear_thread_flag(TIF_SIGPENDING);
- fc = v9fs_create_tflush(req->tag);
- v9fs_send_request(m, fc, v9fs_mux_flush_cb, m);
- return 1;
-}
-
-static void
-v9fs_mux_rpc_cb(struct v9fs_req *req, void *a)
-{
- struct v9fs_mux_rpc *r;
-
- dprintk(DEBUG_MUX, "req %p r %p\n", req, a);
- r = a;
- r->rcall = req->rcall;
- r->err = req->err;
-
- if (req->flush!=None && !req->err)
- r->err = -ERESTARTSYS;
-
- wake_up(&r->wqueue);
-}
-
-/**
- * v9fs_mux_rpc - sends 9P request and waits until a response is available.
- * The function can be interrupted.
- * @m: mux data
- * @tc: request to be sent
- * @rc: pointer where a pointer to the response is stored
- */
-int
-v9fs_mux_rpc(struct v9fs_mux_data *m, struct v9fs_fcall *tc,
- struct v9fs_fcall **rc)
-{
- int err, sigpending;
- unsigned long flags;
- struct v9fs_req *req;
- struct v9fs_mux_rpc r;
-
- r.err = 0;
- r.tcall = tc;
- r.rcall = NULL;
- r.m = m;
- init_waitqueue_head(&r.wqueue);
-
- if (rc)
- *rc = NULL;
-
- sigpending = 0;
- if (signal_pending(current)) {
- sigpending = 1;
- clear_thread_flag(TIF_SIGPENDING);
- }
-
- req = v9fs_send_request(m, tc, v9fs_mux_rpc_cb, &r);
- if (IS_ERR(req)) {
- err = PTR_ERR(req);
- dprintk(DEBUG_MUX, "error %d\n", err);
- return err;
- }
-
- err = wait_event_interruptible(r.wqueue, r.rcall != NULL || r.err < 0);
- if (r.err < 0)
- err = r.err;
-
- if (err == -ERESTARTSYS && m->trans->status == Connected && m->err == 0) {
- if (v9fs_mux_flush_request(m, req)) {
- /* wait until we get response of the flush message */
- do {
- clear_thread_flag(TIF_SIGPENDING);
- err = wait_event_interruptible(r.wqueue,
- r.rcall || r.err);
- } while (!r.rcall && !r.err && err==-ERESTARTSYS &&
- m->trans->status==Connected && !m->err);
- }
- sigpending = 1;
- }
-
- if (sigpending) {
- spin_lock_irqsave(&current->sighand->siglock, flags);
- recalc_sigpending();
- spin_unlock_irqrestore(&current->sighand->siglock, flags);
- }
-
- if (rc)
- *rc = r.rcall;
- else
- kfree(r.rcall);
-
- v9fs_mux_free_request(m, req);
- if (err > 0)
- err = -EIO;
-
- return err;
-}
-
-#if 0
-/**
- * v9fs_mux_rpcnb - sends 9P request without waiting for response.
- * @m: mux data
- * @tc: request to be sent
- * @cb: callback function to be called when response arrives
- * @cba: value to pass to the callback function
- */
-int v9fs_mux_rpcnb(struct v9fs_mux_data *m, struct v9fs_fcall *tc,
- v9fs_mux_req_callback cb, void *a)
-{
- int err;
- struct v9fs_req *req;
-
- req = v9fs_send_request(m, tc, cb, a);
- if (IS_ERR(req)) {
- err = PTR_ERR(req);
- dprintk(DEBUG_MUX, "error %d\n", err);
- return PTR_ERR(req);
- }
-
- dprintk(DEBUG_MUX, "mux %p tc %p tag %d\n", m, tc, req->tag);
- return 0;
-}
-#endif /* 0 */
-
-/**
- * v9fs_mux_cancel - cancel all pending requests with error
- * @m: mux data
- * @err: error code
- */
-void v9fs_mux_cancel(struct v9fs_mux_data *m, int err)
-{
- struct v9fs_req *req, *rtmp;
- LIST_HEAD(cancel_list);
-
- dprintk(DEBUG_ERROR, "mux %p err %d\n", m, err);
- m->err = err;
- spin_lock(&m->lock);
- list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
- list_move(&req->req_list, &cancel_list);
- }
- list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) {
- list_move(&req->req_list, &cancel_list);
- }
- spin_unlock(&m->lock);
-
- list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
- list_del(&req->req_list);
- if (!req->err)
- req->err = err;
-
- if (req->cb)
- (*req->cb) (req, req->cba);
- else
- kfree(req->rcall);
- }
-
- wake_up(&m->equeue);
-}
-
-static u16 v9fs_mux_get_tag(struct v9fs_mux_data *m)
-{
- int tag;
-
- tag = v9fs_get_idpool(&m->tagpool);
- if (tag < 0)
- return V9FS_NOTAG;
- else
- return (u16) tag;
-}
-
-static void v9fs_mux_put_tag(struct v9fs_mux_data *m, u16 tag)
-{
- if (tag != V9FS_NOTAG && v9fs_check_idpool(tag, &m->tagpool))
- v9fs_put_idpool(tag, &m->tagpool);
-}
/> -rw-r--r--arch/x86/include/asm/mpspec.h9
-rw-r--r--arch/x86/include/asm/mrst.h81
-rw-r--r--arch/x86/include/asm/mshyperv.h4
-rw-r--r--arch/x86/include/asm/msr.h24
-rw-r--r--arch/x86/include/asm/mutex_64.h30
-rw-r--r--arch/x86/include/asm/mwait.h43
-rw-r--r--arch/x86/include/asm/nmi.h3
-rw-r--r--arch/x86/include/asm/numaq.h171
-rw-r--r--arch/x86/include/asm/page.h1
-rw-r--r--arch/x86/include/asm/page_32.h4
-rw-r--r--arch/x86/include/asm/page_32_types.h2
-rw-r--r--arch/x86/include/asm/page_64_types.h22
-rw-r--r--arch/x86/include/asm/page_types.h5
-rw-r--r--arch/x86/include/asm/paravirt.h34
-rw-r--r--arch/x86/include/asm/paravirt_types.h22
-rw-r--r--arch/x86/include/asm/pci.h43
-rw-r--r--arch/x86/include/asm/percpu.h109
-rw-r--r--arch/x86/include/asm/pgalloc.h11
-rw-r--r--arch/x86/include/asm/pgtable-2level.h59
-rw-r--r--arch/x86/include/asm/pgtable-3level.h3
-rw-r--r--arch/x86/include/asm/pgtable.h65
-rw-r--r--arch/x86/include/asm/pgtable_64.h8
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h4
-rw-r--r--arch/x86/include/asm/pgtable_types.h97
-rw-r--r--arch/x86/include/asm/preempt.h111
-rw-r--r--arch/x86/include/asm/processor.h94
-rw-r--r--arch/x86/include/asm/prom.h5
-rw-r--r--arch/x86/include/asm/proto.h2
-rw-r--r--arch/x86/include/asm/ptrace.h17
-rw-r--r--arch/x86/include/asm/pvclock.h3
-rw-r--r--arch/x86/include/asm/qrwlock.h17
-rw-r--r--arch/x86/include/asm/rmwcc.h41
-rw-r--r--arch/x86/include/asm/segment.h3
-rw-r--r--arch/x86/include/asm/setup.h23
-rw-r--r--arch/x86/include/asm/signal.h6
-rw-r--r--arch/x86/include/asm/simd.h11
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/special_insns.h10
-rw-r--r--arch/x86/include/asm/spinlock.h146
-rw-r--r--arch/x86/include/asm/spinlock_types.h20
-rw-r--r--arch/x86/include/asm/swiotlb.h7
-rw-r--r--arch/x86/include/asm/switch_to.h4
-rw-r--r--arch/x86/include/asm/sync_bitops.h26
-rw-r--r--arch/x86/include/asm/syscall.h13
-rw-r--r--arch/x86/include/asm/syscalls.h6
-rw-r--r--arch/x86/include/asm/sysfb.h98
-rw-r--r--arch/x86/include/asm/thread_info.h62
-rw-r--r--arch/x86/include/asm/timer.h78
-rw-r--r--arch/x86/include/asm/tlbflush.h37
-rw-r--r--arch/x86/include/asm/topology.h26
-rw-r--r--arch/x86/include/asm/trace/exceptions.h52
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h11
-rw-r--r--arch/x86/include/asm/traps.h34
-rw-r--r--arch/x86/include/asm/tsc.h4
-rw-r--r--arch/x86/include/asm/uaccess.h229
-rw-r--r--arch/x86/include/asm/uaccess_32.h29
-rw-r--r--arch/x86/include/asm/uaccess_64.h52
-rw-r--r--arch/x86/include/asm/unistd.h4
-rw-r--r--arch/x86/include/asm/uprobes.h32
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h69
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h73
-rw-r--r--arch/x86/include/asm/vdso.h72
-rw-r--r--arch/x86/include/asm/vgtod.h71
-rw-r--r--arch/x86/include/asm/visws/cobalt.h127
-rw-r--r--arch/x86/include/asm/visws/lithium.h53
-rw-r--r--arch/x86/include/asm/visws/piix4.h107
-rw-r--r--arch/x86/include/asm/visws/sgivw.h5
-rw-r--r--arch/x86/include/asm/vmx.h7
-rw-r--r--arch/x86/include/asm/vvar.h17
-rw-r--r--arch/x86/include/asm/x86_init.h5
-rw-r--r--arch/x86/include/asm/xen/events.h1
-rw-r--r--arch/x86/include/asm/xen/hypercall.h2
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h16
-rw-r--r--arch/x86/include/asm/xen/interface.h3
-rw-r--r--arch/x86/include/asm/xen/page-coherent.h38
-rw-r--r--arch/x86/include/asm/xen/page.h50
-rw-r--r--arch/x86/include/asm/xor_avx.h4
-rw-r--r--arch/x86/include/asm/xsave.h26
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h4
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h32
-rw-r--r--arch/x86/include/uapi/asm/kvm.h6
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h1
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h81
-rw-r--r--arch/x86/include/uapi/asm/sembuf.h10
-rw-r--r--arch/x86/include/uapi/asm/stat.h42
-rw-r--r--arch/x86/include/uapi/asm/vmx.h6
-rw-r--r--arch/x86/include/uapi/asm/vsyscall.h7
-rw-r--r--arch/x86/kernel/Makefile22
-rw-r--r--arch/x86/kernel/acpi/boot.c146
-rw-r--r--arch/x86/kernel/acpi/cstate.c27
-rw-r--r--arch/x86/kernel/acpi/sleep.c11
-rw-r--r--arch/x86/kernel/acpi/sleep.h2
-rw-r--r--arch/x86/kernel/acpi/wakeup_32.S2
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S2
-rw-r--r--arch/x86/kernel/alternative.c169
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/amd_nb.c17
-rw-r--r--arch/x86/kernel/apb_timer.c10
-rw-r--r--arch/x86/kernel/aperture_64.c79
-rw-r--r--arch/x86/kernel/apic/Makefile3
-rw-r--r--arch/x86/kernel/apic/apic.c102
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c9
-rw-r--r--arch/x86/kernel/apic/apic_noop.c4
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c3
-rw-r--r--arch/x86/kernel/apic/es7000_32.c746
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c23
-rw-r--r--arch/x86/kernel/apic/io_apic.c196
-rw-r--r--arch/x86/kernel/apic/ipi.c1
-rw-r--r--arch/x86/kernel/apic/numaq_32.c525
-rw-r--r--arch/x86/kernel/apic/probe_32.c3
-rw-r--r--arch/x86/kernel/apic/summit_32.c552
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c3
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c3
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c101
-rw-r--r--arch/x86/kernel/apm_32.c14
-rw-r--r--arch/x86/kernel/asm-offsets.c1
-rw-r--r--arch/x86/kernel/check.c2
-rw-r--r--arch/x86/kernel/cpu/Makefile3
-rw-r--r--arch/x86/kernel/cpu/amd.c94
-rw-r--r--arch/x86/kernel/cpu/centaur.c281
-rw-r--r--arch/x86/kernel/cpu/common.c83
-rw-r--r--arch/x86/kernel/cpu/cpu.h20
-rw-r--r--arch/x86/kernel/cpu/cyrix.c1
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c15
-rw-r--r--arch/x86/kernel/cpu/intel.c133
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c27
-rw-r--r--arch/x86/kernel/cpu/match.c42
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c15
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c119
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c72
-rw-r--r--arch/x86/kernel/cpu/mcheck/p5.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c22
-rw-r--r--arch/x86/kernel/cpu/mcheck/threshold.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/winchip.c1
-rw-r--r--arch/x86/kernel/cpu/microcode/Makefile7
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c (renamed from arch/x86/kernel/microcode_amd.c)54
-rw-r--r--arch/x86/kernel/cpu/microcode/amd_early.c (renamed from arch/x86/kernel/microcode_amd_early.c)281
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c (renamed from arch/x86/kernel/microcode_core.c)6
-rw-r--r--arch/x86/kernel/cpu/microcode/core_early.c (renamed from arch/x86/kernel/microcode_core_early.c)37
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c (renamed from arch/x86/kernel/microcode_intel.c)2
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_early.c (renamed from arch/x86/kernel/microcode_intel_early.c)10
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_lib.c (renamed from arch/x86/kernel/microcode_intel_lib.c)0
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c115
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event.c116
-rw-r--r--arch/x86/kernel/cpu/perf_event.h44
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c62
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_uncore.c7
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c349
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c262
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c36
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c714
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c974
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h15
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c34
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c48
-rw-r--r--arch/x86/kernel/cpu/proc.c15
-rw-r--r--arch/x86/kernel/cpu/rdrand.c15
-rw-r--r--arch/x86/kernel/cpu/scattered.c2
-rw-r--r--arch/x86/kernel/cpu/transmeta.c1
-rw-r--r--arch/x86/kernel/cpu/umc.c5
-rw-r--r--arch/x86/kernel/cpu/vmware.c8
-rw-r--r--arch/x86/kernel/cpuid.c15
-rw-r--r--arch/x86/kernel/crash.c9
-rw-r--r--arch/x86/kernel/devicetree.c54
-rw-r--r--arch/x86/kernel/doublefault.c1
-rw-r--r--arch/x86/kernel/dumpstack.c20
-rw-r--r--arch/x86/kernel/dumpstack_32.c46
-rw-r--r--arch/x86/kernel/dumpstack_64.c118
-rw-r--r--arch/x86/kernel/e820.c7
-rw-r--r--arch/x86/kernel/early-quirks.c374
-rw-r--r--arch/x86/kernel/early_printk.c9
-rw-r--r--arch/x86/kernel/entry_32.S85
-rw-r--r--arch/x86/kernel/entry_64.S503
-rw-r--r--arch/x86/kernel/espfix_64.c208
-rw-r--r--arch/x86/kernel/ftrace.c204
-rw-r--r--arch/x86/kernel/head32.c6
-rw-r--r--arch/x86/kernel/head64.c6
-rw-r--r--arch/x86/kernel/head_32.S9
-rw-r--r--arch/x86/kernel/head_64.S6
-rw-r--r--arch/x86/kernel/hpet.c20
-rw-r--r--arch/x86/kernel/hw_breakpoint.c6
-rw-r--r--arch/x86/kernel/i386_ksyms_32.c7
-rw-r--r--arch/x86/kernel/i387.c19
-rw-r--r--arch/x86/kernel/i8259.c23
-rw-r--r--arch/x86/kernel/iosf_mbi.c237
-rw-r--r--arch/x86/kernel/irq.c131
-rw-r--r--arch/x86/kernel/irq_32.c103
-rw-r--r--arch/x86/kernel/irq_64.c21
-rw-r--r--arch/x86/kernel/irq_work.c4
-rw-r--r--arch/x86/kernel/irqinit.c4
-rw-r--r--arch/x86/kernel/jump_label.c95
-rw-r--r--arch/x86/kernel/kgdb.c1
-rw-r--r--arch/x86/kernel/kprobes/common.h5
-rw-r--r--arch/x86/kernel/kprobes/core.c149
-rw-r--r--arch/x86/kernel/kprobes/ftrace.c17
-rw-r--r--arch/x86/kernel/kprobes/opt.c145
-rw-r--r--arch/x86/kernel/ksysfs.c340
-rw-r--r--arch/x86/kernel/kvm.c320
-rw-r--r--arch/x86/kernel/kvmclock.c3
-rw-r--r--arch/x86/kernel/ldt.c5
-rw-r--r--arch/x86/kernel/machine_kexec_32.c1
-rw-r--r--arch/x86/kernel/machine_kexec_64.c2
-rw-r--r--arch/x86/kernel/mcount_64.S217
-rw-r--r--arch/x86/kernel/module.c46
-rw-r--r--arch/x86/kernel/msr.c18
-rw-r--r--arch/x86/kernel/nmi.c55
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c18
-rw-r--r--arch/x86/kernel/paravirt.c15
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c2
-rw-r--r--arch/x86/kernel/pci-calgary_64.c31
-rw-r--r--arch/x86/kernel/pci-dma.c13
-rw-r--r--arch/x86/kernel/pci-nommu.c1
-rw-r--r--arch/x86/kernel/pci-swiotlb.c9
-rw-r--r--arch/x86/kernel/preempt.S25
-rw-r--r--arch/x86/kernel/process.c13
-rw-r--r--arch/x86/kernel/process_32.c19
-rw-r--r--arch/x86/kernel/process_64.c23
-rw-r--r--arch/x86/kernel/ptrace.c8
-rw-r--r--arch/x86/kernel/pvclock.c57
-rw-r--r--arch/x86/kernel/quirks.c39
-rw-r--r--arch/x86/kernel/reboot.c371
-rw-r--r--arch/x86/kernel/rtc.c12
-rw-r--r--arch/x86/kernel/setup.c108
-rw-r--r--arch/x86/kernel/signal.c18
-rw-r--r--arch/x86/kernel/smp.c14
-rw-r--r--arch/x86/kernel/smpboot.c97
-rw-r--r--arch/x86/kernel/sys_x86_64.c2
-rw-r--r--arch/x86/kernel/syscall_32.c2
-rw-r--r--arch/x86/kernel/syscall_64.c5
-rw-r--r--arch/x86/kernel/sysfb.c74
-rw-r--r--arch/x86/kernel/sysfb_efi.c214
-rw-r--r--arch/x86/kernel/sysfb_simplefb.c95
-rw-r--r--arch/x86/kernel/tboot.c10
-rw-r--r--arch/x86/kernel/time.c4
-rw-r--r--arch/x86/kernel/topology.c11
-rw-r--r--arch/x86/kernel/traps.c186
-rw-r--r--arch/x86/kernel/tsc.c340
-rw-r--r--arch/x86/kernel/tsc_msr.c127
-rw-r--r--arch/x86/kernel/tsc_sync.c1
-rw-r--r--arch/x86/kernel/uprobes.c842
-rw-r--r--arch/x86/kernel/vmlinux.lds.S17
-rw-r--r--arch/x86/kernel/vsmp_64.c19
-rw-r--r--arch/x86/kernel/vsyscall_64.c64
-rw-r--r--arch/x86/kernel/vsyscall_gtod.c69
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c7
-rw-r--r--arch/x86/kernel/x86_init.c34
-rw-r--r--arch/x86/kernel/xsave.c10
-rw-r--r--arch/x86/kvm/Kconfig3
-rw-r--r--arch/x86/kvm/Makefile2
-rw-r--r--arch/x86/kvm/cpuid.c150
-rw-r--r--arch/x86/kvm/cpuid.h28
-rw-r--r--arch/x86/kvm/emulate.c245
-rw-r--r--arch/x86/kvm/i8254.c18
-rw-r--r--arch/x86/kvm/irq.c1
-rw-r--r--arch/x86/kvm/lapic.c154
-rw-r--r--arch/x86/kvm/lapic.h6
-rw-r--r--arch/x86/kvm/mmu.c442
-rw-r--r--arch/x86/kvm/mmu.h81
-rw-r--r--arch/x86/kvm/mmu_audit.c2
-rw-r--r--arch/x86/kvm/paging_tmpl.h208
-rw-r--r--arch/x86/kvm/pmu.c32
-rw-r--r--arch/x86/kvm/svm.c177
-rw-r--r--arch/x86/kvm/trace.h20
-rw-r--r--arch/x86/kvm/vmx.c1507
-rw-r--r--arch/x86/kvm/x86.c749
-rw-r--r--arch/x86/kvm/x86.h6
-rw-r--r--arch/x86/lguest/boot.c22
-rw-r--r--arch/x86/lib/Makefile4
-rw-r--r--arch/x86/lib/cmdline.c84
-rw-r--r--arch/x86/lib/copy_user_64.S12
-rw-r--r--arch/x86/lib/csum-wrappers_64.c12
-rw-r--r--arch/x86/lib/delay.c1
-rw-r--r--arch/x86/lib/hash.c92
-rw-r--r--arch/x86/lib/memcpy_32.c6
-rw-r--r--arch/x86/lib/misc.c21
-rw-r--r--arch/x86/lib/msr-smp.c62
-rw-r--r--arch/x86/lib/msr.c89
-rw-r--r--arch/x86/lib/thunk_32.S3
-rw-r--r--arch/x86/lib/thunk_64.S3
-rw-r--r--arch/x86/lib/usercopy.c43
-rw-r--r--arch/x86/lib/usercopy_32.c8
-rw-r--r--arch/x86/lib/usercopy_64.c2
-rw-r--r--arch/x86/lib/x86-opcode-map.txt46
-rw-r--r--arch/x86/math-emu/errors.c21
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/dump_pagetables.c118
-rw-r--r--arch/x86/mm/fault.c197
-rw-r--r--arch/x86/mm/gup.c21
-rw-r--r--arch/x86/mm/hugetlbpage.c11
-rw-r--r--arch/x86/mm/init.c152
-rw-r--r--arch/x86/mm/init_32.c5
-rw-r--r--arch/x86/mm/init_64.c61
-rw-r--r--arch/x86/mm/ioremap.c255
-rw-r--r--arch/x86/mm/kmemcheck/kmemcheck.c8
-rw-r--r--arch/x86/mm/kmmio.c1
-rw-r--r--arch/x86/mm/memtest.c2
-rw-r--r--arch/x86/mm/mmap.c6
-rw-r--r--arch/x86/mm/numa.c80
-rw-r--r--arch/x86/mm/numa_32.c2
-rw-r--r--arch/x86/mm/pageattr-test.c3
-rw-r--r--arch/x86/mm/pageattr.c493
-rw-r--r--arch/x86/mm/pgtable.c50
-rw-r--r--arch/x86/mm/pgtable_32.c2
-rw-r--r--arch/x86/mm/srat.c40
-rw-r--r--arch/x86/mm/tlb.c50
-rw-r--r--arch/x86/net/bpf_jit.S79
-rw-r--r--arch/x86/net/bpf_jit_comp.c1416
-rw-r--r--arch/x86/oprofile/backtrace.c4
-rw-r--r--arch/x86/oprofile/nmi_int.c33
-rw-r--r--arch/x86/oprofile/op_model_amd.c24
-rw-r--r--arch/x86/pci/Makefile5
-rw-r--r--arch/x86/pci/acpi.c84
-rw-r--r--arch/x86/pci/amd_bus.c98
-rw-r--r--arch/x86/pci/broadcom_bus.c4
-rw-r--r--arch/x86/pci/bus_numa.c13
-rw-r--r--arch/x86/pci/common.c133
-rw-r--r--arch/x86/pci/fixup.c61
-rw-r--r--arch/x86/pci/i386.c31
-rw-r--r--arch/x86/pci/intel_mid_pci.c (renamed from arch/x86/pci/mrst.c)65
-rw-r--r--arch/x86/pci/irq.c6
-rw-r--r--arch/x86/pci/legacy.c4
-rw-r--r--arch/x86/pci/mmconfig-shared.c1
-rw-r--r--arch/x86/pci/mmconfig_32.c1
-rw-r--r--arch/x86/pci/numaq_32.c165
-rw-r--r--arch/x86/pci/sta2x11-fixup.c6
-rw-r--r--arch/x86/pci/visws.c87
-rw-r--r--arch/x86/pci/xen.c44
-rw-r--r--arch/x86/platform/Makefile3
-rw-r--r--arch/x86/platform/ce4100/ce4100.c1
-rw-r--r--arch/x86/platform/efi/Makefile2
-rw-r--r--arch/x86/platform/efi/early_printk.c236
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c12
-rw-r--r--arch/x86/platform/efi/efi.c824
-rw-r--r--arch/x86/platform/efi/efi_32.c23
-rw-r--r--arch/x86/platform/efi/efi_64.c489
-rw-r--r--arch/x86/platform/efi/efi_stub_64.S271
-rw-r--r--arch/x86/platform/efi/efi_thunk_64.S65
-rw-r--r--arch/x86/platform/geode/alix.c2
-rw-r--r--arch/x86/platform/geode/geos.c2
-rw-r--r--arch/x86/platform/geode/net5501.c2
-rw-r--r--arch/x86/platform/intel-mid/Makefile7
-rw-r--r--arch/x86/platform/intel-mid/device_libs/Makefile23
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bma023.c20
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_emc1403.c43
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c83
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_ipc.c68
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_ipc.h18
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_lis331.c41
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_max3111.c35
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_max7315.c79
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c36
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic.c87
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic.h19
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c47
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c37
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c48
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c49
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c36
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c37
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c54
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c36
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_tca6416.c57
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_wdt.c72
-rw-r--r--arch/x86/platform/intel-mid/early_printk_intel_mid.c (renamed from arch/x86/platform/mrst/early_printk_mrst.c)12
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c217
-rw-r--r--arch/x86/platform/intel-mid/intel_mid_vrtc.c (renamed from arch/x86/platform/mrst/vrtc.c)19
-rw-r--r--arch/x86/platform/intel-mid/intel_mid_weak_decls.h19
-rw-r--r--arch/x86/platform/intel-mid/mfld.c75
-rw-r--r--arch/x86/platform/intel-mid/mrfl.c103
-rw-r--r--arch/x86/platform/intel-mid/sfi.c516
-rw-r--r--arch/x86/platform/iris/iris.c1
-rw-r--r--arch/x86/platform/mrst/Makefile3
-rw-r--r--arch/x86/platform/mrst/mrst.c1052
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-pm.c2
-rw-r--r--arch/x86/platform/olpc/olpc-xo15-sci.c12
-rw-r--r--arch/x86/platform/ts5500/ts5500.c2
-rw-r--r--arch/x86/platform/uv/Makefile2
-rw-r--r--arch/x86/platform/uv/bios_uv.c2
-rw-r--r--arch/x86/platform/uv/tlb_uv.c71
-rw-r--r--arch/x86/platform/uv/uv_irq.c10
-rw-r--r--arch/x86/platform/uv/uv_nmi.c727
-rw-r--r--arch/x86/platform/visws/Makefile1
-rw-r--r--arch/x86/platform/visws/visws_quirks.c608
-rw-r--r--arch/x86/power/cpu.c8
-rw-r--r--arch/x86/power/hibernate_64.c12
-rw-r--r--arch/x86/realmode/init.c26
-rw-r--r--arch/x86/realmode/rm/Makefile19
-rw-r--r--arch/x86/realmode/rm/reboot.S1
-rw-r--r--arch/x86/realmode/rm/trampoline_32.S1
-rw-r--r--arch/x86/realmode/rm/trampoline_64.S1
-rw-r--r--arch/x86/syscalls/Makefile2
-rw-r--r--arch/x86/syscalls/syscall_32.tbl3
-rw-r--r--arch/x86/syscalls/syscall_64.tbl9
-rw-r--r--arch/x86/tools/Makefile2
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk4
-rw-r--r--arch/x86/tools/relocs.c52
-rw-r--r--arch/x86/tools/relocs.h7
-rw-r--r--arch/x86/tools/relocs_common.c16
-rw-r--r--arch/x86/um/Kconfig5
-rw-r--r--arch/x86/um/asm/barrier.h4
-rw-r--r--arch/x86/um/asm/processor_32.h5
-rw-r--r--arch/x86/um/asm/processor_64.h5
-rw-r--r--arch/x86/um/elfcore.c15
-rw-r--r--arch/x86/um/os-Linux/prctl.c2
-rw-r--r--arch/x86/um/sysrq_32.c66
-rw-r--r--arch/x86/um/sysrq_64.c8
-rw-r--r--arch/x86/um/vdso/.gitignore2
-rw-r--r--arch/x86/um/vdso/vma.c2
-rw-r--r--arch/x86/vdso/.gitignore5
-rw-r--r--arch/x86/vdso/Makefile165
-rw-r--r--arch/x86/vdso/vclock_gettime.c265
-rw-r--r--arch/x86/vdso/vdso-fakesections.c21
-rw-r--r--arch/x86/vdso/vdso-layout.lds.S96
-rw-r--r--arch/x86/vdso/vdso.S22
-rw-r--r--arch/x86/vdso/vdso.lds.S9
-rw-r--r--arch/x86/vdso/vdso2c.c185
-rw-r--r--arch/x86/vdso/vdso2c.h318
-rw-r--r--arch/x86/vdso/vdso32-setup.c354
-rw-r--r--arch/x86/vdso/vdso32.S22
-rw-r--r--arch/x86/vdso/vdso32/vclock_gettime.c30
-rw-r--r--arch/x86/vdso/vdso32/vdso-fakesections.c1
-rw-r--r--arch/x86/vdso/vdso32/vdso32.lds.S24
-rw-r--r--arch/x86/vdso/vdsox32.S22
-rw-r--r--arch/x86/vdso/vdsox32.lds.S9
-rw-r--r--arch/x86/vdso/vma.c242
-rw-r--r--arch/x86/xen/Kconfig11
-rw-r--r--arch/x86/xen/enlighten.c171
-rw-r--r--arch/x86/xen/grant-table.c204
-rw-r--r--arch/x86/xen/irq.c38
-rw-r--r--arch/x86/xen/mmu.c339
-rw-r--r--arch/x86/xen/p2m.c352
-rw-r--r--arch/x86/xen/pci-swiotlb-xen.c4
-rw-r--r--arch/x86/xen/platform-pci-unplug.c79
-rw-r--r--arch/x86/xen/setup.c113
-rw-r--r--arch/x86/xen/smp.c112
-rw-r--r--arch/x86/xen/spinlock.c457
-rw-r--r--arch/x86/xen/suspend.c23
-rw-r--r--arch/x86/xen/time.c4
-rw-r--r--arch/x86/xen/xen-asm_32.S25
-rw-r--r--arch/x86/xen/xen-head.S25
-rw-r--r--arch/x86/xen/xen-ops.h20
566 files changed, 29481 insertions, 15603 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b32ebf92b0c..d24887b645d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -16,14 +16,18 @@ config X86_64
def_bool y
depends on 64BIT
select X86_DEV_DMA_OPS
+ select ARCH_USE_CMPXCHG_LOCKREF
### Arch settings
config X86
def_bool y
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+ select ARCH_MIGHT_HAVE_PC_PARPORT
+ select ARCH_MIGHT_HAVE_PC_SERIO
select HAVE_AOUT if X86_32
select HAVE_UNSTABLE_SCHED_CLOCK
- select ARCH_SUPPORTS_NUMA_BALANCING
+ select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
+ select ARCH_SUPPORTS_INT128 if X86_64
select ARCH_WANTS_PROT_NUMA_PROT_NONE
select HAVE_IDE
select HAVE_OPROFILE
@@ -37,8 +41,9 @@ config X86
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARCH_WANT_FRAME_POINTERS
select HAVE_DMA_ATTRS
- select HAVE_DMA_CONTIGUOUS if !SWIOTLB
+ select HAVE_DMA_CONTIGUOUS
select HAVE_KRETPROBES
+ select GENERIC_EARLY_IOREMAP
select HAVE_OPTPROBES
select HAVE_KPROBES_ON_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
@@ -81,8 +86,6 @@ config X86
select HAVE_USER_RETURN_NOTIFIER
select ARCH_BINFMT_ELF_RANDOMIZE_PIE
select HAVE_ARCH_JUMP_LABEL
- select HAVE_TEXT_POKE_SMP
- select HAVE_GENERIC_HARDIRQS
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select SPARSE_IRQ
select GENERIC_FIND_FIRST_BIT
@@ -91,7 +94,6 @@ config X86
select GENERIC_IRQ_SHOW
select GENERIC_CLOCKEVENTS_MIN_ADJUST
select IRQ_FORCED_THREADING
- select USE_GENERIC_SMP_HELPERS if SMP
select HAVE_BPF_JIT if X86_64
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select CLKEVT_I8253
@@ -103,12 +105,12 @@ config X86
select HAVE_ARCH_SECCOMP_FILTER
select BUILDTIME_EXTABLE_SORT
select GENERIC_CMOS_UPDATE
- select HAVE_ARCH_SOFT_DIRTY
+ select HAVE_ARCH_SOFT_DIRTY if X86_64
select CLOCKSOURCE_WATCHDOG
select GENERIC_CLOCKEVENTS
- select ARCH_CLOCKSOURCE_DATA if X86_64
+ select ARCH_CLOCKSOURCE_DATA
select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
- select GENERIC_TIME_VSYSCALL if X86_64
+ select GENERIC_TIME_VSYSCALL
select KTIME_SCALAR if X86_32
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
@@ -119,11 +121,17 @@ config X86
select MODULES_USE_ELF_RELA if X86_64
select CLONE_BACKWARDS if X86_32
select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_QUEUE_RWLOCK
select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
select OLD_SIGACTION if X86_32
select COMPAT_OLD_SIGACTION if IA32_EMULATION
select RTC_LIB
select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
+ select HAVE_CC_STACKPROTECTOR
+ select GENERIC_CPU_AUTOPROBE
+ select HAVE_ARCH_AUDITSYSCALL
+ select ARCH_SUPPORTS_ATOMIC_RMW
config INSTRUCTION_DECODER
def_bool y
@@ -192,9 +200,6 @@ config ARCH_HAS_CPU_RELAX
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
-config ARCH_HAS_CPU_AUTOPROBE
- def_bool y
-
config HAVE_SETUP_PER_CPU_AREA
def_bool y
@@ -255,11 +260,10 @@ config ARCH_HWEIGHT_CFLAGS
default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
-config ARCH_CPU_PROBE_RELEASE
+config ARCH_SUPPORTS_UPROBES
def_bool y
- depends on HOTPLUG_CPU
-config ARCH_SUPPORTS_UPROBES
+config FIX_EARLYCON_MEM
def_bool y
source "init/Kconfig"
@@ -281,13 +285,13 @@ config SMP
bool "Symmetric multi-processing support"
---help---
This enables support for systems with more than one CPU. If you have
- a system with only one CPU, like most personal computers, say N. If
- you have a system with more than one CPU, say Y.
+ a system with only one CPU, say N. If you have a system with more
+ than one CPU, say Y.
- If you say N here, the kernel will run on single and multiprocessor
+ If you say N here, the kernel will run on uni- and multiprocessor
machines, but will use only one CPU of a multiprocessor machine. If
you say Y here, the kernel will run on many, but not all,
- singleprocessor machines. On a singleprocessor machine, the kernel
+ uniprocessor machines. On a uniprocessor machine, the kernel
will run faster if you say N here.
Note that if you say Y here and choose architecture "586" or
@@ -347,12 +351,9 @@ config X86_EXTENDED_PLATFORM
for the following (non-PC) 32 bit x86 platforms:
Goldfish (Android emulator)
AMD Elan
- NUMAQ (IBM/Sequent)
RDC R-321x SoC
SGI 320/540 (Visual Workstation)
STA2X11-based (e.g. Northville)
- Summit/EXA (IBM x440)
- Unisys ES7000 IA32 series
Moorestown MID devices
If you have one of these systems, or if you want to build a
@@ -419,7 +420,6 @@ config X86_UV
config X86_GOLDFISH
bool "Goldfish (Virtual Platform)"
- depends on X86_32
depends on X86_EXTENDED_PLATFORM
---help---
Enable support for the Goldfish virtual platform used primarily
@@ -441,52 +441,38 @@ config X86_INTEL_CE
This option compiles in support for the CE4100 SOC for settop
boxes and media devices.
-config X86_WANT_INTEL_MID
+config X86_INTEL_MID
bool "Intel MID platform support"
depends on X86_32
depends on X86_EXTENDED_PLATFORM
- ---help---
- Select to build a kernel capable of supporting Intel MID platform
- systems which do not have the PCI legacy interfaces (Moorestown,
- Medfield). If you are building for a PC class system say N here.
-
-if X86_WANT_INTEL_MID
-
-config X86_INTEL_MID
- bool
-
-config X86_MDFLD
- bool "Medfield MID platform"
+ depends on X86_PLATFORM_DEVICES
depends on PCI
depends on PCI_GOANY
depends on X86_IO_APIC
- select X86_INTEL_MID
select SFI
+ select I2C
select DW_APB_TIMER
select APB_TIMER
- select I2C
- select SPI
select INTEL_SCU_IPC
- select X86_PLATFORM_DEVICES
select MFD_INTEL_MSIC
---help---
- Medfield is Intel's Low Power Intel Architecture (LPIA) based Moblin
- Internet Device(MID) platform.
- Unlike standard x86 PCs, Medfield does not have many legacy devices
- nor standard legacy replacement devices/features. e.g. Medfield does
- not contain i8259, i8254, HPET, legacy BIOS, most of the io ports.
+ Select to build a kernel capable of supporting Intel MID (Mobile
+ Internet Device) platform systems which do not have the PCI legacy
+ interfaces. If you are building for a PC class system say N here.
-endif
+ Intel MID platforms are based on an Intel processor and chipset which
+ consume less power than most of the x86 derivatives.
config X86_INTEL_LPSS
bool "Intel Low Power Subsystem Support"
depends on ACPI
select COMMON_CLK
+ select PINCTRL
---help---
Select to build support for Intel Low Power Subsystem such as
found on Intel Lynxpoint PCH. Selecting this option enables
- things like clock tree (common clock framework) which are needed
- by the LPSS peripheral drivers.
+ things like clock tree (common clock framework) and pincontrol
+ which are needed by the LPSS peripheral drivers.
config X86_RDC321X
bool "RDC R-321x SoC"
@@ -504,49 +490,22 @@ config X86_32_NON_STANDARD
depends on X86_32 && SMP
depends on X86_EXTENDED_PLATFORM
---help---
- This option compiles in the NUMAQ, Summit, bigsmp, ES7000,
- STA2X11, default subarchitectures. It is intended for a generic
- binary kernel. If you select them all, kernel will probe it
- one by one and will fallback to default.
+ This option compiles in the bigsmp and STA2X11 default
+ subarchitectures. It is intended for a generic binary
+ kernel. If you select them all, kernel will probe it one by
+ one and will fallback to default.
# Alphabetically sorted list of Non standard 32 bit platforms
-config X86_NUMAQ
- bool "NUMAQ (IBM/Sequent)"
- depends on X86_32_NON_STANDARD
- depends on PCI
- select NUMA
- select X86_MPPARSE
- ---help---
- This option is used for getting Linux to run on a NUMAQ (IBM/Sequent)
- NUMA multiquad box. This changes the way that processors are
- bootstrapped, and uses Clustered Logical APIC addressing mode instead
- of Flat Logical. You will need a new lynxer.elf file to flash your
- firmware with - send email to <Martin.Bligh@us.ibm.com>.
-
config X86_SUPPORTS_MEMORY_FAILURE
def_bool y
# MCE code calls memory_failure():
depends on X86_MCE
# On 32-bit this adds too big of NODES_SHIFT and we run out of page flags:
- depends on !X86_NUMAQ
# On 32-bit SPARSEMEM adds too big of SECTIONS_WIDTH:
depends on X86_64 || !SPARSEMEM
select ARCH_SUPPORTS_MEMORY_FAILURE
-config X86_VISWS
- bool "SGI 320/540 (Visual Workstation)"
- depends on X86_32 && PCI && X86_MPPARSE && PCI_GODIRECT
- depends on X86_32_NON_STANDARD
- ---help---
- The SGI Visual Workstation series is an IA32-based workstation
- based on SGI systems chips with some legacy PC hardware attached.
-
- Say Y here to create a kernel to run on the SGI 320 or 540.
-
- A kernel compiled for the Visual Workstation will run on general
- PCs as well. See <file:Documentation/sgi-visws.txt> for details.
-
config STA2X11
bool "STA2X11 Companion Chip Support"
depends on X86_32_NON_STANDARD && PCI
@@ -563,20 +522,6 @@ config STA2X11
option is selected the kernel will still be able to boot on
standard PC machines.
-config X86_SUMMIT
- bool "Summit/EXA (IBM x440)"
- depends on X86_32_NON_STANDARD
- ---help---
- This option is needed for IBM systems that use the Summit/EXA chipset.
- In particular, it is needed for the x440.
-
-config X86_ES7000
- bool "Unisys ES7000 IA32 series"
- depends on X86_32_NON_STANDARD && X86_BIGSMP
- ---help---
- Support for Unisys ES7000 systems. Say 'Y' here if this kernel is
- supposed to run on an IA32-based Unisys ES7000 system.
-
config X86_32_IRIS
tristate "Eurobraille/Iris poweroff module"
depends on X86_32
@@ -632,15 +577,16 @@ config PARAVIRT_DEBUG
config PARAVIRT_SPINLOCKS
bool "Paravirtualization layer for spinlocks"
depends on PARAVIRT && SMP
+ select UNINLINE_SPIN_UNLOCK
---help---
Paravirtualized spinlocks allow a pvops backend to replace the
spinlock implementation with something virtualization-friendly
(for example, block the virtual CPU rather than spinning).
- Unfortunately the downside is an up to 5% performance hit on
- native kernels, with various workloads.
+ It has a minimal impact on native kernels and gives a nice performance
+ benefit on paravirtualized KVM / Xen kernels.
- If you are unsure how to answer this question, answer N.
+ If you are unsure how to answer this question, answer Y.
source "arch/x86/xen/Kconfig"
@@ -656,6 +602,15 @@ config KVM_GUEST
underlying device model, the host provides the guest with
timing infrastructure such as time of day, and system time
+config KVM_DEBUG_FS
+ bool "Enable debug information for KVM Guests in debugfs"
+ depends on KVM_GUEST && DEBUG_FS
+ default n
+ ---help---
+ This option enables collection of various statistics for KVM guest.
+ Statistics are displayed in debugfs filesystem. Enabling this option
+ may incur significant overhead.
+
source "arch/x86/lguest/Kconfig"
config PARAVIRT_TIME_ACCOUNTING
@@ -689,14 +644,6 @@ config MEMTEST
memtest=4, mean do 4 test patterns.
If you are unsure how to answer this question, answer N.
-config X86_SUMMIT_NUMA
- def_bool y
- depends on X86_32 && NUMA && X86_32_NON_STANDARD
-
-config X86_CYCLONE_TIMER
- def_bool y
- depends on X86_SUMMIT
-
source "arch/x86/Kconfig.cpu"
config HPET_TIMER
@@ -738,6 +685,7 @@ config APB_TIMER
# The code disables itself when not needed.
config DMI
default y
+ select DMI_SCAN_MACHINE_NON_EFI_FALLBACK
bool "Enable DMI scanning" if EXPERT
---help---
Enabled scanning of DMI to identify machine quirks. Say Y
@@ -746,20 +694,25 @@ config DMI
BIOS code.
config GART_IOMMU
- bool "GART IOMMU support" if EXPERT
- default y
+ bool "Old AMD GART IOMMU support"
select SWIOTLB
depends on X86_64 && PCI && AMD_NB
---help---
- Support for full DMA access of devices with 32bit memory access only
- on systems with more than 3GB. This is usually needed for USB,
- sound, many IDE/SATA chipsets and some other devices.
- Provides a driver for the AMD Athlon64/Opteron/Turion/Sempron GART
- based hardware IOMMU and a software bounce buffer based IOMMU used
- on Intel systems and as fallback.
- The code is only active when needed (enough memory and limited
- device) unless CONFIG_IOMMU_DEBUG or iommu=force is specified
- too.
+ Provides a driver for older AMD Athlon64/Opteron/Turion/Sempron
+ GART based hardware IOMMUs.
+
+ The GART supports full DMA access for devices with 32-bit access
+ limitations, on systems with more than 3 GB. This is usually needed
+ for USB, sound, many IDE/SATA chipsets and some other devices.
+
+ Newer systems typically have a modern AMD IOMMU, supported via
+ the CONFIG_AMD_IOMMU=y config option.
+
+ In normal configurations this driver is only active when needed:
+ there's more than 3 GB of memory and the system contains a
+ 32-bit limited device.
+
+ If unsure, say Y.
config CALGARY_IOMMU
bool "IBM Calgary IOMMU support"
@@ -815,14 +768,16 @@ config MAXSMP
config NR_CPUS
int "Maximum number of CPUs" if SMP && !MAXSMP
range 2 8 if SMP && X86_32 && !X86_BIGSMP
- range 2 512 if SMP && !MAXSMP
+ range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+ range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
default "1" if !SMP
- default "4096" if MAXSMP
- default "32" if SMP && (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000)
+ default "8192" if MAXSMP
+ default "32" if SMP && X86_BIGSMP
default "8" if SMP
---help---
This allows you to specify the maximum number of CPUs which this
- kernel will support. The maximum supported value is 512 and the
+ kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum
+ supported value is 4096, otherwise the maximum value is 512. The
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
@@ -850,7 +805,7 @@ source "kernel/Kconfig.preempt"
config X86_UP_APIC
bool "Local APIC support on uniprocessors"
- depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+ depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
---help---
A local APIC (Advanced Programmable Interrupt Controller) is an
integrated interrupt controller in the CPU. If you have a single-CPU
@@ -875,15 +830,12 @@ config X86_UP_IOAPIC
config X86_LOCAL_APIC
def_bool y
- depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+ depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
config X86_IO_APIC
def_bool y
- depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
-
-config X86_VISWS_APIC
- def_bool y
- depends on X86_32 && X86_VISWS
+ depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
+ select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
bool "Reroute for broken boot IRQs"
@@ -938,7 +890,7 @@ config X86_ANCIENT_MCE
depends on X86_32 && X86_MCE
---help---
Include support for machine check handling on old Pentium 5 or WinChip
- systems. These typically need to be enabled explicitely on the command
+ systems. These typically need to be enabled explicitly on the command
line.
config X86_MCE_THRESHOLD
@@ -962,10 +914,27 @@ config VM86
default y
depends on X86_32
---help---
- This option is required by programs like DOSEMU to run 16-bit legacy
- code on X86 processors. It also may be needed by software like
- XFree86 to initialize some video cards via BIOS. Disabling this
- option saves about 6k.
+ This option is required by programs like DOSEMU to run
+ 16-bit real mode legacy code on x86 processors. It also may
+ be needed by software like XFree86 to initialize some video
+ cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+ bool "Enable support for 16-bit segments" if EXPERT
+ default y
+ ---help---
+ This option is required by programs like Wine to run 16-bit
+ protected mode legacy code on x86 processors. Disabling
+ this option saves about 300 bytes on i386, or around 6K text
+ plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+ def_bool y
+ depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+ def_bool y
+ depends on X86_16BIT && X86_64
config TOSHIBA
tristate "Toshiba Laptop support"
@@ -1023,6 +992,7 @@ config X86_REBOOTFIXUPS
config MICROCODE
tristate "CPU microcode loading support"
+ depends on CPU_SUP_AMD || CPU_SUP_INTEL
select FW_LOADER
---help---
@@ -1048,9 +1018,9 @@ config MICROCODE_INTEL
This options enables microcode patch loading support for Intel
processors.
- For latest news and information on obtaining all the required
- Intel ingredients for this driver, check:
- <http://www.urbanmyth.org/microcode/>.
+ For the current Intel microcode data package go to
+ <https://downloadcenter.intel.com> and search for
+ 'Linux Processor Microcode Data File'.
config MICROCODE_AMD
bool "AMD microcode loading support"
@@ -1064,10 +1034,6 @@ config MICROCODE_OLD_INTERFACE
def_bool y
depends on MICROCODE
-config MICROCODE_INTEL_LIB
- def_bool y
- depends on MICROCODE_INTEL
-
config MICROCODE_INTEL_EARLY
def_bool n
@@ -1105,13 +1071,11 @@ config X86_CPUID
choice
prompt "High Memory Support"
- default HIGHMEM64G if X86_NUMAQ
default HIGHMEM4G
depends on X86_32
config NOHIGHMEM
bool "off"
- depends on !X86_NUMAQ
---help---
Linux can use up to 64 Gigabytes of physical memory on x86 systems.
However, the address space of 32-bit x86 processors is only 4
@@ -1148,7 +1112,6 @@ config NOHIGHMEM
config HIGHMEM4G
bool "4GB"
- depends on !X86_NUMAQ
---help---
Select this if you have a 32-bit processor and between 1 and 4
gigabytes of physical RAM.
@@ -1240,8 +1203,8 @@ config DIRECT_GBPAGES
config NUMA
bool "Numa Memory Allocation and Scheduler Support"
depends on SMP
- depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI))
- default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
+ depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
+ default y if X86_BIGSMP
---help---
Enable NUMA (Non Uniform Memory Access) support.
@@ -1252,15 +1215,11 @@ config NUMA
For 64-bit this is recommended if the system is Intel Core i7
(or later), AMD Opteron, or EM64T NUMA.
- For 32-bit this is only needed on (rare) 32-bit-only platforms
- that support NUMA topologies, such as NUMAQ / Summit, or if you
- boot a 32-bit kernel on a 64-bit NUMA platform.
+ For 32-bit this is only needed if you boot a 32-bit
+ kernel on a 64-bit NUMA platform.
Otherwise, you should say N.
-comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
- depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
-
config AMD_NUMA
def_bool y
prompt "Old style AMD Opteron NUMA detection"
@@ -1302,7 +1261,6 @@ config NODES_SHIFT
range 1 10
default "10" if MAXSMP
default "6" if X86_64
- default "4" if X86_NUMAQ
default "3"
depends on NEED_MULTIPLE_NODES
---help---
@@ -1344,8 +1302,12 @@ config ARCH_SELECT_MEMORY_MODEL
depends on ARCH_SPARSEMEM_ENABLE
config ARCH_MEMORY_PROBE
- def_bool y
+ bool "Enable sysfs memory/probe interface"
depends on X86_64 && MEMORY_HOTPLUG
+ help
+ This option enables a sysfs memory/probe interface for testing.
+ See Documentation/memory-hotplug.txt for more information.
+ If you are unsure how to answer this question, answer N.
config ARCH_PROC_KCORE_TEXT
def_bool y
@@ -1579,7 +1541,21 @@ config EFI_STUB
This kernel feature allows a bzImage to be loaded directly
by EFI firmware without the use of a bootloader.
- See Documentation/x86/efi-stub.txt for more information.
+ See Documentation/efi-stub.txt for more information.
+
+config EFI_MIXED
+ bool "EFI mixed-mode support"
+ depends on EFI_STUB && X86_64
+ ---help---
+ Enabling this feature allows a 64-bit kernel to be booted
+ on a 32-bit firmware, provided that your CPU supports 64-bit
+ mode.
+
+ Note that it is not possible to boot a mixed-mode enabled
+ kernel via the EFI boot stub - a bootloader that supports
+ the EFI handover protocol must be used.
+
+ If unsure, say N.
config SECCOMP
def_bool y
@@ -1597,22 +1573,6 @@ config SECCOMP
If unsure, say Y. Only embedded should say N here.
-config CC_STACKPROTECTOR
- bool "Enable -fstack-protector buffer overflow detection"
- ---help---
- This option turns on the -fstack-protector GCC feature. This
- feature puts, at the beginning of functions, a canary value on
- the stack just before the return address, and validates
- the value just before actually returning. Stack based buffer
- overflows (that need to overwrite this return address) now also
- overwrite the canary, which gets detected and the attack is then
- neutralized via a kernel panic.
-
- This feature requires gcc version 4.2 or above, or a distribution
- gcc with the feature backported. Older versions are automatically
- detected and for those versions, this configuration option is
- ignored. (and a warning is printed during bootup)
-
source kernel/Kconfig.hz
config KEXEC
@@ -1627,9 +1587,9 @@ config KEXEC
It is an ongoing process to be certain the hardware in a machine
is properly shutdown, so do not be surprised if this code does not
- initially work for you. It may help to enable device hotplugging
- support. As of this writing the exact hardware interface is
- strongly in flux, so no good recommendation can be made.
+ initially work for you. As of this writing the exact hardware
+ interface is strongly in flux, so no good recommendation can be
+ made.
config CRASH_DUMP
bool "kernel crash dumps"
@@ -1708,17 +1668,68 @@ config RELOCATABLE
Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
it has been loaded at and the compile time physical address
- (CONFIG_PHYSICAL_START) is ignored.
+ (CONFIG_PHYSICAL_START) is used as the minimum location.
-# Relocation on x86-32 needs some additional build support
+config RANDOMIZE_BASE
+ bool "Randomize the address of the kernel image"
+ depends on RELOCATABLE
+ default n
+ ---help---
+ Randomizes the physical and virtual address at which the
+ kernel image is decompressed, as a security feature that
+ deters exploit attempts relying on knowledge of the location
+ of kernel internals.
+
+ Entropy is generated using the RDRAND instruction if it is
+ supported. If RDTSC is supported, it is used as well. If
+ neither RDRAND nor RDTSC are supported, then randomness is
+ read from the i8254 timer.
+
+ The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
+ and aligned according to PHYSICAL_ALIGN. Since the kernel is
+ built using 2GiB addressing, and PHYSICAL_ALGIN must be at a
+ minimum of 2MiB, only 10 bits of entropy is theoretically
+ possible. At best, due to page table layouts, 64-bit can use
+ 9 bits of entropy and 32-bit uses 8 bits.
+
+ If unsure, say N.
+
+config RANDOMIZE_BASE_MAX_OFFSET
+ hex "Maximum kASLR offset allowed" if EXPERT
+ depends on RANDOMIZE_BASE
+ range 0x0 0x20000000 if X86_32
+ default "0x20000000" if X86_32
+ range 0x0 0x40000000 if X86_64
+ default "0x40000000" if X86_64
+ ---help---
+ The lesser of RANDOMIZE_BASE_MAX_OFFSET and available physical
+ memory is used to determine the maximal offset in bytes that will
+ be applied to the kernel when kernel Address Space Layout
+ Randomization (kASLR) is active. This must be a multiple of
+ PHYSICAL_ALIGN.
+
+ On 32-bit this is limited to 512MiB by page table layouts. The
+ default is 512MiB.
+
+ On 64-bit this is limited by how the kernel fixmap page table is
+ positioned, so this cannot be larger than 1GiB currently. Without
+ RANDOMIZE_BASE, there is a 512MiB to 1.5GiB split between kernel
+ and modules. When RANDOMIZE_BASE_MAX_OFFSET is above 512MiB, the
+ modules area will shrink to compensate, up to the current maximum
+ 1GiB to 1GiB split. The default is 1GiB.
+
+ If unsure, leave at the default value.
+
+# Relocation on x86 needs some additional build support
config X86_NEED_RELOCS
def_bool y
- depends on X86_32 && RELOCATABLE
+ depends on RANDOMIZE_BASE || (X86_32 && RELOCATABLE)
config PHYSICAL_ALIGN
- hex "Alignment value to which kernel should be aligned" if X86_32
- default "0x1000000"
- range 0x2000 0x1000000
+ hex "Alignment value to which kernel should be aligned"
+ default "0x200000"
+ range 0x2000 0x1000000 if X86_32
+ range 0x200000 0x1000000 if X86_64
---help---
This value puts the alignment restrictions on physical address
where kernel is loaded and run from. Kernel is compiled for an
@@ -1736,6 +1747,9 @@ config PHYSICAL_ALIGN
end result is that kernel runs from a physical address meeting
above alignment restrictions.
+ On 32-bit this value must be a multiple of 0x2000. On 64-bit
+ this value must be a multiple of 0x200000.
+
Don't change this unless you know what you are doing.
config HOTPLUG_CPU
@@ -1793,17 +1807,29 @@ config DEBUG_HOTPLUG_CPU0
If unsure, say N.
config COMPAT_VDSO
- def_bool y
- prompt "Compat VDSO support"
+ def_bool n
+ prompt "Disable the 32-bit vDSO (needed for glibc 2.3.3)"
depends on X86_32 || IA32_EMULATION
---help---
- Map the 32-bit VDSO to the predictable old-style address too.
+ Certain buggy versions of glibc will crash if they are
+ presented with a 32-bit vDSO that is not mapped at the address
+ indicated in its segment table.
- Say N here if you are running a sufficiently recent glibc
- version (2.3.3 or later), to remove the high-mapped
- VDSO mapping and to exclusively use the randomized VDSO.
+ The bug was introduced by f866314b89d56845f55e6f365e18b31ec978ec3a
+ and fixed by 3b3ddb4f7db98ec9e912ccdf54d35df4aa30e04a and
+ 49ad572a70b8aeb91e57483a11dd1b77e31c4468. Glibc 2.3.3 is
+ the only released version with the bug, but OpenSUSE 9
+ contains a buggy "glibc 2.3.2".
- If unsure, say Y.
+ The symptom of the bug is that everything crashes on startup, saying:
+ dl_main: Assertion `(void *) ph->p_vaddr == _rtld_local._dl_sysinfo_dso' failed!
+
+ Saying Y here changes the default value of the vdso32 boot
+ option from 1 to 0, which turns off the 32-bit vDSO entirely.
+ This works around the glibc bug but hurts performance.
+
+ If unsure, say N: if you are compiling your own kernel, you
+ are unlikely to be using a buggy version of glibc.
config CMDLINE_BOOL
bool "Built-in kernel command line"
@@ -1862,6 +1888,14 @@ config USE_PERCPU_NUMA_NODE_ID
def_bool y
depends on NUMA
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+ def_bool y
+ depends on X86_64 || X86_PAE
+
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+ def_bool y
+ depends on X86_64 && HUGETLB_PAGE && MIGRATION
+
menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
@@ -2014,7 +2048,6 @@ menu "Bus options (PCI etc.)"
config PCI
bool "PCI support"
default y
- select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
---help---
Find out whether you have a PCI motherboard. PCI is the name of a
bus system, i.e. the way the CPU talks to the other stuff inside
@@ -2270,6 +2303,32 @@ config RAPIDIO
source "drivers/rapidio/Kconfig"
+config X86_SYSFB
+ bool "Mark VGA/VBE/EFI FB as generic system framebuffer"
+ help
+ Firmwares often provide initial graphics framebuffers so the BIOS,
+ bootloader or kernel can show basic video-output during boot for
+ user-guidance and debugging. Historically, x86 used the VESA BIOS
+ Extensions and EFI-framebuffers for this, which are mostly limited
+ to x86.
+ This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
+ framebuffers so the new generic system-framebuffer drivers can be
+ used on x86. If the framebuffer is not compatible with the generic
+ modes, it is adverticed as fallback platform framebuffer so legacy
+ drivers like efifb, vesafb and uvesafb can pick it up.
+ If this option is not selected, all system framebuffers are always
+ marked as fallback platform framebuffers as usual.
+
+ Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will
+ not be able to pick up generic system framebuffers if this option
+ is selected. You are highly encouraged to enable simplefb as
+ replacement if you select this option. simplefb can correctly deal
+ with generic system framebuffers. But you should still keep vesafb
+ and others enabled as fallback if a system framebuffer is
+ incompatible with simplefb.
+
+ If unsure, say Y.
+
endmenu
@@ -2332,10 +2391,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config HAVE_TEXT_POKE_SMP
- bool
- select STOP_MACHINE if SMP
-
config X86_DEV_DMA_OPS
bool
depends on X86_64 || STA2X11
@@ -2344,6 +2399,11 @@ config X86_DMA_REMAP
bool
depends on STA2X11
+config IOSF_MBI
+ tristate
+ default m
+ depends on PCI
+
source "net/Kconfig"
source "drivers/Kconfig"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca5602..6983314c8b3 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@ config X86_USE_3DNOW
def_bool y
depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
-config X86_OOSTORE
- def_bool y
- depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
#
# P6_NOPs are a relatively minor optimization that require a family >=
# 6 processor, except that it is broken on certain VIA chips.
@@ -363,7 +359,7 @@ config X86_P6_NOP
config X86_TSC
def_bool y
- depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) && !X86_NUMAQ) || X86_64
+ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
config X86_CMPXCHG64
def_bool y
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 78d91afb8e5..61bd2ad9428 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -59,6 +59,16 @@ config EARLY_PRINTK_DBGP
with klogd/syslogd or the X server. You should normally N here,
unless you want to debug such a crash. You need usb debug device.
+config EARLY_PRINTK_EFI
+ bool "Early printk via the EFI framebuffer"
+ depends on EFI && EARLY_PRINTK
+ select FONT_SUPPORT
+ ---help---
+ Write kernel log output directly into the EFI framebuffer.
+
+ This is useful for kernel debugging when your machine crashes very
+ early before the console code is initialized.
+
config X86_PTDUMP
bool "Export kernel pagetable layout to userspace via debugfs"
depends on DEBUG_KERNEL
@@ -71,6 +81,15 @@ config X86_PTDUMP
kernel.
If in doubt, say "N"
+config EFI_PGT_DUMP
+ bool "Dump the EFI pagetable"
+ depends on EFI && X86_PTDUMP
+ ---help---
+ Enable this if you want to dump the EFI page table before
+ enabling virtual mode. This can be used to debug miscellaneous
+ issues with the mapping of the EFI runtime regions into that
+ table.
+
config DEBUG_RODATA
bool "Write protect kernel read-only data structures"
default y
@@ -174,6 +193,7 @@ config HAVE_MMIOTRACE_SUPPORT
config X86_DECODER_SELFTEST
bool "x86 instruction decoder selftest"
depends on DEBUG_KERNEL && KPROBES
+ depends on !COMPILE_TEST
---help---
Perform x86 instruction decoder selftests at build time.
This option is useful for checking the sanity of x86 instruction
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 07639c656fc..33f71b01fd2 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -11,11 +11,37 @@ else
KBUILD_DEFCONFIG := $(ARCH)_defconfig
endif
+# How to compile the 16-bit code. Note we always compile for -march=i386;
+# that way we can complain to the user if the CPU is insufficient.
+#
+# The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
+# older versions of GCC, we need to play evil and unreliable tricks to
+# attempt to ensure that our asm(".code16gcc") is first in the asm
+# output.
+CODE16GCC_CFLAGS := -m32 -include $(srctree)/arch/x86/boot/code16gcc.h \
+ $(call cc-option, -fno-toplevel-reorder,\
+ $(call cc-option, -fno-unit-at-a-time))
+M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
+
+REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \
+ -DDISABLE_BRANCH_PROFILING \
+ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
+ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+ -mno-mmx -mno-sse \
+ $(call cc-option, -ffreestanding) \
+ $(call cc-option, -fno-stack-protector) \
+ $(call cc-option, -mpreferred-stack-boundary=2)
+export REALMODE_CFLAGS
+
# BITS is used as extension for files which are available in a 32 bit
# and a 64 bit version to simplify shared Makefiles.
# e.g.: obj-y += foo_$(BITS).o
export BITS
+ifdef CONFIG_X86_NEED_RELOCS
+ LDFLAGS_vmlinux := --emit-relocs
+endif
+
ifeq ($(CONFIG_X86_32),y)
BITS := 32
UTS_MACHINE := i386
@@ -25,12 +51,11 @@ ifeq ($(CONFIG_X86_32),y)
KBUILD_AFLAGS += $(biarch)
KBUILD_CFLAGS += $(biarch)
- ifdef CONFIG_RELOCATABLE
- LDFLAGS_vmlinux := --emit-relocs
- endif
-
KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
+ # Don't autogenerate MMX or SSE instructions
+ KBUILD_CFLAGS += -mno-mmx -mno-sse
+
# Never want PIC in a 32-bit kernel, prevent breakage with GCC built
# with nonstandard options
KBUILD_CFLAGS += -fno-pic
@@ -54,11 +79,17 @@ else
UTS_MACHINE := x86_64
CHECKFLAGS += -D__x86_64__ -m64
+ biarch := -m64
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
+ # Don't autogenerate traditional x87, MMX or SSE instructions
+ KBUILD_CFLAGS += -mno-mmx -mno-sse
+ KBUILD_CFLAGS += $(call cc-option,-mno-80387)
+ KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
+
# Use -mpreferred-stack-boundary=3 if supported.
- KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
+ KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
@@ -80,16 +111,14 @@ else
# this works around some issues with generating unwind tables in older gccs
# newer gccs do it by default
- KBUILD_CFLAGS += -maccumulate-outgoing-args
+ KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
endif
+# Make sure compiler does not have buggy stack-protector support.
ifdef CONFIG_CC_STACKPROTECTOR
cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
- ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
- stackp-y := -fstack-protector
- KBUILD_CFLAGS += $(stackp-y)
- else
- $(warning stack protector enabled but no compiler support)
+ ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
+ $(warning stack-protector enabled but compiler support broken)
endif
endif
@@ -126,6 +155,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
@@ -223,8 +253,8 @@ archclean:
PHONY += kvmconfig
kvmconfig:
$(if $(wildcard $(objtree)/.config),, $(error You need an existing .config for this target))
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config arch/x86/configs/kvm_guest.config
- $(Q)yes "" | $(MAKE) oldconfig
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config $(srctree)/arch/x86/configs/kvm_guest.config
+ $(Q)yes "" | $(MAKE) -f $(srctree)/Makefile oldconfig
define archhelp
echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 379814bc41e..dbe8dd2fe24 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -20,7 +20,7 @@ targets := vmlinux.bin setup.bin setup.elf bzImage
targets += fdimage fdimage144 fdimage288 image.iso mtools.conf
subdir- := compressed
-setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o
+setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o
setup-y += early_serial_console.o edd.o header.o main.o mca.o memory.o
setup-y += pm.o pmjump.o printf.o regs.o string.o tty.o video.o
setup-y += video-mode.o version.o
@@ -51,27 +51,15 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
# ---------------------------------------------------------------------------
-# How to compile the 16-bit code. Note we always compile for -march=i386,
-# that way we can complain to the user if the CPU is insufficient.
-KBUILD_CFLAGS := $(USERINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
- -DDISABLE_BRANCH_PROFILING \
- -Wall -Wstrict-prototypes \
- -march=i386 -mregparm=3 \
- -include $(srctree)/$(src)/code16gcc.h \
- -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
- $(call cc-option, -ffreestanding) \
- $(call cc-option, -fno-toplevel-reorder,\
- $(call cc-option, -fno-unit-at-a-time)) \
- $(call cc-option, -fno-stack-protector) \
- $(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS += $(call cc-option, -m32)
+KBUILD_CFLAGS := $(USERINCLUDE) $(REALMODE_CFLAGS) -D_SETUP
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
GCOV_PROFILE := n
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
-cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/zoffset.h > $@
+cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
+ $(obj)/zoffset.h $@
$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
$(call if_changed,image)
@@ -83,7 +71,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) . \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
quiet_cmd_voffset = VOFFSET $@
cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
@@ -92,7 +80,7 @@ targets += voffset.h
$(obj)/voffset.h: vmlinux FORCE
$(call if_changed,voffset)
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
quiet_cmd_zoffset = ZOFFSET $@
cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index 1dfbf64e52a..d401b4a262b 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -1,6 +1,6 @@
/* -----------------------------------------------------------------------
*
- * Copyright 2009 Intel Corporation; author H. Peter Anvin
+ * Copyright 2009-2014 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2 or (at your
@@ -13,8 +13,8 @@
* touching registers they shouldn't be.
*/
- .code16gcc
- .text
+ .code16
+ .section ".inittext","ax"
.globl intcall
.type intcall, @function
intcall:
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 5b7531966b8..bd49ec61255 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -26,9 +26,8 @@
#include <asm/boot.h>
#include <asm/setup.h>
#include "bitops.h"
-#include <asm/cpufeature.h>
-#include <asm/processor-flags.h>
#include "ctype.h"
+#include "cpuflags.h"
/* Useful macros */
#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@@ -178,14 +177,6 @@ static inline void wrgs32(u32 v, addr_t addr)
}
/* Note: these only return true/false, not a signed return value! */
-static inline int memcmp(const void *s1, const void *s2, size_t len)
-{
- u8 diff;
- asm("repe; cmpsb; setnz %0"
- : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
- return diff;
-}
-
static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
{
u8 diff;
@@ -229,11 +220,6 @@ void copy_to_fs(addr_t dst, void *src, size_t len);
void *copy_from_fs(void *dst, addr_t src, size_t len);
void copy_to_gs(addr_t dst, void *src, size_t len);
void *copy_from_gs(void *dst, addr_t src, size_t len);
-void *memcpy(void *dst, void *src, size_t len);
-void *memset(void *dst, int c, size_t len);
-
-#define memcpy(d,s,l) __builtin_memcpy(d,s,l)
-#define memset(d,c,l) __builtin_memset(d,c,l)
/* a20.c */
int enable_a20(void);
@@ -307,14 +293,7 @@ static inline int cmdline_find_option_bool(const char *option)
return __cmdline_find_option_bool(cmd_line_ptr, option);
}
-
/* cpu.c, cpucheck.c */
-struct cpu_features {
- int level; /* Family, or 64 for x86-64 */
- int model;
- u32 flags[NCAPINTS];
-};
-extern struct cpu_features cpu;
int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
int validate_cpu(void);
@@ -355,6 +334,7 @@ int strncmp(const char *cs, const char *ct, size_t count);
size_t strnlen(const char *s, size_t maxlen);
unsigned int atou(const char *s);
unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
+size_t strlen(const char *s);
/* tty.c */
void puts(const char *);
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index dcd90df10ab..0fcd9133790 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -13,6 +13,7 @@ KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
cflags-$(CONFIG_X86_32) := -march=i386
cflags-$(CONFIG_X86_64) := -mcmodel=small
KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += -mno-mmx -mno-sse
KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
@@ -27,7 +28,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include
VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
- $(obj)/piggy.o
+ $(obj)/piggy.o $(obj)/cpuflags.o $(obj)/aslr.o
$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
new file mode 100644
index 00000000000..fc6091abedb
--- /dev/null
+++ b/arch/x86/boot/compressed/aslr.c
@@ -0,0 +1,324 @@
+#include "misc.h"
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+#include <asm/e820.h>
+
+#include <generated/compile.h>
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <generated/utsrelease.h>
+
+/* Simplified build-specific string for starting entropy. */
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+ LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
+#define I8254_PORT_CONTROL 0x43
+#define I8254_PORT_COUNTER0 0x40
+#define I8254_CMD_READBACK 0xC0
+#define I8254_SELECT_COUNTER0 0x02
+#define I8254_STATUS_NOTREADY 0x40
+static inline u16 i8254(void)
+{
+ u16 status, timer;
+
+ do {
+ outb(I8254_PORT_CONTROL,
+ I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+ status = inb(I8254_PORT_COUNTER0);
+ timer = inb(I8254_PORT_COUNTER0);
+ timer |= inb(I8254_PORT_COUNTER0) << 8;
+ } while (status & I8254_STATUS_NOTREADY);
+
+ return timer;
+}
+
+static unsigned long rotate_xor(unsigned long hash, const void *area,
+ size_t size)
+{
+ size_t i;
+ unsigned long *ptr = (unsigned long *)area;
+
+ for (i = 0; i < size / sizeof(hash); i++) {
+ /* Rotate by odd number of bits and XOR. */
+ hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+ hash ^= ptr[i];
+ }
+
+ return hash;
+}
+
+/* Attempt to create a simple but unpredictable starting entropy. */
+static unsigned long get_random_boot(void)
+{
+ unsigned long hash = 0;
+
+ hash = rotate_xor(hash, build_str, sizeof(build_str));
+ hash = rotate_xor(hash, real_mode, sizeof(*real_mode));
+
+ return hash;
+}
+
+static unsigned long get_random_long(void)
+{
+#ifdef CONFIG_X86_64
+ const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+ const unsigned long mix_const = 0x3f39e593UL;
+#endif
+ unsigned long raw, random = get_random_boot();
+ bool use_i8254 = true;
+
+ debug_putstr("KASLR using");
+
+ if (has_cpuflag(X86_FEATURE_RDRAND)) {
+ debug_putstr(" RDRAND");
+ if (rdrand_long(&raw)) {
+ random ^= raw;
+ use_i8254 = false;
+ }
+ }
+
+ if (has_cpuflag(X86_FEATURE_TSC)) {
+ debug_putstr(" RDTSC");
+ rdtscll(raw);
+
+ random ^= raw;
+ use_i8254 = false;
+ }
+
+ if (use_i8254) {
+ debug_putstr(" i8254");
+ random ^= i8254();
+ }
+
+ /* Circular multiply for better bit diffusion */
+ asm("mul %3"
+ : "=a" (random), "=d" (raw)
+ : "a" (random), "rm" (mix_const));
+ random += raw;
+
+ debug_putstr("...\n");
+
+ return random;
+}
+
+struct mem_vector {
+ unsigned long start;
+ unsigned long size;
+};
+
+#define MEM_AVOID_MAX 5
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
+
+static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
+{
+ /* Item at least partially before region. */
+ if (item->start < region->start)
+ return false;
+ /* Item at least partially after region. */
+ if (item->start + item->size > region->start + region->size)
+ return false;
+ return true;
+}
+
+static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
+{
+ /* Item one is entirely before item two. */
+ if (one->start + one->size <= two->start)
+ return false;
+ /* Item one is entirely after item two. */
+ if (one->start >= two->start + two->size)
+ return false;
+ return true;
+}
+
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+ unsigned long output, unsigned long output_size)
+{
+ u64 initrd_start, initrd_size;
+ u64 cmd_line, cmd_line_size;
+ unsigned long unsafe, unsafe_len;
+ char *ptr;
+
+ /*
+ * Avoid the region that is unsafe to overlap during
+ * decompression (see calculations at top of misc.c).
+ */
+ unsafe_len = (output_size >> 12) + 32768 + 18;
+ unsafe = (unsigned long)input + input_size - unsafe_len;
+ mem_avoid[0].start = unsafe;
+ mem_avoid[0].size = unsafe_len;
+
+ /* Avoid initrd. */
+ initrd_start = (u64)real_mode->ext_ramdisk_image << 32;
+ initrd_start |= real_mode->hdr.ramdisk_image;
+ initrd_size = (u64)real_mode->ext_ramdisk_size << 32;
+ initrd_size |= real_mode->hdr.ramdisk_size;
+ mem_avoid[1].start = initrd_start;
+ mem_avoid[1].size = initrd_size;
+
+ /* Avoid kernel command line. */
+ cmd_line = (u64)real_mode->ext_cmd_line_ptr << 32;
+ cmd_line |= real_mode->hdr.cmd_line_ptr;
+ /* Calculate size of cmd_line. */
+ ptr = (char *)(unsigned long)cmd_line;
+ for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+ ;
+ mem_avoid[2].start = cmd_line;
+ mem_avoid[2].size = cmd_line_size;
+
+ /* Avoid heap memory. */
+ mem_avoid[3].start = (unsigned long)free_mem_ptr;
+ mem_avoid[3].size = BOOT_HEAP_SIZE;
+
+ /* Avoid stack memory. */
+ mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
+ mem_avoid[4].size = BOOT_STACK_SIZE;
+}
+
+/* Does this memory vector overlap a known avoided area? */
+static bool mem_avoid_overlap(struct mem_vector *img)
+{
+ int i;
+
+ for (i = 0; i < MEM_AVOID_MAX; i++) {
+ if (mem_overlaps(img, &mem_avoid[i]))
+ return true;
+ }
+
+ return false;
+}
+
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+ CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
+
+static void slots_append(unsigned long addr)
+{
+ /* Overflowing the slots list should be impossible. */
+ if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+ CONFIG_PHYSICAL_ALIGN)
+ return;
+
+ slots[slot_max++] = addr;
+}
+
+static unsigned long slots_fetch_random(void)
+{
+ /* Handle case of no slots stored. */
+ if (slot_max == 0)
+ return 0;
+
+ return slots[get_random_long() % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+ unsigned long minimum,
+ unsigned long image_size)
+{
+ struct mem_vector region, img;
+
+ /* Skip non-RAM entries. */
+ if (entry->type != E820_RAM)
+ return;
+
+ /* Ignore entries entirely above our maximum. */
+ if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+ return;
+
+ /* Ignore entries entirely below our minimum. */
+ if (entry->addr + entry->size < minimum)
+ return;
+
+ region.start = entry->addr;
+ region.size = entry->size;
+
+ /* Potentially raise address to minimum location. */
+ if (region.start < minimum)
+ region.start = minimum;
+
+ /* Potentially raise address to meet alignment requirements. */
+ region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+
+ /* Did we raise the address above the bounds of this e820 region? */
+ if (region.start > entry->addr + entry->size)
+ return;
+
+ /* Reduce size by any delta from the original address. */
+ region.size -= region.start - entry->addr;
+
+ /* Reduce maximum size to fit end of image within maximum limit. */
+ if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+ region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start;
+
+ /* Walk each aligned slot and check for avoided areas. */
+ for (img.start = region.start, img.size = image_size ;
+ mem_contains(&region, &img) ;
+ img.start += CONFIG_PHYSICAL_ALIGN) {
+ if (mem_avoid_overlap(&img))
+ continue;
+ slots_append(img.start);
+ }
+}
+
+static unsigned long find_random_addr(unsigned long minimum,
+ unsigned long size)
+{
+ int i;
+ unsigned long addr;
+
+ /* Make sure minimum is aligned. */
+ minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+ /* Verify potential e820 positions, appending to slots list. */
+ for (i = 0; i < real_mode->e820_entries; i++) {
+ process_e820_entry(&real_mode->e820_map[i], minimum, size);
+ }
+
+ return slots_fetch_random();
+}
+
+unsigned char *choose_kernel_location(unsigned char *input,
+ unsigned long input_size,
+ unsigned char *output,
+ unsigned long output_size)
+{
+ unsigned long choice = (unsigned long)output;
+ unsigned long random;
+
+#ifdef CONFIG_HIBERNATION
+ if (!cmdline_find_option_bool("kaslr")) {
+ debug_putstr("KASLR disabled by default...\n");
+ goto out;
+ }
+#else
+ if (cmdline_find_option_bool("nokaslr")) {
+ debug_putstr("KASLR disabled by cmdline...\n");
+ goto out;
+ }
+#endif
+
+ /* Record the various known unsafe memory ranges. */
+ mem_avoid_init((unsigned long)input, input_size,
+ (unsigned long)output, output_size);
+
+ /* Walk e820 and find a random address. */
+ random = find_random_addr(choice, output_size);
+ if (!random) {
+ debug_putstr("KASLR could not find suitable E820 region...\n");
+ goto out;
+ }
+
+ /* Always enforce the minimum. */
+ if (random < choice)
+ goto out;
+
+ choice = random;
+out:
+ return (unsigned char *)choice;
+}
+
+#endif /* CONFIG_RANDOMIZE_BASE */
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index bffd73b45b1..b68e3033e6b 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,6 +1,6 @@
#include "misc.h"
-#ifdef CONFIG_EARLY_PRINTK
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
static unsigned long fs;
static inline void set_fs(unsigned long seg)
diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
new file mode 100644
index 00000000000..aa313466118
--- /dev/null
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -0,0 +1,12 @@
+#ifdef CONFIG_RANDOMIZE_BASE
+
+#include "../cpuflags.c"
+
+bool has_cpuflag(int flag)
+{
+ get_cpuflags();
+
+ return test_bit(flag, cpu.flags);
+}
+
+#endif
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d606463aa6d..0331d765c2b 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -19,215 +19,273 @@
static efi_system_table_t *sys_table;
-static void efi_char16_printk(efi_char16_t *str)
-{
- struct efi_simple_text_output_protocol *out;
-
- out = (struct efi_simple_text_output_protocol *)sys_table->con_out;
- efi_call_phys2(out->output_string, out, str);
+static struct efi_config *efi_early;
+
+#define efi_call_early(f, ...) \
+ efi_early->call(efi_early->f, __VA_ARGS__);
+
+#define BOOT_SERVICES(bits) \
+static void setup_boot_services##bits(struct efi_config *c) \
+{ \
+ efi_system_table_##bits##_t *table; \
+ efi_boot_services_##bits##_t *bt; \
+ \
+ table = (typeof(table))sys_table; \
+ \
+ c->text_output = table->con_out; \
+ \
+ bt = (typeof(bt))(unsigned long)(table->boottime); \
+ \
+ c->allocate_pool = bt->allocate_pool; \
+ c->allocate_pages = bt->allocate_pages; \
+ c->get_memory_map = bt->get_memory_map; \
+ c->free_pool = bt->free_pool; \
+ c->free_pages = bt->free_pages; \
+ c->locate_handle = bt->locate_handle; \
+ c->handle_protocol = bt->handle_protocol; \
+ c->exit_boot_services = bt->exit_boot_services; \
}
+BOOT_SERVICES(32);
+BOOT_SERVICES(64);
+
+static void efi_printk(efi_system_table_t *, char *);
+static void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
-static void efi_printk(char *str)
+static efi_status_t
+__file_size32(void *__fh, efi_char16_t *filename_16,
+ void **handle, u64 *file_sz)
{
- char *s8;
+ efi_file_handle_32_t *h, *fh = __fh;
+ efi_file_info_t *info;
+ efi_status_t status;
+ efi_guid_t info_guid = EFI_FILE_INFO_ID;
+ u32 info_sz;
- for (s8 = str; *s8; s8++) {
- efi_char16_t ch[2] = { 0 };
+ status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
+ EFI_FILE_MODE_READ, (u64)0);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to open file: ");
+ efi_char16_printk(sys_table, filename_16);
+ efi_printk(sys_table, "\n");
+ return status;
+ }
- ch[0] = *s8;
- if (*s8 == '\n') {
- efi_char16_t nl[2] = { '\r', 0 };
- efi_char16_printk(nl);
- }
+ *handle = h;
- efi_char16_printk(ch);
+ info_sz = 0;
+ status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+ &info_sz, NULL);
+ if (status != EFI_BUFFER_TOO_SMALL) {
+ efi_printk(sys_table, "Failed to get file info size\n");
+ return status;
}
-}
-static efi_status_t __get_map(efi_memory_desc_t **map, unsigned long *map_size,
- unsigned long *desc_size)
-{
- efi_memory_desc_t *m = NULL;
- efi_status_t status;
- unsigned long key;
- u32 desc_version;
-
- *map_size = sizeof(*m) * 32;
-again:
- /*
- * Add an additional efi_memory_desc_t because we're doing an
- * allocation which may be in a new descriptor region.
- */
- *map_size += sizeof(*m);
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, *map_size, (void **)&m);
- if (status != EFI_SUCCESS)
- goto fail;
+grow:
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ info_sz, (void **)&info);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to alloc mem for file info\n");
+ return status;
+ }
- status = efi_call_phys5(sys_table->boottime->get_memory_map, map_size,
- m, &key, desc_size, &desc_version);
+ status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+ &info_sz, info);
if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_phys1(sys_table->boottime->free_pool, m);
- goto again;
+ efi_call_early(free_pool, info);
+ goto grow;
}
+ *file_sz = info->file_size;
+ efi_call_early(free_pool, info);
+
if (status != EFI_SUCCESS)
- efi_call_phys1(sys_table->boottime->free_pool, m);
+ efi_printk(sys_table, "Failed to get initrd info\n");
-fail:
- *map = m;
return status;
}
-/*
- * Allocate at the highest possible address that is not above 'max'.
- */
-static efi_status_t high_alloc(unsigned long size, unsigned long align,
- unsigned long *addr, unsigned long max)
+static efi_status_t
+__file_size64(void *__fh, efi_char16_t *filename_16,
+ void **handle, u64 *file_sz)
{
- unsigned long map_size, desc_size;
- efi_memory_desc_t *map;
+ efi_file_handle_64_t *h, *fh = __fh;
+ efi_file_info_t *info;
efi_status_t status;
- unsigned long nr_pages;
- u64 max_addr = 0;
- int i;
+ efi_guid_t info_guid = EFI_FILE_INFO_ID;
+ u64 info_sz;
- status = __get_map(&map, &map_size, &desc_size);
- if (status != EFI_SUCCESS)
- goto fail;
+ status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
+ EFI_FILE_MODE_READ, (u64)0);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to open file: ");
+ efi_char16_printk(sys_table, filename_16);
+ efi_printk(sys_table, "\n");
+ return status;
+ }
- nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-again:
- for (i = 0; i < map_size / desc_size; i++) {
- efi_memory_desc_t *desc;
- unsigned long m = (unsigned long)map;
- u64 start, end;
+ *handle = h;
- desc = (efi_memory_desc_t *)(m + (i * desc_size));
- if (desc->type != EFI_CONVENTIONAL_MEMORY)
- continue;
+ info_sz = 0;
+ status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+ &info_sz, NULL);
+ if (status != EFI_BUFFER_TOO_SMALL) {
+ efi_printk(sys_table, "Failed to get file info size\n");
+ return status;
+ }
- if (desc->num_pages < nr_pages)
- continue;
+grow:
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ info_sz, (void **)&info);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to alloc mem for file info\n");
+ return status;
+ }
- start = desc->phys_addr;
- end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+ status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+ &info_sz, info);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ efi_call_early(free_pool, info);
+ goto grow;
+ }
- if ((start + size) > end || (start + size) > max)
- continue;
+ *file_sz = info->file_size;
+ efi_call_early(free_pool, info);
- if (end - size > max)
- end = max;
+ if (status != EFI_SUCCESS)
+ efi_printk(sys_table, "Failed to get initrd info\n");
- if (round_down(end - size, align) < start)
- continue;
+ return status;
+}
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table, void *__fh,
+ efi_char16_t *filename_16, void **handle, u64 *file_sz)
+{
+ if (efi_early->is64)
+ return __file_size64(__fh, filename_16, handle, file_sz);
- start = round_down(end - size, align);
+ return __file_size32(__fh, filename_16, handle, file_sz);
+}
- /*
- * Don't allocate at 0x0. It will confuse code that
- * checks pointers against NULL.
- */
- if (start == 0x0)
- continue;
+static inline efi_status_t
+efi_file_read(void *handle, unsigned long *size, void *addr)
+{
+ unsigned long func;
- if (start > max_addr)
- max_addr = start;
- }
+ if (efi_early->is64) {
+ efi_file_handle_64_t *fh = handle;
- if (!max_addr)
- status = EFI_NOT_FOUND;
- else {
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &max_addr);
- if (status != EFI_SUCCESS) {
- max = max_addr;
- max_addr = 0;
- goto again;
- }
+ func = (unsigned long)fh->read;
+ return efi_early->call(func, handle, size, addr);
+ } else {
+ efi_file_handle_32_t *fh = handle;
- *addr = max_addr;
+ func = (unsigned long)fh->read;
+ return efi_early->call(func, handle, size, addr);
}
+}
-free_pool:
- efi_call_phys1(sys_table->boottime->free_pool, map);
+static inline efi_status_t efi_file_close(void *handle)
+{
+ if (efi_early->is64) {
+ efi_file_handle_64_t *fh = handle;
-fail:
- return status;
+ return efi_early->call((unsigned long)fh->close, handle);
+ } else {
+ efi_file_handle_32_t *fh = handle;
+
+ return efi_early->call((unsigned long)fh->close, handle);
+ }
}
-/*
- * Allocate at the lowest possible address.
- */
-static efi_status_t low_alloc(unsigned long size, unsigned long align,
- unsigned long *addr)
+static inline efi_status_t __open_volume32(void *__image, void **__fh)
{
- unsigned long map_size, desc_size;
- efi_memory_desc_t *map;
+ efi_file_io_interface_t *io;
+ efi_loaded_image_32_t *image = __image;
+ efi_file_handle_32_t *fh;
+ efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
efi_status_t status;
- unsigned long nr_pages;
- int i;
+ void *handle = (void *)(unsigned long)image->device_handle;
+ unsigned long func;
- status = __get_map(&map, &map_size, &desc_size);
+ status = efi_call_early(handle_protocol, handle,
+ &fs_proto, (void **)&io);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to handle fs_proto\n");
+ return status;
+ }
+
+ func = (unsigned long)io->open_volume;
+ status = efi_early->call(func, io, &fh);
if (status != EFI_SUCCESS)
- goto fail;
+ efi_printk(sys_table, "Failed to open volume\n");
- nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
- for (i = 0; i < map_size / desc_size; i++) {
- efi_memory_desc_t *desc;
- unsigned long m = (unsigned long)map;
- u64 start, end;
+ *__fh = fh;
+ return status;
+}
- desc = (efi_memory_desc_t *)(m + (i * desc_size));
+static inline efi_status_t __open_volume64(void *__image, void **__fh)
+{
+ efi_file_io_interface_t *io;
+ efi_loaded_image_64_t *image = __image;
+ efi_file_handle_64_t *fh;
+ efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+ efi_status_t status;
+ void *handle = (void *)(unsigned long)image->device_handle;
+ unsigned long func;
- if (desc->type != EFI_CONVENTIONAL_MEMORY)
- continue;
+ status = efi_call_early(handle_protocol, handle,
+ &fs_proto, (void **)&io);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to handle fs_proto\n");
+ return status;
+ }
- if (desc->num_pages < nr_pages)
- continue;
+ func = (unsigned long)io->open_volume;
+ status = efi_early->call(func, io, &fh);
+ if (status != EFI_SUCCESS)
+ efi_printk(sys_table, "Failed to open volume\n");
- start = desc->phys_addr;
- end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+ *__fh = fh;
+ return status;
+}
- /*
- * Don't allocate at 0x0. It will confuse code that
- * checks pointers against NULL. Skip the first 8
- * bytes so we start at a nice even number.
- */
- if (start == 0x0)
- start += 8;
+static inline efi_status_t
+efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
+{
+ if (efi_early->is64)
+ return __open_volume64(__image, __fh);
- start = round_up(start, align);
- if ((start + size) > end)
- continue;
+ return __open_volume32(__image, __fh);
+}
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &start);
- if (status == EFI_SUCCESS) {
- *addr = start;
- break;
- }
- }
+static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
+{
+ unsigned long output_string;
+ size_t offset;
- if (i == map_size / desc_size)
- status = EFI_NOT_FOUND;
+ if (efi_early->is64) {
+ struct efi_simple_text_output_protocol_64 *out;
+ u64 *func;
-free_pool:
- efi_call_phys1(sys_table->boottime->free_pool, map);
-fail:
- return status;
-}
+ offset = offsetof(typeof(*out), output_string);
+ output_string = efi_early->text_output + offset;
+ func = (u64 *)output_string;
-static void low_free(unsigned long size, unsigned long addr)
-{
- unsigned long nr_pages;
+ efi_early->call(*func, efi_early->text_output, str);
+ } else {
+ struct efi_simple_text_output_protocol_32 *out;
+ u32 *func;
+
+ offset = offsetof(typeof(*out), output_string);
+ output_string = efi_early->text_output + offset;
+ func = (u32 *)output_string;
- nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
- efi_call_phys2(sys_table->boottime->free_pages, addr, size);
+ efi_early->call(*func, efi_early->text_output, str);
+ }
}
+#include "../../../../drivers/firmware/efi/efi-stub-helper.c"
+
static void find_bits(unsigned long mask, u8 *pos, u8 *size)
{
u8 first, len;
@@ -251,105 +309,97 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
*size = len;
}
-static efi_status_t setup_efi_pci(struct boot_params *params)
+static efi_status_t
+__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
{
- efi_pci_io_protocol *pci;
+ struct pci_setup_rom *rom = NULL;
efi_status_t status;
- void **pci_handle;
- efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
- unsigned long nr_pci, size = 0;
- int i;
- struct setup_data *data;
-
- data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+ unsigned long size;
+ uint64_t attributes;
- while (data && data->next)
- data = (struct setup_data *)(unsigned long)data->next;
+ status = efi_early->call(pci->attributes, pci,
+ EfiPciIoAttributeOperationGet, 0, 0,
+ &attributes);
+ if (status != EFI_SUCCESS)
+ return status;
- status = efi_call_phys5(sys_table->boottime->locate_handle,
- EFI_LOCATE_BY_PROTOCOL, &pci_proto,
- NULL, &size, pci_handle);
+ if (!pci->romimage || !pci->romsize)
+ return EFI_INVALID_PARAMETER;
- if (status == EFI_BUFFER_TOO_SMALL) {
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, size, &pci_handle);
+ size = pci->romsize + sizeof(*rom);
- if (status != EFI_SUCCESS)
- return status;
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
+ if (status != EFI_SUCCESS)
+ return status;
- status = efi_call_phys5(sys_table->boottime->locate_handle,
- EFI_LOCATE_BY_PROTOCOL, &pci_proto,
- NULL, &size, pci_handle);
- }
+ memset(rom, 0, sizeof(*rom));
- if (status != EFI_SUCCESS)
- goto free_handle;
+ rom->data.type = SETUP_PCI;
+ rom->data.len = size - sizeof(struct setup_data);
+ rom->data.next = 0;
+ rom->pcilen = pci->romsize;
+ *__rom = rom;
- nr_pci = size / sizeof(void *);
- for (i = 0; i < nr_pci; i++) {
- void *h = pci_handle[i];
- uint64_t attributes;
- struct pci_setup_rom *rom;
+ status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+ PCI_VENDOR_ID, 1, &(rom->vendor));
- status = efi_call_phys3(sys_table->boottime->handle_protocol,
- h, &pci_proto, &pci);
+ if (status != EFI_SUCCESS)
+ goto free_struct;
- if (status != EFI_SUCCESS)
- continue;
+ status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+ PCI_DEVICE_ID, 1, &(rom->devid));
- if (!pci)
- continue;
+ if (status != EFI_SUCCESS)
+ goto free_struct;
-#ifdef CONFIG_X86_64
- status = efi_call_phys4(pci->attributes, pci,
- EfiPciIoAttributeOperationGet, 0,
- &attributes);
-#else
- status = efi_call_phys5(pci->attributes, pci,
- EfiPciIoAttributeOperationGet, 0, 0,
- &attributes);
-#endif
- if (status != EFI_SUCCESS)
- continue;
+ status = efi_early->call(pci->get_location, pci, &(rom->segment),
+ &(rom->bus), &(rom->device), &(rom->function));
- if (!pci->romimage || !pci->romsize)
- continue;
+ if (status != EFI_SUCCESS)
+ goto free_struct;
- size = pci->romsize + sizeof(*rom);
+ memcpy(rom->romdata, pci->romimage, pci->romsize);
+ return status;
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, size, &rom);
+free_struct:
+ efi_call_early(free_pool, rom);
+ return status;
+}
- if (status != EFI_SUCCESS)
- continue;
+static efi_status_t
+setup_efi_pci32(struct boot_params *params, void **pci_handle,
+ unsigned long size)
+{
+ efi_pci_io_protocol_32 *pci = NULL;
+ efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ u32 *handles = (u32 *)(unsigned long)pci_handle;
+ efi_status_t status;
+ unsigned long nr_pci;
+ struct setup_data *data;
+ int i;
- rom->data.type = SETUP_PCI;
- rom->data.len = size - sizeof(struct setup_data);
- rom->data.next = 0;
- rom->pcilen = pci->romsize;
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
- status = efi_call_phys5(pci->pci.read, pci,
- EfiPciIoWidthUint16, PCI_VENDOR_ID,
- 1, &(rom->vendor));
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
- if (status != EFI_SUCCESS)
- goto free_struct;
+ nr_pci = size / sizeof(u32);
+ for (i = 0; i < nr_pci; i++) {
+ struct pci_setup_rom *rom = NULL;
+ u32 h = handles[i];
- status = efi_call_phys5(pci->pci.read, pci,
- EfiPciIoWidthUint16, PCI_DEVICE_ID,
- 1, &(rom->devid));
+ status = efi_call_early(handle_protocol, h,
+ &pci_proto, (void **)&pci);
if (status != EFI_SUCCESS)
- goto free_struct;
+ continue;
- status = efi_call_phys5(pci->get_location, pci,
- &(rom->segment), &(rom->bus),
- &(rom->device), &(rom->function));
+ if (!pci)
+ continue;
+ status = __setup_efi_pci32(pci, &rom);
if (status != EFI_SUCCESS)
- goto free_struct;
-
- memcpy(rom->romdata, pci->romimage, pci->romsize);
+ continue;
if (data)
data->next = (unsigned long)rom;
@@ -358,105 +408,155 @@ static efi_status_t setup_efi_pci(struct boot_params *params)
data = (struct setup_data *)rom;
- continue;
- free_struct:
- efi_call_phys1(sys_table->boottime->free_pool, rom);
}
-free_handle:
- efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
return status;
}
-/*
- * See if we have Graphics Output Protocol
- */
-static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
- unsigned long size)
+static efi_status_t
+__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
{
- struct efi_graphics_output_protocol *gop, *first_gop;
- struct efi_pixel_bitmask pixel_info;
- unsigned long nr_gops;
+ struct pci_setup_rom *rom;
efi_status_t status;
- void **gop_handle;
- u16 width, height;
- u32 fb_base, fb_size;
- u32 pixels_per_scan_line;
- int pixel_format;
- int i;
+ unsigned long size;
+ uint64_t attributes;
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, size, &gop_handle);
+ status = efi_early->call(pci->attributes, pci,
+ EfiPciIoAttributeOperationGet, 0,
+ &attributes);
if (status != EFI_SUCCESS)
return status;
- status = efi_call_phys5(sys_table->boottime->locate_handle,
- EFI_LOCATE_BY_PROTOCOL, proto,
- NULL, &size, gop_handle);
+ if (!pci->romimage || !pci->romsize)
+ return EFI_INVALID_PARAMETER;
+
+ size = pci->romsize + sizeof(*rom);
+
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
if (status != EFI_SUCCESS)
- goto free_handle;
+ return status;
- first_gop = NULL;
+ rom->data.type = SETUP_PCI;
+ rom->data.len = size - sizeof(struct setup_data);
+ rom->data.next = 0;
+ rom->pcilen = pci->romsize;
+ *__rom = rom;
- nr_gops = size / sizeof(void *);
- for (i = 0; i < nr_gops; i++) {
- struct efi_graphics_output_mode_info *info;
- efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
- bool conout_found = false;
- void *dummy;
- void *h = gop_handle[i];
+ status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+ PCI_VENDOR_ID, 1, &(rom->vendor));
+
+ if (status != EFI_SUCCESS)
+ goto free_struct;
+
+ status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+ PCI_DEVICE_ID, 1, &(rom->devid));
+
+ if (status != EFI_SUCCESS)
+ goto free_struct;
+
+ status = efi_early->call(pci->get_location, pci, &(rom->segment),
+ &(rom->bus), &(rom->device), &(rom->function));
+
+ if (status != EFI_SUCCESS)
+ goto free_struct;
+
+ memcpy(rom->romdata, pci->romimage, pci->romsize);
+ return status;
+
+free_struct:
+ efi_call_early(free_pool, rom);
+ return status;
+
+}
+
+static efi_status_t
+setup_efi_pci64(struct boot_params *params, void **pci_handle,
+ unsigned long size)
+{
+ efi_pci_io_protocol_64 *pci = NULL;
+ efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ u64 *handles = (u64 *)(unsigned long)pci_handle;
+ efi_status_t status;
+ unsigned long nr_pci;
+ struct setup_data *data;
+ int i;
+
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
+
+ nr_pci = size / sizeof(u64);
+ for (i = 0; i < nr_pci; i++) {
+ struct pci_setup_rom *rom = NULL;
+ u64 h = handles[i];
+
+ status = efi_call_early(handle_protocol, h,
+ &pci_proto, (void **)&pci);
- status = efi_call_phys3(sys_table->boottime->handle_protocol,
- h, proto, &gop);
if (status != EFI_SUCCESS)
continue;
- status = efi_call_phys3(sys_table->boottime->handle_protocol,
- h, &conout_proto, &dummy);
+ if (!pci)
+ continue;
- if (status == EFI_SUCCESS)
- conout_found = true;
+ status = __setup_efi_pci64(pci, &rom);
+ if (status != EFI_SUCCESS)
+ continue;
- status = efi_call_phys4(gop->query_mode, gop,
- gop->mode->mode, &size, &info);
- if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
- /*
- * Systems that use the UEFI Console Splitter may
- * provide multiple GOP devices, not all of which are
- * backed by real hardware. The workaround is to search
- * for a GOP implementing the ConOut protocol, and if
- * one isn't found, to just fall back to the first GOP.
- */
- width = info->horizontal_resolution;
- height = info->vertical_resolution;
- fb_base = gop->mode->frame_buffer_base;
- fb_size = gop->mode->frame_buffer_size;
- pixel_format = info->pixel_format;
- pixel_info = info->pixel_information;
- pixels_per_scan_line = info->pixels_per_scan_line;
+ if (data)
+ data->next = (unsigned long)rom;
+ else
+ params->hdr.setup_data = (unsigned long)rom;
+
+ data = (struct setup_data *)rom;
- /*
- * Once we've found a GOP supporting ConOut,
- * don't bother looking any further.
- */
- first_gop = gop;
- if (conout_found)
- break;
- }
}
- /* Did we find any GOPs? */
- if (!first_gop)
+ return status;
+}
+
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+ efi_status_t status;
+ void **pci_handle = NULL;
+ efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ unsigned long size = 0;
+
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL,
+ &pci_proto, NULL, &size, pci_handle);
+
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ status = efi_call_early(allocate_pool,
+ EFI_LOADER_DATA,
+ size, (void **)&pci_handle);
+
+ if (status != EFI_SUCCESS)
+ return status;
+
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+ NULL, &size, pci_handle);
+ }
+
+ if (status != EFI_SUCCESS)
goto free_handle;
- /* EFI framebuffer */
- si->orig_video_isVGA = VIDEO_TYPE_EFI;
+ if (efi_early->is64)
+ status = setup_efi_pci64(params, pci_handle, size);
+ else
+ status = setup_efi_pci32(params, pci_handle, size);
- si->lfb_width = width;
- si->lfb_height = height;
- si->lfb_base = fb_base;
- si->pages = 1;
+free_handle:
+ efi_call_early(free_pool, pci_handle);
+ return status;
+}
+static void
+setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line,
+ struct efi_pixel_bitmask pixel_info, int pixel_format)
+{
if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
si->lfb_depth = 32;
si->lfb_linelength = pixels_per_scan_line * 4;
@@ -501,372 +601,426 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
si->rsvd_size = 0;
si->rsvd_pos = 0;
}
+}
- si->lfb_size = si->lfb_linelength * si->lfb_height;
+static efi_status_t
+__gop_query32(struct efi_graphics_output_protocol_32 *gop32,
+ struct efi_graphics_output_mode_info **info,
+ unsigned long *size, u32 *fb_base)
+{
+ struct efi_graphics_output_protocol_mode_32 *mode;
+ efi_status_t status;
+ unsigned long m;
- si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+ m = gop32->mode;
+ mode = (struct efi_graphics_output_protocol_mode_32 *)m;
-free_handle:
- efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
+ status = efi_early->call(gop32->query_mode, gop32,
+ mode->mode, size, info);
+ if (status != EFI_SUCCESS)
+ return status;
+
+ *fb_base = mode->frame_buffer_base;
return status;
}
-/*
- * See if we have Universal Graphics Adapter (UGA) protocol
- */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
- unsigned long size)
+static efi_status_t
+setup_gop32(struct screen_info *si, efi_guid_t *proto,
+ unsigned long size, void **gop_handle)
{
- struct efi_uga_draw_protocol *uga, *first_uga;
- unsigned long nr_ugas;
+ struct efi_graphics_output_protocol_32 *gop32, *first_gop;
+ unsigned long nr_gops;
+ u16 width, height;
+ u32 pixels_per_scan_line;
+ u32 fb_base;
+ struct efi_pixel_bitmask pixel_info;
+ int pixel_format;
efi_status_t status;
- u32 width, height;
- void **uga_handle = NULL;
+ u32 *handles = (u32 *)(unsigned long)gop_handle;
int i;
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, size, &uga_handle);
- if (status != EFI_SUCCESS)
- return status;
-
- status = efi_call_phys5(sys_table->boottime->locate_handle,
- EFI_LOCATE_BY_PROTOCOL, uga_proto,
- NULL, &size, uga_handle);
- if (status != EFI_SUCCESS)
- goto free_handle;
-
- first_uga = NULL;
+ first_gop = NULL;
+ gop32 = NULL;
- nr_ugas = size / sizeof(void *);
- for (i = 0; i < nr_ugas; i++) {
- efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
- void *handle = uga_handle[i];
- u32 w, h, depth, refresh;
- void *pciio;
+ nr_gops = size / sizeof(u32);
+ for (i = 0; i < nr_gops; i++) {
+ struct efi_graphics_output_mode_info *info = NULL;
+ efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+ bool conout_found = false;
+ void *dummy = NULL;
+ u32 h = handles[i];
- status = efi_call_phys3(sys_table->boottime->handle_protocol,
- handle, uga_proto, &uga);
+ status = efi_call_early(handle_protocol, h,
+ proto, (void **)&gop32);
if (status != EFI_SUCCESS)
continue;
- efi_call_phys3(sys_table->boottime->handle_protocol,
- handle, &pciio_proto, &pciio);
+ status = efi_call_early(handle_protocol, h,
+ &conout_proto, &dummy);
+ if (status == EFI_SUCCESS)
+ conout_found = true;
- status = efi_call_phys5(uga->get_mode, uga, &w, &h,
- &depth, &refresh);
- if (status == EFI_SUCCESS && (!first_uga || pciio)) {
- width = w;
- height = h;
+ status = __gop_query32(gop32, &info, &size, &fb_base);
+ if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+ /*
+ * Systems that use the UEFI Console Splitter may
+ * provide multiple GOP devices, not all of which are
+ * backed by real hardware. The workaround is to search
+ * for a GOP implementing the ConOut protocol, and if
+ * one isn't found, to just fall back to the first GOP.
+ */
+ width = info->horizontal_resolution;
+ height = info->vertical_resolution;
+ pixel_format = info->pixel_format;
+ pixel_info = info->pixel_information;
+ pixels_per_scan_line = info->pixels_per_scan_line;
/*
- * Once we've found a UGA supporting PCIIO,
+ * Once we've found a GOP supporting ConOut,
* don't bother looking any further.
*/
- if (pciio)
+ first_gop = gop32;
+ if (conout_found)
break;
-
- first_uga = uga;
}
}
- if (!first_uga)
- goto free_handle;
+ /* Did we find any GOPs? */
+ if (!first_gop)
+ goto out;
/* EFI framebuffer */
si->orig_video_isVGA = VIDEO_TYPE_EFI;
- si->lfb_depth = 32;
si->lfb_width = width;
si->lfb_height = height;
+ si->lfb_base = fb_base;
+ si->pages = 1;
- si->red_size = 8;
- si->red_pos = 16;
- si->green_size = 8;
- si->green_pos = 8;
- si->blue_size = 8;
- si->blue_pos = 0;
- si->rsvd_size = 8;
- si->rsvd_pos = 24;
+ setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
+ si->lfb_size = si->lfb_linelength * si->lfb_height;
-free_handle:
- efi_call_phys1(sys_table->boottime->free_pool, uga_handle);
+ si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+out:
return status;
}
-void setup_graphics(struct boot_params *boot_params)
+static efi_status_t
+__gop_query64(struct efi_graphics_output_protocol_64 *gop64,
+ struct efi_graphics_output_mode_info **info,
+ unsigned long *size, u32 *fb_base)
{
- efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID;
- struct screen_info *si;
- efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+ struct efi_graphics_output_protocol_mode_64 *mode;
efi_status_t status;
- unsigned long size;
- void **gop_handle = NULL;
- void **uga_handle = NULL;
+ unsigned long m;
- si = &boot_params->screen_info;
- memset(si, 0, sizeof(*si));
+ m = gop64->mode;
+ mode = (struct efi_graphics_output_protocol_mode_64 *)m;
- size = 0;
- status = efi_call_phys5(sys_table->boottime->locate_handle,
- EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
- NULL, &size, gop_handle);
- if (status == EFI_BUFFER_TOO_SMALL)
- status = setup_gop(si, &graphics_proto, size);
+ status = efi_early->call(gop64->query_mode, gop64,
+ mode->mode, size, info);
+ if (status != EFI_SUCCESS)
+ return status;
- if (status != EFI_SUCCESS) {
- size = 0;
- status = efi_call_phys5(sys_table->boottime->locate_handle,
- EFI_LOCATE_BY_PROTOCOL, &uga_proto,
- NULL, &size, uga_handle);
- if (status == EFI_BUFFER_TOO_SMALL)
- setup_uga(si, &uga_proto, size);
- }
+ *fb_base = mode->frame_buffer_base;
+ return status;
}
-struct initrd {
- efi_file_handle_t *handle;
- u64 size;
-};
-
-/*
- * Check the cmdline for a LILO-style initrd= arguments.
- *
- * We only support loading an initrd from the same filesystem as the
- * kernel image.
- */
-static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
- struct setup_header *hdr)
+static efi_status_t
+setup_gop64(struct screen_info *si, efi_guid_t *proto,
+ unsigned long size, void **gop_handle)
{
- struct initrd *initrds;
- unsigned long initrd_addr;
- efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
- u64 initrd_total;
- efi_file_io_interface_t *io;
- efi_file_handle_t *fh;
+ struct efi_graphics_output_protocol_64 *gop64, *first_gop;
+ unsigned long nr_gops;
+ u16 width, height;
+ u32 pixels_per_scan_line;
+ u32 fb_base;
+ struct efi_pixel_bitmask pixel_info;
+ int pixel_format;
efi_status_t status;
- int nr_initrds;
- char *str;
- int i, j, k;
+ u64 *handles = (u64 *)(unsigned long)gop_handle;
+ int i;
- initrd_addr = 0;
- initrd_total = 0;
+ first_gop = NULL;
+ gop64 = NULL;
- str = (char *)(unsigned long)hdr->cmd_line_ptr;
+ nr_gops = size / sizeof(u64);
+ for (i = 0; i < nr_gops; i++) {
+ struct efi_graphics_output_mode_info *info = NULL;
+ efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+ bool conout_found = false;
+ void *dummy = NULL;
+ u64 h = handles[i];
- j = 0; /* See close_handles */
+ status = efi_call_early(handle_protocol, h,
+ proto, (void **)&gop64);
+ if (status != EFI_SUCCESS)
+ continue;
- if (!str || !*str)
- return EFI_SUCCESS;
+ status = efi_call_early(handle_protocol, h,
+ &conout_proto, &dummy);
+ if (status == EFI_SUCCESS)
+ conout_found = true;
- for (nr_initrds = 0; *str; nr_initrds++) {
- str = strstr(str, "initrd=");
- if (!str)
- break;
+ status = __gop_query64(gop64, &info, &size, &fb_base);
+ if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+ /*
+ * Systems that use the UEFI Console Splitter may
+ * provide multiple GOP devices, not all of which are
+ * backed by real hardware. The workaround is to search
+ * for a GOP implementing the ConOut protocol, and if
+ * one isn't found, to just fall back to the first GOP.
+ */
+ width = info->horizontal_resolution;
+ height = info->vertical_resolution;
+ pixel_format = info->pixel_format;
+ pixel_info = info->pixel_information;
+ pixels_per_scan_line = info->pixels_per_scan_line;
- str += 7;
+ /*
+ * Once we've found a GOP supporting ConOut,
+ * don't bother looking any further.
+ */
+ first_gop = gop64;
+ if (conout_found)
+ break;
+ }
+ }
- /* Skip any leading slashes */
- while (*str == '/' || *str == '\\')
- str++;
+ /* Did we find any GOPs? */
+ if (!first_gop)
+ goto out;
- while (*str && *str != ' ' && *str != '\n')
- str++;
- }
+ /* EFI framebuffer */
+ si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+ si->lfb_width = width;
+ si->lfb_height = height;
+ si->lfb_base = fb_base;
+ si->pages = 1;
- if (!nr_initrds)
- return EFI_SUCCESS;
+ setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA,
- nr_initrds * sizeof(*initrds),
- &initrds);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for initrds\n");
- goto fail;
- }
+ si->lfb_size = si->lfb_linelength * si->lfb_height;
- str = (char *)(unsigned long)hdr->cmd_line_ptr;
- for (i = 0; i < nr_initrds; i++) {
- struct initrd *initrd;
- efi_file_handle_t *h;
- efi_file_info_t *info;
- efi_char16_t filename_16[256];
- unsigned long info_sz;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- efi_char16_t *p;
- u64 file_sz;
-
- str = strstr(str, "initrd=");
- if (!str)
- break;
+ si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+out:
+ return status;
+}
- str += 7;
+/*
+ * See if we have Graphics Output Protocol
+ */
+static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
+ unsigned long size)
+{
+ efi_status_t status;
+ void **gop_handle = NULL;
+
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ size, (void **)&gop_handle);
+ if (status != EFI_SUCCESS)
+ return status;
- initrd = &initrds[i];
- p = filename_16;
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL,
+ proto, NULL, &size, gop_handle);
+ if (status != EFI_SUCCESS)
+ goto free_handle;
- /* Skip any leading slashes */
- while (*str == '/' || *str == '\\')
- str++;
+ if (efi_early->is64)
+ status = setup_gop64(si, proto, size, gop_handle);
+ else
+ status = setup_gop32(si, proto, size, gop_handle);
- while (*str && *str != ' ' && *str != '\n') {
- if ((u8 *)p >= (u8 *)filename_16 + sizeof(filename_16))
- break;
+free_handle:
+ efi_call_early(free_pool, gop_handle);
+ return status;
+}
- if (*str == '/') {
- *p++ = '\\';
- *str++;
- } else {
- *p++ = *str++;
- }
- }
+static efi_status_t
+setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+{
+ struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+ efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+ unsigned long nr_ugas;
+ u32 *handles = (u32 *)uga_handle;;
+ efi_status_t status;
+ int i;
- *p = '\0';
+ first_uga = NULL;
+ nr_ugas = size / sizeof(u32);
+ for (i = 0; i < nr_ugas; i++) {
+ efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ u32 w, h, depth, refresh;
+ void *pciio;
+ u32 handle = handles[i];
- /* Only open the volume once. */
- if (!i) {
- efi_boot_services_t *boottime;
+ status = efi_call_early(handle_protocol, handle,
+ &uga_proto, (void **)&uga);
+ if (status != EFI_SUCCESS)
+ continue;
- boottime = sys_table->boottime;
+ efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
- status = efi_call_phys3(boottime->handle_protocol,
- image->device_handle, &fs_proto, &io);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to handle fs_proto\n");
- goto free_initrds;
- }
+ status = efi_early->call((unsigned long)uga->get_mode, uga,
+ &w, &h, &depth, &refresh);
+ if (status == EFI_SUCCESS && (!first_uga || pciio)) {
+ *width = w;
+ *height = h;
- status = efi_call_phys2(io->open_volume, io, &fh);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to open volume\n");
- goto free_initrds;
- }
- }
+ /*
+ * Once we've found a UGA supporting PCIIO,
+ * don't bother looking any further.
+ */
+ if (pciio)
+ break;
- status = efi_call_phys5(fh->open, fh, &h, filename_16,
- EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to open initrd file: ");
- efi_char16_printk(filename_16);
- efi_printk("\n");
- goto close_handles;
+ first_uga = uga;
}
+ }
- initrd->handle = h;
+ return status;
+}
- info_sz = 0;
- status = efi_call_phys4(h->get_info, h, &info_guid,
- &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk("Failed to get initrd info size\n");
- goto close_handles;
- }
+static efi_status_t
+setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+{
+ struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+ efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+ unsigned long nr_ugas;
+ u64 *handles = (u64 *)uga_handle;;
+ efi_status_t status;
+ int i;
-grow:
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, info_sz, &info);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for initrd info\n");
- goto close_handles;
- }
+ first_uga = NULL;
+ nr_ugas = size / sizeof(u64);
+ for (i = 0; i < nr_ugas; i++) {
+ efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ u32 w, h, depth, refresh;
+ void *pciio;
+ u64 handle = handles[i];
- status = efi_call_phys4(h->get_info, h, &info_guid,
- &info_sz, info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_phys1(sys_table->boottime->free_pool, info);
- goto grow;
- }
+ status = efi_call_early(handle_protocol, handle,
+ &uga_proto, (void **)&uga);
+ if (status != EFI_SUCCESS)
+ continue;
- file_sz = info->file_size;
- efi_call_phys1(sys_table->boottime->free_pool, info);
+ efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to get initrd info\n");
- goto close_handles;
- }
+ status = efi_early->call((unsigned long)uga->get_mode, uga,
+ &w, &h, &depth, &refresh);
+ if (status == EFI_SUCCESS && (!first_uga || pciio)) {
+ *width = w;
+ *height = h;
- initrd->size = file_sz;
- initrd_total += file_sz;
+ /*
+ * Once we've found a UGA supporting PCIIO,
+ * don't bother looking any further.
+ */
+ if (pciio)
+ break;
+
+ first_uga = uga;
+ }
}
- if (initrd_total) {
- unsigned long addr;
+ return status;
+}
- /*
- * Multiple initrd's need to be at consecutive
- * addresses in memory, so allocate enough memory for
- * all the initrd's.
- */
- status = high_alloc(initrd_total, 0x1000,
- &initrd_addr, hdr->initrd_addr_max);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc highmem for initrds\n");
- goto close_handles;
- }
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
+static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+ unsigned long size)
+{
+ efi_status_t status;
+ u32 width, height;
+ void **uga_handle = NULL;
- /* We've run out of free low memory. */
- if (initrd_addr > hdr->initrd_addr_max) {
- efi_printk("We've run out of free low memory\n");
- status = EFI_INVALID_PARAMETER;
- goto free_initrd_total;
- }
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ size, (void **)&uga_handle);
+ if (status != EFI_SUCCESS)
+ return status;
- addr = initrd_addr;
- for (j = 0; j < nr_initrds; j++) {
- u64 size;
-
- size = initrds[j].size;
- while (size) {
- u64 chunksize;
- if (size > EFI_READ_CHUNK_SIZE)
- chunksize = EFI_READ_CHUNK_SIZE;
- else
- chunksize = size;
- status = efi_call_phys3(fh->read,
- initrds[j].handle,
- &chunksize, addr);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to read initrd\n");
- goto free_initrd_total;
- }
- addr += chunksize;
- size -= chunksize;
- }
-
- efi_call_phys1(fh->close, initrds[j].handle);
- }
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL,
+ uga_proto, NULL, &size, uga_handle);
+ if (status != EFI_SUCCESS)
+ goto free_handle;
- }
+ height = 0;
+ width = 0;
- efi_call_phys1(sys_table->boottime->free_pool, initrds);
+ if (efi_early->is64)
+ status = setup_uga64(uga_handle, size, &width, &height);
+ else
+ status = setup_uga32(uga_handle, size, &width, &height);
- hdr->ramdisk_image = initrd_addr;
- hdr->ramdisk_size = initrd_total;
+ if (!width && !height)
+ goto free_handle;
- return status;
+ /* EFI framebuffer */
+ si->orig_video_isVGA = VIDEO_TYPE_EFI;
-free_initrd_total:
- low_free(initrd_total, initrd_addr);
+ si->lfb_depth = 32;
+ si->lfb_width = width;
+ si->lfb_height = height;
-close_handles:
- for (k = j; k < i; k++)
- efi_call_phys1(fh->close, initrds[k].handle);
-free_initrds:
- efi_call_phys1(sys_table->boottime->free_pool, initrds);
-fail:
- hdr->ramdisk_image = 0;
- hdr->ramdisk_size = 0;
+ si->red_size = 8;
+ si->red_pos = 16;
+ si->green_size = 8;
+ si->green_pos = 8;
+ si->blue_size = 8;
+ si->blue_pos = 0;
+ si->rsvd_size = 8;
+ si->rsvd_pos = 24;
+free_handle:
+ efi_call_early(free_pool, uga_handle);
return status;
}
+void setup_graphics(struct boot_params *boot_params)
+{
+ efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID;
+ struct screen_info *si;
+ efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+ efi_status_t status;
+ unsigned long size;
+ void **gop_handle = NULL;
+ void **uga_handle = NULL;
+
+ si = &boot_params->screen_info;
+ memset(si, 0, sizeof(*si));
+
+ size = 0;
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL,
+ &graphics_proto, NULL, &size, gop_handle);
+ if (status == EFI_BUFFER_TOO_SMALL)
+ status = setup_gop(si, &graphics_proto, size);
+
+ if (status != EFI_SUCCESS) {
+ size = 0;
+ status = efi_call_early(locate_handle,
+ EFI_LOCATE_BY_PROTOCOL,
+ &uga_proto, NULL, &size, uga_handle);
+ if (status == EFI_BUFFER_TOO_SMALL)
+ setup_uga(si, &uga_proto, size);
+ }
+}
+
/*
* Because the x86 boot code expects to be passed a boot_params we
* need to create one ourselves (usually the bootloader would create
* one for us).
+ *
+ * The caller is responsible for filling out ->code32_start in the
+ * returned boot_params.
*/
-struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
+struct boot_params *make_boot_params(struct efi_config *c)
{
struct boot_params *boot_params;
struct sys_desc_table *sdt;
@@ -874,32 +1028,41 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
struct setup_header *hdr;
struct efi_info *efi;
efi_loaded_image_t *image;
- void *options;
- u32 load_options_size;
+ void *options, *handle;
efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
int options_size = 0;
efi_status_t status;
- unsigned long cmdline;
+ char *cmdline_ptr;
u16 *s2;
u8 *s1;
int i;
+ unsigned long ramdisk_addr;
+ unsigned long ramdisk_size;
- sys_table = _table;
+ efi_early = c;
+ sys_table = (efi_system_table_t *)(unsigned long)efi_early->table;
+ handle = (void *)(unsigned long)efi_early->image_handle;
/* Check if we were booted by the EFI firmware */
if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
return NULL;
- status = efi_call_phys3(sys_table->boottime->handle_protocol,
- handle, &proto, (void *)&image);
+ if (efi_early->is64)
+ setup_boot_services64(efi_early);
+ else
+ setup_boot_services32(efi_early);
+
+ status = efi_call_early(handle_protocol, handle,
+ &proto, (void *)&image);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+ efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
return NULL;
}
- status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+ status = efi_low_alloc(sys_table, 0x4000, 1,
+ (unsigned long *)&boot_params);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc lowmem for boot params\n");
+ efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
return NULL;
}
@@ -921,45 +1084,13 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
hdr->vid_mode = 0xffff;
hdr->boot_flag = 0xAA55;
- hdr->code32_start = (__u64)(unsigned long)image->image_base;
-
hdr->type_of_loader = 0x21;
/* Convert unicode cmdline to ascii */
- options = image->load_options;
- load_options_size = image->load_options_size / 2; /* ASCII */
- cmdline = 0;
- s2 = (u16 *)options;
-
- if (s2) {
- while (*s2 && *s2 != '\n' && options_size < load_options_size) {
- s2++;
- options_size++;
- }
-
- if (options_size) {
- if (options_size > hdr->cmdline_size)
- options_size = hdr->cmdline_size;
-
- options_size++; /* NUL termination */
-
- status = low_alloc(options_size, 1, &cmdline);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for cmdline\n");
- goto fail;
- }
-
- s1 = (u8 *)(unsigned long)cmdline;
- s2 = (u16 *)options;
-
- for (i = 0; i < options_size - 1; i++)
- *s1++ = *s2++;
-
- *s1 = '\0';
- }
- }
-
- hdr->cmd_line_ptr = cmdline;
+ cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
+ if (!cmdline_ptr)
+ goto fail;
+ hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
hdr->ramdisk_image = 0;
hdr->ramdisk_size = 0;
@@ -969,96 +1100,64 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
memset(sdt, 0, sizeof(*sdt));
- status = handle_ramdisks(image, hdr);
+ status = handle_cmdline_files(sys_table, image,
+ (char *)(unsigned long)hdr->cmd_line_ptr,
+ "initrd=", hdr->initrd_addr_max,
+ &ramdisk_addr, &ramdisk_size);
if (status != EFI_SUCCESS)
goto fail2;
+ hdr->ramdisk_image = ramdisk_addr;
+ hdr->ramdisk_size = ramdisk_size;
return boot_params;
fail2:
- if (options_size)
- low_free(options_size, hdr->cmd_line_ptr);
+ efi_free(sys_table, options_size, hdr->cmd_line_ptr);
fail:
- low_free(0x4000, (unsigned long)boot_params);
+ efi_free(sys_table, 0x4000, (unsigned long)boot_params);
return NULL;
}
-static efi_status_t exit_boot(struct boot_params *boot_params,
- void *handle)
+static void add_e820ext(struct boot_params *params,
+ struct setup_data *e820ext, u32 nr_entries)
{
- struct efi_info *efi = &boot_params->efi_info;
- struct e820entry *e820_map = &boot_params->e820_map[0];
- struct e820entry *prev = NULL;
- unsigned long size, key, desc_size, _size;
- efi_memory_desc_t *mem_map;
+ struct setup_data *data;
efi_status_t status;
- __u32 desc_version;
- bool called_exit = false;
- u8 nr_entries;
- int i;
-
- size = sizeof(*mem_map) * 32;
-
-again:
- size += sizeof(*mem_map) * 2;
- _size = size;
- status = low_alloc(size, 1, (unsigned long *)&mem_map);
- if (status != EFI_SUCCESS)
- return status;
-
-get_map:
- status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
- mem_map, &key, &desc_size, &desc_version);
- if (status == EFI_BUFFER_TOO_SMALL) {
- low_free(_size, (unsigned long)mem_map);
- goto again;
- }
-
- if (status != EFI_SUCCESS)
- goto free_mem_map;
+ unsigned long size;
- memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
- efi->efi_systab = (unsigned long)sys_table;
- efi->efi_memdesc_size = desc_size;
- efi->efi_memdesc_version = desc_version;
- efi->efi_memmap = (unsigned long)mem_map;
- efi->efi_memmap_size = size;
+ e820ext->type = SETUP_E820_EXT;
+ e820ext->len = nr_entries * sizeof(struct e820entry);
+ e820ext->next = 0;
-#ifdef CONFIG_X86_64
- efi->efi_systab_hi = (unsigned long)sys_table >> 32;
- efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
-#endif
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
- /* Might as well exit boot services now */
- status = efi_call_phys2(sys_table->boottime->exit_boot_services,
- handle, key);
- if (status != EFI_SUCCESS) {
- /*
- * ExitBootServices() will fail if any of the event
- * handlers change the memory map. In which case, we
- * must be prepared to retry, but only once so that
- * we're guaranteed to exit on repeated failures instead
- * of spinning forever.
- */
- if (called_exit)
- goto free_mem_map;
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
- called_exit = true;
- goto get_map;
- }
+ if (data)
+ data->next = (unsigned long)e820ext;
+ else
+ params->hdr.setup_data = (unsigned long)e820ext;
+}
- /* Historic? */
- boot_params->alt_mem_k = 32 * 1024;
+static efi_status_t setup_e820(struct boot_params *params,
+ struct setup_data *e820ext, u32 e820ext_size)
+{
+ struct e820entry *e820_map = &params->e820_map[0];
+ struct efi_info *efi = &params->efi_info;
+ struct e820entry *prev = NULL;
+ u32 nr_entries;
+ u32 nr_desc;
+ int i;
- /*
- * Convert the EFI memory map to E820.
- */
nr_entries = 0;
- for (i = 0; i < size / desc_size; i++) {
+ nr_desc = efi->efi_memmap_size / efi->efi_memdesc_size;
+
+ for (i = 0; i < nr_desc; i++) {
efi_memory_desc_t *d;
unsigned int e820_type = 0;
- unsigned long m = (unsigned long)mem_map;
+ unsigned long m = efi->efi_memmap;
- d = (efi_memory_desc_t *)(m + (i * desc_size));
+ d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
switch (d->type) {
case EFI_RESERVED_TYPE:
case EFI_RUNTIME_SERVICES_CODE:
@@ -1095,58 +1194,148 @@ get_map:
/* Merge adjacent mappings */
if (prev && prev->type == e820_type &&
- (prev->addr + prev->size) == d->phys_addr)
+ (prev->addr + prev->size) == d->phys_addr) {
prev->size += d->num_pages << 12;
- else {
- e820_map->addr = d->phys_addr;
- e820_map->size = d->num_pages << 12;
- e820_map->type = e820_type;
- prev = e820_map++;
- nr_entries++;
+ continue;
+ }
+
+ if (nr_entries == ARRAY_SIZE(params->e820_map)) {
+ u32 need = (nr_desc - i) * sizeof(struct e820entry) +
+ sizeof(struct setup_data);
+
+ if (!e820ext || e820ext_size < need)
+ return EFI_BUFFER_TOO_SMALL;
+
+ /* boot_params map full, switch to e820 extended */
+ e820_map = (struct e820entry *)e820ext->data;
}
+
+ e820_map->addr = d->phys_addr;
+ e820_map->size = d->num_pages << PAGE_SHIFT;
+ e820_map->type = e820_type;
+ prev = e820_map++;
+ nr_entries++;
+ }
+
+ if (nr_entries > ARRAY_SIZE(params->e820_map)) {
+ u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map);
+
+ add_e820ext(params, e820ext, nr_e820ext);
+ nr_entries -= nr_e820ext;
}
- boot_params->e820_entries = nr_entries;
+ params->e820_entries = (u8)nr_entries;
return EFI_SUCCESS;
+}
+
+static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
+ u32 *e820ext_size)
+{
+ efi_status_t status;
+ unsigned long size;
+
+ size = sizeof(struct setup_data) +
+ sizeof(struct e820entry) * nr_desc;
+
+ if (*e820ext) {
+ efi_call_early(free_pool, *e820ext);
+ *e820ext = NULL;
+ *e820ext_size = 0;
+ }
+
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ size, (void **)e820ext);
+ if (status == EFI_SUCCESS)
+ *e820ext_size = size;
-free_mem_map:
- low_free(_size, (unsigned long)mem_map);
return status;
}
-static efi_status_t relocate_kernel(struct setup_header *hdr)
+static efi_status_t exit_boot(struct boot_params *boot_params,
+ void *handle, bool is64)
{
- unsigned long start, nr_pages;
+ struct efi_info *efi = &boot_params->efi_info;
+ unsigned long map_sz, key, desc_size;
+ efi_memory_desc_t *mem_map;
+ struct setup_data *e820ext;
+ const char *signature;
+ __u32 e820ext_size;
+ __u32 nr_desc, prev_nr_desc;
efi_status_t status;
+ __u32 desc_version;
+ bool called_exit = false;
+ u8 nr_entries;
+ int i;
- /*
- * The EFI firmware loader could have placed the kernel image
- * anywhere in memory, but the kernel has various restrictions
- * on the max physical address it can run at. Attempt to move
- * the kernel to boot_params.pref_address, or as low as
- * possible.
- */
- start = hdr->pref_address;
- nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ nr_desc = 0;
+ e820ext = NULL;
+ e820ext_size = 0;
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &start);
- if (status != EFI_SUCCESS) {
- status = low_alloc(hdr->init_size, hdr->kernel_alignment,
- &start);
+get_map:
+ status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
+ &desc_version, &key);
+
+ if (status != EFI_SUCCESS)
+ return status;
+
+ prev_nr_desc = nr_desc;
+ nr_desc = map_sz / desc_size;
+ if (nr_desc > prev_nr_desc &&
+ nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
+ u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
+
+ status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
if (status != EFI_SUCCESS)
- efi_printk("Failed to alloc mem for kernel\n");
+ goto free_mem_map;
+
+ efi_call_early(free_pool, mem_map);
+ goto get_map; /* Allocated memory, get map again */
}
- if (status == EFI_SUCCESS)
- memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
- hdr->init_size);
+ signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+ memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
- hdr->pref_address = hdr->code32_start;
- hdr->code32_start = (__u32)start;
+ efi->efi_systab = (unsigned long)sys_table;
+ efi->efi_memdesc_size = desc_size;
+ efi->efi_memdesc_version = desc_version;
+ efi->efi_memmap = (unsigned long)mem_map;
+ efi->efi_memmap_size = map_sz;
+
+#ifdef CONFIG_X86_64
+ efi->efi_systab_hi = (unsigned long)sys_table >> 32;
+ efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+#endif
+
+ /* Might as well exit boot services now */
+ status = efi_call_early(exit_boot_services, handle, key);
+ if (status != EFI_SUCCESS) {
+ /*
+ * ExitBootServices() will fail if any of the event
+ * handlers change the memory map. In which case, we
+ * must be prepared to retry, but only once so that
+ * we're guaranteed to exit on repeated failures instead
+ * of spinning forever.
+ */
+ if (called_exit)
+ goto free_mem_map;
+
+ called_exit = true;
+ efi_call_early(free_pool, mem_map);
+ goto get_map;
+ }
+ /* Historic? */
+ boot_params->alt_mem_k = 32 * 1024;
+
+ status = setup_e820(boot_params, e820ext, e820ext_size);
+ if (status != EFI_SUCCESS)
+ return status;
+
+ return EFI_SUCCESS;
+
+free_mem_map:
+ efi_call_early(free_pool, mem_map);
return status;
}
@@ -1154,14 +1343,23 @@ static efi_status_t relocate_kernel(struct setup_header *hdr)
* On success we return a pointer to a boot_params structure, and NULL
* on failure.
*/
-struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
+struct boot_params *efi_main(struct efi_config *c,
struct boot_params *boot_params)
{
- struct desc_ptr *gdt, *idt;
+ struct desc_ptr *gdt = NULL;
efi_loaded_image_t *image;
struct setup_header *hdr = &boot_params->hdr;
efi_status_t status;
struct desc_struct *desc;
+ void *handle;
+ efi_system_table_t *_table;
+ bool is64;
+
+ efi_early = c;
+
+ _table = (efi_system_table_t *)(unsigned long)efi_early->table;
+ handle = (void *)(unsigned long)efi_early->image_handle;
+ is64 = efi_early->is64;
sys_table = _table;
@@ -1169,48 +1367,48 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
goto fail;
+ if (is64)
+ setup_boot_services64(efi_early);
+ else
+ setup_boot_services32(efi_early);
+
setup_graphics(boot_params);
setup_efi_pci(boot_params);
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, sizeof(*gdt),
- (void **)&gdt);
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ sizeof(*gdt), (void **)&gdt);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
goto fail;
}
gdt->size = 0x800;
- status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt\n");
- goto fail;
- }
-
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, sizeof(*idt),
- (void **)&idt);
+ status = efi_low_alloc(sys_table, gdt->size, 8,
+ (unsigned long *)&gdt->address);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for idt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt\n");
goto fail;
}
- idt->size = 0;
- idt->address = 0;
-
/*
* If the kernel isn't already loaded at the preferred load
* address, relocate it.
*/
if (hdr->pref_address != hdr->code32_start) {
- status = relocate_kernel(hdr);
-
+ unsigned long bzimage_addr = hdr->code32_start;
+ status = efi_relocate_kernel(sys_table, &bzimage_addr,
+ hdr->init_size, hdr->init_size,
+ hdr->pref_address,
+ hdr->kernel_alignment);
if (status != EFI_SUCCESS)
goto fail;
+
+ hdr->pref_address = hdr->code32_start;
+ hdr->code32_start = bzimage_addr;
}
- status = exit_boot(boot_params, handle);
+ status = exit_boot(boot_params, handle, is64);
if (status != EFI_SUCCESS)
goto fail;
@@ -1267,10 +1465,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
desc->base2 = 0x00;
#endif /* CONFIG_X86_64 */
- asm volatile ("lidt %0" : : "m" (*idt));
- asm volatile ("lgdt %0" : : "m" (*gdt));
-
asm volatile("cli");
+ asm volatile ("lgdt %0" : : "m" (*gdt));
return boot_params;
fail:
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e5b0a8f91c5..c88c31ecad1 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -11,9 +11,6 @@
#define DESC_TYPE_CODE_DATA (1 << 0)
-#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
-#define EFI_READ_CHUNK_SIZE (1024 * 1024)
-
#define EFI_CONSOLE_OUT_DEVICE_GUID \
EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \
0x3f, 0xc1, 0x4d)
@@ -40,6 +37,24 @@ struct efi_graphics_output_mode_info {
u32 pixels_per_scan_line;
} __packed;
+struct efi_graphics_output_protocol_mode_32 {
+ u32 max_mode;
+ u32 mode;
+ u32 info;
+ u32 size_of_info;
+ u64 frame_buffer_base;
+ u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+ u32 max_mode;
+ u32 mode;
+ u64 info;
+ u64 size_of_info;
+ u64 frame_buffer_base;
+ u64 frame_buffer_size;
+} __packed;
+
struct efi_graphics_output_protocol_mode {
u32 max_mode;
u32 mode;
@@ -49,6 +64,20 @@ struct efi_graphics_output_protocol_mode {
unsigned long frame_buffer_size;
} __packed;
+struct efi_graphics_output_protocol_32 {
+ u32 query_mode;
+ u32 set_mode;
+ u32 blt;
+ u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+ u64 query_mode;
+ u64 set_mode;
+ u64 blt;
+ u64 mode;
+};
+
struct efi_graphics_output_protocol {
void *query_mode;
unsigned long set_mode;
@@ -56,16 +85,38 @@ struct efi_graphics_output_protocol {
struct efi_graphics_output_protocol_mode *mode;
};
+struct efi_uga_draw_protocol_32 {
+ u32 get_mode;
+ u32 set_mode;
+ u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+ u64 get_mode;
+ u64 set_mode;
+ u64 blt;
+};
+
struct efi_uga_draw_protocol {
void *get_mode;
void *set_mode;
void *blt;
};
-struct efi_simple_text_output_protocol {
- void *reset;
- void *output_string;
- void *test_string;
-};
+struct efi_config {
+ u64 image_handle;
+ u64 table;
+ u64 allocate_pool;
+ u64 allocate_pages;
+ u64 get_memory_map;
+ u64 free_pool;
+ u64 free_pages;
+ u64 locate_handle;
+ u64 handle_protocol;
+ u64 exit_boot_services;
+ u64 text_output;
+ efi_status_t (*call)(unsigned long, ...);
+ bool is64;
+} __packed;
#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
index cedc60de86e..7ff3632806b 100644
--- a/arch/x86/boot/compressed/efi_stub_64.S
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -1 +1,30 @@
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+
#include "../../platform/efi/efi_stub_64.S"
+
+#ifdef CONFIG_EFI_MIXED
+ .code64
+ .text
+ENTRY(efi64_thunk)
+ push %rbp
+ push %rbx
+
+ subq $16, %rsp
+ leaq efi_exit32(%rip), %rax
+ movl %eax, 8(%rsp)
+ leaq efi_gdt64(%rip), %rax
+ movl %eax, 4(%rsp)
+ movl %eax, 2(%rax) /* Fixup the gdt base address */
+ leaq efi32_boot_gdt(%rip), %rax
+ movl %eax, (%rsp)
+
+ call __efi64_thunk
+
+ addq $16, %rsp
+ pop %rbx
+ pop %rbp
+ ret
+ENDPROC(efi64_thunk)
+#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 1e3184f6072..cbed1407a5c 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -42,33 +42,56 @@ ENTRY(startup_32)
ENTRY(efi_pe_entry)
add $0x4, %esp
+ call 1f
+1: popl %esi
+ subl $1b, %esi
+
+ popl %ecx
+ movl %ecx, efi32_config(%esi) /* Handle */
+ popl %ecx
+ movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */
+
+ /* Relocate efi_config->call() */
+ leal efi32_config(%esi), %eax
+ add %esi, 88(%eax)
+ pushl %eax
+
call make_boot_params
cmpl $0, %eax
- je 1f
- movl 0x4(%esp), %esi
- movl (%esp), %ecx
+ je fail
+ movl %esi, BP_code32_start(%eax)
+ popl %ecx
pushl %eax
- pushl %esi
pushl %ecx
- sub $0x4, %esp
+ jmp 2f /* Skip efi_config initialization */
-ENTRY(efi_stub_entry)
+ENTRY(efi32_stub_entry)
add $0x4, %esp
+ popl %ecx
+ popl %edx
+
+ call 1f
+1: popl %esi
+ subl $1b, %esi
+
+ movl %ecx, efi32_config(%esi) /* Handle */
+ movl %edx, efi32_config+8(%esi) /* EFI System table pointer */
+
+ /* Relocate efi_config->call() */
+ leal efi32_config(%esi), %eax
+ add %esi, 88(%eax)
+ pushl %eax
+2:
call efi_main
cmpl $0, %eax
movl %eax, %esi
jne 2f
-1:
+fail:
/* EFI init failed, so hang. */
hlt
- jmp 1b
+ jmp fail
2:
- call 3f
-3:
- popl %eax
- subl $3b, %eax
- subl BP_pref_address(%esi), %eax
- add BP_code32_start(%esi), %eax
+ movl BP_code32_start(%esi), %eax
leal preferred_addr(%eax), %eax
jmp *%eax
@@ -117,9 +140,11 @@ preferred_addr:
addl %eax, %ebx
notl %eax
andl %eax, %ebx
-#else
- movl $LOAD_PHYSICAL_ADDR, %ebx
+ cmpl $LOAD_PHYSICAL_ADDR, %ebx
+ jge 1f
#endif
+ movl $LOAD_PHYSICAL_ADDR, %ebx
+1:
/* Target address to relocate to for decompression */
addl $z_extract_offset, %ebx
@@ -181,8 +206,9 @@ relocated:
/*
* Do the decompression, and jump to the new kernel..
*/
- leal z_extract_offset_negative(%ebx), %ebp
/* push arguments for decompress_kernel: */
+ pushl $z_output_len /* decompressed length */
+ leal z_extract_offset_negative(%ebx), %ebp
pushl %ebp /* output address */
pushl $z_input_len /* input_len */
leal input_data(%ebx), %eax
@@ -190,40 +216,23 @@ relocated:
leal boot_heap(%ebx), %eax
pushl %eax /* heap area */
pushl %esi /* real mode pointer */
- call decompress_kernel
- addl $20, %esp
-
-#if CONFIG_RELOCATABLE
-/*
- * Find the address of the relocations.
- */
- leal z_output_len(%ebp), %edi
-
-/*
- * Calculate the delta between where vmlinux was compiled to run
- * and where it was actually loaded.
- */
- movl %ebp, %ebx
- subl $LOAD_PHYSICAL_ADDR, %ebx
- jz 2f /* Nothing to be done if loaded at compiled addr. */
-/*
- * Process relocations.
- */
-
-1: subl $4, %edi
- movl (%edi), %ecx
- testl %ecx, %ecx
- jz 2f
- addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
- jmp 1b
-2:
-#endif
+ call decompress_kernel /* returns kernel location in %eax */
+ addl $24, %esp
/*
* Jump to the decompressed kernel.
*/
xorl %ebx, %ebx
- jmp *%ebp
+ jmp *%eax
+
+#ifdef CONFIG_EFI_STUB
+ .data
+efi32_config:
+ .fill 11,8,0
+ .long efi_call_phys
+ .long 0
+ .byte 0
+#endif
/*
* Stack and heap for uncompression
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 06e71c2c16b..2884e0c3e8a 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -94,9 +94,11 @@ ENTRY(startup_32)
addl %eax, %ebx
notl %eax
andl %eax, %ebx
-#else
- movl $LOAD_PHYSICAL_ADDR, %ebx
+ cmpl $LOAD_PHYSICAL_ADDR, %ebx
+ jge 1f
#endif
+ movl $LOAD_PHYSICAL_ADDR, %ebx
+1:
/* Target address to relocate to for decompression */
addl $z_extract_offset, %ebx
@@ -111,7 +113,8 @@ ENTRY(startup_32)
lgdt gdt(%ebp)
/* Enable PAE mode */
- movl $(X86_CR4_PAE), %eax
+ movl %cr4, %eax
+ orl $X86_CR4_PAE, %eax
movl %eax, %cr4
/*
@@ -176,6 +179,13 @@ ENTRY(startup_32)
*/
pushl $__KERNEL_CS
leal startup_64(%ebp), %eax
+#ifdef CONFIG_EFI_MIXED
+ movl efi32_config(%ebp), %ebx
+ cmp $0, %ebx
+ jz 1f
+ leal handover_entry(%ebp), %eax
+1:
+#endif
pushl %eax
/* Enter paged protected Mode, activating Long Mode */
@@ -186,6 +196,30 @@ ENTRY(startup_32)
lret
ENDPROC(startup_32)
+#ifdef CONFIG_EFI_MIXED
+ .org 0x190
+ENTRY(efi32_stub_entry)
+ add $0x4, %esp /* Discard return address */
+ popl %ecx
+ popl %edx
+ popl %esi
+
+ leal (BP_scratch+4)(%esi), %esp
+ call 1f
+1: pop %ebp
+ subl $1b, %ebp
+
+ movl %ecx, efi32_config(%ebp)
+ movl %edx, efi32_config+8(%ebp)
+ sgdtl efi32_boot_gdt(%ebp)
+
+ leal efi32_config(%ebp), %eax
+ movl %eax, efi_config(%ebp)
+
+ jmp startup_32
+ENDPROC(efi32_stub_entry)
+#endif
+
.code64
.org 0x200
ENTRY(startup_64)
@@ -207,33 +241,52 @@ ENTRY(startup_64)
jmp preferred_addr
ENTRY(efi_pe_entry)
- mov %rcx, %rdi
- mov %rdx, %rsi
- pushq %rdi
- pushq %rsi
+ movq %rcx, efi64_config(%rip) /* Handle */
+ movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */
+
+ leaq efi64_config(%rip), %rax
+ movq %rax, efi_config(%rip)
+
+ call 1f
+1: popq %rbp
+ subq $1b, %rbp
+
+ /*
+ * Relocate efi_config->call().
+ */
+ addq %rbp, efi64_config+88(%rip)
+
+ movq %rax, %rdi
call make_boot_params
cmpq $0,%rax
- je 1f
- mov %rax, %rdx
- popq %rsi
- popq %rdi
+ je fail
+ mov %rax, %rsi
+ leaq startup_32(%rip), %rax
+ movl %eax, BP_code32_start(%rsi)
+ jmp 2f /* Skip the relocation */
+
+handover_entry:
+ call 1f
+1: popq %rbp
+ subq $1b, %rbp
-ENTRY(efi_stub_entry)
+ /*
+ * Relocate efi_config->call().
+ */
+ movq efi_config(%rip), %rax
+ addq %rbp, 88(%rax)
+2:
+ movq efi_config(%rip), %rdi
call efi_main
movq %rax,%rsi
cmpq $0,%rax
jne 2f
-1:
+fail:
/* EFI init failed, so hang. */
hlt
- jmp 1b
+ jmp fail
2:
- call 3f
-3:
- popq %rax
- subq $3b, %rax
- subq BP_pref_address(%rsi), %rax
- add BP_code32_start(%esi), %eax
+ movl BP_code32_start(%esi), %eax
leaq preferred_addr(%rax), %rax
jmp *%rax
@@ -269,9 +322,11 @@ preferred_addr:
addq %rax, %rbp
notq %rax
andq %rax, %rbp
-#else
- movq $LOAD_PHYSICAL_ADDR, %rbp
+ cmpq $LOAD_PHYSICAL_ADDR, %rbp
+ jge 1f
#endif
+ movq $LOAD_PHYSICAL_ADDR, %rbp
+1:
/* Target address to relocate to for decompression */
leaq z_extract_offset(%rbp), %rbx
@@ -303,6 +358,20 @@ preferred_addr:
leaq relocated(%rbx), %rax
jmp *%rax
+#ifdef CONFIG_EFI_STUB
+ .org 0x390
+ENTRY(efi64_stub_entry)
+ movq %rdi, efi64_config(%rip) /* Handle */
+ movq %rsi, efi64_config+8(%rip) /* EFI System table pointer */
+
+ leaq efi64_config(%rip), %rax
+ movq %rax, efi_config(%rip)
+
+ movq %rdx, %rsi
+ jmp handover_entry
+ENDPROC(efi64_stub_entry)
+#endif
+
.text
relocated:
@@ -338,13 +407,14 @@ relocated:
leaq input_data(%rip), %rdx /* input_data */
movl $z_input_len, %ecx /* input_len */
movq %rbp, %r8 /* output target address */
- call decompress_kernel
+ movq $z_output_len, %r9 /* decompressed length */
+ call decompress_kernel /* returns kernel location in %rax */
popq %rsi
/*
* Jump to the decompressed kernel.
*/
- jmp *%rbp
+ jmp *%rax
.code32
no_longmode:
@@ -367,6 +437,25 @@ gdt:
.quad 0x0000000000000000 /* TS continued */
gdt_end:
+#ifdef CONFIG_EFI_STUB
+efi_config:
+ .quad 0
+
+#ifdef CONFIG_EFI_MIXED
+ .global efi32_config
+efi32_config:
+ .fill 11,8,0
+ .quad efi64_thunk
+ .byte 0
+#endif
+
+ .global efi64_config
+efi64_config:
+ .fill 11,8,0
+ .quad efi_call
+ .byte 1
+#endif /* CONFIG_EFI_STUB */
+
/*
* Stack and heap for uncompression
*/
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0319c88290a..57ab74df7ee 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -10,6 +10,7 @@
*/
#include "misc.h"
+#include "../string.h"
/* WARNING!!
* This code is compiled with -fPIC and it is relocated dynamically
@@ -97,8 +98,14 @@
*/
#define STATIC static
-#undef memset
#undef memcpy
+
+/*
+ * Use a normal definition of memset() from string.c. There are already
+ * included header files which expect a definition of memset() and by
+ * the time we define memset macro, it is too late.
+ */
+#undef memset
#define memzero(s, n) memset((s), 0, (n))
@@ -109,17 +116,8 @@ static void error(char *m);
*/
struct boot_params *real_mode; /* Pointer to real-mode data */
-void *memset(void *s, int c, size_t n);
-void *memcpy(void *dest, const void *src, size_t n);
-
-#ifdef CONFIG_X86_64
-#define memptr long
-#else
-#define memptr unsigned
-#endif
-
-static memptr free_mem_ptr;
-static memptr free_mem_end_ptr;
+memptr free_mem_ptr;
+memptr free_mem_end_ptr;
static char *vidmem;
static int vidport;
@@ -222,45 +220,6 @@ void __putstr(const char *s)
outb(0xff & (pos >> 1), vidport+1);
}
-void *memset(void *s, int c, size_t n)
-{
- int i;
- char *ss = s;
-
- for (i = 0; i < n; i++)
- ss[i] = c;
- return s;
-}
-#ifdef CONFIG_X86_32
-void *memcpy(void *dest, const void *src, size_t n)
-{
- int d0, d1, d2;
- asm volatile(
- "rep ; movsl\n\t"
- "movl %4,%%ecx\n\t"
- "rep ; movsb\n\t"
- : "=&c" (d0), "=&D" (d1), "=&S" (d2)
- : "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
- : "memory");
-
- return dest;
-}
-#else
-void *memcpy(void *dest, const void *src, size_t n)
-{
- long d0, d1, d2;
- asm volatile(
- "rep ; movsq\n\t"
- "movq %4,%%rcx\n\t"
- "rep ; movsb\n\t"
- : "=&c" (d0), "=&D" (d1), "=&S" (d2)
- : "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
- : "memory");
-
- return dest;
-}
-#endif
-
static void error(char *x)
{
error_putstr("\n\n");
@@ -271,6 +230,79 @@ static void error(char *x)
asm("hlt");
}
+#if CONFIG_X86_NEED_RELOCS
+static void handle_relocations(void *output, unsigned long output_len)
+{
+ int *reloc;
+ unsigned long delta, map, ptr;
+ unsigned long min_addr = (unsigned long)output;
+ unsigned long max_addr = min_addr + output_len;
+
+ /*
+ * Calculate the delta between where vmlinux was linked to load
+ * and where it was actually loaded.
+ */
+ delta = min_addr - LOAD_PHYSICAL_ADDR;
+ if (!delta) {
+ debug_putstr("No relocation needed... ");
+ return;
+ }
+ debug_putstr("Performing relocations... ");
+
+ /*
+ * The kernel contains a table of relocation addresses. Those
+ * addresses have the final load address of the kernel in virtual
+ * memory. We are currently working in the self map. So we need to
+ * create an adjustment for kernel memory addresses to the self map.
+ * This will involve subtracting out the base address of the kernel.
+ */
+ map = delta - __START_KERNEL_map;
+
+ /*
+ * Process relocations: 32 bit relocations first then 64 bit after.
+ * Two sets of binary relocations are added to the end of the kernel
+ * before compression. Each relocation table entry is the kernel
+ * address of the location which needs to be updated stored as a
+ * 32-bit value which is sign extended to 64 bits.
+ *
+ * Format is:
+ *
+ * kernel bits...
+ * 0 - zero terminator for 64 bit relocations
+ * 64 bit relocation repeated
+ * 0 - zero terminator for 32 bit relocations
+ * 32 bit relocation repeated
+ *
+ * So we work backwards from the end of the decompressed image.
+ */
+ for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
+ int extended = *reloc;
+ extended += map;
+
+ ptr = (unsigned long)extended;
+ if (ptr < min_addr || ptr > max_addr)
+ error("32-bit relocation outside of kernel!\n");
+
+ *(uint32_t *)ptr += delta;
+ }
+#ifdef CONFIG_X86_64
+ for (reloc--; *reloc; reloc--) {
+ long extended = *reloc;
+ extended += map;
+
+ ptr = (unsigned long)extended;
+ if (ptr < min_addr || ptr > max_addr)
+ error("64-bit relocation outside of kernel!\n");
+
+ *(uint64_t *)ptr += delta;
+ }
+#endif
+}
+#else
+static inline void handle_relocations(void *output, unsigned long output_len)
+{ }
+#endif
+
static void parse_elf(void *output)
{
#ifdef CONFIG_X86_64
@@ -322,10 +354,11 @@ static void parse_elf(void *output)
free(phdrs);
}
-asmlinkage void decompress_kernel(void *rmode, memptr heap,
+asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
unsigned char *input_data,
unsigned long input_len,
- unsigned char *output)
+ unsigned char *output,
+ unsigned long output_len)
{
real_mode = rmode;
@@ -348,6 +381,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
free_mem_ptr = heap; /* Heap */
free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
+ output = choose_kernel_location(input_data, input_len,
+ output, output_len);
+
+ /* Validate memory location choices. */
if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
error("Destination address inappropriately aligned");
#ifdef CONFIG_X86_64
@@ -365,6 +402,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
debug_putstr("\nDecompressing Linux... ");
decompress(input_data, input_len, NULL, NULL, output, NULL, error);
parse_elf(output);
+ handle_relocations(output, output_len);
debug_putstr("done.\nBooting the kernel.\n");
- return;
+ return output;
}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 674019d8e23..24e3e569a13 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,7 +23,15 @@
#define BOOT_BOOT_H
#include "../ctype.h"
+#ifdef CONFIG_X86_64
+#define memptr long
+#else
+#define memptr unsigned
+#endif
+
/* misc.c */
+extern memptr free_mem_ptr;
+extern memptr free_mem_end_ptr;
extern struct boot_params *real_mode; /* Pointer to real-mode data */
void __putstr(const char *s);
#define error_putstr(__x) __putstr(__x)
@@ -39,23 +47,40 @@ static inline void debug_putstr(const char *s)
#endif
-#ifdef CONFIG_EARLY_PRINTK
-
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
/* cmdline.c */
int cmdline_find_option(const char *option, char *buffer, int bufsize);
int cmdline_find_option_bool(const char *option);
+#endif
-/* early_serial_console.c */
-extern int early_serial_base;
-void console_init(void);
+#if CONFIG_RANDOMIZE_BASE
+/* aslr.c */
+unsigned char *choose_kernel_location(unsigned char *input,
+ unsigned long input_size,
+ unsigned char *output,
+ unsigned long output_size);
+/* cpuflags.c */
+bool has_cpuflag(int flag);
#else
+static inline
+unsigned char *choose_kernel_location(unsigned char *input,
+ unsigned long input_size,
+ unsigned char *output,
+ unsigned long output_size)
+{
+ return output;
+}
+#endif
+#ifdef CONFIG_EARLY_PRINTK
/* early_serial_console.c */
+extern int early_serial_base;
+void console_init(void);
+#else
static const int early_serial_base;
static inline void console_init(void)
{ }
-
#endif
#endif
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index 958a641483d..b669ab65bf6 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -36,11 +36,12 @@ int main(int argc, char *argv[])
uint32_t olen;
long ilen;
unsigned long offs;
- FILE *f;
+ FILE *f = NULL;
+ int retval = 1;
if (argc < 2) {
fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
- return 1;
+ goto bail;
}
/* Get the information for the compressed kernel image first */
@@ -48,7 +49,7 @@ int main(int argc, char *argv[])
f = fopen(argv[1], "r");
if (!f) {
perror(argv[1]);
- return 1;
+ goto bail;
}
@@ -58,12 +59,11 @@ int main(int argc, char *argv[])
if (fread(&olen, sizeof(olen), 1, f) != 1) {
perror(argv[1]);
- return 1;
+ goto bail;
}
ilen = ftell(f);
olen = get_unaligned_le32(&olen);
- fclose(f);
/*
* Now we have the input (compressed) and output (uncompressed)
@@ -91,5 +91,9 @@ int main(int argc, char *argv[])
printf(".incbin \"%s\"\n", argv[1]);
printf("input_data_end:\n");
- return 0;
+ retval = 0;
+bail:
+ if (f)
+ fclose(f);
+ return retval;
}
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index ffb9c5c9d74..00e788be1db 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -1,11 +1,41 @@
-#include "misc.h"
+#include "../string.c"
-int memcmp(const void *s1, const void *s2, size_t len)
+#ifdef CONFIG_X86_32
+void *memcpy(void *dest, const void *src, size_t n)
{
- u8 diff;
- asm("repe; cmpsb; setnz %0"
- : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
- return diff;
+ int d0, d1, d2;
+ asm volatile(
+ "rep ; movsl\n\t"
+ "movl %4,%%ecx\n\t"
+ "rep ; movsb\n\t"
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+ : "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
+ : "memory");
+
+ return dest;
}
+#else
+void *memcpy(void *dest, const void *src, size_t n)
+{
+ long d0, d1, d2;
+ asm volatile(
+ "rep ; movsq\n\t"
+ "movq %4,%%rcx\n\t"
+ "rep ; movsb\n\t"
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+ : "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
+ : "memory");
-#include "../string.c"
+ return dest;
+}
+#endif
+
+void *memset(void *s, int c, size_t n)
+{
+ int i;
+ char *ss = s;
+
+ for (i = 0; i < n; i++)
+ ss[i] = c;
+ return s;
+}
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index 11f272c6f5e..1eb7d298b47 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -14,7 +14,7 @@
* Memory copy routines
*/
- .code16gcc
+ .code16
.text
GLOBAL(memcpy)
@@ -30,7 +30,7 @@ GLOBAL(memcpy)
rep; movsb
popw %di
popw %si
- ret
+ retl
ENDPROC(memcpy)
GLOBAL(memset)
@@ -45,25 +45,25 @@ GLOBAL(memset)
andw $3, %cx
rep; stosb
popw %di
- ret
+ retl
ENDPROC(memset)
GLOBAL(copy_from_fs)
pushw %ds
pushw %fs
popw %ds
- call memcpy
+ calll memcpy
popw %ds
- ret
+ retl
ENDPROC(copy_from_fs)
GLOBAL(copy_to_fs)
pushw %es
pushw %fs
popw %es
- call memcpy
+ calll memcpy
popw %es
- ret
+ retl
ENDPROC(copy_to_fs)
#if 0 /* Not currently used, but can be enabled as needed */
@@ -71,17 +71,17 @@ GLOBAL(copy_from_gs)
pushw %ds
pushw %gs
popw %ds
- call memcpy
+ calll memcpy
popw %ds
- ret
+ retl
ENDPROC(copy_from_gs)
GLOBAL(copy_to_gs)
pushw %es
pushw %gs
popw %es
- call memcpy
+ calll memcpy
popw %es
- ret
+ retl
ENDPROC(copy_to_gs)
#endif
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 4d3ff037201..1fd7d575092 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -27,9 +27,8 @@
#include <asm/processor-flags.h>
#include <asm/required-features.h>
#include <asm/msr-index.h>
+#include "string.h"
-struct cpu_features cpu;
-static u32 cpu_vendor[3];
static u32 err_flags[NCAPINTS];
static const int req_level = CONFIG_X86_MINIMUM_CPU_FAMILY;
@@ -69,92 +68,15 @@ static int is_transmeta(void)
cpu_vendor[2] == A32('M', 'x', '8', '6');
}
-static int has_fpu(void)
+static int is_intel(void)
{
- u16 fcw = -1, fsw = -1;
- u32 cr0;
-
- asm("movl %%cr0,%0" : "=r" (cr0));
- if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
- cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
- asm volatile("movl %0,%%cr0" : : "r" (cr0));
- }
-
- asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
- : "+m" (fsw), "+m" (fcw));
-
- return fsw == 0 && (fcw & 0x103f) == 0x003f;
-}
-
-static int has_eflag(u32 mask)
-{
- u32 f0, f1;
-
- asm("pushfl ; "
- "pushfl ; "
- "popl %0 ; "
- "movl %0,%1 ; "
- "xorl %2,%1 ; "
- "pushl %1 ; "
- "popfl ; "
- "pushfl ; "
- "popl %1 ; "
- "popfl"
- : "=&r" (f0), "=&r" (f1)
- : "ri" (mask));
-
- return !!((f0^f1) & mask);
-}
-
-static void get_flags(void)
-{
- u32 max_intel_level, max_amd_level;
- u32 tfms;
-
- if (has_fpu())
- set_bit(X86_FEATURE_FPU, cpu.flags);
-
- if (has_eflag(X86_EFLAGS_ID)) {
- asm("cpuid"
- : "=a" (max_intel_level),
- "=b" (cpu_vendor[0]),
- "=d" (cpu_vendor[1]),
- "=c" (cpu_vendor[2])
- : "a" (0));
-
- if (max_intel_level >= 0x00000001 &&
- max_intel_level <= 0x0000ffff) {
- asm("cpuid"
- : "=a" (tfms),
- "=c" (cpu.flags[4]),
- "=d" (cpu.flags[0])
- : "a" (0x00000001)
- : "ebx");
- cpu.level = (tfms >> 8) & 15;
- cpu.model = (tfms >> 4) & 15;
- if (cpu.level >= 6)
- cpu.model += ((tfms >> 16) & 0xf) << 4;
- }
-
- asm("cpuid"
- : "=a" (max_amd_level)
- : "a" (0x80000000)
- : "ebx", "ecx", "edx");
-
- if (max_amd_level >= 0x80000001 &&
- max_amd_level <= 0x8000ffff) {
- u32 eax = 0x80000001;
- asm("cpuid"
- : "+a" (eax),
- "=c" (cpu.flags[6]),
- "=d" (cpu.flags[1])
- : : "ebx");
- }
- }
+ return cpu_vendor[0] == A32('G', 'e', 'n', 'u') &&
+ cpu_vendor[1] == A32('i', 'n', 'e', 'I') &&
+ cpu_vendor[2] == A32('n', 't', 'e', 'l');
}
/* Returns a bitmask of which words we have error bits in */
-static int check_flags(void)
+static int check_cpuflags(void)
{
u32 err;
int i;
@@ -187,8 +109,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
if (has_eflag(X86_EFLAGS_AC))
cpu.level = 4;
- get_flags();
- err = check_flags();
+ get_cpuflags();
+ err = check_cpuflags();
if (test_bit(X86_FEATURE_LM, cpu.flags))
cpu.level = 64;
@@ -207,8 +129,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
eax &= ~(1 << 15);
asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
- get_flags(); /* Make sure it really did something */
- err = check_flags();
+ get_cpuflags(); /* Make sure it really did something */
+ err = check_cpuflags();
} else if (err == 0x01 &&
!(err_flags[0] & ~(1 << X86_FEATURE_CX8)) &&
is_centaur() && cpu.model >= 6) {
@@ -223,7 +145,7 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
set_bit(X86_FEATURE_CX8, cpu.flags);
- err = check_flags();
+ err = check_cpuflags();
} else if (err == 0x01 && is_transmeta()) {
/* Transmeta might have masked feature bits in word 0 */
@@ -238,7 +160,20 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
: : "ecx", "ebx");
asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
- err = check_flags();
+ err = check_cpuflags();
+ } else if (err == 0x01 &&
+ !(err_flags[0] & ~(1 << X86_FEATURE_PAE)) &&
+ is_intel() && cpu.level == 6 &&
+ (cpu.model == 9 || cpu.model == 13)) {
+ /* PAE is disabled on this Pentium M but can be forced */
+ if (cmdline_find_option_bool("forcepae")) {
+ puts("WARNING: Forcing PAE in CPU flags\n");
+ set_bit(X86_FEATURE_PAE, cpu.flags);
+ err = check_cpuflags();
+ }
+ else {
+ puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n");
+ }
}
if (err_flags_ptr)
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
new file mode 100644
index 00000000000..431fa5f8453
--- /dev/null
+++ b/arch/x86/boot/cpuflags.c
@@ -0,0 +1,119 @@
+#include <linux/types.h>
+#include "bitops.h"
+
+#include <asm/processor-flags.h>
+#include <asm/required-features.h>
+#include <asm/msr-index.h>
+#include "cpuflags.h"
+
+struct cpu_features cpu;
+u32 cpu_vendor[3];
+
+static bool loaded_flags;
+
+static int has_fpu(void)
+{
+ u16 fcw = -1, fsw = -1;
+ unsigned long cr0;
+
+ asm volatile("mov %%cr0,%0" : "=r" (cr0));
+ if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
+ cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
+ asm volatile("mov %0,%%cr0" : : "r" (cr0));
+ }
+
+ asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+ : "+m" (fsw), "+m" (fcw));
+
+ return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+/*
+ * For building the 16-bit code we want to explicitly specify 32-bit
+ * push/pop operations, rather than just saying 'pushf' or 'popf' and
+ * letting the compiler choose. But this is also included from the
+ * compressed/ directory where it may be 64-bit code, and thus needs
+ * to be 'pushfq' or 'popfq' in that case.
+ */
+#ifdef __x86_64__
+#define PUSHF "pushfq"
+#define POPF "popfq"
+#else
+#define PUSHF "pushfl"
+#define POPF "popfl"
+#endif
+
+int has_eflag(unsigned long mask)
+{
+ unsigned long f0, f1;
+
+ asm volatile(PUSHF " \n\t"
+ PUSHF " \n\t"
+ "pop %0 \n\t"
+ "mov %0,%1 \n\t"
+ "xor %2,%1 \n\t"
+ "push %1 \n\t"
+ POPF " \n\t"
+ PUSHF " \n\t"
+ "pop %1 \n\t"
+ POPF
+ : "=&r" (f0), "=&r" (f1)
+ : "ri" (mask));
+
+ return !!((f0^f1) & mask);
+}
+
+/* Handle x86_32 PIC using ebx. */
+#if defined(__i386__) && defined(__PIC__)
+# define EBX_REG "=r"
+#else
+# define EBX_REG "=b"
+#endif
+
+static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
+{
+ asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t"
+ "cpuid \n\t"
+ ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif \n\t"
+ : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b)
+ : "a" (id)
+ );
+}
+
+void get_cpuflags(void)
+{
+ u32 max_intel_level, max_amd_level;
+ u32 tfms;
+ u32 ignored;
+
+ if (loaded_flags)
+ return;
+ loaded_flags = true;
+
+ if (has_fpu())
+ set_bit(X86_FEATURE_FPU, cpu.flags);
+
+ if (has_eflag(X86_EFLAGS_ID)) {
+ cpuid(0x0, &max_intel_level, &cpu_vendor[0], &cpu_vendor[2],
+ &cpu_vendor[1]);
+
+ if (max_intel_level >= 0x00000001 &&
+ max_intel_level <= 0x0000ffff) {
+ cpuid(0x1, &tfms, &ignored, &cpu.flags[4],
+ &cpu.flags[0]);
+ cpu.level = (tfms >> 8) & 15;
+ cpu.model = (tfms >> 4) & 15;
+ if (cpu.level >= 6)
+ cpu.model += ((tfms >> 16) & 0xf) << 4;
+ }
+
+ cpuid(0x80000000, &max_amd_level, &ignored, &ignored,
+ &ignored);
+
+ if (max_amd_level >= 0x80000001 &&
+ max_amd_level <= 0x8000ffff) {
+ cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6],
+ &cpu.flags[1]);
+ }
+ }
+}
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
new file mode 100644
index 00000000000..ea97697e51e
--- /dev/null
+++ b/arch/x86/boot/cpuflags.h
@@ -0,0 +1,19 @@
+#ifndef BOOT_CPUFLAGS_H
+#define BOOT_CPUFLAGS_H
+
+#include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
+
+struct cpu_features {
+ int level; /* Family, or 64 for x86-64 */
+ int model;
+ u32 flags[NCAPINTS];
+};
+
+extern struct cpu_features cpu;
+extern u32 cpu_vendor[3];
+
+int has_eflag(unsigned long mask);
+void get_cpuflags(void);
+
+#endif
diff --git a/arch/x86/boot/edd.c b/arch/x86/boot/edd.c
index c501a5b466f..223e4252707 100644
--- a/arch/x86/boot/edd.c
+++ b/arch/x86/boot/edd.c
@@ -15,6 +15,7 @@
#include "boot.h"
#include <linux/edd.h>
+#include "string.h"
#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 9ec06a1f6d6..7a6d43a554d 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -91,10 +91,9 @@ bs_die:
.section ".bsdata", "a"
bugger_off_msg:
- .ascii "Direct floppy boot is not supported. "
- .ascii "Use a boot loader program instead.\r\n"
+ .ascii "Use a boot loader.\r\n"
.ascii "\n"
- .ascii "Remove disk and press any key to reboot ...\r\n"
+ .ascii "Remove disk and press any key to reboot...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
@@ -108,7 +107,7 @@ coff_header:
#else
.word 0x8664 # x86-64
#endif
- .word 3 # nr_sections
+ .word 4 # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
@@ -250,6 +249,25 @@ section_table:
.word 0 # NumberOfLineNumbers
.long 0x60500020 # Characteristics (section flags)
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".bss"
+ .byte 0
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0xc8000080 # Characteristics (section flags)
+
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
@@ -283,7 +301,7 @@ _start:
# Part 2 of the header, from the old setup.S
.ascii "HdrS" # header signature
- .word 0x020c # header version number (>= 0x0105)
+ .word 0x020d # header version number (>= 0x0105)
# or else old loadlin-1.5 will fail)
.globl realmode_swtch
realmode_swtch: .word 0, 0 # default_switch, SETUPSEG
@@ -350,7 +368,7 @@ cmd_line_ptr: .long 0 # (Header version 0x0202 or later)
# can be located anywhere in
# low memory 0x10000 or higher.
-ramdisk_max: .long 0x7fffffff
+initrd_addr_max: .long 0x7fffffff
# (Header version 0x0203 or later)
# The highest safe address for
# the contents of an initrd
@@ -383,15 +401,26 @@ xloadflags:
#endif
#ifdef CONFIG_EFI_STUB
-# ifdef CONFIG_X86_64
-# define XLF23 XLF_EFI_HANDOVER_64 /* 64-bit EFI handover ok */
+# ifdef CONFIG_EFI_MIXED
+# define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64)
# else
-# define XLF23 XLF_EFI_HANDOVER_32 /* 32-bit EFI handover ok */
+# ifdef CONFIG_X86_64
+# define XLF23 XLF_EFI_HANDOVER_64 /* 64-bit EFI handover ok */
+# else
+# define XLF23 XLF_EFI_HANDOVER_32 /* 32-bit EFI handover ok */
+# endif
# endif
#else
# define XLF23 0
#endif
- .word XLF0 | XLF1 | XLF23
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC)
+# define XLF4 XLF_EFI_KEXEC
+#else
+# define XLF4 0
+#endif
+
+ .word XLF0 | XLF1 | XLF23 | XLF4
cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line,
#added with boot protocol
@@ -419,13 +448,7 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr
#define INIT_SIZE VO_INIT_SIZE
#endif
init_size: .long INIT_SIZE # kernel initialization size
-handover_offset:
-#ifdef CONFIG_EFI_STUB
- .long 0x30 # offset to the handover
- # protocol entry point
-#else
- .long 0
-#endif
+handover_offset: .long 0 # Filled in by build.c
# End of setup header #####################################################
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index cf6083d444f..fd6c9f23699 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -14,6 +14,7 @@
*/
#include "boot.h"
+#include "string.h"
struct boot_params boot_params __attribute__((aligned(16)));
diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index cdac91ca55d..565083c16e5 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -55,7 +55,7 @@ static char *number(char *str, long num, int base, int size, int precision,
locase = (type & SMALL);
if (type & LEFT)
type &= ~ZEROPAD;
- if (base < 2 || base > 36)
+ if (base < 2 || base > 16)
return NULL;
c = (type & ZEROPAD) ? '0' : ' ';
sign = 0;
diff --git a/arch/x86/boot/regs.c b/arch/x86/boot/regs.c
index 958019b1cfa..c0fb356a309 100644
--- a/arch/x86/boot/regs.c
+++ b/arch/x86/boot/regs.c
@@ -17,6 +17,7 @@
*/
#include "boot.h"
+#include "string.h"
void initregs(struct biosregs *reg)
{
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 574dedfe289..493f3fd9f13 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -12,7 +12,16 @@
* Very basic string functions
*/
-#include "boot.h"
+#include <linux/types.h>
+#include "ctype.h"
+
+int memcmp(const void *s1, const void *s2, size_t len)
+{
+ u8 diff;
+ asm("repe; cmpsb; setnz %0"
+ : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+ return diff;
+}
int strcmp(const char *str1, const char *str2)
{
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
new file mode 100644
index 00000000000..725e820602b
--- /dev/null
+++ b/arch/x86/boot/string.h
@@ -0,0 +1,21 @@
+#ifndef BOOT_STRING_H
+#define BOOT_STRING_H
+
+/* Undef any of these macros coming from string_32.h. */
+#undef memcpy
+#undef memset
+#undef memcmp
+
+void *memcpy(void *dst, const void *src, size_t len);
+void *memset(void *dst, int c, size_t len);
+int memcmp(const void *s1, const void *s2, size_t len);
+
+/*
+ * Access builtin version by default. If one needs to use optimized version,
+ * do "undef memcpy" in .c file and link against right string.c
+ */
+#define memcpy(d,s,l) __builtin_memcpy(d,s,l)
+#define memset(d,c,l) __builtin_memset(d,c,l)
+#define memcmp __builtin_memcmp
+
+#endif /* BOOT_STRING_H */
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index c941d6a8887..a7661c430cd 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -5,14 +5,15 @@
*/
/*
- * This file builds a disk-image from two different files:
+ * This file builds a disk-image from three different files:
*
* - setup: 8086 machine code, sets up system parm
* - system: 80386 code for actual system
+ * - zoffset.h: header with ZO_* defines
*
- * It does some checking that all files are of the correct type, and
- * just writes the result to stdout, removing headers and padding to
- * the right amount. It also writes some system data to stderr.
+ * It does some checking that all files are of the correct type, and writes
+ * the result to the specified destination, removing headers and padding to
+ * the right amount. It also writes some system data to stdout.
*/
/*
@@ -52,7 +53,8 @@ int is_big_kernel;
#define PECOFF_RELOC_RESERVE 0x20
-unsigned long efi_stub_entry;
+unsigned long efi32_stub_entry;
+unsigned long efi64_stub_entry;
unsigned long efi_pe_entry;
unsigned long startup_64;
@@ -136,12 +138,12 @@ static void die(const char * str, ...)
static void usage(void)
{
- die("Usage: build setup system [zoffset.h] [> image]");
+ die("Usage: build setup system zoffset.h image");
}
#ifdef CONFIG_EFI_STUB
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
{
unsigned int pe_header;
unsigned short num_sections;
@@ -162,10 +164,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
put_unaligned_le32(size, section + 0x8);
/* section header vma field */
- put_unaligned_le32(offset, section + 0xc);
+ put_unaligned_le32(vma, section + 0xc);
/* section header 'size of initialised data' field */
- put_unaligned_le32(size, section + 0x10);
+ put_unaligned_le32(datasz, section + 0x10);
/* section header 'file offset' field */
put_unaligned_le32(offset, section + 0x14);
@@ -177,6 +179,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
}
}
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+ update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
static void update_pecoff_setup_and_reloc(unsigned int size)
{
u32 setup_offset = 0x200;
@@ -201,9 +208,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
pe_header = get_unaligned_le32(&buf[0x3c]);
- /* Size of image */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
/*
* Size of code: Subtract the size of the first sector (512 bytes)
* which includes the header.
@@ -218,6 +222,70 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
update_pecoff_section_header(".text", text_start, text_sz);
}
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+ unsigned int pe_header;
+ unsigned int bss_sz = init_sz - file_sz;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+
+ /* Size of uninitialized data */
+ put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+ /* Size of image */
+ put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+ update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
+static int reserve_pecoff_reloc_section(int c)
+{
+ /* Reserve 0x20 bytes for .reloc section */
+ memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+ return PECOFF_RELOC_RESERVE;
+}
+
+static void efi_stub_defaults(void)
+{
+ /* Defaults for old kernel */
+#ifdef CONFIG_X86_32
+ efi_pe_entry = 0x10;
+#else
+ efi_pe_entry = 0x210;
+ startup_64 = 0x200;
+#endif
+}
+
+static void efi_stub_entry_update(void)
+{
+ unsigned long addr = efi32_stub_entry;
+
+#ifdef CONFIG_X86_64
+ /* Yes, this is really how we defined it :( */
+ addr = efi64_stub_entry - 0x200;
+#endif
+
+#ifdef CONFIG_EFI_MIXED
+ if (efi32_stub_entry != addr)
+ die("32-bit and 64-bit EFI entry points do not match\n");
+#endif
+ put_unaligned_le32(addr, &buf[0x264]);
+}
+
+#else
+
+static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
+static inline void update_pecoff_text(unsigned int text_start,
+ unsigned int file_sz) {}
+static inline void update_pecoff_bss(unsigned int file_sz,
+ unsigned int init_sz) {}
+static inline void efi_stub_defaults(void) {}
+static inline void efi_stub_entry_update(void) {}
+
+static inline int reserve_pecoff_reloc_section(int c)
+{
+ return 0;
+}
#endif /* CONFIG_EFI_STUB */
@@ -249,7 +317,8 @@ static void parse_zoffset(char *fname)
p = (char *)buf;
while (p && *p) {
- PARSE_ZOFS(p, efi_stub_entry);
+ PARSE_ZOFS(p, efi32_stub_entry);
+ PARSE_ZOFS(p, efi64_stub_entry);
PARSE_ZOFS(p, efi_pe_entry);
PARSE_ZOFS(p, startup_64);
@@ -261,29 +330,24 @@ static void parse_zoffset(char *fname)
int main(int argc, char ** argv)
{
- unsigned int i, sz, setup_sectors;
+ unsigned int i, sz, setup_sectors, init_sz;
int c;
u32 sys_size;
struct stat sb;
- FILE *file;
+ FILE *file, *dest;
int fd;
void *kernel;
u32 crc = 0xffffffffUL;
- /* Defaults for old kernel */
-#ifdef CONFIG_X86_32
- efi_pe_entry = 0x10;
- efi_stub_entry = 0x30;
-#else
- efi_pe_entry = 0x210;
- efi_stub_entry = 0x230;
- startup_64 = 0x200;
-#endif
+ efi_stub_defaults();
- if (argc == 4)
- parse_zoffset(argv[3]);
- else if (argc != 3)
+ if (argc != 5)
usage();
+ parse_zoffset(argv[3]);
+
+ dest = fopen(argv[4], "w");
+ if (!dest)
+ die("Unable to write `%s': %m", argv[4]);
/* Copy the setup code */
file = fopen(argv[1], "r");
@@ -298,11 +362,7 @@ int main(int argc, char ** argv)
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
-#ifdef CONFIG_EFI_STUB
- /* Reserve 0x20 bytes for .reloc section */
- memset(buf+c, 0, PECOFF_RELOC_RESERVE);
- c += PECOFF_RELOC_RESERVE;
-#endif
+ c += reserve_pecoff_reloc_section(c);
/* Pad unused space with zeros */
setup_sectors = (c + 511) / 512;
@@ -311,14 +371,12 @@ int main(int argc, char ** argv)
i = setup_sectors*512;
memset(buf+c, 0, i-c);
-#ifdef CONFIG_EFI_STUB
update_pecoff_setup_and_reloc(i);
-#endif
/* Set the default root device */
put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
- fprintf(stderr, "Setup is %d bytes (padded to %d bytes).\n", c, i);
+ printf("Setup is %d bytes (padded to %d bytes).\n", c, i);
/* Open and stat the kernel file */
fd = open(argv[2], O_RDONLY);
@@ -327,7 +385,7 @@ int main(int argc, char ** argv)
if (fstat(fd, &sb))
die("Unable to stat `%s': %m", argv[2]);
sz = sb.st_size;
- fprintf (stderr, "System is %d kB\n", (sz+1023)/1024);
+ printf("System is %d kB\n", (sz+1023)/1024);
kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
if (kernel == MAP_FAILED)
die("Unable to mmap '%s': %m", argv[2]);
@@ -338,37 +396,38 @@ int main(int argc, char ** argv)
buf[0x1f1] = setup_sectors-1;
put_unaligned_le32(sys_size, &buf[0x1f4]);
-#ifdef CONFIG_EFI_STUB
- update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+ update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+ init_sz = get_unaligned_le32(&buf[0x260]);
+ update_pecoff_bss(i + (sys_size * 16), init_sz);
-#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
- efi_stub_entry -= 0x200;
-#endif
- put_unaligned_le32(efi_stub_entry, &buf[0x264]);
-#endif
+ efi_stub_entry_update();
crc = partial_crc32(buf, i, crc);
- if (fwrite(buf, 1, i, stdout) != i)
+ if (fwrite(buf, 1, i, dest) != i)
die("Writing setup failed");
/* Copy the kernel code */
crc = partial_crc32(kernel, sz, crc);
- if (fwrite(kernel, 1, sz, stdout) != sz)
+ if (fwrite(kernel, 1, sz, dest) != sz)
die("Writing kernel failed");
/* Add padding leaving 4 bytes for the checksum */
while (sz++ < (sys_size*16) - 4) {
crc = partial_crc32_one('\0', crc);
- if (fwrite("\0", 1, 1, stdout) != 1)
+ if (fwrite("\0", 1, 1, dest) != 1)
die("Writing padding failed");
}
/* Write the CRC */
- fprintf(stderr, "CRC %x\n", crc);
+ printf("CRC %x\n", crc);
put_unaligned_le32(crc, buf);
- if (fwrite(buf, 1, 4, stdout) != 4)
+ if (fwrite(buf, 1, 4, dest) != 4)
die("Writing CRC failed");
+ /* Catch any delayed write failures */
+ if (fclose(dest))
+ die("Writing image failed");
+
close(fd);
/* Everything is OK */
diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c
index 11e8c6eb80a..ba3e100654d 100644
--- a/arch/x86/boot/video-vesa.c
+++ b/arch/x86/boot/video-vesa.c
@@ -16,6 +16,7 @@
#include "boot.h"
#include "video.h"
#include "vesa.h"
+#include "string.h"
/* VESA information */
static struct vesa_general_info vginfo;
diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h
index ff339c5db31..0bb25491262 100644
--- a/arch/x86/boot/video.h
+++ b/arch/x86/boot/video.h
@@ -80,7 +80,7 @@ struct card_info {
u16 xmode_n; /* Size of unprobed mode range */
};
-#define __videocard struct card_info __attribute__((section(".videocards")))
+#define __videocard struct card_info __attribute__((used,section(".videocards")))
extern struct card_info video_cards[], video_cards_end[];
int mode_defined(u16 mode); /* video.c */
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 94447086e55..32d2e7056c8 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -60,7 +60,6 @@ CONFIG_CRASH_DUMP=y
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
CONFIG_PM_TRACE_RTC=y
-CONFIG_ACPI_PROCFS=y
CONFIG_ACPI_DOCK=y
CONFIG_CPU_FREQ=y
# CONFIG_CPU_FREQ_STAT is not set
@@ -142,6 +141,8 @@ CONFIG_MAC80211=y
CONFIG_MAC80211_LEDS=y
CONFIG_RFKILL=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
CONFIG_BLK_DEV_LOOP=y
@@ -243,7 +244,6 @@ CONFIG_HID_TOPSEED=y
CONFIG_HID_PID=y
CONFIG_USB_HIDDEV=y
CONFIG_USB=y
-CONFIG_USB_DEBUG=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
CONFIG_USB_EHCI_HCD=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 671524d0f6c..a481dd4755d 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -58,7 +58,6 @@ CONFIG_CRASH_DUMP=y
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
CONFIG_PM_TRACE_RTC=y
-CONFIG_ACPI_PROCFS=y
CONFIG_ACPI_DOCK=y
CONFIG_CPU_FREQ=y
# CONFIG_CPU_FREQ_STAT is not set
@@ -141,6 +140,8 @@ CONFIG_MAC80211=y
CONFIG_MAC80211_LEDS=y
CONFIG_RFKILL=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
CONFIG_BLK_DEV_LOOP=y
@@ -238,7 +239,6 @@ CONFIG_HID_TOPSEED=y
CONFIG_HID_PID=y
CONFIG_USB_HIDDEV=y
CONFIG_USB=y
-CONFIG_USB_DEBUG=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
CONFIG_USB_EHCI_HCD=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 7d6ba9db1be..61d6e281898 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -3,8 +3,9 @@
#
avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+ $(comma)4)$(comma)%ymm2,yes,no)
-obj-$(CONFIG_CRYPTO_ABLK_HELPER_X86) += ablk_helper.o
obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
@@ -75,8 +76,12 @@ ifeq ($(avx2_supported),yes)
endif
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
+aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
+ifeq ($(avx2_supported),yes)
+sha1-ssse3-y += sha1_avx2_x86_64_asm.o
+endif
crc32c-intel-y := crc32c-intel_glue.o
crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
diff --git a/arch/x86/crypto/ablk_helper.c b/arch/x86/crypto/ablk_helper.c
deleted file mode 100644
index 43282fe04a8..00000000000
--- a/arch/x86/crypto/ablk_helper.c
+++ /dev/null
@@ -1,149 +0,0 @@
-/*
- * Shared async block cipher helpers
- *
- * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
- *
- * Based on aesni-intel_glue.c by:
- * Copyright (C) 2008, Intel Corp.
- * Author: Huang Ying <ying.huang@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <crypto/algapi.h>
-#include <crypto/cryptd.h>
-#include <asm/i387.h>
-#include <asm/crypto/ablk_helper.h>
-
-int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
- unsigned int key_len)
-{
- struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
- struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
- int err;
-
- crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
- crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
- & CRYPTO_TFM_REQ_MASK);
- err = crypto_ablkcipher_setkey(child, key, key_len);
- crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
- & CRYPTO_TFM_RES_MASK);
- return err;
-}
-EXPORT_SYMBOL_GPL(ablk_set_key);
-
-int __ablk_encrypt(struct ablkcipher_request *req)
-{
- struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
- struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
- struct blkcipher_desc desc;
-
- desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
- desc.info = req->info;
- desc.flags = 0;
-
- return crypto_blkcipher_crt(desc.tfm)->encrypt(
- &desc, req->dst, req->src, req->nbytes);
-}
-EXPORT_SYMBOL_GPL(__ablk_encrypt);
-
-int ablk_encrypt(struct ablkcipher_request *req)
-{
- struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
- struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
- if (!irq_fpu_usable()) {
- struct ablkcipher_request *cryptd_req =
- ablkcipher_request_ctx(req);
-
- memcpy(cryptd_req, req, sizeof(*req));
- ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-
- return crypto_ablkcipher_encrypt(cryptd_req);
- } else {
- return __ablk_encrypt(req);
- }
-}
-EXPORT_SYMBOL_GPL(ablk_encrypt);
-
-int ablk_decrypt(struct ablkcipher_request *req)
-{
- struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
- struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
- if (!irq_fpu_usable()) {
- struct ablkcipher_request *cryptd_req =
- ablkcipher_request_ctx(req);
-
- memcpy(cryptd_req, req, sizeof(*req));
- ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-
- return crypto_ablkcipher_decrypt(cryptd_req);
- } else {
- struct blkcipher_desc desc;
-
- desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
- desc.info = req->info;
- desc.flags = 0;
-
- return crypto_blkcipher_crt(desc.tfm)->decrypt(
- &desc, req->dst, req->src, req->nbytes);
- }
-}
-EXPORT_SYMBOL_GPL(ablk_decrypt);
-
-void ablk_exit(struct crypto_tfm *tfm)
-{
- struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
-
- cryptd_free_ablkcipher(ctx->cryptd_tfm);
-}
-EXPORT_SYMBOL_GPL(ablk_exit);
-
-int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
-{
- struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
- struct cryptd_ablkcipher *cryptd_tfm;
-
- cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
- if (IS_ERR(cryptd_tfm))
- return PTR_ERR(cryptd_tfm);
-
- ctx->cryptd_tfm = cryptd_tfm;
- tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
- crypto_ablkcipher_reqsize(&cryptd_tfm->base);
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(ablk_init_common);
-
-int ablk_init(struct crypto_tfm *tfm)
-{
- char drv_name[CRYPTO_MAX_ALG_NAME];
-
- snprintf(drv_name, sizeof(drv_name), "__driver-%s",
- crypto_tfm_alg_driver_name(tfm));
-
- return ablk_init_common(tfm, drv_name);
-}
-EXPORT_SYMBOL_GPL(ablk_init);
-
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
new file mode 100644
index 00000000000..522ab68d1c8
--- /dev/null
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -0,0 +1,2811 @@
+########################################################################
+# Copyright (c) 2013, Intel Corporation
+#
+# This software is available to you under a choice of one of two
+# licenses. You may choose to be licensed under the terms of the GNU
+# General Public License (GPL) Version 2, available from the file
+# COPYING in the main directory of this source tree, or the
+# OpenIB.org BSD license below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+# * Redistributions of source code must retain the above copyright
+# notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+# notice, this list of conditions and the following disclaimer in the
+# documentation and/or other materials provided with the
+# distribution.
+#
+# * Neither the name of the Intel Corporation nor the names of its
+# contributors may be used to endorse or promote products derived from
+# this software without specific prior written permission.
+#
+#
+# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES# LOSS OF USE, DATA, OR
+# PROFITS# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+########################################################################
+##
+## Authors:
+## Erdinc Ozturk <erdinc.ozturk@intel.com>
+## Vinodh Gopal <vinodh.gopal@intel.com>
+## James Guilford <james.guilford@intel.com>
+## Tim Chen <tim.c.chen@linux.intel.com>
+##
+## References:
+## This code was derived and highly optimized from the code described in paper:
+## Vinodh Gopal et. al. Optimized Galois-Counter-Mode Implementation
+## on Intel Architecture Processors. August, 2010
+## The details of the implementation is explained in:
+## Erdinc Ozturk et. al. Enabling High-Performance Galois-Counter-Mode
+## on Intel Architecture Processors. October, 2012.
+##
+## Assumptions:
+##
+##
+##
+## iv:
+## 0 1 2 3
+## 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | Salt (From the SA) |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | Initialization Vector |
+## | (This is the sequence number from IPSec header) |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | 0x1 |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+##
+##
+##
+## AAD:
+## AAD padded to 128 bits with 0
+## for example, assume AAD is a u32 vector
+##
+## if AAD is 8 bytes:
+## AAD[3] = {A0, A1}#
+## padded AAD in xmm register = {A1 A0 0 0}
+##
+## 0 1 2 3
+## 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | SPI (A1) |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | 32-bit Sequence Number (A0) |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | 0x0 |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+##
+## AAD Format with 32-bit Sequence Number
+##
+## if AAD is 12 bytes:
+## AAD[3] = {A0, A1, A2}#
+## padded AAD in xmm register = {A2 A1 A0 0}
+##
+## 0 1 2 3
+## 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | SPI (A2) |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | 64-bit Extended Sequence Number {A1,A0} |
+## | |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+## | 0x0 |
+## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+##
+## AAD Format with 64-bit Extended Sequence Number
+##
+##
+## aadLen:
+## from the definition of the spec, aadLen can only be 8 or 12 bytes.
+## The code additionally supports aadLen of length 16 bytes.
+##
+## TLen:
+## from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
+##
+## poly = x^128 + x^127 + x^126 + x^121 + 1
+## throughout the code, one tab and two tab indentations are used. one tab is
+## for GHASH part, two tabs is for AES part.
+##
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+.data
+.align 16
+
+POLY: .octa 0xC2000000000000000000000000000001
+POLY2: .octa 0xC20000000000000000000001C2000000
+TWOONE: .octa 0x00000001000000000000000000000001
+
+# order of these constants should not change.
+# more specifically, ALL_F should follow SHIFT_MASK, and ZERO should follow ALL_F
+
+SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F
+SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
+ALL_F: .octa 0xffffffffffffffffffffffffffffffff
+ZERO: .octa 0x00000000000000000000000000000000
+ONE: .octa 0x00000000000000000000000000000001
+ONEf: .octa 0x01000000000000000000000000000000
+
+.text
+
+
+##define the fields of the gcm aes context
+#{
+# u8 expanded_keys[16*11] store expanded keys
+# u8 shifted_hkey_1[16] store HashKey <<1 mod poly here
+# u8 shifted_hkey_2[16] store HashKey^2 <<1 mod poly here
+# u8 shifted_hkey_3[16] store HashKey^3 <<1 mod poly here
+# u8 shifted_hkey_4[16] store HashKey^4 <<1 mod poly here
+# u8 shifted_hkey_5[16] store HashKey^5 <<1 mod poly here
+# u8 shifted_hkey_6[16] store HashKey^6 <<1 mod poly here
+# u8 shifted_hkey_7[16] store HashKey^7 <<1 mod poly here
+# u8 shifted_hkey_8[16] store HashKey^8 <<1 mod poly here
+# u8 shifted_hkey_1_k[16] store XOR HashKey <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_2_k[16] store XOR HashKey^2 <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_3_k[16] store XOR HashKey^3 <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_4_k[16] store XOR HashKey^4 <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_5_k[16] store XOR HashKey^5 <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_6_k[16] store XOR HashKey^6 <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_7_k[16] store XOR HashKey^7 <<1 mod poly here (for Karatsuba purposes)
+# u8 shifted_hkey_8_k[16] store XOR HashKey^8 <<1 mod poly here (for Karatsuba purposes)
+#} gcm_ctx#
+
+HashKey = 16*11 # store HashKey <<1 mod poly here
+HashKey_2 = 16*12 # store HashKey^2 <<1 mod poly here
+HashKey_3 = 16*13 # store HashKey^3 <<1 mod poly here
+HashKey_4 = 16*14 # store HashKey^4 <<1 mod poly here
+HashKey_5 = 16*15 # store HashKey^5 <<1 mod poly here
+HashKey_6 = 16*16 # store HashKey^6 <<1 mod poly here
+HashKey_7 = 16*17 # store HashKey^7 <<1 mod poly here
+HashKey_8 = 16*18 # store HashKey^8 <<1 mod poly here
+HashKey_k = 16*19 # store XOR of HashKey <<1 mod poly here (for Karatsuba purposes)
+HashKey_2_k = 16*20 # store XOR of HashKey^2 <<1 mod poly here (for Karatsuba purposes)
+HashKey_3_k = 16*21 # store XOR of HashKey^3 <<1 mod poly here (for Karatsuba purposes)
+HashKey_4_k = 16*22 # store XOR of HashKey^4 <<1 mod poly here (for Karatsuba purposes)
+HashKey_5_k = 16*23 # store XOR of HashKey^5 <<1 mod poly here (for Karatsuba purposes)
+HashKey_6_k = 16*24 # store XOR of HashKey^6 <<1 mod poly here (for Karatsuba purposes)
+HashKey_7_k = 16*25 # store XOR of HashKey^7 <<1 mod poly here (for Karatsuba purposes)
+HashKey_8_k = 16*26 # store XOR of HashKey^8 <<1 mod poly here (for Karatsuba purposes)
+
+#define arg1 %rdi
+#define arg2 %rsi
+#define arg3 %rdx
+#define arg4 %rcx
+#define arg5 %r8
+#define arg6 %r9
+#define arg7 STACK_OFFSET+8*1(%r14)
+#define arg8 STACK_OFFSET+8*2(%r14)
+#define arg9 STACK_OFFSET+8*3(%r14)
+
+i = 0
+j = 0
+
+out_order = 0
+in_order = 1
+DEC = 0
+ENC = 1
+
+.macro define_reg r n
+reg_\r = %xmm\n
+.endm
+
+.macro setreg
+.altmacro
+define_reg i %i
+define_reg j %j
+.noaltmacro
+.endm
+
+# need to push 4 registers into stack to maintain
+STACK_OFFSET = 8*4
+
+TMP1 = 16*0 # Temporary storage for AAD
+TMP2 = 16*1 # Temporary storage for AES State 2 (State 1 is stored in an XMM register)
+TMP3 = 16*2 # Temporary storage for AES State 3
+TMP4 = 16*3 # Temporary storage for AES State 4
+TMP5 = 16*4 # Temporary storage for AES State 5
+TMP6 = 16*5 # Temporary storage for AES State 6
+TMP7 = 16*6 # Temporary storage for AES State 7
+TMP8 = 16*7 # Temporary storage for AES State 8
+
+VARIABLE_OFFSET = 16*8
+
+################################
+# Utility Macros
+################################
+
+# Encryption of a single block
+.macro ENCRYPT_SINGLE_BLOCK XMM0
+ vpxor (arg1), \XMM0, \XMM0
+ i = 1
+ setreg
+.rep 9
+ vaesenc 16*i(arg1), \XMM0, \XMM0
+ i = (i+1)
+ setreg
+.endr
+ vaesenclast 16*10(arg1), \XMM0, \XMM0
+.endm
+
+#ifdef CONFIG_AS_AVX
+###############################################################################
+# GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
+# Input: A and B (128-bits each, bit-reflected)
+# Output: C = A*B*x mod poly, (i.e. >>1 )
+# To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
+# GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
+###############################################################################
+.macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
+
+ vpshufd $0b01001110, \GH, \T2
+ vpshufd $0b01001110, \HK, \T3
+ vpxor \GH , \T2, \T2 # T2 = (a1+a0)
+ vpxor \HK , \T3, \T3 # T3 = (b1+b0)
+
+ vpclmulqdq $0x11, \HK, \GH, \T1 # T1 = a1*b1
+ vpclmulqdq $0x00, \HK, \GH, \GH # GH = a0*b0
+ vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
+ vpxor \GH, \T2,\T2
+ vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
+
+ vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
+ vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
+ vpxor \T3, \GH, \GH
+ vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
+
+ #first phase of the reduction
+ vpslld $31, \GH, \T2 # packed right shifting << 31
+ vpslld $30, \GH, \T3 # packed right shifting shift << 30
+ vpslld $25, \GH, \T4 # packed right shifting shift << 25
+
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
+
+ vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
+ vpxor \T2, \GH, \GH # first phase of the reduction complete
+
+ #second phase of the reduction
+
+ vpsrld $1,\GH, \T2 # packed left shifting >> 1
+ vpsrld $2,\GH, \T3 # packed left shifting >> 2
+ vpsrld $7,\GH, \T4 # packed left shifting >> 7
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpxor \T5, \T2, \T2
+ vpxor \T2, \GH, \GH
+ vpxor \T1, \GH, \GH # the result is in GH
+
+
+.endm
+
+.macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
+
+ # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
+ vmovdqa \HK, \T5
+
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
+ vmovdqa \T5, HashKey_2(arg1) # [HashKey_2] = HashKey^2<<1 mod poly
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_2_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
+ vmovdqa \T5, HashKey_3(arg1)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_3_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
+ vmovdqa \T5, HashKey_4(arg1)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_4_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
+ vmovdqa \T5, HashKey_5(arg1)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_5_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
+ vmovdqa \T5, HashKey_6(arg1)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_6_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
+ vmovdqa \T5, HashKey_7(arg1)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_7_k(arg1)
+
+ GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
+ vmovdqa \T5, HashKey_8(arg1)
+ vpshufd $0b01001110, \T5, \T1
+ vpxor \T5, \T1, \T1
+ vmovdqa \T1, HashKey_8_k(arg1)
+
+.endm
+
+## if a = number of total plaintext bytes
+## b = floor(a/16)
+## num_initial_blocks = b mod 4#
+## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
+## r10, r11, r12, rax are clobbered
+## arg1, arg2, arg3, r14 are used as a pointer only, not modified
+
+.macro INITIAL_BLOCKS_AVX num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC
+ i = (8-\num_initial_blocks)
+ setreg
+
+ mov arg6, %r10 # r10 = AAD
+ mov arg7, %r12 # r12 = aadLen
+
+
+ mov %r12, %r11
+
+ vpxor reg_i, reg_i, reg_i
+_get_AAD_loop\@:
+ vmovd (%r10), \T1
+ vpslldq $12, \T1, \T1
+ vpsrldq $4, reg_i, reg_i
+ vpxor \T1, reg_i, reg_i
+
+ add $4, %r10
+ sub $4, %r12
+ jg _get_AAD_loop\@
+
+
+ cmp $16, %r11
+ je _get_AAD_loop2_done\@
+ mov $16, %r12
+
+_get_AAD_loop2\@:
+ vpsrldq $4, reg_i, reg_i
+ sub $4, %r12
+ cmp %r11, %r12
+ jg _get_AAD_loop2\@
+
+_get_AAD_loop2_done\@:
+
+ #byte-reflect the AAD data
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i
+
+ # initialize the data pointer offset as zero
+ xor %r11, %r11
+
+ # start AES for num_initial_blocks blocks
+ mov arg5, %rax # rax = *Y0
+ vmovdqu (%rax), \CTR # CTR = Y0
+ vpshufb SHUF_MASK(%rip), \CTR, \CTR
+
+
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, reg_i
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i # perform a 16Byte swap
+ i = (i+1)
+ setreg
+.endr
+
+ vmovdqa (arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vpxor \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
+
+ j = 1
+ setreg
+.rep 9
+ vmovdqa 16*j(arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vaesenc \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
+
+ j = (j+1)
+ setreg
+.endr
+
+
+ vmovdqa 16*10(arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vaesenclast \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
+
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vmovdqu (arg3, %r11), \T1
+ vpxor \T1, reg_i, reg_i
+ vmovdqu reg_i, (arg2 , %r11) # write back ciphertext for num_initial_blocks blocks
+ add $16, %r11
+.if \ENC_DEC == DEC
+ vmovdqa \T1, reg_i
+.endif
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i # prepare ciphertext for GHASH computations
+ i = (i+1)
+ setreg
+.endr
+
+
+ i = (8-\num_initial_blocks)
+ j = (9-\num_initial_blocks)
+ setreg
+ GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6
+
+.rep \num_initial_blocks
+ vpxor reg_i, reg_j, reg_j
+ GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ # XMM8 has the combined result here
+
+ vmovdqa \XMM8, TMP1(%rsp)
+ vmovdqa \XMM8, \T3
+
+ cmp $128, %r13
+ jl _initial_blocks_done\@ # no need for precomputed constants
+
+###############################################################################
+# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM1
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM2
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM3
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM4
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM5
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM6
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM7
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM8
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+
+ vmovdqa (arg1), \T_key
+ vpxor \T_key, \XMM1, \XMM1
+ vpxor \T_key, \XMM2, \XMM2
+ vpxor \T_key, \XMM3, \XMM3
+ vpxor \T_key, \XMM4, \XMM4
+ vpxor \T_key, \XMM5, \XMM5
+ vpxor \T_key, \XMM6, \XMM6
+ vpxor \T_key, \XMM7, \XMM7
+ vpxor \T_key, \XMM8, \XMM8
+
+ i = 1
+ setreg
+.rep 9 # do 9 rounds
+ vmovdqa 16*i(arg1), \T_key
+ vaesenc \T_key, \XMM1, \XMM1
+ vaesenc \T_key, \XMM2, \XMM2
+ vaesenc \T_key, \XMM3, \XMM3
+ vaesenc \T_key, \XMM4, \XMM4
+ vaesenc \T_key, \XMM5, \XMM5
+ vaesenc \T_key, \XMM6, \XMM6
+ vaesenc \T_key, \XMM7, \XMM7
+ vaesenc \T_key, \XMM8, \XMM8
+ i = (i+1)
+ setreg
+.endr
+
+
+ vmovdqa 16*i(arg1), \T_key
+ vaesenclast \T_key, \XMM1, \XMM1
+ vaesenclast \T_key, \XMM2, \XMM2
+ vaesenclast \T_key, \XMM3, \XMM3
+ vaesenclast \T_key, \XMM4, \XMM4
+ vaesenclast \T_key, \XMM5, \XMM5
+ vaesenclast \T_key, \XMM6, \XMM6
+ vaesenclast \T_key, \XMM7, \XMM7
+ vaesenclast \T_key, \XMM8, \XMM8
+
+ vmovdqu (arg3, %r11), \T1
+ vpxor \T1, \XMM1, \XMM1
+ vmovdqu \XMM1, (arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM1
+ .endif
+
+ vmovdqu 16*1(arg3, %r11), \T1
+ vpxor \T1, \XMM2, \XMM2
+ vmovdqu \XMM2, 16*1(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM2
+ .endif
+
+ vmovdqu 16*2(arg3, %r11), \T1
+ vpxor \T1, \XMM3, \XMM3
+ vmovdqu \XMM3, 16*2(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM3
+ .endif
+
+ vmovdqu 16*3(arg3, %r11), \T1
+ vpxor \T1, \XMM4, \XMM4
+ vmovdqu \XMM4, 16*3(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM4
+ .endif
+
+ vmovdqu 16*4(arg3, %r11), \T1
+ vpxor \T1, \XMM5, \XMM5
+ vmovdqu \XMM5, 16*4(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM5
+ .endif
+
+ vmovdqu 16*5(arg3, %r11), \T1
+ vpxor \T1, \XMM6, \XMM6
+ vmovdqu \XMM6, 16*5(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM6
+ .endif
+
+ vmovdqu 16*6(arg3, %r11), \T1
+ vpxor \T1, \XMM7, \XMM7
+ vmovdqu \XMM7, 16*6(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM7
+ .endif
+
+ vmovdqu 16*7(arg3, %r11), \T1
+ vpxor \T1, \XMM8, \XMM8
+ vmovdqu \XMM8, 16*7(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM8
+ .endif
+
+ add $128, %r11
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpxor TMP1(%rsp), \XMM1, \XMM1 # combine GHASHed value with the corresponding ciphertext
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+
+###############################################################################
+
+_initial_blocks_done\@:
+
+.endm
+
+# encrypt 8 blocks at a time
+# ghash the 8 previously encrypted ciphertext blocks
+# arg1, arg2, arg3 are used as pointers only, not modified
+# r11 is the data offset value
+.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
+
+ vmovdqa \XMM1, \T2
+ vmovdqa \XMM2, TMP2(%rsp)
+ vmovdqa \XMM3, TMP3(%rsp)
+ vmovdqa \XMM4, TMP4(%rsp)
+ vmovdqa \XMM5, TMP5(%rsp)
+ vmovdqa \XMM6, TMP6(%rsp)
+ vmovdqa \XMM7, TMP7(%rsp)
+ vmovdqa \XMM8, TMP8(%rsp)
+
+.if \loop_idx == in_order
+ vpaddd ONE(%rip), \CTR, \XMM1 # INCR CNT
+ vpaddd ONE(%rip), \XMM1, \XMM2
+ vpaddd ONE(%rip), \XMM2, \XMM3
+ vpaddd ONE(%rip), \XMM3, \XMM4
+ vpaddd ONE(%rip), \XMM4, \XMM5
+ vpaddd ONE(%rip), \XMM5, \XMM6
+ vpaddd ONE(%rip), \XMM6, \XMM7
+ vpaddd ONE(%rip), \XMM7, \XMM8
+ vmovdqa \XMM8, \CTR
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+.else
+ vpaddd ONEf(%rip), \CTR, \XMM1 # INCR CNT
+ vpaddd ONEf(%rip), \XMM1, \XMM2
+ vpaddd ONEf(%rip), \XMM2, \XMM3
+ vpaddd ONEf(%rip), \XMM3, \XMM4
+ vpaddd ONEf(%rip), \XMM4, \XMM5
+ vpaddd ONEf(%rip), \XMM5, \XMM6
+ vpaddd ONEf(%rip), \XMM6, \XMM7
+ vpaddd ONEf(%rip), \XMM7, \XMM8
+ vmovdqa \XMM8, \CTR
+.endif
+
+
+ #######################################################################
+
+ vmovdqu (arg1), \T1
+ vpxor \T1, \XMM1, \XMM1
+ vpxor \T1, \XMM2, \XMM2
+ vpxor \T1, \XMM3, \XMM3
+ vpxor \T1, \XMM4, \XMM4
+ vpxor \T1, \XMM5, \XMM5
+ vpxor \T1, \XMM6, \XMM6
+ vpxor \T1, \XMM7, \XMM7
+ vpxor \T1, \XMM8, \XMM8
+
+ #######################################################################
+
+
+
+
+
+ vmovdqu 16*1(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqu 16*2(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+
+ #######################################################################
+
+ vmovdqa HashKey_8(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
+ vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
+
+ vpshufd $0b01001110, \T2, \T6
+ vpxor \T2, \T6, \T6
+
+ vmovdqa HashKey_8_k(arg1), \T5
+ vpclmulqdq $0x00, \T5, \T6, \T6
+
+ vmovdqu 16*3(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP2(%rsp), \T1
+ vmovdqa HashKey_7(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_7_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*4(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ #######################################################################
+
+ vmovdqa TMP3(%rsp), \T1
+ vmovdqa HashKey_6(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_6_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*5(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP4(%rsp), \T1
+ vmovdqa HashKey_5(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_5_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*6(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+
+ vmovdqa TMP5(%rsp), \T1
+ vmovdqa HashKey_4(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_4_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*7(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP6(%rsp), \T1
+ vmovdqa HashKey_3(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_3_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+
+ vmovdqu 16*8(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP7(%rsp), \T1
+ vmovdqa HashKey_2(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_2_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+ #######################################################################
+
+ vmovdqu 16*9(arg1), \T5
+ vaesenc \T5, \XMM1, \XMM1
+ vaesenc \T5, \XMM2, \XMM2
+ vaesenc \T5, \XMM3, \XMM3
+ vaesenc \T5, \XMM4, \XMM4
+ vaesenc \T5, \XMM5, \XMM5
+ vaesenc \T5, \XMM6, \XMM6
+ vaesenc \T5, \XMM7, \XMM7
+ vaesenc \T5, \XMM8, \XMM8
+
+ vmovdqa TMP8(%rsp), \T1
+ vmovdqa HashKey(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpshufd $0b01001110, \T1, \T3
+ vpxor \T1, \T3, \T3
+ vmovdqa HashKey_k(arg1), \T5
+ vpclmulqdq $0x10, \T5, \T3, \T3
+ vpxor \T3, \T6, \T6
+
+ vpxor \T4, \T6, \T6
+ vpxor \T7, \T6, \T6
+
+ vmovdqu 16*10(arg1), \T5
+
+ i = 0
+ j = 1
+ setreg
+.rep 8
+ vpxor 16*i(arg3, %r11), \T5, \T2
+ .if \ENC_DEC == ENC
+ vaesenclast \T2, reg_j, reg_j
+ .else
+ vaesenclast \T2, reg_j, \T3
+ vmovdqu 16*i(arg3, %r11), reg_j
+ vmovdqu \T3, 16*i(arg2, %r11)
+ .endif
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ #######################################################################
+
+
+ vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
+ vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
+ vpxor \T3, \T7, \T7
+ vpxor \T4, \T6, \T6 # accumulate the results in T6:T7
+
+
+
+ #######################################################################
+ #first phase of the reduction
+ #######################################################################
+ vpslld $31, \T7, \T2 # packed right shifting << 31
+ vpslld $30, \T7, \T3 # packed right shifting shift << 30
+ vpslld $25, \T7, \T4 # packed right shifting shift << 25
+
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
+
+ vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
+ .if \ENC_DEC == ENC
+ vmovdqu \XMM1, 16*0(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM2, 16*1(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM3, 16*2(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM4, 16*3(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM5, 16*4(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM6, 16*5(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM7, 16*6(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM8, 16*7(arg2,%r11) # Write to the Ciphertext buffer
+ .endif
+
+ #######################################################################
+ #second phase of the reduction
+ vpsrld $1, \T7, \T2 # packed left shifting >> 1
+ vpsrld $2, \T7, \T3 # packed left shifting >> 2
+ vpsrld $7, \T7, \T4 # packed left shifting >> 7
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpxor \T1, \T2, \T2
+ vpxor \T2, \T7, \T7
+ vpxor \T7, \T6, \T6 # the result is in T6
+ #######################################################################
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+
+
+ vpxor \T6, \XMM1, \XMM1
+
+
+
+.endm
+
+
+# GHASH the last 4 ciphertext blocks.
+.macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
+
+ ## Karatsuba Method
+
+
+ vpshufd $0b01001110, \XMM1, \T2
+ vpxor \XMM1, \T2, \T2
+ vmovdqa HashKey_8(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM1, \T6
+ vpclmulqdq $0x00, \T5, \XMM1, \T7
+
+ vmovdqa HashKey_8_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM2, \T2
+ vpxor \XMM2, \T2, \T2
+ vmovdqa HashKey_7(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM2, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM2, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_7_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM3, \T2
+ vpxor \XMM3, \T2, \T2
+ vmovdqa HashKey_6(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM3, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM3, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_6_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM4, \T2
+ vpxor \XMM4, \T2, \T2
+ vmovdqa HashKey_5(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM4, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM4, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_5_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM5, \T2
+ vpxor \XMM5, \T2, \T2
+ vmovdqa HashKey_4(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM5, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM5, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_4_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM6, \T2
+ vpxor \XMM6, \T2, \T2
+ vmovdqa HashKey_3(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM6, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM6, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_3_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM7, \T2
+ vpxor \XMM7, \T2, \T2
+ vmovdqa HashKey_2(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM7, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM7, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_2_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vpshufd $0b01001110, \XMM8, \T2
+ vpxor \XMM8, \T2, \T2
+ vmovdqa HashKey(arg1), \T5
+ vpclmulqdq $0x11, \T5, \XMM8, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM8, \T4
+ vpxor \T4, \T7, \T7
+
+ vmovdqa HashKey_k(arg1), \T3
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+ vpxor \T6, \XMM1, \XMM1
+ vpxor \T7, \XMM1, \T2
+
+
+
+
+ vpslldq $8, \T2, \T4
+ vpsrldq $8, \T2, \T2
+
+ vpxor \T4, \T7, \T7
+ vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
+ # the accumulated carry-less multiplications
+
+ #######################################################################
+ #first phase of the reduction
+ vpslld $31, \T7, \T2 # packed right shifting << 31
+ vpslld $30, \T7, \T3 # packed right shifting shift << 30
+ vpslld $25, \T7, \T4 # packed right shifting shift << 25
+
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
+
+ vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
+
+
+ #second phase of the reduction
+ vpsrld $1, \T7, \T2 # packed left shifting >> 1
+ vpsrld $2, \T7, \T3 # packed left shifting >> 2
+ vpsrld $7, \T7, \T4 # packed left shifting >> 7
+ vpxor \T3, \T2, \T2 # xor the shifted versions
+ vpxor \T4, \T2, \T2
+
+ vpxor \T1, \T2, \T2
+ vpxor \T2, \T7, \T7
+ vpxor \T7, \T6, \T6 # the result is in T6
+
+.endm
+
+
+# combined for GCM encrypt and decrypt functions
+# clobbering all xmm registers
+# clobbering r10, r11, r12, r13, r14, r15
+.macro GCM_ENC_DEC_AVX ENC_DEC
+
+ #the number of pushes must equal STACK_OFFSET
+ push %r12
+ push %r13
+ push %r14
+ push %r15
+
+ mov %rsp, %r14
+
+
+
+
+ sub $VARIABLE_OFFSET, %rsp
+ and $~63, %rsp # align rsp to 64 bytes
+
+
+ vmovdqu HashKey(arg1), %xmm13 # xmm13 = HashKey
+
+ mov arg4, %r13 # save the number of bytes of plaintext/ciphertext
+ and $-16, %r13 # r13 = r13 - (r13 mod 16)
+
+ mov %r13, %r12
+ shr $4, %r12
+ and $7, %r12
+ jz _initial_num_blocks_is_0\@
+
+ cmp $7, %r12
+ je _initial_num_blocks_is_7\@
+ cmp $6, %r12
+ je _initial_num_blocks_is_6\@
+ cmp $5, %r12
+ je _initial_num_blocks_is_5\@
+ cmp $4, %r12
+ je _initial_num_blocks_is_4\@
+ cmp $3, %r12
+ je _initial_num_blocks_is_3\@
+ cmp $2, %r12
+ je _initial_num_blocks_is_2\@
+
+ jmp _initial_num_blocks_is_1\@
+
+_initial_num_blocks_is_7\@:
+ INITIAL_BLOCKS_AVX 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*7, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_6\@:
+ INITIAL_BLOCKS_AVX 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*6, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_5\@:
+ INITIAL_BLOCKS_AVX 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*5, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_4\@:
+ INITIAL_BLOCKS_AVX 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*4, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_3\@:
+ INITIAL_BLOCKS_AVX 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*3, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_2\@:
+ INITIAL_BLOCKS_AVX 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*2, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_1\@:
+ INITIAL_BLOCKS_AVX 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*1, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_0\@:
+ INITIAL_BLOCKS_AVX 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+
+
+_initial_blocks_encrypted\@:
+ cmp $0, %r13
+ je _zero_cipher_left\@
+
+ sub $128, %r13
+ je _eight_cipher_left\@
+
+
+
+
+ vmovd %xmm9, %r15d
+ and $255, %r15d
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+
+
+_encrypt_by_8_new\@:
+ cmp $(255-8), %r15d
+ jg _encrypt_by_8\@
+
+
+
+ add $8, %r15b
+ GHASH_8_ENCRYPT_8_PARALLEL_AVX %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
+ add $128, %r11
+ sub $128, %r13
+ jne _encrypt_by_8_new\@
+
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ jmp _eight_cipher_left\@
+
+_encrypt_by_8\@:
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ add $8, %r15b
+ GHASH_8_ENCRYPT_8_PARALLEL_AVX %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ add $128, %r11
+ sub $128, %r13
+ jne _encrypt_by_8_new\@
+
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+
+
+
+
+_eight_cipher_left\@:
+ GHASH_LAST_8_AVX %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
+
+
+_zero_cipher_left\@:
+ cmp $16, arg4
+ jl _only_less_than_16\@
+
+ mov arg4, %r13
+ and $15, %r13 # r13 = (arg4 mod 16)
+
+ je _multiple_of_16_bytes\@
+
+ # handle the last <16 Byte block seperately
+
+
+ vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+
+ sub $16, %r11
+ add %r13, %r11
+ vmovdqu (arg3, %r11), %xmm1 # receive the last <16 Byte block
+
+ lea SHIFT_MASK+16(%rip), %r12
+ sub %r13, %r12 # adjust the shuffle mask pointer to be
+ # able to shift 16-r13 bytes (r13 is the
+ # number of bytes in plaintext mod 16)
+ vmovdqu (%r12), %xmm2 # get the appropriate shuffle mask
+ vpshufb %xmm2, %xmm1, %xmm1 # shift right 16-r13 bytes
+ jmp _final_ghash_mul\@
+
+_only_less_than_16\@:
+ # check for 0 length
+ mov arg4, %r13
+ and $15, %r13 # r13 = (arg4 mod 16)
+
+ je _multiple_of_16_bytes\@
+
+ # handle the last <16 Byte block seperately
+
+
+ vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+
+
+ lea SHIFT_MASK+16(%rip), %r12
+ sub %r13, %r12 # adjust the shuffle mask pointer to be
+ # able to shift 16-r13 bytes (r13 is the
+ # number of bytes in plaintext mod 16)
+
+_get_last_16_byte_loop\@:
+ movb (arg3, %r11), %al
+ movb %al, TMP1 (%rsp , %r11)
+ add $1, %r11
+ cmp %r13, %r11
+ jne _get_last_16_byte_loop\@
+
+ vmovdqu TMP1(%rsp), %xmm1
+
+ sub $16, %r11
+
+_final_ghash_mul\@:
+ .if \ENC_DEC == DEC
+ vmovdqa %xmm1, %xmm2
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
+ # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm2, %xmm2
+ vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
+ vpxor %xmm2, %xmm14, %xmm14
+ #GHASH computation for the last <16 Byte block
+ GHASH_MUL_AVX %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+ sub %r13, %r11
+ add $16, %r11
+ .else
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
+ # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ vpxor %xmm9, %xmm14, %xmm14
+ #GHASH computation for the last <16 Byte block
+ GHASH_MUL_AVX %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+ sub %r13, %r11
+ add $16, %r11
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9 # shuffle xmm9 back to output as ciphertext
+ .endif
+
+
+ #############################
+ # output r13 Bytes
+ vmovq %xmm9, %rax
+ cmp $8, %r13
+ jle _less_than_8_bytes_left\@
+
+ mov %rax, (arg2 , %r11)
+ add $8, %r11
+ vpsrldq $8, %xmm9, %xmm9
+ vmovq %xmm9, %rax
+ sub $8, %r13
+
+_less_than_8_bytes_left\@:
+ movb %al, (arg2 , %r11)
+ add $1, %r11
+ shr $8, %rax
+ sub $1, %r13
+ jne _less_than_8_bytes_left\@
+ #############################
+
+_multiple_of_16_bytes\@:
+ mov arg7, %r12 # r12 = aadLen (number of bytes)
+ shl $3, %r12 # convert into number of bits
+ vmovd %r12d, %xmm15 # len(A) in xmm15
+
+ shl $3, arg4 # len(C) in bits (*128)
+ vmovq arg4, %xmm1
+ vpslldq $8, %xmm15, %xmm15 # xmm15 = len(A)|| 0x0000000000000000
+ vpxor %xmm1, %xmm15, %xmm15 # xmm15 = len(A)||len(C)
+
+ vpxor %xmm15, %xmm14, %xmm14
+ GHASH_MUL_AVX %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 # final GHASH computation
+ vpshufb SHUF_MASK(%rip), %xmm14, %xmm14 # perform a 16Byte swap
+
+ mov arg5, %rax # rax = *Y0
+ vmovdqu (%rax), %xmm9 # xmm9 = Y0
+
+ ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Y0)
+
+ vpxor %xmm14, %xmm9, %xmm9
+
+
+
+_return_T\@:
+ mov arg8, %r10 # r10 = authTag
+ mov arg9, %r11 # r11 = auth_tag_len
+
+ cmp $16, %r11
+ je _T_16\@
+
+ cmp $12, %r11
+ je _T_12\@
+
+_T_8\@:
+ vmovq %xmm9, %rax
+ mov %rax, (%r10)
+ jmp _return_T_done\@
+_T_12\@:
+ vmovq %xmm9, %rax
+ mov %rax, (%r10)
+ vpsrldq $8, %xmm9, %xmm9
+ vmovd %xmm9, %eax
+ mov %eax, 8(%r10)
+ jmp _return_T_done\@
+
+_T_16\@:
+ vmovdqu %xmm9, (%r10)
+
+_return_T_done\@:
+ mov %r14, %rsp
+
+ pop %r15
+ pop %r14
+ pop %r13
+ pop %r12
+.endm
+
+
+#############################################################
+#void aesni_gcm_precomp_avx_gen2
+# (gcm_data *my_ctx_data,
+# u8 *hash_subkey)# /* H, the Hash sub key input. Data starts on a 16-byte boundary. */
+#############################################################
+ENTRY(aesni_gcm_precomp_avx_gen2)
+ #the number of pushes must equal STACK_OFFSET
+ push %r12
+ push %r13
+ push %r14
+ push %r15
+
+ mov %rsp, %r14
+
+
+
+ sub $VARIABLE_OFFSET, %rsp
+ and $~63, %rsp # align rsp to 64 bytes
+
+ vmovdqu (arg2), %xmm6 # xmm6 = HashKey
+
+ vpshufb SHUF_MASK(%rip), %xmm6, %xmm6
+ ############### PRECOMPUTATION of HashKey<<1 mod poly from the HashKey
+ vmovdqa %xmm6, %xmm2
+ vpsllq $1, %xmm6, %xmm6
+ vpsrlq $63, %xmm2, %xmm2
+ vmovdqa %xmm2, %xmm1
+ vpslldq $8, %xmm2, %xmm2
+ vpsrldq $8, %xmm1, %xmm1
+ vpor %xmm2, %xmm6, %xmm6
+ #reduction
+ vpshufd $0b00100100, %xmm1, %xmm2
+ vpcmpeqd TWOONE(%rip), %xmm2, %xmm2
+ vpand POLY(%rip), %xmm2, %xmm2
+ vpxor %xmm2, %xmm6, %xmm6 # xmm6 holds the HashKey<<1 mod poly
+ #######################################################################
+ vmovdqa %xmm6, HashKey(arg1) # store HashKey<<1 mod poly
+
+
+ PRECOMPUTE_AVX %xmm6, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5
+
+ mov %r14, %rsp
+
+ pop %r15
+ pop %r14
+ pop %r13
+ pop %r12
+ ret
+ENDPROC(aesni_gcm_precomp_avx_gen2)
+
+###############################################################################
+#void aesni_gcm_enc_avx_gen2(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
+# const u8 *in, /* Plaintext input */
+# u64 plaintext_len, /* Length of data in Bytes for encryption. */
+# u8 *iv, /* Pre-counter block j0: 4 byte salt
+# (from Security Association) concatenated with 8 byte
+# Initialisation Vector (from IPSec ESP Payload)
+# concatenated with 0x00000001. 16-byte aligned pointer. */
+# const u8 *aad, /* Additional Authentication Data (AAD)*/
+# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+# u8 *auth_tag, /* Authenticated Tag output. */
+# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
+# Valid values are 16 (most likely), 12 or 8. */
+###############################################################################
+ENTRY(aesni_gcm_enc_avx_gen2)
+ GCM_ENC_DEC_AVX ENC
+ ret
+ENDPROC(aesni_gcm_enc_avx_gen2)
+
+###############################################################################
+#void aesni_gcm_dec_avx_gen2(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# u8 *out, /* Plaintext output. Decrypt in-place is allowed. */
+# const u8 *in, /* Ciphertext input */
+# u64 plaintext_len, /* Length of data in Bytes for encryption. */
+# u8 *iv, /* Pre-counter block j0: 4 byte salt
+# (from Security Association) concatenated with 8 byte
+# Initialisation Vector (from IPSec ESP Payload)
+# concatenated with 0x00000001. 16-byte aligned pointer. */
+# const u8 *aad, /* Additional Authentication Data (AAD)*/
+# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+# u8 *auth_tag, /* Authenticated Tag output. */
+# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
+# Valid values are 16 (most likely), 12 or 8. */
+###############################################################################
+ENTRY(aesni_gcm_dec_avx_gen2)
+ GCM_ENC_DEC_AVX DEC
+ ret
+ENDPROC(aesni_gcm_dec_avx_gen2)
+#endif /* CONFIG_AS_AVX */
+
+#ifdef CONFIG_AS_AVX2
+###############################################################################
+# GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
+# Input: A and B (128-bits each, bit-reflected)
+# Output: C = A*B*x mod poly, (i.e. >>1 )
+# To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
+# GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
+###############################################################################
+.macro GHASH_MUL_AVX2 GH HK T1 T2 T3 T4 T5
+
+ vpclmulqdq $0x11,\HK,\GH,\T1 # T1 = a1*b1
+ vpclmulqdq $0x00,\HK,\GH,\T2 # T2 = a0*b0
+ vpclmulqdq $0x01,\HK,\GH,\T3 # T3 = a1*b0
+ vpclmulqdq $0x10,\HK,\GH,\GH # GH = a0*b1
+ vpxor \T3, \GH, \GH
+
+
+ vpsrldq $8 , \GH, \T3 # shift-R GH 2 DWs
+ vpslldq $8 , \GH, \GH # shift-L GH 2 DWs
+
+ vpxor \T3, \T1, \T1
+ vpxor \T2, \GH, \GH
+
+ #######################################################################
+ #first phase of the reduction
+ vmovdqa POLY2(%rip), \T3
+
+ vpclmulqdq $0x01, \GH, \T3, \T2
+ vpslldq $8, \T2, \T2 # shift-L T2 2 DWs
+
+ vpxor \T2, \GH, \GH # first phase of the reduction complete
+ #######################################################################
+ #second phase of the reduction
+ vpclmulqdq $0x00, \GH, \T3, \T2
+ vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
+
+ vpclmulqdq $0x10, \GH, \T3, \GH
+ vpslldq $4, \GH, \GH # shift-L GH 1 DW (Shift-L 1-DW to obtain result with no shifts)
+
+ vpxor \T2, \GH, \GH # second phase of the reduction complete
+ #######################################################################
+ vpxor \T1, \GH, \GH # the result is in GH
+
+
+.endm
+
+.macro PRECOMPUTE_AVX2 HK T1 T2 T3 T4 T5 T6
+
+ # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
+ vmovdqa \HK, \T5
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
+ vmovdqa \T5, HashKey_2(arg1) # [HashKey_2] = HashKey^2<<1 mod poly
+
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
+ vmovdqa \T5, HashKey_3(arg1)
+
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
+ vmovdqa \T5, HashKey_4(arg1)
+
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
+ vmovdqa \T5, HashKey_5(arg1)
+
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
+ vmovdqa \T5, HashKey_6(arg1)
+
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
+ vmovdqa \T5, HashKey_7(arg1)
+
+ GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
+ vmovdqa \T5, HashKey_8(arg1)
+
+.endm
+
+
+## if a = number of total plaintext bytes
+## b = floor(a/16)
+## num_initial_blocks = b mod 4#
+## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
+## r10, r11, r12, rax are clobbered
+## arg1, arg2, arg3, r14 are used as a pointer only, not modified
+
+.macro INITIAL_BLOCKS_AVX2 num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER
+ i = (8-\num_initial_blocks)
+ setreg
+
+ mov arg6, %r10 # r10 = AAD
+ mov arg7, %r12 # r12 = aadLen
+
+
+ mov %r12, %r11
+
+ vpxor reg_i, reg_i, reg_i
+_get_AAD_loop\@:
+ vmovd (%r10), \T1
+ vpslldq $12, \T1, \T1
+ vpsrldq $4, reg_i, reg_i
+ vpxor \T1, reg_i, reg_i
+
+ add $4, %r10
+ sub $4, %r12
+ jg _get_AAD_loop\@
+
+
+ cmp $16, %r11
+ je _get_AAD_loop2_done\@
+ mov $16, %r12
+
+_get_AAD_loop2\@:
+ vpsrldq $4, reg_i, reg_i
+ sub $4, %r12
+ cmp %r11, %r12
+ jg _get_AAD_loop2\@
+
+_get_AAD_loop2_done\@:
+
+ #byte-reflect the AAD data
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i
+
+ # initialize the data pointer offset as zero
+ xor %r11, %r11
+
+ # start AES for num_initial_blocks blocks
+ mov arg5, %rax # rax = *Y0
+ vmovdqu (%rax), \CTR # CTR = Y0
+ vpshufb SHUF_MASK(%rip), \CTR, \CTR
+
+
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, reg_i
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i # perform a 16Byte swap
+ i = (i+1)
+ setreg
+.endr
+
+ vmovdqa (arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vpxor \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
+
+ j = 1
+ setreg
+.rep 9
+ vmovdqa 16*j(arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vaesenc \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
+
+ j = (j+1)
+ setreg
+.endr
+
+
+ vmovdqa 16*10(arg1), \T_key
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vaesenclast \T_key, reg_i, reg_i
+ i = (i+1)
+ setreg
+.endr
+
+ i = (9-\num_initial_blocks)
+ setreg
+.rep \num_initial_blocks
+ vmovdqu (arg3, %r11), \T1
+ vpxor \T1, reg_i, reg_i
+ vmovdqu reg_i, (arg2 , %r11) # write back ciphertext for
+ # num_initial_blocks blocks
+ add $16, %r11
+.if \ENC_DEC == DEC
+ vmovdqa \T1, reg_i
+.endif
+ vpshufb SHUF_MASK(%rip), reg_i, reg_i # prepare ciphertext for GHASH computations
+ i = (i+1)
+ setreg
+.endr
+
+
+ i = (8-\num_initial_blocks)
+ j = (9-\num_initial_blocks)
+ setreg
+ GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6
+
+.rep \num_initial_blocks
+ vpxor reg_i, reg_j, reg_j
+ GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ # XMM8 has the combined result here
+
+ vmovdqa \XMM8, TMP1(%rsp)
+ vmovdqa \XMM8, \T3
+
+ cmp $128, %r13
+ jl _initial_blocks_done\@ # no need for precomputed constants
+
+###############################################################################
+# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM1
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM2
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM3
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM4
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM5
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM6
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM7
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+
+ vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
+ vmovdqa \CTR, \XMM8
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+
+ vmovdqa (arg1), \T_key
+ vpxor \T_key, \XMM1, \XMM1
+ vpxor \T_key, \XMM2, \XMM2
+ vpxor \T_key, \XMM3, \XMM3
+ vpxor \T_key, \XMM4, \XMM4
+ vpxor \T_key, \XMM5, \XMM5
+ vpxor \T_key, \XMM6, \XMM6
+ vpxor \T_key, \XMM7, \XMM7
+ vpxor \T_key, \XMM8, \XMM8
+
+ i = 1
+ setreg
+.rep 9 # do 9 rounds
+ vmovdqa 16*i(arg1), \T_key
+ vaesenc \T_key, \XMM1, \XMM1
+ vaesenc \T_key, \XMM2, \XMM2
+ vaesenc \T_key, \XMM3, \XMM3
+ vaesenc \T_key, \XMM4, \XMM4
+ vaesenc \T_key, \XMM5, \XMM5
+ vaesenc \T_key, \XMM6, \XMM6
+ vaesenc \T_key, \XMM7, \XMM7
+ vaesenc \T_key, \XMM8, \XMM8
+ i = (i+1)
+ setreg
+.endr
+
+
+ vmovdqa 16*i(arg1), \T_key
+ vaesenclast \T_key, \XMM1, \XMM1
+ vaesenclast \T_key, \XMM2, \XMM2
+ vaesenclast \T_key, \XMM3, \XMM3
+ vaesenclast \T_key, \XMM4, \XMM4
+ vaesenclast \T_key, \XMM5, \XMM5
+ vaesenclast \T_key, \XMM6, \XMM6
+ vaesenclast \T_key, \XMM7, \XMM7
+ vaesenclast \T_key, \XMM8, \XMM8
+
+ vmovdqu (arg3, %r11), \T1
+ vpxor \T1, \XMM1, \XMM1
+ vmovdqu \XMM1, (arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM1
+ .endif
+
+ vmovdqu 16*1(arg3, %r11), \T1
+ vpxor \T1, \XMM2, \XMM2
+ vmovdqu \XMM2, 16*1(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM2
+ .endif
+
+ vmovdqu 16*2(arg3, %r11), \T1
+ vpxor \T1, \XMM3, \XMM3
+ vmovdqu \XMM3, 16*2(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM3
+ .endif
+
+ vmovdqu 16*3(arg3, %r11), \T1
+ vpxor \T1, \XMM4, \XMM4
+ vmovdqu \XMM4, 16*3(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM4
+ .endif
+
+ vmovdqu 16*4(arg3, %r11), \T1
+ vpxor \T1, \XMM5, \XMM5
+ vmovdqu \XMM5, 16*4(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM5
+ .endif
+
+ vmovdqu 16*5(arg3, %r11), \T1
+ vpxor \T1, \XMM6, \XMM6
+ vmovdqu \XMM6, 16*5(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM6
+ .endif
+
+ vmovdqu 16*6(arg3, %r11), \T1
+ vpxor \T1, \XMM7, \XMM7
+ vmovdqu \XMM7, 16*6(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM7
+ .endif
+
+ vmovdqu 16*7(arg3, %r11), \T1
+ vpxor \T1, \XMM8, \XMM8
+ vmovdqu \XMM8, 16*7(arg2 , %r11)
+ .if \ENC_DEC == DEC
+ vmovdqa \T1, \XMM8
+ .endif
+
+ add $128, %r11
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpxor TMP1(%rsp), \XMM1, \XMM1 # combine GHASHed value with
+ # the corresponding ciphertext
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+
+###############################################################################
+
+_initial_blocks_done\@:
+
+
+.endm
+
+
+
+# encrypt 8 blocks at a time
+# ghash the 8 previously encrypted ciphertext blocks
+# arg1, arg2, arg3 are used as pointers only, not modified
+# r11 is the data offset value
+.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
+
+ vmovdqa \XMM1, \T2
+ vmovdqa \XMM2, TMP2(%rsp)
+ vmovdqa \XMM3, TMP3(%rsp)
+ vmovdqa \XMM4, TMP4(%rsp)
+ vmovdqa \XMM5, TMP5(%rsp)
+ vmovdqa \XMM6, TMP6(%rsp)
+ vmovdqa \XMM7, TMP7(%rsp)
+ vmovdqa \XMM8, TMP8(%rsp)
+
+.if \loop_idx == in_order
+ vpaddd ONE(%rip), \CTR, \XMM1 # INCR CNT
+ vpaddd ONE(%rip), \XMM1, \XMM2
+ vpaddd ONE(%rip), \XMM2, \XMM3
+ vpaddd ONE(%rip), \XMM3, \XMM4
+ vpaddd ONE(%rip), \XMM4, \XMM5
+ vpaddd ONE(%rip), \XMM5, \XMM6
+ vpaddd ONE(%rip), \XMM6, \XMM7
+ vpaddd ONE(%rip), \XMM7, \XMM8
+ vmovdqa \XMM8, \CTR
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+.else
+ vpaddd ONEf(%rip), \CTR, \XMM1 # INCR CNT
+ vpaddd ONEf(%rip), \XMM1, \XMM2
+ vpaddd ONEf(%rip), \XMM2, \XMM3
+ vpaddd ONEf(%rip), \XMM3, \XMM4
+ vpaddd ONEf(%rip), \XMM4, \XMM5
+ vpaddd ONEf(%rip), \XMM5, \XMM6
+ vpaddd ONEf(%rip), \XMM6, \XMM7
+ vpaddd ONEf(%rip), \XMM7, \XMM8
+ vmovdqa \XMM8, \CTR
+.endif
+
+
+ #######################################################################
+
+ vmovdqu (arg1), \T1
+ vpxor \T1, \XMM1, \XMM1
+ vpxor \T1, \XMM2, \XMM2
+ vpxor \T1, \XMM3, \XMM3
+ vpxor \T1, \XMM4, \XMM4
+ vpxor \T1, \XMM5, \XMM5
+ vpxor \T1, \XMM6, \XMM6
+ vpxor \T1, \XMM7, \XMM7
+ vpxor \T1, \XMM8, \XMM8
+
+ #######################################################################
+
+
+
+
+
+ vmovdqu 16*1(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqu 16*2(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+
+ #######################################################################
+
+ vmovdqa HashKey_8(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
+ vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
+ vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
+ vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
+ vpxor \T5, \T6, \T6
+
+ vmovdqu 16*3(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP2(%rsp), \T1
+ vmovdqa HashKey_7(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*4(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ #######################################################################
+
+ vmovdqa TMP3(%rsp), \T1
+ vmovdqa HashKey_6(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*5(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP4(%rsp), \T1
+ vmovdqa HashKey_5(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*6(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+
+ vmovdqa TMP5(%rsp), \T1
+ vmovdqa HashKey_4(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*7(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP6(%rsp), \T1
+ vmovdqa HashKey_3(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vmovdqu 16*8(arg1), \T1
+ vaesenc \T1, \XMM1, \XMM1
+ vaesenc \T1, \XMM2, \XMM2
+ vaesenc \T1, \XMM3, \XMM3
+ vaesenc \T1, \XMM4, \XMM4
+ vaesenc \T1, \XMM5, \XMM5
+ vaesenc \T1, \XMM6, \XMM6
+ vaesenc \T1, \XMM7, \XMM7
+ vaesenc \T1, \XMM8, \XMM8
+
+ vmovdqa TMP7(%rsp), \T1
+ vmovdqa HashKey_2(arg1), \T5
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T4
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+
+ #######################################################################
+
+ vmovdqu 16*9(arg1), \T5
+ vaesenc \T5, \XMM1, \XMM1
+ vaesenc \T5, \XMM2, \XMM2
+ vaesenc \T5, \XMM3, \XMM3
+ vaesenc \T5, \XMM4, \XMM4
+ vaesenc \T5, \XMM5, \XMM5
+ vaesenc \T5, \XMM6, \XMM6
+ vaesenc \T5, \XMM7, \XMM7
+ vaesenc \T5, \XMM8, \XMM8
+
+ vmovdqa TMP8(%rsp), \T1
+ vmovdqa HashKey(arg1), \T5
+
+ vpclmulqdq $0x00, \T5, \T1, \T3
+ vpxor \T3, \T7, \T7
+
+ vpclmulqdq $0x01, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x10, \T5, \T1, \T3
+ vpxor \T3, \T6, \T6
+
+ vpclmulqdq $0x11, \T5, \T1, \T3
+ vpxor \T3, \T4, \T1
+
+
+ vmovdqu 16*10(arg1), \T5
+
+ i = 0
+ j = 1
+ setreg
+.rep 8
+ vpxor 16*i(arg3, %r11), \T5, \T2
+ .if \ENC_DEC == ENC
+ vaesenclast \T2, reg_j, reg_j
+ .else
+ vaesenclast \T2, reg_j, \T3
+ vmovdqu 16*i(arg3, %r11), reg_j
+ vmovdqu \T3, 16*i(arg2, %r11)
+ .endif
+ i = (i+1)
+ j = (j+1)
+ setreg
+.endr
+ #######################################################################
+
+
+ vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
+ vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
+ vpxor \T3, \T7, \T7
+ vpxor \T6, \T1, \T1 # accumulate the results in T1:T7
+
+
+
+ #######################################################################
+ #first phase of the reduction
+ vmovdqa POLY2(%rip), \T3
+
+ vpclmulqdq $0x01, \T7, \T3, \T2
+ vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
+
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
+ .if \ENC_DEC == ENC
+ vmovdqu \XMM1, 16*0(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM2, 16*1(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM3, 16*2(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM4, 16*3(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM5, 16*4(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM6, 16*5(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM7, 16*6(arg2,%r11) # Write to the Ciphertext buffer
+ vmovdqu \XMM8, 16*7(arg2,%r11) # Write to the Ciphertext buffer
+ .endif
+
+ #######################################################################
+ #second phase of the reduction
+ vpclmulqdq $0x00, \T7, \T3, \T2
+ vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
+
+ vpclmulqdq $0x10, \T7, \T3, \T4
+ vpslldq $4, \T4, \T4 # shift-L xmm0 1 DW (Shift-L 1-DW to obtain result with no shifts)
+
+ vpxor \T2, \T4, \T4 # second phase of the reduction complete
+ #######################################################################
+ vpxor \T4, \T1, \T1 # the result is in T1
+
+ vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
+ vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
+
+
+ vpxor \T1, \XMM1, \XMM1
+
+
+
+.endm
+
+
+# GHASH the last 4 ciphertext blocks.
+.macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
+
+ ## Karatsuba Method
+
+ vmovdqa HashKey_8(arg1), \T5
+
+ vpshufd $0b01001110, \XMM1, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM1, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM1, \T6
+ vpclmulqdq $0x00, \T5, \XMM1, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \XMM1
+
+ ######################
+
+ vmovdqa HashKey_7(arg1), \T5
+ vpshufd $0b01001110, \XMM2, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM2, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM2, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM2, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vmovdqa HashKey_6(arg1), \T5
+ vpshufd $0b01001110, \XMM3, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM3, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM3, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM3, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vmovdqa HashKey_5(arg1), \T5
+ vpshufd $0b01001110, \XMM4, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM4, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM4, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM4, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vmovdqa HashKey_4(arg1), \T5
+ vpshufd $0b01001110, \XMM5, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM5, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM5, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM5, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vmovdqa HashKey_3(arg1), \T5
+ vpshufd $0b01001110, \XMM6, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM6, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM6, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM6, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vmovdqa HashKey_2(arg1), \T5
+ vpshufd $0b01001110, \XMM7, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM7, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM7, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM7, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+
+ ######################
+
+ vmovdqa HashKey(arg1), \T5
+ vpshufd $0b01001110, \XMM8, \T2
+ vpshufd $0b01001110, \T5, \T3
+ vpxor \XMM8, \T2, \T2
+ vpxor \T5, \T3, \T3
+
+ vpclmulqdq $0x11, \T5, \XMM8, \T4
+ vpxor \T4, \T6, \T6
+
+ vpclmulqdq $0x00, \T5, \XMM8, \T4
+ vpxor \T4, \T7, \T7
+
+ vpclmulqdq $0x00, \T3, \T2, \T2
+
+ vpxor \T2, \XMM1, \XMM1
+ vpxor \T6, \XMM1, \XMM1
+ vpxor \T7, \XMM1, \T2
+
+
+
+
+ vpslldq $8, \T2, \T4
+ vpsrldq $8, \T2, \T2
+
+ vpxor \T4, \T7, \T7
+ vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
+ # accumulated carry-less multiplications
+
+ #######################################################################
+ #first phase of the reduction
+ vmovdqa POLY2(%rip), \T3
+
+ vpclmulqdq $0x01, \T7, \T3, \T2
+ vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
+
+ vpxor \T2, \T7, \T7 # first phase of the reduction complete
+ #######################################################################
+
+
+ #second phase of the reduction
+ vpclmulqdq $0x00, \T7, \T3, \T2
+ vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
+
+ vpclmulqdq $0x10, \T7, \T3, \T4
+ vpslldq $4, \T4, \T4 # shift-L T4 1 DW (Shift-L 1-DW to obtain result with no shifts)
+
+ vpxor \T2, \T4, \T4 # second phase of the reduction complete
+ #######################################################################
+ vpxor \T4, \T6, \T6 # the result is in T6
+.endm
+
+
+
+# combined for GCM encrypt and decrypt functions
+# clobbering all xmm registers
+# clobbering r10, r11, r12, r13, r14, r15
+.macro GCM_ENC_DEC_AVX2 ENC_DEC
+
+ #the number of pushes must equal STACK_OFFSET
+ push %r12
+ push %r13
+ push %r14
+ push %r15
+
+ mov %rsp, %r14
+
+
+
+
+ sub $VARIABLE_OFFSET, %rsp
+ and $~63, %rsp # align rsp to 64 bytes
+
+
+ vmovdqu HashKey(arg1), %xmm13 # xmm13 = HashKey
+
+ mov arg4, %r13 # save the number of bytes of plaintext/ciphertext
+ and $-16, %r13 # r13 = r13 - (r13 mod 16)
+
+ mov %r13, %r12
+ shr $4, %r12
+ and $7, %r12
+ jz _initial_num_blocks_is_0\@
+
+ cmp $7, %r12
+ je _initial_num_blocks_is_7\@
+ cmp $6, %r12
+ je _initial_num_blocks_is_6\@
+ cmp $5, %r12
+ je _initial_num_blocks_is_5\@
+ cmp $4, %r12
+ je _initial_num_blocks_is_4\@
+ cmp $3, %r12
+ je _initial_num_blocks_is_3\@
+ cmp $2, %r12
+ je _initial_num_blocks_is_2\@
+
+ jmp _initial_num_blocks_is_1\@
+
+_initial_num_blocks_is_7\@:
+ INITIAL_BLOCKS_AVX2 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*7, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_6\@:
+ INITIAL_BLOCKS_AVX2 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*6, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_5\@:
+ INITIAL_BLOCKS_AVX2 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*5, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_4\@:
+ INITIAL_BLOCKS_AVX2 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*4, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_3\@:
+ INITIAL_BLOCKS_AVX2 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*3, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_2\@:
+ INITIAL_BLOCKS_AVX2 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*2, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_1\@:
+ INITIAL_BLOCKS_AVX2 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+ sub $16*1, %r13
+ jmp _initial_blocks_encrypted\@
+
+_initial_num_blocks_is_0\@:
+ INITIAL_BLOCKS_AVX2 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
+
+
+_initial_blocks_encrypted\@:
+ cmp $0, %r13
+ je _zero_cipher_left\@
+
+ sub $128, %r13
+ je _eight_cipher_left\@
+
+
+
+
+ vmovd %xmm9, %r15d
+ and $255, %r15d
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+
+
+_encrypt_by_8_new\@:
+ cmp $(255-8), %r15d
+ jg _encrypt_by_8\@
+
+
+
+ add $8, %r15b
+ GHASH_8_ENCRYPT_8_PARALLEL_AVX2 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
+ add $128, %r11
+ sub $128, %r13
+ jne _encrypt_by_8_new\@
+
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ jmp _eight_cipher_left\@
+
+_encrypt_by_8\@:
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ add $8, %r15b
+ GHASH_8_ENCRYPT_8_PARALLEL_AVX2 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ add $128, %r11
+ sub $128, %r13
+ jne _encrypt_by_8_new\@
+
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+
+
+
+
+_eight_cipher_left\@:
+ GHASH_LAST_8_AVX2 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
+
+
+_zero_cipher_left\@:
+ cmp $16, arg4
+ jl _only_less_than_16\@
+
+ mov arg4, %r13
+ and $15, %r13 # r13 = (arg4 mod 16)
+
+ je _multiple_of_16_bytes\@
+
+ # handle the last <16 Byte block seperately
+
+
+ vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+
+ sub $16, %r11
+ add %r13, %r11
+ vmovdqu (arg3, %r11), %xmm1 # receive the last <16 Byte block
+
+ lea SHIFT_MASK+16(%rip), %r12
+ sub %r13, %r12 # adjust the shuffle mask pointer
+ # to be able to shift 16-r13 bytes
+ # (r13 is the number of bytes in plaintext mod 16)
+ vmovdqu (%r12), %xmm2 # get the appropriate shuffle mask
+ vpshufb %xmm2, %xmm1, %xmm1 # shift right 16-r13 bytes
+ jmp _final_ghash_mul\@
+
+_only_less_than_16\@:
+ # check for 0 length
+ mov arg4, %r13
+ and $15, %r13 # r13 = (arg4 mod 16)
+
+ je _multiple_of_16_bytes\@
+
+ # handle the last <16 Byte block seperately
+
+
+ vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Yn)
+
+
+ lea SHIFT_MASK+16(%rip), %r12
+ sub %r13, %r12 # adjust the shuffle mask pointer to be
+ # able to shift 16-r13 bytes (r13 is the
+ # number of bytes in plaintext mod 16)
+
+_get_last_16_byte_loop\@:
+ movb (arg3, %r11), %al
+ movb %al, TMP1 (%rsp , %r11)
+ add $1, %r11
+ cmp %r13, %r11
+ jne _get_last_16_byte_loop\@
+
+ vmovdqu TMP1(%rsp), %xmm1
+
+ sub $16, %r11
+
+_final_ghash_mul\@:
+ .if \ENC_DEC == DEC
+ vmovdqa %xmm1, %xmm2
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm2, %xmm2
+ vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
+ vpxor %xmm2, %xmm14, %xmm14
+ #GHASH computation for the last <16 Byte block
+ GHASH_MUL_AVX2 %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+ sub %r13, %r11
+ add $16, %r11
+ .else
+ vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
+ vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to mask out top 16-r13 bytes of xmm9
+ vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
+ vpxor %xmm9, %xmm14, %xmm14
+ #GHASH computation for the last <16 Byte block
+ GHASH_MUL_AVX2 %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
+ sub %r13, %r11
+ add $16, %r11
+ vpshufb SHUF_MASK(%rip), %xmm9, %xmm9 # shuffle xmm9 back to output as ciphertext
+ .endif
+
+
+ #############################
+ # output r13 Bytes
+ vmovq %xmm9, %rax
+ cmp $8, %r13
+ jle _less_than_8_bytes_left\@
+
+ mov %rax, (arg2 , %r11)
+ add $8, %r11
+ vpsrldq $8, %xmm9, %xmm9
+ vmovq %xmm9, %rax
+ sub $8, %r13
+
+_less_than_8_bytes_left\@:
+ movb %al, (arg2 , %r11)
+ add $1, %r11
+ shr $8, %rax
+ sub $1, %r13
+ jne _less_than_8_bytes_left\@
+ #############################
+
+_multiple_of_16_bytes\@:
+ mov arg7, %r12 # r12 = aadLen (number of bytes)
+ shl $3, %r12 # convert into number of bits
+ vmovd %r12d, %xmm15 # len(A) in xmm15
+
+ shl $3, arg4 # len(C) in bits (*128)
+ vmovq arg4, %xmm1
+ vpslldq $8, %xmm15, %xmm15 # xmm15 = len(A)|| 0x0000000000000000
+ vpxor %xmm1, %xmm15, %xmm15 # xmm15 = len(A)||len(C)
+
+ vpxor %xmm15, %xmm14, %xmm14
+ GHASH_MUL_AVX2 %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 # final GHASH computation
+ vpshufb SHUF_MASK(%rip), %xmm14, %xmm14 # perform a 16Byte swap
+
+ mov arg5, %rax # rax = *Y0
+ vmovdqu (%rax), %xmm9 # xmm9 = Y0
+
+ ENCRYPT_SINGLE_BLOCK %xmm9 # E(K, Y0)
+
+ vpxor %xmm14, %xmm9, %xmm9
+
+
+
+_return_T\@:
+ mov arg8, %r10 # r10 = authTag
+ mov arg9, %r11 # r11 = auth_tag_len
+
+ cmp $16, %r11
+ je _T_16\@
+
+ cmp $12, %r11
+ je _T_12\@
+
+_T_8\@:
+ vmovq %xmm9, %rax
+ mov %rax, (%r10)
+ jmp _return_T_done\@
+_T_12\@:
+ vmovq %xmm9, %rax
+ mov %rax, (%r10)
+ vpsrldq $8, %xmm9, %xmm9
+ vmovd %xmm9, %eax
+ mov %eax, 8(%r10)
+ jmp _return_T_done\@
+
+_T_16\@:
+ vmovdqu %xmm9, (%r10)
+
+_return_T_done\@:
+ mov %r14, %rsp
+
+ pop %r15
+ pop %r14
+ pop %r13
+ pop %r12
+.endm
+
+
+#############################################################
+#void aesni_gcm_precomp_avx_gen4
+# (gcm_data *my_ctx_data,
+# u8 *hash_subkey)# /* H, the Hash sub key input.
+# Data starts on a 16-byte boundary. */
+#############################################################
+ENTRY(aesni_gcm_precomp_avx_gen4)
+ #the number of pushes must equal STACK_OFFSET
+ push %r12
+ push %r13
+ push %r14
+ push %r15
+
+ mov %rsp, %r14
+
+
+
+ sub $VARIABLE_OFFSET, %rsp
+ and $~63, %rsp # align rsp to 64 bytes
+
+ vmovdqu (arg2), %xmm6 # xmm6 = HashKey
+
+ vpshufb SHUF_MASK(%rip), %xmm6, %xmm6
+ ############### PRECOMPUTATION of HashKey<<1 mod poly from the HashKey
+ vmovdqa %xmm6, %xmm2
+ vpsllq $1, %xmm6, %xmm6
+ vpsrlq $63, %xmm2, %xmm2
+ vmovdqa %xmm2, %xmm1
+ vpslldq $8, %xmm2, %xmm2
+ vpsrldq $8, %xmm1, %xmm1
+ vpor %xmm2, %xmm6, %xmm6
+ #reduction
+ vpshufd $0b00100100, %xmm1, %xmm2
+ vpcmpeqd TWOONE(%rip), %xmm2, %xmm2
+ vpand POLY(%rip), %xmm2, %xmm2
+ vpxor %xmm2, %xmm6, %xmm6 # xmm6 holds the HashKey<<1 mod poly
+ #######################################################################
+ vmovdqa %xmm6, HashKey(arg1) # store HashKey<<1 mod poly
+
+
+ PRECOMPUTE_AVX2 %xmm6, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5
+
+ mov %r14, %rsp
+
+ pop %r15
+ pop %r14
+ pop %r13
+ pop %r12
+ ret
+ENDPROC(aesni_gcm_precomp_avx_gen4)
+
+
+###############################################################################
+#void aesni_gcm_enc_avx_gen4(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
+# const u8 *in, /* Plaintext input */
+# u64 plaintext_len, /* Length of data in Bytes for encryption. */
+# u8 *iv, /* Pre-counter block j0: 4 byte salt
+# (from Security Association) concatenated with 8 byte
+# Initialisation Vector (from IPSec ESP Payload)
+# concatenated with 0x00000001. 16-byte aligned pointer. */
+# const u8 *aad, /* Additional Authentication Data (AAD)*/
+# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+# u8 *auth_tag, /* Authenticated Tag output. */
+# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
+# Valid values are 16 (most likely), 12 or 8. */
+###############################################################################
+ENTRY(aesni_gcm_enc_avx_gen4)
+ GCM_ENC_DEC_AVX2 ENC
+ ret
+ENDPROC(aesni_gcm_enc_avx_gen4)
+
+###############################################################################
+#void aesni_gcm_dec_avx_gen4(
+# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
+# u8 *out, /* Plaintext output. Decrypt in-place is allowed. */
+# const u8 *in, /* Ciphertext input */
+# u64 plaintext_len, /* Length of data in Bytes for encryption. */
+# u8 *iv, /* Pre-counter block j0: 4 byte salt
+# (from Security Association) concatenated with 8 byte
+# Initialisation Vector (from IPSec ESP Payload)
+# concatenated with 0x00000001. 16-byte aligned pointer. */
+# const u8 *aad, /* Additional Authentication Data (AAD)*/
+# u64 aad_len, /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
+# u8 *auth_tag, /* Authenticated Tag output. */
+# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
+# Valid values are 16 (most likely), 12 or 8. */
+###############################################################################
+ENTRY(aesni_gcm_dec_avx_gen4)
+ GCM_ENC_DEC_AVX2 DEC
+ ret
+ENDPROC(aesni_gcm_dec_avx_gen4)
+
+#endif /* CONFIG_AS_AVX2 */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index f80e668785c..948ad0e7774 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -34,7 +34,7 @@
#include <asm/cpu_device_id.h>
#include <asm/i387.h>
#include <asm/crypto/aes.h>
-#include <asm/crypto/ablk_helper.h>
+#include <crypto/ablk_helper.h>
#include <crypto/scatterwalk.h>
#include <crypto/internal/aead.h>
#include <linux/workqueue.h>
@@ -101,6 +101,9 @@ asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
int crypto_fpu_init(void);
void crypto_fpu_exit(void);
+#define AVX_GEN2_OPTSIZE 640
+#define AVX_GEN4_OPTSIZE 4096
+
#ifdef CONFIG_X86_64
asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
@@ -150,6 +153,123 @@ asmlinkage void aesni_gcm_dec(void *ctx, u8 *out,
u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
u8 *auth_tag, unsigned long auth_tag_len);
+
+#ifdef CONFIG_AS_AVX
+/*
+ * asmlinkage void aesni_gcm_precomp_avx_gen2()
+ * gcm_data *my_ctx_data, context data
+ * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
+ */
+asmlinkage void aesni_gcm_precomp_avx_gen2(void *my_ctx_data, u8 *hash_subkey);
+
+asmlinkage void aesni_gcm_enc_avx_gen2(void *ctx, u8 *out,
+ const u8 *in, unsigned long plaintext_len, u8 *iv,
+ const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len);
+
+asmlinkage void aesni_gcm_dec_avx_gen2(void *ctx, u8 *out,
+ const u8 *in, unsigned long ciphertext_len, u8 *iv,
+ const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len);
+
+static void aesni_gcm_enc_avx(void *ctx, u8 *out,
+ const u8 *in, unsigned long plaintext_len, u8 *iv,
+ u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len)
+{
+ if (plaintext_len < AVX_GEN2_OPTSIZE) {
+ aesni_gcm_enc(ctx, out, in, plaintext_len, iv, hash_subkey, aad,
+ aad_len, auth_tag, auth_tag_len);
+ } else {
+ aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
+ aesni_gcm_enc_avx_gen2(ctx, out, in, plaintext_len, iv, aad,
+ aad_len, auth_tag, auth_tag_len);
+ }
+}
+
+static void aesni_gcm_dec_avx(void *ctx, u8 *out,
+ const u8 *in, unsigned long ciphertext_len, u8 *iv,
+ u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len)
+{
+ if (ciphertext_len < AVX_GEN2_OPTSIZE) {
+ aesni_gcm_dec(ctx, out, in, ciphertext_len, iv, hash_subkey, aad,
+ aad_len, auth_tag, auth_tag_len);
+ } else {
+ aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
+ aesni_gcm_dec_avx_gen2(ctx, out, in, ciphertext_len, iv, aad,
+ aad_len, auth_tag, auth_tag_len);
+ }
+}
+#endif
+
+#ifdef CONFIG_AS_AVX2
+/*
+ * asmlinkage void aesni_gcm_precomp_avx_gen4()
+ * gcm_data *my_ctx_data, context data
+ * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
+ */
+asmlinkage void aesni_gcm_precomp_avx_gen4(void *my_ctx_data, u8 *hash_subkey);
+
+asmlinkage void aesni_gcm_enc_avx_gen4(void *ctx, u8 *out,
+ const u8 *in, unsigned long plaintext_len, u8 *iv,
+ const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len);
+
+asmlinkage void aesni_gcm_dec_avx_gen4(void *ctx, u8 *out,
+ const u8 *in, unsigned long ciphertext_len, u8 *iv,
+ const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len);
+
+static void aesni_gcm_enc_avx2(void *ctx, u8 *out,
+ const u8 *in, unsigned long plaintext_len, u8 *iv,
+ u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len)
+{
+ if (plaintext_len < AVX_GEN2_OPTSIZE) {
+ aesni_gcm_enc(ctx, out, in, plaintext_len, iv, hash_subkey, aad,
+ aad_len, auth_tag, auth_tag_len);
+ } else if (plaintext_len < AVX_GEN4_OPTSIZE) {
+ aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
+ aesni_gcm_enc_avx_gen2(ctx, out, in, plaintext_len, iv, aad,
+ aad_len, auth_tag, auth_tag_len);
+ } else {
+ aesni_gcm_precomp_avx_gen4(ctx, hash_subkey);
+ aesni_gcm_enc_avx_gen4(ctx, out, in, plaintext_len, iv, aad,
+ aad_len, auth_tag, auth_tag_len);
+ }
+}
+
+static void aesni_gcm_dec_avx2(void *ctx, u8 *out,
+ const u8 *in, unsigned long ciphertext_len, u8 *iv,
+ u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len)
+{
+ if (ciphertext_len < AVX_GEN2_OPTSIZE) {
+ aesni_gcm_dec(ctx, out, in, ciphertext_len, iv, hash_subkey,
+ aad, aad_len, auth_tag, auth_tag_len);
+ } else if (ciphertext_len < AVX_GEN4_OPTSIZE) {
+ aesni_gcm_precomp_avx_gen2(ctx, hash_subkey);
+ aesni_gcm_dec_avx_gen2(ctx, out, in, ciphertext_len, iv, aad,
+ aad_len, auth_tag, auth_tag_len);
+ } else {
+ aesni_gcm_precomp_avx_gen4(ctx, hash_subkey);
+ aesni_gcm_dec_avx_gen4(ctx, out, in, ciphertext_len, iv, aad,
+ aad_len, auth_tag, auth_tag_len);
+ }
+}
+#endif
+
+static void (*aesni_gcm_enc_tfm)(void *ctx, u8 *out,
+ const u8 *in, unsigned long plaintext_len, u8 *iv,
+ u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len);
+
+static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out,
+ const u8 *in, unsigned long ciphertext_len, u8 *iv,
+ u8 *hash_subkey, const u8 *aad, unsigned long aad_len,
+ u8 *auth_tag, unsigned long auth_tag_len);
+
static inline struct
aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
{
@@ -915,7 +1035,7 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
dst = src;
}
- aesni_gcm_enc(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
+ aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst
+ ((unsigned long)req->cryptlen), auth_tag_len);
@@ -996,12 +1116,12 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
dst = src;
}
- aesni_gcm_dec(aes_ctx, dst, src, tempCipherLen, iv,
+ aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
ctx->hash_subkey, assoc, (unsigned long)req->assoclen,
authTag, auth_tag_len);
/* Compare generated tag with passed in tag. */
- retval = memcmp(src + tempCipherLen, authTag, auth_tag_len) ?
+ retval = crypto_memneq(src + tempCipherLen, authTag, auth_tag_len) ?
-EBADMSG : 0;
if (one_entry_in_sg) {
@@ -1353,6 +1473,27 @@ static int __init aesni_init(void)
if (!x86_match_cpu(aesni_cpu_id))
return -ENODEV;
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_AS_AVX2
+ if (boot_cpu_has(X86_FEATURE_AVX2)) {
+ pr_info("AVX2 version of gcm_enc/dec engaged.\n");
+ aesni_gcm_enc_tfm = aesni_gcm_enc_avx2;
+ aesni_gcm_dec_tfm = aesni_gcm_dec_avx2;
+ } else
+#endif
+#ifdef CONFIG_AS_AVX
+ if (boot_cpu_has(X86_FEATURE_AVX)) {
+ pr_info("AVX version of gcm_enc/dec engaged.\n");
+ aesni_gcm_enc_tfm = aesni_gcm_enc_avx;
+ aesni_gcm_dec_tfm = aesni_gcm_dec_avx;
+ } else
+#endif
+ {
+ pr_info("SSE version of gcm_enc/dec engaged.\n");
+ aesni_gcm_enc_tfm = aesni_gcm_enc;
+ aesni_gcm_dec_tfm = aesni_gcm_dec;
+ }
+#endif
err = crypto_fpu_init();
if (err)
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 50ec333b70e..8af519ed73d 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -223,9 +223,6 @@ static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
src -= 1;
dst -= 1;
} while (nbytes >= bsize * 4);
-
- if (nbytes < bsize)
- goto done;
}
/* Handle leftovers */
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 414fe5d7946..4209a76fcda 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/ctr.h>
#include <crypto/lrw.h>
@@ -21,7 +22,6 @@
#include <asm/xcr.h>
#include <asm/xsave.h>
#include <asm/crypto/camellia.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
#define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 37fd0c0a81e..87a041a10f4 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/ctr.h>
#include <crypto/lrw.h>
@@ -21,7 +22,6 @@
#include <asm/xcr.h>
#include <asm/xsave.h>
#include <asm/crypto/camellia.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
#define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 5cb86ccd4ac..c171dcbf192 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -62,7 +62,7 @@ static void camellia_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
}
/* camellia sboxes */
-const u64 camellia_sp10011110[256] = {
+__visible const u64 camellia_sp10011110[256] = {
0x7000007070707000ULL, 0x8200008282828200ULL, 0x2c00002c2c2c2c00ULL,
0xec0000ecececec00ULL, 0xb30000b3b3b3b300ULL, 0x2700002727272700ULL,
0xc00000c0c0c0c000ULL, 0xe50000e5e5e5e500ULL, 0xe40000e4e4e4e400ULL,
@@ -151,7 +151,7 @@ const u64 camellia_sp10011110[256] = {
0x9e00009e9e9e9e00ULL,
};
-const u64 camellia_sp22000222[256] = {
+__visible const u64 camellia_sp22000222[256] = {
0xe0e0000000e0e0e0ULL, 0x0505000000050505ULL, 0x5858000000585858ULL,
0xd9d9000000d9d9d9ULL, 0x6767000000676767ULL, 0x4e4e0000004e4e4eULL,
0x8181000000818181ULL, 0xcbcb000000cbcbcbULL, 0xc9c9000000c9c9c9ULL,
@@ -240,7 +240,7 @@ const u64 camellia_sp22000222[256] = {
0x3d3d0000003d3d3dULL,
};
-const u64 camellia_sp03303033[256] = {
+__visible const u64 camellia_sp03303033[256] = {
0x0038380038003838ULL, 0x0041410041004141ULL, 0x0016160016001616ULL,
0x0076760076007676ULL, 0x00d9d900d900d9d9ULL, 0x0093930093009393ULL,
0x0060600060006060ULL, 0x00f2f200f200f2f2ULL, 0x0072720072007272ULL,
@@ -329,7 +329,7 @@ const u64 camellia_sp03303033[256] = {
0x004f4f004f004f4fULL,
};
-const u64 camellia_sp00444404[256] = {
+__visible const u64 camellia_sp00444404[256] = {
0x0000707070700070ULL, 0x00002c2c2c2c002cULL, 0x0000b3b3b3b300b3ULL,
0x0000c0c0c0c000c0ULL, 0x0000e4e4e4e400e4ULL, 0x0000575757570057ULL,
0x0000eaeaeaea00eaULL, 0x0000aeaeaeae00aeULL, 0x0000232323230023ULL,
@@ -418,7 +418,7 @@ const u64 camellia_sp00444404[256] = {
0x00009e9e9e9e009eULL,
};
-const u64 camellia_sp02220222[256] = {
+__visible const u64 camellia_sp02220222[256] = {
0x00e0e0e000e0e0e0ULL, 0x0005050500050505ULL, 0x0058585800585858ULL,
0x00d9d9d900d9d9d9ULL, 0x0067676700676767ULL, 0x004e4e4e004e4e4eULL,
0x0081818100818181ULL, 0x00cbcbcb00cbcbcbULL, 0x00c9c9c900c9c9c9ULL,
@@ -507,7 +507,7 @@ const u64 camellia_sp02220222[256] = {
0x003d3d3d003d3d3dULL,
};
-const u64 camellia_sp30333033[256] = {
+__visible const u64 camellia_sp30333033[256] = {
0x3800383838003838ULL, 0x4100414141004141ULL, 0x1600161616001616ULL,
0x7600767676007676ULL, 0xd900d9d9d900d9d9ULL, 0x9300939393009393ULL,
0x6000606060006060ULL, 0xf200f2f2f200f2f2ULL, 0x7200727272007272ULL,
@@ -596,7 +596,7 @@ const u64 camellia_sp30333033[256] = {
0x4f004f4f4f004f4fULL,
};
-const u64 camellia_sp44044404[256] = {
+__visible const u64 camellia_sp44044404[256] = {
0x7070007070700070ULL, 0x2c2c002c2c2c002cULL, 0xb3b300b3b3b300b3ULL,
0xc0c000c0c0c000c0ULL, 0xe4e400e4e4e400e4ULL, 0x5757005757570057ULL,
0xeaea00eaeaea00eaULL, 0xaeae00aeaeae00aeULL, 0x2323002323230023ULL,
@@ -685,7 +685,7 @@ const u64 camellia_sp44044404[256] = {
0x9e9e009e9e9e009eULL,
};
-const u64 camellia_sp11101110[256] = {
+__visible const u64 camellia_sp11101110[256] = {
0x7070700070707000ULL, 0x8282820082828200ULL, 0x2c2c2c002c2c2c00ULL,
0xececec00ececec00ULL, 0xb3b3b300b3b3b300ULL, 0x2727270027272700ULL,
0xc0c0c000c0c0c000ULL, 0xe5e5e500e5e5e500ULL, 0xe4e4e400e4e4e400ULL,
@@ -828,8 +828,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
subRL[1] ^= (subRL[1] & ~subRL[9]) << 32;
/* modified for FLinv(kl2) */
- dw = (subRL[1] & subRL[9]) >> 32,
- subRL[1] ^= rol32(dw, 1);
+ dw = (subRL[1] & subRL[9]) >> 32;
+ subRL[1] ^= rol32(dw, 1);
/* round 8 */
subRL[11] ^= subRL[1];
@@ -840,8 +840,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
subRL[1] ^= (subRL[1] & ~subRL[17]) << 32;
/* modified for FLinv(kl4) */
- dw = (subRL[1] & subRL[17]) >> 32,
- subRL[1] ^= rol32(dw, 1);
+ dw = (subRL[1] & subRL[17]) >> 32;
+ subRL[1] ^= rol32(dw, 1);
/* round 14 */
subRL[19] ^= subRL[1];
@@ -859,8 +859,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
} else {
subRL[1] ^= (subRL[1] & ~subRL[25]) << 32;
/* modified for FLinv(kl6) */
- dw = (subRL[1] & subRL[25]) >> 32,
- subRL[1] ^= rol32(dw, 1);
+ dw = (subRL[1] & subRL[25]) >> 32;
+ subRL[1] ^= rol32(dw, 1);
/* round 20 */
subRL[27] ^= subRL[1];
@@ -882,8 +882,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
kw4 ^= (kw4 & ~subRL[24]) << 32;
/* modified for FL(kl5) */
- dw = (kw4 & subRL[24]) >> 32,
- kw4 ^= rol32(dw, 1);
+ dw = (kw4 & subRL[24]) >> 32;
+ kw4 ^= rol32(dw, 1);
}
/* round 17 */
@@ -895,8 +895,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
kw4 ^= (kw4 & ~subRL[16]) << 32;
/* modified for FL(kl3) */
- dw = (kw4 & subRL[16]) >> 32,
- kw4 ^= rol32(dw, 1);
+ dw = (kw4 & subRL[16]) >> 32;
+ kw4 ^= rol32(dw, 1);
/* round 11 */
subRL[14] ^= kw4;
@@ -907,8 +907,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
kw4 ^= (kw4 & ~subRL[8]) << 32;
/* modified for FL(kl1) */
- dw = (kw4 & subRL[8]) >> 32,
- kw4 ^= rol32(dw, 1);
+ dw = (kw4 & subRL[8]) >> 32;
+ kw4 ^= rol32(dw, 1);
/* round 5 */
subRL[6] ^= kw4;
@@ -928,8 +928,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(6, subRL[5] ^ subRL[7]); /* round 5 */
tl = (subRL[10] >> 32) ^ (subRL[10] & ~subRL[8]);
- dw = tl & (subRL[8] >> 32), /* FL(kl1) */
- tr = subRL[10] ^ rol32(dw, 1);
+ dw = tl & (subRL[8] >> 32); /* FL(kl1) */
+ tr = subRL[10] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(7, subRL[6] ^ tt); /* round 6 */
@@ -937,8 +937,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(9, subRL[9]); /* FLinv(kl2) */
tl = (subRL[7] >> 32) ^ (subRL[7] & ~subRL[9]);
- dw = tl & (subRL[9] >> 32), /* FLinv(kl2) */
- tr = subRL[7] ^ rol32(dw, 1);
+ dw = tl & (subRL[9] >> 32); /* FLinv(kl2) */
+ tr = subRL[7] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(10, subRL[11] ^ tt); /* round 7 */
@@ -948,8 +948,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(14, subRL[13] ^ subRL[15]); /* round 11 */
tl = (subRL[18] >> 32) ^ (subRL[18] & ~subRL[16]);
- dw = tl & (subRL[16] >> 32), /* FL(kl3) */
- tr = subRL[18] ^ rol32(dw, 1);
+ dw = tl & (subRL[16] >> 32); /* FL(kl3) */
+ tr = subRL[18] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(15, subRL[14] ^ tt); /* round 12 */
@@ -957,8 +957,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(17, subRL[17]); /* FLinv(kl4) */
tl = (subRL[15] >> 32) ^ (subRL[15] & ~subRL[17]);
- dw = tl & (subRL[17] >> 32), /* FLinv(kl4) */
- tr = subRL[15] ^ rol32(dw, 1);
+ dw = tl & (subRL[17] >> 32); /* FLinv(kl4) */
+ tr = subRL[15] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(18, subRL[19] ^ tt); /* round 13 */
@@ -972,8 +972,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(24, subRL[24] ^ subRL[23]); /* kw3 */
} else {
tl = (subRL[26] >> 32) ^ (subRL[26] & ~subRL[24]);
- dw = tl & (subRL[24] >> 32), /* FL(kl5) */
- tr = subRL[26] ^ rol32(dw, 1);
+ dw = tl & (subRL[24] >> 32); /* FL(kl5) */
+ tr = subRL[26] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(23, subRL[22] ^ tt); /* round 18 */
@@ -981,8 +981,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(25, subRL[25]); /* FLinv(kl6) */
tl = (subRL[23] >> 32) ^ (subRL[23] & ~subRL[25]);
- dw = tl & (subRL[25] >> 32), /* FLinv(kl6) */
- tr = subRL[23] ^ rol32(dw, 1);
+ dw = tl & (subRL[25] >> 32); /* FLinv(kl6) */
+ tr = subRL[23] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(26, subRL[27] ^ tt); /* round 19 */
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index c6631813dc1..e57e20ab5e0 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -26,13 +26,13 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/cast5.h>
#include <crypto/cryptd.h>
#include <crypto/ctr.h>
#include <asm/xcr.h>
#include <asm/xsave.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
#define CAST5_PARALLEL_BLOCKS 16
@@ -203,9 +203,6 @@ static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
src -= 1;
dst -= 1;
} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
-
- if (nbytes < bsize)
- goto done;
}
/* Handle leftovers */
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 8d0dfb86a55..09f3677393e 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -28,6 +28,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/cast6.h>
#include <crypto/cryptd.h>
@@ -37,7 +38,6 @@
#include <crypto/xts.h>
#include <asm/xcr.h>
#include <asm/xsave.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
#define CAST6_PARALLEL_BLOCKS 8
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 586f41aac36..5d1e0075ac2 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -24,10 +24,6 @@
.align 16
.Lbswap_mask:
.octa 0x000102030405060708090a0b0c0d0e0f
-.Lpoly:
- .octa 0xc2000000000000000000000000000001
-.Ltwo_one:
- .octa 0x00000001000000000000000000000001
#define DATA %xmm0
#define SHASH %xmm1
@@ -96,7 +92,7 @@ __clmul_gf128mul_ble:
ret
ENDPROC(__clmul_gf128mul_ble)
-/* void clmul_ghash_mul(char *dst, const be128 *shash) */
+/* void clmul_ghash_mul(char *dst, const u128 *shash) */
ENTRY(clmul_ghash_mul)
movups (%rdi), DATA
movups (%rsi), SHASH
@@ -110,7 +106,7 @@ ENDPROC(clmul_ghash_mul)
/*
* void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
- * const be128 *shash);
+ * const u128 *shash);
*/
ENTRY(clmul_ghash_update)
cmp $16, %rdx
@@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update)
.Lupdate_just_ret:
ret
ENDPROC(clmul_ghash_update)
-
-/*
- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
- *
- * Calculate hash_key << 1 mod poly
- */
-ENTRY(clmul_ghash_setkey)
- movaps .Lbswap_mask, BSWAP
- movups (%rsi), %xmm0
- PSHUFB_XMM BSWAP %xmm0
- movaps %xmm0, %xmm1
- psllq $1, %xmm0
- psrlq $63, %xmm1
- movaps %xmm1, %xmm2
- pslldq $8, %xmm1
- psrldq $8, %xmm2
- por %xmm1, %xmm0
- # reduction
- pshufd $0b00100100, %xmm2, %xmm1
- pcmpeqd .Ltwo_one, %xmm1
- pand .Lpoly, %xmm1
- pxor %xmm1, %xmm0
- movups %xmm0, (%rdi)
- ret
-ENDPROC(clmul_ghash_setkey)
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 6759dd1135b..88bb7ba8b17 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -25,19 +25,17 @@
#define GHASH_BLOCK_SIZE 16
#define GHASH_DIGEST_SIZE 16
-void clmul_ghash_mul(char *dst, const be128 *shash);
+void clmul_ghash_mul(char *dst, const u128 *shash);
void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
- const be128 *shash);
-
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
+ const u128 *shash);
struct ghash_async_ctx {
struct cryptd_ahash *cryptd_tfm;
};
struct ghash_ctx {
- be128 shash;
+ u128 shash;
};
struct ghash_desc_ctx {
@@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm,
const u8 *key, unsigned int keylen)
{
struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+ be128 *x = (be128 *)key;
+ u64 a, b;
if (keylen != GHASH_BLOCK_SIZE) {
crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
return -EINVAL;
}
- clmul_ghash_setkey(&ctx->shash, key);
+ /* perform multiplication by 'x' in GF(2^128) */
+ a = be64_to_cpu(x->a);
+ b = be64_to_cpu(x->b);
+
+ ctx->shash.a = (b << 1) | (a >> 63);
+ ctx->shash.b = (a << 1) | (b >> 63);
+
+ if (a >> 63)
+ ctx->shash.b ^= ((u64)0xc2) << 56;
return 0;
}
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 23aabc6c20a..2fae489b152 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/ctr.h>
#include <crypto/lrw.h>
@@ -22,7 +23,6 @@
#include <asm/xcr.h>
#include <asm/xsave.h>
#include <asm/crypto/serpent-avx.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
#define SERPENT_AVX2_PARALLEL_BLOCKS 16
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 9ae83cf8d21..ff487087097 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -28,6 +28,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/serpent.h>
#include <crypto/cryptd.h>
@@ -38,7 +39,6 @@
#include <asm/xcr.h>
#include <asm/xsave.h>
#include <asm/crypto/serpent-avx.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
/* 8-way parallel cipher functions */
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 97a356ece24..8c95f863730 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -34,6 +34,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/serpent.h>
#include <crypto/cryptd.h>
@@ -42,7 +43,6 @@
#include <crypto/lrw.h>
#include <crypto/xts.h>
#include <asm/crypto/serpent-sse2.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src)
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
new file mode 100644
index 00000000000..1cd792db15e
--- /dev/null
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -0,0 +1,708 @@
+/*
+ * Implement fast SHA-1 with AVX2 instructions. (x86_64)
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * Ilya Albrekht <ilya.albrekht@intel.com>
+ * Maxim Locktyukhin <maxim.locktyukhin@intel.com>
+ * Ronen Zohar <ronen.zohar@intel.com>
+ * Chandramouli Narayanan <mouli@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * SHA-1 implementation with Intel(R) AVX2 instruction set extensions.
+ *
+ *This implementation is based on the previous SSSE3 release:
+ *Visit http://software.intel.com/en-us/articles/
+ *and refer to improving-the-performance-of-the-secure-hash-algorithm-1/
+ *
+ *Updates 20-byte SHA-1 record in 'hash' for even number of
+ *'num_blocks' consecutive 64-byte blocks
+ *
+ *extern "C" void sha1_transform_avx2(
+ * int *hash, const char* input, size_t num_blocks );
+ */
+
+#include <linux/linkage.h>
+
+#define CTX %rdi /* arg1 */
+#define BUF %rsi /* arg2 */
+#define CNT %rdx /* arg3 */
+
+#define REG_A %ecx
+#define REG_B %esi
+#define REG_C %edi
+#define REG_D %eax
+#define REG_E %edx
+#define REG_TB %ebx
+#define REG_TA %r12d
+#define REG_RA %rcx
+#define REG_RB %rsi
+#define REG_RC %rdi
+#define REG_RD %rax
+#define REG_RE %rdx
+#define REG_RTA %r12
+#define REG_RTB %rbx
+#define REG_T1 %ebp
+#define xmm_mov vmovups
+#define avx2_zeroupper vzeroupper
+#define RND_F1 1
+#define RND_F2 2
+#define RND_F3 3
+
+.macro REGALLOC
+ .set A, REG_A
+ .set B, REG_B
+ .set C, REG_C
+ .set D, REG_D
+ .set E, REG_E
+ .set TB, REG_TB
+ .set TA, REG_TA
+
+ .set RA, REG_RA
+ .set RB, REG_RB
+ .set RC, REG_RC
+ .set RD, REG_RD
+ .set RE, REG_RE
+
+ .set RTA, REG_RTA
+ .set RTB, REG_RTB
+
+ .set T1, REG_T1
+.endm
+
+#define K_BASE %r8
+#define HASH_PTR %r9
+#define BUFFER_PTR %r10
+#define BUFFER_PTR2 %r13
+#define BUFFER_END %r11
+
+#define PRECALC_BUF %r14
+#define WK_BUF %r15
+
+#define W_TMP %xmm0
+#define WY_TMP %ymm0
+#define WY_TMP2 %ymm9
+
+# AVX2 variables
+#define WY0 %ymm3
+#define WY4 %ymm5
+#define WY08 %ymm7
+#define WY12 %ymm8
+#define WY16 %ymm12
+#define WY20 %ymm13
+#define WY24 %ymm14
+#define WY28 %ymm15
+
+#define YMM_SHUFB_BSWAP %ymm10
+
+/*
+ * Keep 2 iterations precalculated at a time:
+ * - 80 DWORDs per iteration * 2
+ */
+#define W_SIZE (80*2*2 +16)
+
+#define WK(t) ((((t) % 80) / 4)*32 + ( (t) % 4)*4 + ((t)/80)*16 )(WK_BUF)
+#define PRECALC_WK(t) ((t)*2*2)(PRECALC_BUF)
+
+
+.macro UPDATE_HASH hash, val
+ add \hash, \val
+ mov \val, \hash
+.endm
+
+.macro PRECALC_RESET_WY
+ .set WY_00, WY0
+ .set WY_04, WY4
+ .set WY_08, WY08
+ .set WY_12, WY12
+ .set WY_16, WY16
+ .set WY_20, WY20
+ .set WY_24, WY24
+ .set WY_28, WY28
+ .set WY_32, WY_00
+.endm
+
+.macro PRECALC_ROTATE_WY
+ /* Rotate macros */
+ .set WY_32, WY_28
+ .set WY_28, WY_24
+ .set WY_24, WY_20
+ .set WY_20, WY_16
+ .set WY_16, WY_12
+ .set WY_12, WY_08
+ .set WY_08, WY_04
+ .set WY_04, WY_00
+ .set WY_00, WY_32
+
+ /* Define register aliases */
+ .set WY, WY_00
+ .set WY_minus_04, WY_04
+ .set WY_minus_08, WY_08
+ .set WY_minus_12, WY_12
+ .set WY_minus_16, WY_16
+ .set WY_minus_20, WY_20
+ .set WY_minus_24, WY_24
+ .set WY_minus_28, WY_28
+ .set WY_minus_32, WY
+.endm
+
+.macro PRECALC_00_15
+ .if (i == 0) # Initialize and rotate registers
+ PRECALC_RESET_WY
+ PRECALC_ROTATE_WY
+ .endif
+
+ /* message scheduling pre-compute for rounds 0-15 */
+ .if ((i & 7) == 0)
+ /*
+ * blended AVX2 and ALU instruction scheduling
+ * 1 vector iteration per 8 rounds
+ */
+ vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+ .elseif ((i & 7) == 1)
+ vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+ WY_TMP, WY_TMP
+ .elseif ((i & 7) == 2)
+ vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
+ .elseif ((i & 7) == 4)
+ vpaddd K_XMM(K_BASE), WY, WY_TMP
+ .elseif ((i & 7) == 7)
+ vmovdqu WY_TMP, PRECALC_WK(i&~7)
+
+ PRECALC_ROTATE_WY
+ .endif
+.endm
+
+.macro PRECALC_16_31
+ /*
+ * message scheduling pre-compute for rounds 16-31
+ * calculating last 32 w[i] values in 8 XMM registers
+ * pre-calculate K+w[i] values and store to mem
+ * for later load by ALU add instruction
+ *
+ * "brute force" vectorization for rounds 16-31 only
+ * due to w[i]->w[i-3] dependency
+ */
+ .if ((i & 7) == 0)
+ /*
+ * blended AVX2 and ALU instruction scheduling
+ * 1 vector iteration per 8 rounds
+ */
+ /* w[i-14] */
+ vpalignr $8, WY_minus_16, WY_minus_12, WY
+ vpsrldq $4, WY_minus_04, WY_TMP /* w[i-3] */
+ .elseif ((i & 7) == 1)
+ vpxor WY_minus_08, WY, WY
+ vpxor WY_minus_16, WY_TMP, WY_TMP
+ .elseif ((i & 7) == 2)
+ vpxor WY_TMP, WY, WY
+ vpslldq $12, WY, WY_TMP2
+ .elseif ((i & 7) == 3)
+ vpslld $1, WY, WY_TMP
+ vpsrld $31, WY, WY
+ .elseif ((i & 7) == 4)
+ vpor WY, WY_TMP, WY_TMP
+ vpslld $2, WY_TMP2, WY
+ .elseif ((i & 7) == 5)
+ vpsrld $30, WY_TMP2, WY_TMP2
+ vpxor WY, WY_TMP, WY_TMP
+ .elseif ((i & 7) == 7)
+ vpxor WY_TMP2, WY_TMP, WY
+ vpaddd K_XMM(K_BASE), WY, WY_TMP
+ vmovdqu WY_TMP, PRECALC_WK(i&~7)
+
+ PRECALC_ROTATE_WY
+ .endif
+.endm
+
+.macro PRECALC_32_79
+ /*
+ * in SHA-1 specification:
+ * w[i] = (w[i-3] ^ w[i-8] ^ w[i-14] ^ w[i-16]) rol 1
+ * instead we do equal:
+ * w[i] = (w[i-6] ^ w[i-16] ^ w[i-28] ^ w[i-32]) rol 2
+ * allows more efficient vectorization
+ * since w[i]=>w[i-3] dependency is broken
+ */
+
+ .if ((i & 7) == 0)
+ /*
+ * blended AVX2 and ALU instruction scheduling
+ * 1 vector iteration per 8 rounds
+ */
+ vpalignr $8, WY_minus_08, WY_minus_04, WY_TMP
+ .elseif ((i & 7) == 1)
+ /* W is W_minus_32 before xor */
+ vpxor WY_minus_28, WY, WY
+ .elseif ((i & 7) == 2)
+ vpxor WY_minus_16, WY_TMP, WY_TMP
+ .elseif ((i & 7) == 3)
+ vpxor WY_TMP, WY, WY
+ .elseif ((i & 7) == 4)
+ vpslld $2, WY, WY_TMP
+ .elseif ((i & 7) == 5)
+ vpsrld $30, WY, WY
+ vpor WY, WY_TMP, WY
+ .elseif ((i & 7) == 7)
+ vpaddd K_XMM(K_BASE), WY, WY_TMP
+ vmovdqu WY_TMP, PRECALC_WK(i&~7)
+
+ PRECALC_ROTATE_WY
+ .endif
+.endm
+
+.macro PRECALC r, s
+ .set i, \r
+
+ .if (i < 40)
+ .set K_XMM, 32*0
+ .elseif (i < 80)
+ .set K_XMM, 32*1
+ .elseif (i < 120)
+ .set K_XMM, 32*2
+ .else
+ .set K_XMM, 32*3
+ .endif
+
+ .if (i<32)
+ PRECALC_00_15 \s
+ .elseif (i<64)
+ PRECALC_16_31 \s
+ .elseif (i < 160)
+ PRECALC_32_79 \s
+ .endif
+.endm
+
+.macro ROTATE_STATE
+ .set T_REG, E
+ .set E, D
+ .set D, C
+ .set C, B
+ .set B, TB
+ .set TB, A
+ .set A, T_REG
+
+ .set T_REG, RE
+ .set RE, RD
+ .set RD, RC
+ .set RC, RB
+ .set RB, RTB
+ .set RTB, RA
+ .set RA, T_REG
+.endm
+
+/* Macro relies on saved ROUND_Fx */
+
+.macro RND_FUN f, r
+ .if (\f == RND_F1)
+ ROUND_F1 \r
+ .elseif (\f == RND_F2)
+ ROUND_F2 \r
+ .elseif (\f == RND_F3)
+ ROUND_F3 \r
+ .endif
+.endm
+
+.macro RR r
+ .set round_id, (\r % 80)
+
+ .if (round_id == 0) /* Precalculate F for first round */
+ .set ROUND_FUNC, RND_F1
+ mov B, TB
+
+ rorx $(32-30), B, B /* b>>>2 */
+ andn D, TB, T1
+ and C, TB
+ xor T1, TB
+ .endif
+
+ RND_FUN ROUND_FUNC, \r
+ ROTATE_STATE
+
+ .if (round_id == 18)
+ .set ROUND_FUNC, RND_F2
+ .elseif (round_id == 38)
+ .set ROUND_FUNC, RND_F3
+ .elseif (round_id == 58)
+ .set ROUND_FUNC, RND_F2
+ .endif
+
+ .set round_id, ( (\r+1) % 80)
+
+ RND_FUN ROUND_FUNC, (\r+1)
+ ROTATE_STATE
+.endm
+
+.macro ROUND_F1 r
+ add WK(\r), E
+
+ andn C, A, T1 /* ~b&d */
+ lea (RE,RTB), E /* Add F from the previous round */
+
+ rorx $(32-5), A, TA /* T2 = A >>> 5 */
+ rorx $(32-30),A, TB /* b>>>2 for next round */
+
+ PRECALC (\r) /* msg scheduling for next 2 blocks */
+
+ /*
+ * Calculate F for the next round
+ * (b & c) ^ andn[b, d]
+ */
+ and B, A /* b&c */
+ xor T1, A /* F1 = (b&c) ^ (~b&d) */
+
+ lea (RE,RTA), E /* E += A >>> 5 */
+.endm
+
+.macro ROUND_F2 r
+ add WK(\r), E
+ lea (RE,RTB), E /* Add F from the previous round */
+
+ /* Calculate F for the next round */
+ rorx $(32-5), A, TA /* T2 = A >>> 5 */
+ .if ((round_id) < 79)
+ rorx $(32-30), A, TB /* b>>>2 for next round */
+ .endif
+ PRECALC (\r) /* msg scheduling for next 2 blocks */
+
+ .if ((round_id) < 79)
+ xor B, A
+ .endif
+
+ add TA, E /* E += A >>> 5 */
+
+ .if ((round_id) < 79)
+ xor C, A
+ .endif
+.endm
+
+.macro ROUND_F3 r
+ add WK(\r), E
+ PRECALC (\r) /* msg scheduling for next 2 blocks */
+
+ lea (RE,RTB), E /* Add F from the previous round */
+
+ mov B, T1
+ or A, T1
+
+ rorx $(32-5), A, TA /* T2 = A >>> 5 */
+ rorx $(32-30), A, TB /* b>>>2 for next round */
+
+ /* Calculate F for the next round
+ * (b and c) or (d and (b or c))
+ */
+ and C, T1
+ and B, A
+ or T1, A
+
+ add TA, E /* E += A >>> 5 */
+
+.endm
+
+/*
+ * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
+ */
+.macro SHA1_PIPELINED_MAIN_BODY
+
+ REGALLOC
+
+ mov (HASH_PTR), A
+ mov 4(HASH_PTR), B
+ mov 8(HASH_PTR), C
+ mov 12(HASH_PTR), D
+ mov 16(HASH_PTR), E
+
+ mov %rsp, PRECALC_BUF
+ lea (2*4*80+32)(%rsp), WK_BUF
+
+ # Precalc WK for first 2 blocks
+ PRECALC_OFFSET = 0
+ .set i, 0
+ .rept 160
+ PRECALC i
+ .set i, i + 1
+ .endr
+ PRECALC_OFFSET = 128
+ xchg WK_BUF, PRECALC_BUF
+
+ .align 32
+_loop:
+ /*
+ * code loops through more than one block
+ * we use K_BASE value as a signal of a last block,
+ * it is set below by: cmovae BUFFER_PTR, K_BASE
+ */
+ cmp K_BASE, BUFFER_PTR
+ jne _begin
+ .align 32
+ jmp _end
+ .align 32
+_begin:
+
+ /*
+ * Do first block
+ * rounds: 0,2,4,6,8
+ */
+ .set j, 0
+ .rept 5
+ RR j
+ .set j, j+2
+ .endr
+
+ jmp _loop0
+_loop0:
+
+ /*
+ * rounds:
+ * 10,12,14,16,18
+ * 20,22,24,26,28
+ * 30,32,34,36,38
+ * 40,42,44,46,48
+ * 50,52,54,56,58
+ */
+ .rept 25
+ RR j
+ .set j, j+2
+ .endr
+
+ add $(2*64), BUFFER_PTR /* move to next odd-64-byte block */
+ cmp BUFFER_END, BUFFER_PTR /* is current block the last one? */
+ cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */
+
+ /*
+ * rounds
+ * 60,62,64,66,68
+ * 70,72,74,76,78
+ */
+ .rept 10
+ RR j
+ .set j, j+2
+ .endr
+
+ UPDATE_HASH (HASH_PTR), A
+ UPDATE_HASH 4(HASH_PTR), TB
+ UPDATE_HASH 8(HASH_PTR), C
+ UPDATE_HASH 12(HASH_PTR), D
+ UPDATE_HASH 16(HASH_PTR), E
+
+ cmp K_BASE, BUFFER_PTR /* is current block the last one? */
+ je _loop
+
+ mov TB, B
+
+ /* Process second block */
+ /*
+ * rounds
+ * 0+80, 2+80, 4+80, 6+80, 8+80
+ * 10+80,12+80,14+80,16+80,18+80
+ */
+
+ .set j, 0
+ .rept 10
+ RR j+80
+ .set j, j+2
+ .endr
+
+ jmp _loop1
+_loop1:
+ /*
+ * rounds
+ * 20+80,22+80,24+80,26+80,28+80
+ * 30+80,32+80,34+80,36+80,38+80
+ */
+ .rept 10
+ RR j+80
+ .set j, j+2
+ .endr
+
+ jmp _loop2
+_loop2:
+
+ /*
+ * rounds
+ * 40+80,42+80,44+80,46+80,48+80
+ * 50+80,52+80,54+80,56+80,58+80
+ */
+ .rept 10
+ RR j+80
+ .set j, j+2
+ .endr
+
+ add $(2*64), BUFFER_PTR2 /* move to next even-64-byte block */
+
+ cmp BUFFER_END, BUFFER_PTR2 /* is current block the last one */
+ cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */
+
+ jmp _loop3
+_loop3:
+
+ /*
+ * rounds
+ * 60+80,62+80,64+80,66+80,68+80
+ * 70+80,72+80,74+80,76+80,78+80
+ */
+ .rept 10
+ RR j+80
+ .set j, j+2
+ .endr
+
+ UPDATE_HASH (HASH_PTR), A
+ UPDATE_HASH 4(HASH_PTR), TB
+ UPDATE_HASH 8(HASH_PTR), C
+ UPDATE_HASH 12(HASH_PTR), D
+ UPDATE_HASH 16(HASH_PTR), E
+
+ /* Reset state for AVX2 reg permutation */
+ mov A, TA
+ mov TB, A
+ mov C, TB
+ mov E, C
+ mov D, B
+ mov TA, D
+
+ REGALLOC
+
+ xchg WK_BUF, PRECALC_BUF
+
+ jmp _loop
+
+ .align 32
+ _end:
+
+.endm
+/*
+ * macro implements SHA-1 function's body for several 64-byte blocks
+ * param: function's name
+ */
+.macro SHA1_VECTOR_ASM name
+ ENTRY(\name)
+
+ push %rbx
+ push %rbp
+ push %r12
+ push %r13
+ push %r14
+ push %r15
+
+ RESERVE_STACK = (W_SIZE*4 + 8+24)
+
+ /* Align stack */
+ mov %rsp, %rbx
+ and $~(0x20-1), %rsp
+ push %rbx
+ sub $RESERVE_STACK, %rsp
+
+ avx2_zeroupper
+
+ lea K_XMM_AR(%rip), K_BASE
+
+ mov CTX, HASH_PTR
+ mov BUF, BUFFER_PTR
+ lea 64(BUF), BUFFER_PTR2
+
+ shl $6, CNT /* mul by 64 */
+ add BUF, CNT
+ add $64, CNT
+ mov CNT, BUFFER_END
+
+ cmp BUFFER_END, BUFFER_PTR2
+ cmovae K_BASE, BUFFER_PTR2
+
+ xmm_mov BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
+
+ SHA1_PIPELINED_MAIN_BODY
+
+ avx2_zeroupper
+
+ add $RESERVE_STACK, %rsp
+ pop %rsp
+
+ pop %r15
+ pop %r14
+ pop %r13
+ pop %r12
+ pop %rbp
+ pop %rbx
+
+ ret
+
+ ENDPROC(\name)
+.endm
+
+.section .rodata
+
+#define K1 0x5a827999
+#define K2 0x6ed9eba1
+#define K3 0x8f1bbcdc
+#define K4 0xca62c1d6
+
+.align 128
+K_XMM_AR:
+ .long K1, K1, K1, K1
+ .long K1, K1, K1, K1
+ .long K2, K2, K2, K2
+ .long K2, K2, K2, K2
+ .long K3, K3, K3, K3
+ .long K3, K3, K3, K3
+ .long K4, K4, K4, K4
+ .long K4, K4, K4, K4
+
+BSWAP_SHUFB_CTL:
+ .long 0x00010203
+ .long 0x04050607
+ .long 0x08090a0b
+ .long 0x0c0d0e0f
+ .long 0x00010203
+ .long 0x04050607
+ .long 0x08090a0b
+ .long 0x0c0d0e0f
+.text
+
+SHA1_VECTOR_ASM sha1_transform_avx2
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 4a11a9d7245..74d16ef707c 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -10,6 +10,7 @@
* Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
* Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
* Copyright (c) Mathias Krause <minipli@googlemail.com>
+ * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
@@ -39,6 +40,12 @@ asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
unsigned int rounds);
#endif
+#ifdef CONFIG_AS_AVX2
+#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */
+
+asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
+ unsigned int rounds);
+#endif
static asmlinkage void (*sha1_transform_asm)(u32 *, const char *, unsigned int);
@@ -165,6 +172,18 @@ static int sha1_ssse3_import(struct shash_desc *desc, const void *in)
return 0;
}
+#ifdef CONFIG_AS_AVX2
+static void sha1_apply_transform_avx2(u32 *digest, const char *data,
+ unsigned int rounds)
+{
+ /* Select the optimal transform based on data block size */
+ if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE)
+ sha1_transform_avx2(digest, data, rounds);
+ else
+ sha1_transform_avx(digest, data, rounds);
+}
+#endif
+
static struct shash_alg alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_ssse3_init,
@@ -201,27 +220,49 @@ static bool __init avx_usable(void)
return true;
}
+
+#ifdef CONFIG_AS_AVX2
+static bool __init avx2_usable(void)
+{
+ if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) &&
+ boot_cpu_has(X86_FEATURE_BMI2))
+ return true;
+
+ return false;
+}
+#endif
#endif
static int __init sha1_ssse3_mod_init(void)
{
+ char *algo_name;
+
/* test for SSSE3 first */
- if (cpu_has_ssse3)
+ if (cpu_has_ssse3) {
sha1_transform_asm = sha1_transform_ssse3;
+ algo_name = "SSSE3";
+ }
#ifdef CONFIG_AS_AVX
/* allow AVX to override SSSE3, it's a little faster */
- if (avx_usable())
+ if (avx_usable()) {
sha1_transform_asm = sha1_transform_avx;
+ algo_name = "AVX";
+#ifdef CONFIG_AS_AVX2
+ /* allow AVX2 to override AVX, it's a little faster */
+ if (avx2_usable()) {
+ sha1_transform_asm = sha1_apply_transform_avx2;
+ algo_name = "AVX2";
+ }
+#endif
+ }
#endif
if (sha1_transform_asm) {
- pr_info("Using %s optimized SHA-1 implementation\n",
- sha1_transform_asm == sha1_transform_ssse3 ? "SSSE3"
- : "AVX");
+ pr_info("Using %s optimized SHA-1 implementation\n", algo_name);
return crypto_register_shash(&alg);
}
- pr_info("Neither AVX nor SSSE3 is available/usable.\n");
+ pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n");
return -ENODEV;
}
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 50226c4b86e..f248546da1c 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -281,7 +281,7 @@ static int __init sha256_ssse3_mod_init(void)
/* allow AVX to override SSSE3, it's a little faster */
if (avx_usable()) {
#ifdef CONFIG_AS_AVX2
- if (boot_cpu_has(X86_FEATURE_AVX2))
+ if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2))
sha256_transform_asm = sha256_transform_rorx;
else
#endif
@@ -319,4 +319,4 @@ MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS("sha224");
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index f30cd10293f..8626b03e83b 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -141,7 +141,7 @@ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out)
/* save number of bits */
bits[1] = cpu_to_be64(sctx->count[0] << 3);
- bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61;
+ bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
/* Pad out to 112 mod 128 and append length */
index = sctx->count[0] & 0x7f;
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index a62ba541884..4e3c665be12 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -28,6 +28,7 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <crypto/twofish.h>
#include <crypto/cryptd.h>
@@ -39,7 +40,6 @@
#include <asm/xcr.h>
#include <asm/xsave.h>
#include <asm/crypto/twofish.h>
-#include <asm/crypto/ablk_helper.h>
#include <asm/crypto/glue_helper.h>
#include <crypto/scatterwalk.h>
#include <linux/workqueue.h>
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index bae3aba95b1..d21ff89207c 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -25,6 +25,7 @@
#include <linux/personality.h>
#include <linux/init.h>
#include <linux/jiffies.h>
+#include <linux/perf_event.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
@@ -33,14 +34,18 @@
#include <asm/ia32.h>
#undef WARN_OLD
-#undef CORE_DUMP /* definitely broken */
static int load_aout_binary(struct linux_binprm *);
static int load_aout_library(struct file *);
-#ifdef CORE_DUMP
-static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
- unsigned long limit);
+#ifdef CONFIG_COREDUMP
+static int aout_core_dump(struct coredump_params *);
+
+static unsigned long get_dr(int n)
+{
+ struct perf_event *bp = current->thread.ptrace_bps[n];
+ return bp ? bp->hw.info.address : 0;
+}
/*
* fill in the user structure for a core dump..
@@ -48,6 +53,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
{
u32 fs, gs;
+ memset(dump, 0, sizeof(*dump));
/* changed the size calculations - should hopefully work better. lbt */
dump->magic = CMAGIC;
@@ -57,15 +63,12 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
dump->u_dsize = ((unsigned long)
(current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
dump->u_dsize -= dump->u_tsize;
- dump->u_ssize = 0;
- dump->u_debugreg[0] = current->thread.debugreg0;
- dump->u_debugreg[1] = current->thread.debugreg1;
- dump->u_debugreg[2] = current->thread.debugreg2;
- dump->u_debugreg[3] = current->thread.debugreg3;
- dump->u_debugreg[4] = 0;
- dump->u_debugreg[5] = 0;
+ dump->u_debugreg[0] = get_dr(0);
+ dump->u_debugreg[1] = get_dr(1);
+ dump->u_debugreg[2] = get_dr(2);
+ dump->u_debugreg[3] = get_dr(3);
dump->u_debugreg[6] = current->thread.debugreg6;
- dump->u_debugreg[7] = current->thread.debugreg7;
+ dump->u_debugreg[7] = current->thread.ptrace_dr7;
if (dump->start_stack < 0xc0000000) {
unsigned long tmp;
@@ -74,24 +77,24 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
dump->u_ssize = tmp >> PAGE_SHIFT;
}
- dump->regs.bx = regs->bx;
- dump->regs.cx = regs->cx;
- dump->regs.dx = regs->dx;
- dump->regs.si = regs->si;
- dump->regs.di = regs->di;
- dump->regs.bp = regs->bp;
- dump->regs.ax = regs->ax;
+ dump->regs.ebx = regs->bx;
+ dump->regs.ecx = regs->cx;
+ dump->regs.edx = regs->dx;
+ dump->regs.esi = regs->si;
+ dump->regs.edi = regs->di;
+ dump->regs.ebp = regs->bp;
+ dump->regs.eax = regs->ax;
dump->regs.ds = current->thread.ds;
dump->regs.es = current->thread.es;
savesegment(fs, fs);
dump->regs.fs = fs;
savesegment(gs, gs);
dump->regs.gs = gs;
- dump->regs.orig_ax = regs->orig_ax;
- dump->regs.ip = regs->ip;
+ dump->regs.orig_eax = regs->orig_ax;
+ dump->regs.eip = regs->ip;
dump->regs.cs = regs->cs;
- dump->regs.flags = regs->flags;
- dump->regs.sp = regs->sp;
+ dump->regs.eflags = regs->flags;
+ dump->regs.esp = regs->sp;
dump->regs.ss = regs->ss;
#if 1 /* FIXME */
@@ -107,7 +110,7 @@ static struct linux_binfmt aout_format = {
.module = THIS_MODULE,
.load_binary = load_aout_binary,
.load_shlib = load_aout_library,
-#ifdef CORE_DUMP
+#ifdef CONFIG_COREDUMP
.core_dump = aout_core_dump,
#endif
.min_coredump = PAGE_SIZE
@@ -122,7 +125,7 @@ static void set_brk(unsigned long start, unsigned long end)
vm_brk(start, end - start);
}
-#ifdef CORE_DUMP
+#ifdef CONFIG_COREDUMP
/*
* These are the only things you should do on a core-file: use only these
* macros to write out all the necessary info.
@@ -130,15 +133,7 @@ static void set_brk(unsigned long start, unsigned long end)
#include <linux/coredump.h>
-#define DUMP_WRITE(addr, nr) \
- if (!dump_write(file, (void *)(addr), (nr))) \
- goto end_coredump;
-
-#define DUMP_SEEK(offset) \
- if (!dump_seek(file, offset)) \
- goto end_coredump;
-
-#define START_DATA() (u.u_tsize << PAGE_SHIFT)
+#define START_DATA(u) (u.u_tsize << PAGE_SHIFT)
#define START_STACK(u) (u.start_stack)
/*
@@ -151,8 +146,7 @@ static void set_brk(unsigned long start, unsigned long end)
* dumping of the process results in another error..
*/
-static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
- unsigned long limit)
+static int aout_core_dump(struct coredump_params *cprm)
{
mm_segment_t fs;
int has_dumped = 0;
@@ -164,19 +158,19 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
has_dumped = 1;
strncpy(dump.u_comm, current->comm, sizeof(current->comm));
dump.u_ar0 = offsetof(struct user32, regs);
- dump.signal = signr;
- dump_thread32(regs, &dump);
+ dump.signal = cprm->siginfo->si_signo;
+ dump_thread32(cprm->regs, &dump);
/*
* If the size of the dump file exceeds the rlimit, then see
* what would happen if we wrote the stack, but not the data
* area.
*/
- if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit)
+ if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > cprm->limit)
dump.u_dsize = 0;
/* Make sure we have enough room to write the stack and data areas. */
- if ((dump.u_ssize + 1) * PAGE_SIZE > limit)
+ if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit)
dump.u_ssize = 0;
/* make sure we actually have a data and stack area to dump */
@@ -190,22 +184,26 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
set_fs(KERNEL_DS);
/* struct user */
- DUMP_WRITE(&dump, sizeof(dump));
+ if (!dump_emit(cprm, &dump, sizeof(dump)))
+ goto end_coredump;
/* Now dump all of the user data. Include malloced stuff as well */
- DUMP_SEEK(PAGE_SIZE - sizeof(dump));
+ if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump)))
+ goto end_coredump;
/* now we start writing out the user space info */
set_fs(USER_DS);
/* Dump the data area */
if (dump.u_dsize != 0) {
dump_start = START_DATA(dump);
dump_size = dump.u_dsize << PAGE_SHIFT;
- DUMP_WRITE(dump_start, dump_size);
+ if (!dump_emit(cprm, (void *)dump_start, dump_size))
+ goto end_coredump;
}
/* Now prepare to dump the stack area */
if (dump.u_ssize != 0) {
dump_start = START_STACK(dump);
dump_size = dump.u_ssize << PAGE_SHIFT;
- DUMP_WRITE(dump_start, dump_size);
+ if (!dump_emit(cprm, (void *)dump_start, dump_size))
+ goto end_coredump;
}
end_coredump:
set_fs(fs);
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c