OpenCloudOS-Kernel/drivers/video/uvesafb.c

2063 lines
51 KiB
C
Raw Normal View History

uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
/*
* A framebuffer driver for VBE 2.0+ compliant video cards
*
* (c) 2007 Michal Januszewski <spock@gentoo.org>
* Loosely based upon the vesafb driver.
*
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/skbuff.h>
#include <linux/timer.h>
#include <linux/completion.h>
#include <linux/connector.h>
#include <linux/random.h>
#include <linux/platform_device.h>
#include <linux/limits.h>
#include <linux/fb.h>
#include <linux/io.h>
#include <linux/mutex.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
#include <video/edid.h>
#include <video/uvesafb.h>
#ifdef CONFIG_X86
#include <video/vga.h>
#endif
#ifdef CONFIG_MTRR
#include <asm/mtrr.h>
#endif
#include "edid.h"
static struct cb_id uvesafb_cn_id = {
.idx = CN_IDX_V86D,
.val = CN_VAL_V86D_UVESAFB
};
static char v86d_path[PATH_MAX] = "/sbin/v86d";
static char v86d_started; /* has v86d been started by uvesafb? */
static struct fb_fix_screeninfo uvesafb_fix __devinitdata = {
.id = "VESA VGA",
.type = FB_TYPE_PACKED_PIXELS,
.accel = FB_ACCEL_NONE,
.visual = FB_VISUAL_TRUECOLOR,
};
static int mtrr __devinitdata = 3; /* enable mtrr by default */
static bool blank = 1; /* enable blanking by default */
drivers/video/uvesafb.c: fix section mismatch warning in param_set_scroll() Fix following warnings: WARNING: drivers/video/built-in.o(.text+0x7c64a): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/video/built-in.o(.text+0x7c65d): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/video/built-in.o(.text+0x7c679): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/video/built-in.o(.text+0x7c699): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/video/built-in.o(.text+0x7c69f): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/built-in.o(.text+0xa3676): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/built-in.o(.text+0xa3689): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/built-in.o(.text+0xa36a5): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/built-in.o(.text+0xa36c5): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: drivers/built-in.o(.text+0xa36cb): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: vmlinux.o(.text+0x4a079a): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: vmlinux.o(.text+0x4a07ad): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: vmlinux.o(.text+0x4a07c9): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: vmlinux.o(.text+0x4a07e9): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan WARNING: vmlinux.o(.text+0x4a07ef): Section mismatch in reference from the function param_set_scroll() to the variable .devinit.data:ypan Remove __devinitdata annotation from the variable ypan. Signed-off-by: Sergio Luis <sergio@larces.uece.br> Cc: Michal Januszewski <spock@gentoo.org> Cc: "Antonino A. Daplas" <adaplas@pol.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-24 07:23:53 +08:00
static int ypan = 1; /* 0: scroll, 1: ypan, 2: ywrap */
static bool pmi_setpal __devinitdata = true; /* use PMI for palette changes */
static bool nocrtc __devinitdata; /* ignore CRTC settings */
static bool noedid __devinitdata; /* don't try DDC transfers */
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
static int vram_remap __devinitdata; /* set amt. of memory to be used */
static int vram_total __devinitdata; /* set total amount of memory */
static u16 maxclk __devinitdata; /* maximum pixel clock */
static u16 maxvf __devinitdata; /* maximum vertical frequency */
static u16 maxhf __devinitdata; /* maximum horizontal frequency */
static u16 vbemode __devinitdata; /* force use of a specific VBE mode */
static char *mode_option __devinitdata;
static u8 dac_width = 6;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
static struct uvesafb_ktask *uvfb_tasks[UVESAFB_TASKS_MAX];
static DEFINE_MUTEX(uvfb_lock);
/*
* A handler for replies from userspace.
*
* Make sure each message passes consistency checks and if it does,
* find the kernel part of the task struct, copy the registers and
* the buffer contents and then complete the task.
*/
static void uvesafb_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
{
struct uvesafb_task *utask;
struct uvesafb_ktask *task;
if (!cap_raised(current_cap(), CAP_SYS_ADMIN))
return;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (msg->seq >= UVESAFB_TASKS_MAX)
return;
mutex_lock(&uvfb_lock);
task = uvfb_tasks[msg->seq];
if (!task || msg->ack != task->ack) {
mutex_unlock(&uvfb_lock);
return;
}
utask = (struct uvesafb_task *)msg->data;
/* Sanity checks for the buffer length. */
if (task->t.buf_len < utask->buf_len ||
utask->buf_len > msg->len - sizeof(*utask)) {
mutex_unlock(&uvfb_lock);
return;
}
uvfb_tasks[msg->seq] = NULL;
mutex_unlock(&uvfb_lock);
memcpy(&task->t, utask, sizeof(*utask));
if (task->t.buf_len && task->buf)
memcpy(task->buf, utask + 1, task->t.buf_len);
complete(task->done);
return;
}
static int uvesafb_helper_start(void)
{
char *envp[] = {
"HOME=/",
"PATH=/sbin:/bin",
NULL,
};
char *argv[] = {
v86d_path,
NULL,
};
return call_usermodehelper(v86d_path, argv, envp, 1);
}
/*
* Execute a uvesafb task.
*
* Returns 0 if the task is executed successfully.
*
* A message sent to the userspace consists of the uvesafb_task
* struct and (optionally) a buffer. The uvesafb_task struct is
* a simplified version of uvesafb_ktask (its kernel counterpart)
* containing only the register values, flags and the length of
* the buffer.
*
* Each message is assigned a sequence number (increased linearly)
* and a random ack number. The sequence number is used as a key
* for the uvfb_tasks array which holds pointers to uvesafb_ktask
* structs for all requests.
*/
static int uvesafb_exec(struct uvesafb_ktask *task)
{
static int seq;
struct cn_msg *m;
int err;
int len = sizeof(task->t) + task->t.buf_len;
/*
* Check whether the message isn't longer than the maximum
* allowed by connector.
*/
if (sizeof(*m) + len > CONNECTOR_MAX_MSG_SIZE) {
printk(KERN_WARNING "uvesafb: message too long (%d), "
"can't execute task\n", (int)(sizeof(*m) + len));
return -E2BIG;
}
m = kzalloc(sizeof(*m) + len, GFP_KERNEL);
if (!m)
return -ENOMEM;
init_completion(task->done);
memcpy(&m->id, &uvesafb_cn_id, sizeof(m->id));
m->seq = seq;
m->len = len;
m->ack = random32();
/* uvesafb_task structure */
memcpy(m + 1, &task->t, sizeof(task->t));
/* Buffer */
memcpy((u8 *)(m + 1) + sizeof(task->t), task->buf, task->t.buf_len);
/*
* Save the message ack number so that we can find the kernel
* part of this task when a reply is received from userspace.
*/
task->ack = m->ack;
mutex_lock(&uvfb_lock);
/* If all slots are taken -- bail out. */
if (uvfb_tasks[seq]) {
mutex_unlock(&uvfb_lock);
err = -EBUSY;
goto out;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
/* Save a pointer to the kernel part of the task struct. */
uvfb_tasks[seq] = task;
mutex_unlock(&uvfb_lock);
err = cn_netlink_send(m, 0, GFP_KERNEL);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (err == -ESRCH) {
/*
* Try to start the userspace helper if sending
* the request failed the first time.
*/
err = uvesafb_helper_start();
if (err) {
printk(KERN_ERR "uvesafb: failed to execute %s\n",
v86d_path);
printk(KERN_ERR "uvesafb: make sure that the v86d "
"helper is installed and executable\n");
} else {
v86d_started = 1;
err = cn_netlink_send(m, 0, gfp_any());
netlink: change return-value logic of netlink_broadcast() Currently, netlink_broadcast() reports errors to the caller if no messages at all were delivered: 1) If, at least, one message has been delivered correctly, returns 0. 2) Otherwise, if no messages at all were delivered due to skb_clone() failure, return -ENOBUFS. 3) Otherwise, if there are no listeners, return -ESRCH. With this patch, the caller knows if the delivery of any of the messages to the listeners have failed: 1) If it fails to deliver any message (for whatever reason), return -ENOBUFS. 2) Otherwise, if all messages were delivered OK, returns 0. 3) Otherwise, if no listeners, return -ESRCH. In the current ctnetlink code and in Netfilter in general, we can add reliable logging and connection tracking event delivery by dropping the packets whose events were not successfully delivered over Netlink. Of course, this option would be settable via /proc as this approach reduces performance (in terms of filtered connections per seconds by a stateful firewall) but providing reliable logging and event delivery (for conntrackd) in return. This patch also changes some clients of netlink_broadcast() that may report ENOBUFS errors via printk. This error handling is not of any help. Instead, the userspace daemons that are listening to those netlink messages should resync themselves with the kernel-side if they hit ENOBUFS. BTW, netlink_broadcast() clients include those that call cn_netlink_send(), nlmsg_multicast() and genlmsg_multicast() since they internally call netlink_broadcast() and return its error value. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-06 15:56:36 +08:00
if (err == -ENOBUFS)
err = 0;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
netlink: change return-value logic of netlink_broadcast() Currently, netlink_broadcast() reports errors to the caller if no messages at all were delivered: 1) If, at least, one message has been delivered correctly, returns 0. 2) Otherwise, if no messages at all were delivered due to skb_clone() failure, return -ENOBUFS. 3) Otherwise, if there are no listeners, return -ESRCH. With this patch, the caller knows if the delivery of any of the messages to the listeners have failed: 1) If it fails to deliver any message (for whatever reason), return -ENOBUFS. 2) Otherwise, if all messages were delivered OK, returns 0. 3) Otherwise, if no listeners, return -ESRCH. In the current ctnetlink code and in Netfilter in general, we can add reliable logging and connection tracking event delivery by dropping the packets whose events were not successfully delivered over Netlink. Of course, this option would be settable via /proc as this approach reduces performance (in terms of filtered connections per seconds by a stateful firewall) but providing reliable logging and event delivery (for conntrackd) in return. This patch also changes some clients of netlink_broadcast() that may report ENOBUFS errors via printk. This error handling is not of any help. Instead, the userspace daemons that are listening to those netlink messages should resync themselves with the kernel-side if they hit ENOBUFS. BTW, netlink_broadcast() clients include those that call cn_netlink_send(), nlmsg_multicast() and genlmsg_multicast() since they internally call netlink_broadcast() and return its error value. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-02-06 15:56:36 +08:00
} else if (err == -ENOBUFS)
err = 0;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (!err && !(task->t.flags & TF_EXIT))
err = !wait_for_completion_timeout(task->done,
msecs_to_jiffies(UVESAFB_TIMEOUT));
mutex_lock(&uvfb_lock);
uvfb_tasks[seq] = NULL;
mutex_unlock(&uvfb_lock);
seq++;
if (seq >= UVESAFB_TASKS_MAX)
seq = 0;
out:
kfree(m);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
return err;
}
/*
* Free a uvesafb_ktask struct.
*/
static void uvesafb_free(struct uvesafb_ktask *task)
{
if (task) {
if (task->done)
kfree(task->done);
kfree(task);
}
}
/*
* Prepare a uvesafb_ktask struct to be used again.
*/
static void uvesafb_reset(struct uvesafb_ktask *task)
{
struct completion *cpl = task->done;
memset(task, 0, sizeof(*task));
task->done = cpl;
}
/*
* Allocate and prepare a uvesafb_ktask struct.
*/
static struct uvesafb_ktask *uvesafb_prep(void)
{
struct uvesafb_ktask *task;
task = kzalloc(sizeof(*task), GFP_KERNEL);
if (task) {
task->done = kzalloc(sizeof(*task->done), GFP_KERNEL);
if (!task->done) {
kfree(task);
task = NULL;
}
}
return task;
}
static void uvesafb_setup_var(struct fb_var_screeninfo *var,
struct fb_info *info, struct vbe_mode_ib *mode)
{
struct uvesafb_par *par = info->par;
var->vmode = FB_VMODE_NONINTERLACED;
var->sync = FB_SYNC_VERT_HIGH_ACT;
var->xres = mode->x_res;
var->yres = mode->y_res;
var->xres_virtual = mode->x_res;
var->yres_virtual = (par->ypan) ?
info->fix.smem_len / mode->bytes_per_scan_line :
mode->y_res;
var->xoffset = 0;
var->yoffset = 0;
var->bits_per_pixel = mode->bits_per_pixel;
if (var->bits_per_pixel == 15)
var->bits_per_pixel = 16;
if (var->bits_per_pixel > 8) {
var->red.offset = mode->red_off;
var->red.length = mode->red_len;
var->green.offset = mode->green_off;
var->green.length = mode->green_len;
var->blue.offset = mode->blue_off;
var->blue.length = mode->blue_len;
var->transp.offset = mode->rsvd_off;
var->transp.length = mode->rsvd_len;
} else {
var->red.offset = 0;
var->green.offset = 0;
var->blue.offset = 0;
var->transp.offset = 0;
var->red.length = 8;
var->green.length = 8;
var->blue.length = 8;
var->transp.length = 0;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
}
static int uvesafb_vbe_find_mode(struct uvesafb_par *par,
int xres, int yres, int depth, unsigned char flags)
{
int i, match = -1, h = 0, d = 0x7fffffff;
for (i = 0; i < par->vbe_modes_cnt; i++) {
h = abs(par->vbe_modes[i].x_res - xres) +
abs(par->vbe_modes[i].y_res - yres) +
abs(depth - par->vbe_modes[i].depth);
/*
* We have an exact match in terms of resolution
* and depth.
*/
if (h == 0)
return i;
if (h < d || (h == d && par->vbe_modes[i].depth > depth)) {
d = h;
match = i;
}
}
i = 1;
if (flags & UVESAFB_EXACT_DEPTH &&
par->vbe_modes[match].depth != depth)
i = 0;
if (flags & UVESAFB_EXACT_RES && d > 24)
i = 0;
if (i != 0)
return match;
else
return -1;
}
static u8 *uvesafb_vbe_state_save(struct uvesafb_par *par)
{
struct uvesafb_ktask *task;
u8 *state;
int err;
if (!par->vbe_state_size)
return NULL;
state = kmalloc(par->vbe_state_size, GFP_KERNEL);
if (!state)
return NULL;
task = uvesafb_prep();
if (!task) {
kfree(state);
return NULL;
}
task->t.regs.eax = 0x4f04;
task->t.regs.ecx = 0x000f;
task->t.regs.edx = 0x0001;
task->t.flags = TF_BUF_RET | TF_BUF_ESBX;
task->t.buf_len = par->vbe_state_size;
task->buf = state;
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f) {
printk(KERN_WARNING "uvesafb: VBE get state call "
"failed (eax=0x%x, err=%d)\n",
task->t.regs.eax, err);
kfree(state);
state = NULL;
}
uvesafb_free(task);
return state;
}
static void uvesafb_vbe_state_restore(struct uvesafb_par *par, u8 *state_buf)
{
struct uvesafb_ktask *task;
int err;
if (!state_buf)
return;
task = uvesafb_prep();
if (!task)
return;
task->t.regs.eax = 0x4f04;
task->t.regs.ecx = 0x000f;
task->t.regs.edx = 0x0002;
task->t.buf_len = par->vbe_state_size;
task->t.flags = TF_BUF_ESBX;
task->buf = state_buf;
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f)
printk(KERN_WARNING "uvesafb: VBE state restore call "
"failed (eax=0x%x, err=%d)\n",
task->t.regs.eax, err);
uvesafb_free(task);
}
static int __devinit uvesafb_vbe_getinfo(struct uvesafb_ktask *task,
struct uvesafb_par *par)
{
int err;
task->t.regs.eax = 0x4f00;
task->t.flags = TF_VBEIB;
task->t.buf_len = sizeof(struct vbe_ib);
task->buf = &par->vbe_ib;
strncpy(par->vbe_ib.vbe_signature, "VBE2", 4);
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f) {
printk(KERN_ERR "uvesafb: Getting VBE info block failed "
"(eax=0x%x, err=%d)\n", (u32)task->t.regs.eax,
err);
return -EINVAL;
}
if (par->vbe_ib.vbe_version < 0x0200) {
printk(KERN_ERR "uvesafb: Sorry, pre-VBE 2.0 cards are "
"not supported.\n");
return -EINVAL;
}
if (!par->vbe_ib.mode_list_ptr) {
printk(KERN_ERR "uvesafb: Missing mode list!\n");
return -EINVAL;
}
printk(KERN_INFO "uvesafb: ");
/*
* Convert string pointers and the mode list pointer into
* usable addresses. Print informational messages about the
* video adapter and its vendor.
*/
if (par->vbe_ib.oem_vendor_name_ptr)
printk("%s, ",
((char *)task->buf) + par->vbe_ib.oem_vendor_name_ptr);
if (par->vbe_ib.oem_product_name_ptr)
printk("%s, ",
((char *)task->buf) + par->vbe_ib.oem_product_name_ptr);
if (par->vbe_ib.oem_product_rev_ptr)
printk("%s, ",
((char *)task->buf) + par->vbe_ib.oem_product_rev_ptr);
if (par->vbe_ib.oem_string_ptr)
printk("OEM: %s, ",
((char *)task->buf) + par->vbe_ib.oem_string_ptr);
printk("VBE v%d.%d\n", ((par->vbe_ib.vbe_version & 0xff00) >> 8),
par->vbe_ib.vbe_version & 0xff);
return 0;
}
static int __devinit uvesafb_vbe_getmodes(struct uvesafb_ktask *task,
struct uvesafb_par *par)
{
int off = 0, err;
u16 *mode;
par->vbe_modes_cnt = 0;
/* Count available modes. */
mode = (u16 *) (((u8 *)&par->vbe_ib) + par->vbe_ib.mode_list_ptr);
while (*mode != 0xffff) {
par->vbe_modes_cnt++;
mode++;
}
par->vbe_modes = kzalloc(sizeof(struct vbe_mode_ib) *
par->vbe_modes_cnt, GFP_KERNEL);
if (!par->vbe_modes)
return -ENOMEM;
/* Get info about all available modes. */
mode = (u16 *) (((u8 *)&par->vbe_ib) + par->vbe_ib.mode_list_ptr);
while (*mode != 0xffff) {
struct vbe_mode_ib *mib;
uvesafb_reset(task);
task->t.regs.eax = 0x4f01;
task->t.regs.ecx = (u32) *mode;
task->t.flags = TF_BUF_RET | TF_BUF_ESDI;
task->t.buf_len = sizeof(struct vbe_mode_ib);
task->buf = par->vbe_modes + off;
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f) {
printk(KERN_WARNING "uvesafb: Getting mode info block "
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
"for mode 0x%x failed (eax=0x%x, err=%d)\n",
*mode, (u32)task->t.regs.eax, err);
mode++;
par->vbe_modes_cnt--;
continue;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
mib = task->buf;
mib->mode_id = *mode;
/*
* We only want modes that are supported with the current
* hardware configuration, color, graphics and that have
* support for the LFB.
*/
if ((mib->mode_attr & VBE_MODE_MASK) == VBE_MODE_MASK &&
mib->bits_per_pixel >= 8)
off++;
else
par->vbe_modes_cnt--;
mode++;
mib->depth = mib->red_len + mib->green_len + mib->blue_len;
/*
* Handle 8bpp modes and modes with broken color component
* lengths.
*/
if (mib->depth == 0 || (mib->depth == 24 &&
mib->bits_per_pixel == 32))
mib->depth = mib->bits_per_pixel;
}
if (par->vbe_modes_cnt > 0)
return 0;
else
return -EINVAL;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
/*
* The Protected Mode Interface is 32-bit x86 code, so we only run it on
* x86 and not x86_64.
*/
#ifdef CONFIG_X86_32
static int __devinit uvesafb_vbe_getpmi(struct uvesafb_ktask *task,
struct uvesafb_par *par)
{
int i, err;
uvesafb_reset(task);
task->t.regs.eax = 0x4f0a;
task->t.regs.ebx = 0x0;
err = uvesafb_exec(task);
if ((task->t.regs.eax & 0xffff) != 0x4f || task->t.regs.es < 0xc000) {
par->pmi_setpal = par->ypan = 0;
} else {
par->pmi_base = (u16 *)phys_to_virt(((u32)task->t.regs.es << 4)
+ task->t.regs.edi);
par->pmi_start = (u8 *)par->pmi_base + par->pmi_base[1];
par->pmi_pal = (u8 *)par->pmi_base + par->pmi_base[2];
printk(KERN_INFO "uvesafb: protected mode interface info at "
"%04x:%04x\n",
(u16)task->t.regs.es, (u16)task->t.regs.edi);
printk(KERN_INFO "uvesafb: pmi: set display start = %p, "
"set palette = %p\n", par->pmi_start,
par->pmi_pal);
if (par->pmi_base[3]) {
printk(KERN_INFO "uvesafb: pmi: ports = ");
for (i = par->pmi_base[3]/2;
par->pmi_base[i] != 0xffff; i++)
printk("%x ", par->pmi_base[i]);
printk("\n");
if (par->pmi_base[i] != 0xffff) {
printk(KERN_INFO "uvesafb: can't handle memory"
" requests, pmi disabled\n");
par->ypan = par->pmi_setpal = 0;
}
}
}
return 0;
}
#endif /* CONFIG_X86_32 */
/*
* Check whether a video mode is supported by the Video BIOS and is
* compatible with the monitor limits.
*/
static int __devinit uvesafb_is_valid_mode(struct fb_videomode *mode,
struct fb_info *info)
{
if (info->monspecs.gtf) {
fb_videomode_to_var(&info->var, mode);
if (fb_validate_mode(&info->var, info))
return 0;
}
if (uvesafb_vbe_find_mode(info->par, mode->xres, mode->yres, 8,
UVESAFB_EXACT_RES) == -1)
return 0;
return 1;
}
static int __devinit uvesafb_vbe_getedid(struct uvesafb_ktask *task,
struct fb_info *info)
{
struct uvesafb_par *par = info->par;
int err = 0;
if (noedid || par->vbe_ib.vbe_version < 0x0300)
return -EINVAL;
task->t.regs.eax = 0x4f15;
task->t.regs.ebx = 0;
task->t.regs.ecx = 0;
task->t.buf_len = 0;
task->t.flags = 0;
err = uvesafb_exec(task);
if ((task->t.regs.eax & 0xffff) != 0x004f || err)
return -EINVAL;
if ((task->t.regs.ebx & 0x3) == 3) {
printk(KERN_INFO "uvesafb: VBIOS/hardware supports both "
"DDC1 and DDC2 transfers\n");
} else if ((task->t.regs.ebx & 0x3) == 2) {
printk(KERN_INFO "uvesafb: VBIOS/hardware supports DDC2 "
"transfers\n");
} else if ((task->t.regs.ebx & 0x3) == 1) {
printk(KERN_INFO "uvesafb: VBIOS/hardware supports DDC1 "
"transfers\n");
} else {
printk(KERN_INFO "uvesafb: VBIOS/hardware doesn't support "
"DDC transfers\n");
return -EINVAL;
}
task->t.regs.eax = 0x4f15;
task->t.regs.ebx = 1;
task->t.regs.ecx = task->t.regs.edx = 0;
task->t.flags = TF_BUF_RET | TF_BUF_ESDI;
task->t.buf_len = EDID_LENGTH;
task->buf = kzalloc(EDID_LENGTH, GFP_KERNEL);
err = uvesafb_exec(task);
if ((task->t.regs.eax & 0xffff) == 0x004f && !err) {
fb_edid_to_monspecs(task->buf, &info->monspecs);
if (info->monspecs.vfmax && info->monspecs.hfmax) {
/*
* If the maximum pixel clock wasn't specified in
* the EDID block, set it to 300 MHz.
*/
if (info->monspecs.dclkmax == 0)
info->monspecs.dclkmax = 300 * 1000000;
info->monspecs.gtf = 1;
}
} else {
err = -EINVAL;
}
kfree(task->buf);
return err;
}
static void __devinit uvesafb_vbe_getmonspecs(struct uvesafb_ktask *task,
struct fb_info *info)
{
struct uvesafb_par *par = info->par;
int i;
memset(&info->monspecs, 0, sizeof(info->monspecs));
/*
* If we don't get all necessary data from the EDID block,
* mark it as incompatible with the GTF and set nocrtc so
* that we always use the default BIOS refresh rate.
*/
if (uvesafb_vbe_getedid(task, info)) {
info->monspecs.gtf = 0;
par->nocrtc = 1;
}
/* Kernel command line overrides. */
if (maxclk)
info->monspecs.dclkmax = maxclk * 1000000;
if (maxvf)
info->monspecs.vfmax = maxvf;
if (maxhf)
info->monspecs.hfmax = maxhf * 1000;
/*
* In case DDC transfers are not supported, the user can provide
* monitor limits manually. Lower limits are set to "safe" values.
*/
if (info->monspecs.gtf == 0 && maxclk && maxvf && maxhf) {
info->monspecs.dclkmin = 0;
info->monspecs.vfmin = 60;
info->monspecs.hfmin = 29000;
info->monspecs.gtf = 1;
par->nocrtc = 0;
}
if (info->monspecs.gtf)
printk(KERN_INFO
"uvesafb: monitor limits: vf = %d Hz, hf = %d kHz, "
"clk = %d MHz\n", info->monspecs.vfmax,
(int)(info->monspecs.hfmax / 1000),
(int)(info->monspecs.dclkmax / 1000000));
else
printk(KERN_INFO "uvesafb: no monitor limits have been set, "
"default refresh rate will be used\n");
/* Add VBE modes to the modelist. */
for (i = 0; i < par->vbe_modes_cnt; i++) {
struct fb_var_screeninfo var;
struct vbe_mode_ib *mode;
struct fb_videomode vmode;
mode = &par->vbe_modes[i];
memset(&var, 0, sizeof(var));
var.xres = mode->x_res;
var.yres = mode->y_res;
fb_get_mode(FB_VSYNCTIMINGS | FB_IGNOREMON, 60, &var, info);
fb_var_to_videomode(&vmode, &var);
fb_add_videomode(&vmode, &info->modelist);
}
/* Add valid VESA modes to our modelist. */
for (i = 0; i < VESA_MODEDB_SIZE; i++) {
if (uvesafb_is_valid_mode((struct fb_videomode *)
&vesa_modes[i], info))
fb_add_videomode(&vesa_modes[i], &info->modelist);
}
for (i = 0; i < info->monspecs.modedb_len; i++) {
if (uvesafb_is_valid_mode(&info->monspecs.modedb[i], info))
fb_add_videomode(&info->monspecs.modedb[i],
&info->modelist);
}
return;
}
static void __devinit uvesafb_vbe_getstatesize(struct uvesafb_ktask *task,
struct uvesafb_par *par)
{
int err;
uvesafb_reset(task);
/*
* Get the VBE state buffer size. We want all available
* hardware state data (CL = 0x0f).
*/
task->t.regs.eax = 0x4f04;
task->t.regs.ecx = 0x000f;
task->t.regs.edx = 0x0000;
task->t.flags = 0;
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f) {
printk(KERN_WARNING "uvesafb: VBE state buffer size "
"cannot be determined (eax=0x%x, err=%d)\n",
task->t.regs.eax, err);
par->vbe_state_size = 0;
return;
}
par->vbe_state_size = 64 * (task->t.regs.ebx & 0xffff);
}
static int __devinit uvesafb_vbe_init(struct fb_info *info)
{
struct uvesafb_ktask *task = NULL;
struct uvesafb_par *par = info->par;
int err;
task = uvesafb_prep();
if (!task)
return -ENOMEM;
err = uvesafb_vbe_getinfo(task, par);
if (err)
goto out;
err = uvesafb_vbe_getmodes(task, par);
if (err)
goto out;
par->nocrtc = nocrtc;
#ifdef CONFIG_X86_32
par->pmi_setpal = pmi_setpal;
par->ypan = ypan;
if (par->pmi_setpal || par->ypan)
uvesafb_vbe_getpmi(task, par);
#else
/* The protected mode interface is not available on non-x86. */
par->pmi_setpal = par->ypan = 0;
#endif
INIT_LIST_HEAD(&info->modelist);
uvesafb_vbe_getmonspecs(task, info);
uvesafb_vbe_getstatesize(task, par);
out: uvesafb_free(task);
return err;
}
static int __devinit uvesafb_vbe_init_mode(struct fb_info *info)
{
struct list_head *pos;
struct fb_modelist *modelist;
struct fb_videomode *mode;
struct uvesafb_par *par = info->par;
int i, modeid;
/* Has the user requested a specific VESA mode? */
if (vbemode) {
for (i = 0; i < par->vbe_modes_cnt; i++) {
if (par->vbe_modes[i].mode_id == vbemode) {
modeid = i;
uvesafb_setup_var(&info->var, info,
&par->vbe_modes[modeid]);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
fb_get_mode(FB_VSYNCTIMINGS | FB_IGNOREMON, 60,
&info->var, info);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
/*
* With pixclock set to 0, the default BIOS
* timings will be used in set_par().
*/
info->var.pixclock = 0;
goto gotmode;
}
}
printk(KERN_INFO "uvesafb: requested VBE mode 0x%x is "
"unavailable\n", vbemode);
vbemode = 0;
}
/* Count the modes in the modelist */
i = 0;
list_for_each(pos, &info->modelist)
i++;
/*
* Convert the modelist into a modedb so that we can use it with
* fb_find_mode().
*/
mode = kzalloc(i * sizeof(*mode), GFP_KERNEL);
if (mode) {
i = 0;
list_for_each(pos, &info->modelist) {
modelist = list_entry(pos, struct fb_modelist, list);
mode[i] = modelist->mode;
i++;
}
if (!mode_option)
mode_option = UVESAFB_DEFAULT_MODE;
i = fb_find_mode(&info->var, info, mode_option, mode, i,
NULL, 8);
kfree(mode);
}
/* fb_find_mode() failed */
if (i == 0) {
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
info->var.xres = 640;
info->var.yres = 480;
mode = (struct fb_videomode *)
fb_find_best_mode(&info->var, &info->modelist);
if (mode) {
fb_videomode_to_var(&info->var, mode);
} else {
modeid = par->vbe_modes[0].mode_id;
uvesafb_setup_var(&info->var, info,
&par->vbe_modes[modeid]);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
fb_get_mode(FB_VSYNCTIMINGS | FB_IGNOREMON, 60,
&info->var, info);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
goto gotmode;
}
}
/* Look for a matching VBE mode. */
modeid = uvesafb_vbe_find_mode(par, info->var.xres, info->var.yres,
info->var.bits_per_pixel, UVESAFB_EXACT_RES);
if (modeid == -1)
return -EINVAL;
uvesafb_setup_var(&info->var, info, &par->vbe_modes[modeid]);
gotmode:
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
/*
* If we are not VBE3.0+ compliant, we're done -- the BIOS will
* ignore our timings anyway.
*/
if (par->vbe_ib.vbe_version < 0x0300 || par->nocrtc)
fb_get_mode(FB_VSYNCTIMINGS | FB_IGNOREMON, 60,
&info->var, info);
return modeid;
}
static int uvesafb_setpalette(struct uvesafb_pal_entry *entries, int count,
int start, struct fb_info *info)
{
struct uvesafb_ktask *task;
#ifdef CONFIG_X86
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
struct uvesafb_par *par = info->par;
int i = par->mode_idx;
#endif
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
int err = 0;
/*
* We support palette modifications for 8 bpp modes only, so
* there can never be more than 256 entries.
*/
if (start + count > 256)
return -EINVAL;
#ifdef CONFIG_X86
/* Use VGA registers if mode is VGA-compatible. */
if (i >= 0 && i < par->vbe_modes_cnt &&
par->vbe_modes[i].mode_attr & VBE_MODE_VGACOMPAT) {
for (i = 0; i < count; i++) {
outb_p(start + i, dac_reg);
outb_p(entries[i].red, dac_val);
outb_p(entries[i].green, dac_val);
outb_p(entries[i].blue, dac_val);
}
}
#ifdef CONFIG_X86_32
else if (par->pmi_setpal) {
__asm__ __volatile__(
"call *(%%esi)"
: /* no return value */
: "a" (0x4f09), /* EAX */
"b" (0), /* EBX */
"c" (count), /* ECX */
"d" (start), /* EDX */
"D" (entries), /* EDI */
"S" (&par->pmi_pal)); /* ESI */
}
#endif /* CONFIG_X86_32 */
else
#endif /* CONFIG_X86 */
{
task = uvesafb_prep();
if (!task)
return -ENOMEM;
task->t.regs.eax = 0x4f09;
task->t.regs.ebx = 0x0;
task->t.regs.ecx = count;
task->t.regs.edx = start;
task->t.flags = TF_BUF_ESDI;
task->t.buf_len = sizeof(struct uvesafb_pal_entry) * count;
task->buf = entries;
err = uvesafb_exec(task);
if ((task->t.regs.eax & 0xffff) != 0x004f)
err = 1;
uvesafb_free(task);
}
return err;
}
static int uvesafb_setcolreg(unsigned regno, unsigned red, unsigned green,
unsigned blue, unsigned transp,
struct fb_info *info)
{
struct uvesafb_pal_entry entry;
int shift = 16 - dac_width;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
int err = 0;
if (regno >= info->cmap.len)
return -EINVAL;
if (info->var.bits_per_pixel == 8) {
entry.red = red >> shift;
entry.green = green >> shift;
entry.blue = blue >> shift;
entry.pad = 0;
err = uvesafb_setpalette(&entry, 1, regno, info);
} else if (regno < 16) {
switch (info->var.bits_per_pixel) {
case 16:
if (info->var.red.offset == 10) {
/* 1:5:5:5 */
((u32 *) (info->pseudo_palette))[regno] =
((red & 0xf800) >> 1) |
((green & 0xf800) >> 6) |
((blue & 0xf800) >> 11);
} else {
/* 0:5:6:5 */
((u32 *) (info->pseudo_palette))[regno] =
((red & 0xf800) ) |
((green & 0xfc00) >> 5) |
((blue & 0xf800) >> 11);
}
break;
case 24:
case 32:
red >>= 8;
green >>= 8;
blue >>= 8;
((u32 *)(info->pseudo_palette))[regno] =
(red << info->var.red.offset) |
(green << info->var.green.offset) |
(blue << info->var.blue.offset);
break;
}
}
return err;
}
static int uvesafb_setcmap(struct fb_cmap *cmap, struct fb_info *info)
{
struct uvesafb_pal_entry *entries;
int shift = 16 - dac_width;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
int i, err = 0;
if (info->var.bits_per_pixel == 8) {
if (cmap->start + cmap->len > info->cmap.start +
info->cmap.len || cmap->start < info->cmap.start)
return -EINVAL;
entries = kmalloc(sizeof(*entries) * cmap->len, GFP_KERNEL);
if (!entries)
return -ENOMEM;
for (i = 0; i < cmap->len; i++) {
entries[i].red = cmap->red[i] >> shift;
entries[i].green = cmap->green[i] >> shift;
entries[i].blue = cmap->blue[i] >> shift;
entries[i].pad = 0;
}
err = uvesafb_setpalette(entries, cmap->len, cmap->start, info);
kfree(entries);
} else {
/*
* For modes with bpp > 8, we only set the pseudo palette in
* the fb_info struct. We rely on uvesafb_setcolreg to do all
* sanity checking.
*/
for (i = 0; i < cmap->len; i++) {
err |= uvesafb_setcolreg(cmap->start + i, cmap->red[i],
cmap->green[i], cmap->blue[i],
0, info);
}
}
return err;
}
static int uvesafb_pan_display(struct fb_var_screeninfo *var,
struct fb_info *info)
{
#ifdef CONFIG_X86_32
int offset;
struct uvesafb_par *par = info->par;
offset = (var->yoffset * info->fix.line_length + var->xoffset) / 4;
/*
* It turns out it's not the best idea to do panning via vm86,
* so we only allow it if we have a PMI.
*/
if (par->pmi_start) {
__asm__ __volatile__(
"call *(%%edi)"
: /* no return value */
: "a" (0x4f07), /* EAX */
"b" (0), /* EBX */
"c" (offset), /* ECX */
"d" (offset >> 16), /* EDX */
"D" (&par->pmi_start)); /* EDI */
}
#endif
return 0;
}
static int uvesafb_blank(int blank, struct fb_info *info)
{
struct uvesafb_ktask *task;
int err = 1;
#ifdef CONFIG_X86
struct uvesafb_par *par = info->par;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (par->vbe_ib.capabilities & VBE_CAP_VGACOMPAT) {
int loop = 10000;
u8 seq = 0, crtc17 = 0;
if (blank == FB_BLANK_POWERDOWN) {
seq = 0x20;
crtc17 = 0x00;
err = 0;
} else {
seq = 0x00;
crtc17 = 0x80;
err = (blank == FB_BLANK_UNBLANK) ? 0 : -EINVAL;
}
vga_wseq(NULL, 0x00, 0x01);
seq |= vga_rseq(NULL, 0x01) & ~0x20;
vga_wseq(NULL, 0x00, seq);
crtc17 |= vga_rcrt(NULL, 0x17) & ~0x80;
while (loop--);
vga_wcrt(NULL, 0x17, crtc17);
vga_wseq(NULL, 0x00, 0x03);
} else
#endif /* CONFIG_X86 */
{
task = uvesafb_prep();
if (!task)
return -ENOMEM;
task->t.regs.eax = 0x4f10;
switch (blank) {
case FB_BLANK_UNBLANK:
task->t.regs.ebx = 0x0001;
break;
case FB_BLANK_NORMAL:
task->t.regs.ebx = 0x0101; /* standby */
break;
case FB_BLANK_POWERDOWN:
task->t.regs.ebx = 0x0401; /* powerdown */
break;
default:
goto out;
}
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f)
err = 1;
out: uvesafb_free(task);
}
return err;
}
static int uvesafb_open(struct fb_info *info, int user)
{
struct uvesafb_par *par = info->par;
int cnt = atomic_read(&par->ref_count);
if (!cnt && par->vbe_state_size)
par->vbe_state_orig = uvesafb_vbe_state_save(par);
atomic_inc(&par->ref_count);
return 0;
}
static int uvesafb_release(struct fb_info *info, int user)
{
struct uvesafb_ktask *task = NULL;
struct uvesafb_par *par = info->par;
int cnt = atomic_read(&par->ref_count);
if (!cnt)
return -EINVAL;
if (cnt != 1)
goto out;
task = uvesafb_prep();
if (!task)
goto out;
/* First, try to set the standard 80x25 text mode. */
task->t.regs.eax = 0x0003;
uvesafb_exec(task);
/*
* Now try to restore whatever hardware state we might have
* saved when the fb device was first opened.
*/
uvesafb_vbe_state_restore(par, par->vbe_state_orig);
out:
atomic_dec(&par->ref_count);
if (task)
uvesafb_free(task);
return 0;
}
static int uvesafb_set_par(struct fb_info *info)
{
struct uvesafb_par *par = info->par;
struct uvesafb_ktask *task = NULL;
struct vbe_crtc_ib *crtc = NULL;
struct vbe_mode_ib *mode = NULL;
int i, err = 0, depth = info->var.bits_per_pixel;
if (depth > 8 && depth != 32)
depth = info->var.red.length + info->var.green.length +
info->var.blue.length;
i = uvesafb_vbe_find_mode(par, info->var.xres, info->var.yres, depth,
UVESAFB_EXACT_RES | UVESAFB_EXACT_DEPTH);
if (i >= 0)
mode = &par->vbe_modes[i];
else
return -EINVAL;
task = uvesafb_prep();
if (!task)
return -ENOMEM;
setmode:
task->t.regs.eax = 0x4f02;
task->t.regs.ebx = mode->mode_id | 0x4000; /* use LFB */
if (par->vbe_ib.vbe_version >= 0x0300 && !par->nocrtc &&
info->var.pixclock != 0) {
task->t.regs.ebx |= 0x0800; /* use CRTC data */
task->t.flags = TF_BUF_ESDI;
crtc = kzalloc(sizeof(struct vbe_crtc_ib), GFP_KERNEL);
if (!crtc) {
err = -ENOMEM;
goto out;
}
crtc->horiz_start = info->var.xres + info->var.right_margin;
crtc->horiz_end = crtc->horiz_start + info->var.hsync_len;
crtc->horiz_total = crtc->horiz_end + info->var.left_margin;
crtc->vert_start = info->var.yres + info->var.lower_margin;
crtc->vert_end = crtc->vert_start + info->var.vsync_len;
crtc->vert_total = crtc->vert_end + info->var.upper_margin;
crtc->pixel_clock = PICOS2KHZ(info->var.pixclock) * 1000;
crtc->refresh_rate = (u16)(100 * (crtc->pixel_clock /
(crtc->vert_total * crtc->horiz_total)));
if (info->var.vmode & FB_VMODE_DOUBLE)
crtc->flags |= 0x1;
if (info->var.vmode & FB_VMODE_INTERLACED)
crtc->flags |= 0x2;
if (!(info->var.sync & FB_SYNC_HOR_HIGH_ACT))
crtc->flags |= 0x4;
if (!(info->var.sync & FB_SYNC_VERT_HIGH_ACT))
crtc->flags |= 0x8;
memcpy(&par->crtc, crtc, sizeof(*crtc));
} else {
memset(&par->crtc, 0, sizeof(*crtc));
}
task->t.buf_len = sizeof(struct vbe_crtc_ib);
task->buf = &par->crtc;
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f) {
/*
* The mode switch might have failed because we tried to
* use our own timings. Try again with the default timings.
*/
if (crtc != NULL) {
printk(KERN_WARNING "uvesafb: mode switch failed "
"(eax=0x%x, err=%d). Trying again with "
"default timings.\n", task->t.regs.eax, err);
uvesafb_reset(task);
kfree(crtc);
crtc = NULL;
info->var.pixclock = 0;
goto setmode;
} else {
printk(KERN_ERR "uvesafb: mode switch failed (eax="
"0x%x, err=%d)\n", task->t.regs.eax, err);
err = -EINVAL;
goto out;
}
}
par->mode_idx = i;
/* For 8bpp modes, always try to set the DAC to 8 bits. */
if (par->vbe_ib.capabilities & VBE_CAP_CAN_SWITCH_DAC &&
mode->bits_per_pixel <= 8) {
uvesafb_reset(task);
task->t.regs.eax = 0x4f08;
task->t.regs.ebx = 0x0800;
err = uvesafb_exec(task);
if (err || (task->t.regs.eax & 0xffff) != 0x004f ||
((task->t.regs.ebx & 0xff00) >> 8) != 8) {
dac_width = 6;
} else {
dac_width = 8;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
}
info->fix.visual = (info->var.bits_per_pixel == 8) ?
FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
info->fix.line_length = mode->bytes_per_scan_line;
out: if (crtc != NULL)
kfree(crtc);
uvesafb_free(task);
return err;
}
static void uvesafb_check_limits(struct fb_var_screeninfo *var,
struct fb_info *info)
{
const struct fb_videomode *mode;
struct uvesafb_par *par = info->par;
/*
* If pixclock is set to 0, then we're using default BIOS timings
* and thus don't have to perform any checks here.
*/
if (!var->pixclock)
return;
if (par->vbe_ib.vbe_version < 0x0300) {
fb_get_mode(FB_VSYNCTIMINGS | FB_IGNOREMON, 60, var, info);
return;
}
if (!fb_validate_mode(var, info))
return;
mode = fb_find_best_mode(var, &info->modelist);
if (mode) {
if (mode->xres == var->xres && mode->yres == var->yres &&
!(mode->vmode & (FB_VMODE_INTERLACED | FB_VMODE_DOUBLE))) {
fb_videomode_to_var(var, mode);
return;
}
}
if (info->monspecs.gtf && !fb_get_mode(FB_MAXTIMINGS, 0, var, info))
return;
/* Use default refresh rate */
var->pixclock = 0;
}
static int uvesafb_check_var(struct fb_var_screeninfo *var,
struct fb_info *info)
{
struct uvesafb_par *par = info->par;
struct vbe_mode_ib *mode = NULL;
int match = -1;
int depth = var->red.length + var->green.length + var->blue.length;
/*
* Various apps will use bits_per_pixel to set the color depth,
* which is theoretically incorrect, but which we'll try to handle
* here.
*/
if (depth == 0 || abs(depth - var->bits_per_pixel) >= 8)
depth = var->bits_per_pixel;
match = uvesafb_vbe_find_mode(par, var->xres, var->yres, depth,
UVESAFB_EXACT_RES);
if (match == -1)
return -EINVAL;
mode = &par->vbe_modes[match];
uvesafb_setup_var(var, info, mode);
/*
* Check whether we have remapped enough memory for this mode.
* We might be called at an early stage, when we haven't remapped
* any memory yet, in which case we simply skip the check.
*/
if (var->yres * mode->bytes_per_scan_line > info->fix.smem_len
&& info->fix.smem_len)
return -EINVAL;
if ((var->vmode & FB_VMODE_DOUBLE) &&
!(par->vbe_modes[match].mode_attr & 0x100))
var->vmode &= ~FB_VMODE_DOUBLE;
if ((var->vmode & FB_VMODE_INTERLACED) &&
!(par->vbe_modes[match].mode_attr & 0x200))
var->vmode &= ~FB_VMODE_INTERLACED;
uvesafb_check_limits(var, info);
var->xres_virtual = var->xres;
var->yres_virtual = (par->ypan) ?
info->fix.smem_len / mode->bytes_per_scan_line :
var->yres;
return 0;
}
static struct fb_ops uvesafb_ops = {
.owner = THIS_MODULE,
.fb_open = uvesafb_open,
.fb_release = uvesafb_release,
.fb_setcolreg = uvesafb_setcolreg,
.fb_setcmap = uvesafb_setcmap,
.fb_pan_display = uvesafb_pan_display,
.fb_blank = uvesafb_blank,
.fb_fillrect = cfb_fillrect,
.fb_copyarea = cfb_copyarea,
.fb_imageblit = cfb_imageblit,
.fb_check_var = uvesafb_check_var,
.fb_set_par = uvesafb_set_par,
};
static void __devinit uvesafb_init_info(struct fb_info *info,
struct vbe_mode_ib *mode)
{
unsigned int size_vmode;
unsigned int size_remap;
unsigned int size_total;
struct uvesafb_par *par = info->par;
int i, h;
info->pseudo_palette = ((u8 *)info->par + sizeof(struct uvesafb_par));
info->fix = uvesafb_fix;
info->fix.ypanstep = par->ypan ? 1 : 0;
info->fix.ywrapstep = (par->ypan > 1) ? 1 : 0;
/* Disable blanking if the user requested so. */
if (!blank)
info->fbops->fb_blank = NULL;
/*
* Find out how much IO memory is required for the mode with
* the highest resolution.
*/
size_remap = 0;
for (i = 0; i < par->vbe_modes_cnt; i++) {
h = par->vbe_modes[i].bytes_per_scan_line *
par->vbe_modes[i].y_res;
if (h > size_remap)
size_remap = h;
}
size_remap *= 2;
/*
* size_vmode -- that is the amount of memory needed for the
* used video mode, i.e. the minimum amount of
* memory we need.
*/
if (mode != NULL) {
size_vmode = info->var.yres * mode->bytes_per_scan_line;
} else {
size_vmode = info->var.yres * info->var.xres *
((info->var.bits_per_pixel + 7) >> 3);
}
/*
* size_total -- all video memory we have. Used for mtrr
* entries, resource allocation and bounds
* checking.
*/
size_total = par->vbe_ib.total_memory * 65536;
if (vram_total)
size_total = vram_total * 1024 * 1024;
if (size_total < size_vmode)
size_total = size_vmode;
/*
* size_remap -- the amount of video memory we are going to
* use for vesafb. With modern cards it is no
* option to simply use size_total as th
* wastes plenty of kernel address space.
*/
if (vram_remap)
size_remap = vram_remap * 1024 * 1024;
if (size_remap < size_vmode)
size_remap = size_vmode;
if (size_remap > size_total)
size_remap = size_total;
info->fix.smem_len = size_remap;
info->fix.smem_start = mode->phys_base_ptr;
/*
* We have to set yres_virtual here because when setup_var() was
* called, smem_len wasn't defined yet.
*/
info->var.yres_virtual = info->fix.smem_len /
mode->bytes_per_scan_line;
if (par->ypan && info->var.yres_virtual > info->var.yres) {
printk(KERN_INFO "uvesafb: scrolling: %s "
"using protected mode interface, "
"yres_virtual=%d\n",
(par->ypan > 1) ? "ywrap" : "ypan",
info->var.yres_virtual);
} else {
printk(KERN_INFO "uvesafb: scrolling: redraw\n");
info->var.yres_virtual = info->var.yres;
par->ypan = 0;
}
info->flags = FBINFO_FLAG_DEFAULT |
(par->ypan ? FBINFO_HWACCEL_YPAN : 0);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (!par->ypan)
info->fbops->fb_pan_display = NULL;
}
static void __devinit uvesafb_init_mtrr(struct fb_info *info)
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
{
#ifdef CONFIG_MTRR
if (mtrr && !(info->fix.smem_start & (PAGE_SIZE - 1))) {
int temp_size = info->fix.smem_len;
unsigned int type = 0;
switch (mtrr) {
case 1:
type = MTRR_TYPE_UNCACHABLE;
break;
case 2:
type = MTRR_TYPE_WRBACK;
break;
case 3:
type = MTRR_TYPE_WRCOMB;
break;
case 4:
type = MTRR_TYPE_WRTHROUGH;
break;
default:
type = 0;
break;
}
if (type) {
int rc;
/* Find the largest power-of-two */
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
temp_size = roundup_pow_of_two(temp_size);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
/* Try and find a power of two to add */
do {
rc = mtrr_add(info->fix.smem_start,
temp_size, type, 1);
temp_size >>= 1;
} while (temp_size >= PAGE_SIZE && rc == -EINVAL);
}
}
#endif /* CONFIG_MTRR */
}
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
static void __devinit uvesafb_ioremap(struct fb_info *info)
{
#ifdef CONFIG_X86
switch (mtrr) {
case 1: /* uncachable */
info->screen_base = ioremap_nocache(info->fix.smem_start, info->fix.smem_len);
break;
case 2: /* write-back */
info->screen_base = ioremap_cache(info->fix.smem_start, info->fix.smem_len);
break;
case 3: /* write-combining */
info->screen_base = ioremap_wc(info->fix.smem_start, info->fix.smem_len);
break;
case 4: /* write-through */
default:
info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
break;
}
#else
info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
#endif /* CONFIG_X86 */
}
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
static ssize_t uvesafb_show_vbe_ver(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
return snprintf(buf, PAGE_SIZE, "%.4x\n", par->vbe_ib.vbe_version);
}
static DEVICE_ATTR(vbe_version, S_IRUGO, uvesafb_show_vbe_ver, NULL);
static ssize_t uvesafb_show_vbe_modes(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
int ret = 0, i;
for (i = 0; i < par->vbe_modes_cnt && ret < PAGE_SIZE; i++) {
ret += snprintf(buf + ret, PAGE_SIZE - ret,
"%dx%d-%d, 0x%.4x\n",
par->vbe_modes[i].x_res, par->vbe_modes[i].y_res,
par->vbe_modes[i].depth, par->vbe_modes[i].mode_id);
}
return ret;
}
static DEVICE_ATTR(vbe_modes, S_IRUGO, uvesafb_show_vbe_modes, NULL);
static ssize_t uvesafb_show_vendor(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
if (par->vbe_ib.oem_vendor_name_ptr)
return snprintf(buf, PAGE_SIZE, "%s\n", (char *)
(&par->vbe_ib) + par->vbe_ib.oem_vendor_name_ptr);
else
return 0;
}
static DEVICE_ATTR(oem_vendor, S_IRUGO, uvesafb_show_vendor, NULL);
static ssize_t uvesafb_show_product_name(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
if (par->vbe_ib.oem_product_name_ptr)
return snprintf(buf, PAGE_SIZE, "%s\n", (char *)
(&par->vbe_ib) + par->vbe_ib.oem_product_name_ptr);
else
return 0;
}
static DEVICE_ATTR(oem_product_name, S_IRUGO, uvesafb_show_product_name, NULL);
static ssize_t uvesafb_show_product_rev(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
if (par->vbe_ib.oem_product_rev_ptr)
return snprintf(buf, PAGE_SIZE, "%s\n", (char *)
(&par->vbe_ib) + par->vbe_ib.oem_product_rev_ptr);
else
return 0;
}
static DEVICE_ATTR(oem_product_rev, S_IRUGO, uvesafb_show_product_rev, NULL);
static ssize_t uvesafb_show_oem_string(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
if (par->vbe_ib.oem_string_ptr)
return snprintf(buf, PAGE_SIZE, "%s\n",
(char *)(&par->vbe_ib) + par->vbe_ib.oem_string_ptr);
else
return 0;
}
static DEVICE_ATTR(oem_string, S_IRUGO, uvesafb_show_oem_string, NULL);
static ssize_t uvesafb_show_nocrtc(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
return snprintf(buf, PAGE_SIZE, "%d\n", par->nocrtc);
}
static ssize_t uvesafb_store_nocrtc(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct fb_info *info = platform_get_drvdata(to_platform_device(dev));
struct uvesafb_par *par = info->par;
if (count > 0) {
if (buf[0] == '0')
par->nocrtc = 0;
else
par->nocrtc = 1;
}
return count;
}
static DEVICE_ATTR(nocrtc, S_IRUGO | S_IWUSR, uvesafb_show_nocrtc,
uvesafb_store_nocrtc);
static struct attribute *uvesafb_dev_attrs[] = {
&dev_attr_vbe_version.attr,
&dev_attr_vbe_modes.attr,
&dev_attr_oem_vendor.attr,
&dev_attr_oem_product_name.attr,
&dev_attr_oem_product_rev.attr,
&dev_attr_oem_string.attr,
&dev_attr_nocrtc.attr,
NULL,
};
static struct attribute_group uvesafb_dev_attgrp = {
.name = NULL,
.attrs = uvesafb_dev_attrs,
};
static int __devinit uvesafb_probe(struct platform_device *dev)
{
struct fb_info *info;
struct vbe_mode_ib *mode = NULL;
struct uvesafb_par *par;
int err = 0, i;
info = framebuffer_alloc(sizeof(*par) + sizeof(u32) * 256, &dev->dev);
if (!info)
return -ENOMEM;
par = info->par;
err = uvesafb_vbe_init(info);
if (err) {
printk(KERN_ERR "uvesafb: vbe_init() failed with %d\n", err);
goto out;
}
info->fbops = &uvesafb_ops;
i = uvesafb_vbe_init_mode(info);
if (i < 0) {
err = -EINVAL;
goto out;
} else {
mode = &par->vbe_modes[i];
}
if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) {
err = -ENXIO;
goto out;
}
uvesafb_init_info(info, mode);
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
if (!request_region(0x3c0, 32, "uvesafb")) {
printk(KERN_ERR "uvesafb: request region 0x3c0-0x3e0 failed\n");
err = -EIO;
goto out_mode;
}
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (!request_mem_region(info->fix.smem_start, info->fix.smem_len,
"uvesafb")) {
printk(KERN_ERR "uvesafb: cannot reserve video memory at "
"0x%lx\n", info->fix.smem_start);
err = -EIO;
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
goto out_reg;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
uvesafb_init_mtrr(info);
uvesafb_ioremap(info);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
if (!info->screen_base) {
printk(KERN_ERR
"uvesafb: abort, cannot ioremap 0x%x bytes of video "
"memory at 0x%lx\n",
info->fix.smem_len, info->fix.smem_start);
err = -EIO;
goto out_mem;
}
platform_set_drvdata(dev, info);
if (register_framebuffer(info) < 0) {
printk(KERN_ERR
"uvesafb: failed to register framebuffer device\n");
err = -EINVAL;
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
goto out_unmap;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
}
printk(KERN_INFO "uvesafb: framebuffer at 0x%lx, mapped to 0x%p, "
"using %dk, total %dk\n", info->fix.smem_start,
info->screen_base, info->fix.smem_len/1024,
par->vbe_ib.total_memory * 64);
printk(KERN_INFO "fb%d: %s frame buffer device\n", info->node,
info->fix.id);
err = sysfs_create_group(&dev->dev.kobj, &uvesafb_dev_attgrp);
if (err != 0)
printk(KERN_WARNING "fb%d: failed to register attributes\n",
info->node);
return 0;
out_unmap:
iounmap(info->screen_base);
out_mem:
release_mem_region(info->fix.smem_start, info->fix.smem_len);
uvesafb,vesafb: create WC or WB PAT-entries with an PAT-enabled kernel, when using uvesafb or vesafb, these drivers will create uncached-minus PAT entries for the framebuffer memory because they use ioremap() (not the *_cache or *_wc variants). When the framebuffer memory intersects with the video RAM used by Xorg, the complete video RAM will be mapped uncached-minus what results in a serve performance penalty. Here are the correct MTRR entries created by uvesafb: schlicht@netbook:~$ cat /proc/mtrr reg00: base=0x000000000 ( 0MB), size= 2048MB, count=1: write-back reg01: base=0x06ff00000 ( 1791MB), size= 1MB, count=1: uncachable reg02: base=0x070000000 ( 1792MB), size= 256MB, count=1: uncachable reg03: base=0x0d0000000 ( 3328MB), size= 16MB, count=1: write-combining And here are the problematic PAT entries: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0xd0000000-0xe0000000 <-- created by xserver-xorg uncached-minus @ 0xd0000000-0xd1194000 <-- created by uvesafb uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 Therefore I created the attached patch for uvesafb which uses ioremap_wc() to create the correct PAT entries, as shown below: schlicht@netbook:~$ sudo cat /sys/kernel/debug/x86/pat_memtype_list PAT memtype list: write-back @ 0x0-0x1000 uncached-minus @ 0x6fedd000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee2000-0x6fee3000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 uncached-minus @ 0x6fee3000-0x6fee4000 write-combining @ 0xd0000000-0xe0000000 write-combining @ 0xd0000000-0xd1194000 uncached-minus @ 0xf4000000-0xf4009000 uncached-minus @ 0xf4200000-0xf4400000 uncached-minus @ 0xf5000000-0xf5010000 uncached-minus @ 0xf5100000-0xf5104000 uncached-minus @ 0xf5400000-0xf5404000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xf5404000-0xf5405000 uncached-minus @ 0xfed00000-0xfed01000 This results in a performance gain, objectively measurable with e.g. x11perf -comppixwin10 -comppixwin100 -comppixwin500: 1: x11perf_xaa.log 2: x11perf_xaa_patched.log 1 2 Operation -------- ---------------- ----------------- 124000.0 202000.0 ( 1.63) Composite 10x10 from pixmap to window 3340.0 24400.0 ( 7.31) Composite 100x100 from pixmap to window 131.0 1150.0 ( 8.78) Composite 500x500 from pixmap to window You can see the serve performance gain when composing larger pixmaps to window. The patches replace the ioremap() function with the variant matching the mtrr- parameter. To create "write-back" PAT entries, the ioremap_cache() function must be called after creating the MTRR entries, and the ioremap_cache() region must completely fit into the MTRR region, this is why the MTRR region size is now rounded up to the next power-of-two. Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
2010-11-27 21:17:55 +08:00
out_reg:
release_region(0x3c0, 32);
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
out_mode:
if (!list_empty(&info->modelist))
fb_destroy_modelist(&info->modelist);
fb_destroy_modedb(info->monspecs.modedb);
fb_dealloc_cmap(&info->cmap);
out:
if (par->vbe_modes)
kfree(par->vbe_modes);
framebuffer_release(info);
return err;
}
static int uvesafb_remove(struct platform_device *dev)
{
struct fb_info *info = platform_get_drvdata(dev);
if (info) {
struct uvesafb_par *par = info->par;
sysfs_remove_group(&dev->dev.kobj, &uvesafb_dev_attgrp);
unregister_framebuffer(info);
release_region(0x3c0, 32);
iounmap(info->screen_base);
release_mem_region(info->fix.smem_start, info->fix.smem_len);
fb_destroy_modedb(info->monspecs.modedb);
fb_dealloc_cmap(&info->cmap);
if (par) {
if (par->vbe_modes)
kfree(par->vbe_modes);
if (par->vbe_state_orig)
kfree(par->vbe_state_orig);
if (par->vbe_state_saved)
kfree(par->vbe_state_saved);
}
framebuffer_release(info);
}
return 0;
}
static struct platform_driver uvesafb_driver = {
.probe = uvesafb_probe,
.remove = uvesafb_remove,
.driver = {
.name = "uvesafb",
},
};
static struct platform_device *uvesafb_device;
#ifndef MODULE
static int __devinit uvesafb_setup(char *options)
{
char *this_opt;
if (!options || !*options)
return 0;
while ((this_opt = strsep(&options, ",")) != NULL) {
if (!*this_opt) continue;
if (!strcmp(this_opt, "redraw"))
ypan = 0;
else if (!strcmp(this_opt, "ypan"))
ypan = 1;
else if (!strcmp(this_opt, "ywrap"))
ypan = 2;
else if (!strcmp(this_opt, "vgapal"))
pmi_setpal = 0;
else if (!strcmp(this_opt, "pmipal"))
pmi_setpal = 1;
else if (!strncmp(this_opt, "mtrr:", 5))
mtrr = simple_strtoul(this_opt+5, NULL, 0);
else if (!strcmp(this_opt, "nomtrr"))
mtrr = 0;
else if (!strcmp(this_opt, "nocrtc"))
nocrtc = 1;
else if (!strcmp(this_opt, "noedid"))
noedid = 1;
else if (!strcmp(this_opt, "noblank"))
blank = 0;
else if (!strncmp(this_opt, "vtotal:", 7))
vram_total = simple_strtoul(this_opt + 7, NULL, 0);
else if (!strncmp(this_opt, "vremap:", 7))
vram_remap = simple_strtoul(this_opt + 7, NULL, 0);
else if (!strncmp(this_opt, "maxhf:", 6))
maxhf = simple_strtoul(this_opt + 6, NULL, 0);
else if (!strncmp(this_opt, "maxvf:", 6))
maxvf = simple_strtoul(this_opt + 6, NULL, 0);
else if (!strncmp(this_opt, "maxclk:", 7))
maxclk = simple_strtoul(this_opt + 7, NULL, 0);
else if (!strncmp(this_opt, "vbemode:", 8))
vbemode = simple_strtoul(this_opt + 8, NULL, 0);
else if (this_opt[0] >= '0' && this_opt[0] <= '9') {
mode_option = this_opt;
} else {
printk(KERN_WARNING
"uvesafb: unrecognized option %s\n", this_opt);
}
}
return 0;
}
#endif /* !MODULE */
static ssize_t show_v86d(struct device_driver *dev, char *buf)
{
return snprintf(buf, PAGE_SIZE, "%s\n", v86d_path);
}
static ssize_t store_v86d(struct device_driver *dev, const char *buf,
size_t count)
{
strncpy(v86d_path, buf, PATH_MAX);
return count;
}
static DRIVER_ATTR(v86d, S_IRUGO | S_IWUSR, show_v86d, store_v86d);
static int __devinit uvesafb_init(void)
{
int err;
#ifndef MODULE
char *option = NULL;
if (fb_get_options("uvesafb", &option))
return -ENODEV;
uvesafb_setup(option);
#endif
err = cn_add_callback(&uvesafb_cn_id, "uvesafb", uvesafb_cn_callback);
if (err)
return err;
err = platform_driver_register(&uvesafb_driver);
if (!err) {
uvesafb_device = platform_device_alloc("uvesafb", 0);
if (uvesafb_device)
err = platform_device_add(uvesafb_device);
else
err = -ENOMEM;
if (err) {
platform_device_put(uvesafb_device);
platform_driver_unregister(&uvesafb_driver);
cn_del_callback(&uvesafb_cn_id);
return err;
}
err = driver_create_file(&uvesafb_driver.driver,
&driver_attr_v86d);
if (err) {
printk(KERN_WARNING "uvesafb: failed to register "
"attributes\n");
err = 0;
}
}
return err;
}
module_init(uvesafb_init);
static void __devexit uvesafb_exit(void)
{
struct uvesafb_ktask *task;
if (v86d_started) {
task = uvesafb_prep();
if (task) {
task->t.flags = TF_EXIT;
uvesafb_exec(task);
uvesafb_free(task);
}
}
cn_del_callback(&uvesafb_cn_id);
driver_remove_file(&uvesafb_driver.driver, &driver_attr_v86d);
platform_device_unregister(uvesafb_device);
platform_driver_unregister(&uvesafb_driver);
}
module_exit(uvesafb_exit);
static int param_set_scroll(const char *val, const struct kernel_param *kp)
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
{
ypan = 0;
if (!strcmp(val, "redraw"))
ypan = 0;
else if (!strcmp(val, "ypan"))
ypan = 1;
else if (!strcmp(val, "ywrap"))
ypan = 2;
else
return -EINVAL;
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
return 0;
}
static struct kernel_param_ops param_ops_scroll = {
.set = param_set_scroll,
};
#define param_check_scroll(name, p) __param_check(name, p, void)
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
module_param_named(scroll, ypan, scroll, 0);
MODULE_PARM_DESC(scroll,
"Scrolling mode, set to 'redraw', 'ypan', or 'ywrap'");
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
module_param_named(vgapal, pmi_setpal, invbool, 0);
MODULE_PARM_DESC(vgapal, "Set palette using VGA registers");
module_param_named(pmipal, pmi_setpal, bool, 0);
MODULE_PARM_DESC(pmipal, "Set palette using PMI calls");
module_param(mtrr, uint, 0);
MODULE_PARM_DESC(mtrr,
"Memory Type Range Registers setting. Use 0 to disable.");
module_param(blank, bool, 0);
MODULE_PARM_DESC(blank, "Enable hardware blanking");
module_param(nocrtc, bool, 0);
MODULE_PARM_DESC(nocrtc, "Ignore CRTC timings when setting modes");
module_param(noedid, bool, 0);
MODULE_PARM_DESC(noedid,
"Ignore EDID-provided monitor limits when setting modes");
module_param(vram_remap, uint, 0);
MODULE_PARM_DESC(vram_remap, "Set amount of video memory to be used [MiB]");
module_param(vram_total, uint, 0);
MODULE_PARM_DESC(vram_total, "Set total amount of video memoery [MiB]");
module_param(maxclk, ushort, 0);
MODULE_PARM_DESC(maxclk, "Maximum pixelclock [MHz], overrides EDID data");
module_param(maxhf, ushort, 0);
MODULE_PARM_DESC(maxhf,
"Maximum horizontal frequency [kHz], overrides EDID data");
module_param(maxvf, ushort, 0);
MODULE_PARM_DESC(maxvf,
"Maximum vertical frequency [Hz], overrides EDID data");
module_param(mode_option, charp, 0);
MODULE_PARM_DESC(mode_option,
uvesafb: the driver core uvesafb is an enhanced version of vesafb. It uses a userspace helper (v86d) to execute calls to the x86 Video BIOS functions. The driver is not limited to any specific arch and whether it works on a given arch or not depends on that arch being supported by the userspace daemon. It has been tested on x86_32 and x86_64. A single BIOS call is represented by an instance of the uvesafb_ktask structure. This structure contains a buffer, a completion struct and a uvesafb_task substructure, containing the values of the x86 registers, a flags field and a field indicating the length of the buffer. Whenever a BIOS call is made in the driver, uvesafb_exec() builds a message using the uvesafb_task substructure and the contents of the buffer. This message is then assigned a random ack number and sent to the userspace daemon using the connector interface. The message's sequence number is used as an index for the uvfb_tasks array, which provides a mapping from the messages coming from userspace to the in-kernel uvesafb_ktask structs. The userspace daemon performs the requested operation and sends a reply in the form of a uvesafb_task struct and, optionally, a buffer. The seq and ack numbers in the reply should be exactly the same as those in the request. Each message from userspace is processed by uvesafb_cn_callback() and after passing a few sanity checks leads to the completion of a BIOS call request. Signed-off-by: Michal Januszewski <spock@gentoo.org> Signed-off-by: Antonino Daplas <adaplas@gmail.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Paulo Marques <pmarques@grupopie.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:28:26 +08:00
"Specify initial video mode as \"<xres>x<yres>[-<bpp>][@<refresh>]\"");
module_param(vbemode, ushort, 0);
MODULE_PARM_DESC(vbemode,
"VBE mode number to set, overrides the 'mode' option");
module_param_string(v86d, v86d_path, PATH_MAX, 0660);
MODULE_PARM_DESC(v86d, "Path to the v86d userspace helper.");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Michal Januszewski <spock@gentoo.org>");
MODULE_DESCRIPTION("Framebuffer driver for VBE2.0+ compliant graphics boards");