1
0
Fork 0
alistair23-linux/drivers/char/agp/sgi-agp.c

339 lines
7.7 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 2003-2005 Silicon Graphics, Inc. All Rights Reserved.
*/
/*
* SGI TIOCA AGPGART routines.
*
*/
#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/pci.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 02:04:11 -06:00
#include <linux/slab.h>
#include <linux/agp_backend.h>
#include <asm/sn/addrs.h>
#include <asm/sn/io.h>
#include <asm/sn/pcidev.h>
#include <asm/sn/pcibus_provider_defs.h>
#include <asm/sn/tioca_provider.h>
#include "agp.h"
extern int agp_memory_reserved;
extern uint32_t tioca_gart_found;
extern struct list_head tioca_list;
static struct agp_bridge_data **sgi_tioca_agp_bridges;
/*
* The aperature size and related information is set up at TIOCA init time.
* Values for this table will be extracted and filled in at
* sgi_tioca_fetch_size() time.
*/
static struct aper_size_info_fixed sgi_tioca_sizes[] = {
{0, 0, 0},
};
static struct page *sgi_tioca_alloc_page(struct agp_bridge_data *bridge)
{
struct page *page;
int nid;
struct tioca_kernel *info =
(struct tioca_kernel *)bridge->dev_private_data;
nid = info->ca_closest_node;
page = alloc_pages_node(nid, GFP_KERNEL, 0);
if (!page)
return NULL;
get_page(page);
atomic_inc(&agp_bridge->current_memory_agp);
return page;
}
/*
* Flush GART tlb's. Cannot selectively flush based on memory so the mem
* arg is ignored.
*/
static void sgi_tioca_tlbflush(struct agp_memory *mem)
{
tioca_tlbflush(mem->bridge->dev_private_data);
}
/*
* Given an address of a host physical page, turn it into a valid gart
* entry.
*/
static unsigned long
sgi_tioca_mask_memory(struct agp_bridge_data *bridge, dma_addr_t addr,
int type)
{
return tioca_physpage_to_gart(addr);
}
static void sgi_tioca_agp_enable(struct agp_bridge_data *bridge, u32 mode)
{
tioca_fastwrite_enable(bridge->dev_private_data);
}
/*
* sgi_tioca_configure() doesn't have anything to do since the base CA driver
* has alreay set up the GART.
*/
static int sgi_tioca_configure(void)
{
return 0;
}
/*
* Determine gfx aperature size. This has already been determined by the
* CA driver init, so just need to set agp_bridge values accordingly.
*/
static int sgi_tioca_fetch_size(void)
{
struct tioca_kernel *info =
(struct tioca_kernel *)agp_bridge->dev_private_data;
sgi_tioca_sizes[0].size = info->ca_gfxap_size / MB(1);
sgi_tioca_sizes[0].num_entries = info->ca_gfxgart_entries;
return sgi_tioca_sizes[0].size;
}
static int sgi_tioca_create_gatt_table(struct agp_bridge_data *bridge)
{
struct tioca_kernel *info =
(struct tioca_kernel *)bridge->dev_private_data;
bridge->gatt_table_real = (u32 *) info->ca_gfxgart;
bridge->gatt_table = bridge->gatt_table_real;
bridge->gatt_bus_addr = info->ca_gfxgart_base;
return 0;
}
static int sgi_tioca_free_gatt_table(struct agp_bridge_data *bridge)
{
return 0;
}
static int sgi_tioca_insert_memory(struct agp_memory *mem, off_t pg_start,
int type)
{
int num_entries;
size_t i;
off_t j;
void *temp;
struct agp_bridge_data *bridge;
u64 *table;
bridge = mem->bridge;
if (!bridge)
return -EINVAL;
table = (u64 *)bridge->gatt_table;
temp = bridge->current_size;
switch (bridge->driver->size_type) {
case U8_APER_SIZE:
num_entries = A_SIZE_8(temp)->num_entries;
break;
case U16_APER_SIZE:
num_entries = A_SIZE_16(temp)->num_entries;
break;
case U32_APER_SIZE:
num_entries = A_SIZE_32(temp)->num_entries;
break;
case FIXED_APER_SIZE:
num_entries = A_SIZE_FIX(temp)->num_entries;
break;
case LVL2_APER_SIZE:
return -EINVAL;
default:
num_entries = 0;
break;
}
num_entries -= agp_memory_reserved / PAGE_SIZE;
if (num_entries < 0)
num_entries = 0;
if (type != 0 || mem->type != 0) {
return -EINVAL;
}
if ((pg_start + mem->page_count) > num_entries)
return -EINVAL;
j = pg_start;
while (j < (pg_start + mem->page_count)) {
if (table[j])
return -EBUSY;
j++;
}
if (!mem->is_flushed) {
bridge->driver->cache_flush();
mem->is_flushed = true;
}
for (i = 0, j = pg_start; i < mem->page_count; i++, j++) {
table[j] =
bridge->driver->mask_memory(bridge,
page_to_phys(mem->pages[i]),
mem->type);
}
bridge->driver->tlb_flush(mem);
return 0;
}
static int sgi_tioca_remove_memory(struct agp_memory *mem, off_t pg_start,
int type)
{
size_t i;
struct agp_bridge_data *bridge;
u64 *table;
bridge = mem->bridge;
if (!bridge)
return -EINVAL;
if (type != 0 || mem->type != 0) {
return -EINVAL;
}
table = (u64 *)bridge->gatt_table;
for (i = pg_start; i < (mem->page_count + pg_start); i++) {
table[i] = 0;
}
bridge->driver->tlb_flush(mem);
return 0;
}
static void sgi_tioca_cache_flush(void)
{
}
/*
* Cleanup. Nothing to do as the CA driver owns the GART.
*/
static void sgi_tioca_cleanup(void)
{
}
static struct agp_bridge_data *sgi_tioca_find_bridge(struct pci_dev *pdev)
{
struct agp_bridge_data *bridge;
list_for_each_entry(bridge, &agp_bridges, list) {
if (bridge->dev->bus == pdev->bus)
break;
}
return bridge;
}
const struct agp_bridge_driver sgi_tioca_driver = {
.owner = THIS_MODULE,
.size_type = U16_APER_SIZE,
.configure = sgi_tioca_configure,
.fetch_size = sgi_tioca_fetch_size,
.cleanup = sgi_tioca_cleanup,
.tlb_flush = sgi_tioca_tlbflush,
.mask_memory = sgi_tioca_mask_memory,
.agp_enable = sgi_tioca_agp_enable,
.cache_flush = sgi_tioca_cache_flush,
.create_gatt_table = sgi_tioca_create_gatt_table,
.free_gatt_table = sgi_tioca_free_gatt_table,
.insert_memory = sgi_tioca_insert_memory,
.remove_memory = sgi_tioca_remove_memory,
.alloc_by_type = agp_generic_alloc_by_type,
.free_by_type = agp_generic_free_by_type,
.agp_alloc_page = sgi_tioca_alloc_page,
.agp_destroy_page = agp_generic_destroy_page,
.agp_type_to_mask_type = agp_generic_type_to_mask_type,
.cant_use_aperture = true,
.needs_scratch_page = false,
.num_aperture_sizes = 1,
};
static int agp_sgi_init(void)
{
unsigned int j;
struct tioca_kernel *info;
struct pci_dev *pdev = NULL;
if (tioca_gart_found)
printk(KERN_INFO PFX "SGI TIO CA GART driver initialized.\n");
else
return 0;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 14:55:00 -06:00
sgi_tioca_agp_bridges = kmalloc_array(tioca_gart_found,
sizeof(struct agp_bridge_data *),
GFP_KERNEL);
if (!sgi_tioca_agp_bridges)
return -ENOMEM;
j = 0;
list_for_each_entry(info, &tioca_list, ca_list) {
if (list_empty(info->ca_devices))
continue;
list_for_each_entry(pdev, info->ca_devices, bus_list) {
u8 cap_ptr;
if (pdev->class != (PCI_CLASS_DISPLAY_VGA << 8))
continue;
cap_ptr = pci_find_capability(pdev, PCI_CAP_ID_AGP);
if (!cap_ptr)
continue;
}
sgi_tioca_agp_bridges[j] = agp_alloc_bridge();
printk(KERN_INFO PFX "bridge %d = 0x%p\n", j,
sgi_tioca_agp_bridges[j]);
if (sgi_tioca_agp_bridges[j]) {
sgi_tioca_agp_bridges[j]->dev = pdev;
sgi_tioca_agp_bridges[j]->dev_private_data = info;
sgi_tioca_agp_bridges[j]->driver = &sgi_tioca_driver;
sgi_tioca_agp_bridges[j]->gart_bus_addr =
info->ca_gfxap_base;
sgi_tioca_agp_bridges[j]->mode = (0x7D << 24) | /* 126 requests */
(0x1 << 9) | /* SBA supported */
(0x1 << 5) | /* 64-bit addresses supported */
(0x1 << 4) | /* FW supported */
(0x1 << 3) | /* AGP 3.0 mode */
0x2; /* 8x transfer only */
sgi_tioca_agp_bridges[j]->current_size =
sgi_tioca_agp_bridges[j]->previous_size =
(void *)&sgi_tioca_sizes[0];
agp_add_bridge(sgi_tioca_agp_bridges[j]);
}
j++;
}
agp_find_bridge = &sgi_tioca_find_bridge;
return 0;
}
static void agp_sgi_cleanup(void)
{
kfree(sgi_tioca_agp_bridges);
sgi_tioca_agp_bridges = NULL;
}
module_init(agp_sgi_init);
module_exit(agp_sgi_cleanup);
MODULE_LICENSE("GPL and additional rights");