aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/aperture_64.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/aperture_64.c')
-rw-r--r--arch/x86/kernel/aperture_64.c241
1 files changed, 119 insertions, 122 deletions
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 676debfc170..76164e173a2 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -10,15 +10,16 @@
*
* Copyright 2002 Andi Kleen, SuSE Labs.
*/
+#define pr_fmt(fmt) "AGP: " fmt
+
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/pci_ids.h>
#include <linux/pci.h>
#include <linux/bitops.h>
-#include <linux/ioport.h>
#include <linux/suspend.h>
#include <asm/e820.h>
#include <asm/io.h>
@@ -26,7 +27,24 @@
#include <asm/gart.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
+#include <asm/x86_init.h>
+
+/*
+ * Using 512M as goal, in case kexec will load kernel_big
+ * that will do the on-position decompress, and could overlap with
+ * with the gart aperture that is used.
+ * Sequence:
+ * kernel_small
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kernel_small (gart area become e820_reserved)
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+ * So don't use 512M below as gart iommu, leave the space for kernel
+ * code for safe.
+ */
+#define GART_MIN_ADDR (512ULL << 20)
+#define GART_MAX_ADDR (1ULL << 32)
int gart_iommu_aperture;
int gart_iommu_aperture_disabled __initdata;
@@ -37,37 +55,13 @@ int fallback_aper_force __initdata;
int fix_aperture __initdata = 1;
-struct bus_dev_range {
- int bus;
- int dev_base;
- int dev_limit;
-};
-
-static struct bus_dev_range bus_dev_ranges[] __initdata = {
- { 0x00, 0x18, 0x20},
- { 0xff, 0x00, 0x20},
- { 0xfe, 0x00, 0x20}
-};
-
-static struct resource gart_resource = {
- .name = "GART",
- .flags = IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
- gart_resource.start = aper_base;
- gart_resource.end = aper_base + aper_size - 1;
- insert_resource(&iomem_resource, &gart_resource);
-}
-
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
static u32 __init allocate_aperture(void)
{
u32 aper_size;
- void *p;
+ unsigned long addr;
/* aper_size should <= 1G */
if (fallback_aper_order > 5)
@@ -80,35 +74,20 @@ static u32 __init allocate_aperture(void)
* memory. Unfortunately we cannot move it up because that would
* make the IOMMU useless.
*/
- /*
- * using 512M as goal, in case kexec will load kernel_big
- * that will do the on position decompress, and could overlap with
- * that positon with gart that is used.
- * sequende:
- * kernel_small
- * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
- * ==> kernel_small(gart area become e820_reserved)
- * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
- * ==> kerne_big (uncompressed size will be big than 64M or 128M)
- * so don't use 512M below as gart iommu, leave the space for kernel
- * code for safe
- */
- p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
- if (!p || __pa(p)+aper_size > 0xffffffff) {
- printk(KERN_ERR
- "Cannot allocate aperture memory hole (%p,%uK)\n",
- p, aper_size>>10);
- if (p)
- free_bootmem(__pa(p), aper_size);
+ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
+ aper_size, aper_size);
+ if (!addr) {
+ pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n",
+ addr, addr + aper_size - 1, aper_size >> 10);
return 0;
}
- printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
- aper_size >> 10, __pa(p));
- insert_aperture_resource((u32)__pa(p), aper_size);
- register_nosave_region((u32)__pa(p) >> PAGE_SHIFT,
- (u32)__pa(p+aper_size) >> PAGE_SHIFT);
+ memblock_reserve(addr, aper_size);
+ pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n",
+ addr, addr + aper_size - 1, aper_size >> 10);
+ register_nosave_region(addr >> PAGE_SHIFT,
+ (addr+aper_size) >> PAGE_SHIFT);
- return (u32)__pa(p);
+ return (u32)addr;
}
@@ -148,10 +127,11 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
u64 aper;
u32 old_order;
- printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func);
+ pr_info("pci 0000:%02x:%02x:%02x: AGP bridge\n", bus, slot, func);
apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14);
if (apsizereg == 0xffffffff) {
- printk(KERN_ERR "APSIZE in AGP bridge unreadable\n");
+ pr_err("pci 0000:%02x:%02x.%d: APSIZE unreadable\n",
+ bus, slot, func);
return 0;
}
@@ -175,16 +155,18 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
* On some sick chips, APSIZE is 0. It means it wants 4G
* so let double check that order, and lets trust AMD NB settings:
*/
- printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n",
- aper, 32 << old_order);
+ pr_info("pci 0000:%02x:%02x.%d: AGP aperture [bus addr %#010Lx-%#010Lx] (old size %uMB)\n",
+ bus, slot, func, aper, aper + (32ULL << (old_order + 20)) - 1,
+ 32 << old_order);
if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) {
- printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n",
- 32 << *order, apsizereg);
+ pr_info("pci 0000:%02x:%02x.%d: AGP aperture size %uMB (APSIZE %#x) is not right, using settings from NB\n",
+ bus, slot, func, 32 << *order, apsizereg);
*order = old_order;
}
- printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n",
- aper, 32 << *order, apsizereg);
+ pr_info("pci 0000:%02x:%02x.%d: AGP aperture [bus addr %#010Lx-%#010Lx] (%uMB, APSIZE %#x)\n",
+ bus, slot, func, aper, aper + (32ULL << (*order + 20)) - 1,
+ 32 << *order, apsizereg);
if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20))
return 0;
@@ -199,7 +181,7 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
* Do an PCI bus scan by hand because we're running before the PCI
* subsystem.
*
- * All K8 AGP bridges are AGPv3 compliant, so we can do this scan
+ * All AMD AGP bridges are AGPv3 compliant, so we can do this scan
* generically. It's probably overkill to always scan all slots because
* the AGP bridges should be always an own bus on the HT hierarchy,
* but do it here for future safety.
@@ -240,7 +222,7 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
}
}
}
- printk(KERN_INFO "No AGP bridge found\n");
+ pr_info("No AGP bridge found\n");
return 0;
}
@@ -273,7 +255,8 @@ void __init early_gart_iommu_check(void)
* or BIOS forget to put that in reserved.
* try to update e820 to make that region as reserved.
*/
- int i, fix, slot;
+ u32 agp_aper_order = 0;
+ int i, fix, slot, valid_agp = 0;
u32 ctl;
u32 aper_size = 0, aper_order = 0, last_aper_order = 0;
u64 aper_base = 0, last_aper_base = 0;
@@ -283,21 +266,23 @@ void __init early_gart_iommu_check(void)
return;
/* This is mostly duplicate of iommu_hole_init */
+ search_agp_bridge(&agp_aper_order, &valid_agp);
+
fix = 0;
- for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ for (i = 0; amd_nb_bus_dev_ranges[i].dev_limit; i++) {
int bus;
int dev_base, dev_limit;
- bus = bus_dev_ranges[i].bus;
- dev_base = bus_dev_ranges[i].dev_base;
- dev_limit = bus_dev_ranges[i].dev_limit;
+ bus = amd_nb_bus_dev_ranges[i].bus;
+ dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+ dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
for (slot = dev_base; slot < dev_limit; slot++) {
- if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
continue;
ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
- aper_enabled = ctl & AMD64_GARTEN;
+ aper_enabled = ctl & GARTEN;
aper_order = (ctl >> 1) & 7;
aper_size = (32 * 1024 * 1024) << aper_order;
aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
@@ -329,30 +314,31 @@ void __init early_gart_iommu_check(void)
if (e820_any_mapped(aper_base, aper_base + aper_size,
E820_RAM)) {
/* reserve it, so we can reuse it in second kernel */
- printk(KERN_INFO "update e820 for GART\n");
+ pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n",
+ aper_base, aper_base + aper_size - 1);
e820_add_region(aper_base, aper_size, E820_RESERVED);
update_e820();
}
}
- if (!fix)
+ if (valid_agp)
return;
- /* different nodes have different setting, disable them all at first*/
- for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ /* disable them all at first */
+ for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
int bus;
int dev_base, dev_limit;
- bus = bus_dev_ranges[i].bus;
- dev_base = bus_dev_ranges[i].dev_base;
- dev_limit = bus_dev_ranges[i].dev_limit;
+ bus = amd_nb_bus_dev_ranges[i].bus;
+ dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+ dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
for (slot = dev_base; slot < dev_limit; slot++) {
- if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
continue;
ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
- ctl &= ~AMD64_GARTEN;
+ ctl &= ~GARTEN;
write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
}
}
@@ -361,7 +347,7 @@ void __init early_gart_iommu_check(void)
static int __initdata printed_gart_size_msg;
-void __init gart_iommu_hole_init(void)
+int __init gart_iommu_hole_init(void)
{
u32 agp_aper_base = 0, agp_aper_order = 0;
u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -371,37 +357,52 @@ void __init gart_iommu_hole_init(void)
if (gart_iommu_aperture_disabled || !fix_aperture ||
!early_pci_allowed())
- return;
+ return -ENODEV;
- printk(KERN_INFO "Checking aperture...\n");
+ pr_info("Checking aperture...\n");
if (!fallback_aper_force)
agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp);
fix = 0;
node = 0;
- for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
+ for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
int bus;
int dev_base, dev_limit;
+ u32 ctl;
- bus = bus_dev_ranges[i].bus;
- dev_base = bus_dev_ranges[i].dev_base;
- dev_limit = bus_dev_ranges[i].dev_limit;
+ bus = amd_nb_bus_dev_ranges[i].bus;
+ dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+ dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
for (slot = dev_base; slot < dev_limit; slot++) {
- if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
continue;
iommu_detected = 1;
gart_iommu_aperture = 1;
+ x86_init.iommu.iommu_init = gart_iommu_init;
- aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+ ctl = read_pci_config(bus, slot, 3,
+ AMD64_GARTAPERTURECTL);
+
+ /*
+ * Before we do anything else disable the GART. It may
+ * still be enabled if we boot into a crash-kernel here.
+ * Reconfiguring the GART while it is enabled could have
+ * unknown side-effects.
+ */
+ ctl &= ~GARTEN;
+ write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+
+ aper_order = (ctl >> 1) & 7;
aper_size = (32 * 1024 * 1024) << aper_order;
aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
aper_base <<= 25;
- printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n",
- node, aper_base, aper_size >> 20);
+ pr_info("Node %d: aperture [bus addr %#010Lx-%#010Lx] (%uMB)\n",
+ node, aper_base, aper_base + aper_size - 1,
+ aper_size >> 20);
node++;
if (!aperture_valid(aper_base, aper_size, 64<<20)) {
@@ -412,9 +413,9 @@ void __init gart_iommu_hole_init(void)
if (!no_iommu &&
max_pfn > MAX_DMA32_PFN &&
!printed_gart_size_msg) {
- printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n");
- printk(KERN_ERR "please increase GART size in your BIOS setup\n");
- printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n");
+ pr_err("you are using iommu with agp, but GART size is less than 64MB\n");
+ pr_err("please increase GART size in your BIOS setup\n");
+ pr_err("if BIOS doesn't have that option, contact your HW vendor!\n");
printed_gart_size_msg = 1;
}
} else {
@@ -435,12 +436,9 @@ void __init gart_iommu_hole_init(void)
out:
if (!fix && !fallback_aper_force) {
- if (last_aper_base) {
- unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
- insert_aperture_resource((u32)last_aper_base, n);
- }
- return;
+ if (last_aper_base)
+ return 1;
+ return 0;
}
if (!fallback_aper_force) {
@@ -450,19 +448,14 @@ out:
if (aper_alloc) {
/* Got the aperture from the AGP bridge */
- } else if (swiotlb && !valid_agp) {
- /* Do nothing */
} else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) ||
force_iommu ||
valid_agp ||
fallback_aper_force) {
- printk(KERN_INFO
- "Your BIOS doesn't leave a aperture memory hole\n");
- printk(KERN_INFO
- "Please enable the IOMMU option in the BIOS setup\n");
- printk(KERN_INFO
- "This costs you %d MB of RAM\n",
- 32 << fallback_aper_order);
+ pr_info("Your BIOS doesn't leave a aperture memory hole\n");
+ pr_info("Please enable the IOMMU option in the BIOS setup\n");
+ pr_info("This costs you %dMB of RAM\n",
+ 32 << fallback_aper_order);
aper_order = fallback_aper_order;
aper_alloc = allocate_aperture();
@@ -478,28 +471,32 @@ out:
panic("Not enough memory for aperture");
}
} else {
- return;
+ return 0;
}
/* Fix up the north bridges */
- for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
- int bus;
- int dev_base, dev_limit;
-
- bus = bus_dev_ranges[i].bus;
- dev_base = bus_dev_ranges[i].dev_base;
- dev_limit = bus_dev_ranges[i].dev_limit;
+ for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
+ int bus, dev_base, dev_limit;
+
+ /*
+ * Don't enable translation yet but enable GART IO and CPU
+ * accesses and set DISTLBWALKPRB since GART table memory is UC.
+ */
+ u32 ctl = aper_order << 1;
+
+ bus = amd_nb_bus_dev_ranges[i].bus;
+ dev_base = amd_nb_bus_dev_ranges[i].dev_base;
+ dev_limit = amd_nb_bus_dev_ranges[i].dev_limit;
for (slot = dev_base; slot < dev_limit; slot++) {
- if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+ if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
continue;
- /* Don't enable translation yet. That is done later.
- Assume this BIOS didn't initialise the GART so
- just overwrite all previous bits */
- write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+ write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
}
}
set_up_gart_resume(aper_order, aper_alloc);
+
+ return 1;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-06 20:05:27 +0000