diff options
| -rw-r--r-- | arch/x86/kernel/aperture_64.c | 307 | ||||
| -rw-r--r-- | arch/x86/kernel/pci-dma.c | 11 | ||||
| -rw-r--r-- | arch/x86/kernel/pci-gart_64.c | 78 | ||||
| -rw-r--r-- | drivers/char/agp/amd64-agp.c | 85 | ||||
| -rw-r--r-- | include/asm-x86/gart.h | 63 |
5 files changed, 348 insertions, 196 deletions
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 479926d9e004..e819362c7068 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -35,6 +35,18 @@ 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, @@ -55,8 +67,9 @@ static u32 __init allocate_aperture(void) u32 aper_size; void *p; - if (fallback_aper_order > 7) - fallback_aper_order = 7; + /* aper_size should <= 1G */ + if (fallback_aper_order > 5) + fallback_aper_order = 5; aper_size = (32 * 1024 * 1024) << fallback_aper_order; /* @@ -65,7 +78,20 @@ static u32 __init allocate_aperture(void) * memory. Unfortunately we cannot move it up because that would * make the IOMMU useless. */ - p = __alloc_bootmem_nopanic(aper_size, aper_size, 0); + /* + * 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", @@ -83,69 +109,53 @@ static u32 __init allocate_aperture(void) return (u32)__pa(p); } -static int __init aperture_valid(u64 aper_base, u32 aper_size) -{ - if (!aper_base) - return 0; - - if (aper_base + aper_size > 0x100000000UL) { - printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n"); - return 0; - } - if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { - printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n"); - return 0; - } - if (aper_size < 64*1024*1024) { - printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20); - return 0; - } - - return 1; -} /* Find a PCI capability */ -static __u32 __init find_cap(int num, int slot, int func, int cap) +static u32 __init find_cap(int bus, int slot, int func, int cap) { int bytes; u8 pos; - if (!(read_pci_config_16(num, slot, func, PCI_STATUS) & + if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) & PCI_STATUS_CAP_LIST)) return 0; - pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST); + pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST); for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) { u8 id; pos &= ~3; - id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID); + id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID); if (id == 0xff) break; if (id == cap) return pos; - pos = read_pci_config_byte(num, slot, func, + pos = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_NEXT); } return 0; } /* Read a standard AGPv3 bridge header */ -static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) +static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) { u32 apsize; u32 apsizereg; int nbits; u32 aper_low, aper_hi; u64 aper; + u32 old_order; - printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func); - apsizereg = read_pci_config_16(num, slot, func, cap + 0x14); + printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\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"); return 0; } + /* old_order could be the value from NB gart setting */ + old_order = *order; + apsize = apsizereg & 0xfff; /* Some BIOS use weird encodings not in the AGPv3 table. */ if (apsize & 0xff) @@ -155,14 +165,26 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) if ((int)*order < 0) /* < 32MB */ *order = 0; - aper_low = read_pci_config(num, slot, func, 0x10); - aper_hi = read_pci_config(num, slot, func, 0x14); + aper_low = read_pci_config(bus, slot, func, 0x10); + aper_hi = read_pci_config(bus, slot, func, 0x14); aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32); + /* + * 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); + 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); + *order = old_order; + } + printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", aper, 32 << *order, apsizereg); - if (!aperture_valid(aper, (32*1024*1024) << *order)) + if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20)) return 0; return (u32)aper; } @@ -180,17 +202,17 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) * the AGP bridges should be always an own bus on the HT hierarchy, * but do it here for future safety. */ -static __u32 __init search_agp_bridge(u32 *order, int *valid_agp) +static u32 __init search_agp_bridge(u32 *order, int *valid_agp) { - int num, slot, func; + int bus, slot, func; /* Poor man's PCI discovery */ - for (num = 0; num < 256; num++) { + for (bus = 0; bus < 256; bus++) { for (slot = 0; slot < 32; slot++) { for (func = 0; func < 8; func++) { u32 class, cap; u8 type; - class = read_pci_config(num, slot, func, + class = read_pci_config(bus, slot, func, PCI_CLASS_REVISION); if (class == 0xffffffff) break; @@ -199,17 +221,17 @@ static __u32 __init search_agp_bridge(u32 *order, int *valid_agp) case PCI_CLASS_BRIDGE_HOST: case PCI_CLASS_BRIDGE_OTHER: /* needed? */ /* AGP bridge? */ - cap = find_cap(num, slot, func, + cap = find_cap(bus, slot, func, PCI_CAP_ID_AGP); if (!cap) break; *valid_agp = 1; - return read_agp(num, slot, func, cap, + return read_agp(bus, slot, func, cap, order); } /* No multi-function device? */ - type = read_pci_config_byte(num, slot, func, + type = read_pci_config_byte(bus, slot, func, PCI_HEADER_TYPE); if (!(type & 0x80)) break; @@ -249,36 +271,50 @@ 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 fix, num; + int i, fix, slot; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; u64 aper_base = 0, last_aper_base = 0; - int aper_enabled = 0, last_aper_enabled = 0; + int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; if (!early_pci_allowed()) return; + /* This is mostly duplicate of iommu_hole_init */ fix = 0; - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; - - ctl = read_pci_config(0, num, 3, 0x90); - aper_enabled = ctl & 1; - aper_order = (ctl >> 1) & 7; - aper_size = (32 * 1024 * 1024) << aper_order; - aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff; - aper_base <<= 25; - - if ((last_aper_order && aper_order != last_aper_order) || - (last_aper_base && aper_base != last_aper_base) || - (last_aper_enabled && aper_enabled != last_aper_enabled)) { - fix = 1; - break; + 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 (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); + aper_enabled = ctl & AMD64_GARTEN; + 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; + + if (last_valid) { + if ((aper_order != last_aper_order) || + (aper_base != last_aper_base) || + (aper_enabled != last_aper_enabled)) { + fix = 1; + break; + } + } + + last_aper_order = aper_order; + last_aper_base = aper_base; + last_aper_enabled = aper_enabled; + last_valid = 1; } - last_aper_order = aper_order; - last_aper_base = aper_base; - last_aper_enabled = aper_enabled; } if (!fix && !aper_enabled) @@ -290,32 +326,46 @@ void __init early_gart_iommu_check(void) if (gart_fix_e820 && !fix && aper_enabled) { if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { - /* reserved it, so we can resuse it in second kernel */ + /* reserve it, so we can reuse it in second kernel */ printk(KERN_INFO "update e820 for GART\n"); add_memory_region(aper_base, aper_size, E820_RESERVED); update_e820(); } - return; } + if (!fix) + return; + /* different nodes have different setting, disable them all at first*/ - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; + 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 (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; - ctl = read_pci_config(0, num, 3, 0x90); - ctl &= ~1; - write_pci_config(0, num, 3, 0x90, ctl); + ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); + ctl &= ~AMD64_GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + } } } +static int __initdata printed_gart_size_msg; + void __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; u64 aper_base, last_aper_base = 0; - int fix, num, valid_agp = 0; - int node; + int fix, slot, valid_agp = 0; + int i, node; if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) @@ -323,38 +373,63 @@ void __init gart_iommu_hole_init(void) printk(KERN_INFO "Checking aperture...\n"); + if (!fallback_aper_force) + agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + fix = 0; node = 0; - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; - - iommu_detected = 1; - gart_iommu_aperture = 1; - - aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7; - aper_size = (32 * 1024 * 1024) << aper_order; - aper_base = read_pci_config(0, num, 3, 0x94) & 0x7fff; - aper_base <<= 25; - - printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n", - node, aper_base, aper_size >> 20); - node++; - - if (!aperture_valid(aper_base, aper_size)) { - fix = 1; - break; - } + 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 (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + iommu_detected = 1; + gart_iommu_aperture = 1; + + aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 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); + node++; + + if (!aperture_valid(aper_base, aper_size, 64<<20)) { + if (valid_agp && agp_aper_base && + agp_aper_base == aper_base && + agp_aper_order == aper_order) { + /* the same between two setting from NB and agp */ + if (!no_iommu && end_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"); + printed_gart_size_msg = 1; + } + } else { + fix = 1; + goto out; + } + } - if ((last_aper_order && aper_order != last_aper_order) || - (last_aper_base && aper_base != last_aper_base)) { - fix = 1; - break; + if ((last_aper_order && aper_order != last_aper_order) || + (last_aper_base && aper_base != last_aper_base)) { + fix = 1; + goto out; + } + last_aper_order = aper_order; + last_aper_base = aper_base; } - last_aper_order = aper_order; - last_aper_base = aper_base; } +out: if (!fix && !fallback_aper_force) { if (last_aper_base) { unsigned long n = (32 * 1024 * 1024) << last_aper_order; @@ -364,8 +439,10 @@ void __init gart_iommu_hole_init(void) return; } - if (!fallback_aper_force) - aper_alloc = search_agp_bridge(&aper_order, &valid_agp); + if (!fallback_aper_force) { + aper_alloc = agp_aper_base; + aper_order = agp_aper_order; + } if (aper_alloc) { /* Got the aperture from the AGP bridge */ @@ -401,16 +478,24 @@ void __init gart_iommu_hole_init(void) } /* Fix up the north bridges */ - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 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(0, num, 3, 0x90, aper_order<<1); - write_pci_config(0, num, 3, 0x94, aper_alloc>>25); + 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 (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_k8_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_GARTAPERTUREBASE, aper_alloc >> 25); + } } + + set_up_gart_resume(aper_order, aper_alloc); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index dc00a1331ace..09c4dac11b5f 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -77,10 +77,14 @@ void __init dma32_reserve_bootmem(void) if (end_pfn <= MAX_DMA32_PFN) return; + /* + * check aperture_64.c allocate_aperture() for reason about + * using 512M as goal + */ align = 64ULL<<20; size = round_up(dma32_bootmem_size, align); dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align, - __pa(MAX_DMA_ADDRESS)); + 512ULL<<20); if (dma32_bootmem_ptr) dma32_bootmem_size = size; else @@ -88,7 +92,6 @@ void __init dma32_reserve_bootmem(void) } static void __init dma32_free_bootmem(void) { - int node; if (end_pfn <= MAX_DMA32_PFN) return; @@ -96,9 +99,7 @@ static void __init dma32_free_bootmem(void) if (!dma32_bootmem_ptr) return; - for_each_online_node(node) - free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr), - dma32_bootmem_size); + free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size); dma32_bootmem_ptr = NULL; dma32_bootmem_size = 0; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index aa8ec928caa8..f505c3890358 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -534,8 +534,8 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size) unsigned aper_size = 0, aper_base_32, aper_order; u64 aper_base; - pci_read_config_dword(dev, 0x94, &aper_base_32); - pci_read_config_dword(dev, 0x90, &aper_order); + pci_read_config_dword(dev, AMD64_GARTAPERTUREBASE, &aper_base_32); + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &aper_order); aper_order = (aper_order >> 1) & 7; aper_base = aper_base_32 & 0x7fff; @@ -549,14 +549,63 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size) return aper_base; } +static void enable_gart_translations(void) +{ + int i; + + for (i = 0; i < num_k8_northbridges; i++) { + struct pci_dev *dev = k8_northbridges[i]; + + enable_gart_translation(dev, __pa(agp_gatt_table)); + } +} + +/* + * If fix_up_north_bridges is set, the north bridges have to be fixed up on + * resume in the same way as they are handled in gart_iommu_hole_init(). + */ +static bool fix_up_north_bridges; +static u32 aperture_order; +static u32 aperture_alloc; + +void set_up_gart_resume(u32 aper_order, u32 aper_alloc) +{ + fix_up_north_bridges = true; + aperture_order = aper_order; + aperture_alloc = aper_alloc; +} + static int gart_resume(struct sys_device *dev) { + printk(KERN_INFO "PCI-DMA: Resuming GART IOMMU\n"); + + if (fix_up_north_bridges) { + int i; + + printk(KERN_INFO "PCI-DMA: Restoring GART aperture settings\n"); + + for (i = 0; i < num_k8_northbridges; i++) { + struct pci_dev *dev = k8_northbridges[i]; + + /* + * Don't enable translations just yet. That is the next + * step. Restore the pre-suspend aperture settings. + */ + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, + aperture_order << 1); + pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, + aperture_alloc >> 25); + } + } + + enable_gart_translations(); + return 0; } static int gart_suspend(struct sys_device *dev, pm_message_t state) { - return -EINVAL; + return 0; } static struct sysdev_class gart_sysdev_class = { @@ -614,27 +663,14 @@ static __init int init_k8_gatt(struct agp_kern_info *info) memset(gatt, 0, gatt_size); agp_gatt_table = gatt; - for (i = 0; i < num_k8_northbridges; i++) { - u32 gatt_reg; - u32 ctl; - - dev = k8_northbridges[i]; - gatt_reg = __pa(gatt) >> 12; - gatt_reg <<= 4; - pci_write_config_dword(dev, 0x98, gatt_reg); - pci_read_config_dword(dev, 0x90, &ctl); - - ctl |= 1; - ctl &= ~((1<<4) | (1<<5)); - - pci_write_config_dword(dev, 0x90, ctl); - } + enable_gart_translations(); error = sysdev_class_register(&gart_sysdev_class); if (!error) error = sysdev_register(&device_gart); if (error) panic("Could not register gart_sysdev -- would corrupt data on next suspend"); + flush_gart(); printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n", @@ -677,11 +713,11 @@ void gart_iommu_shutdown(void) u32 ctl; dev = k8_northbridges[i]; - pci_read_config_dword(dev, 0x90, &ctl); + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); - ctl &= ~1; + ctl &= ~GARTEN; - pci_write_config_dword(dev, 0x90, ctl); + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); } } diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index 13665db363d6..481ffe87c716 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -16,28 +16,9 @@ #include <asm/page.h> /* PAGE_SIZE */ #include <asm/e820.h> #include <asm/k8.h> +#include <asm/gart.h> #include "agp.h" -/* PTE bits. */ -#define GPTE_VALID 1 -#define GPTE_COHERENT 2 - -/* Aperture control register bits. */ -#define GARTEN (1<<0) -#define DISGARTCPU (1<<4) -#define DISGARTIO (1<<5) - -/* GART cache control register bits. */ -#define INVGART (1<<0) -#define GARTPTEERR (1<<1) - -/* K8 On-cpu GART registers */ -#define AMD64_GARTAPERTURECTL 0x90 -#define AMD64_GARTAPERTUREBASE 0x94 -#define AMD64_GARTTABLEBASE 0x98 -#define AMD64_GARTCACHECTL 0x9c -#define AMD64_GARTEN (1<<0) - /* NVIDIA K8 registers */ #define NVIDIA_X86_64_0_APBASE 0x10 #define NVIDIA_X86_64_1_APBASE1 0x50 @@ -165,29 +146,18 @@ static int amd64_fetch_size(void) * In a multiprocessor x86-64 system, this function gets * called once for each CPU. */ -static u64 amd64_configure (struct pci_dev *hammer, u64 gatt_table) +static u64 amd64_configure(struct pci_dev *hammer, u64 gatt_table) { u64 aperturebase; u32 tmp; - u64 addr, aper_base; + u64 aper_base; /* Address to map to */ - pci_read_config_dword (hammer, AMD64_GARTAPERTUREBASE, &tmp); + pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp); aperturebase = tmp << 25; aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK); - /* address of the mappings table */ - addr = (u64) gatt_table; - addr >>= 12; - tmp = (u32) addr<<4; - tmp &= ~0xf; - pci_write_config_dword (hammer, AMD64_GARTTABLEBASE, tmp); - - /* Enable GART translation for this hammer. */ - pci_read_config_dword(hammer, AMD64_GARTAPERTURECTL, &tmp); - tmp |= GARTEN; - tmp &= ~(DISGARTCPU | DISGARTIO); - pci_write_config_dword(hammer, AMD64_GARTAPERTURECTL, tmp); + enable_gart_translation(hammer, gatt_table); return aper_base; } @@ -226,9 +196,9 @@ static void amd64_cleanup(void) for (i = 0; i < num_k8_northbridges; i++) { struct pci_dev *dev = k8_northbridges[i]; /* disable gart translation */ - pci_read_config_dword (dev, AMD64_GARTAPERTURECTL, &tmp); + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &tmp); tmp &= ~AMD64_GARTEN; - pci_write_config_dword (dev, AMD64_GARTAPERTURECTL, tmp); + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, tmp); } } @@ -258,24 +228,10 @@ static const struct agp_bridge_driver amd_8151_driver = { }; /* Some basic sanity checks for the aperture. */ -static int __devinit aperture_valid(u64 aper, u32 size) +static int __devinit agp_aperture_valid(u64 aper, u32 size) { - if (aper == 0) { - printk(KERN_ERR PFX "No aperture\n"); - return 0; - } - if (size < 32*1024*1024) { - printk(KERN_ERR PFX "Aperture too small (%d MB)\n", size>>20); - return 0; - } - if ((u64)aper + size > 0x100000000ULL) { - printk(KERN_ERR PFX "Aperture out of bounds\n"); + if (!aperture_valid(aper, size, 32*1024*1024)) return 0; - } - if (e820_any_mapped(aper, aper + size, E820_RAM)) { - printk(KERN_ERR PFX "Aperture pointing to RAM\n"); - return 0; - } /* Request the Aperture. This catches cases when someone else already put a mapping in there - happens with some very broken BIOS @@ -308,11 +264,11 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, u32 nb_order, nb_base; u16 apsize; - pci_read_config_dword(nb, 0x90, &nb_order); + pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order); nb_order = (nb_order >> 1) & 7; - pci_read_config_dword(nb, 0x94, &nb_base); + pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base); nb_aper = nb_base << 25; - if (aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) { + if (agp_aperture_valid(nb_aper, (32*1024*1024)<<nb_order)) { return 0; } @@ -331,12 +287,23 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, pci_read_config_dword(agp, 0x10, &aper_low); pci_read_config_dword(agp, 0x14, &aper_hi); aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32); + + /* + * On some sick chips APSIZE is 0. This means it wants 4G + * so let double check that order, and lets trust the AMD NB settings + */ + if (order >=0 && aper + (32ULL<<(20 + order)) > 0x100000000ULL) { + printk(KERN_INFO "Aperture size %u MB is not right, using settings from NB\n", + 32 << order); + order = nb_order; + } + printk(KERN_INFO PFX "Aperture from AGP @ %Lx size %u MB\n", aper, 32 << order); - if (order < 0 || !aperture_valid(aper, (32*1024*1024)<<order)) + if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order)) return -1; - pci_write_config_dword(nb, 0x90, order << 1); - pci_write_config_dword(nb, 0x94, aper >> 25); + pci_write_config_dword(nb, AMD64_GARTAPERTURECTL, order << 1); + pci_write_config_dword(nb, AMD64_GARTAPERTUREBASE, aper >> 25); return 0; } diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h index 90958ed993fa..eeca2f51fd8f 100644 --- a/include/asm-x86/gart.h +++ b/include/asm-x86/gart.h @@ -1,16 +1,20 @@ #ifndef _ASM_X8664_IOMMU_H #define _ASM_X8664_IOMMU_H 1 +#include <asm/e820.h> + extern void pci_iommu_shutdown(void); extern void no_iommu_init(void); extern int force_iommu, no_iommu; extern int iommu_detected; +extern int agp_amd64_init(void); #ifdef CONFIG_GART_IOMMU extern void gart_iommu_init(void); extern void gart_iommu_shutdown(void); extern void __init gart_parse_options(char *); extern void early_gart_iommu_check(void); extern void gart_iommu_hole_init(void); +extern void set_up_gart_resume(u32, u32); extern int fallback_aper_order; extern int fallback_aper_force; extern int gart_iommu_aperture; @@ -31,4 +35,63 @@ static inline void gart_iommu_shutdown(void) #endif +/* PTE bits. */ +#define GPTE_VALID 1 +#define GPTE_COHERENT 2 + +/* Aperture control register bits. */ +#define GARTEN (1<<0) +#define DISGARTCPU (1<<4) +#define DISGARTIO (1<<5) + +/* GART cache control register bits. */ +#define INVGART (1<<0) +#define GARTPTEERR (1<<1) + +/* K8 On-cpu GART registers */ +#define AMD64_GARTAPERTURECTL 0x90 +#define AMD64_GARTAPERTUREBASE 0x94 +#define AMD64_GARTTABLEBASE 0x98 +#define AMD64_GARTCACHECTL 0x9c +#define AMD64_GARTEN (1<<0) + +static inline void enable_gart_translation(struct pci_dev *dev, u64 addr) +{ + u32 tmp, ctl; + + /* address of the mappings table */ + addr >>= 12; + tmp = (u32) addr<<4; + tmp &= ~0xf; + pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp); + + /* Enable GART translation for this hammer. */ + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); + ctl |= GARTEN; + ctl &= ~(DISGARTCPU | DISGARTIO); + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); +} + +static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) +{ + if (!aper_base) + return 0; + + if (aper_base + aper_size > 0x100000000ULL) { + printk(KERN_ERR "Aperture beyond 4GB. Ignoring.\n"); + return 0; + } + if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { + printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n"); + return 0; + } + if (aper_size < min_size) { + printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n", + aper_size>>20, min_size>>20); + return 0; + } + + return 1; +} + #endif |