diff options
Diffstat (limited to 'arch/x86/kernel/aperture_64.c')
| -rw-r--r-- | arch/x86/kernel/aperture_64.c | 416 |
1 files changed, 251 insertions, 165 deletions
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 00df126169b..76164e173a2 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -1,62 +1,71 @@ /* * Firmware replacement code. * - * Work around broken BIOSes that don't set an aperture or only set the - * aperture in the AGP bridge. + * Work around broken BIOSes that don't set an aperture, only set the + * aperture in the AGP bridge, or set too small aperture. + * * If all fails map the aperture over some low memory. This is cheaper than * doing bounce buffering. The memory is lost. This is done at early boot * because only the bootmem allocator can allocate 32+MB. * * 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> +#include <asm/iommu.h> #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 = 0; -int gart_iommu_aperture_allowed __initdata = 0; +int gart_iommu_aperture_disabled __initdata; +int gart_iommu_aperture_allowed __initdata; int fallback_aper_order __initdata = 1; /* 64MB */ -int fallback_aper_force __initdata = 0; +int fallback_aper_force __initdata; int fix_aperture __initdata = 1; -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; - 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; /* @@ -65,87 +74,70 @@ 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); - 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; } -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); + 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; } + /* 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 +147,28 @@ 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); - printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", - aper, 32 << *order, apsizereg); + /* + * On some sick chips, APSIZE is 0. It means it wants 4G + * so let double check that order, and lets trust AMD NB settings: + */ + 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) { + 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; + } + + 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)) + if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20)) return 0; return (u32)aper; } @@ -175,22 +181,22 @@ static __u32 __init read_agp(int num, 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. */ -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; @@ -199,24 +205,24 @@ 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; } } } - printk(KERN_INFO "No AGP bridge found\n"); + pr_info("No AGP bridge found\n"); return 0; } @@ -249,36 +255,53 @@ 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; + 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; - 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 */ + search_agp_bridge(&agp_aper_order, &valid_agp); + 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; amd_nb_bus_dev_ranges[i].dev_limit; i++) { + int bus; + int dev_base, 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_amd_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); + 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; + 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) @@ -290,98 +313,149 @@ 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 */ - printk(KERN_INFO "update e820 for GART\n"); - add_memory_region(aper_base, aper_size, E820_RESERVED); + /* reserve it, so we can reuse it in second kernel */ + 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(); } - 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; + if (valid_agp) + return; + + /* 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 = 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_amd_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 &= ~GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + } } } -void __init gart_iommu_hole_init(void) +static int __initdata printed_gart_size_msg; + +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; 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()) - return; + return -ENODEV; + + pr_info("Checking aperture...\n"); - 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; + for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) { + int bus; + int dev_base, dev_limit; + u32 ctl; - iommu_detected = 1; - gart_iommu_aperture = 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; - 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; + for (slot = dev_base; slot < dev_limit; slot++) { + if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; - printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n", - node, aper_base, aper_size >> 20); - node++; + iommu_detected = 1; + gart_iommu_aperture = 1; + x86_init.iommu.iommu_init = gart_iommu_init; - if (!aperture_valid(aper_base, aper_size)) { - fix = 1; - break; - } + ctl = read_pci_config(bus, slot, 3, + AMD64_GARTAPERTURECTL); - if ((last_aper_order && aper_order != last_aper_order) || - (last_aper_base && aper_base != last_aper_base)) { - fix = 1; - break; + /* + * 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; + + 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)) { + 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 && + max_pfn > MAX_DMA32_PFN && + !printed_gart_size_msg) { + 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 { + fix = 1; + goto out; + } + } + + 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; - - insert_aperture_resource((u32)last_aper_base, n); - } - return; + if (last_aper_base) + return 1; + return 0; } - 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 */ - } else if (swiotlb && !valid_agp) { - /* Do nothing */ - } else if ((!no_iommu && end_pfn > MAX_DMA32_PFN) || + } else if ((!no_iommu && max_pfn > MAX_DMA32_PFN) || force_iommu || valid_agp || fallback_aper_force) { - printk(KERN_ERR - "Your BIOS doesn't leave a aperture memory hole\n"); - printk(KERN_ERR - "Please enable the IOMMU option in the BIOS setup\n"); - printk(KERN_ERR - "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(); @@ -397,20 +471,32 @@ void __init gart_iommu_hole_init(void) panic("Not enough memory for aperture"); } } else { - return; + return 0; } /* Fix up the north bridges */ - for (num = 24; num < 32; num++) { - if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) - continue; + for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) { + int bus, dev_base, dev_limit; /* - * Don't enable translation yet. That is done later. - * Assume this BIOS didn't initialise the GART so - * just overwrite all previous bits + * Don't enable translation yet but enable GART IO and CPU + * accesses and set DISTLBWALKPRB since GART table memory is UC. */ - write_pci_config(0, num, 3, 0x90, aper_order<<1); - write_pci_config(0, num, 3, 0x94, aper_alloc>>25); + 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_amd_nb(read_pci_config(bus, slot, 3, 0x00))) + continue; + + 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; } |
