From 1edc1ab3f68168ec6815e6d630f38948a6da005a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 13 Apr 2008 01:11:41 -0700 Subject: x86: agp_gart size checking for buggy device while looking at Rafael J. Wysocki's system boot log, I found a funny printout: Node 0: aperture @ de000000 size 32 MB Aperture too small (32 MB) AGP bridge at 00:04:00 Aperture from AGP @ de000000 size 4096 MB (APSIZE 0) Aperture too small (0 MB) Your BIOS doesn't leave a aperture memory hole Please enable the IOMMU option in the BIOS setup This costs you 64 MB of RAM Mapping aperture over 65536 KB of RAM @ 4000000 ... agpgart: Detected AGP bridge 20 agpgart: Aperture pointing to RAM agpgart: Aperture from AGP @ de000000 size 4096 MB agpgart: Aperture too small (0 MB) agpgart: No usable aperture found. agpgart: Consider rebooting with iommu=memaper=2 to get a good aperture. it means BIOS allocated the correct gart on the NB and AGP bridge, but because a bug in the silicon (the agp bridge reports the wrong order, it wants 4G instead) the kernel will reject that allocation. Also, because the size is only 32MB, and we try to get another 64M for gart, late fix_northbridge can not revert that change because it still reads the wrong size from agp bridge. So try to double check the order value from the agp bridge, before calling aperture_valid(). [ mingo@elte.hu: 32-bit fix. ] Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 479926d9e00..2e93b3132df 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -138,6 +138,7 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) 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); @@ -146,6 +147,9 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) 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) @@ -159,6 +163,16 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) aper_hi = read_pci_config(num, 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: + */ + if (aper + (32UL<<(20 + *order)) > 0x100000000UL) { + 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); -- cgit v1.2.3 From 8c9fd91a0dc503f085169d44f4360be025f75224 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 13 Apr 2008 18:42:31 -0700 Subject: x86: checking aperture size order some systems are using 32M for gart and agp when memory is less than 4G. Kernel will reject and try to allcate another 64M that is not needed, and we will waste 64M of perfectly good RAM. this patch adds a workaround by checking aper_base/order between NB and agp bridge. If they are the same, and memory size is less than 4G, it will allow it. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 47 ++++++++++++++++++++++++++++++++----------- 1 file changed, 35 insertions(+), 12 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 2e93b3132df..8c325b7f2d9 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -83,7 +83,7 @@ static u32 __init allocate_aperture(void) return (u32)__pa(p); } -static int __init aperture_valid(u64 aper_base, u32 aper_size) +static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) { if (!aper_base) return 0; @@ -96,8 +96,9 @@ static int __init aperture_valid(u64 aper_base, u32 aper_size) 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); + 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; } @@ -167,7 +168,9 @@ static __u32 __init read_agp(int num, 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: */ - if (aper + (32UL<<(20 + *order)) > 0x100000000UL) { + 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; @@ -176,7 +179,7 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *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; } @@ -302,8 +305,8 @@ void __init early_gart_iommu_check(void) fix = 1; if (gart_fix_e820 && !fix && aper_enabled) { - if (e820_any_mapped(aper_base, aper_base + aper_size, - E820_RAM)) { + if (!e820_all_mapped(aper_base, aper_base + aper_size, + E820_RESERVED)) { /* 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); @@ -324,8 +327,11 @@ void __init early_gart_iommu_check(void) } +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; @@ -337,6 +343,9 @@ 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++) { @@ -355,9 +364,21 @@ void __init gart_iommu_hole_init(void) node, aper_base, aper_size >> 20); node++; - if (!aperture_valid(aper_base, aper_size)) { - fix = 1; - break; + 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; + break; + } } if ((last_aper_order && aper_order != last_aper_order) || @@ -378,8 +399,10 @@ 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 */ -- cgit v1.2.3 From 7677b2ef6c0c4fddc84f6473f3863f40eb71821b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 14 Apr 2008 20:40:37 -0700 Subject: x86_64: allocate gart aperture from 512M because we try to reserve dma32 early, so we have chance to get aperture from 64M. with some sequence aperture allocated from RAM, could become E820_RESERVED. and then if doing a kexec with a big kernel that uncompressed size is above 64M we could have a range conflict with still using gart. So allocate gart aperture from 512M instead. Also change the fallback_aper_order to 5, because we don't have chance to get 2G or 4G aperture. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 8c325b7f2d9..c63f8d9fad3 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -55,8 +55,9 @@ 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 +66,20 @@ 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", -- cgit v1.2.3 From 55c0d721df80dcc505dc888e85d4ca51ea150ce9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 19 Apr 2008 01:31:11 -0700 Subject: x86: clean up aperture_64.c 1. use symbolic register names where appropriate. 2. num to bus or slot changing 3. handle for new opteron for bus other than 0 Signed-off-by: Yinghai Lu Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 230 +++++++++++++++++++++++++----------------- 1 file changed, 139 insertions(+), 91 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index c63f8d9fad3..02f4dbaa4df 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, @@ -120,33 +132,33 @@ static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) } /* 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; @@ -155,8 +167,8 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) 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; @@ -174,8 +186,8 @@ 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); /* @@ -213,15 +225,15 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order) */ 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; @@ -230,17 +242,17 @@ 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; @@ -280,38 +292,49 @@ 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 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 i; if (!early_pci_allowed()) return; 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_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; + goto out; + } + last_aper_order = aper_order; + last_aper_base = aper_base; + last_aper_enabled = aper_enabled; } - last_aper_order = aper_order; - last_aper_base = aper_base; - last_aper_enabled = aper_enabled; } +out: if (!fix && !aper_enabled) return; @@ -330,13 +353,22 @@ void __init early_gart_iommu_check(void) } /* 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; - ctl = read_pci_config(0, num, 3, 0x90); - ctl &= ~1; - write_pci_config(0, num, 3, 0x90, ctl); + 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); + ctl &= ~AMD64_GARTEN; + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); + } } } @@ -348,8 +380,8 @@ 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()) @@ -362,48 +394,58 @@ void __init gart_iommu_hole_init(void) 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, 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; + 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; } - } else { - fix = 1; - break; } - } - 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; @@ -452,16 +494,22 @@ 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); + } } } -- cgit v1.2.3 From 0abbc78a0137fee60ef092f0b20a3d3d7e7e0cc2 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Tue, 20 May 2008 16:27:17 +0200 Subject: x86, aperture_64: use symbolic constants Factor-out common aperture_valid code. Signed-off-by: Pavel Machek Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 02f4dbaa4df..5373f7834d8 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -109,27 +109,6 @@ static u32 __init allocate_aperture(void) return (u32)__pa(p); } -static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_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 < min_size) { - printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n", - aper_size>>20, min_size>>20); - return 0; - } - - return 1; -} /* Find a PCI capability */ static __u32 __init find_cap(int bus, int slot, int func, int cap) @@ -344,7 +323,7 @@ out: if (gart_fix_e820 && !fix && aper_enabled) { if (!e820_all_mapped(aper_base, aper_base + aper_size, E820_RESERVED)) { - /* 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(); -- cgit v1.2.3 From dd564d0cf08686cf0cc332bf9d48cba5b26a8171 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Tue, 27 May 2008 18:03:56 +0200 Subject: x86: aperture_64.c: cleanups Some small cleanups for aperture_64.c; they should not really change any code. Signed-off-by: Pavel Machek Cc: Dave Jones Cc: Andi Kleen Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 5373f7834d8..6eea42eb287 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -111,7 +111,7 @@ static u32 __init allocate_aperture(void) /* Find a PCI capability */ -static __u32 __init find_cap(int bus, int slot, int func, int cap) +static u32 __init find_cap(int bus, int slot, int func, int cap) { int bytes; u8 pos; @@ -137,7 +137,7 @@ static __u32 __init find_cap(int bus, int slot, int func, int cap) } /* Read a standard AGPv3 bridge header */ -static __u32 __init read_agp(int bus, 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; @@ -202,7 +202,7 @@ static __u32 __init read_agp(int bus, 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 bus, slot, func; -- cgit v1.2.3 From fa5b8a30cf03520737e9a0ee2ee03a61b2eccf05 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Mon, 26 May 2008 20:40:47 +0200 Subject: aperture_64.c: duplicated code, buggy? Hi! void __init early_gart_iommu_check(void) contains for (num = 24; num < 32; num++) { if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00))) continue; loop, with very similar loop duplicated in void __init gart_iommu_hole_init(void) . First copy of a loop seems to be buggy, too. It uses 0 as a "nothing set" value, which may actually bite us in last_aper_enabled case (because it may be often zero). (Beware, it is hard to test this patch, because this code has about 2^8 different code paths, depending on hardware and cmdline settings). Plus, the second loop does not check for consistency of aper_enabled. Should it? Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 6eea42eb287..e5b17f910f8 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -271,16 +271,16 @@ 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, slot; + 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 i; + 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 (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; @@ -301,19 +301,22 @@ void __init early_gart_iommu_check(void) aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 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; - goto out; + 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; } } -out: if (!fix && !aper_enabled) return; -- cgit v1.2.3 From 4f384f8bcdb5d618a0a68fb84c809e602c798b8f Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Mon, 26 May 2008 21:17:30 +0200 Subject: x86: aperture_64.c: corner case wrong If fix == 0, aper_enabled == 1, gart_fix_e820 == 0 if (!fix && !aper_enabled) return; if (gart_fix_e820 && !fix && aper_enabled) { 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"); add_memory_region(aper_base, aper_size, E820_RESERVED); update_e820(); } return; } /* different nodes have different setting, disable them all atfirst*/ we'll fall back here and disable all the settings, even when they were all consistent. What about this? (I hope it compiles...) Signed-off-by: Pavel Machek Cc: Dave Jones Cc: Andi Kleen Signed-off-by: Thomas Gleixner --- arch/x86/kernel/aperture_64.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index e5b17f910f8..eb20f168c0f 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -331,9 +331,11 @@ void __init early_gart_iommu_check(void) 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 (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { int bus; -- cgit v1.2.3 From 6703f6d10dcd3316e03641a5ecaa6c8a04374d98 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 10 Jun 2008 00:10:48 +0200 Subject: x86, gart: add resume handling If GART IOMMU is used on an AMD64 system, the northbridge registers related to it should be restored during resume so that memory is not corrupted. Make gart_resume() handle that as appropriate. Ref. http://lkml.org/lkml/2008/5/25/96 and the following thread. Signed-off-by: Rafael J. Wysocki Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index eb20f168c0f..3409abb231a 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -496,4 +496,6 @@ out: write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25); } } + + set_up_gart_resume(aper_order, aper_alloc); } -- cgit v1.2.3 From 0754557d72c1fbfc5fcfd5235e7c23ae6f77248c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 21 Jun 2008 03:50:47 -0700 Subject: x86: change early_gart_iommu_check() back to any_mapped Kevin Winchester reported a GART related direct rendering failure against linux-next-20080611, which shows up via these log entries: PCI: Using ACPI for IRQ routing PCI: Cannot allocate resource region 0 of device 0000:00:00.0 agpgart: Detected AGP bridge 0 agpgart: Aperture conflicts with PCI mapping. agpgart: Aperture from AGP @ e0000000 size 128 MB agpgart: Aperture conflicts with PCI mapping. agpgart: No usable aperture found. agpgart: Consider rebooting with iommu=memaper=2 to get a good aperture. instead of the expected: PCI: Using ACPI for IRQ routing agpgart: Detected AGP bridge 0 agpgart: Aperture from AGP @ e0000000 size 128 MB Kevin bisected it down to this change in tip/x86/gart: "x86: checking aperture size order". agp check is using request_mem_region(), and could fail if e820 is reserved... change it back to e820_any_mapped(). Reported-and-bisected-by: "Kevin Winchester" Signed-off-by: Yinghai Lu Tested-by: Kevin Winchester Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3409abb231a..e819362c706 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -324,8 +324,8 @@ void __init early_gart_iommu_check(void) fix = 1; if (gart_fix_e820 && !fix && aper_enabled) { - if (!e820_all_mapped(aper_base, aper_base + aper_size, - E820_RESERVED)) { + 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"); add_memory_region(aper_base, aper_size, E820_RESERVED); -- cgit v1.2.3 From d0be6bdea103b8d04c8a3495538b7c0011ae4129 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 15 Jun 2008 18:58:51 -0700 Subject: x86: rename two e820 related functions rename update_memory_range to e820_update_range rename add_memory_region to e820_add_region to make it more clear that they are about e820 map operations. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 479926d9e00..66b140932b2 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -292,7 +292,7 @@ void __init early_gart_iommu_check(void) 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); + e820_add_region(aper_base, aper_size, E820_RESERVED); update_e820(); } return; -- cgit v1.2.3 From c987d12f8455b19b3b057d63bac3de161bd809fc Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 24 Jun 2008 22:14:09 -0700 Subject: x86: remove end_pfn in 64bit and use max_pfn directly. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 600470d464f..9f907806c1a 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -407,7 +407,9 @@ void __init gart_iommu_hole_init(void) 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) { + 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"); @@ -448,7 +450,7 @@ out: /* 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) { -- cgit v1.2.3 From 46a7fa270afbe5fddc6042a598cfe22977b0e989 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 11 Jul 2008 10:23:42 +0900 Subject: x86: make only GART code include gart.h gart.h has only GART-specific stuff. Only GART code needs it. Other IOMMU stuff should include iommu.h instead of gart.h. Signed-off-by: FUJITA Tomonori Acked-by: Muli Ben-Yehuda Signed-off-by: Ingo Molnar --- arch/x86/kernel/aperture_64.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel/aperture_64.c') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 9f907806c1a..44e21826db1 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3