linux/arch/x86/kernel/aperture_64.c

501 lines
14 KiB
C
Raw Normal View History

/*
* Firmware replacement code.
*
* 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>
x86-64, gart: Fix allocation with memblock When trying to change alloc_bootmem with memblock to go with real top-down Found one old system: [ 0.000000] Node 0: aperture @ ac000000 size 64 MB [ 0.000000] Aperture pointing to e820 RAM. Ignoring. [ 0.000000] Your BIOS doesn't leave a aperture memory hole [ 0.000000] Please enable the IOMMU option in the BIOS setup [ 0.000000] This costs you 64 MB of RAM [ 0.000000] memblock_x86_reserve_range: [0x2020000000-0x2023ffffff] aperture64 [ 0.000000] Cannot allocate aperture memory hole (ffff882020000000,65536K) [ 0.000000] memblock_x86_free_range: [0x2020000000-0x2023ffffff] [ 0.000000] Kernel panic - not syncing: Not enough memory for aperture [ 0.000000] Pid: 0, comm: swapper Not tainted 2.6.37-rc5-tip-yh-06229-gb792dc2-dirty #331 [ 0.000000] Call Trace: [ 0.000000] [<ffffffff81cf50fe>] ? panic+0x91/0x1a3 [ 0.000000] [<ffffffff827c66b2>] ? gart_iommu_hole_init+0x3d7/0x4a3 [ 0.000000] [<ffffffff81d026a9>] ? _etext+0x0/0x3 [ 0.000000] [<ffffffff827ba940>] ? pci_iommu_alloc+0x47/0x71 [ 0.000000] [<ffffffff827c820b>] ? mem_init+0x19/0xec [ 0.000000] [<ffffffff827b3c40>] ? start_kernel+0x20a/0x3e8 [ 0.000000] [<ffffffff827b32cc>] ? x86_64_start_reservations+0x9c/0xa0 [ 0.000000] [<ffffffff827b33e4>] ? x86_64_start_kernel+0x114/0x11b it means __alloc_bootmem_nopanic() get too high for that aperture. Use memblock_find_in_range() with limit directly. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0740.90104@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 00:58:40 +00:00
#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/pci_ids.h>
#include <linux/pci.h>
#include <linux/bitops.h>
#include <linux/suspend.h>
#include <asm/e820/api.h>
#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/pci-direct.h>
#include <asm/dma.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;
int gart_iommu_aperture_allowed __initdata;
int fallback_aper_order __initdata = 1; /* 64MB */
int fallback_aper_force __initdata;
int fix_aperture __initdata = 1;
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
static u32 __init allocate_aperture(void)
{
u32 aper_size;
x86-64, gart: Fix allocation with memblock When trying to change alloc_bootmem with memblock to go with real top-down Found one old system: [ 0.000000] Node 0: aperture @ ac000000 size 64 MB [ 0.000000] Aperture pointing to e820 RAM. Ignoring. [ 0.000000] Your BIOS doesn't leave a aperture memory hole [ 0.000000] Please enable the IOMMU option in the BIOS setup [ 0.000000] This costs you 64 MB of RAM [ 0.000000] memblock_x86_reserve_range: [0x2020000000-0x2023ffffff] aperture64 [ 0.000000] Cannot allocate aperture memory hole (ffff882020000000,65536K) [ 0.000000] memblock_x86_free_range: [0x2020000000-0x2023ffffff] [ 0.000000] Kernel panic - not syncing: Not enough memory for aperture [ 0.000000] Pid: 0, comm: swapper Not tainted 2.6.37-rc5-tip-yh-06229-gb792dc2-dirty #331 [ 0.000000] Call Trace: [ 0.000000] [<ffffffff81cf50fe>] ? panic+0x91/0x1a3 [ 0.000000] [<ffffffff827c66b2>] ? gart_iommu_hole_init+0x3d7/0x4a3 [ 0.000000] [<ffffffff81d026a9>] ? _etext+0x0/0x3 [ 0.000000] [<ffffffff827ba940>] ? pci_iommu_alloc+0x47/0x71 [ 0.000000] [<ffffffff827c820b>] ? mem_init+0x19/0xec [ 0.000000] [<ffffffff827b3c40>] ? start_kernel+0x20a/0x3e8 [ 0.000000] [<ffffffff827b32cc>] ? x86_64_start_reservations+0x9c/0xa0 [ 0.000000] [<ffffffff827b33e4>] ? x86_64_start_kernel+0x114/0x11b it means __alloc_bootmem_nopanic() get too high for that aperture. Use memblock_find_in_range() with limit directly. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0740.90104@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 00:58:40 +00:00
unsigned long addr;
/* aper_size should <= 1G */
if (fallback_aper_order > 5)
fallback_aper_order = 5;
aper_size = (32 * 1024 * 1024) << fallback_aper_order;
/*
* Aperture has to be naturally aligned. This means a 2GB aperture
* won't have much chance of finding a place in the lower 4GB of
* memory. Unfortunately we cannot move it up because that would
* make the IOMMU useless.
*/
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);
x86-64, gart: Fix allocation with memblock When trying to change alloc_bootmem with memblock to go with real top-down Found one old system: [ 0.000000] Node 0: aperture @ ac000000 size 64 MB [ 0.000000] Aperture pointing to e820 RAM. Ignoring. [ 0.000000] Your BIOS doesn't leave a aperture memory hole [ 0.000000] Please enable the IOMMU option in the BIOS setup [ 0.000000] This costs you 64 MB of RAM [ 0.000000] memblock_x86_reserve_range: [0x2020000000-0x2023ffffff] aperture64 [ 0.000000] Cannot allocate aperture memory hole (ffff882020000000,65536K) [ 0.000000] memblock_x86_free_range: [0x2020000000-0x2023ffffff] [ 0.000000] Kernel panic - not syncing: Not enough memory for aperture [ 0.000000] Pid: 0, comm: swapper Not tainted 2.6.37-rc5-tip-yh-06229-gb792dc2-dirty #331 [ 0.000000] Call Trace: [ 0.000000] [<ffffffff81cf50fe>] ? panic+0x91/0x1a3 [ 0.000000] [<ffffffff827c66b2>] ? gart_iommu_hole_init+0x3d7/0x4a3 [ 0.000000] [<ffffffff81d026a9>] ? _etext+0x0/0x3 [ 0.000000] [<ffffffff827ba940>] ? pci_iommu_alloc+0x47/0x71 [ 0.000000] [<ffffffff827c820b>] ? mem_init+0x19/0xec [ 0.000000] [<ffffffff827b3c40>] ? start_kernel+0x20a/0x3e8 [ 0.000000] [<ffffffff827b32cc>] ? x86_64_start_reservations+0x9c/0xa0 [ 0.000000] [<ffffffff827b33e4>] ? x86_64_start_kernel+0x114/0x11b it means __alloc_bootmem_nopanic() get too high for that aperture. Use memblock_find_in_range() with limit directly. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0740.90104@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 00:58:40 +00:00
return 0;
}
memblock_reserve(addr, aper_size);
pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n",
addr, addr + aper_size - 1, aper_size >> 10);
x86-64, gart: Fix allocation with memblock When trying to change alloc_bootmem with memblock to go with real top-down Found one old system: [ 0.000000] Node 0: aperture @ ac000000 size 64 MB [ 0.000000] Aperture pointing to e820 RAM. Ignoring. [ 0.000000] Your BIOS doesn't leave a aperture memory hole [ 0.000000] Please enable the IOMMU option in the BIOS setup [ 0.000000] This costs you 64 MB of RAM [ 0.000000] memblock_x86_reserve_range: [0x2020000000-0x2023ffffff] aperture64 [ 0.000000] Cannot allocate aperture memory hole (ffff882020000000,65536K) [ 0.000000] memblock_x86_free_range: [0x2020000000-0x2023ffffff] [ 0.000000] Kernel panic - not syncing: Not enough memory for aperture [ 0.000000] Pid: 0, comm: swapper Not tainted 2.6.37-rc5-tip-yh-06229-gb792dc2-dirty #331 [ 0.000000] Call Trace: [ 0.000000] [<ffffffff81cf50fe>] ? panic+0x91/0x1a3 [ 0.000000] [<ffffffff827c66b2>] ? gart_iommu_hole_init+0x3d7/0x4a3 [ 0.000000] [<ffffffff81d026a9>] ? _etext+0x0/0x3 [ 0.000000] [<ffffffff827ba940>] ? pci_iommu_alloc+0x47/0x71 [ 0.000000] [<ffffffff827c820b>] ? mem_init+0x19/0xec [ 0.000000] [<ffffffff827b3c40>] ? start_kernel+0x20a/0x3e8 [ 0.000000] [<ffffffff827b32cc>] ? x86_64_start_reservations+0x9c/0xa0 [ 0.000000] [<ffffffff827b33e4>] ? x86_64_start_kernel+0x114/0x11b it means __alloc_bootmem_nopanic() get too high for that aperture. Use memblock_find_in_range() with limit directly. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0740.90104@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 00:58:40 +00:00
register_nosave_region(addr >> PAGE_SHIFT,
(addr+aper_size) >> PAGE_SHIFT);
x86-64, gart: Fix allocation with memblock When trying to change alloc_bootmem with memblock to go with real top-down Found one old system: [ 0.000000] Node 0: aperture @ ac000000 size 64 MB [ 0.000000] Aperture pointing to e820 RAM. Ignoring. [ 0.000000] Your BIOS doesn't leave a aperture memory hole [ 0.000000] Please enable the IOMMU option in the BIOS setup [ 0.000000] This costs you 64 MB of RAM [ 0.000000] memblock_x86_reserve_range: [0x2020000000-0x2023ffffff] aperture64 [ 0.000000] Cannot allocate aperture memory hole (ffff882020000000,65536K) [ 0.000000] memblock_x86_free_range: [0x2020000000-0x2023ffffff] [ 0.000000] Kernel panic - not syncing: Not enough memory for aperture [ 0.000000] Pid: 0, comm: swapper Not tainted 2.6.37-rc5-tip-yh-06229-gb792dc2-dirty #331 [ 0.000000] Call Trace: [ 0.000000] [<ffffffff81cf50fe>] ? panic+0x91/0x1a3 [ 0.000000] [<ffffffff827c66b2>] ? gart_iommu_hole_init+0x3d7/0x4a3 [ 0.000000] [<ffffffff81d026a9>] ? _etext+0x0/0x3 [ 0.000000] [<ffffffff827ba940>] ? pci_iommu_alloc+0x47/0x71 [ 0.000000] [<ffffffff827c820b>] ? mem_init+0x19/0xec [ 0.000000] [<ffffffff827b3c40>] ? start_kernel+0x20a/0x3e8 [ 0.000000] [<ffffffff827b32cc>] ? x86_64_start_reservations+0x9c/0xa0 [ 0.000000] [<ffffffff827b33e4>] ? x86_64_start_kernel+0x114/0x11b it means __alloc_bootmem_nopanic() get too high for that aperture. Use memblock_find_in_range() with limit directly. Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0C0740.90104@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-18 00:58:40 +00:00
return (u32)addr;
}
/* Find a PCI capability */
static u32 __init find_cap(int bus, int slot, int func, int cap)
{
int bytes;
u8 pos;
if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) &
PCI_STATUS_CAP_LIST))
return 0;
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(bus, slot, func, pos+PCI_CAP_LIST_ID);
if (id == 0xff)
break;
if (id == cap)
return pos;
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 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;
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) {
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)
apsize |= 0xf00;
nbits = hweight16(apsize);
*order = 7 - nbits;
if ((int)*order < 0) /* < 32MB */
*order = 0;
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:
*/
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, 32<<20))
return 0;
return (u32)aper;
}
/*
* Look for an AGP bridge. Windows only expects the aperture in the
* AGP bridge and some BIOS forget to initialize the Northbridge too.
* Work around this here.
*
* Do an PCI bus scan by hand because we're running before the PCI
* subsystem.
*
* 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)
{
int bus, slot, func;
/* Poor man's PCI discovery */
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(bus, slot, func,
PCI_CLASS_REVISION);
if (class == 0xffffffff)
break;
switch (class >> 16) {
case PCI_CLASS_BRIDGE_HOST:
case PCI_CLASS_BRIDGE_OTHER: /* needed? */
/* AGP bridge? */
cap = find_cap(bus, slot, func,
PCI_CAP_ID_AGP);
if (!cap)
break;
*valid_agp = 1;
return read_agp(bus, slot, func, cap,
order);
}
/* No multi-function device? */
type = read_pci_config_byte(bus, slot, func,
PCI_HEADER_TYPE);
if (!(type & 0x80))
break;
}
}
}
pr_info("No AGP bridge found\n");
return 0;
}
static bool gart_fix_e820 __initdata = true;
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
static int __init parse_gart_mem(char *p)
{
return kstrtobool(p, &gart_fix_e820);
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
}
early_param("gart_fix_e820", parse_gart_mem);
void __init early_gart_iommu_check(void)
{
/*
* in case it is enabled before, esp for kexec/kdump,
* previous kernel already enable that. memset called
* by allocate_aperture/__alloc_bootmem_nopanic cause restart.
* or second kernel have different position for GART hole. and new
* kernel could use hole as RAM that is still used by GART set by
* first kernel
* or BIOS forget to put that in reserved.
* try to update e820 to make that region as reserved.
*/
u32 agp_aper_order = 0;
int i, fix, slot, valid_agp = 0;
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
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, last_valid = 0;
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
x86/gart: Check for GART support before accessing GART registers GART registers are not present in newer AMD processors (Fam15h, Model 10h and later). So, avoid accessing those in PCI config space by returning early in early_gart_iommu_check() and gart_iommu_hole_init() if GART is not available. Current code doesn't break on existing processors but there are some side effects: We get bogus AGP aperture messages which are simply noise on GART-less processors: AGP: Node 0: aperture [bus addr 0x00000000-0x01ffffff] (32MB) AGP: Your BIOS doesn't leave aperture memory hole AGP: Please enable the IOMMU option in the BIOS setup AGP: This costs you 64MB of RAM AGP: Mapping aperture over RAM [mem 0xd4000000-0xd7ffffff] We can avoid calling allocate_aperture() and would not have to wastefully reserve 64MB of RAM with memblock_reserve(). Also, we can avoid having to loop through all PCI buses and devices twice, searching for a non-existent AGP bridge if we bail out early. Refactor the family check used in amd_nb.c into an inline function so we can use it here as well as in amd_nb.c Fix some typos while at it. Tested the patch on Fam10h and Fam15h Model 00h-fh and this code runs fine. On Fam15h Model 60h-6fh and on Fam16h, we bail early as they don't have GART. Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Joerg Rodel <joro@8bytes.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1428443197-3834-1-git-send-email-Aravind.Gopalakrishnan@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-07 21:46:37 +00:00
if (!amd_gart_present())
return;
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
if (!early_pci_allowed())
return;
/* This is mostly duplicate of iommu_hole_init */
search_agp_bridge(&agp_aper_order, &valid_agp);
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
fix = 0;
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;
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
}
}
if (!fix && !aper_enabled)
return;
if (!aper_base || !aper_size || aper_base + aper_size > 0x100000000UL)
fix = 1;
if (gart_fix_e820 && !fix && aper_enabled) {
if (e820__mapped_any(aper_base, aper_base + aper_size,
E820_RAM)) {
/* 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);
x86/boot/e820: Create coherent API function names for E820 range operations We have these three related functions: extern void e820_add_region(u64 start, u64 size, int type); extern u64 e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type); extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype); But it's not clear from the naming that they are 3 operations based around the same 'memory range' concept. Rename them to better signal this, and move the prototypes next to each other: extern void e820__range_add (u64 start, u64 size, int type); extern u64 e820__range_update(u64 start, u64 size, unsigned old_type, unsigned new_type); extern u64 e820__range_remove(u64 start, u64 size, unsigned old_type, int checktype); Note that this improved organization of the functions shows another problem that was easy to miss before: sometimes the E820 entry type is 'int', sometimes 'unsigned int' - but this will be fixed in a separate patch. No change in functionality. Cc: Alex Thorlton <athorlton@sgi.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Huang, Ying <ying.huang@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Jackson <pj@sgi.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-28 13:19:36 +00:00
e820__range_add(aper_base, aper_size, E820_RESERVED);
e820__update_table_print();
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
}
}
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;
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
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);
ctl &= ~GARTEN;
write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
}
x86: disable the GART early, 64-bit For K8 system: 4G RAM with memory hole remapping enabled, or more than 4G RAM installed. when try to use kexec second kernel, and the first doesn't include gart_shutdown. the second kernel could have different aper position than the first kernel. and second kernel could use that hole as RAM that is still used by GART set by the first kernel. esp. when try to kexec 2.6.24 with sparse mem enable from previous kernel (from RHEL 5 or SLES 10). the new kernel will use aper by GART (set by first kernel) for vmemmap. and after new kernel setting one new GART. the position will be real RAM. the _mapcount set is lost. Bad page state in process 'swapper' page:ffffe2000e600020 flags:0x0000000000000000 mapping:0000000000000000 mapcount:1 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 0, comm: swapper Not tainted 2.6.24-rc7-smp-gcdf71a10-dirty #13 Call Trace: [<ffffffff8026401f>] bad_page+0x63/0x8d [<ffffffff80264169>] __free_pages_ok+0x7c/0x2a5 [<ffffffff80ba75d1>] free_all_bootmem_core+0xd0/0x198 [<ffffffff80ba3a42>] numa_free_all_bootmem+0x3b/0x76 [<ffffffff80ba3461>] mem_init+0x3b/0x152 [<ffffffff80b959d3>] start_kernel+0x236/0x2c2 [<ffffffff80b9511a>] _sinittext+0x11a/0x121 and [ffffe2000e600000-ffffe2000e7fffff] PMD ->ffff81001c200000 on node 0 phys addr is : 0x1c200000 RHEL 5.1 kernel -53 said: PCI-DMA: aperture base @ 1c000000 size 65536 KB new kernel said: Mapping aperture over 65536 KB of RAM @ 3c000000 So could try to disable that GART if possible. According to Ingo > hm, i'm wondering, instead of modifying the GART, why dont we simply > _detect_ whatever GART settings we have inherited, and propagate that > into our e820 maps? I.e. if there's inconsistency, then punch that out > from the memory maps and just dont use that memory. > > that way it would not matter whether the GART settings came from a [old > or crashing] Linux kernel that has not called gart_iommu_shutdown(), or > whether it's a BIOS that has set up an aperture hole inconsistent with > the memory map it passed. (or the memory map we _think_ i tried to pass > us) > > it would also be more robust to only read and do a memory map quirk > based on that, than actively trying to change the GART so early in the > bootup. Later on we have to re-enable the GART _anyway_ and have to > punch a hole for it. > > and as a bonus, we would have shored up our defenses against crappy > BIOSes as well. add e820 modification for gart inconsistent setting. gart_fix_e820=off could be used to disable e820 fix. Signed-off-by: Yinghai Lu <yinghai.lu@sun.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:33:09 +00:00
}
}
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, slot, valid_agp = 0;
int i, node;
x86/gart: Check for GART support before accessing GART registers GART registers are not present in newer AMD processors (Fam15h, Model 10h and later). So, avoid accessing those in PCI config space by returning early in early_gart_iommu_check() and gart_iommu_hole_init() if GART is not available. Current code doesn't break on existing processors but there are some side effects: We get bogus AGP aperture messages which are simply noise on GART-less processors: AGP: Node 0: aperture [bus addr 0x00000000-0x01ffffff] (32MB) AGP: Your BIOS doesn't leave aperture memory hole AGP: Please enable the IOMMU option in the BIOS setup AGP: This costs you 64MB of RAM AGP: Mapping aperture over RAM [mem 0xd4000000-0xd7ffffff] We can avoid calling allocate_aperture() and would not have to wastefully reserve 64MB of RAM with memblock_reserve(). Also, we can avoid having to loop through all PCI buses and devices twice, searching for a non-existent AGP bridge if we bail out early. Refactor the family check used in amd_nb.c into an inline function so we can use it here as well as in amd_nb.c Fix some typos while at it. Tested the patch on Fam10h and Fam15h Model 00h-fh and this code runs fine. On Fam15h Model 60h-6fh and on Fam16h, we bail early as they don't have GART. Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Joerg Rodel <joro@8bytes.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1428443197-3834-1-git-send-email-Aravind.Gopalakrishnan@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-07 21:46:37 +00:00
if (!amd_gart_present())
return -ENODEV;
if (gart_iommu_aperture_disabled || !fix_aperture ||
!early_pci_allowed())
return -ENODEV;
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 < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
int bus;
int dev_base, dev_limit;
u32 ctl;
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;
iommu_detected = 1;
gart_iommu_aperture = 1;
x86_init.iommu.iommu_init = gart_iommu_init;
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;
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;
}
}
out:
if (!fix && !fallback_aper_force) {
if (last_aper_base)
return 1;
return 0;
}
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 ((!no_iommu && max_pfn > MAX_DMA32_PFN) ||
force_iommu ||
valid_agp ||
fallback_aper_force) {
x86/gart: Check for GART support before accessing GART registers GART registers are not present in newer AMD processors (Fam15h, Model 10h and later). So, avoid accessing those in PCI config space by returning early in early_gart_iommu_check() and gart_iommu_hole_init() if GART is not available. Current code doesn't break on existing processors but there are some side effects: We get bogus AGP aperture messages which are simply noise on GART-less processors: AGP: Node 0: aperture [bus addr 0x00000000-0x01ffffff] (32MB) AGP: Your BIOS doesn't leave aperture memory hole AGP: Please enable the IOMMU option in the BIOS setup AGP: This costs you 64MB of RAM AGP: Mapping aperture over RAM [mem 0xd4000000-0xd7ffffff] We can avoid calling allocate_aperture() and would not have to wastefully reserve 64MB of RAM with memblock_reserve(). Also, we can avoid having to loop through all PCI buses and devices twice, searching for a non-existent AGP bridge if we bail out early. Refactor the family check used in amd_nb.c into an inline function so we can use it here as well as in amd_nb.c Fix some typos while at it. Tested the patch on Fam10h and Fam15h Model 00h-fh and this code runs fine. On Fam15h Model 60h-6fh and on Fam16h, we bail early as they don't have GART. Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Joerg Rodel <joro@8bytes.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1428443197-3834-1-git-send-email-Aravind.Gopalakrishnan@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-07 21:46:37 +00:00
pr_info("Your BIOS doesn't leave an 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();
if (!aper_alloc) {
/*
* Could disable AGP and IOMMU here, but it's
* probably not worth it. But the later users
* cannot deal with bad apertures and turning
* on the aperture over memory causes very
* strange problems, so it's better to panic
* early.
*/
panic("Not enough memory for aperture");
}
} else {
return 0;
}
/* Fix up the north bridges */
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_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;
}