From 226e9a93a253b7d8811b5ed9ac671c6c5a728022 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 27 May 2008 09:56:49 +0200 Subject: x86: ioremap fix failing nesting check Mika Kukkonen noticed that the nesting check in early_iounmap() is not actually done. Reported-by: Mika Kukkonen Signed-off-by: Ingo Molnar Cc: torvalds@linux-foundation.org Cc: arjan@linux.intel.com Cc: mikukkon@iki.fi Signed-off-by: Thomas Gleixner --- arch/x86/mm/ioremap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 71bb3159031..2b2bb3f9b68 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -593,10 +593,11 @@ void __init early_iounmap(void *addr, unsigned long size) unsigned long offset; unsigned int nrpages; enum fixed_addresses idx; - unsigned int nesting; + int nesting; nesting = --early_ioremap_nested; - WARN_ON(nesting < 0); + if (WARN_ON(nesting < 0)) + return; if (early_ioremap_debug) { printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr, -- cgit v1.2.3 From 2884f110d5409714f3a04eeb6d2ecd77da66b242 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 28 May 2008 19:36:07 +0100 Subject: x86: fix bad pmd ffff810000207xxx(9090909090909090) OGAWA Hirofumi and Fede have reported rare pmd_ERROR messages: mm/memory.c:127: bad pmd ffff810000207xxx(9090909090909090). Initialization's cleanup_highmap was leaving alignment filler behind in the pmd for MODULES_VADDR: when vmalloc's guard page would occupy a new page table, it's not allocated, and then module unload's vfree hits the bad 9090 pmd entry left over. Signed-off-by: Hugh Dickins Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 32ba13b0f81..998a06ea5f7 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -206,7 +206,7 @@ void __init cleanup_highmap(void) pmd_t *last_pmd = pmd + PTRS_PER_PMD; for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) { - if (!pmd_present(*pmd)) + if (pmd_none(*pmd)) continue; if (vaddr < (unsigned long) _text || vaddr > end) set_pmd(pmd, __pmd(0)); -- cgit v1.2.3 From 511631011d39706ac81ee5e4c9084d61e5b4fd34 Mon Sep 17 00:00:00 2001 From: Kevin Winchester Date: Thu, 29 May 2008 21:14:35 -0300 Subject: x86: fix pointer type warning in arch/x86/mm/init_64.c:early_memtest Changed the call to find_e820_area_size to pass u64 instead of unsigned long. Signed-off-by: Kevin Winchester Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 998a06ea5f7..156e6d7b0e3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -506,7 +506,7 @@ early_param("memtest", parse_memtest); static void __init early_memtest(unsigned long start, unsigned long end) { - unsigned long t_start, t_size; + u64 t_start, t_size; unsigned pattern; if (!memtest_pattern) @@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end) if (t_start + t_size > end) t_size = end - t_start; - printk(KERN_CONT "\n %016lx - %016lx pattern %d", + printk(KERN_CONT "\n %016llx - %016llx pattern %d", t_start, t_start + t_size, pattern); memtest(t_start, t_size, pattern); -- cgit v1.2.3 From 282c454cd3a7041f59a37112bb2f82263bc38f6c Mon Sep 17 00:00:00 2001 From: Venki Pallipadi Date: Thu, 29 May 2008 12:01:44 -0700 Subject: x86: fix Xorg crash with xf86MapVidMem error Clarify the usage of mtrr_lookup() in PAT code, and to make PAT code resilient to mtrr lookup problems. Specifically, pat_x_mtrr_type() is restructured to highlight, under what conditions we look for mtrr hint. pat_x_mtrr_type() uses a default type when there are any errors in mtrr lookup (still maintaining the pat consistency). And, reserve_memtype() highlights its usage ot mtrr_lookup for request type of '-1' and also defaults in a sane way on any mtrr lookup failure. pat.c looks at mtrr type of a range to get a hint on what mapping type to request when user/API: (1) hasn't specified any type (/dev/mem mapping) and we do not want to take performance hit by always mapping UC_MINUS. This will be the case for /dev/mem mappings used to map BIOS area or ACPI region which are WB'able. In this case, as long as MTRR is not WB, PAT will request UC_MINUS for such mappings. (2) user/API requests WB mapping while in reality MTRR may have UC or WC. In this case, PAT can map as WB (without checking MTRR) and still effective type will be UC or WC. But, a subsequent request to map same region as UC or WC may fail, as the region will get trackked as WB in PAT list. Looking at MTRR hint helps us to track based on effective type rather than what user requested. Again, here mtrr_lookup is only used as hint and we fallback to WB mapping (as requested by user) as default. In both cases, after using the mtrr hint, we still go through the memtype list to make sure there are no inconsistencies among multiple users. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Tested-by: Rufus & Azrael Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 49 ++++++++++++++++++++++++------------------------- 1 file changed, 24 insertions(+), 25 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index de3a9981245..183fdd36d3b 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -151,32 +151,33 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot, unsigned long pat_type; u8 mtrr_type; - mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == 0xFF) { /* MTRR not enabled */ - *ret_prot = prot; - return 0; - } - if (mtrr_type == 0xFE) { /* MTRR match error */ - *ret_prot = _PAGE_CACHE_UC; - return -1; - } - if (mtrr_type != MTRR_TYPE_UNCACHABLE && - mtrr_type != MTRR_TYPE_WRBACK && - mtrr_type != MTRR_TYPE_WRCOMB) { /* MTRR type unhandled */ - *ret_prot = _PAGE_CACHE_UC; - return -1; - } - pat_type = prot & _PAGE_CACHE_MASK; prot &= (~_PAGE_CACHE_MASK); - /* Currently doing intersection by hand. Optimize it later. */ + /* + * We return the PAT request directly for types where PAT takes + * precedence with respect to MTRR and for UC_MINUS. + * Consistency checks with other PAT requests is done later + * while going through memtype list. + */ if (pat_type == _PAGE_CACHE_WC) { *ret_prot = prot | _PAGE_CACHE_WC; + return 0; } else if (pat_type == _PAGE_CACHE_UC_MINUS) { *ret_prot = prot | _PAGE_CACHE_UC_MINUS; - } else if (pat_type == _PAGE_CACHE_UC || - mtrr_type == MTRR_TYPE_UNCACHABLE) { + return 0; + } else if (pat_type == _PAGE_CACHE_UC) { + *ret_prot = prot | _PAGE_CACHE_UC; + return 0; + } + + /* + * Look for MTRR hint to get the effective type in case where PAT + * request is for WB. + */ + mtrr_type = mtrr_type_lookup(start, end); + + if (mtrr_type == MTRR_TYPE_UNCACHABLE) { *ret_prot = prot | _PAGE_CACHE_UC; } else if (mtrr_type == MTRR_TYPE_WRCOMB) { *ret_prot = prot | _PAGE_CACHE_WC; @@ -233,14 +234,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (req_type == -1) { /* - * Special case where caller wants to inherit from mtrr or - * existing pat mapping, defaulting to UC_MINUS in case of - * no match. + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. */ u8 mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == 0xFE) { /* MTRR match error */ - err = -1; - } if (mtrr_type == MTRR_TYPE_WRBACK) { req_type = _PAGE_CACHE_WB; -- cgit v1.2.3 From be524fb96081e9e511d993ebf39b05a32b19476e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 29 May 2008 00:01:28 -0700 Subject: x86: section mismatch fix Fix this: WARNING: vmlinux.o(.text+0x114bb): Section mismatch in reference from the function nopat() to the function .cpuinit.text:pat_disable() The function nopat() references the function __cpuinit pat_disable(). This is often because nopat lacks a __cpuinit annotation or the annotation of pat_disable is wrong. Reported-by: "Fabio Comolli" Cc: Sam Ravnborg Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 183fdd36d3b..06b7a1c90fb 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -34,7 +34,7 @@ void __cpuinit pat_disable(char *reason) printk(KERN_INFO "%s\n", reason); } -static int nopat(char *str) +static int __init nopat(char *str) { pat_disable("PAT support disabled."); return 0; -- cgit v1.2.3 From 39b8931b5cad9a7cbcd2394a40a088311e783a82 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 9 Jun 2008 16:48:18 -0700 Subject: ACPI: handle invalid ACPI SLIT table This is a SLIT sanity checking patch. It moves slit_valid() function to generic ACPI code and does sanity checking for both x86 and ia64. It sets up node_distance with LOCAL_DISTANCE and REMOTE_DISTANCE when hitting invalid SLIT table on ia64. It also cleans up unused variable localities in acpi_parse_slit() on x86. Signed-off-by: Fenghua Yu Signed-off-by: Andrew Morton Signed-off-by: Len Brown --- arch/x86/mm/srat_64.c | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 3890234e5b2..99649dccad2 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -97,36 +97,9 @@ static __init inline int srat_disabled(void) return numa_off || acpi_numa < 0; } -/* - * A lot of BIOS fill in 10 (= no distance) everywhere. This messes - * up the NUMA heuristics which wants the local node to have a smaller - * distance than the others. - * Do some quick checks here and only use the SLIT if it passes. - */ -static __init int slit_valid(struct acpi_table_slit *slit) -{ - int i, j; - int d = slit->locality_count; - for (i = 0; i < d; i++) { - for (j = 0; j < d; j++) { - u8 val = slit->entry[d*i + j]; - if (i == j) { - if (val != LOCAL_DISTANCE) - return 0; - } else if (val <= LOCAL_DISTANCE) - return 0; - } - } - return 1; -} - /* Callback for SLIT parsing */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { - if (!slit_valid(slit)) { - printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n"); - return; - } acpi_slit = slit; } -- cgit v1.2.3 From b29c701deacd5d24453127c37ed77ef851c53b8b Mon Sep 17 00:00:00 2001 From: Henry Nestler Date: Mon, 12 May 2008 15:44:39 +0200 Subject: x86: fix endless page faults in mount_block_root for Linux 2.6 Page faults in kernel address space between PAGE_OFFSET up to VMALLOC_START should not try to map as vmalloc. Fix rarely endless page faults inside mount_block_root for root filesystem at boot time. All 32bit kernels up to 2.6.25 can fail into this hole. I can not present this under native linux kernel. I see, that the 64bit has fixed the problem. I copied the same lines into 32bit part. Recorded debugs are from coLinux kernel 2.6.22.18 (virtualisation): http://www.henrynestler.com/colinux/testing/pfn-check-0.7.3/20080410-antinx/bug16-recursive-page-fault-endless.txt The physicaly memory was trimmed down to 192MB to better catch the bug. More memory gets the bug more rarely. Details, how every x86 32bit system can fail: Start from "mount_block_root", http://lxr.linux.no/linux/init/do_mounts.c#L297 There the variable "fs_names" got one memory page with 4096 bytes. Variable "p" walks through the existing file system types. The first string is no problem. But, with the second loop in mount_block_root the offset of "p" is not at beginning of page, the offset is for example +9, if "reiserfs" is the first in list. Than calls do_mount_root, and lands in sys_mount. Remember: Variable "type_page" contains now "fs_type+9" and not contains a full page. The sys_mount copies 4096 bytes with function "exact_copy_from_user()": http://lxr.linux.no/linux/fs/namespace.c#L1540 Mostly exist pages after the buffer "fs_names+4096+9" and the page fault handler was not called. No problem. In the case, if the page after "fs_names+4096" is not mapped, the page fault handler was called from http://lxr.linux.no/linux/fs/namespace.c#L1320 The do_page_fault gots an address 0xc03b4000. It's kernel address, address >= TASK_SIZE, but not from vmalloc! It's from "__getname()" alias "kmem_cache_alloc". The "error_code" is 0. "vmalloc_fault" will be call: http://lxr.linux.no/linux/arch/i386/mm/fault.c#L332 "vmalloc_fault" tryed to find the physical page for a non existing virtual memory area. The macro "pte_present" in vmalloc_fault() got a next page fault for 0xc0000ed0 at: http://lxr.linux.no/linux/arch/i386/mm/fault.c#L282 No PTE exist for such virtual address. The page fault handler was trying to sync the physical page for the PTE lockup. This called vmalloc_fault() again for address 0xc000000, and that also was not existing. The endless began... In normal case the cpu would still loop with disabled interrrupts. Under coLinux this was catched by a stack overflow inside printk debugs. Signed-off-by: Henry Nestler Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/mm/fault.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fd7e1798c75..8bcb6f40ccb 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -497,6 +497,11 @@ static int vmalloc_fault(unsigned long address) unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; + + /* Make sure we are in vmalloc area */ + if (!(address >= VMALLOC_START && address < VMALLOC_END)) + return -1; + /* * Synchronize this task's top level page-table * with the 'reference' page table. -- cgit v1.2.3 From eb53e9f3ea859a6d59c37b500593b970aa8562e6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 7 Jun 2008 17:18:40 +0100 Subject: x86: fix an incompatible pointer type warning on 64-bit compilations Fix an incompatible pointer type warning on x86_64 compilations. early_memtest() is passing a u64* to find_e820_area_size() which is expecting an unsigned long. Change t_start and t_size to unsigned long as those are also 64-bit types on x88_64. Signed-off-by: David Howells Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 156e6d7b0e3..998a06ea5f7 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -506,7 +506,7 @@ early_param("memtest", parse_memtest); static void __init early_memtest(unsigned long start, unsigned long end) { - u64 t_start, t_size; + unsigned long t_start, t_size; unsigned pattern; if (!memtest_pattern) @@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end) if (t_start + t_size > end) t_size = end - t_start; - printk(KERN_CONT "\n %016llx - %016llx pattern %d", + printk(KERN_CONT "\n %016lx - %016lx pattern %d", t_start, t_start + t_size, pattern); memtest(t_start, t_size, pattern); -- cgit v1.2.3 From f8a45704f5bd5f037c8e4a75172cab1476fc0447 Mon Sep 17 00:00:00 2001 From: Kevin Winchester Date: Thu, 29 May 2008 21:14:35 -0300 Subject: x86: fix pointer type warning in arch/x86/mm/init_64.c:early_memtest Changed the call to find_e820_area_size to pass u64 instead of unsigned long. Signed-off-by: Kevin Winchester Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 998a06ea5f7..156e6d7b0e3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -506,7 +506,7 @@ early_param("memtest", parse_memtest); static void __init early_memtest(unsigned long start, unsigned long end) { - unsigned long t_start, t_size; + u64 t_start, t_size; unsigned pattern; if (!memtest_pattern) @@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end) if (t_start + t_size > end) t_size = end - t_start; - printk(KERN_CONT "\n %016lx - %016lx pattern %d", + printk(KERN_CONT "\n %016llx - %016llx pattern %d", t_start, t_start + t_size, pattern); memtest(t_start, t_size, pattern); -- cgit v1.2.3