From 76c06927f2a78143763dcff9b4c362d15eb29cc2 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 19:54:23 +0530 Subject: x86: Declare check_efer() before it gets used This sparse warning: arch/x86/mm/init.c:83:16: warning: symbol 'check_efer' was not declared. Should it be static? triggers because check_efer() is not decalared before using it. asm/proto.h includes the declaration of check_efer(), so including asm/proto.h to fix that - this also addresses the sparse warning. Signed-off-by: Jaswinder Singh Rajput Cc: Andrew Morton LKML-Reference: <1246458263.6940.22.camel@hpdv5.satnam> Signed-off-by: Ingo Molnar --- arch/x86/mm/init.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 47ce9a2ce5e7..0607119cef94 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -12,6 +12,7 @@ #include #include #include +#include DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -- cgit v1.2.2 From ad361c9884e809340f6daca80d56a9e9c871690a Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 6 Jul 2009 13:05:40 -0700 Subject: Remove multiple KERN_ prefixes from printk formats Commit 5fd29d6ccbc98884569d6f3105aeca70858b3e0f ("printk: clean up handling of log-levels and newlines") changed printk semantics. printk lines with multiple KERN_ prefixes are no longer emitted as before the patch. is now included in the output on each additional use. Remove all uses of multiple KERN_s in formats. Signed-off-by: Joe Perches Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 78a5fff857be..85307cc6e45f 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -426,10 +426,11 @@ static noinline int vmalloc_fault(unsigned long address) } static const char errata93_warning[] = -KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" -KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n" -KERN_ERR "******* Please consider a BIOS update.\n" -KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n"; +KERN_ERR +"******* Your BIOS seems to not contain a fix for K8 errata #93\n" +"******* Working around it, but it may cause SEGVs or burn power.\n" +"******* Please consider a BIOS update.\n" +"******* Disabling USB legacy in the BIOS may also help.\n"; /* * No vm86 mode in 64-bit mode: -- cgit v1.2.2 From 44b572809581d5a10dbe35aa6bf689f32b9c5ad6 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 8 Jul 2009 09:50:19 -0700 Subject: x86: don't clear nodes_states[N_NORMAL_MEMORY] when numa is not compiled in Alex found that specjbb2005 still can not run with hugepages on an x86-64 machine. This only happens when numa is not compiled in. The root cause: node_set_state will not set it back for us in that case, so don't clear that when numa is not select in config [ v2: use node_clear_state instead ] Reported-and-Tested-by: Alex Shi Signed-off-by: Yinghai Lu Reviewed-by: Christoph Lameter Signed-off-by: Linus Torvalds --- arch/x86/mm/init_64.c | 11 +++++++++-- 1 file changed, 9 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 b177652251a4..6176fe8f29e0 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -598,8 +598,15 @@ void __init paging_init(void) sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); - /* clear the default setting with node 0 */ - nodes_clear(node_states[N_NORMAL_MEMORY]); + + /* + * clear the default setting with node 0 + * note: don't use nodes_clear here, that is really clearing when + * numa support is not compiled in, and later node_set_state + * will not set it back. + */ + node_clear_state(0, N_NORMAL_MEMORY); + free_area_init_nodes(max_zone_pfns); } -- cgit v1.2.2 From a1a08d1cb0ab148fd74216e4c0b4d4db18fe62c6 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Sat, 11 Jul 2009 00:10:04 -0700 Subject: x86: Remove spurious printk level from segfault message Since commit 5fd29d6c ("printk: clean up handling of log-levels and newlines"), the kernel logs segfaults like: <6>gnome-power-man[24509]: segfault at 20 ip 00007f9d4950465a sp 00007fffbb50fc70 error 4 in libgobject-2.0.so.0.2103.0[7f9d494f7000+45000] with the extra "<6>" being KERN_INFO. This happens because the printk in show_signal_msg() started with KERN_CONT and then used "%s" to pass in the real level; and KERN_CONT is no longer an empty string, and printk only pays attention to the level at the very beginning of the format string. Therefore, remove the KERN_CONT from this printk, since it is now actively causing problems (and never really made any sense). Signed-off-by: Roland Dreier Cc: Linus Torvalds LKML-Reference: <874otjitkj.fsf@shaolin.home.digitalvampire.org> Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 85307cc6e45f..bfae139182ff 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -697,7 +697,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, if (!printk_ratelimit()) return; - printk(KERN_CONT "%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); -- cgit v1.2.2 From 429b2b319af3987e808c18f6b81313104caf782c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 18 Jul 2009 08:56:57 +0200 Subject: x86-64: Fix bad_srat() to clear all state Need to clear both nodes and nodes_add state for start/end. Signed-off-by: Andi Kleen LKML-Reference: <20090718065657.GA2898@basil.fritz.box> Signed-off-by: H. Peter Anvin Cc: stable@kernel.org --- arch/x86/mm/srat_64.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 2dfcbf9df2ae..dbb5381f7b3b 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -79,8 +79,10 @@ static __init void bad_srat(void) acpi_numa = -1; for (i = 0; i < MAX_LOCAL_APIC; i++) apicid_to_node[i] = NUMA_NO_NODE; - for (i = 0; i < MAX_NUMNODES; i++) - nodes_add[i].start = nodes[i].end = 0; + for (i = 0; i < MAX_NUMNODES; i++) { + nodes[i].start = nodes[i].end = 0; + nodes_add[i].start = nodes_add[i].end = 0; + } remove_all_active_ranges(); } -- cgit v1.2.2 From 9e1b32caa525cb236e80e9c671e179bcecccc657 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 22 Jul 2009 15:44:28 +1000 Subject: mm: Pass virtual address to [__]p{te,ud,md}_free_tlb() mm: Pass virtual address to [__]p{te,ud,md}_free_tlb() Upcoming paches to support the new 64-bit "BookE" powerpc architecture will need to have the virtual address corresponding to PTE page when freeing it, due to the way the HW table walker works. Basically, the TLB can be loaded with "large" pages that cover the whole virtual space (well, sort-of, half of it actually) represented by a PTE page, and which contain an "indirect" bit indicating that this TLB entry RPN points to an array of PTEs from which the TLB can then create direct entries. Thus, in order to invalidate those when PTE pages are deleted, we need the virtual address to pass to tlbilx or tlbivax instructions. The old trick of sticking it somewhere in the PTE page struct page sucks too much, the address is almost readily available in all call sites and almost everybody implemets these as macros, so we may as well add the argument everywhere. I added it to the pmd and pud variants for consistency. Signed-off-by: Benjamin Herrenschmidt Acked-by: David Howells [MN10300 & FRV] Acked-by: Nick Piggin Acked-by: Martin Schwidefsky [s390] Signed-off-by: Linus Torvalds --- arch/x86/mm/pgtable.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 8e43bdd45456..af8f9650058c 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -25,7 +25,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) return pte; } -void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) +void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pgtable_page_dtor(pte); paravirt_release_pte(page_to_pfn(pte)); @@ -33,14 +33,14 @@ void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) } #if PAGETABLE_LEVELS > 2 -void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) +void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); tlb_remove_page(tlb, virt_to_page(pmd)); } #if PAGETABLE_LEVELS > 3 -void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) +void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); tlb_remove_page(tlb, virt_to_page(pud)); -- cgit v1.2.2 From 73ba651fc246fcc3e446da4155e0425b4219d2c4 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 24 Jul 2009 09:57:33 +0200 Subject: x86: Export kmap_atomic_prot() needed for TTM. This functionality is needed to kmap_atomic() highmem pages that may potentially have or are about to set up other mappings with non-standard caching attributes. Signed-off-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- arch/x86/mm/highmem_32.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 58f621e81919..2112ed55e7ea 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -103,6 +103,7 @@ EXPORT_SYMBOL(kmap); EXPORT_SYMBOL(kunmap); EXPORT_SYMBOL(kmap_atomic); EXPORT_SYMBOL(kunmap_atomic); +EXPORT_SYMBOL(kmap_atomic_prot); void __init set_highmem_pages_init(void) { -- cgit v1.2.2 From bdc6340f4eb68295b1e7c0ade2356b56dca93d93 Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Thu, 30 Jul 2009 14:43:19 -0700 Subject: x86, pat: Fix set_memory_wc related corruption Changeset 3869c4aa18835c8c61b44bd0f3ace36e9d3b5bd0 that went in after 2.6.30-rc1 was a seemingly small change to _set_memory_wc() to make it complaint with SDM requirements. But, introduced a nasty bug, which can result in crash and/or strange corruptions when set_memory_wc is used. One such crash reported here http://lkml.org/lkml/2009/7/30/94 Actually, that changeset introduced two bugs. * change_page_attr_set() takes &addr as first argument and can the addr value might have changed on return, even for single page change_page_attr_set() call. That will make the second change_page_attr_set() in this routine operate on unrelated addr, that can eventually cause strange corruptions and bad page state crash. * The second change_page_attr_set() call, before setting _PAGE_CACHE_WC, should clear the earlier _PAGE_CACHE_UC_MINUS, as otherwise cache attribute will not be WC (will be UC instead). The patch below fixes both these problems. Sending a single patch to fix both the problems, as the change is to the same line of code. The change to have a addr_copy is not very clean. But, it is simpler than making more changes through various routines in pageattr.c. A huge thanks to Jerome for reporting this problem and providing a simple test case that helped us root cause the problem. Reported-by: Jerome Glisse Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha LKML-Reference: <20090730214319.GA1889@linux-os.sc.intel.com> Acked-by: Dave Airlie Signed-off-by: H. Peter Anvin --- arch/x86/mm/pageattr.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 1b734d7a8966..895d90e1a81b 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -997,12 +997,15 @@ EXPORT_SYMBOL(set_memory_array_uc); int _set_memory_wc(unsigned long addr, int numpages) { int ret; + unsigned long addr_copy = addr; + ret = change_page_attr_set(&addr, numpages, __pgprot(_PAGE_CACHE_UC_MINUS), 0); - if (!ret) { - ret = change_page_attr_set(&addr, numpages, - __pgprot(_PAGE_CACHE_WC), 0); + ret = change_page_attr_set_clr(&addr_copy, numpages, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, 0, NULL); } return ret; } -- cgit v1.2.2 From 8523acfe40efc1a8d3da8f473ca67cb195b06f0c Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Mon, 3 Aug 2009 09:25:45 +0200 Subject: x86: Fix CPA memtype reserving in the set_pages_array*() cases The code was incorrectly reserving memtypes using the page virtual address instead of the physical address. Furthermore, the code was not ignoring highmem pages as it ought to. ( upstream does not pass in highmem pages yet - but upcoming graphics code will do it and there's no reason to not handle this properly in the CPA APIs.) Fixes: http://bugzilla.kernel.org/show_bug.cgi?id=13884 Signed-off-by: Thomas Hellstrom Acked-by: Suresh Siddha Cc: Cc: dri-devel@lists.sourceforge.net Cc: venkatesh.pallipadi@intel.com LKML-Reference: <1249284345-7654-1-git-send-email-thellstrom@vmware.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pageattr.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 895d90e1a81b..7e600c1962db 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -591,9 +591,12 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) unsigned int level; pte_t *kpte, old_pte; - if (cpa->flags & CPA_PAGES_ARRAY) - address = (unsigned long)page_address(cpa->pages[cpa->curpage]); - else if (cpa->flags & CPA_ARRAY) + if (cpa->flags & CPA_PAGES_ARRAY) { + struct page *page = cpa->pages[cpa->curpage]; + if (unlikely(PageHighMem(page))) + return 0; + address = (unsigned long)page_address(page); + } else if (cpa->flags & CPA_ARRAY) address = cpa->vaddr[cpa->curpage]; else address = *cpa->vaddr; @@ -697,9 +700,12 @@ static int cpa_process_alias(struct cpa_data *cpa) * No need to redo, when the primary call touched the direct * mapping already: */ - if (cpa->flags & CPA_PAGES_ARRAY) - vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]); - else if (cpa->flags & CPA_ARRAY) + if (cpa->flags & CPA_PAGES_ARRAY) { + struct page *page = cpa->pages[cpa->curpage]; + if (unlikely(PageHighMem(page))) + return 0; + vaddr = (unsigned long)page_address(page); + } else if (cpa->flags & CPA_ARRAY) vaddr = cpa->vaddr[cpa->curpage]; else vaddr = *cpa->vaddr; @@ -1122,7 +1128,9 @@ int set_pages_array_uc(struct page **pages, int addrinarray) int free_idx; for (i = 0; i < addrinarray; i++) { - start = (unsigned long)page_address(pages[i]); + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) goto err_out; @@ -1135,7 +1143,9 @@ int set_pages_array_uc(struct page **pages, int addrinarray) err_out: free_idx = i; for (i = 0; i < free_idx; i++) { - start = (unsigned long)page_address(pages[i]); + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; free_memtype(start, end); } @@ -1164,7 +1174,9 @@ int set_pages_array_wb(struct page **pages, int addrinarray) return retval; for (i = 0; i < addrinarray; i++) { - start = (unsigned long)page_address(pages[i]); + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; free_memtype(start, end); } -- cgit v1.2.2 From 6abf65510944d33b47575d151c6b318993c8d2b5 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 30 Jul 2009 16:49:30 +0100 Subject: x86, 32-bit: Fix double accounting in reserve_top_address() With VMALLOC_END included in the calculation of MAXMEM (as of 2.6.28) it is no longer correct to also bump __VMALLOC_RESERVE in reserve_top_address(). Doing so results in needlessly small lowmem. Signed-off-by: Jan Beulich LKML-Reference: <4A71DD2A020000780000D482@vpn.id2.novell.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pgtable.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index af8f9650058c..ed34f5e35999 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -329,7 +329,6 @@ void __init reserve_top_address(unsigned long reserve) printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", (int)-reserve); __FIXADDR_TOP = -reserve - PAGE_SIZE; - __VMALLOC_RESERVE += reserve; #endif } -- cgit v1.2.2 From 1adcaafe7414c5731f758b158aa0525057225deb Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 17 Aug 2009 13:23:50 -0700 Subject: x86, pat: Allow ISA memory range uncacheable mapping requests Max Vozeler reported: > Bug 13877 - bogl-term broken with CONFIG_X86_PAT=y, works with =n > > strace of bogl-term: > 814 mmap2(NULL, 65536, PROT_READ|PROT_WRITE, MAP_SHARED, 4, 0) > = -1 EAGAIN (Resource temporarily unavailable) > 814 write(2, "bogl: mmaping /dev/fb0: Resource temporarily unavailable\n", > 57) = 57 PAT code maps the ISA memory range as WB in the PAT attribute, so that fixed range MTRR registers define the actual memory type (UC/WC/WT etc). But the upper level is_new_memtype_allowed() API checks are failing, as the request here is for UC and the return tracked type is WB (Tracked type is WB as MTRR type for this legacy range potentially will be different for each 4k page). Fix is_new_memtype_allowed() by always succeeding the ISA address range checks, as the null PAT (WB) and def MTRR fixed range register settings satisfy the memory type needs of the applications that map the ISA address range. Reported-and-Tested-by: Max Vozeler Signed-off-by: Suresh Siddha Signed-off-by: Venkatesh Pallipadi Signed-off-by: H. Peter Anvin --- arch/x86/mm/pat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index e6718bb28065..352aa9e927e2 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -623,7 +623,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, return ret; if (flags != want_flags) { - if (strict_prot || !is_new_memtype_allowed(want_flags, flags)) { + if (strict_prot || + !is_new_memtype_allowed(paddr, size, want_flags, flags)) { free_memtype(paddr, paddr + size); printk(KERN_ERR "%s:%d map pfn expected mapping type %s" " for %Lx-%Lx, got %s\n", -- cgit v1.2.2 From 3e0e1e9c5a327d4dba8490d83ef55c0564e6e8a7 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Fri, 21 Aug 2009 04:34:45 -0400 Subject: x86: Fix an incorrect argument of reserve_bootmem() This line looks suspicious, because if this is true, then the 'flags' parameter of function reserve_bootmem_generic() will be unused when !CONFIG_NUMA. I don't think this is what we want. Signed-off-by: WANG Cong Cc: Yinghai Lu Cc: akpm@linux-foundation.org LKML-Reference: <20090821083709.5098.52505.sendpatchset@localhost.localdomain> 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 6176fe8f29e0..ea56b8cbb6a6 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -796,7 +796,7 @@ int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, return ret; #else - reserve_bootmem(phys, len, BOOTMEM_DEFAULT); + reserve_bootmem(phys, len, flags); #endif if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) { -- cgit v1.2.2