- 12 2月, 2015 2 次提交
-
-
由 Andrea Arcangeli 提交于
This allows the get_user_pages_fast slow path to release the mmap_sem before blocking. Signed-off-by: NAndrea Arcangeli <aarcange@redhat.com> Reviewed-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andres Lagar-Cavilla <andreslc@google.com> Cc: Peter Feiner <pfeiner@google.com> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
由 Naoya Horiguchi 提交于
Currently we have many duplicates in definitions around follow_huge_addr(), follow_huge_pmd(), and follow_huge_pud(), so this patch tries to remove the m. The basic idea is to put the default implementation for these functions in mm/hugetlb.c as weak symbols (regardless of CONFIG_ARCH_WANT_GENERAL_HUGETL B), and to implement arch-specific code only when the arch needs it. For follow_huge_addr(), only powerpc and ia64 have their own implementation, and in all other architectures this function just returns ERR_PTR(-EINVAL). So this patch sets returning ERR_PTR(-EINVAL) as default. As for follow_huge_(pmd|pud)(), if (pmd|pud)_huge() is implemented to always return 0 in your architecture (like in ia64 or sparc,) it's never called (the callsite is optimized away) no matter how implemented it is. So in such architectures, we don't need arch-specific implementation. In some architecture (like mips, s390 and tile,) their current arch-specific follow_huge_(pmd|pud)() are effectively identical with the common code, so this patch lets these architecture use the common code. One exception is metag, where pmd_huge() could return non-zero but it expects follow_huge_pmd() to always return NULL. This means that we need arch-specific implementation which returns NULL. This behavior looks strange to me (because non-zero pmd_huge() implies that the architecture supports PMD-based hugepage, so follow_huge_pmd() can/should return some relevant value,) but that's beyond this cleanup patch, so let's keep it. Justification of non-trivial changes: - in s390, follow_huge_pmd() checks !MACHINE_HAS_HPAGE at first, and this patch removes the check. This is OK because we can assume MACHINE_HAS_HPAGE is true when follow_huge_pmd() can be called (note that pmd_huge() has the same check and always returns 0 for !MACHINE_HAS_HPAGE.) - in s390 and mips, we use HPAGE_MASK instead of PMD_MASK as done in common code. This patch forces these archs use PMD_MASK, but it's OK because they are identical in both archs. In s390, both of HPAGE_SHIFT and PMD_SHIFT are 20. In mips, HPAGE_SHIFT is defined as (PAGE_SHIFT + PAGE_SHIFT - 3) and PMD_SHIFT is define as (PAGE_SHIFT + PAGE_SHIFT + PTE_ORDER - 3), but PTE_ORDER is always 0, so these are identical. Signed-off-by: NNaoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: NHugh Dickins <hughd@google.com> Cc: James Hogan <james.hogan@imgtec.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Steve Capper <steve.capper@linaro.org> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 30 1月, 2015 1 次提交
-
-
由 Linus Torvalds 提交于
The core VM already knows about VM_FAULT_SIGBUS, but cannot return a "you should SIGSEGV" error, because the SIGSEGV case was generally handled by the caller - usually the architecture fault handler. That results in lots of duplication - all the architecture fault handlers end up doing very similar "look up vma, check permissions, do retries etc" - but it generally works. However, there are cases where the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV. In particular, when accessing the stack guard page, libsigsegv expects a SIGSEGV. And it usually got one, because the stack growth is handled by that duplicated architecture fault handler. However, when the generic VM layer started propagating the error return from the stack expansion in commit fee7e49d ("mm: propagate error from stack expansion even for guard page"), that now exposed the existing VM_FAULT_SIGBUS result to user space. And user space really expected SIGSEGV, not SIGBUS. To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those duplicate architecture fault handlers about it. They all already have the code to handle SIGSEGV, so it's about just tying that new return value to the existing code, but it's all a bit annoying. This is the mindless minimal patch to do this. A more extensive patch would be to try to gather up the mostly shared fault handling logic into one generic helper routine, and long-term we really should do that cleanup. Just from this patch, you can generally see that most architectures just copied (directly or indirectly) the old x86 way of doing things, but in the meantime that original x86 model has been improved to hold the VM semaphore for shorter times etc and to handle VM_FAULT_RETRY and other "newer" things, so it would be a good idea to bring all those improvements to the generic case and teach other architectures about them too. Reported-and-tested-by: NTakashi Iwai <tiwai@suse.de> Tested-by: NJan Engelhardt <jengelh@inai.de> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 08 1月, 2015 1 次提交
-
-
由 Martin Schwidefsky 提交于
pmd_to_page() is only available if USE_SPLIT_PMD_PTLOCKS is defined. The use of pmd_to_page in the gmap code can cause compile errors if NR_CPUS is smaller than SPLIT_PTLOCK_CPUS. Do not use pmd_to_page outside of USE_SPLIT_PMD_PTLOCKS sections. Reported-by: NMike Frysinger <vapier@gentoo.org> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 14 12月, 2014 1 次提交
-
-
由 Joonsoo Kim 提交于
Now, we have prepared to avoid using debug-pagealloc in boottime. So introduce new kernel-parameter to disable debug-pagealloc in boottime, and makes related functions to be disabled in this case. Only non-intuitive part is change of guard page functions. Because guard page is effective only if debug-pagealloc is enabled, turning off according to debug-pagealloc is reasonable thing to do. Signed-off-by: NJoonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Dave Hansen <dave@sr71.net> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Jungsoo Son <jungsoo.son@lge.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 28 11月, 2014 1 次提交
-
-
由 Jason J. Herne 提交于
Define get_guest_storage_key which can be used to get the value of a guest storage key. This compliments the functionality provided by the helper function set_guest_storage_key. Both functions are needed for live migration of s390 guests that use storage keys. Signed-off-by: NJason J. Herne <jjherne@linux.vnet.ibm.com> Reviewed-by: NDavid Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
- 21 11月, 2014 1 次提交
-
-
由 Heiko Carstens 提交于
It always confuses me to see the mixed instruction length code and interruption code on user space faults, while the message clearly says it is the interruption code. So split the value and print both values separately. Also add the ILC output to the die() message, so thar user and kernel space faults contain the same information. Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 10 11月, 2014 1 次提交
-
-
由 Thierry Reding 提交于
The xlate_dev_{kmem,mem}_ptr() functions take either a physical address or a kernel virtual address, so data types should be phys_addr_t and void *. They both return a kernel virtual address which is only ever used in calls to copy_{from,to}_user(), so make variables that store it void * rather than char * for consistency. Also only define a weak unxlate_dev_mem_ptr() function if architectures haven't overridden them in the asm/io.h header file. Signed-off-by: NThierry Reding <treding@nvidia.com>
-
- 03 11月, 2014 1 次提交
-
-
由 Martin Schwidefsky 提交于
The page table lock is acquired with a call to get_locked_pte, replace the plain spin_unlock with the correct unlock function pte_unmap_unlock. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 28 10月, 2014 1 次提交
-
-
由 Jason J. Herne 提交于
In set_guest_storage_key, we really want to reference the mm struct given as a parameter to the function. So replace the current->mm reference with the mm struct passed in by the caller. Signed-off-by: NJason J. Herne <jjherne@us.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
- 27 10月, 2014 5 次提交
-
-
由 Dominik Dingel 提交于
After fixup_user_fault does not fail we have a writeable pte. That pte might transform but it should not vanish. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Heiko Carstens 提交于
Use NOKPROBE_SYMBOL() instead of __kprobes annotation. Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Dominik Dingel 提交于
When storage keys are enabled unmerge already merged pages and prevent new pages from being merged. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Acked-by: NChristian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Dominik Dingel 提交于
As soon as storage keys are enabled we need to stop working on zero page mappings to prevent inconsistencies between storage keys and pgste. Otherwise following data corruption could happen: 1) guest enables storage key 2) guest sets storage key for not mapped page X -> change goes to PGSTE 3) guest reads from page X -> as X was not dirty before, the page will be zero page backed, storage key from PGSTE for X will go to storage key for zero page 4) guest sets storage key for not mapped page Y (same logic as above 5) guest reads from page Y -> as Y was not dirty before, the page will be zero page backed, storage key from PGSTE for Y will got to storage key for zero page overwriting storage key for X While holding the mmap sem, we are safe against changes on entries we already fixed, as every fault would need to take the mmap_sem (read). Other vCPUs executing storage key instructions will get a one time interception and be serialized also with mmap_sem. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Dominik Dingel 提交于
Replace the s390 specific page table walker for the pgste updates with a call to the common code walk_page_range function. There are now two pte modification functions, one for the reset of the CMMA state and another one for the initialization of the storage keys. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 15 10月, 2014 1 次提交
-
-
由 Dominik Dingel 提交于
pte_unmap works on page table entry pointers, derefencing should be avoided. As on s390 pte_unmap is a NOP, this is more a cleanup if we want to supply later such function. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Reviewed-by: NThomas Huth <thuth@linux.vnet.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 30 9月, 2014 1 次提交
-
-
由 Heiko Carstens 提交于
Invalidate several pte entries at once if the ipte range facility is available. Currently this works only for DEBUG_PAGE_ALLOC where several up to 2 ^ MAX_ORDER may be invalidated at once. Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 25 9月, 2014 2 次提交
-
-
由 Heiko Carstens 提交于
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Heiko Carstens 提交于
If the vmemmap array gets filled with large pages we allocate those pages with vmemmap_alloc_block(), which returns cleared pages. Only for single 4k pages we call our own vmem_alloc_pages() which does not return cleared pages. However we can also call vmemmap_alloc_block() to allocate the 4k pages. This way we can also make sure the vmemmap array is cleared after its population. Therefore we can remove the memset at the end of the function which would clear the vmmemmap array a second time on machines which do support EDAT1. On very large configurations this can save us several seconds. Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 14 9月, 2014 1 次提交
-
-
由 Ard Biesheuvel 提交于
In order to make the static inline function is_zero_pfn() callable by modules, export its symbol dependencies 'zero_pfn' and (for s390 and mips) 'zero_page_mask'. We need this for KVM, as CONFIG_KVM is a tristate for all supported architectures except ARM and arm64, and testing a pfn whether it refers to the zero page is required to correctly distinguish the zero page from other special RAM ranges that may also have the PG_reserved bit set, but need to be treated as MMIO memory. Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
-
- 29 8月, 2014 1 次提交
-
-
由 Christian Borntraeger 提交于
commit ab3f285f ("KVM: s390/mm: try a cow on read only pages for key ops")' misaligned a code block. Let's fixup the indentation. Reported-by: NBen Hutchings <ben@decadent.org.uk> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
-
- 26 8月, 2014 2 次提交
-
-
由 Martin Schwidefsky 提交于
Add an addressing limit to the gmap address spaces and only allocate the page table levels that are needed for the given limit. The limit is fixed and can not be changed after a gmap has been created. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
由 Martin Schwidefsky 提交于
Store the target address for the gmap segments in a radix tree instead of using invalid segment table entries. gmap_translate becomes a simple radix_tree_lookup, gmap_fault is split into the address translation with gmap_translate and the part that does the linking of the gmap shadow page table with the process page table. A second radix tree is used to keep the pointers to the segment table entries for segments that are mapped in the guest address space. On unmap of a segment the pointer is retrieved from the radix tree and is used to carry out the segment invalidation in the gmap shadow page table. As the radix tree can only store one pointer, each host segment may only be mapped to exactly one guest location. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
- 25 8月, 2014 3 次提交
-
-
由 Martin Schwidefsky 提交于
Make the order of arguments for the gmap calls more consistent, if the gmap pointer is passed it is always the first argument. In addition distinguish between guest address and user address by naming the variables gaddr for a guest address and vmaddr for a user address. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
由 Martin Schwidefsky 提交于
Revert git commit c3a23b9874c1 ("remove unnecessary parameter from gmap_do_ipte_notify"). Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
由 Christian Borntraeger 提交于
The PFMF instruction handler blindly wrote the storage key even if the page was mapped R/O in the host. Lets try a COW before continuing and bail out in case of errors. Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Cc: stable@vger.kernel.org
-
- 01 8月, 2014 2 次提交
-
-
由 Martin Schwidefsky 提交于
The large segment table entry format has block of bits for the ACC/F values for the large page. These bits are valid only if another bit (AV bit 0x10000) of the segment table entry is set. The ACC/F bits do not have a meaning if the AV bit is off. This allows to put the THP splitting bit, the segment young bit and the new segment dirty bit into the ACC/F bits as long as the AV bit stays off. The dirty and young information is only available if the pmd is large. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Christian Borntraeger 提交于
commit ec66ad66 (s390/mm: enable split page table lock for PMD level) activated the split pmd lock for s390. Turns out that we missed one place: We also have to take the pmd lock instead of the page table lock when we reallocate the page tables (==> changing entries in the PMD) during sie enablement. Cc: stable@vger.kernel.org # 3.15+ Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 05 6月, 2014 1 次提交
-
-
由 Naoya Horiguchi 提交于
Currently hugepage migration is available for all archs which support pmd-level hugepage, but testing is done only for x86_64 and there're bugs for other archs. So to avoid breaking such archs, this patch limits the availability strictly to x86_64 until developers of other archs get interested in enabling this feature. Simply disabling hugepage migration on non-x86_64 archs is not enough to fix the reported problem where sys_move_pages() hits the BUG_ON() in follow_page(FOLL_GET), so let's fix this by checking if hugepage migration is supported in vma_migratable(). Signed-off-by: NNaoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reported-by: NMichael Ellerman <mpe@ellerman.id.au> Tested-by: NMichael Ellerman <mpe@ellerman.id.au> Acked-by: NHugh Dickins <hughd@google.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: James Hogan <james.hogan@imgtec.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Miller <davem@davemloft.net> Cc: <stable@vger.kernel.org> [3.12+] Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 20 5月, 2014 4 次提交
-
-
由 Martin Schwidefsky 提交于
The oi and ni instructions used in entry[64].S to set and clear bits in the thread-flags are not guaranteed to be atomic in regard to other CPUs. Split the TIF bits into CPU, pt_regs and thread-info specific bits. Updates on the TIF bits are done with atomic instructions, updates on CPU and pt_regs bits are done with non-atomic instructions. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Martin Schwidefsky 提交于
Always switch to the kernel ASCE in switch_mm. Load the secondary space ASCE in finish_arch_post_lock_switch after checking that any pending page table operations have completed. The primary ASCE is loaded in entry[64].S. With this the update_primary_asce call can be removed from the switch_to macro and from the start of switch_mm function. Remove the load_primary argument from update_user_asce/clear_user_asce, rename update_user_asce to set_user_asce and rename update_primary_asce to load_kernel_asce. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Heiko Carstens 提交于
This is not necessary anymore, since the offending code is gone with the conversion to the memblock code. Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>- Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
由 Philipp Hachtmann 提交于
The original bootmem allocator is getting replaced by memblock. To cover the needs of the s390 kdump implementation the physical memory list is used. With this patch the bootmem allocator and its bitmaps are completely removed from s390. Signed-off-by: NPhilipp Hachtmann <phacht@linux.vnet.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 16 5月, 2014 1 次提交
-
-
由 Martin Schwidefsky 提交于
Use the mm semaphore to serialize multiple invocations of s390_enable_skey. The second CPU faulting on a storage key operation needs to wait for the completion of the page table update. Taking the mm semaphore writable has the positive side-effect that it prevents any host faults from taking place which does have implications on keys vs PGSTE. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
- 22 4月, 2014 4 次提交
-
-
由 Dominik Dingel 提交于
For live migration kvm needs to test and clear the dirty bit of guest pages. That for is ptep_test_and_clear_user_dirty, to be sure we are not racing with other code, we protect the pte. This needs to be done within the architecture memory management code. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Acked-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
由 Martin Schwidefsky 提交于
Switch the user dirty bit detection used for migration from the hardware provided host change-bit in the pgste to a fault based detection method. This reduced the dependency of the host from the storage key to a point where it becomes possible to enable the RCP bypass for KVM guests. The fault based dirty detection will only indicate changes caused by accesses via the guest address space. The hardware based method can detect all changes, even those caused by I/O or accesses via the kernel page table. The KVM/qemu code needs to take this into account. Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
由 Dominik Dingel 提交于
Introduce a new function s390_enable_skey(), which enables storage key handling via setting the use_skey flag in the mmu context. This function is only useful within the context of kvm. Note that enabling storage keys will cause a one-time hickup when walking the page table; however, it saves us special effort for cases like clear reset while making it possible for us to be architecture conform. s390_enable_skey() takes the page table lock to prevent reseting storage keys triggered from multiple vcpus. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Acked-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
由 Dominik Dingel 提交于
page_table_reset_pgste() already does a complete page table walk to reset the pgste. Enhance it to initialize the storage keys to PAGE_DEFAULT_KEY if requested by the caller. This will be used for lazy storage key handling. Also provide an empty stub for !CONFIG_PGSTE Lets adopt the current code (diag 308) to not clear the keys. Signed-off-by: NDominik Dingel <dingel@linux.vnet.ibm.com> Acked-by: NMartin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
-
- 09 4月, 2014 1 次提交
-
-
由 Heiko Carstens 提交于
Print extra debugging information to the console if the kernel or a user space process crashed (with user space debugging enabled): - contents of control register 7 and 13 - failing address and translation exception identification - page table walk for the failing address Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
-
- 08 4月, 2014 1 次提交
-
-
由 Alex Thorlton 提交于
The main motivation behind this patch is to provide a way to disable THP for jobs where the code cannot be modified, and using a malloc hook with madvise is not an option (i.e. statically allocated data). This patch allows us to do just that, without affecting other jobs running on the system. We need to do this sort of thing for jobs where THP hurts performance, due to the possibility of increased remote memory accesses that can be created by situations such as the following: When you touch 1 byte of an untouched, contiguous 2MB chunk, a THP will be handed out, and the THP will be stuck on whatever node the chunk was originally referenced from. If many remote nodes need to do work on that same chunk, they'll be making remote accesses. With THP disabled, 4K pages can be handed out to separate nodes as they're needed, greatly reducing the amount of remote accesses to memory. This patch is based on some of my work combined with some suggestions/patches given by Oleg Nesterov. The main goal here is to add a prctl switch to allow us to disable to THP on a per mm_struct basis. Here's a bit of test data with the new patch in place... First with the flag unset: # perf stat -a ./prctl_wrapper_mmv3 0 ./thp_pthread -C 0 -m 0 -c 512 -b 256g Setting thp_disabled for this task... thp_disable: 0 Set thp_disabled state to 0 Process pid = 18027 PF/ MAX MIN TOTCPU/ TOT_PF/ TOT_PF/ WSEC/ TYPE: CPUS WALL WALL SYS USER TOTCPU CPU WALL_SEC SYS_SEC CPU NODES 512 1.120 0.060 0.000 0.110 0.110 0.000 28571428864 -9223372036854775808 55803572 23 Performance counter stats for './prctl_wrapper_mmv3_hack 0 ./thp_pthread -C 0 -m 0 -c 512 -b 256g': 273719072.841402 task-clock # 641.026 CPUs utilized [100.00%] 1,008,986 context-switches # 0.000 M/sec [100.00%] 7,717 CPU-migrations # 0.000 M/sec [100.00%] 1,698,932 page-faults # 0.000 M/sec 355,222,544,890,379 cycles # 1.298 GHz [100.00%] 536,445,412,234,588 stalled-cycles-frontend # 151.02% frontend cycles idle [100.00%] 409,110,531,310,223 stalled-cycles-backend # 115.17% backend cycles idle [100.00%] 148,286,797,266,411 instructions # 0.42 insns per cycle # 3.62 stalled cycles per insn [100.00%] 27,061,793,159,503 branches # 98.867 M/sec [100.00%] 1,188,655,196 branch-misses # 0.00% of all branches 427.001706337 seconds time elapsed Now with the flag set: # perf stat -a ./prctl_wrapper_mmv3 1 ./thp_pthread -C 0 -m 0 -c 512 -b 256g Setting thp_disabled for this task... thp_disable: 1 Set thp_disabled state to 1 Process pid = 144957 PF/ MAX MIN TOTCPU/ TOT_PF/ TOT_PF/ WSEC/ TYPE: CPUS WALL WALL SYS USER TOTCPU CPU WALL_SEC SYS_SEC CPU NODES 512 0.620 0.260 0.250 0.320 0.570 0.001 51612901376 128000000000 100806448 23 Performance counter stats for './prctl_wrapper_mmv3_hack 1 ./thp_pthread -C 0 -m 0 -c 512 -b 256g': 138789390.540183 task-clock # 641.959 CPUs utilized [100.00%] 534,205 context-switches # 0.000 M/sec [100.00%] 4,595 CPU-migrations # 0.000 M/sec [100.00%] 63,133,119 page-faults # 0.000 M/sec 147,977,747,269,768 cycles # 1.066 GHz [100.00%] 200,524,196,493,108 stalled-cycles-frontend # 135.51% frontend cycles idle [100.00%] 105,175,163,716,388 stalled-cycles-backend # 71.07% backend cycles idle [100.00%] 180,916,213,503,160 instructions # 1.22 insns per cycle # 1.11 stalled cycles per insn [100.00%] 26,999,511,005,868 branches # 194.536 M/sec [100.00%] 714,066,351 branch-misses # 0.00% of all branches 216.196778807 seconds time elapsed As with previous versions of the patch, We're getting about a 2x performance increase here. Here's a link to the test case I used, along with the little wrapper to activate the flag: http://oss.sgi.com/projects/memtests/thp_pthread_mmprctlv3.tar.gz This patch (of 3): Revert commit 8e72033f and add in code to fix up any issues caused by the revert. The revert is necessary because hugepage_madvise would return -EINVAL when VM_NOHUGEPAGE is set, which will break subsequent chunks of this patch set. Here's a snip of an e-mail from Gerald detailing the original purpose of this code, and providing justification for the revert: "The intent of commit 8e72033f was to guard against any future programming errors that may result in an madvice(MADV_HUGEPAGE) on guest mappings, which would crash the kernel. Martin suggested adding the bit to arch/s390/mm/pgtable.c, if 8e72033f was to be reverted, because that check will also prevent a kernel crash in the case described above, it will now send a SIGSEGV instead. This would now also allow to do the madvise on other parts, if needed, so it is a more flexible approach. One could also say that it would have been better to do it this way right from the beginning..." Signed-off-by: NAlex Thorlton <athorlton@sgi.com> Suggested-by: NOleg Nesterov <oleg@redhat.com> Tested-by: NChristian Borntraeger <borntraeger@de.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-