1. 09 Dec, 2017 1 commit
  2. 09 Sep, 2017 2 commits
    • Daniel Micay's avatar
      init/main.c: extract early boot entropy from the passed cmdline · 33d72f38
      Daniel Micay authored
      Feed the boot command-line as to the /dev/random entropy pool
      Existing Android bootloaders usually pass data which may not be known by
      an external attacker on the kernel command-line.  It may also be the
      case on other embedded systems.  Sample command-line from a Google Pixel
      running CopperheadOS....
          console=ttyHSL0,115200,n8 androidboot.console=ttyHSL0
          androidboot.hardware=sailfish user_debug=31 ehci-hcd.park=3
          lpm_levels.sleep_disabled=1 cma=32M@0-0xffffffff buildvariant=user
          androidboot.bootdevice=624000.ufshc androidboot.verifiedbootstate=yellow
          androidboot.veritymode=enforcing androidboot.keymaster=1
          androidboot.serialno=FA6CE0305299 androidboot.baseband=msm
          androidboot.slot_suffix=_b fpsimd.fpsimd_settings=0
          app_setting.use_app_setting=0 kernelflag=0x00000000 debugflag=0x00000000
          androidboot.hardware.revision=PVT radioflag=0x00000000
          radioflagex1=0x00000000 radioflagex2=0x00000000 cpumask=0x00000000
          androidboot.hardware.ddr=4096MB,Hynix,LPDDR4 androidboot.ddrinfo=00000006
          androidboot.ddrsize=4GB androidboot.hardware.color=GRA00
          androidboot.hardware.ufs=32GB,Samsung androidboot.msm.hw_ver_id=268824801
          androidboot.qf.st=2 androidboot.cid=11111111 androidboot.mid=G-2PW4100
          androidboot.oem_unlock_support=1 androidboot.fp_src=1
          androidboot.htc.hrdump=detected androidboot.ramdump.opt=mem@2g:2g,mem@4g:2g
          androidboot.bootreason=reboot androidboot.ramdump_enable=0 ro
          root=/dev/dm-0 dm="system none ro,0 1 android-verity /dev/sda34"
          rootwait skip_initramfs init=/init androidboot.wificountrycode=US
      Among other things, it contains a value unique to the device
      (androidboot.serialno=FA6CE0305299), unique to the OS builds for the
      device variant (veritykeyid=id:dfcb9db0089e5b3b4090a592415c28e1cb4545ab)
      and timings from the bootloader stages in milliseconds
      [tytso@mit.edu: changelog tweak]
      [labbott@redhat.com: line-wrapped command line]
      Link: http://lkml.kernel.org/r/20170816231458.2299-3-labbott@redhat.comSigned-off-by: default avatarDaniel Micay <danielmicay@gmail.com>
      Signed-off-by: default avatarLaura Abbott <labbott@redhat.com>
      Acked-by: default avatarKees Cook <keescook@chromium.org>
      Cc: "Theodore Ts'o" <tytso@mit.edu>
      Cc: Laura Abbott <lauraa@codeaurora.org>
      Cc: Nick Kralevich <nnk@google.com>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
    • Laura Abbott's avatar
      init: move stack canary initialization after setup_arch · 121388a3
      Laura Abbott authored
      Patch series "Command line randomness", v3.
      A series to add the kernel command line as a source of randomness.
      This patch (of 2):
      Stack canary intialization involves getting a random number.  Getting this
      random number may involve accessing caches or other architectural specific
      features which are not available until after the architecture is setup.
      Move the stack canary initialization later to accommodate this.
      Link: http://lkml.kernel.org/r/20170816231458.2299-2-labbott@redhat.comSigned-off-by: default avatarLaura Abbott <lauraa@codeaurora.org>
      Signed-off-by: default avatarLaura Abbott <labbott@redhat.com>
      Acked-by: default avatarKees Cook <keescook@chromium.org>
      Cc: "Theodore Ts'o" <tytso@mit.edu>
      Cc: Daniel Micay <danielmicay@gmail.com>
      Cc: Nick Kralevich <nnk@google.com>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
  3. 07 Sep, 2017 1 commit
  4. 14 Aug, 2017 1 commit
    • Waiman Long's avatar
      debugobjects: Make kmemleak ignore debug objects · caba4cbb
      Waiman Long authored
      The allocated debug objects are either on the free list or in the
      hashed bucket lists. So they won't get lost. However if both debug
      objects and kmemleak are enabled and kmemleak scanning is done
      while some of the debug objects are transitioning from one list to
      the others, false negative reporting of memory leaks may happen for
      those objects. For example,
      [38687.275678] kmemleak: 12 new suspected memory leaks (see
      unreferenced object 0xffff92e98aabeb68 (size 40):
        comm "ksmtuned", pid 4344, jiffies 4298403600 (age 906.430s)
        hex dump (first 32 bytes):
          00 00 00 00 00 00 00 00 d0 bc db 92 e9 92 ff ff  ................
          01 00 00 00 00 00 00 00 38 36 8a 61 e9 92 ff ff  ........86.a....
          [<ffffffff8fa5378a>] kmemleak_alloc+0x4a/0xa0
          [<ffffffff8f47c019>] kmem_cache_alloc+0xe9/0x320
          [<ffffffff8f62ed96>] __debug_object_init+0x3e6/0x400
          [<ffffffff8f62ef01>] debug_object_activate+0x131/0x210
          [<ffffffff8f330d9f>] __call_rcu+0x3f/0x400
          [<ffffffff8f33117d>] call_rcu_sched+0x1d/0x20
          [<ffffffff8f4a183c>] put_object+0x2c/0x40
          [<ffffffff8f4a188c>] __delete_object+0x3c/0x50
          [<ffffffff8f4a18bd>] delete_object_full+0x1d/0x20
          [<ffffffff8fa535c2>] kmemleak_free+0x32/0x80
          [<ffffffff8f47af07>] kmem_cache_free+0x77/0x350
          [<ffffffff8f453912>] unlink_anon_vmas+0x82/0x1e0
          [<ffffffff8f440341>] free_pgtables+0xa1/0x110
          [<ffffffff8f44af91>] exit_mmap+0xc1/0x170
          [<ffffffff8f29db60>] mmput+0x80/0x150
          [<ffffffff8f2a7609>] do_exit+0x2a9/0xd20
      The references in the debug objects may also hide a real memory leak.
      As there is no point in having kmemleak to track debug object
      allocations, kmemleak checking is now disabled for debug objects.
      Signed-off-by: default avatarWaiman Long <longman@redhat.com>
      Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Link: http://lkml.kernel.org/r/1502718733-8527-1-git-send-email-longman@redhat.com
  5. 10 Aug, 2017 1 commit
  6. 26 Jul, 2017 1 commit
    • Dennis Zhou (Facebook)'s avatar
      percpu: replace area map allocator with bitmap · 40064aec
      Dennis Zhou (Facebook) authored
      The percpu memory allocator is experiencing scalability issues when
      allocating and freeing large numbers of counters as in BPF.
      Additionally, there is a corner case where iteration is triggered over
      all chunks if the contig_hint is the right size, but wrong alignment.
      This patch replaces the area map allocator with a basic bitmap allocator
      implementation. Each subsequent patch will introduce new features and
      replace full scanning functions with faster non-scanning options when
      This patchset removes the area map allocator in favor of a bitmap
      allocator backed by metadata blocks. The primary goal is to provide
      consistency in performance and memory footprint with a focus on small
      allocations (< 64 bytes). The bitmap removes the heavy memmove from the
      freeing critical path and provides a consistent memory footprint. The
      metadata blocks provide a bound on the amount of scanning required by
      maintaining a set of hints.
      In an effort to make freeing fast, the metadata is updated on the free
      path if the new free area makes a page free, a block free, or spans
      across blocks. This causes the chunk's contig hint to potentially be
      smaller than what it could allocate by up to the smaller of a page or a
      block. If the chunk's contig hint is contained within a block, a check
      occurs and the hint is kept accurate. Metadata is always kept accurate
      on allocation, so there will not be a situation where a chunk has a
      later contig hint than available.
      I have primarily done testing against a simple workload of allocation of
      1 million objects (2^20) of varying size. Deallocation was done by in
      order, alternating, and in reverse. These numbers were collected after
      rebasing ontop of a80099a1. I present the worst-case numbers here:
        Area Map Allocator:
              Object Size | Alloc Time (ms) | Free Time (ms)
                    4B    |        310      |     4770
                   16B    |        557      |     1325
                   64B    |        436      |      273
                  256B    |        776      |      131
                 1024B    |       3280      |      122
        Bitmap Allocator:
              Object Size | Alloc Time (ms) | Free Time (ms)
                    4B    |        490      |       70
                   16B    |        515      |       75
                   64B    |        610      |       80
                  256B    |        950      |      100
                 1024B    |       3520      |      200
      This data demonstrates the inability for the area map allocator to
      handle less than ideal situations. In the best case of reverse
      deallocation, the area map allocator was able to perform within range
      of the bitmap allocator. In the worst case situation, freeing took
      nearly 5 seconds for 1 million 4-byte objects. The bitmap allocator
      dramatically improves the consistency of the free path. The small
      allocations performed nearly identical regardless of the freeing
      While it does add to the allocation latency, the allocation scenario
      here is optimal for the area map allocator. The area map allocator runs
      into trouble when it is allocating in chunks where the latter half is
      full. It is difficult to replicate this, so I present a variant where
      the pages are second half filled. Freeing was done sequentially. Below
      are the numbers for this scenario:
        Area Map Allocator:
              Object Size | Alloc Time (ms) | Free Time (ms)
                    4B    |       4118      |     4892
                   16B    |       1651      |     1163
                   64B    |        598      |      285
                  256B    |        771      |      158
                 1024B    |       3034      |      160
        Bitmap Allocator:
              Object Size | Alloc Time (ms) | Free Time (ms)
                    4B    |        481      |       67
                   16B    |        506      |       69
                   64B    |        636      |       75
                  256B    |        892      |       90
                 1024B    |       3262      |      147
      The data shows a parabolic curve of performance for the area map
      allocator. This is due to the memmove operation being the dominant cost
      with the lower object sizes as more objects are packed in a chunk and at
      higher object sizes, the traversal of the chunk slots is the dominating
      cost. The bitmap allocator suffers this problem as well. The above data
      shows the inability to scale for the allocation path with the area map
      allocator and that the bitmap allocator demonstrates consistent
      performance in general.
      The second problem of additional scanning can result in the area map
      allocator completing in 52 minutes when trying to allocate 1 million
      4-byte objects with 8-byte alignment. The same workload takes
      approximately 16 seconds to complete for the bitmap allocator.
      Fixed a bug in pcpu_alloc_first_chunk end_offset was setting the bitmap
      using bytes instead of bits.
      Added a comment to pcpu_cnt_pop_pages to explain bitmap_weight.
      Signed-off-by: default avatarDennis Zhou <dennisszhou@gmail.com>
      Reviewed-by: default avatarJosef Bacik <jbacik@fb.com>
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
  7. 18 Jul, 2017 1 commit
    • Tom Lendacky's avatar
      x86, swiotlb: Add memory encryption support · c7753208
      Tom Lendacky authored
      Since DMA addresses will effectively look like 48-bit addresses when the
      memory encryption mask is set, SWIOTLB is needed if the DMA mask of the
      device performing the DMA does not support 48-bits. SWIOTLB will be
      initialized to create decrypted bounce buffers for use by these devices.
      Signed-off-by: default avatarTom Lendacky <thomas.lendacky@amd.com>
      Reviewed-by: default avatarThomas Gleixner <tglx@linutronix.de>
      Cc: Alexander Potapenko <glider@google.com>
      Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
      Cc: Andy Lutomirski <luto@kernel.org>
      Cc: Arnd Bergmann <arnd@arndb.de>
      Cc: Borislav Petkov <bp@alien8.de>
      Cc: Brijesh Singh <brijesh.singh@amd.com>
      Cc: Dave Young <dyoung@redhat.com>
      Cc: Dmitry Vyukov <dvyukov@google.com>
      Cc: Jonathan Corbet <corbet@lwn.net>
      Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
      Cc: Larry Woodman <lwoodman@redhat.com>
      Cc: Linus Torvalds <torvalds@linux-foundation.org>
      Cc: Matt Fleming <matt@codeblueprint.co.uk>
      Cc: Michael S. Tsirkin <mst@redhat.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Radim Krčmář <rkrcmar@redhat.com>
      Cc: Rik van Riel <riel@redhat.com>
      Cc: Toshimitsu Kani <toshi.kani@hpe.com>
      Cc: kasan-dev@googlegroups.com
      Cc: kvm@vger.kernel.org
      Cc: linux-arch@vger.kernel.org
      Cc: linux-doc@vger.kernel.org
      Cc: linux-efi@vger.kernel.org
      Cc: linux-mm@kvack.org
      Link: http://lkml.kernel.org/r/aa2d29b78ae7d508db8881e46a3215231b9327a7.1500319216.git.thomas.lendacky@amd.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
  8. 12 Jul, 2017 1 commit
    • Kees Cook's avatar
      random: do not ignore early device randomness · ee7998c5
      Kees Cook authored
      The add_device_randomness() function would ignore incoming bytes if the
      crng wasn't ready.  This additionally makes sure to make an early enough
      call to add_latent_entropy() to influence the initial stack canary,
      which is especially important on non-x86 systems where it stays the same
      through the life of the boot.
      Link: http://lkml.kernel.org/r/20170626233038.GA48751@beastSigned-off-by: default avatarKees Cook <keescook@chromium.org>
      Cc: "Theodore Ts'o" <tytso@mit.edu>
      Cc: Arnd Bergmann <arnd@arndb.de>
      Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
      Cc: Ingo Molnar <mingo@kernel.org>
      Cc: Jessica Yu <jeyu@redhat.com>
      Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
      Cc: Viresh Kumar <viresh.kumar@linaro.org>
      Cc: Tejun Heo <tj@kernel.org>
      Cc: Prarit Bhargava <prarit@redhat.com>
      Cc: Lokesh Vutla <lokeshvutla@ti.com>
      Cc: Nicholas Piggin <npiggin@gmail.com>
      Cc: AKASHI Takahiro <takahiro.akashi@linaro.org>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
  9. 23 May, 2017 2 commits
  10. 24 Apr, 2017 2 commits
  11. 18 Apr, 2017 1 commit
  12. 03 Apr, 2017 1 commit
    • Steven Rostedt (VMware)'s avatar
      ftrace: Have init/main.c call ftrace directly to free init memory · b80f0f6c
      Steven Rostedt (VMware) authored
      Relying on free_reserved_area() to call ftrace to free init memory proved to
      not be sufficient. The issue is that on x86, when debug_pagealloc is
      enabled, the init memory is not freed, but simply set as not present. Since
      ftrace was uninformed of this, starting function tracing still tries to
      update pages that are not present according to the page tables, causing
      ftrace to bug, as well as killing the kernel itself.
      Instead of relying on free_reserved_area(), have init/main.c call ftrace
      directly just before it frees the init memory. Then it needs to use
      __init_begin and __init_end to know where the init memory location is.
      Looking at all archs (and testing what I can), it appears that this should
      work for each of them.
      Reported-by: default avatarkernel test robot <xiaolong.ye@intel.com>
      Reported-by: default avatarFengguang Wu <fengguang.wu@intel.com>
      Signed-off-by: default avatarSteven Rostedt (VMware) <rostedt@goodmis.org>
  13. 01 Apr, 2017 1 commit
    • Michal Hocko's avatar
      mm: move mm_percpu_wq initialization earlier · 597b7305
      Michal Hocko authored
      Yang Li has reported that drain_all_pages triggers a WARN_ON which means
      that this function is called earlier than the mm_percpu_wq is
      initialized on arm64 with CMA configured:
        WARNING: CPU: 2 PID: 1 at mm/page_alloc.c:2423 drain_all_pages+0x244/0x25c
        Modules linked in:
        CPU: 2 PID: 1 Comm: swapper/0 Not tainted 4.11.0-rc1-next-20170310-00027-g64dfbc5 #127
        Hardware name: Freescale Layerscape 2088A RDB Board (DT)
        task: ffffffc07c4a6d00 task.stack: ffffffc07c4a8000
        PC is at drain_all_pages+0x244/0x25c
        LR is at start_isolate_page_range+0x14c/0x1f0
      Fix this by moving the whole setup_vmstat which is an initcall right now
      to init_mm_internals which will be called right after the WQ subsystem
      is initialized.
      Link: http://lkml.kernel.org/r/20170315164021.28532-1-mhocko@kernel.orgSigned-off-by: default avatarMichal Hocko <mhocko@suse.com>
      Reported-by: default avatarYang Li <pku.leo@gmail.com>
      Tested-by: default avatarYang Li <pku.leo@gmail.com>
      Tested-by: default avatarXiaolong Ye <xiaolong.ye@intel.com>
      Cc: Mel Gorman <mgorman@suse.de>
      Cc: Vlastimil Babka <vbabka@suse.cz>
      Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
  14. 24 Mar, 2017 2 commits
  15. 02 Mar, 2017 5 commits
  16. 28 Feb, 2017 2 commits
  17. 14 Feb, 2017 1 commit
    • Matthew Wilcox's avatar
      Reimplement IDR and IDA using the radix tree · 0a835c4f
      Matthew Wilcox authored
      The IDR is very similar to the radix tree.  It has some functionality that
      the radix tree did not have (alloc next free, cyclic allocation, a
      callback-based for_each, destroy tree), which is readily implementable on
      top of the radix tree.  A few small changes were needed in order to use a
      tag to represent nodes with free space below them.  More extensive
      changes were needed to support storing NULL as a valid entry in an IDR.
      Plain radix trees still interpret NULL as a not-present entry.
      The IDA is reimplemented as a client of the newly enhanced radix tree.  As
      in the current implementation, it uses a bitmap at the last level of the
      Signed-off-by: default avatarMatthew Wilcox <willy@infradead.org>
      Signed-off-by: default avatarMatthew Wilcox <mawilcox@microsoft.com>
      Tested-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
      Cc: Konstantin Khlebnikov <koct9i@gmail.com>
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Cc: Tejun Heo <tj@kernel.org>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
  18. 09 Feb, 2017 1 commit
    • Paul Gortmaker's avatar
      core: migrate exception table users off module.h and onto extable.h · 8a293be0
      Paul Gortmaker authored
      These files were including module.h for exception table related
      functions.  We've now separated that content out into its own file
      "extable.h" so now move over to that and where possible, avoid all
      the extra header content in module.h that we don't really need to
      compile these non-modular files.
         init/main.c still needs module.h for __init_or_module
         kernel/extable.c still needs module.h for is_module_text_address
      ...and so we don't get the benefit of removing module.h from the cpp
      feed for these two files, unlike the almost universal 1:1 exchange
      of module.h for extable.h we were able to do in the arch dirs.
      Cc: Rusty Russell <rusty@rustcorp.com.au>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: Linus Torvalds <torvalds@linux-foundation.org>
      Acked-by: default avatarJessica Yu <jeyu@redhat.com>
      Signed-off-by: default avatarPaul Gortmaker <paul.gortmaker@windriver.com>
  19. 08 Feb, 2017 1 commit
  20. 07 Feb, 2017 1 commit
  21. 01 Feb, 2017 1 commit
  22. 27 Jan, 2017 1 commit
    • Jason A. Donenfeld's avatar
      random: use chacha20 for get_random_int/long · f5b98461
      Jason A. Donenfeld authored
      Now that our crng uses chacha20, we can rely on its speedy
      characteristics for replacing MD5, while simultaneously achieving a
      higher security guarantee. Before the idea was to use these functions if
      you wanted random integers that aren't stupidly insecure but aren't
      necessarily secure either, a vague gray zone, that hopefully was "good
      enough" for its users. With chacha20, we can strengthen this claim,
      since either we're using an rdrand-like instruction, or we're using the
      same crng as /dev/urandom. And it's faster than what was before.
      We could have chosen to replace this with a SipHash-derived function,
      which might be slightly faster, but at the cost of having yet another
      RNG construction in the kernel. By moving to chacha20, we have a single
      RNG to analyze and verify, and we also already get good performance
      improvements on all platforms.
      Implementation-wise, rather than use a generic buffer for both
      get_random_int/long and memcpy based on the size needs, we use a
      specific buffer for 32-bit reads and for 64-bit reads. This way, we're
      guaranteed to always have aligned accesses on all platforms. While
      slightly more verbose in C, the assembly this generates is a lot
      simpler than otherwise.
      Finally, on 32-bit platforms where longs and ints are the same size,
      we simply alias get_random_int to get_random_long.
      Signed-off-by: default avatarJason A. Donenfeld <Jason@zx2c4.com>
      Suggested-by: default avatarTheodore Ts'o <tytso@mit.edu>
      Cc: Theodore Ts'o <tytso@mit.edu>
      Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
      Cc: Andy Lutomirski <luto@amacapital.net>
      Signed-off-by: default avatarTheodore Ts'o <tytso@mit.edu>
  23. 14 Jan, 2017 1 commit
    • Peter Zijlstra's avatar
      sched/clock: Delay switching sched_clock to stable · 9881b024
      Peter Zijlstra authored
      Currently we switch to the stable sched_clock if we guess the TSC is
      usable, and then switch back to the unstable path if it turns out TSC
      isn't stable during SMP bringup after all.
      Delay switching to the stable path until after SMP bringup is
      complete. This way we'll avoid switching during the time we detect the
      worst of the TSC offences.
      Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
      Cc: Linus Torvalds <torvalds@linux-foundation.org>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: linux-kernel@vger.kernel.org
      Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
  24. 25 Dec, 2016 1 commit
    • Nicholas Piggin's avatar
      mm: add PageWaiters indicating tasks are waiting for a page bit · 62906027
      Nicholas Piggin authored
      Add a new page flag, PageWaiters, to indicate the page waitqueue has
      tasks waiting. This can be tested rather than testing waitqueue_active
      which requires another cacheline load.
      This bit is always set when the page has tasks on page_waitqueue(page),
      and is set and cleared under the waitqueue lock. It may be set when
      there are no tasks on the waitqueue, which will cause a harmless extra
      wakeup check that will clears the bit.
      The generic bit-waitqueue infrastructure is no longer used for pages.
      Instead, waitqueues are used directly with a custom key type. The
      generic code was not flexible enough to have PageWaiters manipulation
      under the waitqueue lock (which simplifies concurrency).
      This improves the performance of page lock intensive microbenchmarks by
      Putting two bits in the same word opens the opportunity to remove the
      memory barrier between clearing the lock bit and testing the waiters
      bit, after some work on the arch primitives (e.g., ensuring memory
      operand widths match and cover both bits).
      Signed-off-by: default avatarNicholas Piggin <npiggin@gmail.com>
      Cc: Dave Hansen <dave.hansen@linux.intel.com>
      Cc: Bob Peterson <rpeterso@redhat.com>
      Cc: Steven Whitehouse <swhiteho@redhat.com>
      Cc: Andrew Lutomirski <luto@kernel.org>
      Cc: Andreas Gruenbacher <agruenba@redhat.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Mel Gorman <mgorman@techsingularity.net>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
  25. 09 Dec, 2016 1 commit
    • Thomas Gleixner's avatar
      x86/amd: Check for the C1E bug post ACPI subsystem init · e7ff3a47
      Thomas Gleixner authored
      AMD CPUs affected by the E400 erratum suffer from the issue that the
      local APIC timer stops when the CPU goes into C1E. Unfortunately there
      is no way to detect the affected CPUs on early boot. It's only possible
      to determine the range of possibly affected CPUs from the family/model
      The actual decision whether to enter C1E and thus cause the bug is done
      by the firmware and we need to detect that case late, after ACPI has
      been initialized.
      The current solution is to check in the idle routine whether the CPU is
      affected by reading the MSR_K8_INT_PENDING_MSG MSR and checking for the
      K8_INTP_C1E_ACTIVE_MASK bits. If one of the bits is set then the CPU is
      affected and the system is switched into forced broadcast mode.
      This is ineffective and on non-affected CPUs every entry to idle does
      the extra RDMSR.
      After doing some research it turns out that the bits are visible on the
      boot CPU right after the ACPI subsystem is initialized in the early
      boot process. So instead of polling for the bits in the idle loop, add
      a detection function after acpi_subsystem_init() and check for the MSR
      bits. If set, then the X86_BUG_AMD_APIC_C1E is set on the boot CPU and
      the TSC is marked unstable when X86_FEATURE_NONSTOP_TSC is not set as it
      will stop in C1E state as well.
      The switch to broadcast mode cannot be done at this point because the
      boot CPU still uses HPET as a clockevent device and the local APIC timer
      is not yet calibrated and installed. The switch to broadcast mode on the
      affected CPUs needs to be done when the local APIC timer is actually set
      This allows to cleanup the amd_e400_idle() function in the next step.
      Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
      Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
      Cc: Jiri Olsa <jolsa@redhat.com>
      Link: http://lkml.kernel.org/r/20161209182912.2726-4-bp@alien8.deSigned-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
  26. 28 Nov, 2016 2 commits
  27. 24 Oct, 2016 1 commit
  28. 10 Oct, 2016 1 commit
    • Emese Revfy's avatar
      gcc-plugins: Add latent_entropy plugin · 38addce8
      Emese Revfy authored
      This adds a new gcc plugin named "latent_entropy". It is designed to
      extract as much possible uncertainty from a running system at boot time as
      possible, hoping to capitalize on any possible variation in CPU operation
      (due to runtime data differences, hardware differences, SMP ordering,
      thermal timing variation, cache behavior, etc).
      At the very least, this plugin is a much more comprehensive example for
      how to manipulate kernel code using the gcc plugin internals.
      The need for very-early boot entropy tends to be very architecture or
      system design specific, so this plugin is more suited for those sorts
      of special cases. The existing kernel RNG already attempts to extract
      entropy from reliable runtime variation, but this plugin takes the idea to
      a logical extreme by permuting a global variable based on any variation
      in code execution (e.g. a different value (and permutation function)
      is used to permute the global based on loop count, case statement,
      if/then/else branching, etc).
      To do this, the plugin starts by inserting a local variable in every
      marked function. The plugin then adds logic so that the value of this
      variable is modified by randomly chosen operations (add, xor and rol) and
      random values (gcc generates separate static values for each location at
      compile time and also injects the stack pointer at runtime). The resulting
      value depends on the control flow path (e.g., loops and branches taken).
      Before the function returns, the plugin mixes this local variable into
      the latent_entropy global variable. The value of this global variable
      is added to the kernel entropy pool in do_one_initcall() and _do_fork(),
      though it does not credit any bytes of entropy to the pool; the contents
      of the global are just used to mix the pool.
      Additionally, the plugin can pre-initialize arrays with build-time
      random contents, so that two different kernel builds running on identical
      hardware will not have the same starting values.
      Signed-off-by: default avatarEmese Revfy <re.emese@gmail.com>
      [kees: expanded commit message and code comments]
      Signed-off-by: default avatarKees Cook <keescook@chromium.org>
  29. 17 Sep, 2016 1 commit
    • Tejun Heo's avatar
      workqueue: make workqueue available early during boot · 3347fa09
      Tejun Heo authored
      Workqueue is currently initialized in an early init call; however,
      there are cases where early boot code has to be split and reordered to
      come after workqueue initialization or the same code path which makes
      use of workqueues is used both before workqueue initailization and
      after.  The latter cases have to gate workqueue usages with
      keventd_up() tests, which is nasty and easy to get wrong.
      Workqueue usages have become widespread and it'd be a lot more
      convenient if it can be used very early from boot.  This patch splits
      workqueue initialization into two steps.  workqueue_init_early() which
      sets up the basic data structures so that workqueues can be created
      and work items queued, and workqueue_init() which actually brings up
      workqueues online and starts executing queued work items.  The former
      step can be done very early during boot once memory allocation,
      cpumasks and idr are initialized.  The latter right after kthreads
      become available.
      This allows work item queueing and canceling from very early boot
      which is what most of these use cases want.
      * As systemd_wq being initialized doesn't indicate that workqueue is
        fully online anymore, update keventd_up() to test wq_online instead.
        The follow-up patches will get rid of all its usages and the
        function itself.
      * Flushing doesn't make sense before workqueue is fully initialized.
        The flush functions trigger WARN and return immediately before fully
      * Work items are never in-flight before fully online.  Canceling can
        always succeed by skipping the flush step.
      * Some code paths can no longer assume to be called with irq enabled
        as irq is disabled during early boot.  Use irqsave/restore
        operations instead.
      v2: Watchdog init, which requires timer to be running, moved from
          workqueue_init_early() to workqueue_init().
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      Suggested-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      Link: http://lkml.kernel.org/r/CA+55aFx0vPuMuxn00rBSM192n-Du5uxy+4AvKa0SBSOVJeuCGg@mail.gmail.com
  30. 02 Aug, 2016 1 commit