Skip to content

K
Kernel

openeuler / Kernel
大约 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 15 9月, 2020 1 次提交
  3. 02 9月, 2020 4 次提交
  5. 22 7月, 2020 1 次提交
  7. 20 7月, 2020 1 次提交
  9. 02 6月, 2020 1 次提交
  11. 18 5月, 2020 3 次提交
  13. 15 5月, 2020 2 次提交
    • M
      powerpc: Drop unneeded cast in task_pt_regs() · 24ac99e9
      由 Michael Ellerman 提交于 
      There's no need to cast in task_pt_regs() as tsk->thread.regs should
already be a struct pt_regs. If someone's using task_pt_regs() on
something that's not a task but happens to have a thread.regs then
we'll deal with them later.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200428123152.73566-1-mpe@ellerman.id.au
      24ac99e9
    • M
      powerpc/64: Don't initialise init_task->thread.regs · 7ffa8b7d
      由 Michael Ellerman 提交于 
      Aneesh increased the size of struct pt_regs by 16 bytes and started
seeing this WARN_ON:

  smp: Bringing up secondary CPUs ...
  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 0 at arch/powerpc/kernel/process.c:455 giveup_all+0xb4/0x110
  Modules linked in:
  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.7.0-rc2-gcc-8.2.0-1.g8f6a41f-default+ #318
  NIP:  c00000000001a2b4 LR: c00000000001a29c CTR: c0000000031d0000
  REGS: c0000000026d3980 TRAP: 0700   Not tainted  (5.7.0-rc2-gcc-8.2.0-1.g8f6a41f-default+)
  MSR:  800000000282b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE>  CR: 48048224  XER: 00000000
  CFAR: c000000000019cc8 IRQMASK: 1
  GPR00: c00000000001a264 c0000000026d3c20 c0000000026d7200 800000000280b033
  GPR04: 0000000000000001 0000000000000000 0000000000000077 30206d7372203164
  GPR08: 0000000000002000 0000000002002000 800000000280b033 3230303030303030
  GPR12: 0000000000008800 c0000000031d0000 0000000000800050 0000000002000066
  GPR16: 000000000309a1a0 000000000309a4b0 000000000309a2d8 000000000309a890
  GPR20: 00000000030d0098 c00000000264da40 00000000fd620000 c0000000ff798080
  GPR24: c00000000264edf0 c0000001007469f0 00000000fd620000 c0000000020e5e90
  GPR28: c00000000264edf0 c00000000264d200 000000001db60000 c00000000264d200
  NIP [c00000000001a2b4] giveup_all+0xb4/0x110
  LR [c00000000001a29c] giveup_all+0x9c/0x110
  Call Trace:
  [c0000000026d3c20] [c00000000001a264] giveup_all+0x64/0x110 (unreliable)
  [c0000000026d3c90] [c00000000001ae34] __switch_to+0x104/0x480
  [c0000000026d3cf0] [c000000000e0b8a0] __schedule+0x320/0x970
  [c0000000026d3dd0] [c000000000e0c518] schedule_idle+0x38/0x70
  [c0000000026d3df0] [c00000000019c7c8] do_idle+0x248/0x3f0
  [c0000000026d3e70] [c00000000019cbb8] cpu_startup_entry+0x38/0x40
  [c0000000026d3ea0] [c000000000011bb0] rest_init+0xe0/0xf8
  [c0000000026d3ed0] [c000000002004820] start_kernel+0x990/0x9e0
  [c0000000026d3f90] [c00000000000c49c] start_here_common+0x1c/0x400

Which was unexpected. The warning is checking the thread.regs->msr
value of the task we are switching from:

  usermsr = tsk->thread.regs->msr;
  ...
  WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));

ie. if MSR_VSX is set then both of MSR_FP and MSR_VEC are also set.

Dumping tsk->thread.regs->msr we see that it's: 0x1db60000

Which is not a normal looking MSR, in fact the only valid bit is
MSR_VSX, all the other bits are reserved in the current definition of
the MSR.

We can see from the oops that it was swapper/0 that we were switching
from when we hit the warning, ie. init_task. So its thread.regs points
to the base (high addresses) in init_stack.

Dumping the content of init_task->thread.regs, with the members of
pt_regs annotated (the 16 bytes larger version), we see:

  0000000000000000 c000000002780080    gpr[0]     gpr[1]
  0000000000000000 c000000002666008    gpr[2]     gpr[3]
  c0000000026d3ed0 0000000000000078    gpr[4]     gpr[5]
  c000000000011b68 c000000002780080    gpr[6]     gpr[7]
  0000000000000000 0000000000000000    gpr[8]     gpr[9]
  c0000000026d3f90 0000800000002200    gpr[10]    gpr[11]
  c000000002004820 c0000000026d7200    gpr[12]    gpr[13]
  000000001db60000 c0000000010aabe8    gpr[14]    gpr[15]
  c0000000010aabe8 c0000000010aabe8    gpr[16]    gpr[17]
  c00000000294d598 0000000000000000    gpr[18]    gpr[19]
  0000000000000000 0000000000001ff8    gpr[20]    gpr[21]
  0000000000000000 c00000000206d608    gpr[22]    gpr[23]
  c00000000278e0cc 0000000000000000    gpr[24]    gpr[25]
  000000002fff0000 c000000000000000    gpr[26]    gpr[27]
  0000000002000000 0000000000000028    gpr[28]    gpr[29]
  000000001db60000 0000000004750000    gpr[30]    gpr[31]
  0000000002000000 000000001db60000    nip        msr
  0000000000000000 0000000000000000    orig_r3    ctr
  c00000000000c49c 0000000000000000    link       xer
  0000000000000000 0000000000000000    ccr        softe
  0000000000000000 0000000000000000    trap       dar
  0000000000000000 0000000000000000    dsisr      result
  0000000000000000 0000000000000000    ppr        kuap
  0000000000000000 0000000000000000    pad[2]     pad[3]

This looks suspiciously like stack frames, not a pt_regs. If we look
closely we can see return addresses from the stack trace above,
c000000002004820 (start_kernel) and c00000000000c49c (start_here_common).

init_task->thread.regs is setup at build time in processor.h:

  #define INIT_THREAD  { \
  	.ksp = INIT_SP, \
  	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \

The early boot code where we setup the initial stack is:

  LOAD_REG_ADDR(r3,init_thread_union)

  /* set up a stack pointer */
  LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
  add	r1,r3,r1
  li	r0,0
  stdu	r0,-STACK_FRAME_OVERHEAD(r1)

Which creates a stack frame of size 112 bytes (STACK_FRAME_OVERHEAD).
Which is far too small to contain a pt_regs.

So the result is init_task->thread.regs is pointing at some stack
frames on the init stack, not at a pt_regs.

We have gotten away with this for so long because with pt_regs at its
current size the MSR happens to point into the first frame, at a
location that is not written to by the early asm. With the 16 byte
expansion the MSR falls into the second frame, which is used by the
compiler, and collides with a saved register that tends to be
non-zero.

As far as I can see this has been wrong since the original merge of
64-bit ppc support, back in 2002.

Conceptually swapper should have no regs, it never entered from
userspace, and in fact that's what we do on 32-bit. It's also
presumably what the "bogus" comment is referring to.

So I think the right fix is to just not-initialise regs at all. I'm
slightly worried this will break some code that isn't prepared for a
NULL regs, but we'll have to see.

Remove the comment in head_64.S which refers to us setting up the
regs (even though we never did), and is otherwise not really accurate
any more.
Reported-by: NAneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200428123130.73078-1-mpe@ellerman.id.au
      7ffa8b7d
  15. 20 4月, 2020 1 次提交
  17. 18 2月, 2020 1 次提交
    • C
      powerpc/32s: Fix DSI and ISI exceptions for CONFIG_VMAP_STACK · 232ca1ee
      由 Christophe Leroy 提交于 
      hash_page() needs to read page tables from kernel memory. When entire
kernel memory is mapped by BATs, which is normally the case when
CONFIG_STRICT_KERNEL_RWX is not set, it works even if the page hosting
the page table is not referenced in the MMU hash table.

However, if the page where the page table resides is not covered by
a BAT, a DSI fault can be encountered from hash_page(), and it loops
forever. This can happen when CONFIG_STRICT_KERNEL_RWX is selected
and the alignment of the different regions is too small to allow
covering the entire memory with BATs. This also happens when
CONFIG_DEBUG_PAGEALLOC is selected or when booting with 'nobats'
flag.

Also, if the page containing the kernel stack is not present in the
MMU hash table, registers cannot be saved and a recursive DSI fault
is encountered.

To allow hash_page() to properly do its job at all time and load the
MMU hash table whenever needed, it must run with data MMU disabled.
This means it must be called before re-enabling data MMU. To allow
this, registers clobbered by hash_page() and create_hpte() have to
be saved in the thread struct together with SRR0, SSR1, DAR and DSISR.
It is also necessary to ensure that DSI prolog doesn't overwrite
regs saved by prolog of the current running exception. That means:
- DSI can only use SPRN_SPRG_SCRATCH0
- Exceptions must free SPRN_SPRG_SCRATCH0 before writing to the stack.

This also fixes the Oops reported by Erhard when create_hpte() is
called by add_hash_page().

Due to prolog size increase, a few more exceptions had to get split
in two parts.

Fixes: cd08f109 ("powerpc/32s: Enable CONFIG_VMAP_STACK")
Reported-by: NErhard F. <erhard_f@mailbox.org>
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Tested-by: NErhard F. <erhard_f@mailbox.org>
Tested-by: NLarry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206501
Link: https://lore.kernel.org/r/64a4aa44686e9fd4b01333401367029771d9b231.1581761633.git.christophe.leroy@c-s.fr
      232ca1ee
  19. 26 1月, 2020 1 次提交
  21. 16 1月, 2020 1 次提交
  23. 15 6月, 2019 1 次提交
  25. 31 5月, 2019 1 次提交
  27. 30 4月, 2019 1 次提交
    • N
      powerpc/64s: Reimplement book3s idle code in C · 10d91611
      由 Nicholas Piggin 提交于 
      Reimplement Book3S idle code in C, moving POWER7/8/9 implementation
speific HV idle code to the powernv platform code.

Book3S assembly stubs are kept in common code and used only to save
the stack frame and non-volatile GPRs before executing architected
idle instructions, and restoring the stack and reloading GPRs then
returning to C after waking from idle.

The complex logic dealing with threads and subcores, locking, SPRs,
HMIs, timebase resync, etc., is all done in C which makes it more
maintainable.

This is not a strict translation to C code, there are some
significant differences:

- Idle wakeup no longer uses the ->cpu_restore call to reinit SPRs,
  but saves and restores them itself.

- The optimisation where EC=ESL=0 idle modes did not have to save GPRs
  or change MSR is restored, because it's now simple to do. ESL=1
  sleeps that do not lose GPRs can use this optimization too.

- KVM secondary entry and cede is now more of a call/return style
  rather than branchy. nap_state_lost is not required because KVM
  always returns via NVGPR restoring path.

- KVM secondary wakeup from offline sequence is moved entirely into
  the offline wakeup, which avoids a hwsync in the normal idle wakeup
  path.

Performance measured with context switch ping-pong on different
threads or cores, is possibly improved a small amount, 1-3% depending
on stop state and core vs thread test for shallow states. Deep states
it's in the noise compared with other latencies.

KVM improvements:

- Idle sleepers now always return to caller rather than branch out
  to KVM first.

- This allows optimisations like very fast return to caller when no
  state has been lost.

- KVM no longer requires nap_state_lost because it controls NVGPR
  save/restore itself on the way in and out.

- The heavy idle wakeup KVM request check can be moved out of the
  normal host idle code and into the not-performance-critical offline
  code.

- KVM nap code now returns from where it is called, which makes the
  flow a bit easier to follow.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
[mpe: Squash the KVM changes in]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      10d91611
  29. 21 4月, 2019 1 次提交
    • C
      powerpc/32s: Implement Kernel Userspace Access Protection · a68c31fc
      由 Christophe Leroy 提交于 
      This patch implements Kernel Userspace Access Protection for
book3s/32.

Due to limitations of the processor page protection capabilities,
the protection is only against writing. read protection cannot be
achieved using page protection.

The previous patch modifies the page protection so that RW user
pages are RW for Key 0 and RO for Key 1, and it sets Key 0 for
both user and kernel.

This patch changes userspace segment registers are set to Ku 0
and Ks 1. When kernel needs to write to RW pages, the associated
segment register is then changed to Ks 0 in order to allow write
access to the kernel.

In order to avoid having the read all segment registers when
locking/unlocking the access, some data is kept in the thread_struct
and saved on stack on exceptions. The field identifies both the
first unlocked segment and the first segment following the last
unlocked one. When no segment is unlocked, it contains value 0.

As the hash_page() function is not able to easily determine if a
protfault is due to a bad kernel access to userspace, protfaults
need to be handled by handle_page_fault when KUAP is set.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
[mpe: Drop allow_read/write_to/from_user() as they're now in kup.h,
      and adapt allow_user_access() to do nothing when to == NULL]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      a68c31fc
  31. 23 2月, 2019 4 次提交
  33. 21 2月, 2019 1 次提交
  35. 31 10月, 2018 1 次提交
  37. 14 10月, 2018 2 次提交
    • N
      powerpc/64s/hash: Add a SLB preload cache · 5434ae74
      由 Nicholas Piggin 提交于 
      When switching processes, currently all user SLBEs are cleared, and a
few (exec_base, pc, and stack) are preloaded. In trivial testing with
small apps, this tends to miss the heap and low 256MB segments, and it
will also miss commonly accessed segments on large memory workloads.

Add a simple round-robin preload cache that just inserts the last SLB
miss into the head of the cache and preloads those at context switch
time. Every 256 context switches, the oldest entry is removed from the
cache to shrink the cache and require fewer slbmte if they are unused.

Much more could go into this, including into the SLB entry reclaim
side to track some LRU information etc, which would require a study of
large memory workloads. But this is a simple thing we can do now that
is an obvious win for common workloads.

With the full series, process switching speed on the context_switch
benchmark on POWER9/hash (with kernel speculation security masures
disabled) increases from 140K/s to 178K/s (27%).

POWER8 does not change much (within 1%), it's unclear why it does not
see a big gain like POWER9.

Booting to busybox init with 256MB segments has SLB misses go down
from 945 to 69, and with 1T segments 900 to 21. These could almost all
be eliminated by preloading a bit more carefully with ELF binary
loading.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      5434ae74
    • N
      powerpc/64: Interrupts save PPR on stack rather than thread_struct · 4c2de74c
      由 Nicholas Piggin 提交于 
      PPR is the odd register out when it comes to interrupt handling, it is
saved in current->thread.ppr while all others are saved on the stack.

The difficulty with this is that accessing thread.ppr can cause a SLB
fault, but the SLB fault handler implementation in C change had
assumed the normal exception entry handlers would not cause an SLB
fault.

Fix this by allocating room in the interrupt stack to save PPR.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      4c2de74c
  39. 03 10月, 2018 1 次提交
  41. 19 9月, 2018 1 次提交
    • N
      powerpc/64s/hash: Add a SLB preload cache · 89ca4e12
      由 Nicholas Piggin 提交于 
      When switching processes, currently all user SLBEs are cleared, and a
few (exec_base, pc, and stack) are preloaded. In trivial testing with
small apps, this tends to miss the heap and low 256MB segments, and it
will also miss commonly accessed segments on large memory workloads.

Add a simple round-robin preload cache that just inserts the last SLB
miss into the head of the cache and preloads those at context switch
time. Every 256 context switches, the oldest entry is removed from the
cache to shrink the cache and require fewer slbmte if they are unused.

Much more could go into this, including into the SLB entry reclaim
side to track some LRU information etc, which would require a study of
large memory workloads. But this is a simple thing we can do now that
is an obvious win for common workloads.

With the full series, process switching speed on the context_switch
benchmark on POWER9/hash (with kernel speculation security masures
disabled) increases from 140K/s to 178K/s (27%).

POWER8 does not change much (within 1%), it's unclear why it does not
see a big gain like POWER9.

Booting to busybox init with 256MB segments has SLB misses go down
from 945 to 69, and with 1T segments 900 to 21. These could almost all
be eliminated by preloading a bit more carefully with ELF binary
loading.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      89ca4e12
  43. 30 7月, 2018 1 次提交
  45. 03 6月, 2018 2 次提交
  47. 31 3月, 2018 1 次提交
  49. 30 3月, 2018 2 次提交
  51. 20 1月, 2018 1 次提交
  53. 12 11月, 2017 2 次提交