Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 29 8月, 2014 1 次提交
  3. 13 8月, 2014 7 次提交
    • A
      powerpc/mm: Use read barrier when creating real_pte · 85c1fafd
      由 Aneesh Kumar K.V 提交于 
      On ppc64 we support 4K hash pte with 64K page size. That requires
us to track the hash pte slot information on a per 4k basis. We do that
by storing the slot details in the second half of pte page. The pte bit
_PAGE_COMBO is used to indicate whether the second half need to be
looked while building real_pte. We need to use read memory barrier while
doing that so that load of hidx is not reordered w.r.t _PAGE_COMBO
check. On the store side we already do a lwsync in __hash_page_4K

CC: <stable@vger.kernel.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      85c1fafd
    • A
      powerpc/thp: Handle combo pages in invalidate · fc047955
      由 Aneesh Kumar K.V 提交于 
      If we changed base page size of the segment, either via sub_page_protect
or via remap_4k_pfn, we do a demote_segment which doesn't flush the hash
table entries. We do a lazy hash page table flush for all mapped pages
in the demoted segment. This happens when we handle hash page fault for
these pages.

We use _PAGE_COMBO bit along with _PAGE_HASHPTE to indicate whether a
pte is backed by 4K hash pte. If we find _PAGE_COMBO not set on the pte,
that implies that we could possibly have older 64K hash pte entries in
the hash page table and we need to invalidate those entries.

Use _PAGE_COMBO to determine the page size with which we should
invalidate the hash table entries on unmap.

CC: <stable@vger.kernel.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      fc047955
    • A
      powerpc/thp: Don't recompute vsid and ssize in loop on invalidate · fa1f8ae8
      由 Aneesh Kumar K.V 提交于 
      The segment identifier and segment size will remain the same in
the loop, So we can compute it outside. We also change the
hugepage_invalidate interface so that we can use it the later patch

CC: <stable@vger.kernel.org>
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      fa1f8ae8
    • N
      powerpc: remove duplicate definition of TEXASR_FS · 56758e3c
      由 Nishanth Aravamudan 提交于 
      It appears that commits 7f06f21d ("powerpc/tm: Add checking to
treclaim/trechkpt") and e4e38121 ("KVM: PPC: Book3S HV: Add
transactional memory support") both added definitions of TEXASR_FS.
Remove one of them. At the same time, fix the alignment of the remaining
definition (should be tab-separated like the rest of the #defines).
Signed-off-by: NNishanth Aravamudan <nacc@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      56758e3c
    • V
      powerpc/powernv: Interface to register/unregister opal dump region · b09c2ec4
      由 Vasant Hegde 提交于 
      PowerNV platform is capable of capturing host memory region when system
crashes (because of host/firmware). We have new OPAL API to register/
unregister memory region to be captured when system crashes.

This patch adds support for new API. Also during boot time we register
kernel log buffer and unregister before doing kexec.
Signed-off-by: NVasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      b09c2ec4
    • M
      powerpc: Add POWER8 features to CPU_FTRS_POSSIBLE/ALWAYS · 3609e09f
      由 Michael Ellerman 提交于 
      We have been a bit slack about updating the CPU_FTRS_POSSIBLE and
CPU_FTRS_ALWAYS masks. When we added POWER8, and also POWER8E we forgot
to update the ALWAYS mask. And when we added POWER8_DD1 we forgot to
update both the POSSIBLE and ALWAYS masks.

Luckily this hasn't caused any actual bugs AFAICS. Failing to update the
ALWAYS mask just forgoes a potential optimisation opportunity. Failing
to update the POSSIBLE mask for POWER8_DD1 is also OK because it only
removes a bit rather than adding any.

Regardless they should all be in both masks so as to avoid any future
bugs when the set of ALWAYS/POSSIBLE bits changes, or the masks
themselves change.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Acked-by: NMichael Neuling <mikey@neuling.org>
Acked-by: NJoel Stanley <joel@jms.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      3609e09f
    • M
      powerpc: Add smp_mb() to arch_spin_is_locked() · 51d7d520
      由 Michael Ellerman 提交于 
      The kernel defines the function spin_is_locked(), which can be used to
check if a spinlock is currently locked.

Using spin_is_locked() on a lock you don't hold is obviously racy. That
is, even though you may observe that the lock is unlocked, it may become
locked at any time.

There is (at least) one exception to that, which is if two locks are
used as a pair, and the holder of each checks the status of the other
before doing any update.

Assuming *A and *B are two locks, and *COUNTER is a shared non-atomic
value:

The first CPU does:

	spin_lock(*A)

	if spin_is_locked(*B)
		# nothing
	else
		smp_mb()
		LOAD r = *COUNTER
		r++
		STORE *COUNTER = r

	spin_unlock(*A)

And the second CPU does:

	spin_lock(*B)

	if spin_is_locked(*A)
		# nothing
	else
		smp_mb()
		LOAD r = *COUNTER
		r++
		STORE *COUNTER = r

	spin_unlock(*B)

Although this is a strange locking construct, it should work.

It seems to be understood, but not documented, that spin_is_locked() is
not a memory barrier, so in the examples above and below the caller
inserts its own memory barrier before acting on the result of
spin_is_locked().

For now we assume spin_is_locked() is implemented as below, and we break
it out in our examples:

	bool spin_is_locked(*LOCK) {
		LOAD l = *LOCK
		return l.locked
	}

Our intuition is that there should be no problem even if the two code
sequences run simultaneously such as:

	CPU 0			CPU 1
	==================================================
	spin_lock(*A)		spin_lock(*B)
	LOAD b = *B		LOAD a = *A
	if b.locked # true	if a.locked # true
	# nothing		# nothing
	spin_unlock(*A)		spin_unlock(*B)

If one CPU gets the lock before the other then it will do the update and
the other CPU will back off:

	CPU 0			CPU 1
	==================================================
	spin_lock(*A)
	LOAD b = *B
				spin_lock(*B)
	if b.locked # false	LOAD a = *A
	else			if a.locked # true
	smp_mb()		# nothing
	LOAD r1 = *COUNTER	spin_unlock(*B)
	r1++
	STORE *COUNTER = r1
	spin_unlock(*A)

However in reality spin_lock() itself is not indivisible. On powerpc we
implement it as a load-and-reserve and store-conditional.

Ignoring the retry logic for the lost reservation case, it boils down to:
	spin_lock(*LOCK) {
		LOAD l = *LOCK
		l.locked = true
		STORE *LOCK = l
		ACQUIRE_BARRIER
	}

The ACQUIRE_BARRIER is required to give spin_lock() ACQUIRE semantics as
defined in memory-barriers.txt:

     This acts as a one-way permeable barrier.  It guarantees that all
     memory operations after the ACQUIRE operation will appear to happen
     after the ACQUIRE operation with respect to the other components of
     the system.

On modern powerpc systems we use lwsync for ACQUIRE_BARRIER. lwsync is
also know as "lightweight sync", or "sync 1".

As described in Power ISA v2.07 section B.2.1.1, in this scenario the
lwsync is not the barrier itself. It instead causes the LOAD of *LOCK to
act as the barrier, preventing any loads or stores in the locked region
from occurring prior to the load of *LOCK.

Whether this behaviour is in accordance with the definition of ACQUIRE
semantics in memory-barriers.txt is open to discussion, we may switch to
a different barrier in future.

What this means in practice is that the following can occur:

	CPU 0			CPU 1
	==================================================
	LOAD a = *A 		LOAD b = *B
	a.locked = true		b.locked = true
	LOAD b = *B		LOAD a = *A
	STORE *A = a		STORE *B = b
	if b.locked # false	if a.locked # false
	else			else
	smp_mb()		smp_mb()
	LOAD r1 = *COUNTER	LOAD r2 = *COUNTER
	r1++			r2++
	STORE *COUNTER = r1
				STORE *COUNTER = r2	# Lost update
	spin_unlock(*A)		spin_unlock(*B)

That is, the load of *B can occur prior to the store that makes *A
visibly locked. And similarly for CPU 1. The result is both CPUs hold
their lock and believe the other lock is unlocked.

The easiest fix for this is to add a full memory barrier to the start of
spin_is_locked(), so adding to our previous definition would give us:

	bool spin_is_locked(*LOCK) {
		smp_mb()
		LOAD l = *LOCK
		return l.locked
	}

The new barrier orders the store to the lock we are locking vs the load
of the other lock:

	CPU 0			CPU 1
	==================================================
	LOAD a = *A 		LOAD b = *B
	a.locked = true		b.locked = true
	STORE *A = a		STORE *B = b
	smp_mb()		smp_mb()
	LOAD b = *B		LOAD a = *A
	if b.locked # true	if a.locked # true
	# nothing		# nothing
	spin_unlock(*A)		spin_unlock(*B)

Although the above example is theoretical, there is code similar to this
example in sem_lock() in ipc/sem.c. This commit in addition to the next
commit appears to be a fix for crashes we are seeing in that code where
we believe this race happens in practice.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      51d7d520
  5. 09 8月, 2014 2 次提交
    • A
      arm64,ia64,ppc,s390,sh,tile,um,x86,mm: remove default gate area · a6c19dfe
      由 Andy Lutomirski 提交于 
      The core mm code will provide a default gate area based on
FIXADDR_USER_START and FIXADDR_USER_END if
!defined(__HAVE_ARCH_GATE_AREA) && defined(AT_SYSINFO_EHDR).

This default is only useful for ia64.  arm64, ppc, s390, sh, tile, 64-bit
UML, and x86_32 have their own code just to disable it.  arm, 32-bit UML,
and x86_64 have gate areas, but they have their own implementations.

This gets rid of the default and moves the code into ia64.

This should save some code on architectures without a gate area: it's now
possible to inline the gate_area functions in the default case.
Signed-off-by: NAndy Lutomirski <luto@amacapital.net>
Acked-by: NNathan Lynch <nathan_lynch@mentor.com>
Acked-by: NH. Peter Anvin <hpa@linux.intel.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [in principle]
Acked-by: Richard Weinberger <richard@nod.at> [for um]
Acked-by: Will Deacon <will.deacon@arm.com> [for arm64]
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Nathan Lynch <Nathan_Lynch@mentor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      a6c19dfe
    • L
      lib/scatterlist: make ARCH_HAS_SG_CHAIN an actual Kconfig · 308c09f1
      由 Laura Abbott 提交于 
      Rather than have architectures #define ARCH_HAS_SG_CHAIN in an
architecture specific scatterlist.h, make it a proper Kconfig option and
use that instead.  At same time, remove the header files are are now
mostly useless and just include asm-generic/scatterlist.h.

[sfr@canb.auug.org.au: powerpc files now need asm/dma.h]
Signed-off-by: NLaura Abbott <lauraa@codeaurora.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>			[x86]
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>	[powerpc]
Acked-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      308c09f1
  7. 05 8月, 2014 11 次提交
  9. 31 7月, 2014 1 次提交
    • A
      KVM: PPC: PR: Handle FSCR feature deselects · 8e6afa36
      由 Alexander Graf 提交于 
      We handle FSCR feature bits (well, TAR only really today) lazily when the guest
starts using them. So when a guest activates the bit and later uses that feature
we enable it for real in hardware.

However, when the guest stops using that bit we don't stop setting it in
hardware. That means we can potentially lose a trap that the guest expects to
happen because it thinks a feature is not active.

This patch adds support to drop TAR when then guest turns it off in FSCR. While
at it it also restricts FSCR access to 64bit systems - 32bit ones don't have it.
Signed-off-by: NAlexander Graf <agraf@suse.de>
      8e6afa36
  11. 30 7月, 2014 3 次提交
  13. 29 7月, 2014 3 次提交
  15. 28 7月, 2014 12 次提交
    • A
      KVM: PPC: Handle magic page in kvmppc_ld/st · c12fb43c
      由 Alexander Graf 提交于 
      We use kvmppc_ld and kvmppc_st to emulate load/store instructions that may as
well access the magic page. Special case it out so that we can properly access
it.
Signed-off-by: NAlexander Graf <agraf@suse.de>
      c12fb43c
    • A
      KVM: PPC: Move kvmppc_ld/st to common code · 35c4a733
      由 Alexander Graf 提交于 
      We have enough common infrastructure now to resolve GVA->GPA mappings at
runtime. With this we can move our book3s specific helpers to load / store
in guest virtual address space to common code as well.
Signed-off-by: NAlexander Graf <agraf@suse.de>
      35c4a733
    • A
      KVM: PPC: Implement kvmppc_xlate for all targets · 7d15c06f
      由 Alexander Graf 提交于 
      We have a nice API to find the translated GPAs of a GVA including protection
flags. So far we only use it on Book3S, but there's no reason the same shouldn't
be used on BookE as well.

Implement a kvmppc_xlate() version for BookE and clean it up to make it more
readable in general.
Signed-off-by: NAlexander Graf <agraf@suse.de>
      7d15c06f
    • A
      KVM: PPC: BOOK3S: HV: Update compute_tlbie_rb to handle 16MB base page · 63fff5c1
      由 Aneesh Kumar K.V 提交于 
      When calculating the lower bits of AVA field, use the shift
count based on the base page size. Also add the missing segment
size and remove stale comment.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      63fff5c1
    • S
      Use the POWER8 Micro Partition Prefetch Engine in KVM HV on POWER8 · 9678cdaa
      由 Stewart Smith 提交于 
      The POWER8 processor has a Micro Partition Prefetch Engine, which is
a fancy way of saying "has way to store and load contents of L2 or
L2+MRU way of L3 cache". We initiate the storing of the log (list of
addresses) using the logmpp instruction and start restore by writing
to a SPR.

The logmpp instruction takes parameters in a single 64bit register:
- starting address of the table to store log of L2/L2+L3 cache contents
  - 32kb for L2
  - 128kb for L2+L3
  - Aligned relative to maximum size of the table (32kb or 128kb)
- Log control (no-op, L2 only, L2 and L3, abort logout)

We should abort any ongoing logging before initiating one.

To initiate restore, we write to the MPPR SPR. The format of what to write
to the SPR is similar to the logmpp instruction parameter:
- starting address of the table to read from (same alignment requirements)
- table size (no data, until end of table)
- prefetch rate (from fastest possible to slower. about every 8, 16, 24 or
  32 cycles)

The idea behind loading and storing the contents of L2/L3 cache is to
reduce memory latency in a system that is frequently swapping vcores on
a physical CPU.

The best case scenario for doing this is when some vcores are doing very
cache heavy workloads. The worst case is when they have about 0 cache hits,
so we just generate needless memory operations.

This implementation just does L2 store/load. In my benchmarks this proves
to be useful.

Benchmark 1:
 - 16 core POWER8
 - 3x Ubuntu 14.04LTS guests (LE) with 8 VCPUs each
 - No split core/SMT
 - two guests running sysbench memory test.
   sysbench --test=memory --num-threads=8 run
 - one guest running apache bench (of default HTML page)
   ab -n 490000 -c 400 http://localhost/

This benchmark aims to measure performance of real world application (apache)
where other guests are cache hot with their own workloads. The sysbench memory
benchmark does pointer sized writes to a (small) memory buffer in a loop.

In this benchmark with this patch I can see an improvement both in requests
per second (~5%) and in mean and median response times (again, about 5%).
The spread of minimum and maximum response times were largely unchanged.

benchmark 2:
 - Same VM config as benchmark 1
 - all three guests running sysbench memory benchmark

This benchmark aims to see if there is a positive or negative affect to this
cache heavy benchmark. Although due to the nature of the benchmark (stores) we
may not see a difference in performance, but rather hopefully an improvement
in consistency of performance (when vcore switched in, don't have to wait
many times for cachelines to be pulled in)

The results of this benchmark are improvements in consistency of performance
rather than performance itself. With this patch, the few outliers in duration
go away and we get more consistent performance in each guest.

benchmark 3:
 - same 3 guests and CPU configuration as benchmark 1 and 2.
 - two idle guests
 - 1 guest running STREAM benchmark

This scenario also saw performance improvement with this patch. On Copy and
Scale workloads from STREAM, I got 5-6% improvement with this patch. For
Add and triad, it was around 10% (or more).

benchmark 4:
 - same 3 guests as previous benchmarks
 - two guests running sysbench --memory, distinctly different cache heavy
   workload
 - one guest running STREAM benchmark.

Similar improvements to benchmark 3.

benchmark 5:
 - 1 guest, 8 VCPUs, Ubuntu 14.04
 - Host configured with split core (SMT8, subcores-per-core=4)
 - STREAM benchmark

In this benchmark, we see a 10-20% performance improvement across the board
of STREAM benchmark results with this patch.

Based on preliminary investigation and microbenchmarks
by Prerna Saxena <prerna@linux.vnet.ibm.com>
Signed-off-by: NStewart Smith <stewart@linux.vnet.ibm.com>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      9678cdaa
    • A
      KVM: PPC: Remove 440 support · b2677b8d
      由 Alexander Graf 提交于 
      The 440 target hasn't been properly functioning for a few releases and
before I was the only one who fixes a very serious bug that indicates to
me that nobody used it before either.

Furthermore KVM on 440 is slow to the extent of unusable.

We don't have to carry along completely unused code. Remove 440 and give
us one less thing to worry about.
Signed-off-by: NAlexander Graf <agraf@suse.de>
      b2677b8d
    • B
      KVM: PPC: Remove comment saying SPRG1 is used for vcpu pointer · 8c95ead6
      由 Bharat Bhushan 提交于 
      Scott Wood pointed out that We are no longer using SPRG1 for vcpu pointer,
but using SPRN_SPRG_THREAD <=> SPRG3 (thread->vcpu). So this comment
is not valid now.

Note: SPRN_SPRG3R is not supported (do not see any need as of now),
and if we want to support this in future then we have to shift to using
SPRG1 for VCPU pointer.
Signed-off-by: NBharat Bhushan <Bharat.Bhushan@freescale.com>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      8c95ead6
    • B
      kvm: ppc: bookehv: Save restore SPRN_SPRG9 on guest entry exit · 99e99d19
      由 Bharat Bhushan 提交于 
      SPRN_SPRG is used by debug interrupt handler, so this is required for
debug support.
Signed-off-by: NBharat Bhushan <Bharat.Bhushan@freescale.com>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      99e99d19
    • M
      KVM: PPC: Allow kvmppc_get_last_inst() to fail · 51f04726
      由 Mihai Caraman 提交于 
      On book3e, guest last instruction is read on the exit path using load
external pid (lwepx) dedicated instruction. This load operation may fail
due to TLB eviction and execute-but-not-read entries.

This patch lay down the path for an alternative solution to read the guest
last instruction, by allowing kvmppc_get_lat_inst() function to fail.
Architecture specific implmentations of kvmppc_load_last_inst() may read
last guest instruction and instruct the emulation layer to re-execute the
guest in case of failure.

Make kvmppc_get_last_inst() definition common between architectures.
Signed-off-by: NMihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      51f04726
    • M
      KVM: PPC: Book3e: Add TLBSEL/TSIZE defines for MAS0/1 · 9c0d4e0d
      由 Mihai Caraman 提交于 
      Add mising defines MAS0_GET_TLBSEL() and MAS1_GET_TSIZE() for Book3E.
Signed-off-by: NMihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      9c0d4e0d
    • B
      kvm: ppc: Add SPRN_EPR get helper function · 34f754b9
      由 Bharat Bhushan 提交于 
      kvmppc_set_epr() is already defined in asm/kvm_ppc.h, So
rename and move get_epr helper function to same file.
Signed-off-by: NBharat Bhushan <Bharat.Bhushan@freescale.com>
[agraf: remove duplicate return]
Signed-off-by: NAlexander Graf <agraf@suse.de>
      34f754b9
    • B
      kvm: ppc: booke: Add shared struct helpers of SPRN_ESR · dc168549
      由 Bharat Bhushan 提交于 
      Add and use kvmppc_set_esr() and kvmppc_get_esr() helper functions
Signed-off-by: NBharat Bhushan <Bharat.Bhushan@freescale.com>
Signed-off-by: NAlexander Graf <agraf@suse.de>
      dc168549