Commit graph

982,081 commits

Author SHA1 Message Date
Christoph Hellwig
721be86814 nouveau: use alloc_page_vma directly
hmm_vma_alloc_locked_page is scheduled to go away, use the proper
mm function directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
d0b3517dbc PCI/P2PDMA: use the dev_pagemap internal refcount
The functionality is identical to the one currently open coded in
p2pdma.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Tested-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
ea31d5859f device-dax: use the dev_pagemap internal refcount
The functionality is identical to the one currently open coded in
device-dax.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
24917f6b10 memremap: provide an optional internal refcount in struct dev_pagemap
Provide an internal refcounting logic if no ->ref field is provided
in the pagemap passed into devm_memremap_pages so that callers don't
have to reinvent it poorly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
514caf23a7 memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag
Add a flags field to struct dev_pagemap to replace the altmap_valid
boolean to be a little more extensible.  Also add a pgmap_altmap() helper
to find the optional altmap and clean up the code using the altmap using
it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
80a72d0af0 memremap: remove the data field in struct dev_pagemap
struct dev_pagemap is always embedded into a containing structure, so
there is no need to an additional private data field.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
897e6365cd memremap: add a migrate_to_ram method to struct dev_pagemap_ops
This replaces the hacky ->fault callback, which is currently directly
called from common code through a hmm specific data structure as an
exercise in layering violations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
f6a55e1a3f memremap: lift the devmap_enable manipulation into devm_memremap_pages
Just check if there is a ->page_free operation set and take care of the
static key enable, as well as the put using device managed resources.
Also check that a ->page_free is provided for the pgmaps types that
require it, and check for a valid type as well while we are at it.

Note that this also fixes the fact that hmm never called
dev_pagemap_put_ops and thus would leave the slow path enabled forever,
even after a device driver unload or disable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
d8668bb045 memremap: pass a struct dev_pagemap to ->kill and ->cleanup
Passing the actual typed structure leads to more understandable code
vs just passing the ref member.

Reported-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
1e240e8d4a memremap: move dev_pagemap callbacks into a separate structure
The dev_pagemap is a growing too many callbacks.  Move them into a
separate ops structure so that they are not duplicated for multiple
instances, and an attacker can't easily overwrite them.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
3ed2dcdf54 memremap: validate the pagemap type passed to devm_memremap_pages
Most pgmap types are only supported when certain config options are
enabled.  Check for a type that is valid for the current configuration
before setting up the pagemap.  For this the usage of the 0 type for
device dax gets replaced with an explicit MEMORY_DEVICE_DEVDAX type.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
0092908d16 mm: factor out a devm_request_free_mem_region helper
Keep the physical address allocation that hmm_add_device does with the
rest of the resource code, and allow future reuse of it without the hmm
wrapper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
692622157b mm: export alloc_pages_vma
nouveau is currently using this through an odd hmm wrapper, and I plan
to switch it to the real thing later in this series.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
b7a523109f mm: don't clear ->mapping in hmm_devmem_free
->mapping isn't even used by HMM users, and the field at the same offset
in the zone_device part of the union is declared as pad.  (Which btw is
rather confusing, as DAX uses ->pgmap and ->mapping from two different
sides of the union, but DAX doesn't use hmm_devmem_free).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:44 -03:00
Christoph Hellwig
25b2995a35 mm: remove MEMORY_DEVICE_PUBLIC support
The code hasn't been used since it was added to the tree, and doesn't
appear to actually be usable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-02 14:32:43 -03:00
Wanpeng Li
bb34e690e9 KVM: LAPIC: Fix pending interrupt in IRR blocked by software disable LAPIC
Thomas reported that:

 | Background:
 |
 |    In preparation of supporting IPI shorthands I changed the CPU offline
 |    code to software disable the local APIC instead of just masking it.
 |    That's done by clearing the APIC_SPIV_APIC_ENABLED bit in the APIC_SPIV
 |    register.
 |
 | Failure:
 |
 |    When the CPU comes back online the startup code triggers occasionally
 |    the warning in apic_pending_intr_clear(). That complains that the IRRs
 |    are not empty.
 |
 |    The offending vector is the local APIC timer vector who's IRR bit is set
 |    and stays set.
 |
 | It took me quite some time to reproduce the issue locally, but now I can
 | see what happens.
 |
 | It requires apicv_enabled=0, i.e. full apic emulation. With apicv_enabled=1
 | (and hardware support) it behaves correctly.
 |
 | Here is the series of events:
 |
 |     Guest CPU
 |
 |     goes down
 |
 |       native_cpu_disable()
 |
 | 			apic_soft_disable();
 |
 |     play_dead()
 |
 |     ....
 |
 |     startup()
 |
 |       if (apic_enabled())
 |         apic_pending_intr_clear()	<- Not taken
 |
 |      enable APIC
 |
 |         apic_pending_intr_clear()	<- Triggers warning because IRR is stale
 |
 | When this happens then the deadline timer or the regular APIC timer -
 | happens with both, has fired shortly before the APIC is disabled, but the
 | interrupt was not serviced because the guest CPU was in an interrupt
 | disabled region at that point.
 |
 | The state of the timer vector ISR/IRR bits:
 |
 |     	     	       	        ISR     IRR
 | before apic_soft_disable()    0	      1
 | after apic_soft_disable()     0	      1
 |
 | On startup		      		 0	      1
 |
 | Now one would assume that the IRR is cleared after the INIT reset, but this
 | happens only on CPU0.
 |
 | Why?
 |
 | Because our CPU0 hotplug is just for testing to make sure nothing breaks
 | and goes through an NMI wakeup vehicle because INIT would send it through
 | the boots-trap code which is not really working if that CPU was not
 | physically unplugged.
 |
 | Now looking at a real world APIC the situation in that case is:
 |
 |     	     	       	      	ISR     IRR
 | before apic_soft_disable()    0	      1
 | after apic_soft_disable()     0	      1
 |
 | On startup		      		 0	      0
 |
 | Why?
 |
 | Once the dying CPU reenables interrupts the pending interrupt gets
 | delivered as a spurious interupt and then the state is clear.
 |
 | While that CPU0 hotplug test case is surely an esoteric issue, the APIC
 | emulation is still wrong, Even if the play_dead() code would not enable
 | interrupts then the pending IRR bit would turn into an ISR .. interrupt
 | when the APIC is reenabled on startup.

From SDM 10.4.7.2 Local APIC State After It Has Been Software Disabled
* Pending interrupts in the IRR and ISR registers are held and require
  masking or handling by the CPU.

In Thomas's testing, hardware cpu will not respect soft disable LAPIC
when IRR has already been set or APICv posted-interrupt is in flight,
so we can skip soft disable APIC checking when clearing IRR and set ISR,
continue to respect soft disable APIC when attempting to set IRR.

Reported-by: Rong Chen <rong.a.chen@intel.com>
Reported-by: Feng Tang <feng.tang@intel.com>
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rong Chen <rong.a.chen@intel.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 19:02:46 +02:00
Liran Alon
323d73a8ec KVM: nVMX: Change KVM_STATE_NESTED_EVMCS to signal vmcs12 is copied from eVMCS
Currently KVM_STATE_NESTED_EVMCS is used to signal that eVMCS
capability is enabled on vCPU.
As indicated by vmx->nested.enlightened_vmcs_enabled.

This is quite bizarre as userspace VMM should make sure to expose
same vCPU with same CPUID values in both source and destination.
In case vCPU is exposed with eVMCS support on CPUID, it is also
expected to enable KVM_CAP_HYPERV_ENLIGHTENED_VMCS capability.
Therefore, KVM_STATE_NESTED_EVMCS is redundant.

KVM_STATE_NESTED_EVMCS is currently used on restore path
(vmx_set_nested_state()) only to enable eVMCS capability in KVM
and to signal need_vmcs12_sync such that on next VMEntry to guest
nested_sync_from_vmcs12() will be called to sync vmcs12 content
into eVMCS in guest memory.
However, because restore nested-state is rare enough, we could
have just modified vmx_set_nested_state() to always signal
need_vmcs12_sync.

From all the above, it seems that we could have just removed
the usage of KVM_STATE_NESTED_EVMCS. However, in order to preserve
backwards migration compatibility, we cannot do that.
(vmx_get_nested_state() needs to signal flag when migrating from
new kernel to old kernel).

Returning KVM_STATE_NESTED_EVMCS when just vCPU have eVMCS enabled
have a bad side-effect of userspace VMM having to send nested-state
from source to destination as part of migration stream. Even if
guest have never used eVMCS as it doesn't even run a nested
hypervisor workload. This requires destination userspace VMM and
KVM to support setting nested-state. Which make it more difficult
to migrate from new host to older host.
To avoid this, change KVM_STATE_NESTED_EVMCS to signal eVMCS is
not only enabled but also active. i.e. Guest have made some
eVMCS active via an enlightened VMEntry. i.e. vmcs12 is copied
from eVMCS and therefore should be restored into eVMCS resident
in memory (by copy_vmcs12_to_enlightened()).

Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maran Wilson <maran.wilson@oracle.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 19:02:45 +02:00
Liran Alon
65b712f156 KVM: nVMX: Allow restore nested-state to enable eVMCS when vCPU in SMM
As comment in code specifies, SMM temporarily disables VMX so we cannot
be in guest mode, nor can VMLAUNCH/VMRESUME be pending.

However, code currently assumes that these are the only flags that can be
set on kvm_state->flags. This is not true as KVM_STATE_NESTED_EVMCS
can also be set on this field to signal that eVMCS should be enabled.

Therefore, fix code to check for guest-mode and pending VMLAUNCH/VMRESUME
explicitly.

Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 19:02:44 +02:00
Paolo Bonzini
3f16a5c318 KVM: x86: degrade WARN to pr_warn_ratelimited
This warning can be triggered easily by userspace, so it should certainly not
cause a panic if panic_on_warn is set.

Reported-by: syzbot+c03f30b4f4c46bdf8575@syzkaller.appspotmail.com
Suggested-by: Alexander Potapenko <glider@google.com>
Acked-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 19:02:44 +02:00
Jim Mattson
c550505b57 kvm: x86: Pass through AMD_STIBP_ALWAYS_ON in GET_SUPPORTED_CPUID
This bit is purely advisory. Passing it through to the guest indicates
that the virtual processor, like the physical processor, prefers that
STIBP is only set once during boot and not changed.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 19:01:56 +02:00
Jim Mattson
b119019847 kvm: nVMX: Remove unnecessary sync_roots from handle_invept
When L0 is executing handle_invept(), the TDP MMU is active. Emulating
an L1 INVEPT does require synchronizing the appropriate shadow EPT
root(s), but a call to kvm_mmu_sync_roots in this context won't do
that. Similarly, the hardware TLB and paging-structure-cache entries
associated with the appropriate shadow EPT root(s) must be flushed,
but requesting a TLB_FLUSH from this context won't do that either.

How did this ever work? KVM always does a sync_roots and TLB flush (in
the correct context) when transitioning from L1 to L2. That isn't the
best choice for nested VM performance, but it effectively papers over
the mistakes here.

Remove the unnecessary operations and leave a comment to try to do
better in the future.

Reported-by: Junaid Shahid <junaids@google.com>
Fixes: bfd0a56b90 ("nEPT: Nested INVEPT")
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Nadav Har'El <nyh@il.ibm.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>
Cc: Xinhao Xu <xinhao.xu@intel.com>
Cc: Yang Zhang <yang.z.zhang@Intel.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by Peter Shier <pshier@google.com>
Reviewed-by: Junaid Shahid <junaids@google.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 19:01:56 +02:00
Paolo Bonzini
9824c83f92 Documentation: kvm: document CPUID bit for MSR_KVM_POLL_CONTROL
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 18:57:29 +02:00
Wanpeng Li
32b72ecc83 KVM: X86: Expose PV_SCHED_YIELD CPUID feature bit to guest
Expose PV_SCHED_YIELD feature bit to guest, the guest can check this
feature bit before using paravirtualized sched yield.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 18:56:05 +02:00
Wanpeng Li
715062970f KVM: X86: Implement PV sched yield hypercall
The target vCPUs are in runnable state after vcpu_kick and suitable
as a yield target. This patch implements the sched yield hypercall.

17% performance increasement of ebizzy benchmark can be observed in an
over-subscribe environment. (w/ kvm-pv-tlb disabled, testing TLB flush
call-function IPI-many since call-function is not easy to be trigged
by userspace workload).

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 18:56:04 +02:00
Wanpeng Li
f85f6e7bc9 KVM: X86: Yield to IPI target if necessary
When sending a call-function IPI-many to vCPUs, yield if any of
the IPI target vCPUs was preempted, we just select the first
preempted target vCPU which we found since the state of target
vCPUs can change underneath and to avoid race conditions.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 18:56:01 +02:00
Vitaly Kuznetsov
11e349143e x86/kvm/nVMX: fix VMCLEAR when Enlightened VMCS is in use
When Enlightened VMCS is in use, it is valid to do VMCLEAR and,
according to TLFS, this should "transition an enlightened VMCS from the
active to the non-active state". It is, however, wrong to assume that
it is only valid to do VMCLEAR for the eVMCS which is currently active
on the vCPU performing VMCLEAR.

Currently, the logic in handle_vmclear() is broken: in case, there is no
active eVMCS on the vCPU doing VMCLEAR we treat the argument as a 'normal'
VMCS and kvm_vcpu_write_guest() to the 'launch_state' field irreversibly
corrupts the memory area.

So, in case the VMCLEAR argument is not the current active eVMCS on the
vCPU, how can we know if the area it is pointing to is a normal or an
enlightened VMCS?
Thanks to the bug in Hyper-V (see commit 72aeb60c52 ("KVM: nVMX: Verify
eVMCS revision id match supported eVMCS version on eVMCS VMPTRLD")) we can
not, the revision can't be used to distinguish between them. So let's
assume it is always enlightened in case enlightened vmentry is enabled in
the assist page. Also, check if vmx->nested.enlightened_vmcs_enabled to
minimize the impact for 'unenlightened' workloads.

Fixes: b8bbab928f ("KVM: nVMX: implement enlightened VMPTRLD and VMCLEAR")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 18:56:00 +02:00
Vitaly Kuznetsov
a21a39c206 x86/KVM/nVMX: don't use clean fields data on enlightened VMLAUNCH
Apparently, Windows doesn't maintain clean fields data after it does
VMCLEAR for an enlightened VMCS so we can only use it on VMRESUME.
The issue went unnoticed because currently we do nested_release_evmcs()
in handle_vmclear() and the consecutive enlightened VMPTRLD invalidates
clean fields when a new eVMCS is mapped but we're going to change the
logic.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-07-02 18:56:00 +02:00
Darrick J. Wong
677717fbd4 xfs: refactor INUMBERS to use iwalk functions
Now that we have generic functions to walk inode records, refactor the
INUMBERS implementation to use it.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:06 -07:00
Darrick J. Wong
04b8fba2e1 xfs: refactor iwalk code to handle walking inobt records
Refactor xfs_iwalk_ag_start and xfs_iwalk_ag so that the bits that are
particular to bulkstat (trimming the start irec, starting inode
readahead, and skipping empty groups) can be controlled via flags in the
iwag structure.

This enables us to add a new function to walk all inobt records which
will be used for the new INUMBERS implementation in the next patch.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:06 -07:00
Darrick J. Wong
2b5eb82601 xfs: refactor xfs_iwalk_grab_ichunk
In preparation for reusing the iwalk code for the inogrp walking code
(aka INUMBERS), move the initial inobt lookup and retrieval code out of
xfs_iwalk_grab_ichunk so that we call the masking code only when we need
to trim out the inodes that came before the cursor in the inobt record
(aka BULKSTAT).

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:06 -07:00
Darrick J. Wong
688f7c3678 xfs: clean up long conditionals in xfs_iwalk_ichunk_ra
Refactor xfs_iwalk_ichunk_ra to avoid long conditionals.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:06 -07:00
Darrick J. Wong
5e29f3b720 xfs: change xfs_iwalk_grab_ichunk to use startino, not lastino
Now that the inode chunk grabbing function is a static function in the
iwalk code, change its behavior so that @agino is the inode where we
want to /start/ the iteration.  This reduces cognitive friction with the
callers and simplifes the code.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
da1d9e5912 xfs: move bulkstat ichunk helpers to iwalk code
Now that we've reworked the bulkstat code to use iwalk, we can move the
old bulkstat ichunk helpers to xfs_iwalk.c.  No functional changes here.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
938c710d99 xfs: calculate inode walk prefetch more carefully
The existing inode walk prefetch is based on the old bulkstat code,
which simply allocated 4 pages worth of memory and prefetched that many
inobt records, regardless of however many inodes the caller requested.
65536 inodes is a lot to prefetch (~32M on x64, ~512M on arm64) so let's
scale things down a little more intelligently based on the number of
inodes requested, etc.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
2810bd6840 xfs: convert bulkstat to new iwalk infrastructure
Create a new ibulk structure incore to help us deal with bulk inode stat
state tracking and then convert the bulkstat code to use the new iwalk
iterator.  This disentangles inode walking from bulk stat control for
simpler code and enables us to isolate the formatter functions to the
ioctl handling code.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
f16fe3ecde xfs: bulkstat should copy lastip whenever userspace supplies one
When userspace passes in a @lastip pointer we should copy the results
back, even if the @ocount pointer is NULL.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
ebd126a651 xfs: convert quotacheck to use the new iwalk functions
Convert quotacheck to use the new iwalk iterator to dig through the
inodes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
a211432c27 xfs: create simplified inode walk function
Create a new iterator function to simplify walking inodes in an XFS
filesystem.  This new iterator will replace the existing open-coded
walking that goes on in various places.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Darrick J. Wong
5bb46e3e18 xfs: create iterator error codes
Currently, xfs doesn't have generic error codes defined for "stop
iterating"; we just reuse the XFS_BTREE_QUERY_* return values.  This
looks a little weird if we're not actually iterating a btree index.
Before we start adding more iterators, we should create general
XFS_ITER_{CONTINUE,ABORT} return values and define the XFS_BTREE_QUERY_*
ones from that.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
2019-07-02 09:40:05 -07:00
Jin Yao
c8f7bc1a08 perf diff: Documentation -c cycles option
Documentation the new computation selection 'cycles'.

 v4:
 ---
 Change the column 'Block cycles diff [start:end]' to
 '[Program Block Range] Cycles Diff'

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-8-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 13:20:51 -03:00
Jin Yao
b10c78c509 perf diff: Print the basic block cycles diff
$ perf record -b ./div
 $ perf record -b ./div

Following is the default perf diff output

 $ perf diff

 # Event 'cycles'
 #
 # Baseline  Delta Abs  Shared Object     Symbol
 # ........  .........  ................  ..................................
 #
     48.75%     +0.33%  div               [.] main
      8.21%     -0.20%  div               [.] compute_flag
     19.02%     -0.12%  libc-2.23.so      [.] __random_r
     16.17%     -0.09%  libc-2.23.so      [.] __random
      2.27%     -0.03%  div               [.] rand@plt
                +0.02%  [i915]            [k] gen8_irq_handler
      5.52%     +0.02%  libc-2.23.so      [.] rand

This patch creates a new computation selection 'cycles'.

 $ perf diff -c cycles

 # Event 'cycles'
 #
 # Baseline       [Program Block Range] Cycles Diff Shared Object Symbol
 # ........ ....................................... .........................................
 #
     48.75%             [div.c:42 -> div.c:45]  147 div           [.] main
     48.75%             [div.c:31 -> div.c:40]    4 div           [.] main
     48.75%             [div.c:40 -> div.c:40]    0 div           [.] main
     48.75%             [div.c:42 -> div.c:42]    0 div           [.] main
     48.75%             [div.c:42 -> div.c:44]    0 div           [.] main
     19.02% [random_r.c:357 -> random_r.c:360]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:373]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:376]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:380]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:392]    0 libc-2.23.so  [.] __random_r
     16.17%     [random.c:288 -> random.c:291]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:288 -> random.c:291]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:288 -> random.c:295]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:288 -> random.c:297]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:291 -> random.c:291]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:293 -> random.c:293]    0 libc-2.23.so  [.] __random
      8.21%             [div.c:22 -> div.c:22]  148 div           [.] compute_flag
      8.21%             [div.c:22 -> div.c:25]    0 div           [.] compute_flag
      8.21%             [div.c:27 -> div.c:28]    0 div           [.] compute_flag
      5.52%           [rand.c:26 -> rand.c:27]    0 libc-2.23.so  [.] rand
      5.52%           [rand.c:26 -> rand.c:28]    0 libc-2.23.so  [.] rand
      2.27%         [rand@plt+0 -> rand@plt+0]    0 div           [.] rand@plt
      0.01% [entry_64.S:694 -> entry_64.S:694]   16 [vmlinux]     [k] native_irq_return_iret
      0.00%       [fair.c:7676 -> fair.c:7665]  162 [vmlinux]     [k] update_blocked_averages

"[Program Block Range]" indicates the range of program basic block
(start -> end). If we can find the source line it prints the source line
otherwise it prints the symbol+offset instead.

 v4:
 ---
 Use source lines or symbol+offset to indicate the basic block. It should
 be easier to understand.

 v3:
 ---
 Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf.
 Use symbol_conf.report_block to check if executing hist_entry__block_fprintf.

 v2:
 ---
 Keep standard perf diff format and display the 'Baseline' and
 'Shared Object'.

The output is sorted by "Baseline" and the basic blocks in the same
function are sorted by cycles diff.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 13:20:51 -03:00
Jin Yao
f3810817b2 perf diff: Link same basic blocks among different data
The target is to compare the performance difference (cycles diff) for
the same basic blocks in different data files.

The same basic block means same function, same start address and same
end address. This patch finds the same basic blocks from different data
files and link them together and resort by the cycles diff.

 v3:
 ---
 The block stuffs are maintained by new structure 'block_hist',
 so this patch is update accordingly.

 v2:
 ---
 Since now the basic block hists is changed to per symbol,
 the patch only links the basic block hists for the same
 symbol in different data files.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-6-git-send-email-yao.jin@linux.intel.com
[ sym->name is an array, not a pointer, so no need to check it for NULL, fixes de build in some distros ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 13:20:15 -03:00
Jin Yao
99150a1faa perf diff: Use hists to manage basic blocks per symbol
The hist__account_cycles() can account cycles per basic block. The basic
block information is saved in cycles_hist structure.

This patch processes each symbol, get basic blocks from cycles_hist and
add the basic block entries to a new hists (in 'struct block_hist').
Using a hists is because we need to compare, sort and print the basic
blocks later.

 v6:
 ---
 Since 'ops' argument is removed from hists__add_entry_block,
 update the code accordingly. No functional change.

 v5:
 ---
 Since now we still carry block_info in 'struct hist_entry'
 we don't need to use our own new/free ops for hist entries.
 And the block_info is released in hist_entry__delete.

 v3:
 ---
 1. In v2, we put block stuffs in 'struct hist_entry', but
 it's not a good design. In v3, we create a new
 'struct block_hist' and cast the 'struct hist_entry' to
 'struct block_hist' in some places, which can avoid adding
 new stuffs in 'struct hist_entry'.

 2. abs() -> labs(), in block_cycles_diff_cmp().

 v2:
 ---
 v1 adds the basic block entries to per data-file hists
 but v2 adds the basic block entries to per symbol hists.
 That is to keep current perf-diff format. Will show the
 result in next patches.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 12:47:07 -03:00
Jin Yao
30d815534e perf diff: Check if all data files with branch stacks
We will expand perf diff to support diff cycles of individual programs
blocks, so it requires all data files having branch stacks.

This patch checks HEADER_BRANCH_STACK in header, and only set the flag
has_br_stack when HEADER_BRANCH_STACK are set in all data files.

 v2:
 ---
 Move check_file_brstack() from __cmd_diff() to cmd_diff().
 Because later patch will check flag 'has_br_stack' before
 ui_init().

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 12:46:11 -03:00
Jin Yao
fe96245c7f perf hists: Add block_info in hist_entry
The block_info contains the program basic block information, i.e,
contains the start address and the end address of this basic block and
how much cycles it takes.

We need to compare, sort and even print out the basic block by some
orders, i.e. sort by cycles.

For this purpose, we add block_info field to hist_entry. In order not to
impact current interface, we creates a new function
hists__add_entry_block.

 v6:
 ---
 Remove the 'ops' argument in hists__add_entry_block

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-3-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 12:45:23 -03:00
Jin Yao
0cec2447e7 perf symbol: Create block_info structure
'perf diff' currently can only diff symbols(functions).

We should expand it to diff cycles of individual programs blocks as
reported by timed LBR.  This would allow to identify changes in specific
code accurately.

We need a new structure to maintain the basic block information, such as,
symbol(function), start/end address of this block, cycles. This patch
creates this structure and with some ops.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-02 12:44:19 -03:00
Srinivas Pandruvada
f607874f35 platform/x86: ISST: Restore state on resume
Commands which causes PUNIT writes, store them and restore them on system
resume. The driver stores all such requests in a hash table and stores the
the latest mailbox request parameters. On resume these commands mail box
commands are executed again. There are only 5 such mail box commands which
will trigger such processing so a very low overhead in store and execute
on resume. Also there is no order requirement for mail box commands for
these write/set commands. There is one MSR request for changing turbo
ratio limits, this also stored and get restored on resume and cpu online.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
2019-07-02 18:41:16 +03:00
Srinivas Pandruvada
e765f37b9b platform/x86: ISST: Add Intel Speed Select PUNIT MSR interface
While using new non arhitectural features using PUNIT Mailbox and MMIO
read/write interface, still there is need to operate using MSRs to
control PUNIT. User space could have used user user-space MSR interface for
this, but when user space MSR access is disabled, then it can't. Here only
limited number of MSRs are allowed using this new interface.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
2019-07-02 18:41:16 +03:00
Srinivas Pandruvada
71b21bd7f6 platform/x86: ISST: Add Intel Speed Select mailbox interface via MSRs
Add an IOCTL to send mailbox commands to PUNIT using PUNIT MSRs for
mailbox. Some CPU models don't have PCI device, so need to use MSRs.
A limited set of mailbox commands can be sent to PUNIT.

This MMIO interface is used by the intel-speed-select tool under
tools/x86/power to enumerate and control Intel Speed Select features.
The MBOX commands ids and semantics of the message can be checked from
the source code of the tool.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
2019-07-02 18:41:16 +03:00
Srinivas Pandruvada
31a166fe9c platform/x86: ISST: Add Intel Speed Select mailbox interface via PCI
Add an IOCTL to send mailbox commands to PUNIT using PUNIT PCI device.
A limited set of mailbox commands can be sent to PUNIT.

This MMIO interface is used by the intel-speed-select tool under
tools/x86/power to enumerate and control Intel Speed Select features.
The MBOX commands ids and semantics of the message can be checked from
the source code of the tool.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
2019-07-02 18:41:16 +03:00