Paolo Bonzini [Thu, 11 Jun 2020 18:01:51 +0000 (14:01 -0400)]
KVM: x86: do not pass poisoned hva to __kvm_set_memory_region
__kvm_set_memory_region does not use the hva at all, so trying to
catch use-after-delete is pointless and, worse, it fails access_ok
now that we apply it to all memslots including private kernel ones.
This fixes an AVIC regression.
Fixes: eafc16c93920 ("KVM: check userspace_addr for all memslots") Reported-by: Maxim Levitsky <mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Vitaly Kuznetsov [Wed, 10 Jun 2020 16:41:16 +0000 (18:41 +0200)]
KVM: selftests: fix sync_with_host() in smm_test
It was reported that older GCCs compile smm_test in a way that breaks
it completely:
kvm_exit: reason EXIT_CPUID rip 0x4014db info 0 0
func 7ffffffd idx 830 rax 0 rbx 0 rcx 0 rdx 0, cpuid entry not found
...
kvm_exit: reason EXIT_MSR rip 0x40abd9 info 0 0
kvm_msr: msr_read 487 = 0x0 (#GP)
...
Note, '7ffffffd' was supposed to be '80000001' as we're checking for
SVM. Dropping '-O2' from compiler flags help. Turns out, asm block in
sync_with_host() is wrong. We us 'in 0xe, %%al' instruction to sync
with the host and in 'AL' register we actually pass the parameter
(stage) but after sync 'AL' gets written to but GCC thinks the value
is still there and uses it to compute 'EAX' for 'cpuid'.
smm_test can't fully use standard ucall() framework as we need to
write a very simple SMI handler there. Fix the immediate issue by
making RAX input/output operand. While on it, make sync_with_host()
static inline.
Reported-by: Marcelo Bandeira Condotta <mcondotta@redhat.com> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200610164116.770811-1-vkuznets@redhat.com> Reviewed-by: Jim Mattson <jmattson@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Vitaly Kuznetsov [Wed, 10 Jun 2020 17:55:32 +0000 (19:55 +0200)]
KVM: async_pf: Inject 'page ready' event only if 'page not present' was previously injected
'Page not present' event may or may not get injected depending on
guest's state. If the event wasn't injected, there is no need to
inject the corresponding 'page ready' event as the guest may get
confused. E.g. Linux thinks that the corresponding 'page not present'
event wasn't delivered *yet* and allocates a 'dummy entry' for it.
This entry is never freed.
Note, 'wakeup all' events have no corresponding 'page not present'
event and always get injected.
s390 seems to always be able to inject 'page not present', the
change is effectively a nop.
Vitaly Kuznetsov [Wed, 10 Jun 2020 17:55:31 +0000 (19:55 +0200)]
KVM: async_pf: Cleanup kvm_setup_async_pf()
schedule_work() returns 'false' only when the work is already on the queue
and this can't happen as kvm_setup_async_pf() always allocates a new one.
Also, to avoid potential race, it makes sense to to schedule_work() at the
very end after we've added it to the queue.
While on it, do some minor cleanup. gfn_to_pfn_async() mentioned in a
comment does not currently exist and, moreover, we can check
kvm_is_error_hva() at the very beginning, before we try to allocate work so
'retry_sync' label can go away completely.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200610175532.779793-1-vkuznets@redhat.com> Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Colin Ian King [Tue, 9 Jun 2020 23:31:21 +0000 (00:31 +0100)]
kvm: i8254: remove redundant assignment to pointer s
The pointer s is being assigned a value that is never read, the
assignment is redundant and can be removed.
Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King <colin.king@canonical.com>
Message-Id: <20200609233121.1118683-1-colin.king@canonical.com> Fixes: 10e0eeeb9360 ("KVM: In kernel PIT model") Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Felipe Franciosi [Tue, 19 May 2020 08:11:22 +0000 (08:11 +0000)]
KVM: x86: respect singlestep when emulating instruction
When userspace configures KVM_GUESTDBG_SINGLESTEP, KVM will manage the
presence of X86_EFLAGS_TF via kvm_set/get_rflags on vcpus. The actual
rflag bit is therefore hidden from callers.
That includes init_emulate_ctxt() which uses the value returned from
kvm_get_flags() to set ctxt->tf. As a result, x86_emulate_instruction()
will skip a single step, leaving singlestep_rip stale and not returning
to userspace.
This resolves the issue by observing the vcpu guest_debug configuration
alongside ctxt->tf in x86_emulate_instruction(), performing the single
step if set.
Cc: stable@vger.kernel.org Signed-off-by: Felipe Franciosi <felipe@nutanix.com>
Message-Id: <20200519081048.8204-1-felipe@nutanix.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Vitaly Kuznetsov [Wed, 10 Jun 2020 13:58:46 +0000 (15:58 +0200)]
KVM: selftests: do not substitute SVM/VMX check with KVM_CAP_NESTED_STATE check
state_test/smm_test use KVM_CAP_NESTED_STATE check as an indicator for
nested VMX/SVM presence and this is incorrect. Check for the required
features dirrectly.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200610135847.754289-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: nVMX: Consult only the "basic" exit reason when routing nested exit
Consult only the basic exit reason, i.e. bits 15:0 of vmcs.EXIT_REASON,
when determining whether a nested VM-Exit should be reflected into L1 or
handled by KVM in L0.
For better or worse, the switch statement in nested_vmx_exit_reflected()
currently defaults to "true", i.e. reflects any nested VM-Exit without
dedicated logic. Because the case statements only contain the basic
exit reason, any VM-Exit with modifier bits set will be reflected to L1,
even if KVM intended to handle it in L0.
Practically speaking, this only affects EXIT_REASON_MCE_DURING_VMENTRY,
i.e. a #MC that occurs on nested VM-Enter would be incorrectly routed to
L1, as "failed VM-Entry" is the only modifier that KVM can currently
encounter. The SMM modifiers will never be generated as KVM doesn't
support/employ a SMI Transfer Monitor. Ditto for "exit from enclave",
as KVM doesn't yet support virtualizing SGX, i.e. it's impossible to
enter an enclave in a KVM guest (L1 or L2).
Fixes: e002b955ff6f ("KVM: nVMX: Deciding if L0 or L1 should handle an L2 exit") Cc: Jim Mattson <jmattson@google.com> Cc: Xiaoyao Li <xiaoyao.li@intel.com> Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200227174430.26371-1-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: x86: Unexport x86_fpu_cache and make it static
Make x86_fpu_cache static now that FPU allocation and destruction is
handled entirely by common x86 code.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200608180218.20946-1-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: selftests: Ignore KVM 5-level paging support for VM_MODE_PXXV48_4K
Explicitly set the VA width to 48 bits for the x86_64-only PXXV48_4K VM
mode instead of asserting the guest VA width is 48 bits. The fact that
KVM supports 5-level paging is irrelevant unless the selftests opt-in to
5-level paging by setting CR4.LA57 for the guest. The overzealous
assert prevents running the selftests on a kernel with 5-level paging
enabled.
Incorporate LA57 into the assert instead of removing the assert entirely
as a sanity check of KVM's CPUID output.
Fixes: e9d17eded99f ("KVM: selftests: Introduce VM_MODE_PXXV48_4K") Reported-by: Sergio Perez Gonzalez <sergio.perez.gonzalez@intel.com> Cc: Adriana Cervantes Jimenez <adriana.cervantes.jimenez@intel.com> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200528021530.28091-1-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Eiichi Tsukata [Sat, 6 Jun 2020 04:26:27 +0000 (13:26 +0900)]
KVM: x86: Fix APIC page invalidation race
Commit 357e24c46b9f ("KVM: x86: fix APIC page invalidation") tried
to fix inappropriate APIC page invalidation by re-introducing arch
specific kvm_arch_mmu_notifier_invalidate_range() and calling it from
kvm_mmu_notifier_invalidate_range_start. However, the patch left a
possible race where the VMCS APIC address cache is updated *before*
it is unmapped:
Because of the above race, there can be a mismatch between the
host physical address stored in the APIC_ACCESS_PAGE VMCS field and
the host physical address stored in the EPT entry for the APIC GPA
(0xfee0000). When this happens, the processor will not trap APIC
accesses, and will instead show the raw contents of the APIC-access page.
Because Windows OS periodically checks for unexpected modifications to
the LAPIC register, this will show up as a BSOD crash with BugCheck
CRITICAL_STRUCTURE_CORRUPTION (109) we are currently seeing in
https://bugzilla.redhat.com/show_bug.cgi?id=1751017.
The root cause of the issue is that kvm_arch_mmu_notifier_invalidate_range()
cannot guarantee that no additional references are taken to the pages in
the range before kvm_mmu_notifier_invalidate_range_end(). Fortunately,
this case is supported by the MMU notifier API, as documented in
include/linux/mmu_notifier.h:
* If the subsystem
* can't guarantee that no additional references are taken to
* the pages in the range, it has to implement the
* invalidate_range() notifier to remove any references taken
* after invalidate_range_start().
The fix therefore is to reload the APIC-access page field in the VMCS
from kvm_mmu_notifier_invalidate_range() instead of ..._range_start().
Paolo Bonzini [Mon, 8 Jun 2020 11:11:47 +0000 (07:11 -0400)]
KVM: SVM: fix calls to is_intercept
is_intercept takes an INTERCEPT_* constant, not SVM_EXIT_*; because
of this, the compiler was removing the body of the conditionals,
as if is_intercept returned 0.
This unveils a latent bug: when clearing the VINTR intercept,
int_ctl must also be changed in the L1 VMCB (svm->nested.hsave),
just like the intercept itself is also changed in the L1 VMCB.
Otherwise V_IRQ remains set and, due to the VINTR intercept being clear,
we get a spurious injection of a vector 0 interrupt on the next
L2->L1 vmexit.
Reported-by: Qian Cai <cai@lca.pw> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Revert "KVM: x86: work around leak of uninitialized stack contents"
handle_vmptrst()/handle_vmread() stopped injecting #PF unconditionally
and switched to nested_vmx_handle_memory_failure() which just kills the
guest with KVM_EXIT_INTERNAL_ERROR in case of MMIO access, zeroing
'exception' in kvm_write_guest_virt_system() is not needed anymore.
but it is only set when GVA to GPA conversion fails. In case it doesn't but
we still fail kvm_vcpu_read_guest_page(), X86EMUL_IO_NEEDED is returned and
nested_vmx_get_vmptr() calls kvm_inject_emulated_page_fault() with zeroed
'exception'. This happen when the argument is MMIO.
Paolo also noticed that nested_vmx_get_vmptr() is not the only place in
KVM code where kvm_read/write_guest_virt*() return result is mishandled.
VMX instructions along with INVPCID have the same issue. This was already
noticed before, e.g. see commit c04b9fd59ce7 ("KVM: x86: work around
leak of uninitialized stack contents") but was never fully fixed.
KVM could've handled the request correctly by going to userspace and
performing I/O but there doesn't seem to be a good need for such requests
in the first place.
Introduce vmx_handle_memory_failure() as an interim solution.
Note, nested_vmx_get_vmptr() now has three possible outcomes: OK, PF,
KVM_EXIT_INTERNAL_ERROR and callers need to know if userspace exit is
needed (for KVM_EXIT_INTERNAL_ERROR) in case of failure. We don't seem
to have a good enum describing this tristate, just add "int *ret" to
nested_vmx_get_vmptr() interface to pass the information.
Reported-by: syzbot+2a7156e11dc199bdbd8a@syzkaller.appspotmail.com Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200605115906.532682-1-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Fri, 15 May 2020 16:18:14 +0000 (12:18 -0400)]
KVM: x86: emulate reserved nops from 0f/18 to 0f/1f
Instructions starting with 0f18 up to 0f1f are reserved nops, except those
that were assigned to MPX. These include the endbr markers used by CET.
List them correctly in the opcode table.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
"make ARCH=x86", however, works. The problem is that arch specific headers
for x86_64 live in 'tools/arch/x86/include', not in
'tools/arch/x86_64/include'.
Anthony Yznaga [Tue, 2 Jun 2020 20:07:30 +0000 (13:07 -0700)]
KVM: x86: minor code refactor and comments fixup around dirty logging
Consolidate the code and correct the comments to show that the actions
taken to update existing mappings to disable or enable dirty logging
are not necessary when creating, moving, or deleting a memslot.
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Message-Id: <1591128450-11977-4-git-send-email-anthony.yznaga@oracle.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Anthony Yznaga [Tue, 2 Jun 2020 20:07:29 +0000 (13:07 -0700)]
KVM: x86: avoid unnecessary rmap walks when creating/moving slots
On large memory guests it has been observed that creating a memslot
for a very large range can take noticeable amount of time.
Investigation showed that the time is spent walking the rmaps to update
existing sptes to remove write access or set/clear dirty bits to support
dirty logging. These rmap walks are unnecessary when creating or moving
a memslot. A newly created memslot will not have any existing mappings,
and the existing mappings of a moved memslot will have been invalidated
and flushed. Any mappings established once the new/moved memslot becomes
visible will be set using the properties of the new slot.
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Message-Id: <1591128450-11977-3-git-send-email-anthony.yznaga@oracle.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Anthony Yznaga [Tue, 2 Jun 2020 20:07:28 +0000 (13:07 -0700)]
KVM: x86: remove unnecessary rmap walk of read-only memslots
There's no write access to remove. An existing memslot cannot be updated
to set or clear KVM_MEM_READONLY, and any mappings established in a newly
created or moved read-only memslot will already be read-only.
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Message-Id: <1591128450-11977-2-git-send-email-anthony.yznaga@oracle.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove KVM_DEBUG_FS, which can easily be misconstrued as controlling
KVM-as-a-host. The sole user of CONFIG_KVM_DEBUG_FS was removed by
commit ca6318d3f8cc6 ("x86, locking/spinlocks: Remove ticket (spin)lock
implementation").
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200528031121.28904-1-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:41 +0000 (15:56 +0800)]
KVM: MIPS: Enable KVM support for Loongson-3
This patch enable KVM support for Loongson-3 by selecting HAVE_KVM, but
only enable KVM/VZ on Loongson-3A R4+ (because VZ of early processors
are incomplete). Besides, Loongson-3 support SMP guests, so we clear the
linked load bit of LLAddr in kvm_vz_vcpu_load() if the guest has more
than one VCPUs.
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-15-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:39 +0000 (15:56 +0800)]
KVM: MIPS: Add CONFIG6 and DIAG registers emulation
Loongson-3 has CONFIG6 and DIAG registers which need to be emulated.
CONFIG6 is mostly used to enable/disable FTLB and SFB, while DIAG is
mostly used to flush BTB, ITLB, DTLB, VTLB and FTLB.
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-13-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:38 +0000 (15:56 +0800)]
KVM: MIPS: Add CPUCFG emulation for Loongson-3
Loongson-3 overrides lwc2 instructions to implement CPUCFG and CSR
read/write functions. These instructions all cause guest exit so CSR
doesn't benifit KVM guest (and there are always legacy methods to
provide the same functions as CSR). So, we only emulate CPUCFG and let
it return a reduced feature list (which means the virtual CPU doesn't
have any other advanced features, including CSR) in KVM.
Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-12-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:37 +0000 (15:56 +0800)]
KVM: MIPS: Add Loongson-3 Virtual IPI interrupt support
This patch add Loongson-3 Virtual IPI interrupt support in the kernel.
The current implementation of IPI emulation in QEMU is based on GIC for
MIPS, but Loongson-3 doesn't use GIC. Furthermore, IPI emulation in QEMU
is too expensive for performance (because of too many context switches
between Host and Guest). With current solution, the IPI delay may even
cause RCU stall warnings in a multi-core Guest. So, we design a faster
solution that emulate IPI interrupt in kernel (only used by Loongson-3
now).
Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-11-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:36 +0000 (15:56 +0800)]
KVM: MIPS: Add more types of virtual interrupts
In current implementation, MIPS KVM uses IP2, IP3, IP4 and IP7 for
external interrupt, two kinds of IPIs and timer interrupt respectively,
but Loongson-3 based machines prefer to use IP2, IP3, IP6 and IP7 for
two kinds of external interrupts, IPI and timer interrupt. So we define
two priority-irq mapping tables: kvm_loongson3_priority_to_irq[] for
Loongson-3, and kvm_default_priority_to_irq[] for others. The virtual
interrupt infrastructure is updated to deliver all types of interrupts
from IP2, IP3, IP4, IP6 and IP7.
Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-10-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:35 +0000 (15:56 +0800)]
KVM: MIPS: Let indexed cacheops cause guest exit on Loongson-3
Loongson-3's indexed cache operations need a node-id in the address,
but in KVM guest the node-id may be incorrect. So, let indexed cache
operations cause guest exit on Loongson-3.
Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-9-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:34 +0000 (15:56 +0800)]
KVM: MIPS: Use root tlb to control guest's CCA for Loongson-3
KVM guest has two levels of address translation: guest tlb translates
GVA to GPA, and root tlb translates GPA to HPA. By default guest's CCA
is controlled by guest tlb, but Loongson-3 maintains all cache coherency
by hardware (including multi-core coherency and I/O DMA coherency) so it
prefers all guest mappings be cacheable mappings. Thus, we use root tlb
to control guest's CCA for Loongson-3.
Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-8-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Huacai Chen [Sat, 23 May 2020 07:56:33 +0000 (15:56 +0800)]
KVM: MIPS: Introduce and use cpu_guest_has_ldpte
Loongson-3 has lddir/ldpte instructions and their related CP0 registers
are the same as HTW. So we introduce a cpu_guest_has_ldpte flag and use
it to indicate whether we need to save/restore HTW related CP0 registers
(PWBase, PWSize, PWField and PWCtl).
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Huacai Chen <chenhc@lemote.com> Co-developed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Message-Id: <1590220602-3547-7-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xing Li [Sat, 23 May 2020 07:56:29 +0000 (15:56 +0800)]
KVM: MIPS: Fix VPN2_MASK definition for variable cpu_vmbits
If a CPU support more than 32bit vmbits (which is true for 64bit CPUs),
VPN2_MASK set to fixed 0xffffe000 will lead to a wrong EntryHi in some
functions such as _kvm_mips_host_tlb_inv().
The cpu_vmbits definition of 32bit CPU in cpu-features.h is 31, so we
still use the old definition.
Cc: Stable <stable@vger.kernel.org> Reviewed-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> Signed-off-by: Xing Li <lixing@loongson.cn>
[Huacai: Improve commit messages] Signed-off-by: Huacai Chen <chenhc@lemote.com>
Message-Id: <1590220602-3547-3-git-send-email-chenhc@lemote.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Babu Moger [Tue, 12 May 2020 23:59:16 +0000 (18:59 -0500)]
KVM: x86: Move MPK feature detection to common code
Both Intel and AMD support (MPK) Memory Protection Key feature.
Move the feature detection from VMX to the common code. It should
work for both the platforms now.
Signed-off-by: Babu Moger <babu.moger@amd.com>
Message-Id: <158932795627.44260.15144185478040178638.stgit@naples-babu.amd.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: VMX: Always treat MSR_IA32_PERF_CAPABILITIES as a valid PMU MSR
Unconditionally return true when querying the validity of
MSR_IA32_PERF_CAPABILITIES so as to defer the validity check to
intel_pmu_{get,set}_msr(), which can properly give the MSR a pass when
the access is initiated from host userspace. The MSR is emulated so
there is no underlying hardware dependency to worry about.
Fixes: 6a5e366a31d57 ("KVM: x86/pmu: Support full width counting") Cc: Like Xu <like.xu@linux.intel.com> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200603203303.28545-1-sean.j.christopherson@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Thu, 4 Jun 2020 13:16:52 +0000 (15:16 +0200)]
KVM: let kvm_destroy_vm_debugfs clean up vCPU debugfs directories
After commit bcf4938 ("KVM: x86: move kvm_create_vcpu_debugfs after
last failure point") we are creating the pre-vCPU debugfs files
after the creation of the vCPU file descriptor. This makes it
possible for userspace to reach kvm_vcpu_release before
kvm_create_vcpu_debugfs has finished. The vcpu->debugfs_dentry
then does not have any associated inode anymore, and this causes
a NULL-pointer dereference in debugfs_create_file.
The solution is simply to avoid removing the files; they are
cleaned up when the VM file descriptor is closed (and that must be
after KVM_CREATE_VCPU returns). We can stop storing the dentry
in struct kvm_vcpu too, because it is not needed anywhere after
kvm_create_vcpu_debugfs returns.
Reported-by: syzbot+705f4401d5a93a59b87d@syzkaller.appspotmail.com Fixes: bcf4938d486b ("KVM: x86: move kvm_create_vcpu_debugfs after last failure point") Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Linus Torvalds [Thu, 4 Jun 2020 04:22:46 +0000 (21:22 -0700)]
atomisp: avoid warning about unused function
The atomisp_mrfld_power() function isn't actually ever called, because
the two call-sites have commented out the use because it breaks on some
platforms. That results in:
drivers/staging/media/atomisp/pci/atomisp_v4l2.c:764:12: warning: ‘atomisp_mrfld_power’ defined but not used [-Wunused-function]
764 | static int atomisp_mrfld_power(struct atomisp_device *isp, bool enable)
| ^~~~~~~~~~~~~~~~~~~
during the build.
Rather than commenting out the use entirely, just disable it
semantically instead (using a "0 &&" construct), leaving the call in
place from a syntax standpoint, and avoiding the warning.
I really don't want my builds to have any warnings that can then hide
real issues.
Linus Torvalds [Thu, 4 Jun 2020 03:59:38 +0000 (20:59 -0700)]
Merge tag 'media/v5.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media
Pull media updates from Mauro Carvalho Chehab:
- Media documentation is now split into admin-guide, driver-api and
userspace-api books (a longstanding request from Jon);
- The media Kconfig was reorganized, in order to make easier to select
drivers and their dependencies;
- The testing drivers now has a separate directory;
- added a new driver for Rockchip Video Decoder IP;
- The atomisp staging driver was resurrected. It is meant to work with
4 generations of cameras on Atom-based laptops, tablets and cell
phones. So, it seems worth investing time to cleanup this driver and
making it in good shape.
- Added some V4L2 core ancillary routines to help with h264 codecs;
- Added an ov2740 image sensor driver;
- The si2157 gained support for Analog TV, which, in turn, added
support for some cx231xx and cx23885 boards to also support analog
standards;
- Added some V4L2 controls (V4L2_CID_CAMERA_ORIENTATION and
V4L2_CID_CAMERA_SENSOR_ROTATION) to help identifying where the camera
is located at the device;
- VIDIOC_ENUM_FMT was extended to support MC-centric devices;
- Lots of drivers improvements and cleanups.
* tag 'media/v5.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media: (503 commits)
media: Documentation: media: Refer to mbus format documentation from CSI-2 docs
media: s5k5baf: Replace zero-length array with flexible-array
media: i2c: imx219: Drop <linux/clk-provider.h> and <linux/clkdev.h>
media: i2c: Add ov2740 image sensor driver
media: ov8856: Implement sensor module revision identification
media: ov8856: Add devicetree support
media: dt-bindings: ov8856: Document YAML bindings
media: dvb-usb: Add Cinergy S2 PCIe Dual Port support
media: dvbdev: Fix tuner->demod media controller link
media: dt-bindings: phy: phy-rockchip-dphy-rx0: move rockchip dphy rx0 bindings out of staging
media: staging: dt-bindings: phy-rockchip-dphy-rx0: remove non-used reg property
media: atomisp: unify the version for isp2401 a0 and b0 versions
media: atomisp: update TODO with the current data
media: atomisp: adjust some code at sh_css that could be broken
media: atomisp: don't produce errs for ignored IRQs
media: atomisp: print IRQ when debugging
media: atomisp: isp_mmu: don't use kmem_cache
media: atomisp: add a notice about possible leak resources
media: atomisp: disable the dynamic and reserved pools
media: atomisp: turn on camera before setting it
...
Linus Torvalds [Thu, 4 Jun 2020 03:24:15 +0000 (20:24 -0700)]
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
"More mm/ work, plenty more to come
Subsystems affected by this patch series: slub, memcg, gup, kasan,
pagealloc, hugetlb, vmscan, tools, mempolicy, memblock, hugetlbfs,
thp, mmap, kconfig"
* akpm: (131 commits)
arm64: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
x86: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
riscv: support DEBUG_WX
mm: add DEBUG_WX support
drivers/base/memory.c: cache memory blocks in xarray to accelerate lookup
mm/thp: rename pmd_mknotpresent() as pmd_mkinvalid()
powerpc/mm: drop platform defined pmd_mknotpresent()
mm: thp: don't need to drain lru cache when splitting and mlocking THP
hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
sparc32: register memory occupied by kernel as memblock.memory
include/linux/memblock.h: fix minor typo and unclear comment
mm, mempolicy: fix up gup usage in lookup_node
tools/vm/page_owner_sort.c: filter out unneeded line
mm: swap: memcg: fix memcg stats for huge pages
mm: swap: fix vmstats for huge pages
mm: vmscan: limit the range of LRU type balancing
mm: vmscan: reclaim writepage is IO cost
mm: vmscan: determine anon/file pressure balance at the reclaim root
mm: balance LRU lists based on relative thrashing
mm: only count actual rotations as LRU reclaim cost
...
Zong Li [Wed, 3 Jun 2020 23:03:52 +0000 (16:03 -0700)]
mm: add DEBUG_WX support
Patch series "Extract DEBUG_WX to shared use".
Some architectures support DEBUG_WX function, it's verbatim from each
others, so extract to mm/Kconfig.debug for shared use.
PPC and ARM ports don't support generic page dumper yet, so we only
refine x86 and arm64 port in this patch series.
For RISC-V port, the DEBUG_WX support depends on other patches which
be merged already:
- RISC-V page table dumper
- Support strict kernel memory permissions for security
This patch (of 4):
Some architectures support DEBUG_WX function, it's verbatim from each
others. Extract to mm/Kconfig.debug for shared use.
Scott Cheloha [Wed, 3 Jun 2020 23:03:48 +0000 (16:03 -0700)]
drivers/base/memory.c: cache memory blocks in xarray to accelerate lookup
Searching for a particular memory block by id is an O(n) operation because
each memory block's underlying device is kept in an unsorted linked list
on the subsystem bus.
We can cut the lookup cost to O(log n) if we cache each memory block
in an xarray. This time complexity improvement is significant on
systems with many memory blocks. For example:
1. A 128GB POWER9 VM with 256MB memblocks has 512 blocks. With this
change memory_dev_init() completes ~12ms faster and walk_memory_blocks()
completes ~12ms faster.
2. A 256GB POWER9 LPAR with 256MB memblocks has 1024 blocks. With
this change memory_dev_init() completes ~88ms faster and
walk_memory_blocks() completes ~87ms faster.
3. A 32TB POWER9 LPAR with 256MB memblocks has 131072 blocks. With
this change we complete memory_dev_init() ~37 minutes faster and
walk_memory_blocks() at least ~30 minutes faster. The exact timing
for walk_memory_blocks() is missing, though I observed that the
soft lockups in walk_memory_blocks() disappeared with the change,
suggesting that lower bound.
After:
[ 13.696898] memory_dev_init: adding blocks
[ 15.660035] memory_dev_init: added all blocks
(the walk_memory_blocks traces disappear)
There should be no significant negative impact for machines with few
memory blocks. A sparse xarray has a small footprint and an O(log n)
lookup is negligibly slower than an O(n) lookup for only the smallest
number of memory blocks.
1. A 16GB x86 machine with 128MB memblocks has 132 blocks. With this
change memory_dev_init() completes ~300us faster and walk_memory_blocks()
completes no faster or slower. The improvement is pretty close to noise.
mm/thp: rename pmd_mknotpresent() as pmd_mkinvalid()
pmd_present() is expected to test positive after pmdp_mknotpresent() as
the PMD entry still points to a valid huge page in memory.
pmdp_mknotpresent() implies that given PMD entry is just invalidated from
MMU perspective while still holding on to pmd_page() referred valid huge
page thus also clearing pmd_present() test. This creates the following
situation which is counter intuitive.
[pmd_present(pmd_mknotpresent(pmd)) = true]
This renames pmd_mknotpresent() as pmd_mkinvalid() reflecting the helper's
functionality more accurately while changing the above mentioned situation
as follows. This does not create any functional change.
[pmd_present(pmd_mkinvalid(pmd)) = true]
This is not applicable for platforms that define own pmdp_invalidate() via
__HAVE_ARCH_PMDP_INVALIDATE. Suggestion for renaming came during a
previous discussion here.
powerpc/mm: drop platform defined pmd_mknotpresent()
Patch series "mm/thp: Rename pmd_mknotpresent() as pmd_mknotvalid()", v2.
This series renames pmd_mknotpresent() as pmd_mknotvalid(). Before that
it drops an existing pmd_mknotpresent() definition from powerpc platform
which was never required as it defines it's pmdp_invalidate() through
subscribing __HAVE_ARCH_PMDP_INVALIDATE. This does not create any
functional change.
This rename was suggested by Catalin during a previous discussion while we
were trying to change the THP helpers on arm64 platform for migration.
Platform needs to define pmd_mknotpresent() for generic pmdp_invalidate()
only when __HAVE_ARCH_PMDP_INVALIDATE is not subscribed. Otherwise
platform specific pmd_mknotpresent() is not required. Hence just drop it.
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1587520326-10099-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r/1584680057-13753-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r/1584680057-13753-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Yang Shi [Wed, 3 Jun 2020 23:03:37 +0000 (16:03 -0700)]
mm: thp: don't need to drain lru cache when splitting and mlocking THP
Since commit 4f1d33f5ce94 ("mm/swap.c: flush lru pvecs on compound page
arrival") THP would not stay in pagevec anymore. So the optimization made
by commit 3166d3d92f77 ("thp: increase split_huge_page() success rate")
doesn't make sense anymore, which tries to unpin munlocked THPs from
pagevec by draining pagevec.
Draining lru cache before isolating THP in mlock path is also unnecessary. 634720d40076 ("mm, thp: fix mapped pages avoiding unevictable list on
mlock") added it and 28d7bdb0830c ("thp, mlock: do not mlock PTE-mapped
file huge pages") accidentally carried it over after the above
optimization went in.
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Link: http://lkml.kernel.org/r/1585946493-7531-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Shijie Hu [Wed, 3 Jun 2020 23:03:34 +0000 (16:03 -0700)]
hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
In a 32-bit program, running on arm64 architecture. When the address
space below mmap base is completely exhausted, shmat() for huge pages will
return ENOMEM, but shmat() for normal pages can still success on no-legacy
mode. This seems not fair.
For normal pages, the calling trace of get_unmapped_area() is:
=> mm->get_unmapped_area()
if on legacy mode,
=> arch_get_unmapped_area()
=> vm_unmapped_area()
if on no-legacy mode,
=> arch_get_unmapped_area_topdown()
=> vm_unmapped_area()
For huge pages, the calling trace of get_unmapped_area() is:
To solve this issue, we only need to make hugetlb_get_unmapped_area() take
the same way as mm->get_unmapped_area(). Add *bottomup() and *topdown()
for hugetlbfs, and check current mm->get_unmapped_area() to decide which
one to use. If mm->get_unmapped_area is equal to
arch_get_unmapped_area_topdown(), hugetlb_get_unmapped_area() calls
topdown routine, otherwise calls bottomup routine.
Reported-by: kbuild test robot <lkp@intel.com> Signed-off-by: Shijie Hu <hushijie3@huawei.com> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Will Deacon <will@kernel.org> Cc: Xiaoming Ni <nixiaoming@huawei.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: yangerkun <yangerkun@huawei.com> Cc: ChenGang <cg.chen@huawei.com> Cc: Chen Jie <chenjie6@huawei.com> Link: http://lkml.kernel.org/r/20200518065338.113664-1-hushijie3@huawei.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mike Rapoport [Wed, 3 Jun 2020 23:03:31 +0000 (16:03 -0700)]
sparc32: register memory occupied by kernel as memblock.memory
sparc32 never registered the memory occupied by the kernel image with
memblock_add() and it only reserved this memory with meblock_reserve().
With openbios as system firmware, the memory occupied by the kernel is
reserved in openbios and removed from mem.available. The prom setup code
in the kernel uses mem.available to set up the memory banks and
essentially there is a hole for the memory occupied by the kernel image.
Later in bootmem_init() this memory is memblock_reserve()d.
Up until recently, memmap initialization would call __init_single_page()
for the pages in that hole, the free_low_memory_core_early() would mark
them as reserved and everything would be Ok.
After the change in memmap initialization introduced by the commit "mm:
memmap_init: iterate over memblock regions rather that check each PFN",
the hole is skipped and the page structs for it are not initialized. And
when they are passed from memblock to page allocator as reserved, the
latter gets confused.
Simply registering the memory occupied by the kernel with memblock_add()
resolves this issue.
Tested on qemu-system-sparc with Debian Etch [1] userspace.
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: David S. Miller <davem@davemloft.net> Cc: Guenter Roeck <linux@roeck-us.net> Link: https://lkml.kernel.org/r/20200517000050.GA87467@roeck-us.nlllllet/ Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
chenqiwu [Wed, 3 Jun 2020 23:03:28 +0000 (16:03 -0700)]
include/linux/memblock.h: fix minor typo and unclear comment
Fix a minor typo "usabe->usable" for the current discription of member
variable "memory" in struct memblock.
BTW, I think it's unclear the member variable "base" in struct
memblock_type is currently described as the physical address of memory
region, change it to base address of the region is clearer since the
variable is decorated as phys_addr_t.
Michal Hocko [Wed, 3 Jun 2020 23:03:25 +0000 (16:03 -0700)]
mm, mempolicy: fix up gup usage in lookup_node
a970f48055e4 ("mm/mempolicy: Allow lookup_node() to handle fatal signal")
has added a special casing for 0 return value because that was a possible
gup return value when interrupted by fatal signal. This has been fixed by 2baf50d068ff ("mm/gup: Let __get_user_pages_locked() return -EINTR for
fatal signal") in the mean time so a970f48055e4 can be reverted.
This patch however doesn't go all the way to revert it because the check
for 0 is wrong and confusing here. Firstly it is inherently unsafe to
access the page when get_user_pages_locked returns 0 (aka no page
returned).
Fortunatelly this will not happen because get_user_pages_locked will not
return 0 when nr_pages > 0 unless FOLL_NOWAIT is specified which is not
the case here. Document this potential error code in gup code while we
are at it.
Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Xu <peterx@redhat.com> Link: http://lkml.kernel.org/r/20200421071026.18394-1-mhocko@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Changhee Han [Wed, 3 Jun 2020 23:03:22 +0000 (16:03 -0700)]
tools/vm/page_owner_sort.c: filter out unneeded line
To see a sorted result from page_owner, there must be a tiresome
preprocessing step before running page_owner_sort. This patch simply
filters out lines which start with "PFN" while reading the page owner
report.
Signed-off-by: Changhee Han <ch0.han@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Jonathan Corbet <corbet@lwn.net> Link: http://lkml.kernel.org/r/20200429052940.16968-1-ch0.han@lge.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Shakeel Butt [Wed, 3 Jun 2020 23:03:19 +0000 (16:03 -0700)]
mm: swap: memcg: fix memcg stats for huge pages
The commit 947a705ad4fb ("mm: per-cgroup memory reclaim stats") added
PGLAZYFREE, PGACTIVATE & PGDEACTIVATE stats for cgroups but missed
couple of places and PGLAZYFREE missed huge page handling. Fix that.
Also for PGLAZYFREE use the irq-unsafe function to update as the irq is
already disabled.
Shakeel Butt [Wed, 3 Jun 2020 23:03:16 +0000 (16:03 -0700)]
mm: swap: fix vmstats for huge pages
Many of the callbacks called by pagevec_lru_move_fn() does not correctly
update the vmstats for huge pages. Fix that. Also __pagevec_lru_add_fn()
use the irq-unsafe alternative to update the stat as the irqs are
already disabled.
Signed-off-by: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: http://lkml.kernel.org/r/20200527182916.249910-1-shakeelb@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:03:13 +0000 (16:03 -0700)]
mm: vmscan: limit the range of LRU type balancing
When LRU cost only shows up on one list, we abruptly stop scanning that
list altogether. That's an extreme reaction: by the time the other list
starts thrashing and the pendulum swings back, we may have no recent age
information on the first list anymore, and we could have significant
latencies until the scanner has caught up.
Soften this change in the feedback system by ensuring that no list
receives less than a third of overall pressure, and only distribute the
other 66% according to LRU cost. This ensures that we maintain a minimum
rate of aging on the entire workingset while it's being pressured, while
still allowing a generous rate of convergence when the relative sizes of
the lists need to adjust.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-15-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:03:09 +0000 (16:03 -0700)]
mm: vmscan: reclaim writepage is IO cost
The VM tries to balance reclaim pressure between anon and file so as to
reduce the amount of IO incurred due to the memory shortage. It already
counts refaults and swapins, but in addition it should also count
writepage calls during reclaim.
For swap, this is obvious: it's IO that wouldn't have occurred if the
anonymous memory hadn't been under memory pressure. From a relative
balancing point of view this makes sense as well: even if anon is cold and
reclaimable, a cache that isn't thrashing may have equally cold pages that
don't require IO to reclaim.
For file writeback, it's trickier: some of the reclaim writepage IO would
have likely occurred anyway due to dirty expiration. But not all of it -
premature writeback reduces batching and generates additional writes.
Since the flushers are already woken up by the time the VM starts writing
cache pages one by one, let's assume that we'e likely causing writes that
wouldn't have happened without memory pressure. In addition, the per-page
cost of IO would have probably been much cheaper if written in larger
batches from the flusher thread rather than the single-page-writes from
kswapd.
For our purposes - getting the trend right to accelerate convergence on a
stable state that doesn't require paging at all - this is sufficiently
accurate. If we later wanted to optimize for sustained thrashing, we can
still refine the measurements.
Count all writepage calls from kswapd as IO cost toward the LRU that the
page belongs to.
Why do this dynamically? Don't we know in advance that anon pages require
IO to reclaim, and so could build in a static bias?
First, scanning is not the same as reclaiming. If all the anon pages are
referenced, we may not swap for a while just because we're scanning the
anon list. During this time, however, it's important that we age
anonymous memory and the page cache at the same rate so that their
hot-cold gradients are comparable. Everything else being equal, we still
want to reclaim the coldest memory overall.
Second, we keep copies in swap unless the page changes. If there is
swap-backed data that's mostly read (tmpfs file) and has been swapped out
before, we can reclaim it without incurring additional IO.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:03:06 +0000 (16:03 -0700)]
mm: vmscan: determine anon/file pressure balance at the reclaim root
We split the LRU lists into anon and file, and we rebalance the scan
pressure between them when one of them begins thrashing: if the file cache
experiences workingset refaults, we increase the pressure on anonymous
pages; if the workload is stalled on swapins, we increase the pressure on
the file cache instead.
With cgroups and their nested LRU lists, we currently don't do this
correctly. While recursive cgroup reclaim establishes a relative LRU
order among the pages of all involved cgroups, LRU pressure balancing is
done on an individual cgroup LRU level. As a result, when one cgroup is
thrashing on the filesystem cache while a sibling may have cold anonymous
pages, pressure doesn't get equalized between them.
This patch moves LRU balancing decision to the root of reclaim - the same
level where the LRU order is established.
It does this by tracking LRU cost recursively, so that every level of the
cgroup tree knows the aggregate LRU cost of all memory within its domain.
When the page scanner calculates the scan balance for any given individual
cgroup's LRU list, it uses the values from the ancestor cgroup that
initiated the reclaim cycle.
If one sibling is then thrashing on the cache, it will tip the pressure
balance inside its ancestors, and the next hierarchical reclaim iteration
will go more after the anon pages in the tree.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:03:03 +0000 (16:03 -0700)]
mm: balance LRU lists based on relative thrashing
Since the LRUs were split into anon and file lists, the VM has been
balancing between page cache and anonymous pages based on per-list ratios
of scanned vs. rotated pages. In most cases that tips page reclaim
towards the list that is easier to reclaim and has the fewest actively
used pages, but there are a few problems with it:
1. Refaults and LRU rotations are weighted the same way, even though
one costs IO and the other costs a bit of CPU.
2. The less we scan an LRU list based on already observed rotations,
the more we increase the sampling interval for new references, and
rotations become even more likely on that list. This can enter a
death spiral in which we stop looking at one list completely until
the other one is all but annihilated by page reclaim.
Since commit 907c142b39d9 ("mm: thrash detection-based file cache sizing")
we have refault detection for the page cache. Along with swapin events,
they are good indicators of when the file or anon list, respectively, is
too small for its workingset and needs to grow.
For example, if the page cache is thrashing, the cache pages need more
time in memory, while there may be colder pages on the anonymous list.
Likewise, if swapped pages are faulting back in, it indicates that we
reclaim anonymous pages too aggressively and should back off.
Replace LRU rotations with refaults and swapins as the basis for relative
reclaim cost of the two LRUs. This will have the VM target list balances
that incur the least amount of IO on aggregate.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:03:00 +0000 (16:03 -0700)]
mm: only count actual rotations as LRU reclaim cost
When shrinking the active file list we rotate referenced pages only when
they're in an executable mapping. The others get deactivated. When it
comes to balancing scan pressure, though, we count all referenced pages as
rotated, even the deactivated ones. Yet they do not carry the same cost
to the system: the deactivated page *might* refault later on, but the
deactivation is tangible progress toward freeing pages; rotations on the
other hand cost time and effort without getting any closer to freeing
memory.
Don't treat both events as equal. The following patch will hook up LRU
balancing to cache and anon refaults, which are a much more concrete cost
signal for reclaiming one list over the other. Thus, remove the maybe-IO
cost bias from page references, and only note the CPU cost for actual
rotations that prevent the pages from getting reclaimed.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Minchan Kim <minchan@kernel.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:57 +0000 (16:02 -0700)]
mm: deactivations shouldn't bias the LRU balance
Operations like MADV_FREE, FADV_DONTNEED etc. currently move any affected
active pages to the inactive list to accelerate their reclaim (good) but
also steer page reclaim toward that LRU type, or away from the other
(bad).
The reason why this is undesirable is that such operations are not part of
the regular page aging cycle, and rather a fluke that doesn't say much
about the remaining pages on that list; they might all be in heavy use,
and once the chunk of easy victims has been purged, the VM continues to
apply elevated pressure on those remaining hot pages. The other LRU,
meanwhile, might have easily reclaimable pages, and there was never a need
to steer away from it in the first place.
As the previous patch outlined, we should focus on recording actually
observed cost to steer the balance rather than speculating about the
potential value of one LRU list over the other. In that spirit, leave
explicitely deactivated pages to the LRU algorithm to pick up, and let
rotations decide which list is the easiest to reclaim.
[cai@lca.pw: fix set-but-not-used warning] Link: http://lkml.kernel.org/r/20200522133335.GA624@Qians-MacBook-Air.local Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Minchan Kim <minchan@kernel.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Rik van Riel <riel@surriel.com> Cc: Qian Cai <cai@lca.pw> Link: http://lkml.kernel.org/r/20200520232525.798933-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:53 +0000 (16:02 -0700)]
mm: base LRU balancing on an explicit cost model
Currently, scan pressure between the anon and file LRU lists is balanced
based on a mixture of reclaim efficiency and a somewhat vague notion of
"value" of having certain pages in memory over others. That concept of
value is problematic, because it has caused us to count any event that
remotely makes one LRU list more or less preferrable for reclaim, even
when these events are not directly comparable and impose very different
costs on the system. One example is referenced file pages that we still
deactivate and referenced anonymous pages that we actually rotate back to
the head of the list.
There is also conceptual overlap with the LRU algorithm itself. By
rotating recently used pages instead of reclaiming them, the algorithm
already biases the applied scan pressure based on page value. Thus, when
rebalancing scan pressure due to rotations, we should think of reclaim
cost, and leave assessing the page value to the LRU algorithm.
Lastly, considering both value-increasing as well as value-decreasing
events can sometimes cause the same type of event to be counted twice,
i.e. how rotating a page increases the LRU value, while reclaiming it
succesfully decreases the value. In itself this will balance out fine,
but it quietly skews the impact of events that are only recorded once.
The abstract metric of "value", the murky relationship with the LRU
algorithm, and accounting both negative and positive events make the
current pressure balancing model hard to reason about and modify.
This patch switches to a balancing model of accounting the concrete,
actually observed cost of reclaiming one LRU over another. For now, that
cost includes pages that are scanned but rotated back to the list head.
Subsequent patches will add consideration for IO caused by refaulting of
recently evicted pages.
Replace struct zone_reclaim_stat with two cost counters in the lruvec, and
make everything that affects cost go through a new lru_note_cost()
function.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:50 +0000 (16:02 -0700)]
mm: vmscan: drop unnecessary div0 avoidance rounding in get_scan_count()
When we calculate the relative scan pressure between the anon and file LRU
lists, we have to assume that reclaim_stat can contain zeroes. To avoid
div0 crashes, we add 1 to all denominators like so:
/*
* The amount of pressure on anon vs file pages is inversely
* proportional to the fraction of recently scanned pages on
* each list that were recently referenced and in active use.
*/
ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
ap /= reclaim_stat->recent_rotated[0] + 1;
While reclaim_stat can contain 0, it's not actually possible for ap + fp
to be 0. One of anon_prio or file_prio could be zero, but they must still
add up to 200. And the reclaim_stat fraction, due to the +1 in there, is
always at least 1. So if one of the two numerators is 0, the other one
can't be. ap + fp is always at least 1. Drop the + 1.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-8-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:46 +0000 (16:02 -0700)]
mm: remove use-once cache bias from LRU balancing
When the splitlru patches divided page cache and swap-backed pages into
separate LRU lists, the pressure balance between the lists was biased to
account for the fact that streaming IO can cause memory pressure with a
flood of pages that are used only once. New page cache additions would
tip the balance toward the file LRU, and repeat access would neutralize
that bias again. This ensured that page reclaim would always go for
used-once cache first.
Since a9c649200577 ("mm,vmscan: only evict file pages when we have
plenty"), page reclaim generally skips over swap-backed memory entirely as
long as there is used-once cache present, and will apply the LRU balancing
when only repeatedly accessed cache pages are left - at which point the
previous use-once bias will have been neutralized. This makes the
use-once cache balancing bias unnecessary.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-7-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:43 +0000 (16:02 -0700)]
mm: workingset: let cache workingset challenge anon
We activate cache refaults with reuse distances in pages smaller than the
size of the total cache. This allows new pages with competitive access
frequencies to establish themselves, as well as challenge and potentially
displace pages on the active list that have gone cold.
However, that assumes that active cache can only replace other active
cache in a competition for the hottest memory. This is not a great
default assumption. The page cache might be thrashing while there are
enough completely cold and unused anonymous pages sitting around that we'd
only have to write to swap once to stop all IO from the cache.
Activate cache refaults when their reuse distance in pages is smaller than
the total userspace workingset, including anonymous pages.
Reclaim can still decide how to balance pressure among the two LRUs
depending on the IO situation. Rotational drives will prefer avoiding
random IO from swap and go harder after cache. But fundamentally, hot
cache should be able to compete with anon pages for a place in RAM.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-6-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:40 +0000 (16:02 -0700)]
mm: fold and remove lru_cache_add_anon() and lru_cache_add_file()
They're the same function, and for the purpose of all callers they are
equivalent to lru_cache_add().
[akpm@linux-foundation.org: fix it for local_lock changes] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@surriel.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Link: http://lkml.kernel.org/r/20200520232525.798933-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:37 +0000 (16:02 -0700)]
mm: allow swappiness that prefers reclaiming anon over the file workingset
With the advent of fast random IO devices (SSDs, PMEM) and in-memory swap
devices such as zswap, it's possible for swap to be much faster than
filesystems, and for swapping to be preferable over thrashing filesystem
caches.
Allow setting swappiness - which defines the rough relative IO cost of
cache misses between page cache and swap-backed pages - to reflect such
situations by making the swap-preferred range configurable.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:34 +0000 (16:02 -0700)]
mm: keep separate anon and file statistics on page reclaim activity
Having statistics on pages scanned and pages reclaimed for both anon and
file pages makes it easier to evaluate changes to LRU balancing.
While at it, clean up the stat-keeping mess for isolation, putback,
reclaim stats etc. a bit: first the physical LRU operation (isolation and
putback), followed by vmstats, reclaim_stats, and then vm events.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Link: http://lkml.kernel.org/r/20200520232525.798933-3-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:31 +0000 (16:02 -0700)]
mm: fix LRU balancing effect of new transparent huge pages
The reclaim code that balances between swapping and cache reclaim tries to
predict likely reuse based on in-memory reference patterns alone. This
works in many cases, but when it fails it cannot detect when the cache is
thrashing pathologically, or when we're in the middle of a swap storm.
The high seek cost of rotational drives under which the algorithm evolved
also meant that mistakes could quickly result in lockups from too
aggressive swapping (which is predominantly random IO). As a result, the
balancing code has been tuned over time to a point where it mostly goes
for page cache and defers swapping until the VM is under significant
memory pressure.
The resulting strategy doesn't make optimal caching decisions - where
optimal is the least amount of IO required to execute the workload.
The proliferation of fast random IO devices such as SSDs, in-memory
compression such as zswap, and persistent memory technologies on the
horizon, has made this undesirable behavior very noticable: Even in the
presence of large amounts of cold anonymous memory and a capable swap
device, the VM refuses to even seriously scan these pages, and can leave
the page cache thrashing needlessly.
This series sets out to address this. Since commit ("907c142b39d9 mm:
thrash detection-based file cache sizing") we have exact tracking of
refault IO - the ultimate cost of reclaiming the wrong pages. This allows
us to use an IO cost based balancing model that is more aggressive about
scanning anonymous memory when the cache is thrashing, while being able to
avoid unnecessary swap storms.
These patches base the LRU balance on the rate of refaults on each list,
times the relative IO cost between swap device and filesystem
(swappiness), in order to optimize reclaim for least IO cost incurred.
History
I floated these changes in 2016. At the time they were incomplete and
full of workarounds due to a lack of infrastructure in the reclaim code:
We didn't have PageWorkingset, we didn't have hierarchical cgroup
statistics, and problems with the cgroup swap controller. As swapping
wasn't too high a priority then, the patches stalled out. With all
dependencies in place now, here we are again with much cleaner,
feature-complete patches.
I kept the acks for patches that stayed materially the same :-)
Below is a series of test results that demonstrate certain problematic
behavior of the current code, as well as showcase the new code's more
predictable and appropriate balancing decisions.
Test #1: No convergence
This test shows an edge case where the VM currently doesn't converge at
all on a new file workingset with a stale anon/tmpfs set.
The test sets up a cold anon set the size of 3/4 RAM, then tries to
establish a new file set half the size of RAM (flat access pattern).
The vanilla kernel refuses to even scan anon pages and never converges.
The file set is perpetually served from the filesystem.
The first test kernel is with the series up to the workingset patch
applied. This allows thrashing page cache to challenge the anonymous
workingset. The VM then scans the lists based on the current
scanned/rotated balancing algorithm. It converges on a stable state where
all cold anon pages are pushed out and the fileset is served entirely from
cache:
The second test kernel is with the full patch series applied, which
replaces the scanned/rotated ratios with refault/swapin rate-based
balancing. It evicts the cold anon pages more aggressively in the
presence of a thrashing cache and the absence of swapins, and so converges
with about 60% of the IO and reclaim activity:
We're triggering this case in host sideloading scenarios: When a host's
primary workload is not saturating the machine (primary load is usually
driven by user activity), we can optimistically sideload a batch job; if
user activity picks up and the primary workload needs the whole host
during this time, we freeze the sideload and rely on it getting pushed to
swap. Frequently that swapping doesn't happen and the completely inactive
sideload simply stays resident while the expanding primary worklad is
struggling to gain ground.
Test #2: Kernel build
This test is a a kernel build that is slightly memory-restricted (make -j4
inside a 400M cgroup).
Despite the very aggressive swapping of cold anon pages in test #1, this
test shows that the new kernel carefully balances swap against cache
refaults when both the file and the cache set are pressured.
It shows the patched kernel to be slightly better at finding the coldest
memory from the combined anon and file set to evict under pressure. The
result is lower aggregate reclaim and paging activity:
This next test is not about performance, but rather about the
predictability of the algorithm. The current balancing behavior doesn't
always lead to comprehensible results, which makes performance analysis
and parameter tuning (swappiness e.g.) very difficult.
The test shows the balancing behavior under equivalent anon and file
input. Anon and file sets are created of equal size (3/4 RAM), have the
same access patterns (a hot-cold gradient), and synchronized access rates.
Swappiness is raised from the default of 60 to 100 to indicate equal IO
cost between swap and cache.
With the vanilla balancing code, anon scans make up around 9% of the total
pages scanned, or a ~1:10 ratio. This is a surprisingly skewed ratio, and
it's an outcome that is hard to explain given the input parameters to the
VM.
The new balancing model targets a 1:2 balance: All else being equal,
reclaiming a file page costs one page IO - the refault; reclaiming an anon
page costs two IOs - the swapout and the swapin. In the test we observe a
~1:3 balance.
The scanned and paging IO numbers indicate that the anon LRU algorithm we
have in place right now does a slightly worse job at picking the coldest
pages compared to the file algorithm. There is ongoing work to improve
this, like Joonsoo's anon workingset patches; however, it's difficult to
compare the two aging strategies when the balancing between them is
behaving unintuitively.
The slightly less efficient anon reclaim results in a deviation from the
optimal 1:2 scan ratio we would like to see here - however, 1:3 is much
closer to what we'd want to see in this test than the vanilla kernel's
aging of 10+ cache pages for every anonymous one:
It's important to note that these patches only affect the situation where
the kernel has to reclaim workingset memory, which is usually a
transitionary period. The vast majority of page reclaim occuring in a
system is from trimming the ever-expanding page cache.
These patches don't affect cache trimming behavior. We never swap as long
as we only have use-once cache moving through the file LRU, we only
consider swapping when the cache is actively thrashing.
The following test demonstrates this. It has an anon workingset that
takes up half of RAM and then writes a file that is twice the size of RAM
out to disk.
As the cache is funneled through the inactive file list, no anon pages are
scanned (aside from apparently some background noise of 10 pages):
Currently, THP are counted as single pages until they are split right
before being swapped out. However, at that point the VM is already in the
middle of reclaim, and adjusting the LRU balance then is useless.
Always account THP by the number of basepages, and remove the fixup from
the splitting path.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@surriel.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Link: http://lkml.kernel.org/r/20200520232525.798933-1-hannes@cmpxchg.org Link: http://lkml.kernel.org/r/20200520232525.798933-2-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The previous patches have simplified the access rules around
page->mem_cgroup somewhat:
1. We never change page->mem_cgroup while the page is isolated by
somebody else. This was by far the biggest exception to our rules and
it didn't stop at lock_page() or lock_page_memcg().
2. We charge pages before they get put into page tables now, so the
somewhat fishy rule about "can be in page table as long as it's still
locked" is now gone and boiled down to having an exclusive reference to
the page.
Document the new rules. Any of the following will stabilize the
page->mem_cgroup association:
- the page lock
- LRU isolation
- lock_page_memcg()
- exclusive access to the page
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-20-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:24 +0000 (16:02 -0700)]
mm: memcontrol: delete unused lrucare handling
Swapin faults were the last event to charge pages after they had already
been put on the LRU list. Now that we charge directly on swapin, the
lrucare portion of the charge code is unused.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Shakeel Butt <shakeelb@google.com> Link: http://lkml.kernel.org/r/20200508183105.225460-19-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:17 +0000 (16:02 -0700)]
mm: memcontrol: charge swapin pages on instantiation
Right now, users that are otherwise memory controlled can easily escape
their containment and allocate significant amounts of memory that they're
not being charged for. That's because swap readahead pages are not being
charged until somebody actually faults them into their page table. This
can be exploited with MADV_WILLNEED, which triggers arbitrary readahead
allocations without charging the pages.
There are additional problems with the delayed charging of swap pages:
1. To implement refault/workingset detection for anonymous pages, we
need to have a target LRU available at swapin time, but the LRU is not
determinable until the page has been charged.
2. To implement per-cgroup LRU locking, we need page->mem_cgroup to be
stable when the page is isolated from the LRU; otherwise, the locks
change under us. But swapcache gets charged after it's already on the
LRU, and even if we cannot isolate it ourselves (since charging is not
exactly optional).
The previous patch ensured we always maintain cgroup ownership records for
swap pages. This patch moves the swapcache charging point from the fault
handler to swapin time to fix all of the above problems.
v2: simplify swapin error checking (Joonsoo)
[hughd@google.com: fix livelock in __read_swap_cache_async()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2005212246080.8458@eggly.anvils Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Rafael Aquini <aquini@redhat.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Link: http://lkml.kernel.org/r/20200508183105.225460-17-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:14 +0000 (16:02 -0700)]
mm: memcontrol: make swap tracking an integral part of memory control
Without swap page tracking, users that are otherwise memory controlled can
easily escape their containment and allocate significant amounts of memory
that they're not being charged for. That's because swap does readahead,
but without the cgroup records of who owned the page at swapout, readahead
pages don't get charged until somebody actually faults them into their
page table and we can identify an owner task. This can be maliciously
exploited with MADV_WILLNEED, which triggers arbitrary readahead
allocations without charging the pages.
Make swap swap page tracking an integral part of memcg and remove the
Kconfig options. In the first place, it was only made configurable to
allow users to save some memory. But the overhead of tracking cgroup
ownership per swap page is minimal - 2 byte per page, or 512k per 1G of
swap, or 0.04%. Saving that at the expense of broken containment
semantics is not something we should present as a coequal option.
The swapaccount=0 boot option will continue to exist, and it will
eliminate the page_counter overhead and hide the swap control files, but
it won't disable swap slot ownership tracking.
This patch makes sure we always have the cgroup records at swapin time;
the next patch will fix the actual bug by charging readahead swap pages at
swapin time rather than at fault time.
v2: fix double swap charge bug in cgroup1/cgroup2 code gating
[hannes@cmpxchg.org: fix crash with cgroup_disable=memory] Link: http://lkml.kernel.org/r/20200521215855.GB815153@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Naresh Kamboju <naresh.kamboju@linaro.org> Link: http://lkml.kernel.org/r/20200508183105.225460-16-hannes@cmpxchg.org Debugged-by: Hugh Dickins <hughd@google.com> Debugged-by: Michal Hocko <mhocko@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:11 +0000 (16:02 -0700)]
mm: memcontrol: prepare swap controller setup for integration
A few cleanups to streamline the swap controller setup:
- Replace the do_swap_account flag with cgroup_memory_noswap. This
brings it in line with other functionality that is usually available
unless explicitly opted out of - nosocket, nokmem.
- Remove the really_do_swap_account flag that stores the boot option
and is later used to switch the do_swap_account. It's not clear why
this indirection is/was necessary. Use do_swap_account directly.
- Minor coding style polishing
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-15-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:04 +0000 (16:02 -0700)]
mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API
With the page->mapping requirement gone from memcg, we can charge anon and
file-thp pages in one single step, right after they're allocated.
This removes two out of three API calls - especially the tricky commit
step that needed to happen at just the right time between when the page is
"set up" and when it's "published" - somewhat vague and fluid concepts
that varied by page type. All we need is a freshly allocated page and a
memcg context to charge.
v2: prevent double charges on pre-allocated hugepages in khugepaged
[hannes@cmpxchg.org: Fix crash - *hpage could be ERR_PTR instead of NULL] Link: http://lkml.kernel.org/r/20200512215813.GA487759@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Qian Cai <cai@lca.pw> Link: http://lkml.kernel.org/r/20200508183105.225460-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:02:01 +0000 (16:02 -0700)]
mm: memcontrol: switch to native NR_ANON_THPS counter
With rmap memcg locking already in place for NR_ANON_MAPPED, it's just a
small step to remove the MEMCG_RSS_HUGE wart and switch memcg to the
native NR_ANON_THPS accounting sites.
[hannes@cmpxchg.org: fixes] Link: http://lkml.kernel.org/r/20200512121750.GA397968@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Randy Dunlap <rdunlap@infradead.org> [build-tested] Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:57 +0000 (16:01 -0700)]
mm: memcontrol: switch to native NR_ANON_MAPPED counter
Memcg maintains a private MEMCG_RSS counter. This divergence from the
generic VM accounting means unnecessary code overhead, and creates a
dependency for memcg that page->mapping is set up at the time of charging,
so that page types can be told apart.
Convert the generic accounting sites to mod_lruvec_page_state and friends
to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED. We use
lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the
same way we do for NR_FILE_MAPPED.
With the previous patch removing MEMCG_CACHE and the private NR_SHMEM
counter, this patch finally eliminates the need to have page->mapping set
up at charge time. However, we need to have page->mem_cgroup set up by
the time rmap runs and does the accounting, so switch the commit and the
rmap callbacks around.
v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo)
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:54 +0000 (16:01 -0700)]
mm: memcontrol: switch to native NR_FILE_PAGES and NR_SHMEM counters
Memcg maintains private MEMCG_CACHE and NR_SHMEM counters. This
divergence from the generic VM accounting means unnecessary code overhead,
and creates a dependency for memcg that page->mapping is set up at the
time of charging, so that page types can be told apart.
Convert the generic accounting sites to mod_lruvec_page_state and friends
to maintain the per-cgroup vmstat counters of NR_FILE_PAGES and NR_SHMEM.
The page is already locked in these places, so page->mem_cgroup is stable;
we only need minimal tweaks of two mem_cgroup_migrate() calls to ensure
it's set up in time.
Then replace MEMCG_CACHE with NR_FILE_PAGES and delete the private
NR_SHMEM accounting sites.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:51 +0000 (16:01 -0700)]
mm: memcontrol: prepare cgroup vmstat infrastructure for native anon counters
Anonymous compound pages can be mapped by ptes, which means that if we
want to track NR_MAPPED_ANON, NR_ANON_THPS on a per-cgroup basis, we have
to be prepared to see tail pages in our accounting functions.
Make mod_lruvec_page_state() and lock_page_memcg() deal with tail pages
correctly, namely by redirecting to the head page which has the
page->mem_cgroup set up.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:47 +0000 (16:01 -0700)]
mm: memcontrol: prepare move_account for removal of private page type counters
When memcg uses the generic vmstat counters, it doesn't need to do
anything at charging and uncharging time. It does, however, need to
migrate counts when pages move to a different cgroup in move_account.
Prepare the move_account function for the arrival of NR_FILE_PAGES,
NR_ANON_MAPPED, NR_ANON_THPS etc. by having a branch for files and a
branch for anon, which can then divided into sub-branches.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-8-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:44 +0000 (16:01 -0700)]
mm: memcontrol: prepare uncharging for removal of private page type counters
The uncharge batching code adds up the anon, file, kmem counts to
determine the total number of pages to uncharge and references to drop.
But the next patches will remove the anon and file counters.
Maintain an aggregate nr_pages in the uncharge_gather struct.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-7-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:41 +0000 (16:01 -0700)]
mm: memcontrol: convert page cache to a new mem_cgroup_charge() API
The try/commit/cancel protocol that memcg uses dates back to when pages
used to be uncharged upon removal from the page cache, and thus couldn't
be committed before the insertion had succeeded. Nowadays, pages are
uncharged when they are physically freed; it doesn't matter whether the
insertion was successful or not. For the page cache, the transaction
dance has become unnecessary.
Introduce a mem_cgroup_charge() function that simply charges a newly
allocated page to a cgroup and sets up page->mem_cgroup in one single
step. If the insertion fails, the caller doesn't have to do anything but
free/put the page.
Then switch the page cache over to this new API.
Subsequent patches will also convert anon pages, but it needs a bit more
prep work. Right now, memcg depends on page->mapping being already set up
at the time of charging, so that it can maintain its own MEMCG_CACHE and
MEMCG_RSS counters. For anon, page->mapping is set under the same pte
lock under which the page is publishd, so a single charge point that can
block doesn't work there just yet.
The following prep patches will replace the private memcg counters with
the generic vmstat counters, thus removing the page->mapping dependency,
then complete the transition to the new single-point charge API and delete
the old transactional scheme.
v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo)
v3: rebase on preceeding shmem simplification patch
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:38 +0000 (16:01 -0700)]
mm: memcontrol: move out cgroup swaprate throttling
The cgroup swaprate throttling is about matching new anon allocations to
the rate of available IO when that is being throttled. It's the io
controller hooking into the VM, rather than a memory controller thing.
Rename mem_cgroup_throttle_swaprate() to cgroup_throttle_swaprate(), and
drop the @memcg argument which is only used to check whether the preceding
page charge has succeeded and the fault is proceeding.
We could decouple the call from mem_cgroup_try_charge() here as well, but
that would cause unnecessary churn: the following patches convert all
callsites to a new charge API and we'll decouple as we go along.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:34 +0000 (16:01 -0700)]
mm: shmem: remove rare optimization when swapin races with hole punching
Commit 3b86b3d14d59 ("tmpfs: fix shmem_getpage_gfp() VM_BUG_ON")
recognized that hole punching can race with swapin and removed the
BUG_ON() for a truncated entry from the swapin path.
The patch also added a swapcache deletion to optimize this rare case:
Since swapin has the page locked, and free_swap_and_cache() merely
trylocks, this situation can leave the page stranded in swapcache.
Usually, page reclaim picks up stale swapcache pages, and the race can
happen at any other time when the page is locked. (The same happens for
non-shmem swapin racing with page table zapping.) The thinking here was:
we already observed the race and we have the page locked, we may as well
do the cleanup instead of waiting for reclaim.
However, this optimization complicates the next patch which moves the
cgroup charging code around. As this is just a minor speedup for a race
condition that is so rare that it required a fuzzer to trigger the
original BUG_ON(), it's no longer worth the complications.
Suggested-by: Hugh Dickins <hughd@google.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Hugh Dickins <hughd@google.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200511181056.GA339505@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:31 +0000 (16:01 -0700)]
mm: memcontrol: drop @compound parameter from memcg charging API
The memcg charging API carries a boolean @compound parameter that tells
whether the page we're dealing with is a hugepage.
mem_cgroup_commit_charge() has another boolean @lrucare that indicates
whether the page needs LRU locking or not while charging. The majority of
callsites know those parameters at compile time, which results in a lot of
naked "false, false" argument lists. This makes for cryptic code and is a
breeding ground for subtle mistakes.
Thankfully, the huge page state can be inferred from the page itself and
doesn't need to be passed along. This is safe because charging completes
before the page is published and somebody may split it.
Simplify the callsites by removing @compound, and let memcg infer the
state by using hpage_nr_pages() unconditionally. That function does
PageTransHuge() to identify huge pages, which also helpfully asserts that
nobody passes in tail pages by accident.
The following patches will introduce a new charging API, best not to carry
over unnecessary weight.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:28 +0000 (16:01 -0700)]
mm: memcontrol: fix stat-corrupting race in charge moving
The move_lock is a per-memcg lock, but the VM accounting code that needs
to acquire it comes from the page and follows page->mem_cgroup under RCU
protection. That means that the page becomes unlocked not when we drop
the move_lock, but when we update page->mem_cgroup. And that assignment
doesn't imply any memory ordering. If that pointer write gets reordered
against the reads of the page state - page_mapped, PageDirty etc. the
state may change while we rely on it being stable and we can end up
corrupting the counters.
Place an SMP memory barrier to make sure we're done with all page state by
the time the new page->mem_cgroup becomes visible.
Also replace the open-coded move_lock with a lock_page_memcg() to make it
more obvious what we're serializing against.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Hugh Dickins <hughd@google.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <guro@fb.com> Cc: Balbir Singh <bsingharora@gmail.com> Link: http://lkml.kernel.org/r/20200508183105.225460-3-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Wed, 3 Jun 2020 23:01:24 +0000 (16:01 -0700)]
mm: fix NUMA node file count error in replace_page_cache()
Patch series "mm: memcontrol: charge swapin pages on instantiation", v2.
This patch series reworks memcg to charge swapin pages directly at
swapin time, rather than at fault time, which may be much later, or
not happen at all.
Changes in version 2:
- prevent double charges on pre-allocated hugepages in khugepaged
- leave shmem swapcache when charging fails to avoid double IO (Joonsoo)
- fix temporary accounting bug by switching rmap<->commit (Joonsoo)
- fix double swap charge bug in cgroup1/cgroup2 code gating
- simplify swapin error checking (Joonsoo)
- mm: memcontrol: document the new swap control behavior (Alex)
- review tags
The delayed swapin charging scheme we have right now causes problems:
- Alex's per-cgroup lru_lock patches rely on pages that have been
isolated from the LRU to have a stable page->mem_cgroup; otherwise
the lock may change underneath him. Swapcache pages are charged only
after they are added to the LRU, and charging doesn't follow the LRU
isolation protocol.
- Joonsoo's anon workingset patches need a suitable LRU at the time
the page enters the swap cache and displaces the non-resident
info. But the correct LRU is only available after charging.
- It's a containment hole / DoS vector. Users can trigger arbitrarily
large swap readahead using MADV_WILLNEED. The memory is never
charged unless somebody actually touches it.
- It complicates the page->mem_cgroup stabilization rules
In order to charge pages directly at swapin time, the memcg code base
needs to be prepared, and several overdue cleanups become a necessity:
To charge pages at swapin time, we need to always have cgroup
ownership tracking of swap records. We also cannot rely on
page->mapping to tell apart page types at charge time, because that's
only set up during a page fault.
To eliminate the page->mapping dependency, memcg needs to ditch its
private page type counters (MEMCG_CACHE, MEMCG_RSS, NR_SHMEM) in favor
of the generic vmstat counters and accounting sites, such as
NR_FILE_PAGES, NR_ANON_MAPPED etc.
To switch to generic vmstat counters, the charge sequence must be
adjusted such that page->mem_cgroup is set up by the time these
counters are modified.
The series is structured as follows:
1. Bug fixes
2. Decoupling charging from rmap
3. Swap controller integration into memcg
4. Direct swapin charging
This patch (of 19):
When replacing one page with another one in the cache, we have to decrease
the file count of the old page's NUMA node and increase the one of the new
NUMA node, otherwise the old node leaks the count and the new node
eventually underflows its counter.
Fixes: 7f62535e367f ("page cache: Add and replace pages using the XArray") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reviewed-by: Balbir Singh <bsingharora@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Roman Gushchin <guro@fb.com> Link: http://lkml.kernel.org/r/20200508183105.225460-1-hannes@cmpxchg.org Link: http://lkml.kernel.org/r/20200508183105.225460-2-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Maninder Singh [Wed, 3 Jun 2020 23:01:18 +0000 (16:01 -0700)]
mm/vmscan.c: change prototype for shrink_page_list
commit 9ac7ebba32ee ("mm, vmscan extract shrink_page_list reclaim counters
into a struct") changed data type for the function, so changing return
type for funciton and its caller.
Jaewon Kim [Wed, 3 Jun 2020 23:01:15 +0000 (16:01 -0700)]
mm/vmscan: count layzfree pages and fix nr_isolated_* mismatch
Fix an nr_isolate_* mismatch problem between cma and dirty lazyfree pages.
If try_to_unmap_one is used for reclaim and it detects a dirty lazyfree
page, then the lazyfree page is changed to a normal anon page having
SwapBacked by commit 7b7c384222d6 ("mm: reclaim MADV_FREE pages"). Even
with the change, reclaim context correctly counts isolated files because
it uses is_file_lru to distinguish file. And the change to anon is not
happened if try_to_unmap_one is used for migration. So migration context
like compaction also correctly counts isolated files even though it uses
page_is_file_lru insted of is_file_lru. Recently page_is_file_cache was
renamed to page_is_file_lru by commit 3dff26cb70c6 ("mm: code cleanup for
MADV_FREE").
But the nr_isolate_* mismatch problem happens on cma alloc. There is
reclaim_clean_pages_from_list which is being used only by cma. It was
introduced by commit bf30603eb38b ("mm: cma: discard clean pages during
contiguous allocation instead of migration") to reclaim clean file pages
without migration. The cma alloc uses both reclaim_clean_pages_from_list
and migrate_pages, and it uses page_is_file_lru to count isolated files.
If there are dirty lazyfree pages allocated from cma memory region, the
pages are counted as isolated file at the beginging but are counted as
isolated anon after finished.
Like log above, there were too much isolated files, 37664kB, which
triggers too_many_isolated in reclaim even when there is no actually
isolated file in system wide. It could be reproducible by running two
programs, writing on MADV_FREE page and doing cma alloc, respectively.
Although isolated anon is 0, I found that the internal value of isolated
anon was the negative value of isolated file.
Fix this by compensating the isolated count for both LRU lists. Count
non-discarded lazyfree pages in shrink_page_list, then compensate the
counted number in reclaim_clean_pages_from_list.
Reported-by: Yong-Taek Lee <ytk.lee@samsung.com> Suggested-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Shaohua Li <shli@fb.com> Link: http://lkml.kernel.org/r/20200426011718.30246-1-jaewon31.kim@samsung.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / kernel.git / log