From: Leonardo Bras <leonardo@linux.ibm.com>
To: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Cc: Leonardo Bras <leonardo@linux.ibm.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Paul Mackerras <paulus@samba.org>,
Michael Ellerman <mpe@ellerman.id.au>,
Arnd Bergmann <arnd@arndb.de>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
Christophe Leroy <christophe.leroy@c-s.fr>,
Andrew Morton <akpm@linux-foundation.org>,
Dan Williams <dan.j.williams@intel.com>,
Nicholas Piggin <npiggin@gmail.com>,
Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>,
Thomas Gleixner <tglx@linutronix.de>,
Richard Fontana <rfontana@redhat.com>,
Ganesh Goudar <ganeshgr@linux.ibm.com>,
Allison Randal <allison@lohutok.net>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Mike Rapoport <rppt@linux.ibm.com>,
YueHaibing <yuehaibing@huawei.com>,
Ira Weiny <ira.weiny@intel.com>, Jason Gunthorpe <jgg@ziepe.ca>,
John Hubbard <jhubbard@nvidia.com>,
Keith Busch <keith.busch@intel.com>
Subject: [PATCH v2 09/11] powerpc/kvm/book3s_64: Applies counting method to monitor lockless pgtbl walks
Date: Fri, 20 Sep 2019 16:50:45 -0300 [thread overview]
Message-ID: <20190920195047.7703-10-leonardo@linux.ibm.com> (raw)
In-Reply-To: <20190920195047.7703-1-leonardo@linux.ibm.com>
Applies the counting-based method for monitoring all book3s_64-related
functions that do lockless pagetable walks.
Signed-off-by: Leonardo Bras <leonardo@linux.ibm.com>
---
It may be necessary to merge an older patch first:
powerpc: kvm: Reduce calls to get current->mm by storing the value locally
Link: https://lore.kernel.org/linuxppc-dev/20190919222748.20761-1-leonardo@linux.ibm.com/
arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 ++
arch/powerpc/kvm/book3s_64_mmu_radix.c | 20 ++++++++++++++++++--
arch/powerpc/kvm/book3s_64_vio_hv.c | 4 ++++
3 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f2b9aea43216..a938733c3f7b 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -622,6 +622,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
* We need to protect against page table destruction
* hugepage split and collapse.
*/
+ start_lockless_pgtbl_walk(mm);
local_irq_save(flags);
ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL);
if (ptep) {
@@ -630,6 +631,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
write_ok = 1;
}
local_irq_restore(flags);
+ end_lockless_pgtbl_walk(mm);
}
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 2d415c36a61d..d46f8258d8d6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -741,6 +741,7 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, bool writing,
unsigned long pgflags;
unsigned int shift;
pte_t *ptep;
+ bool ret = false;
/*
* Need to set an R or C bit in the 2nd-level tables;
@@ -755,12 +756,14 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, bool writing,
* We can do this without disabling irq because the Linux MM
* subsystem doesn't do THP splits and collapses on this tree.
*/
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
- return true;
+ ret = true;
}
- return false;
+ end_lockless_pgtbl_walk(kvm->mm);
+ return ret;
}
int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
@@ -813,6 +816,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
* Read the PTE from the process' radix tree and use that
* so we get the shift and attribute bits.
*/
+ start_lockless_pgtbl_walk(kvm->mm);
local_irq_disable();
ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
/*
@@ -821,12 +825,14 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
*/
if (!ptep) {
local_irq_enable();
+ end_lockless_pgtbl_walk(kvm->mm);
if (page)
put_page(page);
return RESUME_GUEST;
}
pte = *ptep;
local_irq_enable();
+ end_lockless_pgtbl_walk(kvm->mm);
/* If we're logging dirty pages, always map single pages */
large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES);
@@ -972,10 +978,12 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gpa = gfn << PAGE_SHIFT;
unsigned int shift;
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep))
kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
kvm->arch.lpid);
+ end_lockless_pgtbl_walk(kvm->mm);
return 0;
}
@@ -989,6 +997,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
int ref = 0;
unsigned long old, *rmapp;
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
@@ -1001,6 +1010,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
1UL << shift);
ref = 1;
}
+ end_lockless_pgtbl_walk(kvm->mm);
return ref;
}
@@ -1013,9 +1023,11 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned int shift;
int ref = 0;
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep))
ref = 1;
+ end_lockless_pgtbl_walk(kvm->mm);
return ref;
}
@@ -1030,6 +1042,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
int ret = 0;
unsigned long old, *rmapp;
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
ret = 1;
@@ -1046,6 +1059,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
1UL << shift);
spin_unlock(&kvm->mmu_lock);
}
+ end_lockless_pgtbl_walk(kvm->mm);
return ret;
}
@@ -1084,6 +1098,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
gpa = memslot->base_gfn << PAGE_SHIFT;
spin_lock(&kvm->mmu_lock);
+ start_lockless_pgtbl_walk(kvm->mm);
for (n = memslot->npages; n; --n) {
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep))
@@ -1091,6 +1106,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
kvm->arch.lpid);
gpa += PAGE_SIZE;
}
+ end_lockless_pgtbl_walk(kvm->mm);
spin_unlock(&kvm->mmu_lock);
}
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index b4f20f13b860..d7ea44f28993 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -431,6 +431,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
unsigned long ua, unsigned long *phpa)
{
+ struct kvm *kvm = vcpu->kvm;
pte_t *ptep, pte;
unsigned shift = 0;
@@ -443,10 +444,13 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
* to exit which will agains result in the below page table walk
* to finish.
*/
+
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
if (!ptep || !pte_present(*ptep))
return -ENXIO;
pte = *ptep;
+ end_lockless_pgtbl_walk(kvm->mm);
if (!shift)
shift = PAGE_SHIFT;
--
2.20.1
next prev parent reply other threads:[~2019-09-20 19:53 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-20 19:50 [PATCH v2 00/11] Introduces new count-based method for monitoring lockless pagetable wakls Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 01/11] powerpc/mm: Adds counting method to monitor lockless pgtable walks Leonardo Bras
[not found] ` <90ceb0ca-9f04-65a5-586c-e37c2ecc6e4e@nvidia.com>
2019-09-23 20:50 ` Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 02/11] asm-generic/pgtable: Adds dummy functions " Leonardo Bras
[not found] ` <cb7d4196-c646-82c7-d61f-b28ee9ab47b9@nvidia.com>
2019-09-23 20:48 ` Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 03/11] mm/gup: Applies counting method to monitor gup_pgd_range Leonardo Bras
[not found] ` <2e060677-eadf-c32e-d8c5-8e22c8ca118e@nvidia.com>
2019-09-23 21:01 ` Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 04/11] powerpc/mce_power: Applies counting method to monitor lockless pgtbl walks Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 05/11] powerpc/perf: " Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 06/11] powerpc/mm/book3s64/hash: " Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 07/11] powerpc/kvm/e500: " Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 08/11] powerpc/kvm/book3s_hv: " Leonardo Bras
2019-09-20 19:50 ` Leonardo Bras [this message]
2019-09-20 19:50 ` [PATCH v2 10/11] powerpc/book3s_64: Enables counting method to monitor lockless pgtbl walk Leonardo Bras
2019-09-20 19:50 ` [PATCH v2 11/11] powerpc/mm/book3s64/pgtable: Uses counting method to skip serializing Leonardo Bras
[not found] ` <1b39eaa7-751d-40bc-d3d7-41aaa15be42a@nvidia.com>
2019-09-20 20:28 ` Leonardo Bras
[not found] ` <4ea26ffb-ad03-bdff-7893-95332b22a5fd@nvidia.com>
2019-09-23 17:25 ` Leonardo Bras
[not found] ` <8706a1f1-0c5e-d152-938b-f355b9a5aaa8@nvidia.com>
2019-09-23 19:40 ` Leonardo Bras
[not found] ` <1568b3ef-cec9-bf47-edaa-c775c2f544fb@nvidia.com>
2019-09-23 20:23 ` Leonardo Bras
2019-09-23 20:26 ` John Hubbard
2019-09-20 19:56 ` [PATCH v2 00/11] Introduces new count-based method for monitoring lockless pagetable wakls Leonardo Bras
2019-09-20 20:12 ` Leonardo Bras
[not found] ` <b2d47f4b-2bf2-20a8-2438-4fd3f9b08a63@nvidia.com>
2019-09-23 20:58 ` Leonardo Bras
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190920195047.7703-10-leonardo@linux.ibm.com \
--to=leonardo@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=allison@lohutok.net \
--cc=aneesh.kumar@linux.ibm.com \
--cc=arnd@arndb.de \
--cc=benh@kernel.crashing.org \
--cc=christophe.leroy@c-s.fr \
--cc=dan.j.williams@intel.com \
--cc=ganeshgr@linux.ibm.com \
--cc=gregkh@linuxfoundation.org \
--cc=ira.weiny@intel.com \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=keith.busch@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mahesh@linux.vnet.ibm.com \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=paulus@samba.org \
--cc=rfontana@redhat.com \
--cc=rppt@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=yuehaibing@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).