From: Nicholas Piggin <npiggin@gmail.com>
To: kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org, Nicholas Piggin <npiggin@gmail.com>
Subject: [PATCH v1 43/55] KVM: PPC: Book3S HV P9: Comment and fix MMU context switching code
Date: Mon, 26 Jul 2021 13:50:24 +1000 [thread overview]
Message-ID: <20210726035036.739609-44-npiggin@gmail.com> (raw)
In-Reply-To: <20210726035036.739609-1-npiggin@gmail.com>
Tighten up partition switching code synchronisation and comments.
In particular, hwsync ; isync is required after the last access that is
performed in the context of a partition, before the partition is
switched away from.
-301 cycles (6319) POWER9 virt-mode NULL hcall
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_64_mmu_radix.c | 4 +++
arch/powerpc/kvm/book3s_hv_p9_entry.c | 40 +++++++++++++++++++-------
2 files changed, 33 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index b5905ae4377c..c5508744e14c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -54,6 +54,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
preempt_disable();
+ asm volatile("hwsync" ::: "memory");
+ isync();
/* switch the lpid first to avoid running host with unallocated pid */
old_lpid = mfspr(SPRN_LPID);
if (old_lpid != lpid)
@@ -70,6 +72,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
else
ret = copy_to_user_nofault((void __user *)to, from, n);
+ asm volatile("hwsync" ::: "memory");
+ isync();
/* switch the pid first to avoid running host with unallocated pid */
if (quadrant == 1 && pid != old_pid)
mtspr(SPRN_PID, old_pid);
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 5fca0a09425d..0aad2bf29d6e 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -521,17 +521,19 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
/*
- * All the isync()s are overkill but trivially follow the ISA
- * requirements. Some can likely be replaced with justification
- * comment for why they are not needed.
+ * Prior memory accesses to host PID Q3 must be completed before we
+ * start switching, and stores must be drained to avoid not-my-LPAR
+ * logic (see switch_mmu_to_host).
*/
+ asm volatile("hwsync" ::: "memory");
isync();
mtspr(SPRN_LPID, lpid);
- isync();
mtspr(SPRN_LPCR, lpcr);
- isync();
mtspr(SPRN_PID, vcpu->arch.pid);
- isync();
+ /*
+ * isync not required here because we are HRFID'ing to guest before
+ * any guest context access, which is context synchronising.
+ */
}
static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
@@ -541,25 +543,41 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
lpid = kvm->arch.lpid;
+ /*
+ * See switch_mmu_to_guest_radix. ptesync should not be required here
+ * even if the host is in HPT mode because speculative accesses would
+ * not cause RC updates (we are in real mode).
+ */
+ asm volatile("hwsync" ::: "memory");
+ isync();
mtspr(SPRN_LPID, lpid);
mtspr(SPRN_LPCR, lpcr);
mtspr(SPRN_PID, vcpu->arch.pid);
for (i = 0; i < vcpu->arch.slb_max; i++)
mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv);
-
- isync();
+ /*
+ * isync not required here, see switch_mmu_to_guest_radix.
+ */
}
static void switch_mmu_to_host(struct kvm *kvm, u32 pid)
{
+ /*
+ * The guest has exited, so guest MMU context is no longer being
+ * non-speculatively accessed, but a hwsync is needed before the
+ * mtLPIDR / mtPIDR switch, in order to ensure all stores are drained,
+ * so the not-my-LPAR tlbie logic does not overlook them.
+ */
+ asm volatile("hwsync" ::: "memory");
isync();
mtspr(SPRN_PID, pid);
- isync();
mtspr(SPRN_LPID, kvm->arch.host_lpid);
- isync();
mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
- isync();
+ /*
+ * isync is not required after the switch, because mtmsrd with L=0
+ * is performed after this switch, which is context synchronising.
+ */
if (!radix_enabled())
slb_restore_bolted_realmode();
--
2.23.0
next prev parent reply other threads:[~2021-07-26 4:09 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-26 3:49 [PATCH v1 00/55] KVM: PPC: Book3S HV P9: entry/exit optimisations Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 01/55] KVM: PPC: Book3S HV: Remove TM emulation from POWER7/8 path Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 02/55] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt Nicholas Piggin
2021-08-06 1:16 ` Michael Ellerman
2021-08-06 10:25 ` Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 03/55] KVM: PPC: Book3S HV: Sanitise vcpu registers in nested path Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 04/55] KVM: PPC: Book3S HV: Stop forwarding all HFUs to L1 Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 05/55] KVM: PPC: Book3S HV Nested: Reflect guest PMU in-use to L0 when guest SPRs are live Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 06/55] powerpc/64s: Remove WORT SPR from POWER9/10 Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 07/55] KMV: PPC: Book3S HV P9: Use set_dec to set decrementer to host Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 08/55] KVM: PPC: Book3S HV P9: Use host timer accounting to avoid decrementer read Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 09/55] KVM: PPC: Book3S HV P9: Use large decrementer for HDEC Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 10/55] KVM: PPC: Book3S HV P9: Reduce mftb per guest entry/exit Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 11/55] powerpc/time: add API for KVM to re-arm the host timer/decrementer Nicholas Piggin
2021-08-05 7:22 ` Christophe Leroy
2021-08-06 10:30 ` Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 12/55] KVM: PPC: Book3S HV: POWER10 enable HAIL when running radix guests Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 13/55] powerpc/64s: Keep AMOR SPR a constant ~0 at runtime Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 14/55] KVM: PPC: Book3S HV: Don't always save PMU for guest capable of nesting Nicholas Piggin
2021-08-06 7:34 ` Michael Ellerman
2021-08-06 10:32 ` Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 15/55] powerpc/64s: Always set PMU control registers to frozen/disabled when not in use Nicholas Piggin
2021-07-26 3:49 ` [PATCH v1 16/55] powerpc/64s: Implement PMU override command line option Nicholas Piggin
2021-08-06 7:33 ` Madhavan Srinivasan
2021-08-06 10:38 ` Nicholas Piggin
2021-08-11 12:46 ` Madhavan Srinivasan
2021-08-06 9:28 ` Athira Rajeev
2021-08-06 10:42 ` Nicholas Piggin
2021-08-11 10:54 ` Athira Rajeev
2021-07-26 3:49 ` [PATCH v1 17/55] KVM: PPC: Book3S HV P9: Implement PMU save/restore in C Nicholas Piggin
2021-08-09 3:03 ` Athira Rajeev
2021-08-13 4:24 ` Nicholas Piggin
2021-08-14 7:12 ` Athira Rajeev
2021-07-26 3:49 ` [PATCH v1 18/55] KVM: PPC: Book3S HV P9: Factor PMU save/load into context switch functions Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 19/55] KVM: PPC: Book3S HV P9: Demand fault PMU SPRs when marked not inuse Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 20/55] KVM: PPC: Book3S HV P9: Factor out yield_count increment Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 21/55] KVM: PPC: Book3S HV: CTRL SPR does not require read-modify-write Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 22/55] KVM: PPC: Book3S HV P9: Move SPRG restore to restore_p9_host_os_sprs Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 23/55] KVM: PPC: Book3S HV P9: Reduce mtmsrd instructions required to save host SPRs Nicholas Piggin
2021-07-26 6:57 ` kernel test robot
2021-07-26 7:01 ` kernel test robot
2021-07-26 3:50 ` [PATCH v1 24/55] KVM: PPC: Book3S HV P9: Improve mtmsrd scheduling by delaying MSR[EE] disable Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 25/55] KVM: PPC: Book3S HV P9: Add kvmppc_stop_thread to match kvmppc_start_thread Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 26/55] KVM: PPC: Book3S HV: Change dec_expires to be relative to guest timebase Nicholas Piggin
2021-08-07 23:17 ` Michael Ellerman
2021-07-26 3:50 ` [PATCH v1 27/55] KVM: PPC: Book3S HV P9: Move TB updates Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 28/55] KVM: PPC: Book3S HV P9: Optimise timebase reads Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 29/55] KVM: PPC: Book3S HV P9: Avoid SPR scoreboard stalls Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 30/55] KVM: PPC: Book3S HV P9: Only execute mtSPR if the value changed Nicholas Piggin
2021-08-06 20:45 ` Fabiano Rosas
2021-07-26 3:50 ` [PATCH v1 31/55] KVM: PPC: Book3S HV P9: Juggle SPR switching around Nicholas Piggin
2021-08-06 20:46 ` Fabiano Rosas
2021-07-26 3:50 ` [PATCH v1 32/55] KVM: PPC: Book3S HV P9: Move vcpu register save/restore into functions Nicholas Piggin
2021-08-06 20:49 ` Fabiano Rosas
2021-07-26 3:50 ` [PATCH v1 33/55] KVM: PPC: Book3S HV P9: Move host OS save/restore functions to built-in Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 34/55] KVM: PPC: Book3S HV P9: Move nested guest entry into its own function Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 35/55] KVM: PPC: Book3S HV P9: Move remaining SPR and MSR access into low level entry Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 36/55] KVM: PPC: Book3S HV P9: Implement TM fastpath for guest entry/exit Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 37/55] KVM: PPC: Book3S HV P9: Switch PMU to guest as late as possible Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 38/55] KVM: PPC: Book3S HV P9: Restrict DSISR canary workaround to processors that require it Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 39/55] KVM: PPC: Book3S HV P9: More SPR speed improvements Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 40/55] KVM: PPC: Book3S HV P9: Demand fault EBB facility registers Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 41/55] KVM: PPC: Book3S HV P9: Demand fault TM " Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 42/55] KVM: PPC: Book3S HV P9: Use Linux SPR save/restore to manage some host SPRs Nicholas Piggin
2021-07-26 3:50 ` Nicholas Piggin [this message]
2021-07-26 3:50 ` [PATCH v1 44/55] KVM: PPC: Book3S HV P9: Test dawr_enabled() before saving host DAWR SPRs Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 45/55] KVM: PPC: Book3S HV P9: Don't restore PSSCR if not needed Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 46/55] KVM: PPC: Book3S HV P9: Avoid tlbsync sequence on radix guest exit Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 47/55] KVM: PPC: Book3S HV Nested: Avoid extra mftb() in nested entry Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 48/55] KVM: PPC: Book3S HV P9: Improve mfmsr performance on entry Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 49/55] KVM: PPC: Book3S HV P9: Optimise hash guest SLB saving Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 50/55] KVM: PPC: Book3S HV P9: Add unlikely annotation for !mmu_ready Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 51/55] KVM: PPC: Book3S HV P9: Avoid cpu_in_guest atomics on entry and exit Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 52/55] KVM: PPC: Book3S HV P9: Remove most of the vcore logic Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 53/55] KVM: PPC: Book3S HV P9: Tidy kvmppc_create_dtl_entry Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 54/55] KVM: PPC: Book3S HV P9: Stop using vc->dpdes Nicholas Piggin
2021-07-26 3:50 ` [PATCH v1 55/55] KVM: PPC: Book3S HV P9: Remove subcore HMI handling Nicholas Piggin
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=20210726035036.739609-44-npiggin@gmail.com \
--to=npiggin@gmail.com \
--cc=kvm-ppc@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
/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).