[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <a7e15de5-5b04-7a33-1d7d-81edf07193ba@redhat.com>
Date: Thu, 22 Apr 2021 09:30:02 +0200
From: Paolo Bonzini <pbonzini@...hat.com>
To: Sean Christopherson <seanjc@...gle.com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Andy Lutomirski <luto@...nel.org>,
Peter Zijlstra <peterz@...radead.org>
Cc: Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org, Borislav Petkov <bp@...e.de>,
Tom Lendacky <thomas.lendacky@....com>,
Brijesh Singh <brijesh.singh@....com>
Subject: Re: [PATCH v5 15/15] KVM: SVM: Skip SEV cache flush if no ASIDs have
been used
On 22/04/21 04:11, Sean Christopherson wrote:
> + int ret, pos, error = 0;
> +
> + /* Check if there are any ASIDs to reclaim before performing a flush */
> + pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid);
> + if (pos >= max_asid)
> + return -EBUSY;
There's a tiny bug here which would cause sev_flush_asids to return 0
if there are reclaimed SEV ASIDs and the caller is looking for an SEV-ES
ASID, or vice versa. The bug used to be in __sev_recycle_asids, you're
just moving the code.
It's not a big deal because sev_asid_new only retries once, but we might
as well fix it:
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 02b3426a9e39..403c6991e67c 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -74,12 +74,13 @@ struct enc_region {
unsigned long size;
};
+/* Called with the sev_bitmap_lock held, or on shutdown */
static int sev_flush_asids(int min_asid, int max_asid)
{
int ret, pos, error = 0;
/* Check if there are any ASIDs to reclaim before performing a flush */
- pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid);
+ pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid);
if (pos >= max_asid)
return -EBUSY;
Paolo
> /*
> * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail,
> @@ -87,14 +92,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm)
> /* Must be called with the sev_bitmap_lock held */
> static bool __sev_recycle_asids(int min_asid, int max_asid)
> {
> - int pos;
> -
> - /* Check if there are any ASIDs to reclaim before performing a flush */
> - pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid);
> - if (pos >= max_asid)
> - return false;
> -
> - if (sev_flush_asids())
> + if (sev_flush_asids(min_asid, max_asid))
> return false;
>
> /* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
> @@ -1846,10 +1844,11 @@ void sev_hardware_teardown(void)
> if (!sev_enabled)
> return;
>
> + /* No need to take sev_bitmap_lock, all VMs have been destroyed. */
> + sev_flush_asids(0, max_sev_asid);
> +
> bitmap_free(sev_asid_bitmap);
> bitmap_free(sev_reclaim_asid_bitmap);
> -
> - sev_flush_asids();
> }
>
> int sev_cpu_init(struct svm_cpu_data *sd)
>
Powered by blists - more mailing lists