Re: [PATCH 3/4] KVM: MMU: Avoid calling gfn_to_page() in mmu_set_spte()

[Marcelo Tosatti <marcelo-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>]

On Sun, Dec 30, 2007 at 01:17:18PM +0200, Avi Kivity wrote:
> Since gfn_to_page() is a sleeping function, and we want to make the core mmu
> spinlocked, we need to pass the page from the walker context (which can sleep)
> to the shadow context (which cannot).
> 
> Signed-off-by: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
> ---
>  arch/x86/kvm/mmu.c         |   58 ++++++++++++++++++++++++++++++++++++++++----
>  arch/x86/kvm/paging_tmpl.h |   25 +++++++++++++++----
>  include/asm-x86/kvm_host.h |    5 ++++
>  3 files changed, 78 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index 3b91227..1b68f07 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c

> +static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
> +					  const u8 *new, int bytes)
> +{
> +	gfn_t gfn;
> +	int r;
> +	u64 gpte = 0;
> +
> +	if (bytes != 4 && bytes != 8)
> +		return;
> +
> +	down_read(&current->mm->mmap_sem);

kvm_mmu_pte_write() already holds mmap_sem in read-mode, so this is not
required (and is deadlock prone actually).

Other than that the patchset looks good, thanks.


--- mmu.c.orig	2007-12-31 09:34:50.000000000 -0500
+++ mmu.c	2007-12-31 09:34:52.000000000 -0500
@@ -1360,7 +1360,6 @@ static void mmu_guess_page_from_pte_writ
 	if (bytes != 4 && bytes != 8)
 		return;
 
-	down_read(&current->mm->mmap_sem);
 	/*
 	 * Assume that the pte write on a page table of the same type
 	 * as the current vcpu paging mode.  This is nearly always true
@@ -1372,7 +1371,7 @@ static void mmu_guess_page_from_pte_writ
 		if ((bytes == 4) && (gpa % 4 == 0)) {
 			r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8);
 			if (r)
-				goto out;
+				return;
 			memcpy((void *)&gpte + (gpa % 8), new, 4);
 		} else if ((bytes == 8) && (gpa % 8 == 0)) {
 			memcpy((void *)&gpte, new, 8);
@@ -1382,12 +1381,10 @@ static void mmu_guess_page_from_pte_writ
 			memcpy((void *)&gpte, new, 4);
 	}
 	if (!is_present_pte(gpte))
-		goto out;
+		return;
 	gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 	vcpu->arch.update_pte.gfn = gfn;
 	vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn);
-out:
-	up_read(&current->mm->mmap_sem);
 }
 
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,

-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2005.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/