Re: [PATCH] powerpc/mm: Always invalidate tlb on hpte invalidate and update

2013-06-02 Thread Aneesh Kumar K.V
Michael Ellerman writes: > On Fri, May 31, 2013 at 04:33:24PM +0530, Aneesh Kumar K.V wrote: >> From: "Aneesh Kumar K.V" >> >> If a hash bucket gets full, we "evict" a more/less random entry from it. >> When we do that we don't invalidate the TLB (hpte_remove) because we assume >> the old trans

Re: [PATCH] powerpc/mm: Always invalidate tlb on hpte invalidate and update

2013-06-01 Thread Benjamin Herrenschmidt
On Sat, 2013-06-01 at 21:19 +1000, Michael Ellerman wrote: > On Fri, May 31, 2013 at 04:33:24PM +0530, Aneesh Kumar K.V wrote: > > From: "Aneesh Kumar K.V" > > > > If a hash bucket gets full, we "evict" a more/less random entry from it. > > When we do that we don't invalidate the TLB (hpte_remove

Re: [PATCH] powerpc/mm: Always invalidate tlb on hpte invalidate and update

2013-06-01 Thread Michael Ellerman
On Fri, May 31, 2013 at 04:33:24PM +0530, Aneesh Kumar K.V wrote: > From: "Aneesh Kumar K.V" > > If a hash bucket gets full, we "evict" a more/less random entry from it. > When we do that we don't invalidate the TLB (hpte_remove) because we assume > the old translation is still technically "valid

[PATCH] powerpc/mm: Always invalidate tlb on hpte invalidate and update

2013-05-31 Thread Aneesh Kumar K.V
From: "Aneesh Kumar K.V" If a hash bucket gets full, we "evict" a more/less random entry from it. When we do that we don't invalidate the TLB (hpte_remove) because we assume the old translation is still technically "valid". This implies that when we are invalidating or updating pte, even if HPTE