Date: Thu, 15 Nov 2012 12:59:58 +0200 From: Aleksandr Rybalko <ray@ddteam.net> To: Alan Cox <alc@FreeBSD.org> Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org Subject: Re: svn commit: r243030 - in head/sys/mips: include mips Message-ID: <20121115125958.c8fe031258c233ff359223d6@ddteam.net> In-Reply-To: <201211141733.qAEHX126017682@svn.freebsd.org> References: <201211141733.qAEHX126017682@svn.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 14 Nov 2012 17:33:01 +0000 (UTC) Alan Cox <alc@FreeBSD.org> wrote: > Author: alc > Date: Wed Nov 14 17:33:00 2012 > New Revision: 243030 > URL: http://svnweb.freebsd.org/changeset/base/243030 > > Log: > The function pmap_alloc_direct_page() unconditionally zeroes the returned > page. Therefore, it is really inappropriate for use by the function > uma_small_alloc(). The effect of using it was that every page was zeroed > at least once and possibly twice if M_ZERO was passed as a "wait" flag. Many thanks Alan! No I able to store 8MB fw image on tmpfs. Bot only once :) > > Modified: > head/sys/mips/include/pmap.h > head/sys/mips/mips/pmap.c > head/sys/mips/mips/uma_machdep.c > > Modified: head/sys/mips/include/pmap.h > ============================================================================== > --- head/sys/mips/include/pmap.h Wed Nov 14 17:23:48 2012 (r243029) > +++ head/sys/mips/include/pmap.h Wed Nov 14 17:33:00 2012 (r243030) > @@ -179,7 +179,6 @@ void pmap_kenter_temporary_free(vm_paddr > void pmap_flush_pvcache(vm_page_t m); > int pmap_emulate_modified(pmap_t pmap, vm_offset_t va); > void pmap_grow_direct_page_cache(void); > -vm_page_t pmap_alloc_direct_page(unsigned int index, int req); > > #endif /* _KERNEL */ > > > Modified: head/sys/mips/mips/pmap.c > ============================================================================== > --- head/sys/mips/mips/pmap.c Wed Nov 14 17:23:48 2012 (r243029) > +++ head/sys/mips/mips/pmap.c Wed Nov 14 17:33:00 2012 (r243030) > @@ -163,6 +163,7 @@ static vm_page_t pmap_pv_reclaim(pmap_t > static void pmap_pvh_free(struct md_page *pvh, pmap_t pmap, vm_offset_t va); > static pv_entry_t pmap_pvh_remove(struct md_page *pvh, pmap_t pmap, > vm_offset_t va); > +static vm_page_t pmap_alloc_direct_page(unsigned int index, int req); > static vm_page_t pmap_enter_quick_locked(pmap_t pmap, vm_offset_t va, > vm_page_t m, vm_prot_t prot, vm_page_t mpte); > static int pmap_remove_pte(struct pmap *pmap, pt_entry_t *ptq, vm_offset_t va, > @@ -1041,7 +1042,7 @@ pmap_grow_direct_page_cache() > #endif > } > > -vm_page_t > +static vm_page_t > pmap_alloc_direct_page(unsigned int index, int req) > { > vm_page_t m; > > Modified: head/sys/mips/mips/uma_machdep.c > ============================================================================== > --- head/sys/mips/mips/uma_machdep.c Wed Nov 14 17:23:48 2012 (r243029) > +++ head/sys/mips/mips/uma_machdep.c Wed Nov 14 17:33:00 2012 (r243030) > @@ -50,12 +50,14 @@ uma_small_alloc(uma_zone_t zone, int byt > *flags = UMA_SLAB_PRIV; > > if ((wait & (M_NOWAIT|M_USE_RESERVE)) == M_NOWAIT) > - pflags = VM_ALLOC_INTERRUPT; > + pflags = VM_ALLOC_INTERRUPT | VM_ALLOC_WIRED; > else > - pflags = VM_ALLOC_SYSTEM; > + pflags = VM_ALLOC_SYSTEM | VM_ALLOC_WIRED; > + if (wait & M_ZERO) > + pflags |= VM_ALLOC_ZERO; > > for (;;) { > - m = pmap_alloc_direct_page(0, pflags); > + m = vm_page_alloc_freelist(VM_FREELIST_DIRECT, pflags); > if (m == NULL) { > if (wait & M_NOWAIT) > return (NULL); -- Aleksandr Rybalko <ray@ddteam.net>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20121115125958.c8fe031258c233ff359223d6>