From: Izik Eidus <ieidus@redhat.com> To: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, avi@redhat.com, aarcange@redhat.com, chrisw@redhat.com, mtosatti@redhat.com, hugh@veritas.com, kamezawa.hiroyu@jp.fujitsu.com Subject: Re: [PATCH 4/4] add ksm kernel shared memory driver. Date: Thu, 16 Apr 2009 03:57:17 +0300 [thread overview] Message-ID: <49E6826D.7050407@redhat.com> (raw) In-Reply-To: <49E67F17.1070805@goop.org> Jeremy Fitzhardinge wrote: > Andrew Morton wrote: >>> +static pte_t *get_pte(struct mm_struct *mm, unsigned long addr) >>> +{ >>> + pgd_t *pgd; >>> + pud_t *pud; >>> + pmd_t *pmd; >>> + pte_t *ptep = NULL; >>> + >>> + pgd = pgd_offset(mm, addr); >>> + if (!pgd_present(*pgd)) >>> + goto out; >>> + >>> + pud = pud_offset(pgd, addr); >>> + if (!pud_present(*pud)) >>> + goto out; >>> + >>> + pmd = pmd_offset(pud, addr); >>> + if (!pmd_present(*pmd)) >>> + goto out; >>> + >>> + ptep = pte_offset_map(pmd, addr); >>> +out: >>> + return ptep; >>> +} >>> >> >> hm, this looks very generic. Does it duplicate anything which core >> kernel already provides? If not, perhaps core kernel should provide >> this (perhaps after some reorganisation). >> > > It is lookup_address() which works on user addresses, and as such is > very useful. But ksm need the pgd offset of an mm struct, not the kernel pgd, so maybe changing it to get the pgd offset would be nice.. Another thing it is just for x86 right now, so probably it need to go out to the common code > But it would need to deal with returning a level so it can deal with > large pages in usermode, and have some well-defined semantics on > whether the caller is responsible for unmapping the returned thing > (ie, only if its a pte). > > I implemented this myself a couple of months ago, but I can't find it > anywhere... > >>> +static int memcmp_pages(struct page *page1, struct page *page2) >>> +{ >>> + char *addr1, *addr2; >>> + int r; >>> + >>> + addr1 = kmap_atomic(page1, KM_USER0); >>> + addr2 = kmap_atomic(page2, KM_USER1); >>> + r = memcmp(addr1, addr2, PAGE_SIZE); >>> + kunmap_atomic(addr1, KM_USER0); >>> + kunmap_atomic(addr2, KM_USER1); >>> + return r; >>> +} >>> >> >> I wonder if this code all does enough cpu cache flushing to be able to >> guarantee that it's looking at valid data. Not my area, and presumably >> not an issue on x86. >> > > Shouldn't that be kmap_atomic's job anyway? Otherwise it would be > hard to use on any virtual-tag/indexed cache machine. > > J
WARNING: multiple messages have this Message-ID (diff)
From: Izik Eidus <ieidus@redhat.com> To: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andrew Morton <akpm@linux-foundation.org>, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, avi@redhat.com, aarcange@redhat.com, chrisw@redhat.com, mtosatti@redhat.com, hugh@veritas.com, kamezawa.hiroyu@jp.fujitsu.com Subject: Re: [PATCH 4/4] add ksm kernel shared memory driver. Date: Thu, 16 Apr 2009 03:57:17 +0300 [thread overview] Message-ID: <49E6826D.7050407@redhat.com> (raw) In-Reply-To: <49E67F17.1070805@goop.org> Jeremy Fitzhardinge wrote: > Andrew Morton wrote: >>> +static pte_t *get_pte(struct mm_struct *mm, unsigned long addr) >>> +{ >>> + pgd_t *pgd; >>> + pud_t *pud; >>> + pmd_t *pmd; >>> + pte_t *ptep = NULL; >>> + >>> + pgd = pgd_offset(mm, addr); >>> + if (!pgd_present(*pgd)) >>> + goto out; >>> + >>> + pud = pud_offset(pgd, addr); >>> + if (!pud_present(*pud)) >>> + goto out; >>> + >>> + pmd = pmd_offset(pud, addr); >>> + if (!pmd_present(*pmd)) >>> + goto out; >>> + >>> + ptep = pte_offset_map(pmd, addr); >>> +out: >>> + return ptep; >>> +} >>> >> >> hm, this looks very generic. Does it duplicate anything which core >> kernel already provides? If not, perhaps core kernel should provide >> this (perhaps after some reorganisation). >> > > It is lookup_address() which works on user addresses, and as such is > very useful. But ksm need the pgd offset of an mm struct, not the kernel pgd, so maybe changing it to get the pgd offset would be nice.. Another thing it is just for x86 right now, so probably it need to go out to the common code > But it would need to deal with returning a level so it can deal with > large pages in usermode, and have some well-defined semantics on > whether the caller is responsible for unmapping the returned thing > (ie, only if its a pte). > > I implemented this myself a couple of months ago, but I can't find it > anywhere... > >>> +static int memcmp_pages(struct page *page1, struct page *page2) >>> +{ >>> + char *addr1, *addr2; >>> + int r; >>> + >>> + addr1 = kmap_atomic(page1, KM_USER0); >>> + addr2 = kmap_atomic(page2, KM_USER1); >>> + r = memcmp(addr1, addr2, PAGE_SIZE); >>> + kunmap_atomic(addr1, KM_USER0); >>> + kunmap_atomic(addr2, KM_USER1); >>> + return r; >>> +} >>> >> >> I wonder if this code all does enough cpu cache flushing to be able to >> guarantee that it's looking at valid data. Not my area, and presumably >> not an issue on x86. >> > > Shouldn't that be kmap_atomic's job anyway? Otherwise it would be > hard to use on any virtual-tag/indexed cache machine. > > J -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2009-04-16 0:59 UTC|newest] Thread overview: 106+ messages / expand[flat|nested] mbox.gz Atom feed top 2009-04-09 3:58 [PATCH 0/4] ksm - dynamic page sharing driver for linux v3 Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 2/4] add page_wrprotect(): write protecting page Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-09 3:58 ` [PATCH 4/4] add ksm kernel shared memory driver Izik Eidus 2009-04-09 3:58 ` Izik Eidus 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-15 22:37 ` Izik Eidus 2009-04-15 22:37 ` Izik Eidus 2009-04-15 22:50 ` Andrew Morton 2009-04-15 22:50 ` Andrew Morton 2009-04-15 23:21 ` Andrea Arcangeli 2009-04-15 23:21 ` Andrea Arcangeli 2009-04-16 0:43 ` Jeremy Fitzhardinge 2009-04-16 0:43 ` Jeremy Fitzhardinge 2009-04-16 0:57 ` Izik Eidus [this message] 2009-04-16 0:57 ` Izik Eidus 2009-04-16 11:39 ` Andrea Arcangeli 2009-04-16 11:39 ` Andrea Arcangeli 2009-04-16 16:08 ` Jeremy Fitzhardinge 2009-04-16 16:08 ` Jeremy Fitzhardinge 2009-04-18 14:58 ` Andrea Arcangeli 2009-04-18 14:58 ` Andrea Arcangeli 2009-04-14 22:09 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-15 11:25 ` Andrea Arcangeli 2009-04-15 11:25 ` Andrea Arcangeli 2009-04-15 22:48 ` Izik Eidus 2009-04-15 22:48 ` Izik Eidus 2009-04-14 22:09 ` [PATCH 0/4] ksm - dynamic page sharing driver for linux v3 Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-14 22:09 ` Andrew Morton 2009-04-16 17:55 ` Nick Piggin 2009-04-16 17:55 ` Nick Piggin 2009-04-16 18:25 ` Izik Eidus 2009-04-16 18:25 ` Izik Eidus 2009-04-17 7:08 ` Jared Hulbert 2009-04-17 7:08 ` Jared Hulbert 2009-04-21 2:59 ` Nick Piggin 2009-04-21 2:59 ` Nick Piggin -- strict thread matches above, loose matches on Subject: below -- 2009-04-04 14:35 [PATCH 0/4] ksm - dynamic page sharing driver for linux v2 Izik Eidus 2009-04-04 14:35 ` [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Izik Eidus 2009-04-04 14:35 ` [PATCH 2/4] add page_wrprotect(): write protecting page Izik Eidus 2009-04-04 14:35 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Izik Eidus 2009-04-04 14:35 ` [PATCH 4/4] add ksm kernel shared memory driver Izik Eidus 2009-04-04 14:35 ` Izik Eidus 2009-04-06 9:13 ` Andrey Panin 2009-04-06 9:13 ` Andrey Panin 2009-04-06 10:58 ` Izik Eidus 2009-04-06 10:58 ` Izik Eidus 2009-04-06 10:58 ` Izik Eidus 2009-03-30 23:59 [PATCH 0/4] ksm - dynamic page sharing driver for linux Izik Eidus 2009-03-30 23:59 ` [PATCH 1/4] MMU_NOTIFIERS: add set_pte_at_notify() Izik Eidus 2009-03-30 23:59 ` [PATCH 2/4] add page_wrprotect(): write protecting page Izik Eidus 2009-03-30 23:59 ` [PATCH 3/4] add replace_page(): change the page pte is pointing to Izik Eidus 2009-03-30 23:59 ` [PATCH 4/4] add ksm kernel shared memory driver Izik Eidus 2009-03-30 23:59 ` Izik Eidus 2009-03-31 2:12 ` Anthony Liguori 2009-03-31 2:12 ` Anthony Liguori 2009-03-31 12:24 ` Izik Eidus 2009-03-31 12:24 ` Izik Eidus 2009-03-31 13:31 ` Anthony Liguori 2009-03-31 13:31 ` Anthony Liguori 2009-03-31 14:25 ` Andrea Arcangeli 2009-03-31 14:25 ` Andrea Arcangeli 2009-03-31 14:37 ` Anthony Liguori 2009-03-31 14:37 ` Anthony Liguori 2009-03-31 15:02 ` Andrea Arcangeli 2009-03-31 15:02 ` Andrea Arcangeli 2009-03-31 15:09 ` Anthony Liguori 2009-03-31 15:09 ` Anthony Liguori 2009-03-31 15:18 ` Andrea Arcangeli 2009-03-31 15:18 ` Andrea Arcangeli 2009-03-31 15:54 ` Anthony Liguori 2009-03-31 15:54 ` Anthony Liguori 2009-03-31 16:25 ` Andrea Arcangeli 2009-03-31 16:25 ` Andrea Arcangeli 2009-03-31 16:51 ` Anthony Liguori 2009-03-31 16:51 ` Anthony Liguori 2009-03-31 17:11 ` Andrea Arcangeli 2009-03-31 17:11 ` Andrea Arcangeli 2009-04-01 22:54 ` Izik Eidus 2009-04-01 22:54 ` Izik Eidus 2009-04-02 0:31 ` Anthony Liguori 2009-04-02 0:31 ` Anthony Liguori 2009-04-02 0:48 ` Chris Wright 2009-04-02 0:48 ` Chris Wright 2009-04-02 1:22 ` Chris Wright 2009-04-02 1:22 ` Chris Wright 2009-04-02 2:36 ` Anthony Liguori 2009-04-02 2:36 ` Anthony Liguori 2009-04-02 7:24 ` Avi Kivity 2009-04-02 7:24 ` Avi Kivity 2009-04-02 9:38 ` Andrea Arcangeli 2009-04-02 9:38 ` Andrea Arcangeli 2009-04-02 11:23 ` Izik Eidus 2009-04-02 11:23 ` Izik Eidus 2009-03-31 2:15 ` KAMEZAWA Hiroyuki 2009-03-31 2:15 ` KAMEZAWA Hiroyuki 2009-03-31 12:21 ` Izik Eidus 2009-03-31 12:21 ` Izik Eidus 2009-03-31 23:57 ` KAMEZAWA Hiroyuki 2009-03-31 23:57 ` KAMEZAWA Hiroyuki 2009-04-01 17:28 ` Izik Eidus 2009-04-01 17:28 ` Izik Eidus 2009-03-31 20:52 ` Andrea Arcangeli 2009-03-31 20:52 ` Andrea Arcangeli
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=49E6826D.7050407@redhat.com \ --to=ieidus@redhat.com \ --cc=aarcange@redhat.com \ --cc=akpm@linux-foundation.org \ --cc=avi@redhat.com \ --cc=chrisw@redhat.com \ --cc=hugh@veritas.com \ --cc=jeremy@goop.org \ --cc=kamezawa.hiroyu@jp.fujitsu.com \ --cc=kvm@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mtosatti@redhat.com \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.