From: Stephen Rothwell <sfr@canb.auug.org.au>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-next@vger.kernel.org, linux-kernel@vger.kernel.org,
Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
"H. Peter Anvin" <hpa@zytor.com>,
Peter Zijlstra <peterz@infradead.org>,
Gerald Schaefer <gerald.schaefer@de.ibm.com>
Subject: linux-next: manual merge of the akpm tree with the tip tree
Date: Thu, 27 Sep 2012 17:15:45 +1000 [thread overview]
Message-ID: <20120927171545.79c597f3fa5f7d5f66a7e2ce@canb.auug.org.au> (raw)
[-- Attachment #1: Type: text/plain, Size: 4824 bytes --]
Hi Andrew,
Today's linux-next merge of the akpm tree got a conflict in
mm/huge_memory.c between commit 93c9d633bd9e ("93c9d633bd9e") from the
tip tree and commit "thp: introduce pmdp_invalidate()" from the akpm tree.
I fixed it up (see below) and can carry the fix as necessary (no action
is required).
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
diff --cc mm/huge_memory.c
index 9267537,56f9443..0000000
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@@ -1384,55 -1312,59 +1384,54 @@@ static int __split_huge_page_map(struc
spin_lock(&mm->page_table_lock);
pmd = page_check_address_pmd(page, mm, address,
PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
- if (pmd) {
- pgtable = pgtable_trans_huge_withdraw(mm);
- pmd_populate(mm, &_pmd, pgtable);
-
- for (i = 0, haddr = address; i < HPAGE_PMD_NR;
- i++, haddr += PAGE_SIZE) {
- pte_t *pte, entry;
- BUG_ON(PageCompound(page+i));
- entry = mk_pte(page + i, vma->vm_page_prot);
- entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- if (!pmd_write(*pmd))
- entry = pte_wrprotect(entry);
- else
- BUG_ON(page_mapcount(page) != 1);
- if (!pmd_young(*pmd))
- entry = pte_mkold(entry);
- pte = pte_offset_map(&_pmd, haddr);
- BUG_ON(!pte_none(*pte));
- set_pte_at(mm, haddr, pte, entry);
- pte_unmap(pte);
- }
+ if (!pmd)
+ goto unlock;
- smp_wmb(); /* make pte visible before pmd */
- /*
- * Up to this point the pmd is present and huge and
- * userland has the whole access to the hugepage
- * during the split (which happens in place). If we
- * overwrite the pmd with the not-huge version
- * pointing to the pte here (which of course we could
- * if all CPUs were bug free), userland could trigger
- * a small page size TLB miss on the small sized TLB
- * while the hugepage TLB entry is still established
- * in the huge TLB. Some CPU doesn't like that. See
- * http://support.amd.com/us/Processor_TechDocs/41322.pdf,
- * Erratum 383 on page 93. Intel should be safe but is
- * also warns that it's only safe if the permission
- * and cache attributes of the two entries loaded in
- * the two TLB is identical (which should be the case
- * here). But it is generally safer to never allow
- * small and huge TLB entries for the same virtual
- * address to be loaded simultaneously. So instead of
- * doing "pmd_populate(); flush_tlb_range();" we first
- * mark the current pmd notpresent (atomically because
- * here the pmd_trans_huge and pmd_trans_splitting
- * must remain set at all times on the pmd until the
- * split is complete for this pmd), then we flush the
- * SMP TLB and finally we write the non-huge version
- * of the pmd entry with pmd_populate.
- */
- pmdp_invalidate(vma, address, pmd);
- pmd_populate(mm, pmd, pgtable);
- ret = 1;
+ prot = pmd_pgprot(*pmd);
+ pgtable = pgtable_trans_huge_withdraw(mm);
+ pmd_populate(mm, &_pmd, pgtable);
+
+ for (i = 0, haddr = address; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+ pte_t *pte, entry;
+
+ BUG_ON(PageCompound(page+i));
+ entry = mk_pte(page + i, prot);
+ entry = pte_mkdirty(entry);
+ if (!pmd_young(*pmd))
+ entry = pte_mkold(entry);
+ pte = pte_offset_map(&_pmd, haddr);
+ BUG_ON(!pte_none(*pte));
+ set_pte_at(mm, haddr, pte, entry);
+ pte_unmap(pte);
}
+
+ smp_wmb(); /* make ptes visible before pmd, see __pte_alloc */
+ /*
+ * Up to this point the pmd is present and huge.
+ *
+ * If we overwrite the pmd with the not-huge version, we could trigger
+ * a small page size TLB miss on the small sized TLB while the hugepage
+ * TLB entry is still established in the huge TLB.
+ *
+ * Some CPUs don't like that. See
+ * http://support.amd.com/us/Processor_TechDocs/41322.pdf, Erratum 383
+ * on page 93.
+ *
+ * Thus it is generally safer to never allow small and huge TLB entries
+ * for overlapping virtual addresses to be loaded. So we first mark the
+ * current pmd not present, then we flush the TLB and finally we write
+ * the non-huge version of the pmd entry with pmd_populate.
+ *
+ * The above needs to be done under the ptl because pmd_trans_huge and
+ * pmd_trans_splitting must remain set on the pmd until the split is
+ * complete. The ptl also protects against concurrent faults due to
+ * making the pmd not-present.
+ */
- set_pmd_at(mm, address, pmd, pmd_mknotpresent(*pmd));
- flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
++ pmdp_invalidate(vma, address, pmd);
+ pmd_populate(mm, pmd, pgtable);
+ ret = 1;
+
+unlock:
spin_unlock(&mm->page_table_lock);
return ret;
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
next reply other threads:[~2012-09-27 7:15 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-27 7:15 Stephen Rothwell [this message]
-- strict thread matches above, loose matches on Subject: below --
2020-05-29 10:57 linux-next: manual merge of the akpm tree with the tip tree Stephen Rothwell
2020-05-29 10:49 Stephen Rothwell
2020-01-22 6:37 Stephen Rothwell
2019-02-13 6:49 Stephen Rothwell
2019-02-13 19:59 ` Andrew Morton
2018-01-09 5:02 Stephen Rothwell
2018-01-09 10:36 ` Andy Shevchenko
2017-10-16 18:48 Mark Brown
2017-10-16 20:01 ` Mark Brown
2017-04-12 7:08 Stephen Rothwell
2017-03-31 5:44 Stephen Rothwell
2017-03-31 6:42 ` Peter Zijlstra
2017-03-31 13:54 ` Andi Kleen
2017-03-31 14:45 ` Peter Zijlstra
2017-03-31 16:02 ` Andi Kleen
2017-03-31 17:48 ` Peter Zijlstra
2017-03-24 5:40 Stephen Rothwell
2017-03-24 8:05 ` Peter Zijlstra
2016-03-10 5:28 Stephen Rothwell
2016-03-10 8:00 ` Ingo Molnar
2016-03-10 20:38 ` Andrew Morton
2016-02-09 4:50 Stephen Rothwell
2016-02-09 14:04 ` Matt Fleming
2016-02-09 14:07 ` Ingo Molnar
2015-06-09 14:12 Stephen Rothwell
2015-04-08 8:49 Stephen Rothwell
2015-04-08 15:13 ` Ingo Molnar
2015-04-08 20:46 ` Andrew Morton
2015-04-08 21:57 ` Stephen Rothwell
2014-03-21 6:45 Stephen Rothwell
2014-01-13 6:17 Stephen Rothwell
2013-04-23 7:17 Stephen Rothwell
2013-02-14 4:33 Stephen Rothwell
2013-02-14 4:25 Stephen Rothwell
2013-02-14 4:34 ` H. Peter Anvin
2013-02-04 7:00 Stephen Rothwell
2013-01-28 12:29 Stephen Rothwell
2012-12-10 8:29 Stephen Rothwell
2012-12-10 10:46 ` Ingo Molnar
2012-12-10 8:25 Stephen Rothwell
2012-12-10 8:20 Stephen Rothwell
2012-12-10 8:11 Stephen Rothwell
2012-12-10 8:01 Stephen Rothwell
2012-12-10 11:13 ` Will Deacon
2012-12-10 7:47 Stephen Rothwell
2012-11-15 6:32 Stephen Rothwell
2012-10-01 14:22 Stephen Rothwell
2012-09-27 7:10 Stephen Rothwell
2012-09-27 7:04 Stephen Rothwell
2012-09-27 6:57 Stephen Rothwell
2012-09-27 6:49 Stephen Rothwell
2012-07-27 3:50 Stephen Rothwell
2012-07-25 4:08 Stephen Rothwell
2012-07-25 7:10 ` Ingo Molnar
2012-07-25 7:35 ` Johannes Weiner
2012-07-25 18:57 ` Andrew Morton
2012-07-25 19:03 ` Ingo Molnar
2012-07-25 19:26 ` Andrew Morton
2012-07-26 7:51 ` Ingo Molnar
2012-07-26 18:05 ` Andrew Morton
2012-07-25 19:20 ` Johannes Weiner
2012-07-26 7:03 ` Stephen Rothwell
2012-05-21 8:29 Stephen Rothwell
2012-05-21 8:04 Stephen Rothwell
2012-05-21 7:59 Stephen Rothwell
2012-03-27 4:57 Stephen Rothwell
2012-03-26 4:01 Stephen Rothwell
2012-03-26 5:20 ` Alex Shi
2012-03-08 6:32 Stephen Rothwell
2012-03-08 6:28 Stephen Rothwell
2012-02-29 6:27 Stephen Rothwell
2012-02-28 4:52 Stephen Rothwell
2012-02-27 5:53 Stephen Rothwell
2012-02-27 5:57 ` Cyrill Gorcunov
2012-02-27 6:02 ` H. Peter Anvin
2012-02-27 6:05 ` Cyrill Gorcunov
2012-02-27 6:01 ` H. Peter Anvin
2012-02-27 6:19 ` Stephen Rothwell
2012-02-27 5:44 Stephen Rothwell
2012-02-27 5:33 Stephen Rothwell
2012-02-27 5:23 Stephen Rothwell
2012-02-27 5:16 Stephen Rothwell
2011-12-06 4:04 Stephen Rothwell
2011-09-27 7:13 Stephen Rothwell
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=20120927171545.79c597f3fa5f7d5f66a7e2ce@canb.auug.org.au \
--to=sfr@canb.auug.org.au \
--cc=akpm@linux-foundation.org \
--cc=gerald.schaefer@de.ibm.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-next@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).