linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: linuxppc-dev@ozlabs.org
Subject: [PATCH 2/5] powerpc/mm: Move around testing of _PAGE_PRESENT in hash code
Date: Fri, 23 Jul 2010 10:41:41 +1000	[thread overview]
Message-ID: <1279845704-14848-2-git-send-email-benh@kernel.crashing.org> (raw)
In-Reply-To: <1279845704-14848-1-git-send-email-benh@kernel.crashing.org>

Instead of adding _PAGE_PRESENT to the access permission mask
in each low level routine independently, we add it once from
hash_page().

We also move the preliminary access check (the racy one before
the PTE is locked) up so it applies to the huge page case. This
duplicates code in __hash_page_huge() which we'll remove in a
subsequent patch to fix a race in there.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/mm/hash_low_64.S   |    9 ---------
 arch/powerpc/mm/hash_utils_64.c |   19 +++++++++++--------
 2 files changed, 11 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index a719f53..3079f6b 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -68,9 +68,6 @@ _GLOBAL(__hash_page_4K)
 	std	r8,STK_PARM(r8)(r1)
 	std	r9,STK_PARM(r9)(r1)
 	
-	/* Add _PAGE_PRESENT to access */
-	ori	r4,r4,_PAGE_PRESENT
-
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
@@ -347,9 +344,6 @@ _GLOBAL(__hash_page_4K)
 	std	r8,STK_PARM(r8)(r1)
 	std	r9,STK_PARM(r9)(r1)
 
-	/* Add _PAGE_PRESENT to access */
-	ori	r4,r4,_PAGE_PRESENT
-
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
@@ -687,9 +681,6 @@ _GLOBAL(__hash_page_64K)
 	std	r8,STK_PARM(r8)(r1)
 	std	r9,STK_PARM(r9)(r1)
 
-	/* Add _PAGE_PRESENT to access */
-	ori	r4,r4,_PAGE_PRESENT
-
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 98f262d..40847a9 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -955,6 +955,17 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		return 1;
 	}
 
+	/* Add _PAGE_PRESENT to the required access perm */
+	access |= _PAGE_PRESENT;
+
+	/* Pre-check access permissions (will be re-checked atomically
+	 * in __hash_page_XX but this pre-check is a fast path
+	 */
+	if (access & ~pte_val(*ptep)) {
+		DBG_LOW(" no access !\n");
+		return 1;
+	}
+
 #ifdef CONFIG_HUGETLB_PAGE
 	if (hugeshift)
 		return __hash_page_huge(ea, access, vsid, ptep, trap, local,
@@ -967,14 +978,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	DBG_LOW(" i-pte: %016lx %016lx\n", pte_val(*ptep),
 		pte_val(*(ptep + PTRS_PER_PTE)));
 #endif
-	/* Pre-check access permissions (will be re-checked atomically
-	 * in __hash_page_XX but this pre-check is a fast path
-	 */
-	if (access & ~pte_val(*ptep)) {
-		DBG_LOW(" no access !\n");
-		return 1;
-	}
-
 	/* Do actual hashing */
 #ifdef CONFIG_PPC_64K_PAGES
 	/* If _PAGE_4K_PFN is set, make sure this is a 4k segment */
-- 
1.6.3.3

  reply	other threads:[~2010-07-23  0:42 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-07-23  0:41 [PATCH 1/5] powerpc/mm: Handle hypervisor pte insert failure in __hash_page_huge Benjamin Herrenschmidt
2010-07-23  0:41 ` Benjamin Herrenschmidt [this message]
2010-07-23  0:41   ` [PATCH 3/5] powerpc/mm: Fix bugs in huge page hashing Benjamin Herrenschmidt
2010-07-23  0:41     ` [PATCH 4/5] powerpc/mm: Add some debug output when hash insertion fails Benjamin Herrenschmidt
2010-07-23  0:41       ` [PATCH 5/5] powerpc: Fix erroneous lmb->memblock conversions Benjamin Herrenschmidt
2010-07-23  3:03     ` [PATCH 3/5] powerpc/mm: Fix bugs in huge page hashing Benjamin Herrenschmidt

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=1279845704-14848-2-git-send-email-benh@kernel.crashing.org \
    --to=benh@kernel.crashing.org \
    --cc=linuxppc-dev@ozlabs.org \
    /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).