From: Greg KH <gregkh@suse.de>
To: linux-kernel@vger.kernel.org, stable@kernel.org
Cc: stable-review@kernel.org, torvalds@linux-foundation.org,
akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk,
linuxppc-dev list <linuxppc-dev@ozlabs.org>,
RFeany@mrv.com, Rex Feany <rfeany@mrv.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: [patch 26/30] powerpc/8xx: Fix regression introduced by cache coherency rewrite
Date: Thu, 01 Oct 2009 16:31:42 -0700 [thread overview]
Message-ID: <20091001233322.677176498@mini.kroah.org> (raw)
In-Reply-To: <20091001233504.GA17709@kroah.com>
[-- Attachment #1: powerpc-8xx-fix-regression-introduced-by-cache-coherency-rewrite.patch --]
[-- Type: text/plain, Size: 2679 bytes --]
2.6.30-stable review patch. If anyone has any objections, please let us know.
------------------
From: Rex Feany <RFeany@mrv.com>
commit e0908085fc2391c85b85fb814ae1df377c8e0dcb upstream.
After upgrading to the latest kernel on my mpc875 userspace started
running incredibly slow (hours to get to a shell, even!).
I tracked it down to commit 8d30c14cab30d405a05f2aaceda1e9ad57800f36,
that patch removed a work-around for the 8xx. Adding it
back makes my problem go away.
Signed-off-by: Rex Feany <rfeany@mrv.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
arch/powerpc/mm/pgtable.c | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -30,6 +30,8 @@
#include <asm/tlbflush.h>
#include <asm/tlb.h>
+#include "mmu_decl.h"
+
static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
static unsigned long pte_freelist_forced_free;
@@ -119,7 +121,7 @@ void pte_free_finish(void)
/*
* Handle i/d cache flushing, called from set_pte_at() or ptep_set_access_flags()
*/
-static pte_t do_dcache_icache_coherency(pte_t pte)
+static pte_t do_dcache_icache_coherency(pte_t pte, unsigned long addr)
{
unsigned long pfn = pte_pfn(pte);
struct page *page;
@@ -128,6 +130,17 @@ static pte_t do_dcache_icache_coherency(
return pte;
page = pfn_to_page(pfn);
+#ifdef CONFIG_8xx
+ /* On 8xx, cache control instructions (particularly
+ * "dcbst" from flush_dcache_icache) fault as write
+ * operation if there is an unpopulated TLB entry
+ * for the address in question. To workaround that,
+ * we invalidate the TLB here, thus avoiding dcbst
+ * misbehaviour.
+ */
+ _tlbil_va(addr, 0 /* 8xx doesn't care about PID */);
+#endif
+
if (!PageReserved(page) && !test_bit(PG_arch_1, &page->flags)) {
pr_debug("do_dcache_icache_coherency... flushing\n");
flush_dcache_icache_page(page);
@@ -198,7 +211,7 @@ void set_pte_at(struct mm_struct *mm, un
*/
pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
if (pte_need_exec_flush(pte, 1))
- pte = do_dcache_icache_coherency(pte);
+ pte = do_dcache_icache_coherency(pte, addr);
/* Perform the setting of the PTE */
__set_pte_at(mm, addr, ptep, pte, 0);
@@ -216,7 +229,7 @@ int ptep_set_access_flags(struct vm_area
{
int changed;
if (!dirty && pte_need_exec_flush(entry, 0))
- entry = do_dcache_icache_coherency(entry);
+ entry = do_dcache_icache_coherency(entry, address);
changed = !pte_same(*(ptep), entry);
if (changed) {
if (!(vma->vm_flags & VM_HUGETLB))
next prev parent reply other threads:[~2009-10-01 23:38 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20091001233116.947658905@mini.kroah.org>
2009-10-01 23:35 ` [patch 00/30] 2.6.30.9-stable review Greg KH
2009-10-01 23:31 ` [patch 01/30] ACPI: pci_slot.ko wants a 64-bit _SUN Greg KH
2009-10-01 23:31 ` [patch 02/30] fs: make sure data stored into inode is properly seen before unlocking new inode Greg KH
2009-10-01 23:31 ` [patch 03/30] kallsyms: fix segfault in prefix_underscores_count() Greg KH
2009-10-01 23:31 ` [patch 04/30] nilfs2: fix missing zero-fill initialization of btree node cache Greg KH
2009-10-01 23:31 ` [patch 05/30] p54usb: add Zcomax XG-705A usbid Greg KH
2009-10-01 23:31 ` [patch 06/30] [CIFS] Re-enable Lanman security Greg KH
2009-10-01 23:31 ` [patch 07/30] KVM: VMX: Check cpl before emulating debug register access Greg KH
2009-10-01 23:31 ` [patch 08/30] KVM: VMX: Fix cr8 exiting control clobbering by EPT Greg KH
2009-10-01 23:31 ` [patch 09/30] KVM: MMU: make __kvm_mmu_free_some_pages handle empty list Greg KH
2009-10-01 23:31 ` [patch 10/30] KVM: x86: Disallow hypercalls for guest callers in rings > 0 Greg KH
2009-10-01 23:31 ` [patch 11/30] KVM: MMU: fix missing locking in alloc_mmu_pages Greg KH
2009-10-01 23:31 ` [patch 12/30] KVM: MMU: fix bogus alloc_mmu_pages assignment Greg KH
2009-10-01 23:31 ` [patch 13/30] KVM: limit lapic periodic timer frequency Greg KH
2009-10-01 23:31 ` [patch 14/30] KVM guest: fix bogus wallclock physical address calculation Greg KH
2009-10-01 23:31 ` [patch 15/30] KVM: fix cpuid E2BIG handling for extended request types Greg KH
2009-10-01 23:31 ` [patch 16/30] Revert "KVM: x86: check for cr3 validity in ioctl_set_sregs" Greg KH
2009-10-01 23:31 ` [patch 17/30] ahci: restore pci_intx() handling Greg KH
2009-10-01 23:31 ` [patch 18/30] net ax25: Fix signed comparison in the sockopt handler Greg KH
2009-10-01 23:31 ` [patch 19/30] net: Make the copy length in af_packet sockopt handler unsigned Greg KH
2009-10-01 23:31 ` [patch 20/30] [CPUFREQ] Fix NULL ptr regression in powernow-k8 Greg KH
2009-10-01 23:31 ` [patch 21/30] netfilter: bridge: refcount fix Greg KH
2009-10-01 23:31 ` [patch 22/30] netfilter: ebt_ulog: fix checkentry return value Greg KH
2009-10-01 23:31 ` [patch 23/30] netfilter: nf_nat: fix inverted logic for persistent NAT mappings Greg KH
2009-10-01 23:31 ` [patch 24/30] Fix idle time field in /proc/uptime Greg KH
2009-10-01 23:31 ` [patch 25/30] hugetlb: restore interleaving of bootmem huge pages (2.6.31) Greg KH
2009-10-01 23:31 ` Greg KH [this message]
2009-10-01 23:31 ` [patch 27/30] powerpc: Fix incorrect setting of __HAVE_ARCH_PTE_SPECIAL Greg KH
2009-10-01 23:31 ` [patch 28/30] /proc/kcore: work around a BUG() Greg KH
2009-10-01 23:31 ` [patch 29/30] PM / PCMCIA: Drop second argument of pcmcia_socket_dev_suspend() Greg KH
2009-10-01 23:31 ` [patch 30/30] PM / yenta: Fix cardbus suspend/resume regression Greg KH
2009-10-02 2:43 ` [patch 00/30] 2.6.30.9-stable review Henrique de Moraes Holschuh
2009-10-02 14:20 ` [stable] " Greg KH
2009-10-03 14:39 ` Henrique de Moraes Holschuh
2009-10-02 16:42 ` [31/30] thinkpad-acpi: fix incorrect use of TPACPI_BRGHT_MODE_ECNVRAM Greg KH
2009-10-02 17:20 ` [patch 32/30] mm: fix anonymous dirtying Greg KH
2009-10-02 17:21 ` [patch 33/30] mmap: avoid unnecessary anon_vma lock acquisition in vma_adjust() Greg KH
2009-10-02 17:23 ` [patch 00/30] 2.6.30.9-stable review Greg KH
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=20091001233322.677176498@mini.kroah.org \
--to=gregkh@suse.de \
--cc=RFeany@mrv.com \
--cc=akpm@linux-foundation.org \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=benh@kernel.crashing.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=stable-review@kernel.org \
--cc=stable@kernel.org \
--cc=torvalds@linux-foundation.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