From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, "David S. Miller" <davem@davemloft.net>
Subject: [PATCH 3.10 17/24] sparc64: Fix huge TSB mapping on pre-UltraSPARC-III cpus.
Date: Fri, 8 Aug 2014 14:35:10 -0700 [thread overview]
Message-ID: <20140808213336.134285060@linuxfoundation.org> (raw)
In-Reply-To: <20140808213335.421758947@linuxfoundation.org>
3.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: "David S. Miller" <davem@davemloft.net>
[ Upstream commit b18eb2d779240631a098626cb6841ee2dd34fda0 ]
Access to the TSB hash tables during TLB misses requires that there be
an atomic 128-bit quad load available so that we fetch a matching TAG
and DATA field at the same time.
On cpus prior to UltraSPARC-III only virtual address based quad loads
are available. UltraSPARC-III and later provide physical address
based variants which are easier to use.
When we only have virtual address based quad loads available this
means that we have to lock the TSB into the TLB at a fixed virtual
address on each cpu when it runs that process. We can't just access
the PAGE_OFFSET based aliased mapping of these TSBs because we cannot
take a recursive TLB miss inside of the TLB miss handler without
risking running out of hardware trap levels (some trap combinations
can be deep, such as those generated by register window spill and fill
traps).
Without huge pages it's working perfectly fine, but when the huge TSB
got added another chunk of fixed virtual address space was not
allocated for this second TSB mapping.
So we were mapping both the 8K and 4MB TSBs to the same exact virtual
address, causing multiple TLB matches which gives undefined behavior.
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/sparc/include/asm/pgtable_64.h | 6 ++++--
arch/sparc/mm/tsb.c | 14 +++++++++++++-
2 files changed, 17 insertions(+), 3 deletions(-)
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -24,7 +24,8 @@
/* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
* The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
* The PROM resides in an area spanning 0xf0000000 to 0x100000000.
* The vmalloc area spans 0x100000000 to 0x200000000.
* Since modules need to be in the lowest 32-bits of the address space,
@@ -33,7 +34,8 @@
* 0x400000000.
*/
#define TLBTEMP_BASE _AC(0x0000000006000000,UL)
-#define TSBMAP_BASE _AC(0x0000000008000000,UL)
+#define TSBMAP_8K_BASE _AC(0x0000000008000000,UL)
+#define TSBMAP_4M_BASE _AC(0x0000000008400000,UL)
#define MODULES_VADDR _AC(0x0000000010000000,UL)
#define MODULES_LEN _AC(0x00000000e0000000,UL)
#define MODULES_END _AC(0x00000000f0000000,UL)
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_s
mm->context.tsb_block[tsb_idx].tsb_nentries =
tsb_bytes / sizeof(struct tsb);
- base = TSBMAP_BASE;
+ switch (tsb_idx) {
+ case MM_TSB_BASE:
+ base = TSBMAP_8K_BASE;
+ break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ case MM_TSB_HUGE:
+ base = TSBMAP_4M_BASE;
+ break;
+#endif
+ default:
+ BUG();
+ }
+
tte = pgprot_val(PAGE_KERNEL_LOCKED);
tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
next prev parent reply other threads:[~2014-08-08 22:07 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-08 21:34 [PATCH 3.10 00/24] 3.10.53-stable review Greg Kroah-Hartman
2014-08-08 21:34 ` [PATCH 3.10 01/24] bnx2x: fix crash during TSO tunneling Greg Kroah-Hartman
2014-08-08 21:34 ` [PATCH 3.10 02/24] inetpeer: get rid of ip_id_count Greg Kroah-Hartman
2014-08-08 21:34 ` [PATCH 3.10 03/24] ip: make IP identifiers less predictable Greg Kroah-Hartman
2014-08-08 21:34 ` [PATCH 3.10 04/24] net: sendmsg: fix NULL pointer dereference Greg Kroah-Hartman
2014-08-08 21:34 ` [PATCH 3.10 05/24] tcp: Fix integer-overflows in TCP veno Greg Kroah-Hartman
2014-08-08 21:34 ` [PATCH 3.10 06/24] tcp: Fix integer-overflow in TCP vegas Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 07/24] net: sctp: inherit auth_capable on INIT collisions Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 08/24] macvlan: Initialize vlan_features to turn on offload support Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 09/24] net: Correctly set segment mac_len in skb_segment() Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 10/24] iovec: make sure the caller actually wants anything in memcpy_fromiovecend Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 11/24] sctp: fix possible seqlock seadlock in sctp_packet_transmit() Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 12/24] sparc64: Fix argument sign extension for compat_sys_futex() Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 13/24] sparc64: Make itc_sync_lock raw Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 14/24] sparc64: Handle 32-bit tasks properly in compute_effective_address() Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 15/24] sparc64: Fix top-level fault handling bugs Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 16/24] sparc64: Dont bark so loudly about 32-bit tasks generating 64-bit fault addresses Greg Kroah-Hartman
2014-08-08 21:35 ` Greg Kroah-Hartman [this message]
2014-08-08 21:35 ` [PATCH 3.10 18/24] sparc64: Add membar to Niagara2 memcpy code Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 19/24] sparc64: Do not insert non-valid PTEs into the TSB hash table Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 20/24] sparc64: Guard against flushing openfirmware mappings Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 21/24] bbc-i2c: Fix BBC I2C envctrl on SunBlade 2000 Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 22/24] sunsab: Fix detection of BREAK on sunsab serial console Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 23/24] sparc64: ldc_connect() should not return EINVAL when handshake is in progress Greg Kroah-Hartman
2014-08-08 21:35 ` [PATCH 3.10 24/24] arch/sparc/math-emu/math_32.c: drop stray break operator Greg Kroah-Hartman
2014-08-09 1:03 ` [PATCH 3.10 00/24] 3.10.53-stable review Guenter Roeck
2014-08-09 14:41 ` Shuah Khan
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=20140808213336.134285060@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=davem@davemloft.net \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.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).