linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2] powerpc/mm: Add a parameter to disable 1TB segs
@ 2016-07-05  1:43 Oliver O'Halloran
  2016-07-05 14:10 ` [v2] " Michael Ellerman
  0 siblings, 1 reply; 2+ messages in thread
From: Oliver O'Halloran @ 2016-07-05  1:43 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: mikey, mpe, Oliver O'Halloran

This patch adds the kernel command line parameter "no_tb_segs" which
forces the kernel to use 256MB rather than 1TB segments. Forcing the use
of 256MB segments makes it considerably easier to test code that depends
on an SLB miss occurring.

Suggested-by: Michael Neuling <mikey@neuling.org>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
Changes in from v1:
	Renamed parameter from "no_tb_segs" to "disable_1tb_segments"
	Added kernel-parameters.txt entry

 Documentation/kernel-parameters.txt |  6 ++++++
 arch/powerpc/mm/hash_utils_64.c     | 15 +++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 4640ea2dce9b..3be08fda82dd 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -920,6 +920,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
+	disable_1tb_segments [PPC]
+			Disables the use of 1TB hash page table segments. This
+			causes the kernel to fall back to 256MB segments which
+			can be useful when debugging issues that require an SLB
+			miss to occur.
+
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5b22ba0b58bc..7e6d38e01645 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -321,6 +321,15 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 	return ret;
 }
 
+static bool disable_1tb_segments = false;
+
+static int __init parse_disable_1tb_segments(char *p)
+{
+	disable_1tb_segments = true;
+	return 0;
+}
+early_param("disable_1tb_segments", parse_disable_1tb_segments);
+
 static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
 					 void *data)
@@ -339,6 +348,12 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 	for (; size >= 4; size -= 4, ++prop) {
 		if (be32_to_cpu(prop[0]) == 40) {
 			DBG("1T segment support detected\n");
+
+			if (disable_1tb_segments) {
+				DBG("1T segments disabled by command line\n");
+				break;
+			}
+
 			cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
 			return 1;
 		}
-- 
2.5.5

^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [v2] powerpc/mm: Add a parameter to disable 1TB segs
  2016-07-05  1:43 [PATCH v2] powerpc/mm: Add a parameter to disable 1TB segs Oliver O'Halloran
@ 2016-07-05 14:10 ` Michael Ellerman
  0 siblings, 0 replies; 2+ messages in thread
From: Michael Ellerman @ 2016-07-05 14:10 UTC (permalink / raw)
  To: Oliver O'Halloran, linuxppc-dev; +Cc: mikey, Oliver O'Halloran

On Tue, 2016-05-07 at 01:43:21 UTC, Oliver O'Halloran wrote:
> This patch adds the kernel command line parameter "no_tb_segs" which
> forces the kernel to use 256MB rather than 1TB segments. Forcing the use
> of 256MB segments makes it considerably easier to test code that depends
> on an SLB miss occurring.
> 
> Suggested-by: Michael Neuling <mikey@neuling.org>
> Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
> Signed-off-by: Oliver O'Halloran <oohall@gmail.com>

Applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/faf7882962e78a4c8ebb846f45

cheers

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2016-07-05 14:10 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-07-05  1:43 [PATCH v2] powerpc/mm: Add a parameter to disable 1TB segs Oliver O'Halloran
2016-07-05 14:10 ` [v2] " Michael Ellerman

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).