linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Arnd Bergmann <arnd@arndb.de>
To: paulus@samba.org
Cc: Arnd Bergmann <arnd.bergmann@de.ibm.com>,
	linuxppc-dev@ozlabs.org, cbe-oss-dev@ozlabs.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH 08/13] spufs: set up correct SLB entries for 64k pages
Date: Sun, 30 Apr 2006 01:28:20 +0200	[thread overview]
Message-ID: <20060429233921.357349000@localhost.localdomain> (raw)
In-Reply-To: 20060429232812.825714000@localhost.localdomain

spufs currently knows only 4k pages and 16M hugetlb
pages. Make it use the regular methods for deciding on
the SLB bits.

Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
---
Index: linus-2.6/arch/powerpc/platforms/cell/spu_base.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spu_base.c	2006-04-29 22:53:40.000000000 +0200
+++ linus-2.6/arch/powerpc/platforms/cell/spu_base.c	2006-04-29 22:53:43.000000000 +0200
@@ -71,7 +71,7 @@
 {
 	struct spu_priv2 __iomem *priv2 = spu->priv2;
 	struct mm_struct *mm = spu->mm;
-	u64 esid, vsid;
+	u64 esid, vsid, llp;
 
 	pr_debug("%s\n", __FUNCTION__);
 
@@ -91,9 +91,14 @@
 	}
 
 	esid = (ea & ESID_MASK) | SLB_ESID_V;
-	vsid = (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT) | SLB_VSID_USER;
+#ifdef CONFIG_HUGETLB_PAGE
 	if (in_hugepage_area(mm->context, ea))
-		vsid |= SLB_VSID_L;
+		llp = mmu_psize_defs[mmu_huge_psize].sllp;
+	else
+#endif
+		llp = mmu_psize_defs[mmu_virtual_psize].sllp;
+	vsid = (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT) |
+			SLB_VSID_USER | llp;
 
 	out_be64(&priv2->slb_index_W, spu->slb_replace);
 	out_be64(&priv2->slb_vsid_RW, vsid);
Index: linus-2.6/arch/powerpc/platforms/cell/spufs/switch.c
===================================================================
--- linus-2.6.orig/arch/powerpc/platforms/cell/spufs/switch.c	2006-04-29 22:47:55.000000000 +0200
+++ linus-2.6/arch/powerpc/platforms/cell/spufs/switch.c	2006-04-29 22:53:43.000000000 +0200
@@ -718,13 +718,15 @@
 
 static inline void get_kernel_slb(u64 ea, u64 slb[2])
 {
-	slb[0] = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) | SLB_VSID_KERNEL;
-	slb[1] = (ea & ESID_MASK) | SLB_ESID_V;
+	u64 llp;
 
-	/* Large pages are used for kernel text/data, but not vmalloc.  */
-	if (cpu_has_feature(CPU_FTR_16M_PAGE)
-	    && REGION_ID(ea) == KERNEL_REGION_ID)
-		slb[0] |= SLB_VSID_L;
+	if (REGION_ID(ea) == KERNEL_REGION_ID)
+		llp = mmu_psize_defs[mmu_linear_psize].sllp;
+	else
+		llp = mmu_psize_defs[mmu_virtual_psize].sllp;
+	slb[0] = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) |
+		SLB_VSID_KERNEL | llp;
+	slb[1] = (ea & ESID_MASK) | SLB_ESID_V;
 }
 
 static inline void load_mfc_slb(struct spu *spu, u64 slb[2], int slbe)

--

  parent reply	other threads:[~2006-04-29 23:28 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-04-29 23:28 [PATCH 00/13] Cell patches for 2.6.18 Arnd Bergmann
2006-04-29 23:28 ` [PATCH 01/13] cell: always build spu base into the kernel Arnd Bergmann
2006-04-29 23:28 ` [PATCH 02/13] spufs: restore mapping of mssync register Arnd Bergmann
2006-04-29 23:28 ` [PATCH 03/13] cell: fix interrupt priority handling Arnd Bergmann
2006-04-29 23:28 ` [PATCH 04/13] cell: remove broken __setup_cpu_be function Arnd Bergmann
2006-05-05  6:03   ` Paul Mackerras
2006-05-06  0:00     ` Geoff Levand
2006-05-08 18:09       ` Information for setting up SMT related parameters on linux 2.6.16 on POWER5 Meswani, Mitesh
2006-05-08 20:03         ` Will Schmidt
2006-05-08 23:04           ` Segher Boessenkool
2006-05-09 23:17             ` Meswani, Mitesh
2006-05-10 16:27               ` Will Schmidt
2006-05-20  0:25             ` Meswani, Mitesh
2006-04-29 23:28 ` [PATCH 05/13] cell: enable CPU_FTR_CI_LARGE_PAGE Arnd Bergmann
2006-04-29 23:28 ` [PATCH 06/13] powerpc: fix 64k pages on non-hypervisor Arnd Bergmann
2006-04-29 23:28 ` [PATCH 07/13] powerpc: export symbols for page size selection Arnd Bergmann
2006-05-05  5:56   ` Paul Mackerras
2006-05-05  9:12     ` Arnd Bergmann
2006-04-29 23:28 ` Arnd Bergmann [this message]
2006-04-29 23:28 ` [PATCH 09/13] spufs: add a phys-id attribute to each SPU context Arnd Bergmann
2006-04-29 23:28 ` [PATCH 11/13] cell: split out board specific files Arnd Bergmann
2006-04-30  2:52   ` Segher Boessenkool
2006-05-01 22:51     ` Geoff Levand
2006-05-01 23:09       ` Segher Boessenkool
2006-05-01 23:49         ` [Cbe-oss-dev] " Arnd Bergmann
2006-05-01 23:50       ` Arnd Bergmann
2006-05-02  0:06         ` Segher Boessenkool
2006-05-02 10:59           ` Arnd Bergmann
2006-05-02 23:38             ` Segher Boessenkool
2006-05-03  0:18               ` Arnd Bergmann
2006-05-03  2:46               ` Paul Mackerras
2006-05-03  6:28                 ` Segher Boessenkool
2006-05-04  2:03                   ` Benjamin Herrenschmidt
2006-05-02 18:20         ` Geoff Levand
2006-05-02 18:30           ` Arnd Bergmann
2006-05-02  0:13       ` Michael Ellerman
2006-05-02 18:20         ` [Cbe-oss-dev] [PATCH 11/13] cell: split out board specificfil es Geoff Levand
2006-05-02 13:45       ` [PATCH 11/13] cell: split out board specific files Christoph Hellwig
2006-04-29 23:28 ` [PATCH 12/13] cell: abstract priviledge-1 SPU registers for hypervisors Arnd Bergmann
2006-04-29 23:28 ` [PATCH 13/13] cell: set SPU interrupt affinity in spu_priv1 code Arnd Bergmann
2006-04-29 23:42 ` [PATCH 10/13] cell: correctly detect systemsim host Arnd Bergmann

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=20060429233921.357349000@localhost.localdomain \
    --to=arnd@arndb.de \
    --cc=arnd.bergmann@de.ibm.com \
    --cc=cbe-oss-dev@ozlabs.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=paulus@samba.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).