[PATCH] Fix bug in ppc64 dynamic hugepage support
In adjusting the logic for SLB miss for the dynamic hugepage stuff, I messed up the !CONFIG_HUGETLB_PAGE case, failing to set the SLB flags properly. This fixes it. It also streamlines the logic for the HUGETLB_PAGE case (removing a couple of branches) while we're at it. Booted, and roughly tested on POWER5 (with and without HUGETLB_PAGE), iSeries/RS64 (no hugepage available), and G5 (with and without HUGETLB_PAGE). Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
Родитель
7eaa414ee8
Коммит
319e76a1ae
|
@ -97,25 +97,21 @@ BEGIN_FTR_SECTION
|
|||
lhz r9,PACAHIGHHTLBAREAS(r13)
|
||||
srdi r11,r3,(HTLB_AREA_SHIFT-SID_SHIFT)
|
||||
srd r9,r9,r11
|
||||
andi. r9,r9,1
|
||||
bne 5f
|
||||
|
||||
li r11,SLB_VSID_USER
|
||||
|
||||
cmpldi r3,16
|
||||
bge 6f
|
||||
|
||||
lhz r9,PACALOWHTLBAREAS(r13)
|
||||
srd r9,r9,r3
|
||||
andi. r9,r9,1
|
||||
|
||||
beq 6f
|
||||
|
||||
5: li r11,SLB_VSID_USER|SLB_VSID_L
|
||||
lhz r11,PACALOWHTLBAREAS(r13)
|
||||
srd r11,r11,r3
|
||||
or r9,r9,r11
|
||||
END_FTR_SECTION_IFSET(CPU_FTR_16M_PAGE)
|
||||
#endif /* CONFIG_HUGETLB_PAGE */
|
||||
|
||||
6: ld r9,PACACONTEXTID(r13)
|
||||
li r11,SLB_VSID_USER
|
||||
|
||||
#ifdef CONFIG_HUGETLB_PAGE
|
||||
BEGIN_FTR_SECTION
|
||||
rldimi r11,r9,8,55 /* shift masked bit into SLB_VSID_L */
|
||||
END_FTR_SECTION_IFSET(CPU_FTR_16M_PAGE)
|
||||
#endif /* CONFIG_HUGETLB_PAGE */
|
||||
|
||||
ld r9,PACACONTEXTID(r13)
|
||||
rldimi r3,r9,USER_ESID_BITS,0
|
||||
|
||||
9: /* r3 = protovsid, r11 = flags, r10 = esid_data, cr7 = <>KERNELBASE */
|
||||
|
|
Загрузка…
Ссылка в новой задаче