[PATCH 7/7] [RFC] SMP support code
Eric Van Hensbergen
ericvh at gmail.com
Thu May 19 07:24:55 EST 2011
This patch adds the necessary core code to enable SMP support on BlueGene/P
Signed-off-by: Eric Van Hensbergen <ericvh at gmail.com>
---
arch/powerpc/kernel/head_44x.S | 72 +++++++++++++++++++++++++++++
arch/powerpc/mm/fault.c | 77 ++++++++++++++++++++++++++++++++
arch/powerpc/platforms/Kconfig.cputype | 2 +-
3 files changed, 150 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 1f7ae60..57d4483 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1133,6 +1133,70 @@ clear_utlb_entry:
#endif /* CONFIG_PPC_47x */
+#if defined(CONFIG_BGP) && defined(CONFIG_SMP)
+_GLOBAL(start_secondary_bgp)
+ /* U2 will be enabled in TLBs. */
+ lis r7,PPC44x_MMUCR_U2 at h
+ mtspr SPRN_MMUCR,r7
+ li r7,0
+ mtspr SPRN_PID,r7
+ sync
+ lis r8,KERNELBASE at h
+
+ /* The tlb_44x_hwater global var (setup by cpu#0) reveals how many
+ * 256M TLBs we need to map.
+ */
+ lis r9, tlb_44x_hwater at ha
+ lwz r9, tlb_44x_hwater at l(r9)
+
+ li r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | \
+ PPC44x_TLB_M|PPC44x_TLB_U2)
+ oris r5, r5, PPC44x_TLB_WL1 at h
+
+ /* tlb_44x_hwater is the biggest TLB slot number for regular TLBs.
+ TLB 63 covers kernel base mapping(256MB) and TLB 62 covers CNS.
+ With 768MB lowmem, it is set to 59.
+ */
+2:
+ addi r9, r9, 1
+ cmpwi r9,62 /* Stop at entry 62 which is the fw */
+ beq 3f
+ addis r7,r7,0x1000 /* add 256M */
+ addis r8,r8,0x1000
+ ori r6,r8,PPC44x_TLB_VALID | PPC44x_TLB_256M
+
+ tlbwe r6,r9,PPC44x_TLB_PAGEID /* Load the pageid fields */
+ tlbwe r7,r9,PPC44x_TLB_XLAT /* Load the translation fields */
+ tlbwe r5,r9,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */
+ b 2b
+
+3: isync
+
+ /* Setup context from global var secondary_ti */
+ lis r1, secondary_ti at ha
+ lwz r1, secondary_ti at l(r1)
+ lwz r2, TI_TASK(r1) /* r2 = task_info */
+
+ addi r3,r2,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG3,r3
+
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+
+ /* Let's move on */
+ lis r4,start_secondary at h
+ ori r4,r4,start_secondary at l
+ lis r3,MSR_KERNEL at h
+ ori r3,r3,MSR_KERNEL at l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi /* change context and jump to start_secondary */
+
+_GLOBAL(start_secondary_resume)
+ /* I don't think this currently happens on BGP */
+ b .
+#endif /* CONFIG_BGP && CONFIG_SMP */
+
/*
* Here we are back to code that is common between 44x and 47x
*
@@ -1144,6 +1208,14 @@ head_start_common:
lis r4,interrupt_base at h /* IVPR only uses the high 16-bits */
mtspr SPRN_IVPR,r4
+#if defined(CONFIG_BGP) && defined(CONFIG_SMP)
+ /* are we an additional CPU */
+ li r0, 0
+ mfspr r4, SPRN_PIR
+ cmpw r4, r0
+ bgt start_secondary_bgp
+#endif /* CONFIG_BGP && CONFIG_SMP */
+
addis r22,r22,KERNELBASE at h
mtlr r22
isync
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 54f4fb9..0e73244 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -103,6 +103,77 @@ static int store_updates_sp(struct pt_regs *regs)
return 0;
}
+#ifdef CONFIG_BGP
+/*
+ * The icbi instruction does not broadcast to all cpus in the ppc450
+ * processor used by Blue Gene/P. It is unlikely this problem will
+ * be exhibited in other processors so this remains ifdef'ed for BGP
+ * specifically.
+ *
+ * We deal with this by marking executable pages either writable, or
+ * executable, but never both. The permissions will fault back and
+ * forth if the thread is actively writing to executable sections.
+ * Each time we fault to become executable we flush the dcache into
+ * icache on all cpus.
+ */
+struct bgp_fixup_parm {
+ struct page *page;
+ unsigned long address;
+ struct vm_area_struct *vma;
+};
+
+static void bgp_fixup_cache_tlb(void *parm)
+{
+ struct bgp_fixup_parm *p = parm;
+
+ if (!PageHighMem(p->page))
+ flush_dcache_icache_page(p->page);
+ local_flush_tlb_page(p->vma, p->address);
+}
+
+static void bgp_fixup_access_perms(struct vm_area_struct *vma,
+ unsigned long address,
+ int is_write, int is_exec)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pte_t *ptep = NULL;
+ pmd_t *pmdp;
+
+ if (get_pteptr(mm, address, &ptep, &pmdp)) {
+ spinlock_t *ptl = pte_lockptr(mm, pmdp);
+ pte_t old;
+
+ spin_lock(ptl);
+ old = *ptep;
+ if (pte_present(old)) {
+ struct page *page = pte_page(old);
+
+ if (is_exec) {
+ struct bgp_fixup_parm param = {
+ .page = page,
+ .address = address,
+ .vma = vma,
+ };
+ pte_update(ptep, _PAGE_HWWRITE, 0);
+ on_each_cpu(bgp_fixup_cache_tlb, ¶m, 1);
+ pte_update(ptep, 0, _PAGE_EXEC);
+ pte_unmap_unlock(ptep, ptl);
+ return;
+ }
+ if (is_write &&
+ (pte_val(old) & _PAGE_RW) &&
+ (pte_val(old) & _PAGE_DIRTY) &&
+ !(pte_val(old) & _PAGE_HWWRITE)) {
+ pte_update(ptep, _PAGE_EXEC, _PAGE_HWWRITE);
+ }
+ }
+ if (!pte_same(old, *ptep))
+ flush_tlb_page(vma, address);
+ pte_unmap_unlock(ptep, ptl);
+ }
+}
+#endif /* CONFIG_BGP */
+
/*
* For 600- and 800-family processors, the error_code parameter is DSISR
* for a data fault, SRR1 for an instruction fault. For 400-family processors
@@ -333,6 +404,12 @@ good_area:
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
regs, address);
}
+
+#ifdef CONFIG_BGP
+ /* Fixup _PAGE_EXEC and _PAGE_HWWRITE if necessary */
+ bgp_fixup_access_perms(vma, address, is_write, is_exec);
+#endif /* CONFIG_BGP */
+
up_read(&mm->mmap_sem);
return 0;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 3a3c711..b77a25f 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -300,7 +300,7 @@ config PPC_PERF_CTRS
This enables the powerpc-specific perf_event back-end.
config SMP
- depends on PPC_BOOK3S || PPC_BOOK3E || FSL_BOOKE || PPC_47x
+ depends on PPC_BOOK3S || PPC_BOOK3E || FSL_BOOKE || PPC_47x || BGP
bool "Symmetric multi-processing support"
---help---
This enables support for systems with more than one CPU. If you have
--
1.7.4.1
More information about the Linuxppc-dev
mailing list