[PATCH v3 25/31] powerpc/mm: Convert 4k insert from asm to C
Aneesh Kumar K.V
aneesh.kumar at linux.vnet.ibm.com
Tue Oct 13 05:40:09 AEDT 2015
This is similar to 64K insert. May be we want to consolidate
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.vnet.ibm.com>
---
arch/powerpc/mm/Makefile | 6 +-
arch/powerpc/mm/hash64_4k.c | 139 +++++++++++++++++
arch/powerpc/mm/hash_low_64.S | 331 ----------------------------------------
arch/powerpc/mm/hash_utils_64.c | 26 ----
4 files changed, 142 insertions(+), 360 deletions(-)
create mode 100644 arch/powerpc/mm/hash64_4k.c
delete mode 100644 arch/powerpc/mm/hash_low_64.S
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index f80ad1a76cc8..1ffeda85c086 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -14,11 +14,11 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \
obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(CONFIG_WORD_SIZE)e.o
hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o
obj-$(CONFIG_PPC_STD_MMU_64) += hash_utils_64.o slb_low.o slb.o $(hash64-y)
-obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o
-obj-$(CONFIG_PPC_STD_MMU) += hash_low_$(CONFIG_WORD_SIZE).o \
- tlb_hash$(CONFIG_WORD_SIZE).o \
+obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o
+obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(CONFIG_WORD_SIZE).o \
mmu_context_hash$(CONFIG_WORD_SIZE).o
ifeq ($(CONFIG_PPC_STD_MMU_64),y)
+obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o
obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o
endif
obj-$(CONFIG_PPC_ICSWX) += icswx.o
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
new file mode 100644
index 000000000000..3b49c6f18741
--- /dev/null
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright IBM Corporation, 2015
+ * Author Aneesh Kumar K.V <aneesh.kumar at linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/mm.h>
+#include <asm/machdep.h>
+#include <asm/mmu.h>
+
+int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
+ pte_t *ptep, unsigned long trap, unsigned long flags,
+ int ssize, int subpg_prot)
+{
+ unsigned long hpte_group;
+ unsigned long rflags, pa;
+ unsigned long old_pte, new_pte;
+ unsigned long vpn, hash, slot;
+ unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift;
+
+ /*
+ * atomically mark the linux large page PTE busy and dirty
+ */
+ do {
+ pte_t pte = READ_ONCE(*ptep);
+
+ old_pte = pte_val(pte);
+ /* If PTE busy, retry the access */
+ if (unlikely(old_pte & _PAGE_BUSY))
+ return 0;
+ /* If PTE permissions don't match, take page fault */
+ if (unlikely(access & ~old_pte))
+ return 1;
+ /*
+ * Try to lock the PTE, add ACCESSED and DIRTY if it was
+ * a write access. Since this is 4K insert of 64K page size
+ * also add _PAGE_COMBO
+ */
+ new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE;
+ if (access & _PAGE_RW)
+ new_pte |= _PAGE_DIRTY;
+ } while (old_pte != __cmpxchg_u64((unsigned long *)ptep,
+ old_pte, new_pte));
+ /*
+ * PP bits. _PAGE_USER is already PP bit 0x2, so we only
+ * need to add in 0x1 if it's a read-only user page
+ */
+ rflags = new_pte & _PAGE_USER;
+ if ((new_pte & _PAGE_USER) && !((new_pte & _PAGE_RW) &&
+ (new_pte & _PAGE_DIRTY)))
+ rflags |= 0x1;
+ /*
+ * _PAGE_EXEC -> HW_NO_EXEC since it's inverted
+ */
+ rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
+ /*
+ * Always add C and Memory coherence bit
+ */
+ rflags |= HPTE_R_C | HPTE_R_M;
+ /*
+ * Add in WIMG bits
+ */
+ rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
+ _PAGE_COHERENT | _PAGE_GUARDED));
+
+ if (!cpu_has_feature(CPU_FTR_NOEXECUTE) &&
+ !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
+ rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
+
+ vpn = hpt_vpn(ea, vsid, ssize);
+ if (unlikely(old_pte & _PAGE_HASHPTE)) {
+ /*
+ * There MIGHT be an HPTE for this pte
+ */
+ hash = hpt_hash(vpn, shift, ssize);
+ if (old_pte & _PAGE_F_SECOND)
+ hash = ~hash;
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += (old_pte & _PAGE_F_GIX) >> _PAGE_F_GIX_SHIFT;
+
+ if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
+ MMU_PAGE_4K, ssize, flags) == -1)
+ old_pte &= ~_PAGE_HPTEFLAGS;
+ }
+
+ if (likely(!(old_pte & _PAGE_HASHPTE))) {
+
+ pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
+ hash = hpt_hash(vpn, shift, ssize);
+
+repeat:
+ hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
+
+ /* Insert into the hash table, primary slot */
+ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+ MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+ /*
+ * Primary is full, try the secondary
+ */
+ if (unlikely(slot == -1)) {
+ hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
+ slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
+ rflags, HPTE_V_SECONDARY,
+ MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+ if (slot == -1) {
+ if (mftb() & 0x1)
+ hpte_group = ((hash & htab_hash_mask) *
+ HPTES_PER_GROUP) & ~0x7UL;
+ ppc_md.hpte_remove(hpte_group);
+ /*
+ * FIXME!! Should be try the group from which we removed ?
+ */
+ goto repeat;
+ }
+ }
+ /*
+ * Hypervisor failure. Restore old pmd and return -1
+ * similar to __hash_page_*
+ */
+ if (unlikely(slot == -2)) {
+ *ptep = __pte(old_pte);
+ hash_failure_debug(ea, access, vsid, trap, ssize,
+ MMU_PAGE_4K, MMU_PAGE_4K, old_pte);
+ return -1;
+ }
+ new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+ new_pte |= (slot << _PAGE_F_GIX_SHIFT) & (_PAGE_F_SECOND | _PAGE_F_GIX);
+ }
+ *ptep = __pte(new_pte & ~_PAGE_BUSY);
+ return 0;
+}
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
deleted file mode 100644
index f7d49cf0ccb7..000000000000
--- a/arch/powerpc/mm/hash_low_64.S
+++ /dev/null
@@ -1,331 +0,0 @@
-/*
- * ppc64 MMU hashtable management routines
- *
- * (c) Copyright IBM Corp. 2003, 2005
- *
- * Maintained by: Benjamin Herrenschmidt
- * <benh at kernel.crashing.org>
- *
- * This file is covered by the GNU Public Licence v2 as
- * described in the kernel's COPYING file.
- */
-
-#include <asm/reg.h>
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/page.h>
-#include <asm/types.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/cputable.h>
-
- .text
-
-/*
- * Stackframe:
- *
- * +-> Back chain (SP + 256)
- * | General register save area (SP + 112)
- * | Parameter save area (SP + 48)
- * | TOC save area (SP + 40)
- * | link editor doubleword (SP + 32)
- * | compiler doubleword (SP + 24)
- * | LR save area (SP + 16)
- * | CR save area (SP + 8)
- * SP ---> +-- Back chain (SP + 0)
- */
-
-#ifndef CONFIG_PPC_64K_PAGES
-
-/*****************************************************************************
- * *
- * 4K SW & 4K HW pages implementation *
- * *
- *****************************************************************************/
-
-
-/*
- * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- * pte_t *ptep, unsigned long trap, unsigned long flags,
- * int ssize)
- *
- * Adds a 4K page to the hash table in a segment of 4K pages only
- */
-
-_GLOBAL(__hash_page_4K)
- mflr r0
- std r0,16(r1)
- stdu r1,-STACKFRAMESIZE(r1)
- /* Save all params that we need after a function call */
- std r6,STK_PARAM(R6)(r1)
- std r8,STK_PARAM(R8)(r1)
- std r9,STK_PARAM(R9)(r1)
-
- /* Save non-volatile registers.
- * r31 will hold "old PTE"
- * r30 is "new PTE"
- * r29 is vpn
- * r28 is a hash value
- * r27 is hashtab mask (maybe dynamic patched instead ?)
- */
- std r27,STK_REG(R27)(r1)
- std r28,STK_REG(R28)(r1)
- std r29,STK_REG(R29)(r1)
- std r30,STK_REG(R30)(r1)
- std r31,STK_REG(R31)(r1)
-
- /* Step 1:
- *
- * Check permissions, atomically mark the linux PTE busy
- * and hashed.
- */
-1:
- ldarx r31,0,r6
- /* Check access rights (access & ~(pte_val(*ptep))) */
- andc. r0,r4,r31
- bne- htab_wrong_access
- /* Check if PTE is busy */
- andi. r0,r31,_PAGE_BUSY
- /* If so, just bail out and refault if needed. Someone else
- * is changing this PTE anyway and might hash it.
- */
- bne- htab_bail_ok
-
- /* Prepare new PTE value (turn access RW into DIRTY, then
- * add BUSY,HASHPTE and ACCESSED)
- */
- rlwinm r30,r4,32-9+7,31-7,31-7 /* _PAGE_RW -> _PAGE_DIRTY */
- or r30,r30,r31
- ori r30,r30,_PAGE_BUSY | _PAGE_ACCESSED | _PAGE_HASHPTE
- /* Write the linux PTE atomically (setting busy) */
- stdcx. r30,0,r6
- bne- 1b
- isync
-
- /* Step 2:
- *
- * Insert/Update the HPTE in the hash table. At this point,
- * r4 (access) is re-useable, we use it for the new HPTE flags
- */
-
-BEGIN_FTR_SECTION
- cmpdi r9,0 /* check segment size */
- bne 3f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc vpn and put it in r29 */
- sldi r29,r5,SID_SHIFT - VPN_SHIFT
- rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
- or r29,r28,r29
- /*
- * Calculate hash value for primary slot and store it in r28
- * r3 = va, r5 = vsid
- * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
- */
- rldicl r0,r3,64-12,48
- xor r28,r5,r0 /* hash */
- b 4f
-
-3: /* Calc vpn and put it in r29 */
- sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
- rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
- or r29,r28,r29
-
- /*
- * calculate hash value for primary slot and
- * store it in r28 for 1T segment
- * r3 = va, r5 = vsid
- */
- sldi r28,r5,25 /* vsid << 25 */
- /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */
- rldicl r0,r3,64-12,36
- xor r28,r28,r5 /* vsid ^ ( vsid << 25) */
- xor r28,r28,r0 /* hash */
-
- /* Convert linux PTE bits into HW equivalents */
-4: andi. r3,r30,0x1fe /* Get basic set of flags */
- xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */
- rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */
- rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */
- and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/
- andc r0,r30,r0 /* r0 = pte & ~r0 */
- rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */
- /*
- * Always add "C" bit for perf. Memory coherence is always enabled
- */
- ori r3,r3,HPTE_R_C | HPTE_R_M
-
- /* We eventually do the icache sync here (maybe inline that
- * code rather than call a C function...)
- */
-BEGIN_FTR_SECTION
- mr r4,r30
- mr r5,r7
- bl hash_page_do_lazy_icache
-END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
-
- /* At this point, r3 contains new PP bits, save them in
- * place of "access" in the param area (sic)
- */
- std r3,STK_PARAM(R4)(r1)
-
- /* Get htab_hash_mask */
- ld r4,htab_hash_mask at got(2)
- ld r27,0(r4) /* htab_hash_mask -> r27 */
-
- /* Check if we may already be in the hashtable, in this case, we
- * go to out-of-line code to try to modify the HPTE
- */
- andi. r0,r31,_PAGE_HASHPTE
- bne htab_modify_pte
-
-htab_insert_pte:
- /* Clear hpte bits in new pte (we also clear BUSY btw) and
- * add _PAGE_HASHPTE
- */
- lis r0,_PAGE_HPTEFLAGS at h
- ori r0,r0,_PAGE_HPTEFLAGS at l
- andc r30,r30,r0
- ori r30,r30,_PAGE_HASHPTE
-
- /* physical address r5 */
- rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT
- sldi r5,r5,PAGE_SHIFT
-
- /* Calculate primary group hash */
- and r0,r28,r27
- rldicr r3,r0,3,63-3 /* r3 = (hash & mask) << 3 */
-
- /* Call ppc_md.hpte_insert */
- ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve vpn */
- li r7,0 /* !bolted, !secondary */
- li r8,MMU_PAGE_4K /* page size */
- li r9,MMU_PAGE_4K /* actual page size */
- ld r10,STK_PARAM(R9)(r1) /* segment size */
-.globl htab_call_hpte_insert1
-htab_call_hpte_insert1:
- bl . /* Patched by htab_finish_init() */
- cmpdi 0,r3,0
- bge htab_pte_insert_ok /* Insertion successful */
- cmpdi 0,r3,-2 /* Critical failure */
- beq- htab_pte_insert_failure
-
- /* Now try secondary slot */
-
- /* physical address r5 */
- rldicl r5,r31,64-PTE_RPN_SHIFT,PTE_RPN_SHIFT
- sldi r5,r5,PAGE_SHIFT
-
- /* Calculate secondary group hash */
- andc r0,r27,r28
- rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */
-
- /* Call ppc_md.hpte_insert */
- ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve vpn */
- li r7,HPTE_V_SECONDARY /* !bolted, secondary */
- li r8,MMU_PAGE_4K /* page size */
- li r9,MMU_PAGE_4K /* actual page size */
- ld r10,STK_PARAM(R9)(r1) /* segment size */
-.globl htab_call_hpte_insert2
-htab_call_hpte_insert2:
- bl . /* Patched by htab_finish_init() */
- cmpdi 0,r3,0
- bge+ htab_pte_insert_ok /* Insertion successful */
- cmpdi 0,r3,-2 /* Critical failure */
- beq- htab_pte_insert_failure
-
- /* Both are full, we need to evict something */
- mftb r0
- /* Pick a random group based on TB */
- andi. r0,r0,1
- mr r5,r28
- bne 2f
- not r5,r5
-2: and r0,r5,r27
- rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
- /* Call ppc_md.hpte_remove */
-.globl htab_call_hpte_remove
-htab_call_hpte_remove:
- bl . /* Patched by htab_finish_init() */
-
- /* Try all again */
- b htab_insert_pte
-
-htab_bail_ok:
- li r3,0
- b htab_bail
-
-htab_pte_insert_ok:
- /* Insert slot number & secondary bit in PTE */
- rldimi r30,r3,12,63-15
-
- /* Write out the PTE with a normal write
- * (maybe add eieio may be good still ?)
- */
-htab_write_out_pte:
- ld r6,STK_PARAM(R6)(r1)
- std r30,0(r6)
- li r3, 0
-htab_bail:
- ld r27,STK_REG(R27)(r1)
- ld r28,STK_REG(R28)(r1)
- ld r29,STK_REG(R29)(r1)
- ld r30,STK_REG(R30)(r1)
- ld r31,STK_REG(R31)(r1)
- addi r1,r1,STACKFRAMESIZE
- ld r0,16(r1)
- mtlr r0
- blr
-
-htab_modify_pte:
- /* Keep PP bits in r4 and slot idx from the PTE around in r3 */
- mr r4,r3
- rlwinm r3,r31,32-12,29,31
-
- /* Secondary group ? if yes, get a inverted hash value */
- mr r5,r28
- andi. r0,r31,_PAGE_F_SECOND
- beq 1f
- not r5,r5
-1:
- /* Calculate proper slot value for ppc_md.hpte_updatepp */
- and r0,r5,r27
- rldicr r0,r0,3,63-3 /* r0 = (hash & mask) << 3 */
- add r3,r0,r3 /* add slot idx */
-
- /* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* vpn */
- li r6,MMU_PAGE_4K /* base page size */
- li r7,MMU_PAGE_4K /* actual page size */
- ld r8,STK_PARAM(R9)(r1) /* segment size */
- ld r9,STK_PARAM(R8)(r1) /* get "flags" param */
-.globl htab_call_hpte_updatepp
-htab_call_hpte_updatepp:
- bl . /* Patched by htab_finish_init() */
-
- /* if we failed because typically the HPTE wasn't really here
- * we try an insertion.
- */
- cmpdi 0,r3,-1
- beq- htab_insert_pte
-
- /* Clear the BUSY bit and Write out the PTE */
- li r0,_PAGE_BUSY
- andc r30,r30,r0
- b htab_write_out_pte
-
-htab_wrong_access:
- /* Bail out clearing reservation */
- stdcx. r31,0,r6
- li r3,1
- b htab_bail
-
-htab_pte_insert_failure:
- /* Bail out restoring old PTE */
- ld r6,STK_PARAM(R6)(r1)
- std r31,0(r6)
- li r3,-1
- b htab_bail
-
-#endif
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d890580a4c87..db35e7d83088 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -629,31 +629,6 @@ int remove_section_mapping(unsigned long start, unsigned long end)
}
#endif /* CONFIG_MEMORY_HOTPLUG */
-extern u32 htab_call_hpte_insert1[];
-extern u32 htab_call_hpte_insert2[];
-extern u32 htab_call_hpte_remove[];
-extern u32 htab_call_hpte_updatepp[];
-
-static void __init htab_finish_init(void)
-{
-
-#ifdef CONFIG_PPC_4K_PAGES
- patch_branch(htab_call_hpte_insert1,
- ppc_function_entry(ppc_md.hpte_insert),
- BRANCH_SET_LINK);
- patch_branch(htab_call_hpte_insert2,
- ppc_function_entry(ppc_md.hpte_insert),
- BRANCH_SET_LINK);
- patch_branch(htab_call_hpte_remove,
- ppc_function_entry(ppc_md.hpte_remove),
- BRANCH_SET_LINK);
- patch_branch(htab_call_hpte_updatepp,
- ppc_function_entry(ppc_md.hpte_updatepp),
- BRANCH_SET_LINK);
-#endif
-
-}
-
static void __init htab_initialize(void)
{
unsigned long table;
@@ -800,7 +775,6 @@ static void __init htab_initialize(void)
mmu_linear_psize, mmu_kernel_ssize));
}
- htab_finish_init();
DBG(" <- htab_initialize()\n");
}
--
2.5.0
More information about the Linuxppc-dev
mailing list