* [PATCH 1/2 V2] powerpc: Move opcode definitions from kvm/emulate.c to asm/ppc-opcode.h
From: Jia Hongtao @ 2013-04-28 5:20 UTC (permalink / raw)
To: linuxppc-dev, galak, B07421, segher; +Cc: hongtao.jia
Opcode and xopcode are useful definitions not just for KVM. Move these
definitions to asm/ppc-opcode.h for public use.
Signed-off-by: Jia Hongtao <hongtao.jia@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
---
V2:
* Add LHAUX definition.
arch/powerpc/include/asm/ppc-opcode.h | 46 +++++++++++++++++++++++++++++++++++
arch/powerpc/kvm/emulate.c | 44 +--------------------------------
2 files changed, 47 insertions(+), 43 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 8752bc8..79057f7 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -81,6 +81,52 @@
#define __REGA0_R30 30
#define __REGA0_R31 31
+/* opcode and xopcode for instructions */
+#define OP_TRAP 3
+#define OP_TRAP_64 2
+
+#define OP_31_XOP_TRAP 4
+#define OP_31_XOP_LWZX 23
+#define OP_31_XOP_LWZUX 55
+#define OP_31_XOP_TRAP_64 68
+#define OP_31_XOP_DCBF 86
+#define OP_31_XOP_LBZX 87
+#define OP_31_XOP_STWX 151
+#define OP_31_XOP_STBX 215
+#define OP_31_XOP_LBZUX 119
+#define OP_31_XOP_STBUX 247
+#define OP_31_XOP_LHZX 279
+#define OP_31_XOP_LHZUX 311
+#define OP_31_XOP_MFSPR 339
+#define OP_31_XOP_LHAX 343
+#define OP_31_XOP_LHAUX 375
+#define OP_31_XOP_STHX 407
+#define OP_31_XOP_STHUX 439
+#define OP_31_XOP_MTSPR 467
+#define OP_31_XOP_DCBI 470
+#define OP_31_XOP_LWBRX 534
+#define OP_31_XOP_TLBSYNC 566
+#define OP_31_XOP_STWBRX 662
+#define OP_31_XOP_LHBRX 790
+#define OP_31_XOP_STHBRX 918
+
+#define OP_LWZ 32
+#define OP_LD 58
+#define OP_LWZU 33
+#define OP_LBZ 34
+#define OP_LBZU 35
+#define OP_STW 36
+#define OP_STWU 37
+#define OP_STD 62
+#define OP_STB 38
+#define OP_STBU 39
+#define OP_LHZ 40
+#define OP_LHZU 41
+#define OP_LHA 42
+#define OP_LHAU 43
+#define OP_STH 44
+#define OP_STHU 45
+
/* sorted alphabetically */
#define PPC_INST_DCBA 0x7c0005ec
#define PPC_INST_DCBA_MASK 0xfc0007fe
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 7a73b6f..426d3f5 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -30,52 +30,10 @@
#include <asm/byteorder.h>
#include <asm/kvm_ppc.h>
#include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
#include "timing.h"
#include "trace.h"
-#define OP_TRAP 3
-#define OP_TRAP_64 2
-
-#define OP_31_XOP_TRAP 4
-#define OP_31_XOP_LWZX 23
-#define OP_31_XOP_TRAP_64 68
-#define OP_31_XOP_DCBF 86
-#define OP_31_XOP_LBZX 87
-#define OP_31_XOP_STWX 151
-#define OP_31_XOP_STBX 215
-#define OP_31_XOP_LBZUX 119
-#define OP_31_XOP_STBUX 247
-#define OP_31_XOP_LHZX 279
-#define OP_31_XOP_LHZUX 311
-#define OP_31_XOP_MFSPR 339
-#define OP_31_XOP_LHAX 343
-#define OP_31_XOP_STHX 407
-#define OP_31_XOP_STHUX 439
-#define OP_31_XOP_MTSPR 467
-#define OP_31_XOP_DCBI 470
-#define OP_31_XOP_LWBRX 534
-#define OP_31_XOP_TLBSYNC 566
-#define OP_31_XOP_STWBRX 662
-#define OP_31_XOP_LHBRX 790
-#define OP_31_XOP_STHBRX 918
-
-#define OP_LWZ 32
-#define OP_LD 58
-#define OP_LWZU 33
-#define OP_LBZ 34
-#define OP_LBZU 35
-#define OP_STW 36
-#define OP_STWU 37
-#define OP_STD 62
-#define OP_STB 38
-#define OP_STBU 39
-#define OP_LHZ 40
-#define OP_LHZU 41
-#define OP_LHA 42
-#define OP_LHAU 43
-#define OP_STH 44
-#define OP_STHU 45
-
void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
{
unsigned long dec_nsec;
--
1.8.0
^ permalink raw reply related
* [PATCH 2/2 V8] powerpc/85xx: Add machine check handler to fix PCIe erratum on mpc85xx
From: Jia Hongtao @ 2013-04-28 5:20 UTC (permalink / raw)
To: linuxppc-dev, galak, B07421, segher; +Cc: hongtao.jia
In-Reply-To: <1367126408-12997-1-git-send-email-hongtao.jia@freescale.com>
A PCIe erratum of mpc85xx may causes a core hang when a link of PCIe
goes down. when the link goes down, Non-posted transactions issued
via the ATMU requiring completion result in an instruction stall.
At the same time a machine-check exception is generated to the core
to allow further processing by the handler. We implements the handler
which skips the instruction caused the stall.
This patch depends on patch:
powerpc/85xx: Add platform_device declaration to fsl_pci.h
Signed-off-by: Zhao Chenhui <b35336@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Liu Shuo <soniccat.liu@gmail.com>
Signed-off-by: Jia Hongtao <hongtao.jia@freescale.com>
---
V8:
* Add A variant load instruction emulation.
V7:
* Correct PCIe checking method (Using indirect_type member of pci_controller
stucture).
V6:
* Move OP and XOP defines to a new header file: asm/ppc-disassemble.h
* Add X UX BRX variant of load instruction emulation
* Remove A variant of load instruction emulation
V5:
* Fill rd with all-Fs if the skipped instruction is load and emulate the
instruction.
* Let KVM/QEMU deal with the exception if the machine check comes from KVM.
arch/powerpc/kernel/cpu_setup_fsl_booke.S | 2 +-
arch/powerpc/kernel/traps.c | 3 +
arch/powerpc/sysdev/fsl_pci.c | 158 ++++++++++++++++++++++++++++++
arch/powerpc/sysdev/fsl_pci.h | 6 ++
4 files changed, 168 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 0b9af01..bfb18c7 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -75,7 +75,7 @@ _GLOBAL(__setup_cpu_e500v2)
bl __e500_icache_setup
bl __e500_dcache_setup
bl __setup_e500_ivors
-#ifdef CONFIG_FSL_RIO
+#if defined(CONFIG_FSL_RIO) || defined(CONFIG_FSL_PCI)
/* Ensure that RFXE is set */
mfspr r3,SPRN_HID1
oris r3,r3,HID1_RFXE@h
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 37cc40e..d15cfb5 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -60,6 +60,7 @@
#include <asm/switch_to.h>
#include <asm/tm.h>
#include <asm/debug.h>
+#include <sysdev/fsl_pci.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -565,6 +566,8 @@ int machine_check_e500(struct pt_regs *regs)
if (reason & MCSR_BUS_RBERR) {
if (fsl_rio_mcheck_exception(regs))
return 1;
+ if (fsl_pci_mcheck_exception(regs))
+ return 1;
}
printk("Machine check in kernel mode.\n");
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 40ffe29..5fa851a 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -26,11 +26,15 @@
#include <linux/memblock.h>
#include <linux/log2.h>
#include <linux/slab.h>
+#include <linux/uaccess.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
#include <asm/machdep.h>
+#include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
#include <sysdev/fsl_soc.h>
#include <sysdev/fsl_pci.h>
@@ -876,6 +880,160 @@ u64 fsl_pci_immrbar_base(struct pci_controller *hose)
return 0;
}
+#ifdef CONFIG_E500
+static int mcheck_handle_load(struct pt_regs *regs, u32 inst)
+{
+ unsigned int rd, ra, rb, d;
+
+ rd = get_rt(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+ d = get_d(inst);
+
+ switch (get_op(inst)) {
+ case 31:
+ switch (get_xop(inst)) {
+ case OP_31_XOP_LWZX:
+ case OP_31_XOP_LWBRX:
+ regs->gpr[rd] = 0xffffffff;
+ break;
+
+ case OP_31_XOP_LWZUX:
+ regs->gpr[rd] = 0xffffffff;
+ regs->gpr[ra] += regs->gpr[rb];
+ break;
+
+ case OP_31_XOP_LBZX:
+ regs->gpr[rd] = 0xff;
+ break;
+
+ case OP_31_XOP_LBZUX:
+ regs->gpr[rd] = 0xff;
+ regs->gpr[ra] += regs->gpr[rb];
+ break;
+
+ case OP_31_XOP_LHZX:
+ case OP_31_XOP_LHBRX:
+ regs->gpr[rd] = 0xffff;
+ break;
+
+ case OP_31_XOP_LHZUX:
+ regs->gpr[rd] = 0xffff;
+ regs->gpr[ra] += regs->gpr[rb];
+ break;
+
+ case OP_31_XOP_LHAX:
+ regs->gpr[rd] = ~0UL;
+ break;
+
+ case OP_31_XOP_LHAUX:
+ regs->gpr[rd] = ~0UL;
+ regs->gpr[ra] += regs->gpr[rb];
+ break;
+
+ default:
+ return 0;
+ }
+ break;
+
+ case OP_LWZ:
+ regs->gpr[rd] = 0xffffffff;
+ break;
+
+ case OP_LWZU:
+ regs->gpr[rd] = 0xffffffff;
+ regs->gpr[ra] += (s16)d;
+ break;
+
+ case OP_LBZ:
+ regs->gpr[rd] = 0xff;
+ break;
+
+ case OP_LBZU:
+ regs->gpr[rd] = 0xff;
+ regs->gpr[ra] += (s16)d;
+ break;
+
+ case OP_LHZ:
+ regs->gpr[rd] = 0xffff;
+ break;
+
+ case OP_LHZU:
+ regs->gpr[rd] = 0xffff;
+ regs->gpr[ra] += (s16)d;
+ break;
+
+ case OP_LHA:
+ regs->gpr[rd] = ~0UL;
+ break;
+
+ case OP_LHAU:
+ regs->gpr[rd] = ~0UL;
+ regs->gpr[ra] += (s16)d;
+ break;
+
+ default:
+ return 0;
+ }
+
+ return 1;
+}
+
+static int is_in_pci_mem_space(phys_addr_t addr)
+{
+ struct pci_controller *hose;
+ struct resource *res;
+ int i;
+
+ list_for_each_entry(hose, &hose_list, list_node) {
+ if (!(hose->indirect_type & PPC_INDIRECT_TYPE_EXT_REG))
+ continue;
+
+ for (i = 0; i < 3; i++) {
+ res = &hose->mem_resources[i];
+ if ((res->flags & IORESOURCE_MEM) &&
+ addr >= res->start && addr <= res->end)
+ return 1;
+ }
+ }
+ return 0;
+}
+
+int fsl_pci_mcheck_exception(struct pt_regs *regs)
+{
+ u32 inst;
+ int ret;
+ phys_addr_t addr = 0;
+
+ /* Let KVM/QEMU deal with the exception */
+ if (regs->msr & MSR_GS)
+ return 0;
+
+#ifdef CONFIG_PHYS_64BIT
+ addr = mfspr(SPRN_MCARU);
+ addr <<= 32;
+#endif
+ addr += mfspr(SPRN_MCAR);
+
+ if (is_in_pci_mem_space(addr)) {
+ if (user_mode(regs)) {
+ pagefault_disable();
+ ret = get_user(regs->nip, &inst);
+ pagefault_enable();
+ } else {
+ ret = probe_kernel_address(regs->nip, inst);
+ }
+
+ if (mcheck_handle_load(regs, inst)) {
+ regs->nip += 4;
+ return 1;
+ }
+ }
+
+ return 0;
+}
+#endif
+
#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
static const struct of_device_id pci_ids[] = {
{ .compatible = "fsl,mpc8540-pci", },
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index 72b5625..defc422 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -126,5 +126,11 @@ static inline int mpc85xx_pci_err_probe(struct platform_device *op)
}
#endif
+#ifdef CONFIG_FSL_PCI
+extern int fsl_pci_mcheck_exception(struct pt_regs *);
+#else
+static inline int fsl_pci_mcheck_exception(struct pt_regs *regs) {return 0; }
+#endif
+
#endif /* __POWERPC_FSL_PCI_H */
#endif /* __KERNEL__ */
--
1.8.0
^ permalink raw reply related
* Re: [PATCH v2 12/15] powerpc/85xx: add time base sync support for e6500
From: Zhao Chenhui @ 2013-04-28 9:56 UTC (permalink / raw)
To: Scott Wood; +Cc: linuxppc-dev, linux-kernel, r58472
In-Reply-To: <1366934844.30341.16@snotra>
On Thu, Apr 25, 2013 at 07:07:24PM -0500, Scott Wood wrote:
> On 04/24/2013 07:28:18 PM, Zhao Chenhui wrote:
> >On Wed, Apr 24, 2013 at 05:38:16PM -0500, Scott Wood wrote:
> >> On 04/24/2013 06:29:29 AM, Zhao Chenhui wrote:
> >> >On Tue, Apr 23, 2013 at 07:04:06PM -0500, Scott Wood wrote:
> >> >> On 04/19/2013 05:47:45 AM, Zhao Chenhui wrote:
> >> >> >From: Chen-Hui Zhao <chenhui.zhao@freescale.com>
> >> >> >
> >> >> >For e6500, two threads in one core share one time base. Just
> >need
> >> >> >to do time base sync on first thread of one core, and skip it on
> >> >> >the other thread.
> >> >> >
> >> >> >Signed-off-by: Zhao Chenhui <chenhui.zhao@freescale.com>
> >> >> >Signed-off-by: Li Yang <leoli@freescale.com>
> >> >> >Signed-off-by: Andy Fleming <afleming@freescale.com>
> >> >> >---
> >> >> > arch/powerpc/platforms/85xx/smp.c | 52
> >> >> >+++++++++++++++++++++++++++++++-----
> >> >> > 1 files changed, 44 insertions(+), 8 deletions(-)
> >> >> >
> >> >> >diff --git a/arch/powerpc/platforms/85xx/smp.c
> >> >> >b/arch/powerpc/platforms/85xx/smp.c
> >> >> >index 74d8cde..5f3eee3 100644
> >> >> >--- a/arch/powerpc/platforms/85xx/smp.c
> >> >> >+++ b/arch/powerpc/platforms/85xx/smp.c
> >> >> >@@ -53,26 +55,40 @@ static inline u32 get_phy_cpu_mask(void)
> >> >> > u32 mask;
> >> >> > int cpu;
> >> >> >
> >> >> >- mask = 1 << cur_booting_core;
> >> >> >- for_each_online_cpu(cpu)
> >> >> >- mask |= 1 << get_hard_smp_processor_id(cpu);
> >> >> >+ if (smt_capable()) {
> >> >> >+ /* two threads in one core share one time base */
> >> >> >+ mask = 1 << cpu_core_index_of_thread(cur_booting_core);
> >> >> >+ for_each_online_cpu(cpu)
> >> >> >+ mask |= 1 << cpu_core_index_of_thread(
> >> >> >+ get_hard_smp_processor_id(cpu));
> >> >> >+ } else {
> >> >> >+ mask = 1 << cur_booting_core;
> >> >> >+ for_each_online_cpu(cpu)
> >> >> >+ mask |= 1 << get_hard_smp_processor_id(cpu);
> >> >> >+ }
> >> >>
> >> >> Where is smt_capable defined()? I assume somewhere in the
> >patchset
> >> >> but it's a pain to search 12 patches...
> >> >>
> >> >
> >> >It is defined in arch/powerpc/include/asm/topology.h.
> >> > #define smt_capable() (cpu_has_feature(CPU_FTR_SMT))
> >> >
> >> >Thanks for your review again.
> >>
> >> We shouldn't base it on CPU_FTR_SMT. For example, e6500 doesn't
> >> claim that feature yet, except in our SDK kernel. That doesn't
> >> change the topology of CPU numbering.
> >>
> >
> >Then, where can I get the thread information? dts?
> >Or, wait for upstream of the thread suppport of e6500.
>
> It's an inherent property of e6500 (outside of some virtualization
> scenarios, but you wouldn't run this code under a hypervisor) that
> you have two threads per core (whether Linux uses them or not). Or
> you could read TMCFG0[NTHRD] if you know you're on a chip that has
> TMRs but aren't positive it's an e6500, but I wouldn't bother. If
> we do ever have such a chip, there are probably other things that
> will need updating.
>
But how to know that there are TMRs on a chip except by CPU_FTR_SMT.
> >> >static inline u32 get_phy_cpu_mask(void)
> >> >{
> >> > u32 mask;
> >> > int cpu;
> >> >
> >> > mask = 1 << cpu_core_index_of_thread(cur_booting_core);
> >> > for_each_online_cpu(cpu)
> >> > mask |= 1 << cpu_core_index_of_thread(
> >> > get_hard_smp_processor_id(cpu));
> >> >
> >> > return mask;
> >> >}
> >>
> >> Likewise, this will get it wrong if SMT is disabled or not yet
> >> implemented on a core.
> >>
> >> -Scott
> >
> >Let's look into cpu_core_index_of_thread() in
> >arch/powerpc/kernel/smp.c.
> >
> > int cpu_core_index_of_thread(int cpu)
> > {
> > return cpu >> threads_shift;
> > }
> >
> >If no thread, the threads_shift is equal to 0. It can work with no
> >thread.
>
> My point is that if threads are disabled, threads_shift will be 0,
> but e6500 cores will still be numbered 0, 2, 4, etc.
>
> >Perhaps, I should submit this patch after the thread patches for
> >e6500.
>
> Why?
>
> -Scott
Even if threads are disabled, the threads_shift derived from dts is right.
But, if there aren't the thread related patches existed in SDK, the threads_shift
gets a wrong value on T4.
-Chenhui
^ permalink raw reply
* Re: [PATCH v2 02/15] powerpc/85xx: add sleep and deep sleep support
From: Zhao Chenhui @ 2013-04-28 10:20 UTC (permalink / raw)
To: Scott Wood; +Cc: linuxppc-dev, linux-kernel, r58472
In-Reply-To: <1366761200.5825.18@snotra>
On Tue, Apr 23, 2013 at 06:53:20PM -0500, Scott Wood wrote:
> On 04/19/2013 05:47:35 AM, Zhao Chenhui wrote:
> > static int pmc_suspend_enter(suspend_state_t state)
> > {
> >- int ret;
> >+ int ret = 0;
> >+
> >+ switch (state) {
> >+#ifdef CONFIG_PPC_85xx
> >+ case PM_SUSPEND_MEM:
> >+#ifdef CONFIG_SPE
> >+ enable_kernel_spe();
> >+#endif
> >+ enable_kernel_fp();
>
> Why does enable_kernel_spe() need an ifdef but enable_kernel_fp()
> doesn't?
>
will enclose it with CONFIG_PPC_FPU.
> >+ case PM_SUSPEND_STANDBY:
> >+#ifdef CONFIG_FSL_SOC_BOOKE
> >+ flush_dcache_L1();
> >+#endif
> >+ setbits32(&pmc_regs->powmgtcsr, POWMGTCSR_SLP);
>
> Only L1, even on e500mc?
>
> -Scott
This patch is just for chips with pmc unit. They have no e500mc core.
-Chenhui
^ permalink raw reply
* [PATCH -V7 05/18] powerpc: Save DAR and DSISR in pt_regs on MCE
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
We were not saving DAR and DSISR on MCE. Save then and also print the values
along with exception details in xmon.
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/kernel/exceptions-64s.S | 9 +++++++++
arch/powerpc/xmon/xmon.c | 2 +-
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 56bd923..7da3f94 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -688,9 +688,18 @@ slb_miss_user_pseries:
.align 7
.globl machine_check_common
machine_check_common:
+
+ mfspr r10,SPRN_DAR
+ std r10,PACA_EXGEN+EX_DAR(r13)
+ mfspr r10,SPRN_DSISR
+ stw r10,PACA_EXGEN+EX_DSISR(r13)
EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
FINISH_NAP
DISABLE_INTS
+ ld r3,PACA_EXGEN+EX_DAR(r13)
+ lwz r4,PACA_EXGEN+EX_DSISR(r13)
+ std r3,_DAR(r1)
+ std r4,_DSISR(r1)
bl .save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl .machine_check_exception
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 13f85de..51e237c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1430,7 +1430,7 @@ static void excprint(struct pt_regs *fp)
printf(" sp: %lx\n", fp->gpr[1]);
printf(" msr: %lx\n", fp->msr);
- if (trap == 0x300 || trap == 0x380 || trap == 0x600) {
+ if (trap == 0x300 || trap == 0x380 || trap == 0x600 || trap == 0x200) {
printf(" dar: %lx\n", fp->dar);
if (trap != 0x380)
printf(" dsisr: %lx\n", fp->dsisr);
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 13/18] powerpc: Use encode avpn where we need only avpn values
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
In all these cases we are doing something similar to
HPTE_V_COMPARE(hpte_v, want_v) which ignores the HPTE_V_LARGE bit
With MPSS support we would need actual page size to set HPTE_V_LARGE
bit and that won't be available in most of these cases. Since we are ignoring
HPTE_V_LARGE bit, use the avpn value instead. There should not be any change
in behaviour after this patch.
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/hash_native_64.c | 8 ++++----
arch/powerpc/platforms/cell/beat_htab.c | 10 +++++-----
arch/powerpc/platforms/ps3/htab.c | 2 +-
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index ffc1e00..9d8983a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -252,7 +252,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long hpte_v, want_v;
int ret = 0;
- want_v = hpte_encode_v(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
DBG_LOW(" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
vpn, want_v & HPTE_V_AVPN, slot, newpp);
@@ -288,7 +288,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
unsigned long want_v, hpte_v;
hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
- want_v = hpte_encode_v(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
/* Bolted mappings are only ever in the primary group */
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -348,7 +348,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
DBG_LOW(" invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
- want_v = hpte_encode_v(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
native_lock_hpte(hptep);
hpte_v = hptep->v;
@@ -520,7 +520,7 @@ static void native_flush_hash_range(unsigned long number, int local)
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
hptep = htab_address + slot;
- want_v = hpte_encode_v(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
native_lock_hpte(hptep);
hpte_v = hptep->v;
if (!HPTE_V_COMPARE(hpte_v, want_v) ||
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 0f6f839..472f9a7 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -191,7 +191,7 @@ static long beat_lpar_hpte_updatepp(unsigned long slot,
u64 dummy0, dummy1;
unsigned long want_v;
- want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
DBG_LOW(" update: "
"avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ",
@@ -228,7 +228,7 @@ static long beat_lpar_hpte_find(unsigned long vpn, int psize)
unsigned long want_v, hpte_v;
hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M);
- want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
for (j = 0; j < 2; j++) {
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -283,7 +283,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
slot, va, psize, local);
- want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
raw_spin_lock_irqsave(&beat_htab_lock, flags);
dummy1 = beat_lpar_hpte_getword0(slot);
@@ -372,7 +372,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
unsigned long want_v;
unsigned long pss;
- want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
DBG_LOW(" update: "
@@ -402,7 +402,7 @@ static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
slot, vpn, psize, local);
- want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss);
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 6cc5820..cd8f2fb 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -117,7 +117,7 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long flags;
long ret;
- want_v = hpte_encode_v(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
spin_lock_irqsave(&ps3_htab_lock, flags);
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 10/18] powerpc: Reduce the PTE_INDEX_SIZE
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This make one PMD cover 16MB range. That helps in easier implementation of THP
on power. THP core code make use of one pmd entry to track the hugepage and
the range mapped by a single pmd entry should be equal to the hugepage size
supported by the hardware.
This also switch PGD to cover 16GB. That is needed so that we can simplify the
hugetlb page walking code so that we have same pte format for explicit hugepage
and THP hugepage.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgtable-ppc64-64k.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
index be4e287..45142d6 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
@@ -4,10 +4,10 @@
#include <asm-generic/pgtable-nopud.h>
-#define PTE_INDEX_SIZE 12
-#define PMD_INDEX_SIZE 12
+#define PTE_INDEX_SIZE 8
+#define PMD_INDEX_SIZE 10
#define PUD_INDEX_SIZE 0
-#define PGD_INDEX_SIZE 6
+#define PGD_INDEX_SIZE 12
#ifndef __ASSEMBLY__
#define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE)
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 00/18] THP support for PPC64 (Patchset 1)
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev
Hi,
This patchset include changes needed for mm/ and powerpc/mm/ to support THP.
I have split the patch series into two patchset, so that we can look at getting
prerequisite patches upstream in 3.10.
Some numbers:
The latency measurements code from Anton found at
http://ozlabs.org/~anton/junkcode/latency2001.c
64K page size (With THP support)
--------------------------
[root@llmp24l02 test]# ./latency2001 8G
8589934592 428.49 cycles 120.50 ns
[root@llmp24l02 test]# ./latency2001 -l 8G
8589934592 471.16 cycles 132.50 ns
[root@llmp24l02 test]# echo never > /sys/kernel/mm/transparent_hugepage/enabled
[root@llmp24l02 test]# ./latency2001 8G
8589934592 766.52 cycles 215.56 ns
[root@llmp24l02 test]#
4K page size (No THP support for 4K)
----------------------------
[root@llmp24l02 test]# ./latency2001 8G
8589934592 814.88 cycles 229.16 ns
[root@llmp24l02 test]# ./latency2001 -l 8G
8589934592 463.69 cycles 130.40 ns
[root@llmp24l02 test]#
We are close to hugetlbfs in latency and we can achieve this with zero
config/page reservation. Most of the allocations above are fault allocated.
Another test that does 50000000 random access over 1GB area goes from
2.65 seconds to 1.07 seconds with this patchset.
split_huge_page impact:
---------------------
To look at the performance impact of large page invalidate, I tried the below
experiment. The test involved, accessing a large contiguous region of memory
location as below
for (i = 0; i < size; i += PAGE_SIZE)
data[i] = i;
We wanted to access the data in sequential order so that we look at the
worst case THP performance. Accesing the data in sequential order implies
we have the Page table cached and overhead of TLB miss is as minimal as
possible. We also don't touch the entire page, because that can result in
cache evict.
After we touched the full range as above, we now call mprotect on each
of that page. A mprotect will result in a hugepage split. This should
allow us to measure the impact of hugepage split.
for (i = 0; i < size; i += PAGE_SIZE)
mprotect(&data[i], PAGE_SIZE, PROT_READ);
Split hugepage impact:
---------------------
THP enabled: 2.851561705 seconds for test completion
THP disable: 3.599146098 seconds for test completion
We are 20.7% better than non THP case even when we have all the large pages split.
Detailed output:
THP enabled:
---------------------------------------
[root@llmp24l02 ~]# cat /proc/vmstat | grep thp
thp_fault_alloc 0
thp_fault_fallback 0
thp_collapse_alloc 0
thp_collapse_alloc_failed 0
thp_split 0
thp_zero_page_alloc 0
thp_zero_page_alloc_failed 0
[root@llmp24l02 ~]# /root/thp/tools/perf/perf stat -e page-faults,dTLB-load-misses ./split-huge-page-mpro 20G
time taken to touch all the data in ns: 2763096913
Performance counter stats for './split-huge-page-mpro 20G':
1,581 page-faults
3,159 dTLB-load-misses
2.851561705 seconds time elapsed
[root@llmp24l02 ~]#
[root@llmp24l02 ~]# cat /proc/vmstat | grep thp
thp_fault_alloc 1279
thp_fault_fallback 0
thp_collapse_alloc 0
thp_collapse_alloc_failed 0
thp_split 1279
thp_zero_page_alloc 0
thp_zero_page_alloc_failed 0
[root@llmp24l02 ~]#
77.05% split-huge-page [kernel.kallsyms] [k] .clear_user_page
7.10% split-huge-page [kernel.kallsyms] [k] .perf_event_mmap_ctx
1.51% split-huge-page split-huge-page-mpro [.] 0x0000000000000a70
0.96% split-huge-page [unknown] [H] 0x000000000157e3bc
0.81% split-huge-page [kernel.kallsyms] [k] .up_write
0.76% split-huge-page [kernel.kallsyms] [k] .perf_event_mmap
0.76% split-huge-page [kernel.kallsyms] [k] .down_write
0.74% split-huge-page [kernel.kallsyms] [k] .lru_add_page_tail
0.61% split-huge-page [kernel.kallsyms] [k] .split_huge_page
0.59% split-huge-page [kernel.kallsyms] [k] .change_protection
0.51% split-huge-page [kernel.kallsyms] [k] .release_pages
0.96% split-huge-page [unknown] [H] 0x000000000157e3bc
|
|--79.44%-- reloc_start
| |
| |--86.54%-- .__pSeries_lpar_hugepage_invalidate
| | .pSeries_lpar_hugepage_invalidate
| | .hpte_need_hugepage_flush
| | .split_huge_page
| | .__split_huge_page_pmd
| | .vma_adjust
| | .vma_merge
| | .mprotect_fixup
| | .SyS_mprotect
THP disabled:
---------------
[root@llmp24l02 ~]# echo never > /sys/kernel/mm/transparent_hugepage/enabled
[root@llmp24l02 ~]# /root/thp/tools/perf/perf stat -e page-faults,dTLB-load-misses ./split-huge-page-mpro 20G
time taken to touch all the data in ns: 3513767220
Performance counter stats for './split-huge-page-mpro 20G':
3,27,726 page-faults
3,29,654 dTLB-load-misses
3.599146098 seconds time elapsed
[root@llmp24l02 ~]#
Changes from V6:
* split the patch series into two patchset.
* Address review feedback.
Changes from V5:
* Address review comments
* Added new patch to not use hugepd for explcit hugepages. Explicit hugepaes
now use PTE format similar to transparent hugepages.
* We don't use page->_mapcount for tracking free PTE frags in a PTE page.
* rebased to a86d52667d8eda5de39393ce737794403bdce1eb
* Tested with libhugetlbfs test suite
Changes from V4:
* Fix bad page error in page_table_alloc
BUG: Bad page state in process stream pfn:f1a59
page:f0000000034dc378 count:1 mapcount:0 mapping: (null) index:0x0
[c000000f322c77d0] [c00000000015e198] .bad_page+0xe8/0x140
[c000000f322c7860] [c00000000015e3c4] .free_pages_prepare+0x1d4/0x1e0
[c000000f322c7910] [c000000000160450] .free_hot_cold_page+0x50/0x230
[c000000f322c79c0] [c00000000003ad18] .page_table_alloc+0x168/0x1c0
Changes from V3:
* PowerNV boot fixes
Change from V2:
* Change patch "powerpc: Reduce PTE table memory wastage" to use much simpler approach
for PTE page sharing.
* Changes to handle huge pages in KVM code.
* Address other review comments
Changes from V1
* Address review comments
* More patch split
* Add batch hpte invalidate for hugepages.
Changes from RFC V2:
* Address review comments
* More code cleanup and patch split
Changes from RFC V1:
* HugeTLB fs now works
* Compile issues fixed
* rebased to v3.8
* Patch series reorded so that ppc64 cleanups and MM THP changes are moved
early in the series. This should help in picking those patches early.
Thanks,
-aneesh
^ permalink raw reply
* [PATCH -V7 12/18] powerpc: Reduce PTE table memory wastage
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
We allocate one page for the last level of linux page table. With THP and
large page size of 16MB, that would mean we are wasting large part
of that page. To map 16MB area, we only need a PTE space of 2K with 64K
page size. This patch reduce the space wastage by sharing the page
allocated for the last level of linux page table with multiple pmd
entries. We call these smaller chunks PTE page fragments and allocated
page, PTE page.
In order to support systems which doesn't have 64K HPTE support, we also
add another 2K to PTE page fragment. The second half of the PTE fragments
is used for storing slot and secondary bit information of an HPTE. With this
we now have a 4K PTE fragment.
We use a simple approach to share the PTE page. On allocation, we bump the
PTE page refcount to 16 and share the PTE page with the next 16 pte alloc
request. This should help in the node locality of the PTE page fragment,
assuming that the immediate pte alloc request will mostly come from the
same NUMA node. We don't try to reuse the freed PTE page fragment. Hence
we could be waisting some space.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mmu-book3e.h | 4 ++
arch/powerpc/include/asm/mmu-hash64.h | 4 ++
arch/powerpc/include/asm/page.h | 4 ++
arch/powerpc/include/asm/pgalloc-64.h | 82 +++++++----------------
arch/powerpc/kernel/setup_64.c | 4 +-
arch/powerpc/mm/mmu_context_hash64.c | 37 +++++++++++
arch/powerpc/mm/pgtable_64.c | 118 ++++++++++++++++++++++++++++++++++
7 files changed, 195 insertions(+), 58 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 99d43e0..8bd560c 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -231,6 +231,10 @@ typedef struct {
u64 high_slices_psize; /* 4 bits per slice for now */
u16 user_psize; /* page size index */
#endif
+#ifdef CONFIG_PPC_64K_PAGES
+ /* for 4K PTE fragment support */
+ void *pte_frag;
+#endif
} mm_context_t;
/* Page size definitions, common between 32 and 64-bit
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 05895cf..de9e577 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -516,6 +516,10 @@ typedef struct {
unsigned long acop; /* mask of enabled coprocessor types */
unsigned int cop_pid; /* pid value used with coprocessors */
#endif /* CONFIG_PPC_ICSWX */
+#ifdef CONFIG_PPC_64K_PAGES
+ /* for 4K PTE fragment support */
+ void *pte_frag;
+#endif
} mm_context_t;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 711e83a..988c812 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -393,7 +393,11 @@ void arch_free_page(struct page *page, int order);
struct vm_area_struct;
+#ifdef CONFIG_PPC_64K_PAGES
+typedef pte_t *pgtable_t;
+#else
typedef struct page *pgtable_t;
+#endif
#include <asm-generic/memory_model.h>
#endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index d390123..91acb12 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -152,6 +152,23 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
}
#else /* if CONFIG_PPC_64K_PAGES */
+/*
+ * we support 16 fragments per PTE page.
+ */
+#define PTE_FRAG_NR 16
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ */
+#define PTE_FRAG_SIZE_SHIFT 12
+#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
+
+extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int);
+extern void page_table_free(struct mm_struct *, unsigned long *, int);
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
+#ifdef CONFIG_SMP
+extern void __tlb_remove_table(void *_table);
+#endif
#define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd)
@@ -164,90 +181,42 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
pgtable_t pte_page)
{
- pmd_populate_kernel(mm, pmd, page_address(pte_page));
+ pmd_set(pmd, (unsigned long)pte_page);
}
static inline pgtable_t pmd_pgtable(pmd_t pmd)
{
- return pmd_page(pmd);
+ return (pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE);
}
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ return (pte_t *)page_table_alloc(mm, address, 1);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
- unsigned long address)
+ unsigned long address)
{
- struct page *page;
- pte_t *pte;
-
- pte = pte_alloc_one_kernel(mm, address);
- if (!pte)
- return NULL;
- page = virt_to_page(pte);
- pgtable_page_ctor(page);
- return page;
+ return (pgtable_t)page_table_alloc(mm, address, 0);
}
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
- free_page((unsigned long)pte);
+ page_table_free(mm, (unsigned long *)pte, 1);
}
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
{
- pgtable_page_dtor(ptepage);
- __free_page(ptepage);
+ page_table_free(mm, (unsigned long *)ptepage, 0);
}
-static inline void pgtable_free(void *table, unsigned index_size)
-{
- if (!index_size)
- free_page((unsigned long)table);
- else {
- BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
- kmem_cache_free(PGT_CACHE(index_size), table);
- }
-}
-
-#ifdef CONFIG_SMP
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
- void *table, int shift)
-{
- unsigned long pgf = (unsigned long)table;
- BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
- pgf |= shift;
- tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
- void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
- unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
- pgtable_free(table, shift);
-}
-#else /* !CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
- void *table, int shift)
-{
- pgtable_free(table, shift);
-}
-#endif /* CONFIG_SMP */
-
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- struct page *page = page_address(table);
-
tlb_flush_pgtable(tlb, address);
- pgtable_page_dtor(page);
- pgtable_free_tlb(tlb, page, 0);
+ pgtable_free_tlb(tlb, table, 0);
}
-
#endif /* CONFIG_PPC_64K_PAGES */
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -261,7 +230,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
}
-
#define __pmd_free_tlb(tlb, pmd, addr) \
pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
#ifndef CONFIG_PPC_64K_PAGES
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 75fbaceb..e379d3f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -583,7 +583,9 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = klimit;
-
+#ifdef CONFIG_PPC_64K_PAGES
+ init_mm.context.pte_frag = NULL;
+#endif
irqstack_early_init();
exc_lvl_early_init();
emergency_stack_init();
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index d1d1b92..178876ae 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
#include "icswx.h"
@@ -85,6 +86,9 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
spin_lock_init(mm->context.cop_lockp);
#endif /* CONFIG_PPC_ICSWX */
+#ifdef CONFIG_PPC_64K_PAGES
+ mm->context.pte_frag = NULL;
+#endif
return 0;
}
@@ -96,13 +100,46 @@ void __destroy_context(int context_id)
}
EXPORT_SYMBOL_GPL(__destroy_context);
+#ifdef CONFIG_PPC_64K_PAGES
+static void destroy_pagetable_page(struct mm_struct *mm)
+{
+ int count;
+ void *pte_frag;
+ struct page *page;
+
+ pte_frag = mm->context.pte_frag;
+ if (!pte_frag)
+ return;
+
+ page = virt_to_page(pte_frag);
+ /* drop all the pending references */
+ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
+ /* We allow PTE_FRAG_NR fragments from a PTE page */
+ count = atomic_sub_return(PTE_FRAG_NR - count, &page->_count);
+ if (!count) {
+ pgtable_page_dtor(page);
+ free_hot_cold_page(page, 0);
+ }
+}
+
+#else
+static inline void destroy_pagetable_page(struct mm_struct *mm)
+{
+ return;
+}
+#endif
+
+
void destroy_context(struct mm_struct *mm)
{
+
#ifdef CONFIG_PPC_ICSWX
drop_cop(mm->context.acop, mm);
kfree(mm->context.cop_lockp);
mm->context.cop_lockp = NULL;
#endif /* CONFIG_PPC_ICSWX */
+
+ destroy_pagetable_page(mm);
__destroy_context(mm->context.id);
subpage_prot_free(mm);
mm->context.id = MMU_NO_CONTEXT;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 654258f..a854096 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -337,3 +337,121 @@ EXPORT_SYMBOL(__ioremap_at);
EXPORT_SYMBOL(iounmap);
EXPORT_SYMBOL(__iounmap);
EXPORT_SYMBOL(__iounmap_at);
+
+#ifdef CONFIG_PPC_64K_PAGES
+static pte_t *get_from_cache(struct mm_struct *mm)
+{
+ void *pte_frag, *ret;
+
+ spin_lock(&mm->page_table_lock);
+ ret = mm->context.pte_frag;
+ if (ret) {
+ pte_frag = ret + PTE_FRAG_SIZE;
+ /*
+ * If we have taken up all the fragments mark PTE page NULL
+ */
+ if (((unsigned long)pte_frag & ~PAGE_MASK) == 0)
+ pte_frag = NULL;
+ mm->context.pte_frag = pte_frag;
+ }
+ spin_unlock(&mm->page_table_lock);
+ return (pte_t *)ret;
+}
+
+static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
+{
+ void *ret = NULL;
+ struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
+ __GFP_REPEAT | __GFP_ZERO);
+ if (!page)
+ return NULL;
+
+ ret = page_address(page);
+ spin_lock(&mm->page_table_lock);
+ /*
+ * If we find pgtable_page set, we return
+ * the allocated page with single fragement
+ * count.
+ */
+ if (likely(!mm->context.pte_frag)) {
+ atomic_set(&page->_count, PTE_FRAG_NR);
+ mm->context.pte_frag = ret + PTE_FRAG_SIZE;
+ }
+ spin_unlock(&mm->page_table_lock);
+
+ if (!kernel)
+ pgtable_page_ctor(page);
+
+ return (pte_t *)ret;
+}
+
+pte_t *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)
+{
+ pte_t *pte;
+
+ pte = get_from_cache(mm);
+ if (pte)
+ return pte;
+
+ return __alloc_for_cache(mm, kernel);
+}
+
+void page_table_free(struct mm_struct *mm, unsigned long *table, int kernel)
+{
+ struct page *page = virt_to_page(table);
+ if (put_page_testzero(page)) {
+ if (!kernel)
+ pgtable_page_dtor(page);
+ free_hot_cold_page(page, 0);
+ }
+}
+
+#ifdef CONFIG_SMP
+static void page_table_free_rcu(void *table)
+{
+ struct page *page = virt_to_page(table);
+ if (put_page_testzero(page)) {
+ pgtable_page_dtor(page);
+ free_hot_cold_page(page, 0);
+ }
+}
+
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+ unsigned long pgf = (unsigned long)table;
+
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ pgf |= shift;
+ tlb_remove_table(tlb, (void *)pgf);
+}
+
+void __tlb_remove_table(void *_table)
+{
+ void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+ unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+ if (!shift)
+ /* PTE page needs special handling */
+ page_table_free_rcu(table);
+ else {
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ kmem_cache_free(PGT_CACHE(shift), table);
+ }
+}
+#else
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+ if (!shift) {
+ /* PTE page needs special handling */
+ struct page *page = virt_to_page(table);
+ if (put_page_testzero(page)) {
+ pgtable_page_dtor(page);
+ free_hot_cold_page(page, 0);
+ }
+ } else {
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ kmem_cache_free(PGT_CACHE(shift), table);
+ }
+}
+#endif
+#endif /* CONFIG_PPC_64K_PAGES */
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 18/18] powerpc: Update tlbie/tlbiel as per ISA doc
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Encode the actual page correctly in tlbie/tlbiel. This make sure we handle
multiple page size segment correctly.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/hash_native_64.c | 32 ++++++++++++++++++++++++++++++--
1 file changed, 30 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index bb920ee..6a2aead 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -61,7 +61,10 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
switch (psize) {
case MMU_PAGE_4K:
+ /* clear out bits after (52) [0....52.....63] */
+ va &= ~((1ul << (64 - 52)) - 1);
va |= ssize << 8;
+ va |= mmu_psize_defs[apsize].sllp << 6;
asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
: : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
: "memory");
@@ -69,9 +72,20 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
default:
/* We need 14 to 14 + i bits of va */
penc = mmu_psize_defs[psize].penc[apsize];
- va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+ va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
+ /* Add AVAL part */
+ if (psize != apsize) {
+ /*
+ * MPSS, 64K base page size and 16MB parge page size
+ * We don't need all the bits, but rest of the bits
+ * must be ignored by the processor.
+ * vpn cover upto 65 bits of va. (0...65) and we need
+ * 58..64 bits of va.
+ */
+ va |= (vpn & 0xfe);
+ }
va |= 1; /* L */
asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
: : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -96,16 +110,30 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
switch (psize) {
case MMU_PAGE_4K:
+ /* clear out bits after(52) [0....52.....63] */
+ va &= ~((1ul << (64 - 52)) - 1);
va |= ssize << 8;
+ va |= mmu_psize_defs[apsize].sllp << 6;
asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
: : "r"(va) : "memory");
break;
default:
/* We need 14 to 14 + i bits of va */
penc = mmu_psize_defs[psize].penc[apsize];
- va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+ va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
+ /* Add AVAL part */
+ if (psize != apsize) {
+ /*
+ * MPSS, 64K base page size and 16MB parge page size
+ * We don't need all the bits, but rest of the bits
+ * must be ignored by the processor.
+ * vpn cover upto 65 bits of va. (0...65) and we need
+ * 58..64 bits of va.
+ */
+ va |= (vpn & 0xfe);
+ }
va |= 1; /* L */
asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
: : "r"(va) : "memory");
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 03/18] mm/THP: withdraw the pgtable after pmdp related operations
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
For architectures like ppc64 we look at deposited pgtable when
calling pmdp_get_and_clear. So do the pgtable_trans_huge_withdraw
after finishing pmdp related operations.
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
mm/huge_memory.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 84f3180..21c5ebd 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1363,9 +1363,15 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
struct page *page;
pgtable_t pgtable;
pmd_t orig_pmd;
- pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
+ /*
+ * For architectures like ppc64 we look at deposited pgtable
+ * when calling pmdp_get_and_clear. So do the
+ * pgtable_trans_huge_withdraw after finishing pmdp related
+ * operations.
+ */
orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+ pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
if (is_huge_zero_pmd(orig_pmd)) {
tlb->mm->nr_ptes--;
spin_unlock(&tlb->mm->page_table_lock);
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 01/18] mm/THP: HPAGE_SHIFT is not a #define on some arch
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
On archs like powerpc that support different hugepage sizes, HPAGE_SHIFT
and other derived values like HPAGE_PMD_ORDER are not constants. So move
that to hugepage_init
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
include/linux/huge_mm.h | 3 ---
mm/huge_memory.c | 9 ++++++---
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ee1c244..bdc5aef 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -119,9 +119,6 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma,
} while (0)
extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
pmd_t *pmd);
-#if HPAGE_PMD_ORDER > MAX_ORDER
-#error "hugepages can't be allocated by the buddy allocator"
-#endif
extern int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice);
extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e2f7f5aa..78bd84f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -45,7 +45,7 @@ unsigned long transparent_hugepage_flags __read_mostly =
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
/* default scan 8*512 pte (or vmas) every 30 second */
-static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
+static unsigned int khugepaged_pages_to_scan __read_mostly;
static unsigned int khugepaged_pages_collapsed;
static unsigned int khugepaged_full_scans;
static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
@@ -60,7 +60,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
* it would have happened if the vma was large enough during page
* fault.
*/
-static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
+static unsigned int khugepaged_max_ptes_none __read_mostly;
static int khugepaged(void *none);
static int khugepaged_slab_init(void);
@@ -620,11 +620,14 @@ static int __init hugepage_init(void)
int err;
struct kobject *hugepage_kobj;
- if (!has_transparent_hugepage()) {
+ if (!has_transparent_hugepage() || (HPAGE_PMD_ORDER > MAX_ORDER)) {
transparent_hugepage_flags = 0;
return -EINVAL;
}
+ khugepaged_pages_to_scan = HPAGE_PMD_NR*8;
+ khugepaged_max_ptes_none = HPAGE_PMD_NR-1;
+
err = hugepage_init_sysfs(&hugepage_kobj);
if (err)
return err;
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 17/18] powerpc: Print page size info during boot
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This gives hint about different base and actual page size combination
supported by the platform.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/hash_utils_64.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 33cdc3a..d0eb6d4 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -316,7 +316,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
prop = (u32 *)of_get_flat_dt_prop(node,
"ibm,segment-page-sizes", &size);
if (prop != NULL) {
- DBG("Page sizes from device-tree:\n");
+ pr_info("Page sizes from device-tree:\n");
size /= 4;
cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
while(size > 0) {
@@ -370,10 +370,10 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
"shift=%d\n", base_shift, shift);
def->penc[idx] = penc;
- DBG(" %d: shift=%02x, sllp=%04lx, "
- "avpnm=%08lx, tlbiel=%d, penc=%d\n",
- idx, shift, def->sllp, def->avpnm,
- def->tlbiel, def->penc[idx]);
+ pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
+ " avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
+ base_shift, shift, def->sllp,
+ def->avpnm, def->tlbiel, def->penc[idx]);
}
}
return 1;
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 07/18] powerpc: Don't truncate pgd_index wrongly
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
With PGD_INDEX_SIZE set to 12 the existing macro doesn't work. Fix it to
use PTRS_PER_PGD
The idea originally was to have one more bit in the result of
pgd_index() than PGD_INDEX_SIZE, so that if one had an address
corresponding to the last PGD entry, and then incremented that address
by PGD_SIZE, and took pgd_index() of that, you wouldn't end up with
zero. The commit that introduced that dates back to 2002, and the
code that was sensitive to that edge case has long since been
refactored (several times), so there is no need for it these days.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgtable-ppc64.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 0182c20..e3d55f6f 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -167,8 +167,7 @@
* Find an entry in a page-table-directory. We combine the address region
* (the high order N bits) and the pgd portion of the address.
*/
-/* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */
-#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff)
+#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1))
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 15/18] powerpc: Fix hpte_decode to use the correct decoding for page sizes
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
As per ISA doc, we encode base and actual page size in the LP bits of
PTE. The number of bit used to encode the page sizes depend on actual
page size. ISA doc lists this as
PTE LP actual page size
rrrr rrrz >=8KB
rrrr rrzz >=16KB
rrrr rzzz >=32KB
rrrr zzzz >=64KB
rrrz zzzz >=128KB
rrzz zzzz >=256KB
rzzz zzzz >=512KB
zzzz zzzz >=1MB
ISA doc also says
"The values of the “z” bits used to specify each size, along with all possible
values of “r” bits in the LP field, must result in LP values distinct from
other LP values for other sizes."
based on the above update hpte_decode to use the correct decoding for LP bits.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/hash_native_64.c | 53 +++++++++++++++++-----------------------
1 file changed, 22 insertions(+), 31 deletions(-)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 14e3fe8..bb920ee 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -245,19 +245,10 @@ static long native_hpte_remove(unsigned long hpte_group)
return i;
}
-static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
{
int i, shift;
unsigned int mask;
- /* Look at the 8 bit LP value */
- unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
-
- if (!(hptep->v & HPTE_V_VALID))
- return -1;
-
- /* First check if it is large page */
- if (!(hptep->v & HPTE_V_LARGE))
- return MMU_PAGE_4K;
/* start from 1 ignoring MMU_PAGE_4K */
for (i = 1; i < MMU_PAGE_COUNT; i++) {
@@ -284,6 +275,21 @@ static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
return -1;
}
+static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
+{
+ /* Look at the 8 bit LP value */
+ unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+
+ if (!(hptep->v & HPTE_V_VALID))
+ return -1;
+
+ /* First check if it is large page */
+ if (!(hptep->v & HPTE_V_LARGE))
+ return MMU_PAGE_4K;
+
+ return __hpte_actual_psize(lp, psize);
+}
+
static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long vpn, int psize, int ssize,
int local)
@@ -425,42 +431,27 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
int *psize, int *apsize, int *ssize, unsigned long *vpn)
{
unsigned long avpn, pteg, vpi;
- unsigned long hpte_r = hpte->r;
unsigned long hpte_v = hpte->v;
unsigned long vsid, seg_off;
- int i, size, a_size, shift, penc;
+ int size, a_size, shift;
+ /* Look at the 8 bit LP value */
+ unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
if (!(hpte_v & HPTE_V_LARGE)) {
size = MMU_PAGE_4K;
a_size = MMU_PAGE_4K;
} else {
- for (i = 0; i < LP_BITS; i++) {
- if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
- break;
- }
- penc = LP_MASK(i+1) >> LP_SHIFT;
for (size = 0; size < MMU_PAGE_COUNT; size++) {
/* valid entries have a shift value */
if (!mmu_psize_defs[size].shift)
continue;
- for (a_size = 0; a_size < MMU_PAGE_COUNT; a_size++) {
-
- /* 4K pages are not represented by LP */
- if (a_size == MMU_PAGE_4K)
- continue;
- /* valid entries have a shift value */
- if (!mmu_psize_defs[a_size].shift)
- continue;
-
- if (penc == mmu_psize_defs[size].penc[a_size])
- goto out;
- }
+ a_size = __hpte_actual_psize(lp, size);
+ if (a_size != -1)
+ break;
}
}
-
-out:
/* This works for all page sizes, and for 256M and 1T segments */
*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
shift = mmu_psize_defs[size].shift;
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 08/18] powerpc: New hugepage directory format
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Change the hugepage directory format so that we can have leaf ptes directly
at page directory avoiding the allocation of hugepage directory.
With the new table format we have 3 cases for pgds and pmds:
(1) invalid (all zeroes)
(2) pointer to next table, as normal; bottom 6 bits == 0
(4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
Instead of storing shift value in hugepd pointer we use mmu_psize_def index
so that we can fit all the supported hugepage size in 4 bits
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/hugetlb.h | 30 ++++++++++++++++++++++++++++++
arch/powerpc/include/asm/mmu-hash64.h | 20 +++++++++++++++++++-
arch/powerpc/include/asm/page.h | 13 +++++++++++++
arch/powerpc/include/asm/pgalloc-64.h | 5 ++++-
arch/powerpc/mm/hugetlbpage.c | 26 ++++++++------------------
arch/powerpc/mm/init_64.c | 3 +--
6 files changed, 75 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 62e11a3..4daf7e6 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -6,6 +6,33 @@
extern struct kmem_cache *hugepte_cache;
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * This should work for other subarchs too. But right now we use the
+ * new format only for 64bit book3s
+ */
+static inline pte_t *hugepd_page(hugepd_t hpd)
+{
+ BUG_ON(!hugepd_ok(hpd));
+ /*
+ * We have only four bits to encode, MMU page size
+ */
+ BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
+ return (pte_t *)(hpd.pd & ~HUGEPD_SHIFT_MASK);
+}
+
+static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
+{
+ return (hpd.pd & HUGEPD_SHIFT_MASK) >> 2;
+}
+
+static inline unsigned int hugepd_shift(hugepd_t hpd)
+{
+ return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
+}
+
+#else
+
static inline pte_t *hugepd_page(hugepd_t hpd)
{
BUG_ON(!hugepd_ok(hpd));
@@ -17,6 +44,9 @@ static inline unsigned int hugepd_shift(hugepd_t hpd)
return hpd.pd & HUGEPD_SHIFT_MASK;
}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+
static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
unsigned pdshift)
{
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index b59e06f..05895cf 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -21,6 +21,7 @@
* complete pgtable.h but only a portion of it.
*/
#include <asm/pgtable-ppc64.h>
+#include <asm/bug.h>
/*
* Segment table
@@ -159,6 +160,24 @@ struct mmu_psize_def
unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */
unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */
};
+extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+
+static inline int shift_to_mmu_psize(unsigned int shift)
+{
+ int psize;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+ if (mmu_psize_defs[psize].shift == shift)
+ return psize;
+ return -1;
+}
+
+static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
+{
+ if (mmu_psize_defs[mmu_psize].shift)
+ return mmu_psize_defs[mmu_psize].shift;
+ BUG();
+}
#endif /* __ASSEMBLY__ */
@@ -193,7 +212,6 @@ static inline int segment_shift(int ssize)
/*
* The current system page and segment sizes
*/
-extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
extern int mmu_linear_psize;
extern int mmu_virtual_psize;
extern int mmu_vmalloc_psize;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index f072e97..652719c 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -249,6 +249,7 @@ extern long long virt_phys_offset;
#define is_kernel_addr(x) ((x) >= PAGE_OFFSET)
#endif
+#ifndef CONFIG_PPC_BOOK3S_64
/*
* Use the top bit of the higher-level page table entries to indicate whether
* the entries we point to contain hugepages. This works because we know that
@@ -260,6 +261,7 @@ extern long long virt_phys_offset;
#else
#define PD_HUGE 0x80000000
#endif
+#endif /* CONFIG_PPC_BOOK3S_64 */
/*
* Some number of bits at the level of the page table that points to
@@ -354,10 +356,21 @@ typedef unsigned long pgprot_t;
typedef struct { signed long pd; } hugepd_t;
#ifdef CONFIG_HUGETLB_PAGE
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline int hugepd_ok(hugepd_t hpd)
+{
+ /*
+ * hugepd pointer, bottom two bits == 00 and next 4 bits
+ * indicate size of table
+ */
+ return (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0));
+}
+#else
static inline int hugepd_ok(hugepd_t hpd)
{
return (hpd.pd > 0);
}
+#endif
#define is_hugepd(pdep) (hugepd_ok(*((hugepd_t *)(pdep))))
#else /* CONFIG_HUGETLB_PAGE */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 292725c..69e352a 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -35,7 +35,10 @@ struct vmemmap_backing {
#define MAX_PGTABLE_INDEX_SIZE 0xf
extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
+#define PGT_CACHE(shift) ({ \
+ BUG_ON(!(shift)); \
+ pgtable_cache[(shift) - 1]; \
+ })
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1a6de0a..b5f4a5f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -48,23 +48,6 @@ static u64 gpage_freearray[MAX_NUMBER_GPAGES];
static unsigned nr_gpages;
#endif
-static inline int shift_to_mmu_psize(unsigned int shift)
-{
- int psize;
-
- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
- if (mmu_psize_defs[psize].shift == shift)
- return psize;
- return -1;
-}
-
-static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
-{
- if (mmu_psize_defs[mmu_psize].shift)
- return mmu_psize_defs[mmu_psize].shift;
- BUG();
-}
-
#define hugepd_none(hpd) ((hpd).pd == 0)
pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
@@ -145,6 +128,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
if (unlikely(!hugepd_none(*hpdp)))
break;
else
+ /* We use the old format for PPC_FSL_BOOK3E */
hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
}
/* If we bailed from the for loop early, an error occurred, clean up */
@@ -156,9 +140,15 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
#else
if (!hugepd_none(*hpdp))
kmem_cache_free(cachep, new);
- else
+ else {
+#ifdef CONFIG_PPC_BOOK3S_64
+ hpdp->pd = (unsigned long)new |
+ (shift_to_mmu_psize(pshift) << 2);
+#else
hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
#endif
+ }
+#endif
spin_unlock(&mm->page_table_lock);
return 0;
}
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 7e2246f..a56de85 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -129,8 +129,7 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
align = max_t(unsigned long, align, minalign);
name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
new = kmem_cache_create(name, table_size, align, 0, ctor);
- PGT_CACHE(shift) = new;
-
+ pgtable_cache[shift - 1] = new;
pr_debug("Allocated pgtable cache for order %d\n", shift);
}
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 04/18] powerpc: Use signed formatting when printing error
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
PAPR defines these errors as negative values. So print them accordingly
for easy debugging.
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/lpar.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 299731e..9b02ab1 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -155,7 +155,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
*/
if (unlikely(lpar_rc != H_SUCCESS)) {
if (!(vflags & HPTE_V_BOLTED))
- pr_devel(" lpar err %lu\n", lpar_rc);
+ pr_devel(" lpar err %ld\n", lpar_rc);
return -2;
}
if (!(vflags & HPTE_V_BOLTED))
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 16/18] powerpc: print both base and actual page size on hash failure
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mmu-hash64.h | 3 ++-
arch/powerpc/mm/hash_utils_64.c | 12 +++++++-----
arch/powerpc/mm/hugetlbpage-hash64.c | 2 +-
3 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 18171a8..2accc96 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -342,7 +342,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
unsigned int shift, unsigned int mmu_psize);
extern void hash_failure_debug(unsigned long ea, unsigned long access,
unsigned long vsid, unsigned long trap,
- int ssize, int psize, unsigned long pte);
+ int ssize, int psize, int lpsize,
+ unsigned long pte);
extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
unsigned long pstart, unsigned long prot,
int psize, int ssize);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d98626a..33cdc3a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -936,14 +936,14 @@ static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
void hash_failure_debug(unsigned long ea, unsigned long access,
unsigned long vsid, unsigned long trap,
- int ssize, int psize, unsigned long pte)
+ int ssize, int psize, int lpsize, unsigned long pte)
{
if (!printk_ratelimit())
return;
pr_info("mm: Hashing failure ! EA=0x%lx access=0x%lx current=%s\n",
ea, access, current->comm);
- pr_info(" trap=0x%lx vsid=0x%lx ssize=%d psize=%d pte=0x%lx\n",
- trap, vsid, ssize, psize, pte);
+ pr_info(" trap=0x%lx vsid=0x%lx ssize=%d base psize=%d psize %d pte=0x%lx\n",
+ trap, vsid, ssize, psize, lpsize, pte);
}
/* Result code is:
@@ -1116,7 +1116,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
*/
if (rc == -1)
hash_failure_debug(ea, access, vsid, trap, ssize, psize,
- pte_val(*ptep));
+ psize, pte_val(*ptep));
#ifndef CONFIG_PPC_64K_PAGES
DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep));
#else
@@ -1194,7 +1194,9 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
*/
if (rc == -1)
hash_failure_debug(ea, access, vsid, trap, ssize,
- mm->context.user_psize, pte_val(*ptep));
+ mm->context.user_psize,
+ mm->context.user_psize,
+ pte_val(*ptep));
local_irq_restore(flags);
}
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index e0d52ee..06ecb55 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -129,7 +129,7 @@ repeat:
if (unlikely(slot == -2)) {
*ptep = __pte(old_pte);
hash_failure_debug(ea, access, vsid, trap, ssize,
- mmu_psize, old_pte);
+ mmu_psize, mmu_psize, old_pte);
return -1;
}
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 06/18] powerpc: Don't hard code the size of pte page
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
USE PTRS_PER_PTE to indicate the size of pte page. To support THP,
later patches will be changing PTRS_PER_PTE value.
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgtable.h | 6 ++++++
arch/powerpc/mm/hash_low_64.S | 4 ++--
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index a9cbd3b..4b52726 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -17,6 +17,12 @@ struct mm_struct;
# include <asm/pgtable-ppc32.h>
#endif
+/*
+ * We save the slot number & secondary bit in the second half of the
+ * PTE page. We use the 8 bytes per each pte entry.
+ */
+#define PTE_PAGE_HIDX_OFFSET (PTRS_PER_PTE * 8)
+
#ifndef __ASSEMBLY__
#include <asm/tlbflush.h>
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 7443481..abdd5e2 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -490,7 +490,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
beq htab_inval_old_hpte
ld r6,STK_PARAM(R6)(r1)
- ori r26,r6,0x8000 /* Load the hidx mask */
+ ori r26,r6,PTE_PAGE_HIDX_OFFSET /* Load the hidx mask. */
ld r26,0(r26)
addi r5,r25,36 /* Check actual HPTE_SUB bit, this */
rldcr. r0,r31,r5,0 /* must match pgtable.h definition */
@@ -607,7 +607,7 @@ htab_pte_insert_ok:
sld r4,r4,r5
andc r26,r26,r4
or r26,r26,r3
- ori r5,r6,0x8000
+ ori r5,r6,PTE_PAGE_HIDX_OFFSET
std r26,0(r5)
lwsync
std r30,0(r6)
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 02/18] mm/THP: Add pmd args to pgtable deposit and withdraw APIs
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This will be later used by powerpc THP support. In powerpc we want to use
pgtable for storing the hash index values. So instead of adding them to
mm_context list, we would like to store them in the second half of pmd
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/s390/include/asm/pgtable.h | 5 +++--
arch/s390/mm/pgtable.c | 5 +++--
arch/sparc/include/asm/pgtable_64.h | 5 +++--
arch/sparc/mm/tlb.c | 5 +++--
include/asm-generic/pgtable.h | 5 +++--
mm/huge_memory.c | 18 +++++++++---------
mm/pgtable-generic.c | 5 +++--
7 files changed, 27 insertions(+), 21 deletions(-)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 3cb47cf..83da660 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1283,10 +1283,11 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW)
#define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable);
#define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
static inline int pmd_trans_splitting(pmd_t pmd)
{
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ae44d2a..9ab3224 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -920,7 +920,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
}
}
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable)
{
struct list_head *lh = (struct list_head *) pgtable;
@@ -934,7 +935,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
mm->pmd_huge_pte = pgtable;
}
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
struct list_head *lh;
pgtable_t pgtable;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 08fcce9..4c86de2 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -853,10 +853,11 @@ extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd);
#define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable);
#define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
#endif
/* Encode and de-code a swap entry */
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index ba6ae7f..0a8ac2a 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -157,7 +157,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
}
}
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable)
{
struct list_head *lh = (struct list_head *) pgtable;
@@ -171,7 +172,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
mm->pmd_huge_pte = pgtable;
}
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
struct list_head *lh;
pgtable_t pgtable;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index bfd8768..7250645 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -163,11 +163,12 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,
#endif
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable);
#endif
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
#endif
#ifndef __HAVE_ARCH_PMDP_INVALIDATE
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 78bd84f..84f3180 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -735,7 +735,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
*/
page_add_new_anon_rmap(page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
- pgtable_trans_huge_deposit(mm, pgtable);
+ pgtable_trans_huge_deposit(mm, pmd, pgtable);
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
mm->nr_ptes++;
spin_unlock(&mm->page_table_lock);
@@ -777,7 +777,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
entry = pmd_wrprotect(entry);
entry = pmd_mkhuge(entry);
set_pmd_at(mm, haddr, pmd, entry);
- pgtable_trans_huge_deposit(mm, pgtable);
+ pgtable_trans_huge_deposit(mm, pmd, pgtable);
mm->nr_ptes++;
return true;
}
@@ -922,7 +922,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmdp_set_wrprotect(src_mm, addr, src_pmd);
pmd = pmd_mkold(pmd_wrprotect(pmd));
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
- pgtable_trans_huge_deposit(dst_mm, pgtable);
+ pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
dst_mm->nr_ptes++;
ret = 0;
@@ -992,7 +992,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm,
pmdp_clear_flush(vma, haddr, pmd);
/* leave pmd empty until pte is filled */
- pgtable = pgtable_trans_huge_withdraw(mm);
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
@@ -1087,10 +1087,10 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
goto out_free_pages;
VM_BUG_ON(!PageHead(page));
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmdp_clear_flush(vma, haddr, pmd);
/* leave pmd empty until pte is filled */
- pgtable = pgtable_trans_huge_withdraw(mm);
pmd_populate(mm, &_pmd, pgtable);
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
@@ -1363,7 +1363,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
struct page *page;
pgtable_t pgtable;
pmd_t orig_pmd;
- pgtable = pgtable_trans_huge_withdraw(tlb->mm);
+ pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd);
tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
if (is_huge_zero_pmd(orig_pmd)) {
@@ -1695,7 +1695,7 @@ static int __split_huge_page_map(struct page *page,
pmd = page_check_address_pmd(page, mm, address,
PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
if (pmd) {
- pgtable = pgtable_trans_huge_withdraw(mm);
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
haddr = address;
@@ -2352,7 +2352,7 @@ static void collapse_huge_page(struct mm_struct *mm,
page_add_new_anon_rmap(new_page, vma, address);
set_pmd_at(mm, address, pmd, _pmd);
update_mmu_cache_pmd(vma, address, pmd);
- pgtable_trans_huge_deposit(mm, pgtable);
+ pgtable_trans_huge_deposit(mm, pmd, pgtable);
spin_unlock(&mm->page_table_lock);
*hpage = NULL;
@@ -2658,7 +2658,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
pmdp_clear_flush(vma, haddr, pmd);
/* leave pmd empty until pte is filled */
- pgtable = pgtable_trans_huge_withdraw(mm);
+ pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 0c8323f..e1a6e4f 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -124,7 +124,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable)
{
assert_spin_locked(&mm->page_table_lock);
@@ -141,7 +142,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* no "address" argument so destroys page coloring of some arch */
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
pgtable_t pgtable;
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 09/18] powerpc: Switch 16GB and 16MB explicit hugepages to a different page table format
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
We will be switching PMD_SHIFT to 24 bits to facilitate THP impmenetation.
With PMD_SHIFT set to 24, we now have 16MB huge pages allocated at PGD level.
That means with 32 bit process we cannot allocate normal pages at
all, because we cover the entire address space with one pgd entry. Fix this
by switching to a new page table format for hugepages. With the new page table
format for 16GB and 16MB hugepages we won't allocate hugepage directory. Instead
we encode the PTE information directly at the directory level. This forces 16MB
hugepage at PMD level. This will also make the page take walk much simpler later
when we add the THP support.
With the new table format we have 4 cases for pgds and pmds:
(1) invalid (all zeroes)
(2) pointer to next table, as normal; bottom 6 bits == 0
(3) leaf pte for huge page, bottom two bits != 00
(4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/page.h | 2 +
arch/powerpc/include/asm/pgtable.h | 2 +
arch/powerpc/mm/gup.c | 18 +++-
arch/powerpc/mm/hugetlbpage.c | 176 +++++++++++++++++++++++++++++++------
4 files changed, 168 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 652719c..711e83a 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -373,8 +373,10 @@ static inline int hugepd_ok(hugepd_t hpd)
#endif
#define is_hugepd(pdep) (hugepd_ok(*((hugepd_t *)(pdep))))
+int pgd_huge(pgd_t pgd);
#else /* CONFIG_HUGETLB_PAGE */
#define is_hugepd(pdep) 0
+#define pgd_huge(pgd) 0
#endif /* CONFIG_HUGETLB_PAGE */
struct page;
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 4b52726..7aeb955 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -218,6 +218,8 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr);
+extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr);
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index d7efdbf..4b921af 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -68,7 +68,11 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
next = pmd_addr_end(addr, end);
if (pmd_none(pmd))
return 0;
- if (is_hugepd(pmdp)) {
+ if (pmd_huge(pmd)) {
+ if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
+ write, pages, nr))
+ return 0;
+ } else if (is_hugepd(pmdp)) {
if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
addr, next, write, pages, nr))
return 0;
@@ -92,7 +96,11 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
next = pud_addr_end(addr, end);
if (pud_none(pud))
return 0;
- if (is_hugepd(pudp)) {
+ if (pud_huge(pud)) {
+ if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next,
+ write, pages, nr))
+ return 0;
+ } else if (is_hugepd(pudp)) {
if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
addr, next, write, pages, nr))
return 0;
@@ -153,7 +161,11 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (is_hugepd(pgdp)) {
+ if (pgd_huge(pgd)) {
+ if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next,
+ write, pages, &nr))
+ goto slow;
+ } else if (is_hugepd(pgdp)) {
if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT,
addr, next, write, pages, &nr))
goto slow;
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index b5f4a5f..fbe6be7 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -50,11 +50,69 @@ static unsigned nr_gpages;
#define hugepd_none(hpd) ((hpd).pd == 0)
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * At this point we do the placement change only for BOOK3S 64. This would
+ * possibly work on other subarchs.
+ */
+
+/*
+ * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
+ * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD;
+ */
+int pmd_huge(pmd_t pmd)
+{
+ /*
+ * leaf pte for huge page, bottom two bits != 00
+ */
+ return ((pmd_val(pmd) & 0x3) != 0x0);
+}
+
+int pud_huge(pud_t pud)
+{
+ /*
+ * leaf pte for huge page, bottom two bits != 00
+ */
+ return ((pud_val(pud) & 0x3) != 0x0);
+}
+
+int pgd_huge(pgd_t pgd)
+{
+ /*
+ * leaf pte for huge page, bottom two bits != 00
+ */
+ return ((pgd_val(pgd) & 0x3) != 0x0);
+}
+#else
+int pmd_huge(pmd_t pmd)
+{
+ return 0;
+}
+
+int pud_huge(pud_t pud)
+{
+ return 0;
+}
+
+int pgd_huge(pgd_t pgd)
+{
+ return 0;
+}
+#endif
+
+/*
+ * We have 4 cases for pgds and pmds:
+ * (1) invalid (all zeroes)
+ * (2) pointer to next table, as normal; bottom 6 bits == 0
+ * (3) leaf pte for huge page, bottom two bits != 00
+ * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
+ */
pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
{
pgd_t *pg;
pud_t *pu;
pmd_t *pm;
+ pte_t *ret_pte;
hugepd_t *hpdp = NULL;
unsigned pdshift = PGDIR_SHIFT;
@@ -62,30 +120,43 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
*shift = 0;
pg = pgdir + pgd_index(ea);
- if (is_hugepd(pg)) {
+
+ if (pgd_huge(*pg)) {
+ ret_pte = (pte_t *) pg;
+ goto out;
+ } else if (is_hugepd(pg))
hpdp = (hugepd_t *)pg;
- } else if (!pgd_none(*pg)) {
+ else if (!pgd_none(*pg)) {
pdshift = PUD_SHIFT;
pu = pud_offset(pg, ea);
- if (is_hugepd(pu))
+
+ if (pud_huge(*pu)) {
+ ret_pte = (pte_t *) pu;
+ goto out;
+ } else if (is_hugepd(pu))
hpdp = (hugepd_t *)pu;
else if (!pud_none(*pu)) {
pdshift = PMD_SHIFT;
pm = pmd_offset(pu, ea);
- if (is_hugepd(pm))
+
+ if (pmd_huge(*pm)) {
+ ret_pte = (pte_t *) pm;
+ goto out;
+ } else if (is_hugepd(pm))
hpdp = (hugepd_t *)pm;
- else if (!pmd_none(*pm)) {
+ else if (!pmd_none(*pm))
return pte_offset_kernel(pm, ea);
- }
}
}
-
if (!hpdp)
return NULL;
+ ret_pte = hugepte_offset(hpdp, ea, pdshift);
+ pdshift = hugepd_shift(*hpdp);
+out:
if (shift)
- *shift = hugepd_shift(*hpdp);
- return hugepte_offset(hpdp, ea, pdshift);
+ *shift = pdshift;
+ return ret_pte;
}
EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
@@ -165,6 +236,61 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
#define HUGEPD_PUD_SHIFT PMD_SHIFT
#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * At this point we do the placement change only for BOOK3S 64. This would
+ * possibly work on other subarchs.
+ */
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+{
+ pgd_t *pg;
+ pud_t *pu;
+ pmd_t *pm;
+ hugepd_t *hpdp = NULL;
+ unsigned pshift = __ffs(sz);
+ unsigned pdshift = PGDIR_SHIFT;
+
+ addr &= ~(sz-1);
+ pg = pgd_offset(mm, addr);
+
+ if (pshift == PGDIR_SHIFT)
+ /* 16GB huge page */
+ return (pte_t *) pg;
+ else if (pshift > PUD_SHIFT)
+ /*
+ * We need to use hugepd table
+ */
+ hpdp = (hugepd_t *)pg;
+ else {
+ pdshift = PUD_SHIFT;
+ pu = pud_alloc(mm, pg, addr);
+ if (pshift == PUD_SHIFT)
+ return (pte_t *)pu;
+ else if (pshift > PMD_SHIFT)
+ hpdp = (hugepd_t *)pu;
+ else {
+ pdshift = PMD_SHIFT;
+ pm = pmd_alloc(mm, pu, addr);
+ if (pshift == PMD_SHIFT)
+ /* 16MB hugepage */
+ return (pte_t *)pm;
+ else
+ hpdp = (hugepd_t *)pm;
+ }
+ }
+ if (!hpdp)
+ return NULL;
+
+ BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
+
+ if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
+ return NULL;
+
+ return hugepte_offset(hpdp, addr, pdshift);
+}
+
+#else
+
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
pgd_t *pg;
@@ -202,6 +328,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
return hugepte_offset(hpdp, addr, pdshift);
}
+#endif
#ifdef CONFIG_PPC_FSL_BOOK3E
/* Build list of addresses of gigantic pages. This function is used in early
@@ -465,7 +592,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
do {
pmd = pmd_offset(pud, addr);
next = pmd_addr_end(addr, end);
- if (pmd_none(*pmd))
+ if (pmd_none_or_clear_bad(pmd))
continue;
#ifdef CONFIG_PPC_FSL_BOOK3E
/*
@@ -618,16 +745,6 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
return page;
}
-int pmd_huge(pmd_t pmd)
-{
- return 0;
-}
-
-int pud_huge(pud_t pud)
-{
- return 0;
-}
-
struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
@@ -636,8 +753,8 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
return NULL;
}
-static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask;
unsigned long pte_end;
@@ -873,11 +990,16 @@ static int __init hugetlbpage_init(void)
pdshift = PUD_SHIFT;
else
pdshift = PGDIR_SHIFT;
-
- pgtable_cache_add(pdshift - shift, NULL);
- if (!PGT_CACHE(pdshift - shift))
- panic("hugetlbpage_init(): could not create "
- "pgtable cache for %d bit pagesize\n", shift);
+ /*
+ * if we have pdshift and shift value same, we don't
+ * use pgt cache for hugepd.
+ */
+ if (pdshift != shift) {
+ pgtable_cache_add(pdshift - shift, NULL);
+ if (!PGT_CACHE(pdshift - shift))
+ panic("hugetlbpage_init(): could not create "
+ "pgtable cache for %d bit pagesize\n", shift);
+ }
}
/* Set default large page size. Currently, we pick 16M or 1M
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 11/18] powerpc: Move the pte free routines from common header
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This patch moves the common code to 32/64 bit headers and also duplicate
4K_PAGES and 64K_PAGES section. We will later change the 64 bit 64K_PAGES
version to support smaller PTE fragments. The patch doesn't introduce
any functional changes.
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgalloc-32.h | 45 ++++++++++
arch/powerpc/include/asm/pgalloc-64.h | 157 +++++++++++++++++++++++++++++++---
arch/powerpc/include/asm/pgalloc.h | 46 +---------
3 files changed, 189 insertions(+), 59 deletions(-)
diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index 580cf73..27b2386 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -37,6 +37,17 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+ pgtable_page_dtor(ptepage);
+ __free_page(ptepage);
+}
+
static inline void pgtable_free(void *table, unsigned index_size)
{
BUG_ON(index_size); /* 32-bit doesn't use this */
@@ -45,4 +56,38 @@ static inline void pgtable_free(void *table, unsigned index_size)
#define check_pgt_cache() do { } while (0)
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+ void *table, int shift)
+{
+ unsigned long pgf = (unsigned long)table;
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ pgf |= shift;
+ tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+ void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+ unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+ pgtable_free(table, shift);
+}
+#else
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+ void *table, int shift)
+{
+ pgtable_free(table, shift);
+}
+#endif
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+ unsigned long address)
+{
+ struct page *page = page_address(table);
+
+ tlb_flush_pgtable(tlb, address);
+ pgtable_page_dtor(page);
+ pgtable_free_tlb(tlb, page, 0);
+}
#endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 69e352a..d390123 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -75,8 +75,83 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
#define pmd_pgtable(pmd) pmd_page(pmd)
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+ unsigned long address)
+{
+ return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
+ unsigned long address)
+{
+ struct page *page;
+ pte_t *pte;
+
+ pte = pte_alloc_one_kernel(mm, address);
+ if (!pte)
+ return NULL;
+ page = virt_to_page(pte);
+ pgtable_page_ctor(page);
+ return page;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+ pgtable_page_dtor(ptepage);
+ __free_page(ptepage);
+}
+
+static inline void pgtable_free(void *table, unsigned index_size)
+{
+ if (!index_size)
+ free_page((unsigned long)table);
+ else {
+ BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+ kmem_cache_free(PGT_CACHE(index_size), table);
+ }
+}
+
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+ void *table, int shift)
+{
+ unsigned long pgf = (unsigned long)table;
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ pgf |= shift;
+ tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+ void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+ unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+ pgtable_free(table, shift);
+}
+#else /* !CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+ void *table, int shift)
+{
+ pgtable_free(table, shift);
+}
+#endif /* CONFIG_SMP */
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+ unsigned long address)
+{
+ struct page *page = page_address(table);
+
+ tlb_flush_pgtable(tlb, address);
+ pgtable_page_dtor(page);
+ pgtable_free_tlb(tlb, page, 0);
+}
-#else /* CONFIG_PPC_64K_PAGES */
+#else /* if CONFIG_PPC_64K_PAGES */
#define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd)
@@ -86,31 +161,25 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
pmd_set(pmd, (unsigned long)pte);
}
-#define pmd_populate(mm, pmd, pte_page) \
- pmd_populate_kernel(mm, pmd, page_address(pte_page))
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-#endif /* CONFIG_PPC_64K_PAGES */
-
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+ pgtable_t pte_page)
{
- return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
- GFP_KERNEL|__GFP_REPEAT);
+ pmd_populate_kernel(mm, pmd, page_address(pte_page));
}
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+static inline pgtable_t pmd_pgtable(pmd_t pmd)
{
- kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+ return pmd_page(pmd);
}
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+ return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
- unsigned long address)
+ unsigned long address)
{
struct page *page;
pte_t *pte;
@@ -123,6 +192,17 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
return page;
}
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+ pgtable_page_dtor(ptepage);
+ __free_page(ptepage);
+}
+
static inline void pgtable_free(void *table, unsigned index_size)
{
if (!index_size)
@@ -133,6 +213,55 @@ static inline void pgtable_free(void *table, unsigned index_size)
}
}
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+ void *table, int shift)
+{
+ unsigned long pgf = (unsigned long)table;
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ pgf |= shift;
+ tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+ void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+ unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+ pgtable_free(table, shift);
+}
+#else /* !CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+ void *table, int shift)
+{
+ pgtable_free(table, shift);
+}
+#endif /* CONFIG_SMP */
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+ unsigned long address)
+{
+ struct page *page = page_address(table);
+
+ tlb_flush_pgtable(tlb, address);
+ pgtable_page_dtor(page);
+ pgtable_free_tlb(tlb, page, 0);
+}
+
+#endif /* CONFIG_PPC_64K_PAGES */
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+ GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+}
+
+
#define __pmd_free_tlb(tlb, pmd, addr) \
pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
#ifndef CONFIG_PPC_64K_PAGES
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index bf301ac..e9a9f60 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -3,6 +3,7 @@
#ifdef __KERNEL__
#include <linux/mm.h>
+#include <asm-generic/tlb.h>
#ifdef CONFIG_PPC_BOOK3E
extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
@@ -13,56 +14,11 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
}
#endif /* !CONFIG_PPC_BOOK3E */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
- pgtable_page_dtor(ptepage);
- __free_page(ptepage);
-}
-
#ifdef CONFIG_PPC64
#include <asm/pgalloc-64.h>
#else
#include <asm/pgalloc-32.h>
#endif
-#ifdef CONFIG_SMP
-struct mmu_gather;
-extern void tlb_remove_table(struct mmu_gather *, void *);
-
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
- unsigned long pgf = (unsigned long)table;
- BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
- pgf |= shift;
- tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
- void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
- unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
- pgtable_free(table, shift);
-}
-#else /* CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
- pgtable_free(table, shift);
-}
-#endif /* !CONFIG_SMP */
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
- unsigned long address)
-{
- tlb_flush_pgtable(tlb, address);
- pgtable_page_dtor(ptepage);
- pgtable_free_tlb(tlb, page_address(ptepage), 0);
-}
-
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PGALLOC_H */
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 14/18] powerpc: Decode the pte-lp-encoding bits correctly.
From: Aneesh Kumar K.V @ 2013-04-28 19:37 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367177859-7893-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
We look at both the segment base page size and actual page size and store
the pte-lp-encodings in an array per base page size.
We also update all relevant functions to take actual page size argument
so that we can use the correct PTE LP encoding in HPTE. This should also
get the basic Multiple Page Size per Segment (MPSS) support. This is needed
to enable THP on ppc64.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 3 +-
arch/powerpc/include/asm/mmu-hash64.h | 33 ++++----
arch/powerpc/kvm/book3s_hv.c | 8 +-
arch/powerpc/mm/hash_low_64.S | 18 +++--
arch/powerpc/mm/hash_native_64.c | 135 +++++++++++++++++++++++---------
arch/powerpc/mm/hash_utils_64.c | 121 ++++++++++++++++++----------
arch/powerpc/mm/hugetlbpage-hash64.c | 4 +-
arch/powerpc/platforms/cell/beat_htab.c | 16 ++--
arch/powerpc/platforms/ps3/htab.c | 6 +-
arch/powerpc/platforms/pseries/lpar.c | 6 +-
10 files changed, 233 insertions(+), 117 deletions(-)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 3d6b410..3f3f691 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -50,7 +50,8 @@ struct machdep_calls {
unsigned long prpn,
unsigned long rflags,
unsigned long vflags,
- int psize, int ssize);
+ int psize, int apsize,
+ int ssize);
long (*hpte_remove)(unsigned long hpte_group);
void (*hpte_removebolted)(unsigned long ea,
int psize, int ssize);
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index de9e577..18171a8 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -155,7 +155,7 @@ extern unsigned long htab_hash_mask;
struct mmu_psize_def
{
unsigned int shift; /* number of bits */
- unsigned int penc; /* HPTE encoding */
+ int penc[MMU_PAGE_COUNT]; /* HPTE encoding */
unsigned int tlbiel; /* tlbiel supported for that page size */
unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */
unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */
@@ -200,6 +200,13 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
*/
#define VPN_SHIFT 12
+/*
+ * HPTE Large Page (LP) details
+ */
+#define LP_SHIFT 12
+#define LP_BITS 8
+#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT)
+
#ifndef __ASSEMBLY__
static inline int segment_shift(int ssize)
@@ -255,14 +262,14 @@ static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
/*
* This function sets the AVPN and L fields of the HPTE appropriately
- * for the page size
+ * using the base page size and actual page size.
*/
-static inline unsigned long hpte_encode_v(unsigned long vpn,
- int psize, int ssize)
+static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
+ int actual_psize, int ssize)
{
unsigned long v;
- v = hpte_encode_avpn(vpn, psize, ssize);
- if (psize != MMU_PAGE_4K)
+ v = hpte_encode_avpn(vpn, base_psize, ssize);
+ if (actual_psize != MMU_PAGE_4K)
v |= HPTE_V_LARGE;
return v;
}
@@ -272,19 +279,17 @@ static inline unsigned long hpte_encode_v(unsigned long vpn,
* for the page size. We assume the pa is already "clean" that is properly
* aligned for the requested page size
*/
-static inline unsigned long hpte_encode_r(unsigned long pa, int psize)
+static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
+ int actual_psize)
{
- unsigned long r;
-
/* A 4K page needs no special encoding */
- if (psize == MMU_PAGE_4K)
+ if (actual_psize == MMU_PAGE_4K)
return pa & HPTE_R_RPN;
else {
- unsigned int penc = mmu_psize_defs[psize].penc;
- unsigned int shift = mmu_psize_defs[psize].shift;
- return (pa & ~((1ul << shift) - 1)) | (penc << 12);
+ unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize];
+ unsigned int shift = mmu_psize_defs[actual_psize].shift;
+ return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT);
}
- return r;
}
/*
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 80dcc53..c794a4c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1515,7 +1515,13 @@ static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
(*sps)->page_shift = def->shift;
(*sps)->slb_enc = def->sllp;
(*sps)->enc[0].page_shift = def->shift;
- (*sps)->enc[0].pte_enc = def->penc;
+ /*
+ * Only return base page encoding. We don't want to return
+ * all the supporting pte_enc, because our H_ENTER doesn't
+ * support MPSS yet. Once they do, we can start passing all
+ * support pte_enc here
+ */
+ (*sps)->enc[0].pte_enc = def->penc[linux_psize];
(*sps)++;
}
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index abdd5e2..0e980ac 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -196,7 +196,8 @@ htab_insert_pte:
mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
_GLOBAL(htab_call_hpte_insert1)
bl . /* Patched by htab_finish_init() */
cmpdi 0,r3,0
@@ -219,7 +220,8 @@ _GLOBAL(htab_call_hpte_insert1)
mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
_GLOBAL(htab_call_hpte_insert2)
bl . /* Patched by htab_finish_init() */
cmpdi 0,r3,0
@@ -515,7 +517,8 @@ htab_special_pfn:
mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
_GLOBAL(htab_call_hpte_insert1)
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
@@ -542,7 +545,8 @@ _GLOBAL(htab_call_hpte_insert1)
mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_4K /* page size */
- ld r9,STK_PARAM(R9)(r1) /* segment size */
+ li r9,MMU_PAGE_4K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
_GLOBAL(htab_call_hpte_insert2)
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
@@ -840,7 +844,8 @@ ht64_insert_pte:
mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_64K
- ld r9,STK_PARAM(R9)(r1) /* segment size */
+ li r9,MMU_PAGE_64K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
_GLOBAL(ht64_call_hpte_insert1)
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
@@ -863,7 +868,8 @@ _GLOBAL(ht64_call_hpte_insert1)
mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_64K
- ld r9,STK_PARAM(R9)(r1) /* segment size */
+ li r9,MMU_PAGE_64K /* actual page size */
+ ld r10,STK_PARAM(R9)(r1) /* segment size */
_GLOBAL(ht64_call_hpte_insert2)
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 9d8983a..14e3fe8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -39,7 +39,7 @@
DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbie(unsigned long vpn, int psize, int ssize)
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
{
unsigned long va;
unsigned int penc;
@@ -68,7 +68,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
break;
default:
/* We need 14 to 14 + i bits of va */
- penc = mmu_psize_defs[psize].penc;
+ penc = mmu_psize_defs[psize].penc[apsize];
va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
@@ -80,7 +80,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
}
}
-static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
+static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
{
unsigned long va;
unsigned int penc;
@@ -102,7 +102,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
break;
default:
/* We need 14 to 14 + i bits of va */
- penc = mmu_psize_defs[psize].penc;
+ penc = mmu_psize_defs[psize].penc[apsize];
va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
@@ -114,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
}
-static inline void tlbie(unsigned long vpn, int psize, int ssize, int local)
+static inline void tlbie(unsigned long vpn, int psize, int apsize,
+ int ssize, int local)
{
unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
@@ -125,10 +126,10 @@ static inline void tlbie(unsigned long vpn, int psize, int ssize, int local)
raw_spin_lock(&native_tlbie_lock);
asm volatile("ptesync": : :"memory");
if (use_local) {
- __tlbiel(vpn, psize, ssize);
+ __tlbiel(vpn, psize, apsize, ssize);
asm volatile("ptesync": : :"memory");
} else {
- __tlbie(vpn, psize, ssize);
+ __tlbie(vpn, psize, apsize, ssize);
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
if (lock_tlbie && !use_local)
@@ -156,7 +157,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
unsigned long pa, unsigned long rflags,
- unsigned long vflags, int psize, int ssize)
+ unsigned long vflags, int psize, int apsize, int ssize)
{
struct hash_pte *hptep = htab_address + hpte_group;
unsigned long hpte_v, hpte_r;
@@ -183,8 +184,8 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
if (i == HPTES_PER_GROUP)
return -1;
- hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(pa, psize) | rflags;
+ hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+ hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED)) {
DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
@@ -244,6 +245,45 @@ static long native_hpte_remove(unsigned long hpte_group)
return i;
}
+static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
+{
+ int i, shift;
+ unsigned int mask;
+ /* Look at the 8 bit LP value */
+ unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+
+ if (!(hptep->v & HPTE_V_VALID))
+ return -1;
+
+ /* First check if it is large page */
+ if (!(hptep->v & HPTE_V_LARGE))
+ return MMU_PAGE_4K;
+
+ /* start from 1 ignoring MMU_PAGE_4K */
+ for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+ /* invalid penc */
+ if (mmu_psize_defs[psize].penc[i] == -1)
+ continue;
+ /*
+ * encoding bits per actual page size
+ * PTE LP actual page size
+ * rrrr rrrz >=8KB
+ * rrrr rrzz >=16KB
+ * rrrr rzzz >=32KB
+ * rrrr zzzz >=64KB
+ * .......
+ */
+ shift = mmu_psize_defs[i].shift - LP_SHIFT;
+ if (shift > LP_BITS)
+ shift = LP_BITS;
+ mask = (1 << shift) - 1;
+ if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+ return i;
+ }
+ return -1;
+}
+
static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long vpn, int psize, int ssize,
int local)
@@ -251,6 +291,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v, want_v;
int ret = 0;
+ int actual_psize;
want_v = hpte_encode_avpn(vpn, psize, ssize);
@@ -260,9 +301,13 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
native_lock_hpte(hptep);
hpte_v = hptep->v;
-
+ actual_psize = hpte_actual_psize(hptep, psize);
+ if (actual_psize < 0) {
+ native_unlock_hpte(hptep);
+ return -1;
+ }
/* Even if we miss, we need to invalidate the TLB */
- if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
+ if (!HPTE_V_COMPARE(hpte_v, want_v)) {
DBG_LOW(" -> miss\n");
ret = -1;
} else {
@@ -274,7 +319,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
native_unlock_hpte(hptep);
/* Ensure it is out of the tlb too. */
- tlbie(vpn, psize, ssize, local);
+ tlbie(vpn, psize, actual_psize, ssize, local);
return ret;
}
@@ -315,6 +360,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
int psize, int ssize)
{
+ int actual_psize;
unsigned long vpn;
unsigned long vsid;
long slot;
@@ -327,13 +373,16 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
if (slot == -1)
panic("could not find page to bolt\n");
hptep = htab_address + slot;
+ actual_psize = hpte_actual_psize(hptep, psize);
+ if (actual_psize < 0)
+ return;
/* Update the HPTE */
hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
(newpp & (HPTE_R_PP | HPTE_R_N));
/* Ensure it is out of the tlb too. */
- tlbie(vpn, psize, ssize, 0);
+ tlbie(vpn, psize, actual_psize, ssize, 0);
}
static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
@@ -343,6 +392,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
unsigned long hpte_v;
unsigned long want_v;
unsigned long flags;
+ int actual_psize;
local_irq_save(flags);
@@ -352,35 +402,38 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
native_lock_hpte(hptep);
hpte_v = hptep->v;
+ actual_psize = hpte_actual_psize(hptep, psize);
+ if (actual_psize < 0) {
+ native_unlock_hpte(hptep);
+ local_irq_restore(flags);
+ return;
+ }
/* Even if we miss, we need to invalidate the TLB */
- if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
+ if (!HPTE_V_COMPARE(hpte_v, want_v))
native_unlock_hpte(hptep);
else
/* Invalidate the hpte. NOTE: this also unlocks it */
hptep->v = 0;
/* Invalidate the TLB */
- tlbie(vpn, psize, ssize, local);
+ tlbie(vpn, psize, actual_psize, ssize, local);
local_irq_restore(flags);
}
-#define LP_SHIFT 12
-#define LP_BITS 8
-#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT)
-
static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
- int *psize, int *ssize, unsigned long *vpn)
+ int *psize, int *apsize, int *ssize, unsigned long *vpn)
{
unsigned long avpn, pteg, vpi;
unsigned long hpte_r = hpte->r;
unsigned long hpte_v = hpte->v;
unsigned long vsid, seg_off;
- int i, size, shift, penc;
+ int i, size, a_size, shift, penc;
- if (!(hpte_v & HPTE_V_LARGE))
- size = MMU_PAGE_4K;
- else {
+ if (!(hpte_v & HPTE_V_LARGE)) {
+ size = MMU_PAGE_4K;
+ a_size = MMU_PAGE_4K;
+ } else {
for (i = 0; i < LP_BITS; i++) {
if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
break;
@@ -388,19 +441,26 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
penc = LP_MASK(i+1) >> LP_SHIFT;
for (size = 0; size < MMU_PAGE_COUNT; size++) {
- /* 4K pages are not represented by LP */
- if (size == MMU_PAGE_4K)
- continue;
-
/* valid entries have a shift value */
if (!mmu_psize_defs[size].shift)
continue;
+ for (a_size = 0; a_size < MMU_PAGE_COUNT; a_size++) {
- if (penc == mmu_psize_defs[size].penc)
- break;
+ /* 4K pages are not represented by LP */
+ if (a_size == MMU_PAGE_4K)
+ continue;
+
+ /* valid entries have a shift value */
+ if (!mmu_psize_defs[a_size].shift)
+ continue;
+
+ if (penc == mmu_psize_defs[size].penc[a_size])
+ goto out;
+ }
}
}
+out:
/* This works for all page sizes, and for 256M and 1T segments */
*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
shift = mmu_psize_defs[size].shift;
@@ -433,7 +493,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
default:
*vpn = size = 0;
}
- *psize = size;
+ *psize = size;
+ *apsize = a_size;
}
/*
@@ -451,7 +512,7 @@ static void native_hpte_clear(void)
struct hash_pte *hptep = htab_address;
unsigned long hpte_v;
unsigned long pteg_count;
- int psize, ssize;
+ int psize, apsize, ssize;
pteg_count = htab_hash_mask + 1;
@@ -477,9 +538,9 @@ static void native_hpte_clear(void)
* already hold the native_tlbie_lock.
*/
if (hpte_v & HPTE_V_VALID) {
- hpte_decode(hptep, slot, &psize, &ssize, &vpn);
+ hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
hptep->v = 0;
- __tlbie(vpn, psize, ssize);
+ __tlbie(vpn, psize, apsize, ssize);
}
}
@@ -540,7 +601,7 @@ static void native_flush_hash_range(unsigned long number, int local)
pte_iterate_hashed_subpages(pte, psize,
vpn, index, shift) {
- __tlbiel(vpn, psize, ssize);
+ __tlbiel(vpn, psize, psize, ssize);
} pte_iterate_hashed_end();
}
asm volatile("ptesync":::"memory");
@@ -557,7 +618,7 @@ static void native_flush_hash_range(unsigned long number, int local)
pte_iterate_hashed_subpages(pte, psize,
vpn, index, shift) {
- __tlbie(vpn, psize, ssize);
+ __tlbie(vpn, psize, psize, ssize);
} pte_iterate_hashed_end();
}
asm volatile("eieio; tlbsync; ptesync":::"memory");
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index f410c3e..d98626a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -126,7 +126,7 @@ static struct mmu_psize_def mmu_psize_defaults_old[] = {
[MMU_PAGE_4K] = {
.shift = 12,
.sllp = 0,
- .penc = 0,
+ .penc = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
.avpnm = 0,
.tlbiel = 0,
},
@@ -140,14 +140,15 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
[MMU_PAGE_4K] = {
.shift = 12,
.sllp = 0,
- .penc = 0,
+ .penc = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
.avpnm = 0,
.tlbiel = 1,
},
[MMU_PAGE_16M] = {
.shift = 24,
.sllp = SLB_VSID_L,
- .penc = 0,
+ .penc = {[0 ... MMU_PAGE_16M - 1] = -1, [MMU_PAGE_16M] = 0,
+ [MMU_PAGE_16M + 1 ... MMU_PAGE_COUNT - 1] = -1 },
.avpnm = 0x1UL,
.tlbiel = 0,
},
@@ -209,7 +210,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
BUG_ON(!ppc_md.hpte_insert);
ret = ppc_md.hpte_insert(hpteg, vpn, paddr, tprot,
- HPTE_V_BOLTED, psize, ssize);
+ HPTE_V_BOLTED, psize, psize, ssize);
if (ret < 0)
break;
@@ -276,6 +277,30 @@ static void __init htab_init_seg_sizes(void)
of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL);
}
+static int __init get_idx_from_shift(unsigned int shift)
+{
+ int idx = -1;
+
+ switch (shift) {
+ case 0xc:
+ idx = MMU_PAGE_4K;
+ break;
+ case 0x10:
+ idx = MMU_PAGE_64K;
+ break;
+ case 0x14:
+ idx = MMU_PAGE_1M;
+ break;
+ case 0x18:
+ idx = MMU_PAGE_16M;
+ break;
+ case 0x22:
+ idx = MMU_PAGE_16G;
+ break;
+ }
+ return idx;
+}
+
static int __init htab_dt_scan_page_sizes(unsigned long node,
const char *uname, int depth,
void *data)
@@ -295,60 +320,61 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
size /= 4;
cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
while(size > 0) {
- unsigned int shift = prop[0];
+ unsigned int base_shift = prop[0];
unsigned int slbenc = prop[1];
unsigned int lpnum = prop[2];
- unsigned int lpenc = 0;
struct mmu_psize_def *def;
- int idx = -1;
+ int idx, base_idx;
size -= 3; prop += 3;
- while(size > 0 && lpnum) {
- if (prop[0] == shift)
- lpenc = prop[1];
- prop += 2; size -= 2;
- lpnum--;
+ base_idx = get_idx_from_shift(base_shift);
+ if (base_idx < 0) {
+ /*
+ * skip the pte encoding also
+ */
+ prop += lpnum * 2; size -= lpnum * 2;
+ continue;
}
- switch(shift) {
- case 0xc:
- idx = MMU_PAGE_4K;
- break;
- case 0x10:
- idx = MMU_PAGE_64K;
- break;
- case 0x14:
- idx = MMU_PAGE_1M;
- break;
- case 0x18:
- idx = MMU_PAGE_16M;
+ def = &mmu_psize_defs[base_idx];
+ if (base_idx == MMU_PAGE_16M)
cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
- break;
- case 0x22:
- idx = MMU_PAGE_16G;
- break;
- }
- if (idx < 0)
- continue;
- def = &mmu_psize_defs[idx];
- def->shift = shift;
- if (shift <= 23)
+
+ def->shift = base_shift;
+ if (base_shift <= 23)
def->avpnm = 0;
else
- def->avpnm = (1 << (shift - 23)) - 1;
+ def->avpnm = (1 << (base_shift - 23)) - 1;
def->sllp = slbenc;
- def->penc = lpenc;
- /* We don't know for sure what's up with tlbiel, so
+ /*
+ * We don't know for sure what's up with tlbiel, so
* for now we only set it for 4K and 64K pages
*/
- if (idx == MMU_PAGE_4K || idx == MMU_PAGE_64K)
+ if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
def->tlbiel = 1;
else
def->tlbiel = 0;
- DBG(" %d: shift=%02x, sllp=%04lx, avpnm=%08lx, "
- "tlbiel=%d, penc=%d\n",
- idx, shift, def->sllp, def->avpnm, def->tlbiel,
- def->penc);
+ while (size > 0 && lpnum) {
+ unsigned int shift = prop[0];
+ int penc = prop[1];
+
+ prop += 2; size -= 2;
+ lpnum--;
+
+ idx = get_idx_from_shift(shift);
+ if (idx < 0)
+ continue;
+
+ if (penc == -1)
+ pr_err("Invalid penc for base_shift=%d "
+ "shift=%d\n", base_shift, shift);
+
+ def->penc[idx] = penc;
+ DBG(" %d: shift=%02x, sllp=%04lx, "
+ "avpnm=%08lx, tlbiel=%d, penc=%d\n",
+ idx, shift, def->sllp, def->avpnm,
+ def->tlbiel, def->penc[idx]);
+ }
}
return 1;
}
@@ -397,10 +423,21 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
}
#endif /* CONFIG_HUGETLB_PAGE */
+static void mmu_psize_set_default_penc(void)
+{
+ int bpsize, apsize;
+ for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
+ for (apsize = 0; apsize < MMU_PAGE_COUNT; apsize++)
+ mmu_psize_defs[bpsize].penc[apsize] = -1;
+}
+
static void __init htab_init_page_sizes(void)
{
int rc;
+ /* se the invalid penc to -1 */
+ mmu_psize_set_default_penc();
+
/* Default to 4K pages only */
memcpy(mmu_psize_defs, mmu_psize_defaults_old,
sizeof(mmu_psize_defaults_old));
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index cecad34..e0d52ee 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -103,7 +103,7 @@ repeat:
/* Insert into the hash table, primary slot */
slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
- mmu_psize, ssize);
+ mmu_psize, mmu_psize, ssize);
/* Primary is full, try the secondary */
if (unlikely(slot == -1)) {
@@ -111,7 +111,7 @@ repeat:
HPTES_PER_GROUP) & ~0x7UL;
slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags,
HPTE_V_SECONDARY,
- mmu_psize, ssize);
+ mmu_psize, mmu_psize, ssize);
if (slot == -1) {
if (mftb() & 0x1)
hpte_group = ((hash & htab_hash_mask) *
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 472f9a7..246e1d8 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -90,7 +90,7 @@ static inline unsigned int beat_read_mask(unsigned hpte_group)
static long beat_lpar_hpte_insert(unsigned long hpte_group,
unsigned long vpn, unsigned long pa,
unsigned long rflags, unsigned long vflags,
- int psize, int ssize)
+ int psize, int apsize, int ssize)
{
unsigned long lpar_rc;
u64 hpte_v, hpte_r, slot;
@@ -103,9 +103,9 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
"rflags=%lx, vflags=%lx, psize=%d)\n",
hpte_group, va, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
+ hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) |
vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(pa, psize) | rflags;
+ hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
@@ -314,7 +314,7 @@ void __init hpte_init_beat(void)
static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
unsigned long vpn, unsigned long pa,
unsigned long rflags, unsigned long vflags,
- int psize, int ssize)
+ int psize, int apsize, int ssize)
{
unsigned long lpar_rc;
u64 hpte_v, hpte_r, slot;
@@ -327,9 +327,9 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
"rflags=%lx, vflags=%lx, psize=%d)\n",
hpte_group, vpn, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
+ hpte_v = hpte_encode_v(vpn, psize, apsize, MMU_SEGSIZE_256M) |
vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(pa, psize) | rflags;
+ hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
@@ -373,7 +373,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
unsigned long pss;
want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
- pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
+ pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize];
DBG_LOW(" update: "
"avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ",
@@ -403,7 +403,7 @@ static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
slot, vpn, psize, local);
want_v = hpte_encode_avpn(vpn, psize, MMU_SEGSIZE_256M);
- pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
+ pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc[psize];
lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss);
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index cd8f2fb..177a2f7 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -46,7 +46,7 @@ static DEFINE_SPINLOCK(ps3_htab_lock);
static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
unsigned long pa, unsigned long rflags, unsigned long vflags,
- int psize, int ssize)
+ int psize, int apsize, int ssize)
{
int result;
u64 hpte_v, hpte_r;
@@ -62,8 +62,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
*/
vflags &= ~HPTE_V_SECONDARY;
- hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags;
+ hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+ hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize, apsize) | rflags;
spin_lock_irqsave(&ps3_htab_lock, flags);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 9b02ab1..6d62072 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -109,7 +109,7 @@ void vpa_init(int cpu)
static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
unsigned long vpn, unsigned long pa,
unsigned long rflags, unsigned long vflags,
- int psize, int ssize)
+ int psize, int apsize, int ssize)
{
unsigned long lpar_rc;
unsigned long flags;
@@ -121,8 +121,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
"pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
hpte_group, vpn, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(pa, psize) | rflags;
+ hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+ hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
--
1.8.1.2
^ permalink raw reply related
* [PATCH -V7 00/10] THP support for PPC64 (Patchset 2)
From: Aneesh Kumar K.V @ 2013-04-28 19:51 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev
Hi,
This is the second patchset needed to support THP on ppc64. Some of the changes
included in this series are tricky in that it changes the powerpc linux page table
walk subtly. We also overload few of the pte flags for ptes at PMD leve (huge
page PTEs). This patchset require closer review before merging upstream.
I have split the patch series into two patchset, so that we can look at getting
prerequisite patches upstream in 3.10.
Some numbers:
The latency measurements code from Anton found at
http://ozlabs.org/~anton/junkcode/latency2001.c
64K page size (With THP support)
--------------------------
[root@llmp24l02 test]# ./latency2001 8G
8589934592 428.49 cycles 120.50 ns
[root@llmp24l02 test]# ./latency2001 -l 8G
8589934592 471.16 cycles 132.50 ns
[root@llmp24l02 test]# echo never > /sys/kernel/mm/transparent_hugepage/enabled
[root@llmp24l02 test]# ./latency2001 8G
8589934592 766.52 cycles 215.56 ns
[root@llmp24l02 test]#
4K page size (No THP support for 4K)
----------------------------
[root@llmp24l02 test]# ./latency2001 8G
8589934592 814.88 cycles 229.16 ns
[root@llmp24l02 test]# ./latency2001 -l 8G
8589934592 463.69 cycles 130.40 ns
[root@llmp24l02 test]#
We are close to hugetlbfs in latency and we can achieve this with zero
config/page reservation. Most of the allocations above are fault allocated.
Another test that does 50000000 random access over 1GB area goes from
2.65 seconds to 1.07 seconds with this patchset.
split_huge_page impact:
---------------------
To look at the performance impact of large page invalidate, I tried the below
experiment. The test involved, accessing a large contiguous region of memory
location as below
for (i = 0; i < size; i += PAGE_SIZE)
data[i] = i;
We wanted to access the data in sequential order so that we look at the
worst case THP performance. Accesing the data in sequential order implies
we have the Page table cached and overhead of TLB miss is as minimal as
possible. We also don't touch the entire page, because that can result in
cache evict.
After we touched the full range as above, we now call mprotect on each
of that page. A mprotect will result in a hugepage split. This should
allow us to measure the impact of hugepage split.
for (i = 0; i < size; i += PAGE_SIZE)
mprotect(&data[i], PAGE_SIZE, PROT_READ);
Split hugepage impact:
---------------------
THP enabled: 2.851561705 seconds for test completion
THP disable: 3.599146098 seconds for test completion
We are 20.7% better than non THP case even when we have all the large pages split.
Detailed output:
THP enabled:
---------------------------------------
[root@llmp24l02 ~]# cat /proc/vmstat | grep thp
thp_fault_alloc 0
thp_fault_fallback 0
thp_collapse_alloc 0
thp_collapse_alloc_failed 0
thp_split 0
thp_zero_page_alloc 0
thp_zero_page_alloc_failed 0
[root@llmp24l02 ~]# /root/thp/tools/perf/perf stat -e page-faults,dTLB-load-misses ./split-huge-page-mpro 20G
time taken to touch all the data in ns: 2763096913
Performance counter stats for './split-huge-page-mpro 20G':
1,581 page-faults
3,159 dTLB-load-misses
2.851561705 seconds time elapsed
[root@llmp24l02 ~]#
[root@llmp24l02 ~]# cat /proc/vmstat | grep thp
thp_fault_alloc 1279
thp_fault_fallback 0
thp_collapse_alloc 0
thp_collapse_alloc_failed 0
thp_split 1279
thp_zero_page_alloc 0
thp_zero_page_alloc_failed 0
[root@llmp24l02 ~]#
77.05% split-huge-page [kernel.kallsyms] [k] .clear_user_page
7.10% split-huge-page [kernel.kallsyms] [k] .perf_event_mmap_ctx
1.51% split-huge-page split-huge-page-mpro [.] 0x0000000000000a70
0.96% split-huge-page [unknown] [H] 0x000000000157e3bc
0.81% split-huge-page [kernel.kallsyms] [k] .up_write
0.76% split-huge-page [kernel.kallsyms] [k] .perf_event_mmap
0.76% split-huge-page [kernel.kallsyms] [k] .down_write
0.74% split-huge-page [kernel.kallsyms] [k] .lru_add_page_tail
0.61% split-huge-page [kernel.kallsyms] [k] .split_huge_page
0.59% split-huge-page [kernel.kallsyms] [k] .change_protection
0.51% split-huge-page [kernel.kallsyms] [k] .release_pages
0.96% split-huge-page [unknown] [H] 0x000000000157e3bc
|
|--79.44%-- reloc_start
| |
| |--86.54%-- .__pSeries_lpar_hugepage_invalidate
| | .pSeries_lpar_hugepage_invalidate
| | .hpte_need_hugepage_flush
| | .split_huge_page
| | .__split_huge_page_pmd
| | .vma_adjust
| | .vma_merge
| | .mprotect_fixup
| | .SyS_mprotect
THP disabled:
---------------
[root@llmp24l02 ~]# echo never > /sys/kernel/mm/transparent_hugepage/enabled
[root@llmp24l02 ~]# /root/thp/tools/perf/perf stat -e page-faults,dTLB-load-misses ./split-huge-page-mpro 20G
time taken to touch all the data in ns: 3513767220
Performance counter stats for './split-huge-page-mpro 20G':
3,27,726 page-faults
3,29,654 dTLB-load-misses
3.599146098 seconds time elapsed
[root@llmp24l02 ~]#
Changes from V6:
* split the patch series into two patchset.
* Address review feedback.
Changes from V5:
* Address review comments
* Added new patch to not use hugepd for explcit hugepages. Explicit hugepaes
now use PTE format similar to transparent hugepages.
* We don't use page->_mapcount for tracking free PTE frags in a PTE page.
* rebased to a86d52667d8eda5de39393ce737794403bdce1eb
* Tested with libhugetlbfs test suite
Changes from V4:
* Fix bad page error in page_table_alloc
BUG: Bad page state in process stream pfn:f1a59
page:f0000000034dc378 count:1 mapcount:0 mapping: (null) index:0x0
[c000000f322c77d0] [c00000000015e198] .bad_page+0xe8/0x140
[c000000f322c7860] [c00000000015e3c4] .free_pages_prepare+0x1d4/0x1e0
[c000000f322c7910] [c000000000160450] .free_hot_cold_page+0x50/0x230
[c000000f322c79c0] [c00000000003ad18] .page_table_alloc+0x168/0x1c0
Changes from V3:
* PowerNV boot fixes
Change from V2:
* Change patch "powerpc: Reduce PTE table memory wastage" to use much simpler approach
for PTE page sharing.
* Changes to handle huge pages in KVM code.
* Address other review comments
Changes from V1
* Address review comments
* More patch split
* Add batch hpte invalidate for hugepages.
Changes from RFC V2:
* Address review comments
* More code cleanup and patch split
Changes from RFC V1:
* HugeTLB fs now works
* Compile issues fixed
* rebased to v3.8
* Patch series reorded so that ppc64 cleanups and MM THP changes are moved
early in the series. This should help in picking those patches early.
Thanks,
-aneesh
^ permalink raw reply
* [PATCH -V7 01/10] powerpc/THP: Double the PMD table size for THP
From: Aneesh Kumar K.V @ 2013-04-28 19:51 UTC (permalink / raw)
To: benh, paulus, dwg, linux-mm; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1367178711-8232-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
THP code does PTE page allocation along with large page request and deposit them
for later use. This is to ensure that we won't have any failures when we split
hugepages to regular pages.
On powerpc we want to use the deposited PTE page for storing hash pte slot and
secondary bit information for the HPTEs. We use the second half
of the pmd table to save the deposted PTE page.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgalloc-64.h | 6 +++---
arch/powerpc/include/asm/pgtable-ppc64.h | 6 +++++-
arch/powerpc/mm/init_64.c | 9 ++++++---
3 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 91acb12..c756463 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -221,17 +221,17 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+ return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
GFP_KERNEL|__GFP_REPEAT);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
- kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+ kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
}
#define __pmd_free_tlb(tlb, pmd, addr) \
- pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
+ pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
#ifndef CONFIG_PPC_64K_PAGES
#define __pud_free_tlb(tlb, pud, addr) \
pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index e3d55f6f..ab84332 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -20,7 +20,11 @@
PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
#define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
-
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX (PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX PMD_INDEX_SIZE
+#endif
/*
* Define the address range of the kernel non-linear virtual area
*/
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a56de85..97f741d 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -88,7 +88,11 @@ static void pgd_ctor(void *addr)
static void pmd_ctor(void *addr)
{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ memset(addr, 0, PMD_TABLE_SIZE * 2);
+#else
memset(addr, 0, PMD_TABLE_SIZE);
+#endif
}
struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
@@ -137,10 +141,9 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
void pgtable_cache_init(void)
{
pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
- pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
- if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+ pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+ if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
panic("Couldn't allocate pgtable caches");
-
/* In all current configs, when the PUD index exists it's the
* same size as either the pgd or pmd index. Verify that the
* initialization above has also created a PUD cache. This
--
1.8.1.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox