* Re: next BUG: using smp_processor_id() in preemptible
From: Hugh Dickins @ 2011-12-22 12:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: linuxppc-dev
In-Reply-To: <alpine.LSU.2.00.1112051539100.3938@sister.anvils>
On Mon, 5 Dec 2011, Hugh Dickins wrote:
> 3.2.0-rc3-next-20111202 with CONFIG_DEBUG_PREEMPT=y gives me lots of
>
> Dec 4 20:03:19 thorn kernel: BUG: using smp_processor_id() in preemptible [00000000] code: startpar/1365
> Dec 4 20:03:19 thorn kernel: caller is .arch_local_irq_restore+0x44/0x90
> Dec 4 20:03:19 thorn kernel: Call Trace:
> Dec 4 20:03:19 thorn kernel: [c0000001b45a7c60] [c000000000011fe8] .show_stack+0x6c/0x16c (unreliable)
> Dec 4 20:03:19 thorn kernel: [c0000001b45a7d10] [c00000000024318c] .debug_smp_processor_id+0xe4/0x11c
> Dec 4 20:03:19 thorn kernel: [c0000001b45a7da0] [c00000000000e2e8] .arch_local_irq_restore+0x44/0x90
> Dec 4 20:03:19 thorn kernel: [c0000001b45a7e30] [c000000000005870] .do_hash_page+0x70/0x74
> Dec 4 20:03:21 thorn kernel: debug_smp_processor_id: 21950 callbacks suppressed
>
> from the u64 *next_tb = &__get_cpu_var(decrementers_next_tb)
> in decrementer_check_overflow(): I've no idea whether it's safe
> just to use get_cpu_var then put_cpu_var there instead,
> but no hurry, I can survive with DEBUG_PREEMPT off.
Still a problem in 3.2.0-rc6-next-20111222
Hugh
^ permalink raw reply
* [PATCH v3 4/4] fsl_pmc: update device bindings
From: Zhao Chenhui @ 2011-12-22 11:43 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1324554214-19502-1-git-send-email-chenhui.zhao@freescale.com>
From: Li Yang <leoli@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
---
.../devicetree/bindings/powerpc/fsl/pmc.txt | 63 +++++++++++--------
1 files changed, 36 insertions(+), 27 deletions(-)
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/pmc.txt b/Documentation/devicetree/bindings/powerpc/fsl/pmc.txt
index 07256b7..d84b4f8 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/pmc.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/pmc.txt
@@ -9,22 +9,27 @@ Properties:
"fsl,mpc8548-pmc" should be listed for any chip whose PMC is
compatible. "fsl,mpc8536-pmc" should also be listed for any chip
- whose PMC is compatible, and implies deep-sleep capability.
+ whose PMC is compatible, and implies deep-sleep capability and
+ wake on user defined packet(wakeup on ARP).
+
+ "fsl,p1022-pmc" should be listed for any chip whose PMC is
+ compatible, and implies lossless Ethernet capability during sleep.
"fsl,mpc8641d-pmc" should be listed for any chip whose PMC is
compatible; all statements below that apply to "fsl,mpc8548-pmc" also
apply to "fsl,mpc8641d-pmc".
Compatibility does not include bit assignments in SCCR/PMCDR/DEVDISR; these
- bit assignments are indicated via the sleep specifier in each device's
- sleep property.
+ bit assignments are indicated via the clock nodes. Device which has a
+ controllable clock source should have a "clk-handle" property pointing
+ to the clock node.
- reg: For devices compatible with "fsl,mpc8349-pmc", the first resource
is the PMC block, and the second resource is the Clock Configuration
block.
- For devices compatible with "fsl,mpc8548-pmc", the first resource
- is a 32-byte block beginning with DEVDISR.
+ For devices compatible with "fsl,mpc8548-pmc", the second resource
+ is a 32-byte block beginning with DEVDISR if supported.
- interrupts: For "fsl,mpc8349-pmc"-compatible devices, the first
resource is the PMC block interrupt.
@@ -33,31 +38,35 @@ Properties:
this is a phandle to an "fsl,gtm" node on which timer 4 can be used as
a wakeup source from deep sleep.
-Sleep specifiers:
+Clock nodes:
+The clock nodes are to describe the masks in PM controller registers for each
+soc clock.
+- fsl,pmcdr-mask: For "fsl,mpc8548-pmc"-compatible devices, the mask will be
+ ORed into PMCDR before suspend if the device using this clock is the wake-up
+ source and need to be running during low power mode; clear the mask if
+ otherwise.
- fsl,mpc8349-pmc: Sleep specifiers consist of one cell. For each bit
- that is set in the cell, the corresponding bit in SCCR will be saved
- and cleared on suspend, and restored on resume. This sleep controller
- supports disabling and resuming devices at any time.
+- fsl,sccr-mask: For "fsl,mpc8349-pmc"-compatible devices, the corresponding
+ bit specified by the mask in SCCR will be saved and cleared on suspend, and
+ restored on resume.
- fsl,mpc8536-pmc: Sleep specifiers consist of three cells, the third of
- which will be ORed into PMCDR upon suspend, and cleared from PMCDR
- upon resume. The first two cells are as described for fsl,mpc8578-pmc.
- This sleep controller only supports disabling devices during system
- sleep, or permanently.
-
- fsl,mpc8548-pmc: Sleep specifiers consist of one or two cells, the
- first of which will be ORed into DEVDISR (and the second into
- DEVDISR2, if present -- this cell should be zero or absent if the
- hardware does not have DEVDISR2) upon a request for permanent device
- disabling. This sleep controller does not support configuring devices
- to disable during system sleep (unless supported by another compatible
- match), or dynamically.
+- fsl,devdisr-mask: Contain one or two cells, depending on the availability of
+ DEVDISR2 register. For compatible devices, the mask will be ORed into DEVDISR
+ or DEVDISR2 when the clock should be permenently disabled.
Example:
- power@b00 {
- compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
- reg = <0xb00 0x100 0xa00 0x100>;
- interrupts = <80 8>;
+ power@e0070 {
+ compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc";
+ reg = <0xe0070 0x20>;
+
+ etsec1_clk: soc-clk@24 {
+ fsl,pmcdr-mask = <0x00000080>;
+ };
+ etsec2_clk: soc-clk@25 {
+ fsl,pmcdr-mask = <0x00000040>;
+ };
+ etsec3_clk: soc-clk@26 {
+ fsl,pmcdr-mask = <0x00000020>;
+ };
};
--
1.6.4.1
^ permalink raw reply related
* [PATCH v3 2/4] powerpc/85xx: add sleep and deep sleep support
From: Zhao Chenhui @ 2011-12-22 11:43 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1324554214-19502-1-git-send-email-chenhui.zhao@freescale.com>
From: Li Yang <leoli@freescale.com>
In sleep PM mode, the clocks of e500 core and unused IP blocks is
turned off. IP blocks which are allowed to wake up the processor
are still running.
Some Freescale chips like MPC8536 and P1022 has deep sleep PM mode
in addtion to the sleep PM mode.
While in deep sleep PM mode, additionally, the power supply is
removed from e500 core and most IP blocks. Only the blocks needed
to wake up the chip out of deep sleep are ON.
This patch supports 32-bit and 36-bit address space.
The sleep mode is equal to the Standby state in Linux. The deep sleep
mode is equal to the Suspend-to-RAM state of Linux Power Management.
Command to enter sleep mode.
echo standby > /sys/power/state
Command to enter deep sleep mode.
echo mem > /sys/power/state
Signed-off-by: Dave Liu <daveliu@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Jin Qing <b24347@freescale.com>
Signed-off-by: Jerry Huang <Chang-Ming.Huang@freescale.com>
Cc: Scott Wood <scottwood@freescale.com>
Signed-off-by: Zhao Chenhui <chenhui.zhao@freescale.com>
---
arch/powerpc/kernel/Makefile | 3 +
arch/powerpc/kernel/l2cache_85xx.S | 53 +++
arch/powerpc/platforms/85xx/Makefile | 3 +
arch/powerpc/platforms/85xx/sleep.S | 609 ++++++++++++++++++++++++++++++++++
arch/powerpc/sysdev/fsl_pmc.c | 91 ++++-
arch/powerpc/sysdev/fsl_soc.h | 5 +
6 files changed, 746 insertions(+), 18 deletions(-)
create mode 100644 arch/powerpc/kernel/l2cache_85xx.S
create mode 100644 arch/powerpc/platforms/85xx/sleep.S
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ce4f7f1..bfd687b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -63,6 +63,9 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
ifeq ($(CONFIG_PPC32),y)
obj-$(CONFIG_E500) += idle_e500.o
endif
+ifneq ($(CONFIG_PPC_E500MC),y)
+obj-$(CONFIG_PPC_85xx) += l2cache_85xx.o
+endif
obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
obj-$(CONFIG_TAU) += tau_6xx.o
obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o
diff --git a/arch/powerpc/kernel/l2cache_85xx.S b/arch/powerpc/kernel/l2cache_85xx.S
new file mode 100644
index 0000000..95dfef0
--- /dev/null
+++ b/arch/powerpc/kernel/l2cache_85xx.S
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2009-2011 Freescale Semiconductor, Inc. All rights reserved.
+ * Scott Wood <scottwood@freescale.com>
+ * Dave Liu <daveliu@freescale.com>
+ * implement the L2 cache operations of e500 based L2 controller
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+ .section .text
+
+ /* r3 = virtual address of L2 controller, WIMG = 01xx */
+_GLOBAL(flush_disable_L2)
+ /* It's a write-through cache, so only invalidation is needed. */
+ mbar
+ isync
+ lwz r4, 0(r3)
+ li r5, 1
+ rlwimi r4, r5, 30, 0xc0000000
+ stw r4, 0(r3)
+
+ /* Wait for the invalidate to finish */
+1: lwz r4, 0(r3)
+ andis. r4, r4, 0x4000
+ bne 1b
+ mbar
+
+ blr
+
+ /* r3 = virtual address of L2 controller, WIMG = 01xx */
+_GLOBAL(invalidate_enable_L2)
+ mbar
+ isync
+ lwz r4, 0(r3)
+ li r5, 3
+ rlwimi r4, r5, 30, 0xc0000000
+ stw r4, 0(r3)
+
+ /* Wait for the invalidate to finish */
+1: lwz r4, 0(r3)
+ andis. r4, r4, 0x4000
+ bne 1b
+ mbar
+
+ blr
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 9cb2d43..f9fcbf4 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -2,6 +2,9 @@
# Makefile for the PowerPC 85xx linux kernel.
#
obj-$(CONFIG_SMP) += smp.o
+ifneq ($(CONFIG_PPC_E500MC),y)
+obj-$(CONFIG_SUSPEND) += sleep.o
+endif
obj-y += common.o
diff --git a/arch/powerpc/platforms/85xx/sleep.S b/arch/powerpc/platforms/85xx/sleep.S
new file mode 100644
index 0000000..763d2f2
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/sleep.S
@@ -0,0 +1,609 @@
+/*
+ * Enter and leave deep sleep/sleep state on MPC85xx
+ *
+ * Author: Scott Wood <scottwood@freescale.com>
+ *
+ * Copyright (C) 2006-2011 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+#include <asm/reg.h>
+#include <asm/asm-offsets.h>
+
+#define SS_TB 0x00
+#define SS_HID 0x08 /* 2 HIDs */
+#define SS_IAC 0x10 /* 2 IACs */
+#define SS_DAC 0x18 /* 2 DACs */
+#define SS_DBCR 0x20 /* 3 DBCRs */
+#define SS_PID 0x2c /* 3 PIDs */
+#define SS_SPRG 0x38 /* 8 SPRGs */
+#define SS_IVOR 0x58 /* 20 interrupt vectors */
+#define SS_TCR 0xa8
+#define SS_BUCSR 0xac
+#define SS_L1CSR 0xb0 /* 2 L1CSRs */
+#define SS_MSR 0xb8
+#define SS_USPRG 0xbc
+#define SS_GPREG 0xc0 /* r12-r31 */
+#define SS_LR 0x110
+#define SS_CR 0x114
+#define SS_SP 0x118
+#define SS_CURRENT 0x11c
+#define SS_IVPR 0x120
+#define SS_BPTR 0x124
+
+
+#define STATE_SAVE_SIZE 0x128
+
+ .section .data
+ .align 5
+mpc85xx_sleep_save_area:
+ .space STATE_SAVE_SIZE
+ccsrbase_low:
+ .long 0
+ccsrbase_high:
+ .long 0
+powmgtreq:
+ .long 0
+
+ .section .text
+ .align 12
+
+ /*
+ * r3 = high word of physical address of CCSR
+ * r4 = low word of physical address of CCSR
+ * r5 = JOG or deep sleep request
+ * JOG-0x00200000, deep sleep-0x00100000
+ */
+_GLOBAL(mpc85xx_enter_deep_sleep)
+ lis r6, ccsrbase_low@ha
+ stw r4, ccsrbase_low@l(r6)
+ lis r6, ccsrbase_high@ha
+ stw r3, ccsrbase_high@l(r6)
+
+ lis r6, powmgtreq@ha
+ stw r5, powmgtreq@l(r6)
+
+ lis r10, mpc85xx_sleep_save_area@h
+ ori r10, r10, mpc85xx_sleep_save_area@l
+
+ mfspr r5, SPRN_HID0
+ mfspr r6, SPRN_HID1
+
+ stw r5, SS_HID+0(r10)
+ stw r6, SS_HID+4(r10)
+
+ mfspr r4, SPRN_IAC1
+ mfspr r5, SPRN_IAC2
+ mfspr r6, SPRN_DAC1
+ mfspr r7, SPRN_DAC2
+
+ stw r4, SS_IAC+0(r10)
+ stw r5, SS_IAC+4(r10)
+ stw r6, SS_DAC+0(r10)
+ stw r7, SS_DAC+4(r10)
+
+ mfspr r4, SPRN_DBCR0
+ mfspr r5, SPRN_DBCR1
+ mfspr r6, SPRN_DBCR2
+
+ stw r4, SS_DBCR+0(r10)
+ stw r5, SS_DBCR+4(r10)
+ stw r6, SS_DBCR+8(r10)
+
+ mfspr r4, SPRN_PID0
+ mfspr r5, SPRN_PID1
+ mfspr r6, SPRN_PID2
+
+ stw r4, SS_PID+0(r10)
+ stw r5, SS_PID+4(r10)
+ stw r6, SS_PID+8(r10)
+
+ mfspr r4, SPRN_SPRG0
+ mfspr r5, SPRN_SPRG1
+ mfspr r6, SPRN_SPRG2
+ mfspr r7, SPRN_SPRG3
+
+ stw r4, SS_SPRG+0x00(r10)
+ stw r5, SS_SPRG+0x04(r10)
+ stw r6, SS_SPRG+0x08(r10)
+ stw r7, SS_SPRG+0x0c(r10)
+
+ mfspr r4, SPRN_SPRG4
+ mfspr r5, SPRN_SPRG5
+ mfspr r6, SPRN_SPRG6
+ mfspr r7, SPRN_SPRG7
+
+ stw r4, SS_SPRG+0x10(r10)
+ stw r5, SS_SPRG+0x14(r10)
+ stw r6, SS_SPRG+0x18(r10)
+ stw r7, SS_SPRG+0x1c(r10)
+
+ mfspr r4, SPRN_IVPR
+ stw r4, SS_IVPR(r10)
+
+ mfspr r4, SPRN_IVOR0
+ mfspr r5, SPRN_IVOR1
+ mfspr r6, SPRN_IVOR2
+ mfspr r7, SPRN_IVOR3
+
+ stw r4, SS_IVOR+0x00(r10)
+ stw r5, SS_IVOR+0x04(r10)
+ stw r6, SS_IVOR+0x08(r10)
+ stw r7, SS_IVOR+0x0c(r10)
+
+ mfspr r4, SPRN_IVOR4
+ mfspr r5, SPRN_IVOR5
+ mfspr r6, SPRN_IVOR6
+ mfspr r7, SPRN_IVOR7
+
+ stw r4, SS_IVOR+0x10(r10)
+ stw r5, SS_IVOR+0x14(r10)
+ stw r6, SS_IVOR+0x18(r10)
+ stw r7, SS_IVOR+0x1c(r10)
+
+ mfspr r4, SPRN_IVOR8
+ mfspr r5, SPRN_IVOR9
+ mfspr r6, SPRN_IVOR10
+ mfspr r7, SPRN_IVOR11
+
+ stw r4, SS_IVOR+0x20(r10)
+ stw r5, SS_IVOR+0x24(r10)
+ stw r6, SS_IVOR+0x28(r10)
+ stw r7, SS_IVOR+0x2c(r10)
+
+ mfspr r4, SPRN_IVOR12
+ mfspr r5, SPRN_IVOR13
+ mfspr r6, SPRN_IVOR14
+ mfspr r7, SPRN_IVOR15
+
+ stw r4, SS_IVOR+0x30(r10)
+ stw r5, SS_IVOR+0x34(r10)
+ stw r6, SS_IVOR+0x38(r10)
+ stw r7, SS_IVOR+0x3c(r10)
+
+ mfspr r4, SPRN_IVOR32
+ mfspr r5, SPRN_IVOR33
+ mfspr r6, SPRN_IVOR34
+ mfspr r7, SPRN_IVOR35
+
+ stw r4, SS_IVOR+0x40(r10)
+ stw r5, SS_IVOR+0x44(r10)
+ stw r6, SS_IVOR+0x48(r10)
+ stw r7, SS_IVOR+0x4c(r10)
+
+ mfspr r4, SPRN_TCR
+ mfspr r5, SPRN_BUCSR
+ mfspr r6, SPRN_L1CSR0
+ mfspr r7, SPRN_L1CSR1
+ mfspr r8, SPRN_USPRG0
+
+ stw r4, SS_TCR(r10)
+ stw r5, SS_BUCSR(r10)
+ stw r6, SS_L1CSR+0(r10)
+ stw r7, SS_L1CSR+4(r10)
+ stw r8, SS_USPRG+0(r10)
+
+ stmw r12, SS_GPREG(r10)
+
+ mfmsr r4
+ mflr r5
+ mfcr r6
+
+ stw r4, SS_MSR(r10)
+ stw r5, SS_LR(r10)
+ stw r6, SS_CR(r10)
+ stw r1, SS_SP(r10)
+ stw r2, SS_CURRENT(r10)
+
+1: mftbu r4
+ mftb r5
+ mftbu r6
+ cmpw r4, r6
+ bne 1b
+
+ stw r4, SS_TB+0(r10)
+ stw r5, SS_TB+4(r10)
+
+ lis r5, ccsrbase_low@ha
+ lwz r4, ccsrbase_low@l(r5)
+ lis r5, ccsrbase_high@ha
+ lwz r3, ccsrbase_high@l(r5)
+
+ /* Disable machine checks and critical exceptions */
+ mfmsr r5
+ rlwinm r5, r5, 0, ~MSR_CE
+ rlwinm r5, r5, 0, ~MSR_ME
+ mtmsr r5
+ isync
+
+ /* Use TLB1[15] to map the CCSR at 0xf0000000 */
+ lis r5, 0x100f
+ mtspr SPRN_MAS0, r5
+ lis r5, 0xc000
+ ori r5, r5, 0x0500
+ mtspr SPRN_MAS1, r5
+ lis r5, 0xf000
+ ori r5, r5, 0x000a
+ mtspr SPRN_MAS2, r5
+ rlwinm r5, r4, 0, 0xfffff000
+ ori r5, r5, 0x0005
+ mtspr SPRN_MAS3, r5
+ mtspr SPRN_MAS7, r3
+ isync
+ tlbwe
+ isync
+
+ lis r3, 0xf000
+ lwz r4, 0x20(r3)
+ stw r4, SS_BPTR(r10)
+
+ lis r3, 0xf002 /* L2 cache controller at CCSR+0x20000 */
+ bl flush_disable_L2
+ bl flush_disable_L1
+
+ /* Enable I-cache, so as not to upset the bus
+ * with our loop.
+ */
+
+ mfspr r4, SPRN_L1CSR1
+ ori r4, r4, 1
+ mtspr SPRN_L1CSR1, r4
+ isync
+
+ /* Set boot page translation */
+ lis r3, 0xf000
+ lis r4, (mpc85xx_deep_resume - PAGE_OFFSET)@h
+ ori r4, r4, (mpc85xx_deep_resume - PAGE_OFFSET)@l
+ rlwinm r4, r4, 20, 0x000fffff
+ oris r4, r4, 0x8000
+ stw r4, 0x20(r3)
+ lwz r4, 0x20(r3) /* read-back to flush write */
+ twi 0, r4, 0
+ isync
+
+ /* Disable the decrementer */
+ mfspr r4, SPRN_TCR
+ rlwinm r4, r4, 0, ~TCR_DIE
+ mtspr SPRN_TCR, r4
+
+ mfspr r4, SPRN_TSR
+ oris r4, r4, TSR_DIS@h
+ mtspr SPRN_TSR, r4
+
+ /* set PMRCCR[VRCNT] to wait power stable for 40ms */
+ lis r3, 0xf00e
+ lwz r4, 0x84(r3)
+ clrlwi r4, r4, 16
+ oris r4, r4, 0x12a3
+ stw r4, 0x84(r3)
+ lwz r4, 0x84(r3)
+
+ /* set deep sleep bit in POWMGTSCR */
+ lis r3, powmgtreq@ha
+ lwz r8, powmgtreq@l(r3)
+
+ lis r3, 0xf00e
+ lwz r4, 0x80(r3)
+ or r4, r4, r8
+ stw r4, 0x80(r3)
+ lwz r4, 0x80(r3) /* read-back to flush write */
+ twi 0, r4, 0
+ isync
+
+ mftb r5
+1: /* spin until either we enter deep sleep, or the sleep process is
+ * aborted due to a pending wakeup event. Wait some time between
+ * accesses, so we don't flood the bus and prevent the pmc from
+ * detecting an idle system.
+ */
+
+ mftb r4
+ subf r7, r5, r4
+ cmpwi r7, 1000
+ blt 1b
+ mr r5, r4
+
+ lwz r6, 0x80(r3)
+ andis. r6, r6, 0x0010
+ bne 1b
+ b 2f
+
+2: mfspr r4, SPRN_PIR
+ andi. r4, r4, 1
+99: bne 99b
+
+ /* Establish a temporary 64MB 0->0 mapping in TLB1[1]. */
+ lis r4, 0x1001
+ mtspr SPRN_MAS0, r4
+ lis r4, 0xc000
+ ori r4, r4, 0x0800
+ mtspr SPRN_MAS1, r4
+ li r4, 0
+ mtspr SPRN_MAS2, r4
+ li r4, 0x0015
+ mtspr SPRN_MAS3, r4
+ li r4, 0
+ mtspr SPRN_MAS7, r4
+ isync
+ tlbwe
+ isync
+
+ lis r3, (3f - PAGE_OFFSET)@h
+ ori r3, r3, (3f - PAGE_OFFSET)@l
+ mtctr r3
+ bctr
+
+ /* Locate the resume vector in the last word of the current page. */
+ . = mpc85xx_enter_deep_sleep + 0xffc
+mpc85xx_deep_resume:
+ b 2b
+
+3:
+ /* Restore the contents of TLB1[0]. It is assumed that it covers
+ * the currently executing code and the sleep save area, and that
+ * it does not alias our temporary mapping (which is at virtual zero).
+ */
+ lis r3, (TLBCAM - PAGE_OFFSET)@h
+ ori r3, r3, (TLBCAM - PAGE_OFFSET)@l
+
+ lwz r4, 0(r3)
+ lwz r5, 4(r3)
+ lwz r6, 8(r3)
+ lwz r7, 12(r3)
+ lwz r8, 16(r3)
+
+ mtspr SPRN_MAS0, r4
+ mtspr SPRN_MAS1, r5
+ mtspr SPRN_MAS2, r6
+ mtspr SPRN_MAS3, r7
+ mtspr SPRN_MAS7, r8
+
+ isync
+ tlbwe
+ isync
+
+ /* Access the ccsrbase address with TLB1[0] */
+ lis r5, ccsrbase_low@ha
+ lwz r4, ccsrbase_low@l(r5)
+ lis r5, ccsrbase_high@ha
+ lwz r3, ccsrbase_high@l(r5)
+
+ /* Use TLB1[15] to map the CCSR at 0xf0000000 */
+ lis r5, 0x100f
+ mtspr SPRN_MAS0, r5
+ lis r5, 0xc000
+ ori r5, r5, 0x0500
+ mtspr SPRN_MAS1, r5
+ lis r5, 0xf000
+ ori r5, r5, 0x000a
+ mtspr SPRN_MAS2, r5
+ rlwinm r5, r4, 0, 0xfffff000
+ ori r5, r5, 0x0005
+ mtspr SPRN_MAS3, r5
+ mtspr SPRN_MAS7, r3
+ isync
+ tlbwe
+ isync
+
+ lis r3, 0xf002 /* L2 cache controller at CCSR+0x20000 */
+ bl invalidate_enable_L2
+
+ /* Access the MEM(r10) with TLB1[0] */
+ lis r10, mpc85xx_sleep_save_area@h
+ ori r10, r10, mpc85xx_sleep_save_area@l
+
+ lis r3, 0xf000
+ lwz r4, SS_BPTR(r10)
+ stw r4, 0x20(r3) /* restore BPTR */
+
+ /* Program shift running space to PAGE_OFFSET */
+ mfmsr r3
+ lis r4, 1f@h
+ ori r4, r4, 1f@l
+
+ mtsrr1 r3
+ mtsrr0 r4
+ rfi
+
+1: /* Restore the rest of TLB1, in ascending order so that
+ * the TLB1[1] gets invalidated first.
+ *
+ * XXX: It's better to invalidate the temporary mapping
+ * TLB1[15] for CCSR before restore any TLB1 entry include 0.
+ */
+ lis r4, 0x100f
+ mtspr SPRN_MAS0, r4
+ lis r4, 0
+ mtspr SPRN_MAS1, r4
+ isync
+ tlbwe
+ isync
+
+ lis r3, (TLBCAM + 5*4 - 4)@h
+ ori r3, r3, (TLBCAM + 5*4 - 4)@l
+ li r4, 15
+ mtctr r4
+
+2:
+ lwz r5, 4(r3)
+ lwz r6, 8(r3)
+ lwz r7, 12(r3)
+ lwz r8, 16(r3)
+ lwzu r9, 20(r3)
+
+ mtspr SPRN_MAS0, r5
+ mtspr SPRN_MAS1, r6
+ mtspr SPRN_MAS2, r7
+ mtspr SPRN_MAS3, r8
+ mtspr SPRN_MAS7, r9
+
+ isync
+ tlbwe
+ isync
+ bdnz 2b
+
+ lis r10, mpc85xx_sleep_save_area@h
+ ori r10, r10, mpc85xx_sleep_save_area@l
+
+ lwz r5, SS_HID+0(r10)
+ lwz r6, SS_HID+4(r10)
+
+ isync
+ mtspr SPRN_HID0, r5
+ isync
+
+ msync
+ mtspr SPRN_HID1, r6
+ isync
+
+ lwz r4, SS_IAC+0(r10)
+ lwz r5, SS_IAC+4(r10)
+ lwz r6, SS_DAC+0(r10)
+ lwz r7, SS_DAC+4(r10)
+
+ mtspr SPRN_IAC1, r4
+ mtspr SPRN_IAC2, r5
+ mtspr SPRN_DAC1, r6
+ mtspr SPRN_DAC2, r7
+
+ lwz r4, SS_DBCR+0(r10)
+ lwz r5, SS_DBCR+4(r10)
+ lwz r6, SS_DBCR+8(r10)
+
+ mtspr SPRN_DBCR0, r4
+ mtspr SPRN_DBCR1, r5
+ mtspr SPRN_DBCR2, r6
+
+ lwz r4, SS_PID+0(r10)
+ lwz r5, SS_PID+4(r10)
+ lwz r6, SS_PID+8(r10)
+
+ mtspr SPRN_PID0, r4
+ mtspr SPRN_PID1, r5
+ mtspr SPRN_PID2, r6
+
+ lwz r4, SS_SPRG+0x00(r10)
+ lwz r5, SS_SPRG+0x04(r10)
+ lwz r6, SS_SPRG+0x08(r10)
+ lwz r7, SS_SPRG+0x0c(r10)
+
+ mtspr SPRN_SPRG0, r4
+ mtspr SPRN_SPRG1, r5
+ mtspr SPRN_SPRG2, r6
+ mtspr SPRN_SPRG3, r7
+
+ lwz r4, SS_SPRG+0x10(r10)
+ lwz r5, SS_SPRG+0x14(r10)
+ lwz r6, SS_SPRG+0x18(r10)
+ lwz r7, SS_SPRG+0x1c(r10)
+
+ mtspr SPRN_SPRG4, r4
+ mtspr SPRN_SPRG5, r5
+ mtspr SPRN_SPRG6, r6
+ mtspr SPRN_SPRG7, r7
+
+ lwz r4, SS_IVPR(r10)
+ mtspr SPRN_IVPR, r4
+
+ lwz r4, SS_IVOR+0x00(r10)
+ lwz r5, SS_IVOR+0x04(r10)
+ lwz r6, SS_IVOR+0x08(r10)
+ lwz r7, SS_IVOR+0x0c(r10)
+
+ mtspr SPRN_IVOR0, r4
+ mtspr SPRN_IVOR1, r5
+ mtspr SPRN_IVOR2, r6
+ mtspr SPRN_IVOR3, r7
+
+ lwz r4, SS_IVOR+0x10(r10)
+ lwz r5, SS_IVOR+0x14(r10)
+ lwz r6, SS_IVOR+0x18(r10)
+ lwz r7, SS_IVOR+0x1c(r10)
+
+ mtspr SPRN_IVOR4, r4
+ mtspr SPRN_IVOR5, r5
+ mtspr SPRN_IVOR6, r6
+ mtspr SPRN_IVOR7, r7
+
+ lwz r4, SS_IVOR+0x20(r10)
+ lwz r5, SS_IVOR+0x24(r10)
+ lwz r6, SS_IVOR+0x28(r10)
+ lwz r7, SS_IVOR+0x2c(r10)
+
+ mtspr SPRN_IVOR8, r4
+ mtspr SPRN_IVOR9, r5
+ mtspr SPRN_IVOR10, r6
+ mtspr SPRN_IVOR11, r7
+
+ lwz r4, SS_IVOR+0x30(r10)
+ lwz r5, SS_IVOR+0x34(r10)
+ lwz r6, SS_IVOR+0x38(r10)
+ lwz r7, SS_IVOR+0x3c(r10)
+
+ mtspr SPRN_IVOR12, r4
+ mtspr SPRN_IVOR13, r5
+ mtspr SPRN_IVOR14, r6
+ mtspr SPRN_IVOR15, r7
+
+ lwz r4, SS_IVOR+0x40(r10)
+ lwz r5, SS_IVOR+0x44(r10)
+ lwz r6, SS_IVOR+0x48(r10)
+ lwz r7, SS_IVOR+0x4c(r10)
+
+ mtspr SPRN_IVOR32, r4
+ mtspr SPRN_IVOR33, r5
+ mtspr SPRN_IVOR34, r6
+ mtspr SPRN_IVOR35, r7
+
+ lwz r4, SS_TCR(r10)
+ lwz r5, SS_BUCSR(r10)
+ lwz r6, SS_L1CSR+0(r10)
+ lwz r7, SS_L1CSR+4(r10)
+ lwz r8, SS_USPRG+0(r10)
+
+ mtspr SPRN_TCR, r4
+ mtspr SPRN_BUCSR, r5
+
+ msync
+ isync
+ mtspr SPRN_L1CSR0, r6
+ isync
+
+ mtspr SPRN_L1CSR1, r7
+ isync
+
+ mtspr SPRN_USPRG0, r8
+
+ lmw r12, SS_GPREG(r10)
+
+ lwz r1, SS_SP(r10)
+ lwz r2, SS_CURRENT(r10)
+ lwz r4, SS_MSR(r10)
+ lwz r5, SS_LR(r10)
+ lwz r6, SS_CR(r10)
+
+ msync
+ mtmsr r4
+ isync
+
+ mtlr r5
+ mtcr r6
+
+ li r4, 0
+ mtspr SPRN_TBWL, r4
+
+ lwz r4, SS_TB+0(r10)
+ lwz r5, SS_TB+4(r10)
+
+ mtspr SPRN_TBWU, r4
+ mtspr SPRN_TBWL, r5
+
+ lis r3, 1
+ mtdec r3
+
+ blr
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
index 592a0f8..618a52c 100644
--- a/arch/powerpc/sysdev/fsl_pmc.c
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -2,6 +2,7 @@
* Suspend/resume support
*
* Copyright 2009 MontaVista Software, Inc.
+ * Copyright 2010-2011 Freescale Semiconductor Inc.
*
* Author: Anton Vorontsov <avorontsov@ru.mvista.com>
*
@@ -19,39 +20,83 @@
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/of_platform.h>
+#include <linux/pm.h>
+
+#include <sysdev/fsl_soc.h>
struct pmc_regs {
__be32 devdisr;
__be32 devdisr2;
- __be32 :32;
- __be32 :32;
- __be32 pmcsr;
-#define PMCSR_SLP (1 << 17)
+ __be32 res1;
+ __be32 res2;
+ __be32 powmgtcsr;
+#define POWMGTCSR_SLP_MASK 0x00020000
+#define POWMGTCSR_DPSLP_MASK 0x00100000
+ __be32 res3[2];
+ __be32 pmcdr;
};
-static struct device *pmc_dev;
static struct pmc_regs __iomem *pmc_regs;
+static unsigned int pmc_flag;
+
+#define PMC_SLEEP 0x1
+#define PMC_DEEP_SLEEP 0x2
static int pmc_suspend_enter(suspend_state_t state)
{
- int ret;
+ int ret = 0;
+ unsigned long flags;
+
+ switch (state) {
+ case PM_SUSPEND_MEM:
+#ifdef CONFIG_SPE
+ enable_kernel_spe();
+#endif
+ enable_kernel_fp();
+
+ pr_debug("%s: Entering deep sleep\n", __func__);
+
+ local_irq_save(flags);
+
+ mpc85xx_enter_deep_sleep(get_immrbase(), POWMGTCSR_DPSLP_MASK);
+
+ local_irq_restore(flags);
+
+ pr_debug("%s: Resumed from deep sleep\n", __func__);
+ break;
- setbits32(&pmc_regs->pmcsr, PMCSR_SLP);
- /* At this point, the CPU is asleep. */
+ case PM_SUSPEND_STANDBY:
+ local_irq_save(flags);
- /* Upon resume, wait for SLP bit to be clear. */
- ret = spin_event_timeout((in_be32(&pmc_regs->pmcsr) & PMCSR_SLP) == 0,
- 10000, 10) ? 0 : -ETIMEDOUT;
- if (ret)
- dev_err(pmc_dev, "tired waiting for SLP bit to clear\n");
+ setbits32(&pmc_regs->powmgtcsr, POWMGTCSR_SLP_MASK);
+ /* At this point, the CPU is asleep. */
+
+ local_irq_restore(flags);
+ /* Upon resume, wait for SLP bit to be clear. */
+ ret = spin_event_timeout(
+ (in_be32(&pmc_regs->powmgtcsr) & POWMGTCSR_SLP_MASK) == 0,
+ 10000, 10);
+ if (!ret) {
+ pr_err("%s: timeout waiting for SLP bit "
+ "to be cleared\n", __func__);
+ ret = -EINVAL;
+ }
+ break;
+
+ default:
+ ret = -EINVAL;
+
+ }
return ret;
}
static int pmc_suspend_valid(suspend_state_t state)
{
- if (state != PM_SUSPEND_STANDBY)
+ if (((pmc_flag & PMC_SLEEP) && (state == PM_SUSPEND_STANDBY)) ||
+ ((pmc_flag & PMC_DEEP_SLEEP) && (state == PM_SUSPEND_MEM)))
+ return 1;
+ else
return 0;
- return 1;
}
static const struct platform_suspend_ops pmc_suspend_ops = {
@@ -59,14 +104,24 @@ static const struct platform_suspend_ops pmc_suspend_ops = {
.enter = pmc_suspend_enter,
};
-static int pmc_probe(struct platform_device *ofdev)
+static int pmc_probe(struct platform_device *pdev)
{
- pmc_regs = of_iomap(ofdev->dev.of_node, 0);
+ struct device_node *np = pdev->dev.of_node;
+
+ pmc_regs = of_iomap(np, 0);
if (!pmc_regs)
return -ENOMEM;
- pmc_dev = &ofdev->dev;
+ pmc_flag = PMC_SLEEP;
+ if (of_device_is_compatible(np, "fsl,mpc8536-pmc"))
+ pmc_flag |= PMC_DEEP_SLEEP;
+
+ if (of_device_is_compatible(np, "fsl,p1022-pmc"))
+ pmc_flag |= PMC_DEEP_SLEEP;
+
suspend_set_ops(&pmc_suspend_ops);
+
+ pr_info("Freescale PMC driver\n");
return 0;
}
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index c6d0073..949377d 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -48,5 +48,10 @@ extern struct platform_diu_data_ops diu_ops;
void fsl_hv_restart(char *cmd);
void fsl_hv_halt(void);
+/*
+ * Cast the ccsrbar to 64-bit parameter so that the assembly
+ * code can be compatible with both 32-bit & 36-bit.
+ */
+extern void mpc85xx_enter_deep_sleep(u64 ccsrbar, u32 powmgtreq);
#endif
#endif
--
1.6.4.1
^ permalink raw reply related
* [PATCH v3 3/4] fsl_pmc: Add API to enable device as wakeup event source
From: Zhao Chenhui @ 2011-12-22 11:43 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1324554214-19502-1-git-send-email-chenhui.zhao@freescale.com>
Add APIs for setting wakeup source and lossless Ethernet in low power modes.
These APIs can be used by wake-on-packet feature.
Signed-off-by: Dave Liu <daveliu@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Jin Qing <b24347@freescale.com>
Signed-off-by: Zhao Chenhui <chenhui.zhao@freescale.com>
---
arch/powerpc/sysdev/fsl_pmc.c | 70 ++++++++++++++++++++++++++++++++++++++++-
arch/powerpc/sysdev/fsl_soc.h | 9 +++++
2 files changed, 78 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
index 618a52c..0c99591 100644
--- a/arch/powerpc/sysdev/fsl_pmc.c
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -32,6 +32,7 @@ struct pmc_regs {
__be32 powmgtcsr;
#define POWMGTCSR_SLP_MASK 0x00020000
#define POWMGTCSR_DPSLP_MASK 0x00100000
+#define POWMGTCSR_LOSSLESS_MASK 0x00400000
__be32 res3[2];
__be32 pmcdr;
};
@@ -41,6 +42,73 @@ static unsigned int pmc_flag;
#define PMC_SLEEP 0x1
#define PMC_DEEP_SLEEP 0x2
+#define PMC_LOSSLESS 0x4
+
+/**
+ * mpc85xx_pmc_set_wake - enable devices as wakeup event source
+ * @pdev: platform device affected
+ * @enable: True to enable event generation; false to disable
+ *
+ * This enables the device as a wakeup event source, or disables it.
+ *
+ * RETURN VALUE:
+ * 0 is returned on success
+ * -EINVAL is returned if device is not supposed to wake up the system
+ * Error code depending on the platform is returned if both the platform and
+ * the native mechanism fail to enable the generation of wake-up events
+ */
+int mpc85xx_pmc_set_wake(struct platform_device *pdev, bool enable)
+{
+ int ret = 0;
+ struct device_node *clk_np;
+ u32 pmcdr_mask;
+
+ if (!pmc_regs) {
+ pr_err("%s: PMC is unavailable\n", __func__);
+ return -ENODEV;
+ }
+
+ if (enable && !device_may_wakeup(&pdev->dev))
+ return -EINVAL;
+
+ clk_np = of_parse_phandle(pdev->dev.of_node, "clk-handle", 0);
+ if (!clk_np)
+ return -EINVAL;
+
+ if (of_property_read_u32(clk_np, "fsl,pmcdr-mask", &pmcdr_mask)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (enable)
+ /* clear to enable clock in low power mode */
+ clrbits32(&pmc_regs->pmcdr, pmcdr_mask);
+ else
+ setbits32(&pmc_regs->pmcdr, pmcdr_mask);
+
+out:
+ of_node_put(clk_np);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mpc85xx_pmc_set_wake);
+
+/**
+ * mpc85xx_pmc_set_lossless_ethernet - enable lossless ethernet
+ * in (deep) sleep mode
+ * @enable: True to enable event generation; false to disable
+ */
+void mpc85xx_pmc_set_lossless_ethernet(int enable)
+{
+ if (pmc_flag & PMC_LOSSLESS) {
+ if (enable)
+ setbits32(&pmc_regs->powmgtcsr,
+ POWMGTCSR_LOSSLESS_MASK);
+ else
+ clrbits32(&pmc_regs->powmgtcsr,
+ POWMGTCSR_LOSSLESS_MASK);
+ }
+}
+EXPORT_SYMBOL_GPL(mpc85xx_pmc_set_lossless_ethernet);
static int pmc_suspend_enter(suspend_state_t state)
{
@@ -117,7 +185,7 @@ static int pmc_probe(struct platform_device *pdev)
pmc_flag |= PMC_DEEP_SLEEP;
if (of_device_is_compatible(np, "fsl,p1022-pmc"))
- pmc_flag |= PMC_DEEP_SLEEP;
+ pmc_flag |= PMC_DEEP_SLEEP | PMC_LOSSLESS;
suspend_set_ops(&pmc_suspend_ops);
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index 949377d..29a87ee 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -3,6 +3,7 @@
#ifdef __KERNEL__
#include <asm/mmu.h>
+#include <linux/platform_device.h>
struct spi_device;
@@ -21,6 +22,14 @@ struct device_node;
extern void fsl_rstcr_restart(char *cmd);
+#ifdef CONFIG_FSL_PMC
+int mpc85xx_pmc_set_wake(struct platform_device *pdev, bool enable);
+void mpc85xx_pmc_set_lossless_ethernet(int enable);
+#else
+#define mpc85xx_pmc_set_wake(pdev, enable)
+#define mpc85xx_pmc_set_lossless_ethernet(enable)
+#endif
+
#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
/* The different ports that the DIU can be connected to */
--
1.6.4.1
^ permalink raw reply related
* [PATCH v3 1/4] powerpc/85xx: add HOTPLUG_CPU support
From: Zhao Chenhui @ 2011-12-22 11:43 UTC (permalink / raw)
To: linuxppc-dev
From: Li Yang <leoli@freescale.com>
Add support to disable and re-enable individual cores at runtime
on MPC85xx/QorIQ SMP machines. Currently support e500v1/e500v2 core.
MPC85xx machines use ePAPR spin-table in boot page for CPU kick-off.
This patch uses the boot page from bootloader to boot core at runtime.
It supports 32-bit and 36-bit physical address.
Add generic_set_cpu_up() to set cpu_state as CPU_UP_PREPARE in kick_cpu().
Signed-off-by: Li Yang <leoli@freescale.com>
Signed-off-by: Jin Qing <b24347@freescale.com>
Signed-off-by: Zhao Chenhui <chenhui.zhao@freescale.com>
---
changes for v3
* Move "out_be32(&spin_table->pir, hw_cpu)" after core reset.
* Keep the default value of the BPTR register. Don't change it.
* Merge the timebase patch.
* Don't support e500mc for HOTPLUG_CPU.
arch/powerpc/Kconfig | 5 +-
arch/powerpc/include/asm/cacheflush.h | 2 +
arch/powerpc/include/asm/smp.h | 2 +
arch/powerpc/kernel/head_fsl_booke.S | 28 +++++++
arch/powerpc/kernel/smp.c | 10 +++
arch/powerpc/platforms/85xx/smp.c | 145 +++++++++++++++++++++++++--------
6 files changed, 154 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 7c93c7e..bf942b1 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -213,7 +213,7 @@ config ARCH_HIBERNATION_POSSIBLE
config ARCH_SUSPEND_POSSIBLE
def_bool y
depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \
- (PPC_85xx && !SMP) || PPC_86xx || PPC_PSERIES || 44x || 40x
+ PPC_85xx || PPC_86xx || PPC_PSERIES || 44x || 40x
config PPC_DCR_NATIVE
bool
@@ -324,7 +324,8 @@ config SWIOTLB
config HOTPLUG_CPU
bool "Support for enabling/disabling CPUs"
- depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC || PPC_POWERNV)
+ depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || \
+ PPC_PMAC || PPC_POWERNV || (E500 && !PPC_E500MC))
---help---
Say Y here to be able to disable and re-enable individual
CPUs at runtime on SMP machines.
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index ab9e402..dd41442 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -30,6 +30,8 @@ extern void flush_dcache_page(struct page *page);
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
+extern void flush_disable_L1(void);
+
extern void __flush_icache_range(unsigned long, unsigned long);
static inline void flush_icache_range(unsigned long start, unsigned long stop)
{
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index adba970..7517863 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -65,6 +65,7 @@ int generic_cpu_disable(void);
void generic_cpu_die(unsigned int cpu);
void generic_mach_cpu_die(void);
void generic_set_cpu_dead(unsigned int cpu);
+void generic_set_cpu_up(unsigned int cpu);
int generic_check_cpu_restart(unsigned int cpu);
#endif
@@ -191,6 +192,7 @@ extern unsigned long __secondary_hold_spinloop;
extern unsigned long __secondary_hold_acknowledge;
extern char __secondary_hold;
+extern void __early_start(void);
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 9f5d210..1d93272 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1004,6 +1004,34 @@ _GLOBAL(flush_dcache_L1)
blr
+/* Flush L1 d-cache, invalidate and disable d-cache and i-cache */
+_GLOBAL(flush_disable_L1)
+ mflr r10
+ bl flush_dcache_L1 /* Flush L1 d-cache */
+ mtlr r10
+
+ mfspr r4, SPRN_L1CSR0 /* Invalidate and disable d-cache */
+ li r5, 2
+ rlwimi r4, r5, 0, 3
+
+ msync
+ isync
+ mtspr SPRN_L1CSR0, r4
+ isync
+
+1: mfspr r4, SPRN_L1CSR0 /* Wait for the invalidate to finish */
+ andi. r4, r4, 2
+ bne 1b
+
+ mfspr r4, SPRN_L1CSR1 /* Invalidate and disable i-cache */
+ li r5, 2
+ rlwimi r4, r5, 0, 3
+
+ mtspr SPRN_L1CSR1, r4
+ isync
+
+ blr
+
#ifdef CONFIG_SMP
/* When we get here, r24 needs to hold the CPU # */
.globl __secondary_start
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index f0abe92..7b675bb 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -423,6 +423,16 @@ void generic_set_cpu_dead(unsigned int cpu)
per_cpu(cpu_state, cpu) = CPU_DEAD;
}
+/*
+ * The cpu_state should be set to CPU_UP_PREPARE in kick_cpu(), otherwise
+ * the cpu_state is always CPU_DEAD after calling generic_set_cpu_dead(),
+ * which makes the delay in generic_cpu_die() not happen.
+ */
+void generic_set_cpu_up(unsigned int cpu)
+{
+ per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+}
+
int generic_check_cpu_restart(unsigned int cpu)
{
return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 2df4785..2bff696 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -17,6 +17,7 @@
#include <linux/of.h>
#include <linux/kexec.h>
#include <linux/highmem.h>
+#include <linux/cpu.h>
#include <asm/machdep.h>
#include <asm/pgtable.h>
@@ -28,28 +29,58 @@
#include <sysdev/fsl_soc.h>
#include <sysdev/mpic.h>
-extern void __early_start(void);
-
-#define BOOT_ENTRY_ADDR_UPPER 0
-#define BOOT_ENTRY_ADDR_LOWER 1
-#define BOOT_ENTRY_R3_UPPER 2
-#define BOOT_ENTRY_R3_LOWER 3
-#define BOOT_ENTRY_RESV 4
-#define BOOT_ENTRY_PIR 5
-#define BOOT_ENTRY_R6_UPPER 6
-#define BOOT_ENTRY_R6_LOWER 7
-#define NUM_BOOT_ENTRY 8
-#define SIZE_BOOT_ENTRY (NUM_BOOT_ENTRY * sizeof(u32))
-
-static int __init
-smp_85xx_kick_cpu(int nr)
+struct epapr_spin_table {
+ u32 addr_h;
+ u32 addr_l;
+ u32 r3_h;
+ u32 r3_l;
+ u32 reserved;
+ u32 pir;
+};
+
+static void __cpuinit smp_85xx_setup_cpu(int cpu_nr);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __cpuinit smp_85xx_mach_cpu_die(void)
+{
+ unsigned int cpu = smp_processor_id();
+ register u32 tmp;
+
+ local_irq_disable();
+ idle_task_exit();
+ generic_set_cpu_dead(cpu);
+ mb();
+
+ mtspr(SPRN_TCR, 0);
+
+ flush_disable_L1();
+ tmp = (mfspr(SPRN_HID0) & ~(HID0_DOZE|HID0_SLEEP)) | HID0_NAP;
+ mb();
+ isync();
+ mtspr(SPRN_HID0, tmp);
+ isync();
+
+ /* Enter NAP mode. */
+ tmp = mfmsr();
+ tmp |= MSR_WE;
+ mb();
+ mtmsr(tmp);
+ isync();
+
+ for (;;);
+}
+#endif
+
+static int __cpuinit smp_85xx_kick_cpu(int nr)
+
{
unsigned long flags;
const u64 *cpu_rel_addr;
- __iomem u32 *bptr_vaddr;
+ __iomem struct epapr_spin_table *spin_table;
struct device_node *np;
int n = 0, hw_cpu = get_hard_smp_processor_id(nr);
int ioremappable;
+ int ret = 0;
WARN_ON(nr < 0 || nr >= NR_CPUS);
WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS);
@@ -60,7 +91,8 @@ smp_85xx_kick_cpu(int nr)
cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL);
if (cpu_rel_addr == NULL) {
- printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
+ pr_err("%s: No cpu-release-addr for cpu %d\n",
+ __func__, nr);
return -ENOENT;
}
@@ -74,50 +106,89 @@ smp_85xx_kick_cpu(int nr)
/* Map the spin table */
if (ioremappable)
- bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY);
+ spin_table = ioremap(*cpu_rel_addr,
+ sizeof(struct epapr_spin_table));
else
- bptr_vaddr = phys_to_virt(*cpu_rel_addr);
+ spin_table = phys_to_virt(*cpu_rel_addr);
local_irq_save(flags);
-
- out_be32(bptr_vaddr + BOOT_ENTRY_PIR, hw_cpu);
#ifdef CONFIG_PPC32
- out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
+#ifdef CONFIG_HOTPLUG_CPU
+ /* Corresponding to generic_set_cpu_dead() */
+ generic_set_cpu_up(nr);
+
+ if (system_state == SYSTEM_RUNNING) {
+ out_be32(&spin_table->addr_l, 0);
+
+ /*
+ * We don't set the BPTR register here upon it points
+ * to the boot page properly.
+ */
+ mpic_reset_core(hw_cpu);
+
+ /* wait until core is ready... */
+ n = 0;
+ while ((in_be32(&spin_table->addr_l) != 1) && (++n < 1000))
+ udelay(100);
+ if (n >= 1000) {
+ pr_err("%s: timeout waiting for core %d to reset\n",
+ __func__, hw_cpu);
+ ret = -ENOENT;
+ goto out;
+ }
+ /* clear the acknowledge status */
+ __secondary_hold_acknowledge = -1;
+ }
+#endif
+ out_be32(&spin_table->pir, hw_cpu);
+ out_be32(&spin_table->addr_l, __pa(__early_start));
if (!ioremappable)
- flush_dcache_range((ulong)bptr_vaddr,
- (ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
+ flush_dcache_range((ulong)spin_table,
+ (ulong)spin_table + sizeof(struct epapr_spin_table));
/* Wait a bit for the CPU to ack. */
+ n = 0;
while ((__secondary_hold_acknowledge != hw_cpu) && (++n < 1000))
mdelay(1);
+ if (n >= 1000) {
+ pr_err("%s: timeout waiting for core %d to ack\n",
+ __func__, hw_cpu);
+ ret = -ENOENT;
+ goto out;
+ }
+out:
#else
smp_generic_kick_cpu(nr);
- out_be64((u64 *)(bptr_vaddr + BOOT_ENTRY_ADDR_UPPER),
- __pa((u64)*((unsigned long long *) generic_secondary_smp_init)));
+ out_be32(&spin_table->pir, hw_cpu);
+ out_be64((u64 *)(&spin_table->addr_h),
+ __pa((u64)*((unsigned long long *)generic_secondary_smp_init)));
if (!ioremappable)
- flush_dcache_range((ulong)bptr_vaddr,
- (ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
+ flush_dcache_range((ulong)spin_table,
+ (ulong)spin_table + sizeof(struct epapr_spin_table));
#endif
local_irq_restore(flags);
if (ioremappable)
- iounmap(bptr_vaddr);
+ iounmap(spin_table);
pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
- return 0;
+ return ret;
}
struct smp_ops_t smp_85xx_ops = {
.kick_cpu = smp_85xx_kick_cpu,
-#ifdef CONFIG_KEXEC
+ .setup_cpu = smp_85xx_setup_cpu,
+#ifdef CONFIG_HOTPLUG_CPU
+ .cpu_disable = generic_cpu_disable,
+ .cpu_die = generic_cpu_die,
+#endif
.give_timebase = smp_generic_give_timebase,
.take_timebase = smp_generic_take_timebase,
-#endif
};
#ifdef CONFIG_KEXEC
@@ -217,8 +288,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
}
#endif /* CONFIG_KEXEC */
-static void __init
-smp_85xx_setup_cpu(int cpu_nr)
+static void __cpuinit smp_85xx_setup_cpu(int cpu_nr)
{
if (smp_85xx_ops.probe == smp_mpic_probe)
mpic_setup_this_cpu();
@@ -231,13 +301,12 @@ void __init mpc85xx_smp_init(void)
{
struct device_node *np;
- smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu;
-
np = of_find_node_by_type(NULL, "open-pic");
if (np) {
smp_85xx_ops.probe = smp_mpic_probe;
smp_85xx_ops.message_pass = smp_mpic_message_pass;
}
+ of_node_put(np);
if (cpu_has_feature(CPU_FTR_DBELL)) {
/*
@@ -248,6 +317,10 @@ void __init mpc85xx_smp_init(void)
smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
}
+#ifdef CONFIG_HOTPLUG_CPU
+ ppc_md.cpu_die = smp_85xx_mach_cpu_die;
+#endif
+
smp_ops = &smp_85xx_ops;
#ifdef CONFIG_KEXEC
--
1.6.4.1
^ permalink raw reply related
* RE: [PATCH 1/2] mtd/nand: fixup for fmr initialization of Freescale NAND controller
From: Artem Bityutskiy @ 2011-12-22 10:24 UTC (permalink / raw)
To: Liu Shengzhou-B36685
Cc: Wood Scott-B07421, Gala Kumar-B11780,
linuxppc-dev@lists.ozlabs.org, dwmw2@infradead.org,
linux-mtd@lists.infradead.org
In-Reply-To: <3F453DDFF675A64A89321A1F352810216C9D5C@039-SN1MPN1-005.039d.mgd.msft.net>
[-- Attachment #1: Type: text/plain, Size: 1370 bytes --]
On Tue, 2011-12-20 at 06:40 +0000, Liu Shengzhou-B36685 wrote:
> > -----Original Message-----
> > From: Artem Bityutskiy [mailto:dedekind1@gmail.com]
> > Sent: Saturday, December 17, 2011 10:45 PM
> > To: Liu Shengzhou-B36685
> > Cc: linuxppc-dev@lists.ozlabs.org; Wood Scott-B07421;
> > dwmw2@infradead.org; Gala Kumar-B11780; linux-mtd@lists.infradead.org
> > Subject: Re: [PATCH 1/2] mtd/nand: fixup for fmr initialization of
> > Freescale NAND controller
> >
> > On Mon, 2011-12-12 at 17:40 +0800, Shengzhou Liu wrote:
> > > There was a bug for fmr initialization, which lead to fmr was always
> > > 0x100 in fsl_elbc_chip_init() and caused FCM command timeout before
> > > calling fsl_elbc_chip_init_tail(), now we initialize CWTO to maximum
> > > timeout value and not relying on the setting of bootloader.
> > >
> > > Signed-off-by: Shengzhou Liu <Shengzhou.Liu@freescale.com>
> >
> > Pushed both to l2-mtd-2.6.git, thanks!
> >
> > --
> > Best Regards,
> > Artem Bityutskiy
>
> I noted it had been applied in linux-next.git tree.
> Does it still need to l2-mtd-2.6.git?
> Thanks.
It is in linux-next because it is pulled there from l2-mtd-2.6.git.
Thanks for head up, but no, it should stay in the l2-mtd-2.6.git.
David Woodhouse then should take care of merging the l2 tree upstream.
--
Best Regards,
Artem Bityutskiy
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [PATCH 2/2] [PowerPC Book3E] Introduce new ptrace debug feature flag
From: K.Prasad @ 2011-12-22 9:34 UTC (permalink / raw)
To: linuxppc-dev, Thiago Jung Bauermann, Edjunior Barbosa Machado,
dwg
In-Reply-To: <20111221005502.GE5188@truffala.fritz.box>
On Wed, Dec 21, 2011 at 11:55:02AM +1100, David Gibson wrote:
> On Thu, Dec 08, 2011 at 04:53:30PM +0530, K.Prasad wrote:
> > While PPC_PTRACE_SETHWDEBUG ptrace flag in PowerPC accepts
> > PPC_BREAKPOINT_MODE_EXACT mode of breakpoint, the same is not intimated to the
> > user-space debuggers (like GDB) who may want to use it. Hence we introduce a
> > new PPC_DEBUG_FEATURE_DATA_BP_EXACT flag which will be populated on the
> > "features" member of "struct ppc_debug_info" to advertise support for the
> > same on Book3E PowerPC processors.
>
> Hrm. I had assumed the reason there wasn't a feature bit for EXACT
> originally was that EXACT breakpoints were *always* supposed to be
> supported by the new interface.
>
Okay. Although BookS doesn't support EXACT breakpoints, it is possible
(after the introduction of new hw-breakpoint interfaces) to request for
a breakpoint of length 1 Byte.
The hw-breakpoint infrastructure would take care of filtering the
extraneous interrupts arising out of accesses in the neighbourhood, in
such a case.
David,
Can you Ack this patch too, if you find the changes acceptable?
Thanks,
K.Prasad
^ permalink raw reply
* Re: linux-next: build warnings after merge of the final tree
From: Stephen Rothwell @ 2011-12-22 5:33 UTC (permalink / raw)
To: H. Peter Anvin
Cc: Peter Zijlstra, linux-kernel, Steven Rostedt, linux-next,
Paul Mackerras, Thomas Gleixner, linuxppc-dev, Ingo Molnar
In-Reply-To: <4EE8D305.8020407@zytor.com>
[-- Attachment #1: Type: text/plain, Size: 752 bytes --]
Hi Peter,
On Wed, 14 Dec 2011 08:47:01 -0800 "H. Peter Anvin" <hpa@zytor.com> wrote:
>
> On 12/14/2011 08:32 AM, Steven Rostedt wrote:
> > On Wed, 2011-12-14 at 18:15 +1100, Stephen Rothwell wrote:
> >
> >> Maybe caused by commit d5e553d6e0a4 ("trace: Include <asm/asm-offsets.h>
> >> in trace_syscalls.c") from the tip tree. These warnings may have been
> >> here for a while as it is hard to catch the new ones among the flood.
> >>
> >
> > hpa,
> >
> > Was this change only needed for x86? If so, could you put that into
> > asm/ftrace.h instead?
> >
>
> Yes (on both accounts). It was part of the syscall changes; I'll move
> the include.
Ping?
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* linux-next: boot failure for next-20111216
From: Stephen Rothwell @ 2011-12-22 0:21 UTC (permalink / raw)
To: LKML; +Cc: linux-next, ppc-dev, Alan Cox
[-- Attachment #1: Type: text/plain, Size: 1780 bytes --]
Hi all,
next-20111216 (and all later so far) fails to boot on a Power7 blade
server like this:
calling .serial8250_init+0x0/0x1e0 @ 1
Serial: 8250/16550 driver, 4 ports, IRQ sharing disabled
INFO: rcu_sched detected stalls on CPUs/tasks: { 3 4 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31} (detected by 5, t=6002 jiffies)
Call Trace:
[c0000003fd9e74e0] [c000000000015054] .show_stack+0x74/0x1c0 (unreliable)
[c0000003fd9e7590] [c00000000012ad2c] .__rcu_pending+0x49c/0x4b0
[c0000003fd9e7650] [c00000000012ae94] .rcu_check_callbacks+0x154/0x250
[c0000003fd9e76f0] [c0000000000b8ab4] .update_process_times+0x44/0xa0
[c0000003fd9e7780] [c0000000000fcdbc] .tick_sched_timer+0x7c/0x100
[c0000003fd9e7820] [c0000000000d5b38] .__run_hrtimer+0xb8/0x270
[c0000003fd9e78d0] [c0000000000d6068] .hrtimer_interrupt+0x138/0x2d0
[c0000003fd9e79e0] [c00000000001e4d0] .timer_interrupt+0x130/0x300
[c0000003fd9e7a90] [c0000000000038e4] decrementer_common+0x164/0x180
--- Exception: 901 at .arch_local_irq_restore+0xd8/0x140
LR = .cpu_idle+0x180/0x220
[c0000003fd9e7d80] [c000000000c7c368] wireless_seq_fops+0x109a8/0x2f418 (unreliable)
[c0000003fd9e7e20] [c000000000017970] .cpu_idle+0x180/0x220
[c0000003fd9e7ed0] [c0000000008369e8] .start_secondary+0x3a4/0x3b0
[c0000003fd9e7f90] [c0000000000093f4] .start_secondary_prolog+0x10/0x14
There are quite a few more rcu stalls after this and the boot never
completes (at least not before our automated test system steps in and
reboots the server).
So the obvious first place to point the finger would be changes to the
8250 code ... but there is nothing too obvious there.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [PATCH 3/3] powerpc/44x: Add support PCI-E for APM821xx SoC and Bluestone board
From: Josh Boyer @ 2011-12-21 20:20 UTC (permalink / raw)
To: Vinh Huu Tuong Nguyen
Cc: Ayman El-Khashab, Dave Kleikamp, Lucas De Marchi, Rob Herring,
Paul Gortmaker, Paul Mackerras, Anton Blanchard, Jiri Kosina,
linuxppc-dev, linux-kernel
In-Reply-To: <e10be3d24de889e9e80d2fd76de9dcd8@mail.gmail.com>
On Tue, Dec 20, 2011 at 11:47 PM, Vinh Huu Tuong Nguyen
<vhtnguyen@apm.com> wrote:
>> +
>> + =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET,
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mfdcri(SDR0, port->sdr_base + PESDRn_RCSSE=
T) |
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 (PESDRx_RCSSET_RSTGU | PESDRx_RCSSET_RSTPY=
N));
>> +
>> + =A0 =A0 =A0 /* Poll for PHY reset */
>> + =A0 =A0 =A0 timeout =3D 0;
>> + =A0 =A0 =A0 while ((!(mfdcri(SDR0, PESDR0_460EX_RSTSTA +
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 (port->index * 0x55)) & 0x=
1)) &&
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0(timeout < PCIE_PHY_RESET_TIMEOUT)) {
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 udelay(10);
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 timeout++;
>> + =A0 =A0 =A0 }
>> +
>> + =A0 =A0 =A0 if (timeout < PCIE_PHY_RESET_TIMEOUT) {
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_RCSSE=
T,
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 (mfdcri(SDR0, port->sdr_ba=
se + PESDRn_RCSSET) &
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 ~(PESDRx_RCSSET_RSTGU | PE=
SDRx_RCSSET_RSTDL)) |
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 PESDRx_RCSSET_RSTPYN);
>> +
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 port->has_ibpre =3D 1;
>> +
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 return 0;
>> + =A0 =A0 =A0 } else {
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 printk(KERN_INFO "PCIE: Can't reset PHY\n"=
);
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 return -1;
>> + =A0 =A0 =A0 }
>
> If we can't reset the PHY, does this whole function essentially fail?
> Do the devices not get renumbered, etc? =A0If so, you probably want to
> make that KERN_ERR.
> [Vinh Nguyen] if we can't reset the PHY, maybe the device can't work
> properly. I will update codes to return the error in case PHY can't reset=
.
OK.
>> @@ -1751,9 +1856,9 @@ static void __init
> ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
>> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 * if it works
>> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 */
>> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM0LAL, 0x0000000=
0);
>> - =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM0LAH, 0x00000000=
);
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM0LAH, 0x00000008=
); /* Moving
> on HB */
>> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM1LAL, 0x0000000=
0);
>> - =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM1LAH, 0x00000000=
);
>> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM1LAH, 0x0000000c=
); /* Moving
> on HB */
>> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM01SAH, 0xffff00=
00);
>> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM01SAL, 0x000000=
00);
>
> Why are these values changed, and are those changes only needed on
> APM821xx?
> [Vinh Nguyen] In system memory map of 460EX chip, we have an "alias DDR
> SDRAM" area that is Local Memory Alias for HB(high bandwidth), so we trie=
d
> to initialize it for speedup. For APM821xx, although we didn't mention
> about this area, this configuration still works well. So we keep it.
This function isn't just called for 460EX or APM821xx SoCs. It's
called on any 4xx SoC with PCIe configured.
Is this change going to work on them all? If not, it needs to be
conditionalized.
>> diff --git a/arch/powerpc/sysdev/ppc4xx_pci.h
> b/arch/powerpc/sysdev/ppc4xx_pci.h
>> index 32ce763..faf3017 100644
>> --- a/arch/powerpc/sysdev/ppc4xx_pci.h
>> +++ b/arch/powerpc/sysdev/ppc4xx_pci.h
>> @@ -441,6 +441,7 @@
>> =A0/*
>> =A0* Config space register offsets
>> =A0*/
>> +#define PECFG_ECDEVCTL =A0 =A0 =A0 =A0 0x060
>> =A0#define PECFG_ECRTCTL =A0 =A0 =A0 =A0 =A00x074
>>
>> =A0#define PECFG_BAR0LMPA =A0 =A0 =A0 =A0 0x210
>> @@ -448,6 +449,7 @@
>> =A0#define PECFG_BAR1MPA =A0 =A0 =A0 =A0 =A00x218
>> =A0#define PECFG_BAR2LMPA =A0 =A0 =A0 =A0 0x220
>> =A0#define PECFG_BAR2HMPA =A0 =A0 =A0 =A0 0x224
>> +#define PECFG_ECDEVCAPPA =A0 =A0 =A0 0x25c
>>
>> =A0#define PECFG_PIMEN =A0 =A0 =A0 =A0 =A0 =A00x33c
>> =A0#define PECFG_PIM0LAL =A0 =A0 =A0 =A0 =A00x340
>> @@ -494,5 +496,7 @@ enum
>> =A0 =A0 =A0 =A0LNKW_X8 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =3D 0x8
>> =A0};
>>
>> +/* Timout for reset phy */
>> +#define PCIE_PHY_RESET_TIMEOUT 10
>
> Is this value applicable to all the 44x devices with PCI-e?
> [Vinh Nguyen] At this time, we only checked this on APM821xx chips.
Then it should probably be conditionalized somehow. Or put as a
worst-case value that will work for them all.
josh
^ permalink raw reply
* Re: Please pull 'next' branch of 4xx tree
From: Josh Boyer @ 2011-12-21 20:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Artem Bityutskiy, Stephen Rothwell, linuxppc-dev
In-Reply-To: <CA+5PVA4=sc+QxqSp617BDBnOd+VfUis+r8QPJZLhRgee6Sy89A@mail.gmail.com>
On Tue, Dec 20, 2011 at 11:23 AM, Josh Boyer <jwboyer@gmail.com> wrote:
> Hi Ben,
>
> This is the relocatable series from Suzie that has been brewing for quite=
a
> while. =A0I also included a small fix for currituck that I hit when I was=
building
> various kernels.
>
> NOTE: To build anything config that includes the NDFC driver, you need th=
e fix
> Tony posted and is in linux-next to the ndfc driver. =A0I didn't include =
it here
> since it is already queued up in the MTD tree.
>
I've added Suzie's patch from today to change the WARN to INFO in the boot
wrapper thing. Updated tree info below.
josh
The following changes since commit 3f53638c805f75989f4b4be07efcfd173cdd5e2d=
:
powerpc: Fix old bug in prom_init setting of the color (2011-12-19
14:41:25 +1100)
are available in the git repository at:
git://git.infradead.org/users/jwboyer/powerpc-4xx.git next
Josh Boyer (1):
powerpc/44x: Fix build error on currituck platform
Suzuki Poulose (8):
powerpc: Rename mapping based RELOCATABLE to DYNAMIC_MEMSTART for Boo=
kE
powerpc/44x: Enable DYNAMIC_MEMSTART for 440x
powerpc: Process dynamic relocations for kernel
powerpc: Define virtual-physical translations for RELOCATABLE
powerpc/44x: Enable CONFIG_RELOCATABLE for PPC44x
powerpc/44x: Enable CRASH_DUMP for 440x
powerpc/boot: Change the load address for the wrapper to fit the kern=
el
powerpc/boot: Change the WARN to INFO for boot wrapper overlap messag=
e
arch/powerpc/Kconfig | 45 +++++-
arch/powerpc/Makefile | 6 +-
arch/powerpc/boot/wrapper | 20 +++
arch/powerpc/configs/44x/iss476-smp_defconfig | 3 +-
arch/powerpc/include/asm/kdump.h | 4 +-
arch/powerpc/include/asm/page.h | 89 ++++++++++-
arch/powerpc/kernel/Makefile | 2 +
arch/powerpc/kernel/crash_dump.c | 4 +-
arch/powerpc/kernel/head_44x.S | 105 +++++++++++++
arch/powerpc/kernel/head_fsl_booke.S | 2 +-
arch/powerpc/kernel/machine_kexec.c | 2 +-
arch/powerpc/kernel/prom_init.c | 2 +-
arch/powerpc/kernel/reloc_32.S | 208 +++++++++++++++++++++=
++++
arch/powerpc/kernel/vmlinux.lds.S | 8 +-
arch/powerpc/mm/44x_mmu.c | 2 +-
arch/powerpc/mm/init_32.c | 7 +
arch/powerpc/platforms/44x/currituck.c | 2 +-
arch/powerpc/relocs_check.pl | 14 ++-
18 files changed, 496 insertions(+), 29 deletions(-)
create mode 100644 arch/powerpc/kernel/reloc_32.S
^ permalink raw reply
* [PATCH] arch/powerpc/kvm/e500: Additional module.h => export.h fixup
From: Kyle Moffett @ 2011-12-21 18:09 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Alexander Graf, kvm-ppc, Kyle Moffett
This file, like many others, needs to include <linux/export.h>.
Signed-off-by: Kyle Moffett <Kyle.D.Moffett@boeing.com>
---
arch/powerpc/kvm/e500.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 26d2090..387c383 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -13,6 +13,7 @@
*/
#include <linux/kvm_host.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/err.h>
--
1.7.7.3
^ permalink raw reply related
* [PATCH SDK1.2 3/3] powerpc/fsl-pci: Add pci inbound/outbound PM support
From: Jia Hongtao @ 2011-12-21 7:10 UTC (permalink / raw)
To: linuxppc-dev; +Cc: B11780, b38951
In-Reply-To: <1324451458-4644-1-git-send-email-B38951@freescale.com>
Power supply for PCI inbound/outbound window registers is off when system
go to deep-sleep state. We save the values of registers before suspend
and restore to registers after resume.
Signed-off-by: Jiang Yutang <b14898@freescale.com>
Signed-off-by: Jia Hongtao <B38951@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
---
arch/powerpc/include/asm/pci-bridge.h | 6 ++
arch/powerpc/sysdev/fsl_pci.c | 108 +++++++++++++++++++++++++++++++++
2 files changed, 114 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 882b6aa..c99b40e 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -92,6 +92,12 @@ struct pci_controller {
void *private_data;
#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_SUSPEND
+ struct pci_outbound_window_regs __iomem *pci_pow;
+ struct pci_inbound_window_regs __iomem *pci_piw;
+ void *saved_regs;
+#endif
};
/* These are used for config access before all the PCI probing
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index e318e9d..046866f 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -756,12 +756,120 @@ static int __devinit fsl_pci_probe(struct platform_device *pdev)
return 0;
}
+#ifdef CONFIG_SUSPEND
+
+#define PCI_POW_NUMBER 5
+#define PCI_POW_BIAS 0xc00
+#define PCI_PIW_NUMBER 3
+#define PCI_PIW_BIAS 0xda0
+
+static int fsl_pci_suspend(struct platform_device *dev, pm_message_t state)
+{
+ struct pci_controller *hose;
+ struct pci_outbound_window_regs *pci_saved_pow;
+ struct pci_inbound_window_regs *pci_saved_piw;
+ struct resource pci_rsrc;
+ unsigned int i;
+
+ hose = pci_find_hose_for_OF_device(dev->dev.of_node);
+ of_address_to_resource(dev->dev.of_node, 0, &pci_rsrc);
+
+ hose->pci_pow = ioremap(pci_rsrc.start + PCI_POW_BIAS,
+ sizeof(struct pci_outbound_window_regs)
+ * PCI_POW_NUMBER);
+ if (!hose->pci_pow) {
+ pr_err("pci_pow ioremap error!\n");
+ return -ENOMEM;
+ }
+
+ hose->pci_piw = ioremap(pci_rsrc.start + PCI_PIW_BIAS,
+ sizeof(struct pci_inbound_window_regs)
+ * PCI_PIW_NUMBER);
+ if (!hose->pci_piw) {
+ pr_err("pci_piw ioremap error!\n");
+ goto err1;
+ }
+
+ hose->saved_regs = kmalloc(
+ sizeof(struct pci_outbound_window_regs) * PCI_POW_NUMBER +
+ sizeof(struct pci_inbound_window_regs) * PCI_PIW_NUMBER,
+ GFP_KERNEL);
+ if (!hose->saved_regs)
+ goto err2;
+
+ pci_saved_pow = hose->saved_regs;
+ for (i = 0; i < PCI_POW_NUMBER; i++) {
+ pci_saved_pow[i].potar = in_be32(&hose->pci_pow[i].potar);
+ pci_saved_pow[i].potear = in_be32(&hose->pci_pow[i].potear);
+ pci_saved_pow[i].powbar = in_be32(&hose->pci_pow[i].powbar);
+ pci_saved_pow[i].powar = in_be32(&hose->pci_pow[i].powar);
+ }
+
+ pci_saved_piw = (struct pci_inbound_window_regs *)
+ (pci_saved_pow + PCI_POW_NUMBER);
+ for (i = 0; i < PCI_PIW_NUMBER; i++) {
+ pci_saved_piw[i].pitar = in_be32(&hose->pci_piw[i].pitar);
+ pci_saved_piw[i].piwbar = in_be32(&hose->pci_piw[i].piwbar);
+ pci_saved_piw[i].piwbear = in_be32(&hose->pci_piw[i].piwbear);
+ pci_saved_piw[i].piwar = in_be32(&hose->pci_piw[i].piwar);
+ }
+
+ return 0;
+
+err2:
+ iounmap(hose->pci_piw);
+
+err1:
+ iounmap(hose->pci_pow);
+ return -ENOMEM;
+}
+
+static int fsl_pci_resume(struct platform_device *dev)
+{
+ struct pci_controller *hose;
+ struct pci_outbound_window_regs *pci_saved_pow;
+ struct pci_inbound_window_regs *pci_saved_piw;
+ unsigned int i;
+
+ hose = pci_find_hose_for_OF_device(dev->dev.of_node);
+ if (!hose->pci_pow || !hose->pci_piw || !hose->saved_regs)
+ return 0;
+
+ pci_saved_pow = hose->saved_regs;
+ for (i = 0; i < PCI_POW_NUMBER; i++) {
+ out_be32(&hose->pci_pow[i].potar, pci_saved_pow[i].potar);
+ out_be32(&hose->pci_pow[i].potear, pci_saved_pow[i].potear);
+ out_be32(&hose->pci_pow[i].powbar, pci_saved_pow[i].powbar);
+ out_be32(&hose->pci_pow[i].powar, pci_saved_pow[i].powar);
+ }
+ iounmap(hose->pci_pow);
+
+ pci_saved_piw = (struct pci_inbound_window_regs *)
+ (pci_saved_pow + PCI_POW_NUMBER);
+ for (i = 0; i < PCI_PIW_NUMBER; i++) {
+ out_be32(&hose->pci_piw[i].pitar, pci_saved_piw[i].pitar);
+ out_be32(&hose->pci_piw[i].piwbar, pci_saved_piw[i].piwbar);
+ out_be32(&hose->pci_piw[i].piwbear, pci_saved_piw[i].piwbear);
+ out_be32(&hose->pci_piw[i].piwar, pci_saved_piw[i].piwar);
+ }
+ iounmap(hose->pci_piw);
+ kfree(hose->saved_regs);
+ hose->saved_regs = NULL;
+
+ return 0;
+}
+#endif
+
static struct platform_driver fsl_pci_driver = {
.driver = {
.name = "fsl-pci",
.of_match_table = pci_ids,
},
.probe = fsl_pci_probe,
+#ifdef CONFIG_SUSPEND
+ .suspend = fsl_pci_suspend,
+ .resume = fsl_pci_resume,
+#endif
};
static int __init fsl_pci_init(void)
--
1.7.5.1
^ permalink raw reply related
* [PATCH SDK1.2 2/3] powerpc/fsl-pci: Only scan PCI bus if configured as a host
From: Jia Hongtao @ 2011-12-21 7:10 UTC (permalink / raw)
To: linuxppc-dev; +Cc: B11780, b38951
In-Reply-To: <1324451458-4644-1-git-send-email-B38951@freescale.com>
If we're an agent/end-point or fsl_add_bridge doesn't succeed due to some
resource failure we should not scan the PCI bus. We change fsl_add_bridge()
to return -ENODEV in the case we're an agent/end-point.
Signed-off-by: Jia Hongtao <B38951@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
---
arch/powerpc/sysdev/fsl_pci.c | 34 +++++++++++++++++++---------------
1 files changed, 19 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index a0f305d..e318e9d 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -370,7 +370,7 @@ int __init fsl_add_bridge(struct device_node *dev, int is_primary)
iounmap(hose->cfg_data);
iounmap(hose->cfg_addr);
pcibios_free_controller(hose);
- return 0;
+ return -ENODEV;
}
setup_pci_cmd(hose);
@@ -723,29 +723,33 @@ static const struct of_device_id pci_ids[] = {
static int __devinit fsl_pci_probe(struct platform_device *pdev)
{
struct pci_controller *hose;
+ int ret;
if (of_match_node(pci_ids, pdev->dev.of_node)) {
struct resource rsrc;
of_address_to_resource(pdev->dev.of_node, 0, &rsrc);
if ((rsrc.start & 0xfffff) == 8000)
- fsl_add_bridge(pdev->dev.of_node, 1);
+ ret = fsl_add_bridge(pdev->dev.of_node, 1);
else
- fsl_add_bridge(pdev->dev.of_node, 0);
+ ret = fsl_add_bridge(pdev->dev.of_node, 0);
+ if (ret == 0) {
#ifdef CONFIG_SWIOTLB
- hose = pci_find_hose_for_OF_device(pdev->dev.of_node);
- /*
- * if we couldn't map all of DRAM via the dma windows
- * we need SWIOTLB to handle buffers located outside of
- * dma capable memory region
- */
- if (memblock_end_of_DRAM() > hose->dma_window_base_cur
- + hose->dma_window_size) {
- ppc_swiotlb_enable = 1;
- set_pci_dma_ops(&swiotlb_dma_ops);
- ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
- }
+ hose = pci_find_hose_for_OF_device(pdev->dev.of_node);
+ /*
+ * if we couldn't map all of DRAM via the dma windows
+ * we need SWIOTLB to handle buffers located outside of
+ * dma capable memory region
+ */
+ if (memblock_end_of_DRAM() > hose->dma_window_base_cur
+ + hose->dma_window_size) {
+ ppc_swiotlb_enable = 1;
+ set_pci_dma_ops(&swiotlb_dma_ops);
+ ppc_md.pci_dma_dev_setup =
+ pci_dma_dev_setup_swiotlb;
+ }
#endif
+ }
}
--
1.7.5.1
^ permalink raw reply related
* [PATCH SDK1.2 1/3] powerpc/fsl-pci: Unify pci/pcie initialization code
From: Jia Hongtao @ 2011-12-21 7:10 UTC (permalink / raw)
To: linuxppc-dev; +Cc: B11780, b38951
In-Reply-To: <1324451458-4644-1-git-send-email-B38951@freescale.com>
We unified the Freescale pci/pcie initialization by changing the fsl_pci
to a platform driver.
In previous version pci/pcie initialization is in platform code which
Initialize pci bridge base on EP/RC or host/agent settings.
Signed-off-by: Jia Hongtao <B38951@freescale.com>
Signed-off-by: Li Yang <leoli@freescale.com>
---
arch/powerpc/platforms/85xx/p1022_ds.c | 39 +++++++----------------
arch/powerpc/sysdev/fsl_pci.c | 53 ++++++++++++++++++++++++++++++++
2 files changed, 65 insertions(+), 27 deletions(-)
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 2bf4342..41de2c1 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -277,32 +277,9 @@ void __init mpc85xx_smp_init(void);
*/
static void __init p1022_ds_setup_arch(void)
{
-#ifdef CONFIG_PCI
- struct device_node *np;
-#endif
- dma_addr_t max = 0xffffffff;
-
if (ppc_md.progress)
ppc_md.progress("p1022_ds_setup_arch()", 0);
-#ifdef CONFIG_PCI
- for_each_compatible_node(np, "pci", "fsl,p1022-pcie") {
- struct resource rsrc;
- struct pci_controller *hose;
-
- of_address_to_resource(np, 0, &rsrc);
-
- if ((rsrc.start & 0xfffff) == 0x8000)
- fsl_add_bridge(np, 1);
- else
- fsl_add_bridge(np, 0);
-
- hose = pci_find_hose_for_OF_device(np);
- max = min(max, hose->dma_window_base_cur +
- hose->dma_window_size);
- }
-#endif
-
#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
diu_ops.get_pixel_format = p1022ds_get_pixel_format;
diu_ops.set_gamma_table = p1022ds_set_gamma_table;
@@ -316,11 +293,8 @@ static void __init p1022_ds_setup_arch(void)
#endif
#ifdef CONFIG_SWIOTLB
- if (memblock_end_of_DRAM() > max) {
+ if (memblock_end_of_DRAM() > 0xffffffff)
ppc_swiotlb_enable = 1;
- set_pci_dma_ops(&swiotlb_dma_ops);
- ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
- }
#endif
pr_info("Freescale P1022 DS reference board\n");
@@ -339,6 +313,17 @@ static int __init p1022_ds_publish_devices(void)
}
machine_device_initcall(p1022_ds, p1022_ds_publish_devices);
+static struct of_device_id __initdata p1022_pci_ids[] = {
+ { .compatible = "fsl,p1022-pcie", },
+ {},
+};
+
+static int __init p1022_ds_publish_pci_device(void)
+{
+ return of_platform_bus_probe(NULL, p1022_pci_ids, NULL);
+}
+machine_arch_initcall(p1022_ds, p1022_ds_publish_pci_device);
+
machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
/*
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 4ce547e..a0f305d 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -712,3 +712,56 @@ u64 fsl_pci_immrbar_base(struct pci_controller *hose)
return 0;
}
+
+static const struct of_device_id pci_ids[] = {
+ { .compatible = "fsl,mpc8540-pci", },
+ { .compatible = "fsl,mpc8548-pcie", },
+ { .compatible = "fsl,p1022-pcie", },
+ {},
+};
+
+static int __devinit fsl_pci_probe(struct platform_device *pdev)
+{
+ struct pci_controller *hose;
+
+ if (of_match_node(pci_ids, pdev->dev.of_node)) {
+ struct resource rsrc;
+ of_address_to_resource(pdev->dev.of_node, 0, &rsrc);
+ if ((rsrc.start & 0xfffff) == 8000)
+ fsl_add_bridge(pdev->dev.of_node, 1);
+ else
+ fsl_add_bridge(pdev->dev.of_node, 0);
+
+#ifdef CONFIG_SWIOTLB
+ hose = pci_find_hose_for_OF_device(pdev->dev.of_node);
+ /*
+ * if we couldn't map all of DRAM via the dma windows
+ * we need SWIOTLB to handle buffers located outside of
+ * dma capable memory region
+ */
+ if (memblock_end_of_DRAM() > hose->dma_window_base_cur
+ + hose->dma_window_size) {
+ ppc_swiotlb_enable = 1;
+ set_pci_dma_ops(&swiotlb_dma_ops);
+ ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
+ }
+#endif
+
+ }
+
+ return 0;
+}
+
+static struct platform_driver fsl_pci_driver = {
+ .driver = {
+ .name = "fsl-pci",
+ .of_match_table = pci_ids,
+ },
+ .probe = fsl_pci_probe,
+};
+
+static int __init fsl_pci_init(void)
+{
+ return platform_driver_register(&fsl_pci_driver);
+}
+arch_initcall(fsl_pci_init);
--
1.7.5.1
^ permalink raw reply related
* [PATCH SDK1.2 0/3] pci patches description
From: Jia Hongtao @ 2011-12-21 7:10 UTC (permalink / raw)
To: linuxppc-dev; +Cc: B11780, b38951
This serials of patches include two parts.
First, we unify the pci initialization code using platform driver
mechanism. Then, we add PM support for deep sleep stat to save and
restore inbound/outbound window registers.
These patches are against 'next' branch on:
http://git.kernel.org/?p=linux/kernel/git/galak/powerpc.git
^ permalink raw reply
* [PATCH] [boot] Change the WARN to INFO for boot wrapper overlap message
From: Suzuki K. Poulose @ 2011-12-21 7:20 UTC (permalink / raw)
To: Josh Boyer, Stephen Rothwell; +Cc: linuxppc-dev, paulus, linux-kernel
In-Reply-To: <CA+5PVA7NhzxwxR5WGDmUQ432NehNnzRT+y05wve+FBXHyGaiwA@mail.gmail.com>
commit c55aef0e5bc6 ("powerpc/boot: Change the load address
for the wrapper to fit the kernel") introduced a WARNING to
inform the user that the uncompressed kernel would overlap
the boot uncompressing wrapper code. Change it to an INFO.
I initially thought, this would be a 'WARNING' for the those
boards, where the link_address should be fixed, so that the
user can take actions accordingly.
Changing the same to INFO.
Signed-off-by: Suzuki K. Poulose <suzuki@in.ibm.com>
---
arch/powerpc/boot/wrapper | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index c8d6aaf..2b171cd 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -282,9 +282,9 @@ round_size=0x$(printf "%x" $round_size)
link_addr=$(printf "%d" $link_address)
if [ $link_addr -lt $strip_size ]; then
- echo "WARN: Uncompressed kernel (size 0x$(printf "%x\n" $strip_size))" \
+ echo "INFO: Uncompressed kernel (size 0x$(printf "%x\n" $strip_size))" \
"overlaps the address of the wrapper($link_address)"
- echo "WARN: Fixing the link_address of wrapper to ($round_size)"
+ echo "INFO: Fixing the link_address of wrapper to ($round_size)"
link_address=$round_size
fi
^ permalink raw reply related
* RE: [PATCH 3/3] powerpc/44x: Add support PCI-E for APM821xx SoC and Bluestone board
From: Vinh Huu Tuong Nguyen @ 2011-12-21 4:47 UTC (permalink / raw)
To: Josh Boyer
Cc: Ayman El-Khashab, Dave Kleikamp, Lucas De Marchi, Rob Herring,
Paul Gortmaker, Paul Mackerras, Anton Blanchard, Jiri Kosina,
linuxppc-dev, linux-kernel
In-Reply-To: <CA+5PVA41Haf-_H3UoR1O3VFbC3XtgScyo5hekNjt0VWxunL-fg@mail.gmail.com>
Hi Josh,
Please see below for my comments. If you have any concerns or suggestion,
please let me know.
Best regards,
Vinh Nguyen.
-----Original Message-----
From: Josh Boyer [mailto:jwboyer@gmail.com]
Sent: Tuesday, December 20, 2011 10:32 PM
To: Vinh Nguyen Huu Tuong
Cc: Benjamin Herrenschmidt; Paul Mackerras; Matt Porter; Kumar Gala; Paul
Gortmaker; Anton Blanchard; Dave Kleikamp; Grant Likely; Tony Breeds; Rob
Herring; Jiri Kosina; Lucas De Marchi; Ayman El-Khashab;
linuxppc-dev@lists.ozlabs.org; linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/3] powerpc/44x: Add support PCI-E for APM821xx SoC
and Bluestone board
On Tue, Dec 20, 2011 at 7:44 AM, Vinh Nguyen Huu Tuong
<vhtnguyen@apm.com> wrote:
> This patch extends PCI-E driver to support PCI-E for APM821xx SoC on
Bluestone board.
>
> Signed-off-by: Vinh Nguyen Huu Tuong <vhtnguyen@apm.com>
> +static int apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
> +{
> + =A0 =A0 =A0 u32 val;
> + =A0 =A0 =A0 u32 utlset1;
> + =A0 =A0 =A0 u32 timeout;
> +
> + =A0 =A0 =A0 /*
> + =A0 =A0 =A0 =A0* Do a software reset on PCIe ports.
> + =A0 =A0 =A0 =A0* This code is to fix the issue that pci drivers doesn't
re-assign
> + =A0 =A0 =A0 =A0* bus number for PCIE devices after Uboot
> + =A0 =A0 =A0 =A0* scanned and configured all the buses (eg. PCIE NIC
IntelPro/1000
> + =A0 =A0 =A0 =A0* PT quad port, SAS LSI 1064E)
> + =A0 =A0 =A0 =A0*/
> +
> + =A0 =A0 =A0 mtdcri(SDR0, PESDR0_460EX_PHY_CTL_RST + (port->index * 0x55=
),
0x0);
> + =A0 =A0 =A0 mdelay(10);
> +
> + =A0 =A0 =A0 if (port->endpoint)
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 val =3D PTYPE_LEGACY_ENDPOINT << 20;
> + =A0 =A0 =A0 else
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 val =3D PTYPE_ROOT_PORT << 20;
> +
> + =A0 =A0 =A0 if (port->index =3D=3D 0) {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 val |=3D LNKW_X1 << 12;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 utlset1 =3D 0x00000000;
> + =A0 =A0 =A0 } else {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 val |=3D LNKW_X4 << 12;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 utlset1 =3D 0x20101101;
> + =A0 =A0 =A0 }
> +
> + =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_DLPSET, val);
> + =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET1, utlset1);
> + =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET2, 0x01010000);
> +
> + =A0 =A0 =A0 switch (port->index) {
> + =A0 =A0 =A0 case 0:
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR0_460EX_L0CDRCTL, 0x00003=
230);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR0_460EX_L0DRV, 0x00000130=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR0_460EX_L0CLK, 0x00000006=
);
> +
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR0_460EX_PHY_CTL_RST, 0x10=
000000);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mdelay(50);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR0_460EX_PHY_CTL_RST, 0x30=
000000);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 break;
> +
> + =A0 =A0 =A0 case 1:
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L0CDRCTL, 0x00003=
230);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L1CDRCTL, 0x00003=
230);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L2CDRCTL, 0x00003=
230);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L3CDRCTL, 0x00003=
230);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L0DRV, 0x00000130=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L1DRV, 0x00000130=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L2DRV, 0x00000130=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L3DRV, 0x00000130=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L0CLK, 0x00000006=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L1CLK, 0x00000006=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L2CLK, 0x00000006=
);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_L3CLK, 0x00000006=
);
> +
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, PESDR1_460EX_PHY_CTL_RST, 0x10=
000000);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 break;
> + =A0 =A0 =A0 }
Do we need a default case here to catch oddness and exit the function?
[Vinh Nguyen] we've already checked the port->index before calling this
function, so we assume that the port->index never exceed the checked
values.
> +
> + =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET,
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mfdcri(SDR0, port->sdr_base + PESDRn_RCSSET=
) |
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 (PESDRx_RCSSET_RSTGU | PESDRx_RCSSET_RSTPYN=
));
> +
> + =A0 =A0 =A0 /* Poll for PHY reset */
> + =A0 =A0 =A0 timeout =3D 0;
> + =A0 =A0 =A0 while ((!(mfdcri(SDR0, PESDR0_460EX_RSTSTA +
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 (port->index * 0x55)) & 0x1=
)) &&
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0(timeout < PCIE_PHY_RESET_TIMEOUT)) {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 udelay(10);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 timeout++;
> + =A0 =A0 =A0 }
> +
> + =A0 =A0 =A0 if (timeout < PCIE_PHY_RESET_TIMEOUT) {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET=
,
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 (mfdcri(SDR0, port->sdr_bas=
e + PESDRn_RCSSET) &
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 ~(PESDRx_RCSSET_RSTGU | PES=
DRx_RCSSET_RSTDL)) |
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 PESDRx_RCSSET_RSTPYN);
> +
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 port->has_ibpre =3D 1;
> +
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 return 0;
> + =A0 =A0 =A0 } else {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 printk(KERN_INFO "PCIE: Can't reset PHY\n")=
;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 return -1;
> + =A0 =A0 =A0 }
If we can't reset the PHY, does this whole function essentially fail?
Do the devices not get renumbered, etc? If so, you probably want to
make that KERN_ERR.
[Vinh Nguyen] if we can't reset the PHY, maybe the device can't work
properly. I will update codes to return the error in case PHY can't reset.
> @@ -1751,9 +1856,9 @@ static void __init
ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 * if it works
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 */
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM0LAL, 0x00000000=
);
> - =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM0LAH, 0x00000000)=
;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM0LAH, 0x00000008)=
; /* Moving
on HB */
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM1LAL, 0x00000000=
);
> - =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM1LAH, 0x00000000)=
;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 out_le32(mbase + PECFG_PIM1LAH, 0x0000000c)=
; /* Moving
on HB */
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM01SAH, 0xffff000=
0);
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0out_le32(mbase + PECFG_PIM01SAL, 0x0000000=
0);
Why are these values changed, and are those changes only needed on
APM821xx?
[Vinh Nguyen] In system memory map of 460EX chip, we have an "alias DDR
SDRAM" area that is Local Memory Alias for HB(high bandwidth), so we tried
to initialize it for speedup. For APM821xx, although we didn't mention
about this area, this configuration still works well. So we keep it.
> diff --git a/arch/powerpc/sysdev/ppc4xx_pci.h
b/arch/powerpc/sysdev/ppc4xx_pci.h
> index 32ce763..faf3017 100644
> --- a/arch/powerpc/sysdev/ppc4xx_pci.h
> +++ b/arch/powerpc/sysdev/ppc4xx_pci.h
> @@ -441,6 +441,7 @@
> =A0/*
> =A0* Config space register offsets
> =A0*/
> +#define PECFG_ECDEVCTL =A0 =A0 =A0 =A0 0x060
> =A0#define PECFG_ECRTCTL =A0 =A0 =A0 =A0 =A00x074
>
> =A0#define PECFG_BAR0LMPA =A0 =A0 =A0 =A0 0x210
> @@ -448,6 +449,7 @@
> =A0#define PECFG_BAR1MPA =A0 =A0 =A0 =A0 =A00x218
> =A0#define PECFG_BAR2LMPA =A0 =A0 =A0 =A0 0x220
> =A0#define PECFG_BAR2HMPA =A0 =A0 =A0 =A0 0x224
> +#define PECFG_ECDEVCAPPA =A0 =A0 =A0 0x25c
>
> =A0#define PECFG_PIMEN =A0 =A0 =A0 =A0 =A0 =A00x33c
> =A0#define PECFG_PIM0LAL =A0 =A0 =A0 =A0 =A00x340
> @@ -494,5 +496,7 @@ enum
> =A0 =A0 =A0 =A0LNKW_X8 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =3D 0x8
> =A0};
>
> +/* Timout for reset phy */
> +#define PCIE_PHY_RESET_TIMEOUT 10
Is this value applicable to all the 44x devices with PCI-e?
[Vinh Nguyen] At this time, we only checked this on APM821xx chips.
josh
^ permalink raw reply
* Re: [PATCH] Copy machine descriptor after probe succeed
From: bill4carson @ 2011-12-21 2:15 UTC (permalink / raw)
To: Stephen Rothwell; +Cc: linuxppc-dev
In-Reply-To: <20111220211751.7dcff65ecfb1c5eaf022070d@canb.auug.org.au>
On 2011年12月20日 18:17, Stephen Rothwell wrote:
> Hi Bill,
>
> On Tue, 20 Dec 2011 17:08:47 +0800 bill4carson@gmail.com wrote:
>> From: Bill Carson<bill4carson@gmail.com>
>>
>> It make more sense to copy machine descriptor AFTER machine probe return
>> succeed.
> Some of the platform's probe routines modify the ppc_md structure and so
> assume that it is has been popluated before the probe routine is called.
>
I didn't see the whole picture before :(
thanks for your point.
--
I am a slow learner
but I will keep trying to fight for my dreams!
--bill
^ permalink raw reply
* [RFC PATCH 14/16] KVM: PPC: booke: category E.HV (GS-mode) support
From: Scott Wood @ 2011-12-21 1:34 UTC (permalink / raw)
To: agraf; +Cc: linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <20111221013340.GA8368@schlenkerla.am.freescale.net>
Chips such as e500mc that implement category E.HV in Power ISA 2.06
provide hardware virtualization features, including a new MSR mode for
guest state. The guest OS can perform many operations without trapping
into the hypervisor, including transitions to and from guest userspace.
Since we can use SRR1[GS] to reliably tell whether an exception came from
guest state, instead of messing around with IVPR, we use DO_KVM similarly
to book3s.
Current issues include:
- Machine checks from guest state are not routed to the host handler.
- The guest can cause a host oops by executing an emulated instruction
in a page that lacks read permission. Existing e500/4xx support has
the same problem.
Includes work by Ashish Kalra <Ashish.Kalra@freescale.com>,
Varun Sethi <Varun.Sethi@freescale.com>, and
Liu Yu <yu.liu@freescale.com>.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/include/asm/dbell.h | 1 +
arch/powerpc/include/asm/kvm_asm.h | 8 +
arch/powerpc/include/asm/kvm_booke_hv_asm.h | 49 +++
arch/powerpc/include/asm/kvm_host.h | 19 +-
arch/powerpc/include/asm/kvm_ppc.h | 3 +
arch/powerpc/include/asm/mmu-book3e.h | 6 +
arch/powerpc/include/asm/processor.h | 3 +
arch/powerpc/include/asm/reg.h | 2 +
arch/powerpc/include/asm/reg_booke.h | 34 ++
arch/powerpc/kernel/asm-offsets.c | 15 +-
arch/powerpc/kernel/head_booke.h | 28 ++-
arch/powerpc/kvm/Kconfig | 3 +
arch/powerpc/kvm/booke.c | 398 ++++++++++++++-----
arch/powerpc/kvm/booke.h | 24 +-
arch/powerpc/kvm/booke_emulate.c | 23 +-
arch/powerpc/kvm/bookehv_interrupts.S | 587 +++++++++++++++++++++++++++
arch/powerpc/kvm/powerpc.c | 5 +
arch/powerpc/kvm/timing.h | 6 +
18 files changed, 1107 insertions(+), 107 deletions(-)
create mode 100644 arch/powerpc/include/asm/kvm_booke_hv_asm.h
create mode 100644 arch/powerpc/kvm/bookehv_interrupts.S
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index efa74ac..d7365b0 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -19,6 +19,7 @@
#define PPC_DBELL_MSG_BRDCAST (0x04000000)
#define PPC_DBELL_TYPE(x) (((x) & 0xf) << (63-36))
+#define PPC_DBELL_LPID(x) ((x) << (63 - 49))
enum ppc_dbell {
PPC_DBELL = 0, /* doorbell */
PPC_DBELL_CRIT = 1, /* critical doorbell */
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 7b1f0e0..0978152 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -48,6 +48,14 @@
#define BOOKE_INTERRUPT_SPE_FP_DATA 33
#define BOOKE_INTERRUPT_SPE_FP_ROUND 34
#define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
+#define BOOKE_INTERRUPT_DOORBELL 36
+#define BOOKE_INTERRUPT_DOORBELL_CRITICAL 37
+
+/* booke_hv */
+#define BOOKE_INTERRUPT_GUEST_DBELL 38
+#define BOOKE_INTERRUPT_GUEST_DBELL_CRIT 39
+#define BOOKE_INTERRUPT_HV_SYSCALL 40
+#define BOOKE_INTERRUPT_HV_PRIV 41
/* book3s */
diff --git a/arch/powerpc/include/asm/kvm_booke_hv_asm.h b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
new file mode 100644
index 0000000..30a600f
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_KVM_BOOKE_HV_ASM_H
+#define ASM_KVM_BOOKE_HV_ASM_H
+
+#ifdef __ASSEMBLY__
+
+/*
+ * All exceptions from guest state must go through KVM
+ * (except for those which are delivered directly to the guest) --
+ * there are no exceptions for which we fall through directly to
+ * the normal host handler.
+ *
+ * Expected inputs (normal exceptions):
+ * SCRATCH0 = saved r10
+ * r10 = thread struct
+ * r11 = appropriate SRR1 variant (currently used as scratch)
+ * r13 = saved CR
+ * *(r10 + THREAD_NORMSAVE(0)) = saved r11
+ * *(r10 + THREAD_NORMSAVE(2)) = saved r13
+ *
+ * Expected inputs (crit/mcheck/debug exceptions):
+ * appropriate SCRATCH = saved r8
+ * r8 = exception level stack frame
+ * r9 = *(r8 + _CCR) = saved CR
+ * r11 = appropriate SRR1 variant (currently used as scratch)
+ * *(r8 + GPR9) = saved r9
+ * *(r8 + GPR10) = saved r10 (r10 not yet clobbered)
+ * *(r8 + GPR11) = saved r11
+ */
+.macro DO_KVM intno srr1
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mtocrf 0x80, r11 /* check MSR[GS] without clobbering reg */
+ bf 3, kvmppc_resume_\intno\()_\srr1
+ b kvmppc_handler_\intno\()_\srr1
+kvmppc_resume_\intno\()_\srr1:
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
+.endm
+
+#endif /*__ASSEMBLY__ */
+#endif /* ASM_KVM_BOOKE_HV_ASM_H */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ad4d671..d603513 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -107,6 +107,8 @@ struct kvm_vcpu_stat {
u32 dec_exits;
u32 ext_intr_exits;
u32 halt_wakeup;
+ u32 dbell_exits;
+ u32 gdbell_exits;
#ifdef CONFIG_PPC_BOOK3S
u32 pf_storage;
u32 pf_instruc;
@@ -141,6 +143,7 @@ enum kvm_exit_types {
EMULATED_TLBSX_EXITS,
EMULATED_TLBWE_EXITS,
EMULATED_RFI_EXITS,
+ EMULATED_RFCI_EXITS,
DEC_EXITS,
EXT_INTR_EXITS,
HALT_WAKEUP,
@@ -148,6 +151,8 @@ enum kvm_exit_types {
FP_UNAVAIL,
DEBUG_EXITS,
TIMEINGUEST,
+ DBELL_EXITS,
+ GDBELL_EXITS,
__NUMBER_OF_KVM_EXIT_TYPES
};
@@ -213,10 +218,10 @@ struct revmap_entry {
#define KVMPPC_GOT_PAGE 0x80
struct kvm_arch {
+ unsigned int lpid;
#ifdef CONFIG_KVM_BOOK3S_64_HV
unsigned long hpt_virt;
struct revmap_entry *revmap;
- unsigned int lpid;
unsigned int host_lpid;
unsigned long host_lpcr;
unsigned long sdr1;
@@ -346,6 +351,17 @@ struct kvm_vcpu_arch {
u32 qpr[32];
#endif
+#ifdef CONFIG_KVM_BOOKE_HV
+ u32 host_mas4;
+ u32 host_mas6;
+ u32 shadow_epcr;
+ u32 epcr;
+ u32 shadow_msrp;
+ u32 eplc;
+ u32 epsc;
+ u32 oldpir;
+#endif
+
#ifdef CONFIG_PPC_BOOK3S
ulong hflags;
ulong guest_owned_ext;
@@ -417,6 +433,7 @@ struct kvm_vcpu_arch {
ulong queued_esr;
u32 tlbcfg[4];
u32 mmucfg;
+ u32 epr;
#endif
gpa_t paddr_accessed;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 5524f88..247b920 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -137,6 +137,9 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem);
+extern int kvmppc_bookehv_init(void);
+extern void kvmppc_bookehv_exit(void);
+
/*
* Cuts out inst bits with ordering according to spec.
* That means the leftmost bit is zero. All given bits are included.
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 36a6eaa..b8e303c 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -104,6 +104,8 @@
#define MAS4_TSIZED_MASK 0x00000f80 /* Default TSIZE */
#define MAS4_TSIZED_SHIFT 7
+#define MAS5_SGS 0x80000000
+
#define MAS6_SPID0 0x3FFF0000
#define MAS6_SPID1 0x00007FFE
#define MAS6_ISIZE(x) MAS1_TSIZE(x)
@@ -118,6 +120,10 @@
#define MAS7_RPN 0xFFFFFFFF
+#define MAS8_TGS 0x80000000 /* Guest space */
+#define MAS8_VF 0x40000000 /* Virtualization Fault */
+#define MAS8_TLPID 0x000000ff
+
/* Bit definitions for MMUCFG */
#define MMUCFG_MAVN 0x00000003 /* MMU Architecture Version Number */
#define MMUCFG_MAVN_V1 0x00000000 /* v1.0 */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index eb11a44..032a984 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -243,6 +243,9 @@ struct thread_struct {
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
void* kvm_shadow_vcpu; /* KVM internal data */
#endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
+#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
+ struct kvm_vcpu *kvm_vcpu;
+#endif
#ifdef CONFIG_PPC64
unsigned long dscr;
int dscr_inherit;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 209dc74..5993770 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -257,7 +257,9 @@
#define LPCR_LPES_SH 2
#define LPCR_RMI 0x00000002 /* real mode is cache inhibit */
#define LPCR_HDICE 0x00000001 /* Hyp Decr enable (HV,PR,EE) */
+#ifndef SPRN_LPID
#define SPRN_LPID 0x13F /* Logical Partition Identifier */
+#endif
#define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */
#define SPRN_HMER 0x150 /* Hardware m? error recovery */
#define SPRN_HMEER 0x151 /* Hardware m? enable error recovery */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 03c48e8..bd80b8d 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -56,17 +56,29 @@
#define SPRN_SPRG7W 0x117 /* Special Purpose Register General 7 Write */
#define SPRN_EPCR 0x133 /* Embedded Processor Control Register */
#define SPRN_DBCR2 0x136 /* Debug Control Register 2 */
+#define SPRN_MSRP 0x137 /* MSR Protect Register */
#define SPRN_IAC3 0x13A /* Instruction Address Compare 3 */
#define SPRN_IAC4 0x13B /* Instruction Address Compare 4 */
#define SPRN_DVC1 0x13E /* Data Value Compare Register 1 */
#define SPRN_DVC2 0x13F /* Data Value Compare Register 2 */
+#define SPRN_LPID 0x152 /* Logical Partition ID */
#define SPRN_MAS8 0x155 /* MMU Assist Register 8 */
#define SPRN_TLB0PS 0x158 /* TLB 0 Page Size Register */
#define SPRN_MAS5_MAS6 0x15c /* MMU Assist Register 5 || 6 */
#define SPRN_MAS8_MAS1 0x15d /* MMU Assist Register 8 || 1 */
#define SPRN_EPTCFG 0x15e /* Embedded Page Table Config */
+#define SPRN_GSPRG0 0x170 /* Guest SPRG0 */
+#define SPRN_GSPRG1 0x171 /* Guest SPRG1 */
+#define SPRN_GSPRG2 0x172 /* Guest SPRG2 */
+#define SPRN_GSPRG3 0x173 /* Guest SPRG3 */
#define SPRN_MAS7_MAS3 0x174 /* MMU Assist Register 7 || 3 */
#define SPRN_MAS0_MAS1 0x175 /* MMU Assist Register 0 || 1 */
+#define SPRN_GSRR0 0x17A /* Guest SRR0 */
+#define SPRN_GSRR1 0x17B /* Guest SRR1 */
+#define SPRN_GEPR 0x17C /* Guest EPR */
+#define SPRN_GDEAR 0x17D /* Guest DEAR */
+#define SPRN_GPIR 0x17E /* Guest PIR */
+#define SPRN_GESR 0x17F /* Guest Exception Syndrome Register */
#define SPRN_IVOR0 0x190 /* Interrupt Vector Offset Register 0 */
#define SPRN_IVOR1 0x191 /* Interrupt Vector Offset Register 1 */
#define SPRN_IVOR2 0x192 /* Interrupt Vector Offset Register 2 */
@@ -87,6 +99,13 @@
#define SPRN_IVOR39 0x1B1 /* Interrupt Vector Offset Register 39 */
#define SPRN_IVOR40 0x1B2 /* Interrupt Vector Offset Register 40 */
#define SPRN_IVOR41 0x1B3 /* Interrupt Vector Offset Register 41 */
+#define SPRN_GIVOR2 0x1B8 /* Guest IVOR2 */
+#define SPRN_GIVOR3 0x1B9 /* Guest IVOR3 */
+#define SPRN_GIVOR4 0x1BA /* Guest IVOR4 */
+#define SPRN_GIVOR8 0x1BB /* Guest IVOR8 */
+#define SPRN_GIVOR13 0x1BC /* Guest IVOR13 */
+#define SPRN_GIVOR14 0x1BD /* Guest IVOR14 */
+#define SPRN_GIVPR 0x1BF /* Guest IVPR */
#define SPRN_SPEFSCR 0x200 /* SPE & Embedded FP Status & Control */
#define SPRN_BBEAR 0x201 /* Branch Buffer Entry Address Register */
#define SPRN_BBTAR 0x202 /* Branch Buffer Target Address Register */
@@ -235,6 +254,10 @@
#define MCSR_LDG 0x00002000UL /* Guarded Load */
#define MCSR_TLBSYNC 0x00000002UL /* Multiple tlbsyncs detected */
#define MCSR_BSL2_ERR 0x00000001UL /* Backside L2 cache error */
+
+#define MSRP_UCLEP 0x04000000 /* Protect MSR[UCLE] */
+#define MSRP_DEP 0x00000200 /* Protect MSR[DE] */
+#define MSRP_PMMP 0x00000004 /* Protect MSR[PMM] */
#endif
#ifdef CONFIG_E200
@@ -589,6 +612,17 @@
#define SPRN_EPCR_DMIUH 0x00400000 /* Disable MAS Interrupt updates
* for hypervisor */
+/* Bit definitions for EPLC/EPSC */
+#define EPC_EPR 0x80000000 /* 1 = user, 0 = kernel */
+#define EPC_EPR_SHIFT 31
+#define EPC_EAS 0x40000000 /* Address Space */
+#define EPC_EAS_SHIFT 30
+#define EPC_EGS 0x20000000 /* 1 = guest, 0 = hypervisor */
+#define EPC_EGS_SHIFT 29
+#define EPC_ELPID 0x00ff0000
+#define EPC_ELPID_SHIFT 16
+#define EPC_EPID 0x00003fff
+#define EPC_EPID_SHIFT 0
/*
* The IBM-403 is an even more odd special case, as it is much
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c80bdd1..e179f09 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -119,6 +119,9 @@ int main(void)
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
#endif
+#ifdef CONFIG_KVM_BOOKE_HV
+ DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
+#endif
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
@@ -400,6 +403,7 @@ int main(void)
#ifdef CONFIG_KVM
DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
+ DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.pid));
DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.regs.gpr));
DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr));
@@ -442,9 +446,11 @@ int main(void)
DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4));
DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6));
+ DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
+ DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
+
/* book3s */
#ifdef CONFIG_KVM_BOOK3S_64_HV
- DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
@@ -459,7 +465,6 @@ int main(void)
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
#endif
#ifdef CONFIG_PPC_BOOK3S
- DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
@@ -605,6 +610,12 @@ int main(void)
DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr));
#endif
+#ifdef CONFIG_KVM_BOOKE_HV
+ DEFINE(VCPU_HOST_MAS4, offsetof(struct kvm_vcpu, arch.host_mas4));
+ DEFINE(VCPU_HOST_MAS6, offsetof(struct kvm_vcpu, arch.host_mas6));
+ DEFINE(VCPU_EPLC, offsetof(struct kvm_vcpu, arch.eplc));
+#endif
+
#ifdef CONFIG_KVM_EXIT_TIMING
DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
arch.timing_exit.tv32.tbu));
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 06ab353..b87c335 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -3,6 +3,7 @@
#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
#include <asm/kvm_asm.h>
+#include <asm/kvm_booke_hv_asm.h>
/*
* Macros used for common Book-e exception handling
@@ -36,8 +37,9 @@
stw r11, THREAD_NORMSAVE(0)(r10); \
stw r13, THREAD_NORMSAVE(2)(r10); \
mfcr r13; /* save CR in r13 for now */\
- mfspr r11,SPRN_SRR1; /* check whether user or kernel */\
- andi. r11,r11,MSR_PR; \
+ mfspr r11, SPRN_SRR1; \
+ DO_KVM BOOKE_INTERRUPT_##intno SPRN_SRR1; \
+ andi. r11, r11, MSR_PR; /* check whether user or kernel */\
mr r11, r1; \
beq 1f; \
/* if from user, start at top of this thread's kernel stack */ \
@@ -123,8 +125,9 @@
stw r10,GPR10(r8); \
stw r11,GPR11(r8); \
stw r9,_CCR(r8); /* save CR on stack */\
- mfspr r10,exc_level_srr1; /* check whether user or kernel */\
- andi. r10,r10,MSR_PR; \
+ mfspr r11,exc_level_srr1; /* check whether user or kernel */\
+ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \
+ andi. r11,r11,MSR_PR; \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\
@@ -173,6 +176,23 @@
SPRN_MCSRR0, SPRN_MCSRR1)
/*
+ * Guest Doorbell -- this is a bit odd in that uses GSRR0/1 despite
+ * being delivered to the host. This exception can only happen
+ * inside a KVM guest -- so we just handle up to the DO_KVM rather
+ * than try to fit this into one of the existing prolog macros.
+ */
+#define GUEST_DOORBELL_EXCEPTION \
+ START_EXCEPTION(GuestDoorbell); \
+ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \
+ mfspr r10, SPRN_SPRG_THREAD; \
+ stw r11, THREAD_NORMSAVE(0)(r10); \
+ mfspr r11, SPRN_SRR1; \
+ stw r13, THREAD_NORMSAVE(2)(r10); \
+ mfcr r13; /* save CR in r13 for now */\
+ DO_KVM BOOKE_INTERRUPT_GUEST_DBELL SPRN_GSRR1; \
+ trap
+
+/*
* Exception vectors.
*/
#define START_EXCEPTION(label) \
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 8f64709..2c33cd3 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -90,6 +90,9 @@ config KVM_BOOK3S_64_PR
depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV
select KVM_BOOK3S_PR
+config KVM_BOOKE_HV
+ bool
+
config KVM_440
bool "KVM support for PowerPC 440 processors"
depends on EXPERIMENTAL && 44x
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index f66e741..cf63b93 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -17,6 +17,8 @@
*
* Authors: Hollis Blanchard <hollisb@us.ibm.com>
* Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ * Scott Wood <scottwood@freescale.com>
+ * Varun Sethi <varun.sethi@freescale.com>
*/
#include <linux/errno.h>
@@ -30,9 +32,12 @@
#include <asm/cputable.h>
#include <asm/uaccess.h>
#include <asm/kvm_ppc.h>
-#include "timing.h"
#include <asm/cacheflush.h>
+#include <asm/dbell.h>
+#include <asm/hw_irq.h>
+#include <asm/irq.h>
+#include "timing.h"
#include "booke.h"
unsigned long kvmppc_booke_handlers;
@@ -55,6 +60,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "dec", VCPU_STAT(dec_exits) },
{ "ext_intr", VCPU_STAT(ext_intr_exits) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+ { "doorbell", VCPU_STAT(dbell_exits) },
+ { "guest doorbell", VCPU_STAT(gdbell_exits) },
{ NULL }
};
@@ -123,6 +130,10 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
{
u32 old_msr = vcpu->arch.shared->msr;
+#ifdef CONFIG_KVM_BOOKE_HV
+ new_msr |= MSR_GS;
+#endif
+
vcpu->arch.shared->msr = new_msr;
kvmppc_mmu_msr_notify(vcpu, old_msr);
@@ -197,6 +208,75 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
}
+static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_GSRR0, srr0);
+ mtspr(SPRN_GSRR1, srr1);
+#else
+ vcpu->arch.shared->srr0 = srr0;
+ vcpu->arch.shared->srr1 = srr1;
+#endif
+}
+
+static void set_guest_csrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+ vcpu->arch.csrr0 = srr0;
+ vcpu->arch.csrr1 = srr1;
+}
+
+static void set_guest_dsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+ if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) {
+ vcpu->arch.dsrr0 = srr0;
+ vcpu->arch.dsrr1 = srr1;
+ } else {
+ set_guest_csrr(vcpu, srr0, srr1);
+ }
+}
+
+static void set_guest_mcsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+ vcpu->arch.mcsrr0 = srr0;
+ vcpu->arch.mcsrr1 = srr1;
+}
+
+static unsigned long get_guest_dear(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+ return mfspr(SPRN_GDEAR);
+#else
+ return vcpu->arch.shared->dar;
+#endif
+}
+
+static void set_guest_dear(struct kvm_vcpu *vcpu, unsigned long dear)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_GDEAR, dear);
+#else
+ vcpu->arch.shared->dar = dear;
+#endif
+}
+
+static unsigned long get_guest_esr(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+ return mfspr(SPRN_ESR);
+#else
+ return vcpu->arch.shared->esr;
+#endif
+}
+
+static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_GESR, esr);
+#else
+ vcpu->arch.shared->esr = esr;
+#endif
+}
+
/* Deliver the interrupt of the corresponding priority, if possible. */
static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
unsigned int priority)
@@ -208,6 +288,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
bool crit;
bool keep_irq = false;
+ enum int_class int_class;
/* Truncate crit indicators in 32 bit mode */
if (!(vcpu->arch.shared->msr & MSR_SF)) {
@@ -243,16 +324,20 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
case BOOKE_IRQPRIO_AP_UNAVAIL:
case BOOKE_IRQPRIO_ALIGNMENT:
allowed = 1;
- msr_mask = MSR_CE|MSR_ME|MSR_DE;
+ msr_mask = MSR_GS | MSR_CE | MSR_ME | MSR_DE;
+ int_class = INT_CLASS_NONCRIT;
break;
case BOOKE_IRQPRIO_CRITICAL:
- case BOOKE_IRQPRIO_WATCHDOG:
allowed = vcpu->arch.shared->msr & MSR_CE;
- msr_mask = MSR_ME;
+ allowed = allowed && !crit;
+ msr_mask = MSR_GS | MSR_ME;
+ int_class = INT_CLASS_CRIT;
break;
case BOOKE_IRQPRIO_MACHINE_CHECK:
allowed = vcpu->arch.shared->msr & MSR_ME;
- msr_mask = 0;
+ allowed = allowed && !crit;
+ msr_mask = MSR_GS;
+ int_class = INT_CLASS_MC;
break;
case BOOKE_IRQPRIO_DECREMENTER:
case BOOKE_IRQPRIO_FIT:
@@ -261,29 +346,63 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
case BOOKE_IRQPRIO_EXTERNAL:
allowed = vcpu->arch.shared->msr & MSR_EE;
allowed = allowed && !crit;
- msr_mask = MSR_CE|MSR_ME|MSR_DE;
+ msr_mask = MSR_GS | MSR_CE | MSR_ME | MSR_DE;
+ int_class = INT_CLASS_NONCRIT;
break;
case BOOKE_IRQPRIO_DEBUG:
allowed = vcpu->arch.shared->msr & MSR_DE;
- msr_mask = MSR_ME;
+ allowed = allowed && !crit;
+ msr_mask = MSR_GS | MSR_ME;
+ int_class = INT_CLASS_CRIT;
break;
}
if (allowed) {
- vcpu->arch.shared->srr0 = vcpu->arch.regs.nip;
- vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
+ switch (int_class) {
+ case INT_CLASS_NONCRIT:
+ set_guest_srr(vcpu, vcpu->arch.regs.nip,
+ vcpu->arch.shared->msr);
+ break;
+ case INT_CLASS_CRIT:
+ set_guest_csrr(vcpu, vcpu->arch.regs.nip,
+ vcpu->arch.shared->msr);
+ break;
+ case INT_CLASS_DBG:
+ set_guest_dsrr(vcpu, vcpu->arch.regs.nip,
+ vcpu->arch.shared->msr);
+ break;
+ case INT_CLASS_MC:
+ set_guest_mcsrr(vcpu, vcpu->arch.regs.nip,
+ vcpu->arch.shared->msr);
+ break;
+ }
+
vcpu->arch.regs.nip = vcpu->arch.ivpr |
vcpu->arch.ivor[priority];
if (update_esr == true)
- vcpu->arch.shared->esr = vcpu->arch.queued_esr;
+ set_guest_esr(vcpu, vcpu->arch.queued_esr);
if (update_dear == true)
- vcpu->arch.shared->dar = vcpu->arch.queued_dear;
+ set_guest_dear(vcpu, vcpu->arch.queued_dear);
kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
if (!keep_irq)
clear_bit(priority, &vcpu->arch.pending_exceptions);
}
+#ifdef CONFIG_KVM_BOOKE_HV
+ /*
+ * If an interrupt is pending but masked, raise a guest doorbell
+ * so that we are notified when the guest enables the relevant
+ * MSR bit.
+ */
+ if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_EE)
+ kvmppc_set_pending_interrupt(vcpu, INT_CLASS_NONCRIT);
+ if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_CE)
+ kvmppc_set_pending_interrupt(vcpu, INT_CLASS_CRIT);
+ if (vcpu->arch.pending_exceptions & BOOKE_IRQPRIO_MACHINE_CHECK)
+ kvmppc_set_pending_interrupt(vcpu, INT_CLASS_MC);
+#endif
+
return allowed;
}
@@ -347,6 +466,11 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
return -EINVAL;
}
+ if (!current->thread.kvm_vcpu) {
+ WARN(1, "no vcpu\n");
+ return -EPERM;
+ }
+
local_irq_disable();
kvmppc_core_prepare_to_enter(vcpu);
@@ -366,6 +490,38 @@ out:
return ret;
}
+static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+ enum emulation_result er;
+
+ er = kvmppc_emulate_instruction(run, vcpu);
+ switch (er) {
+ case EMULATE_DONE:
+ /* don't overwrite subtypes, just account kvm_stats */
+ kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
+ /* Future optimization: only reload non-volatiles if
+ * they were actually modified by emulation. */
+ return RESUME_GUEST_NV;
+
+ case EMULATE_DO_DCR:
+ run->exit_reason = KVM_EXIT_DCR;
+ return RESUME_HOST;
+
+ case EMULATE_FAIL:
+ /* XXX Deliver Program interrupt to guest. */
+ printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
+ __func__, vcpu->arch.regs.nip, vcpu->arch.last_inst);
+ /* For debugging, encode the failing instruction and
+ * report it to userspace. */
+ run->hw.hardware_exit_reason = ~0ULL << 32;
+ run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
+ return RESUME_HOST;
+
+ default:
+ BUG();
+ }
+}
+
/**
* kvmppc_handle_exit
*
@@ -374,12 +530,39 @@ out:
int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int exit_nr)
{
- enum emulation_result er;
int r = RESUME_HOST;
/* update before a new last_exit_type is rewritten */
kvmppc_update_timing_stats(vcpu);
+ /*
+ * If we actually care, we could copy MSR, DEAR, and ESR to regs,
+ * insert an appropriate trap number, etc.
+ *
+ * Seems like a waste of cycles for something that should only matter
+ * to someone using sysrq-t/p or similar host kernel debug facility.
+ * We have other debug facilities to get that information from a
+ * guest through userspace.
+ */
+ switch (exit_nr) {
+ case BOOKE_INTERRUPT_EXTERNAL:
+ do_IRQ(&vcpu->arch.regs);
+ break;
+
+ case BOOKE_INTERRUPT_DECREMENTER:
+ timer_interrupt(&vcpu->arch.regs);
+ break;
+
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3E_64)
+ case BOOKE_INTERRUPT_DOORBELL:
+ doorbell_exception(&vcpu->arch.regs);
+ break;
+#endif
+ case BOOKE_INTERRUPT_MACHINE_CHECK:
+ /* FIXME */
+ break;
+ }
+
local_irq_enable();
run->exit_reason = KVM_EXIT_UNKNOWN;
@@ -387,30 +570,56 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
switch (exit_nr) {
case BOOKE_INTERRUPT_MACHINE_CHECK:
- printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
- kvmppc_dump_vcpu(vcpu);
- r = RESUME_HOST;
+ kvm_resched(vcpu);
+ r = RESUME_GUEST;
break;
case BOOKE_INTERRUPT_EXTERNAL:
kvmppc_account_exit(vcpu, EXT_INTR_EXITS);
- if (need_resched())
- cond_resched();
+ kvm_resched(vcpu);
r = RESUME_GUEST;
break;
case BOOKE_INTERRUPT_DECREMENTER:
- /* Since we switched IVPR back to the host's value, the host
- * handled this interrupt the moment we enabled interrupts.
- * Now we just offer it a chance to reschedule the guest. */
kvmppc_account_exit(vcpu, DEC_EXITS);
- if (need_resched())
- cond_resched();
+ kvm_resched(vcpu);
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_DOORBELL:
+ kvmppc_account_exit(vcpu, DBELL_EXITS);
+ kvm_resched(vcpu);
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_GUEST_DBELL_CRIT:
+ kvmppc_account_exit(vcpu, GDBELL_EXITS);
+
+ /*
+ * We are here because there is a pending guest interrupt
+ * which could not be delivered as MSR_CE or MSR_ME was not
+ * set. Once we break from here we will retry delivery.
+ */
r = RESUME_GUEST;
break;
+ case BOOKE_INTERRUPT_GUEST_DBELL:
+ kvmppc_account_exit(vcpu, GDBELL_EXITS);
+
+ /*
+ * We are here because there is a pending guest interrupt
+ * which could not be delivered as MSR_EE was not set. Once
+ * we break from here we will retry delivery.
+ */
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_HV_PRIV:
+ r = emulation_exit(run, vcpu);
+ break;
+
case BOOKE_INTERRUPT_PROGRAM:
- if (vcpu->arch.shared->msr & MSR_PR) {
+ if (vcpu->arch.shared->msr & (MSR_PR | MSR_GS)) {
/* Program traps generated by user-level software must be handled
* by the guest kernel. */
kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
@@ -419,33 +628,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
}
- er = kvmppc_emulate_instruction(run, vcpu);
- switch (er) {
- case EMULATE_DONE:
- /* don't overwrite subtypes, just account kvm_stats */
- kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
- /* Future optimization: only reload non-volatiles if
- * they were actually modified by emulation. */
- r = RESUME_GUEST_NV;
- break;
- case EMULATE_DO_DCR:
- run->exit_reason = KVM_EXIT_DCR;
- r = RESUME_HOST;
- break;
- case EMULATE_FAIL:
- /* XXX Deliver Program interrupt to guest. */
- printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
- __func__, vcpu->arch.regs.nip,
- vcpu->arch.last_inst);
- /* For debugging, encode the failing instruction and
- * report it to userspace. */
- run->hw.hardware_exit_reason = ~0ULL << 32;
- run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
- r = RESUME_HOST;
- break;
- default:
- BUG();
- }
+ r = emulation_exit(run, vcpu);
break;
case BOOKE_INTERRUPT_FP_UNAVAIL:
@@ -510,6 +693,21 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
r = RESUME_GUEST;
break;
+#ifdef CONFIG_KVM_BOOKE_HV
+ case BOOKE_INTERRUPT_HV_SYSCALL:
+ if (!(vcpu->arch.shared->msr & MSR_PR)) {
+ kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+ } else {
+ /*
+ * hcall from guest userspace -- send privileged
+ * instruction program check.
+ */
+ kvmppc_core_queue_program(vcpu, ESR_PPR);
+ }
+
+ r = RESUME_GUEST;
+ break;
+#else
case BOOKE_INTERRUPT_SYSCALL:
if (!(vcpu->arch.shared->msr & MSR_PR) &&
(((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
@@ -523,6 +721,47 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
kvmppc_account_exit(vcpu, SYSCALL_EXITS);
r = RESUME_GUEST;
break;
+#endif
+
+ case BOOKE_INTERRUPT_ITLB_MISS: {
+ unsigned long eaddr = vcpu->arch.regs.nip;
+ gpa_t gpaddr;
+ gfn_t gfn;
+ int gtlb_index;
+
+ r = RESUME_GUEST;
+
+ /* Check the guest TLB. */
+ gtlb_index = kvmppc_mmu_itlb_index(vcpu, eaddr);
+ if (gtlb_index < 0) {
+ /* The guest didn't have a mapping for it. */
+ kvmppc_booke_queue_irqprio(vcpu,
+ BOOKE_IRQPRIO_ITLB_MISS);
+ kvmppc_mmu_itlb_miss(vcpu);
+ kvmppc_account_exit(vcpu, ITLB_REAL_MISS_EXITS);
+ break;
+ }
+
+ kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
+
+ gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
+ gfn = gpaddr >> PAGE_SHIFT;
+
+ if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+ /* The guest TLB had a mapping, but the shadow TLB
+ * didn't. This could be because:
+ * a) the entry is mapping the host kernel, or
+ * b) the guest used a large mapping which we're faking
+ * Either way, we need to satisfy the fault without
+ * invoking the guest. */
+ kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
+ } else {
+ /* Guest mapped and leaped at non-RAM! */
+ kvmppc_booke_queue_irqprio(vcpu,
+ BOOKE_IRQPRIO_MACHINE_CHECK);
+ }
+ break;
+ }
case BOOKE_INTERRUPT_DTLB_MISS: {
unsigned long eaddr = vcpu->arch.fault_dear;
@@ -578,45 +817,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
break;
}
- case BOOKE_INTERRUPT_ITLB_MISS: {
- unsigned long eaddr = vcpu->arch.regs.nip;
- gpa_t gpaddr;
- gfn_t gfn;
- int gtlb_index;
-
- r = RESUME_GUEST;
-
- /* Check the guest TLB. */
- gtlb_index = kvmppc_mmu_itlb_index(vcpu, eaddr);
- if (gtlb_index < 0) {
- /* The guest didn't have a mapping for it. */
- kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ITLB_MISS);
- kvmppc_mmu_itlb_miss(vcpu);
- kvmppc_account_exit(vcpu, ITLB_REAL_MISS_EXITS);
- break;
- }
-
- kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
-
- gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
- gfn = gpaddr >> PAGE_SHIFT;
-
- if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
- /* The guest TLB had a mapping, but the shadow TLB
- * didn't. This could be because:
- * a) the entry is mapping the host kernel, or
- * b) the guest used a large mapping which we're faking
- * Either way, we need to satisfy the fault without
- * invoking the guest. */
- kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
- } else {
- /* Guest mapped and leaped at non-RAM! */
- kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_MACHINE_CHECK);
- }
-
- break;
- }
-
case BOOKE_INTERRUPT_DEBUG: {
u32 dbsr;
@@ -663,12 +863,15 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
int r;
vcpu->arch.regs.nip = 0;
- vcpu->arch.shared->msr = 0;
- vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
vcpu->arch.shared->pir = vcpu->vcpu_id;
kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
+ kvmppc_set_msr(vcpu, 0);
+#ifndef CONFIG_KVM_BOOKE_HV
+ vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
vcpu->arch.shadow_pid = 1;
+ vcpu->arch.shared->msr = 0;
+#endif
/* Eye-catching numbers so we know if the guest takes an interrupt
* before it's programmed its own IVPR/IVORs. */
@@ -749,8 +952,8 @@ static void get_sregs_base(struct kvm_vcpu *vcpu,
sregs->u.e.csrr0 = vcpu->arch.csrr0;
sregs->u.e.csrr1 = vcpu->arch.csrr1;
sregs->u.e.mcsr = vcpu->arch.mcsr;
- sregs->u.e.esr = vcpu->arch.shared->esr;
- sregs->u.e.dear = vcpu->arch.shared->dar;
+ sregs->u.e.esr = get_guest_esr(vcpu);
+ sregs->u.e.dear = get_guest_dear(vcpu);
sregs->u.e.tsr = vcpu->arch.tsr;
sregs->u.e.tcr = vcpu->arch.tcr;
sregs->u.e.dec = kvmppc_get_dec(vcpu, tb);
@@ -767,8 +970,8 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
vcpu->arch.csrr0 = sregs->u.e.csrr0;
vcpu->arch.csrr1 = sregs->u.e.csrr1;
vcpu->arch.mcsr = sregs->u.e.mcsr;
- vcpu->arch.shared->esr = sregs->u.e.esr;
- vcpu->arch.shared->dar = sregs->u.e.dear;
+ set_guest_esr(vcpu, sregs->u.e.esr);
+ set_guest_dear(vcpu, sregs->u.e.dear);
vcpu->arch.vrsave = sregs->u.e.vrsave;
kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
@@ -965,14 +1168,17 @@ void kvmppc_decrementer_func(unsigned long data)
void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
+ current->thread.kvm_vcpu = vcpu;
}
void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
{
+ current->thread.kvm_vcpu = NULL;
}
int __init kvmppc_booke_init(void)
{
+#ifndef CONFIG_KVM_BOOKE_HV
unsigned long ivor[16];
unsigned long max_ivor = 0;
int i;
@@ -1015,7 +1221,7 @@ int __init kvmppc_booke_init(void)
}
flush_icache_range(kvmppc_booke_handlers,
kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
-
+#endif /* !BOOKE_HV */
return 0;
}
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 05d1d99..d53bcf2 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -48,7 +48,20 @@
#define BOOKE_IRQPRIO_PERFORMANCE_MONITOR 19
/* Internal pseudo-irqprio for level triggered externals */
#define BOOKE_IRQPRIO_EXTERNAL_LEVEL 20
-#define BOOKE_IRQPRIO_MAX 20
+#define BOOKE_IRQPRIO_DBELL 21
+#define BOOKE_IRQPRIO_DBELL_CRIT 22
+#define BOOKE_IRQPRIO_MAX 23
+
+#define BOOKE_IRQMASK_EE ((1 << BOOKE_IRQPRIO_EXTERNAL_LEVEL) | \
+ (1 << BOOKE_IRQPRIO_PERFORMANCE_MONITOR) | \
+ (1 << BOOKE_IRQPRIO_DBELL) | \
+ (1 << BOOKE_IRQPRIO_DECREMENTER) | \
+ (1 << BOOKE_IRQPRIO_FIT) | \
+ (1 << BOOKE_IRQPRIO_EXTERNAL))
+
+#define BOOKE_IRQMASK_CE ((1 << BOOKE_IRQPRIO_DBELL_CRIT) | \
+ (1 << BOOKE_IRQPRIO_WATCHDOG) | \
+ (1 << BOOKE_IRQPRIO_CRITICAL))
extern unsigned long kvmppc_booke_handlers;
@@ -74,4 +87,13 @@ void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu);
void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu);
+enum int_class {
+ INT_CLASS_NONCRIT,
+ INT_CLASS_CRIT,
+ INT_CLASS_MC,
+ INT_CLASS_DBG,
+};
+
+void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type);
+
#endif /* __KVM_BOOKE_H__ */
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index a4af03b..3eb7fc6 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -99,6 +99,12 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
return emulated;
}
+/*
+ * NOTE: some of these registers are not emulated on BOOKE_HV (GS-mode).
+ * Their backing store is in real registers, and these functions
+ * will return the wrong result if called for them in another context
+ * (such as debugging).
+ */
int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
{
int emulated = EMULATE_DONE;
@@ -122,9 +128,11 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
kvmppc_set_tcr(vcpu, spr_val);
break;
- /* Note: SPRG4-7 are user-readable. These values are
- * loaded into the real SPRGs when resuming the
- * guest. */
+ /*
+ * Note: SPRG4-7 are user-readable.
+ * These values are loaded into the real SPRGs when resuming the
+ * guest (PR-mode only).
+ */
case SPRN_SPRG4:
vcpu->arch.shared->sprg4 = spr_val; break;
case SPRN_SPRG5:
@@ -136,6 +144,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
case SPRN_IVPR:
vcpu->arch.ivpr = spr_val;
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_GIVPR, spr_val);
+#endif
break;
case SPRN_IVOR0:
vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = spr_val;
@@ -145,6 +156,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
break;
case SPRN_IVOR2:
vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = spr_val;
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_GIVOR2, spr_val);
+#endif
break;
case SPRN_IVOR3:
vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = spr_val;
@@ -163,6 +177,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
break;
case SPRN_IVOR8:
vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = spr_val;
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_GIVOR8, spr_val);
+#endif
break;
case SPRN_IVOR9:
vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = spr_val;
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
new file mode 100644
index 0000000..9eaeebd
--- /dev/null
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -0,0 +1,587 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
+ *
+ * Author: Varun Sethi <varun.sethi@freescale.com>
+ * Author: Scott Wood <scotwood@freescale.com>
+ *
+ * This file is derived from arch/powerpc/kvm/booke_interrupts.S
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/mmu-44x.h>
+#include <asm/page.h>
+#include <asm/asm-compat.h>
+#include <asm/asm-offsets.h>
+#include <asm/bitsperlong.h>
+
+#include "../kernel/head_booke.h" /* for THREAD_NORMSAVE() */
+
+#define GET_VCPU(vcpu, thread) \
+ PPC_LL vcpu, THREAD_KVM_VCPU(thread)
+
+#define SET_VCPU(vcpu) \
+ PPC_STL vcpu, (THREAD + THREAD_KVM_VCPU)(r2)
+
+#define LONGBYTES (BITS_PER_LONG / 8)
+
+#define VCPU_GPR(n) (VCPU_GPRS + (n * LONGBYTES))
+#define VCPU_GUEST_SPRG(n) (VCPU_GUEST_SPRGS + (n * LONGBYTES))
+
+/* The host stack layout: */
+#define HOST_R1 (0 * LONGBYTES) /* Implied by stwu. */
+#define HOST_CALLEE_LR (1 * LONGBYTES)
+#define HOST_RUN (2 * LONGBYTES) /* struct kvm_run */
+/*
+ * r2 is special: it holds 'current', and it made nonvolatile in the
+ * kernel with the -ffixed-r2 gcc option.
+ */
+#define HOST_R2 (3 * LONGBYTES)
+#define HOST_NV_GPRS (4 * LONGBYTES)
+#define HOST_NV_GPR(n) (HOST_NV_GPRS + ((n - 14) * LONGBYTES))
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + LONGBYTES)
+#define HOST_STACK_SIZE ((HOST_MIN_STACK_SIZE + 15) & ~15) /* Align. */
+#define HOST_STACK_LR (HOST_STACK_SIZE + LONGBYTES) /* In caller stack frame. */
+
+#define NEED_EMU 0x00000001 /* emulation -- save nv regs */
+#define NEED_DEAR 0x00000002 /* save faulting DEAR */
+#define NEED_ESR 0x00000004 /* save faulting ESR */
+
+/*
+ * On entry:
+ * r4 = vcpu, r5 = srr0, r6 = srr1
+ * saved in vcpu: cr, ctr, r3-r13
+ */
+.macro kvm_handler_common intno, srr0, flags
+ mfspr r10, SPRN_PID
+ lwz r8, VCPU_HOST_PID(r4)
+ PPC_LL r11, VCPU_SHARED(r4)
+ PPC_STL r14, VCPU_GPR(r14)(r4) /* We need a non-volatile GPR. */
+ li r14, \intno
+
+ stw r10, VCPU_GUEST_PID(r4)
+ mtspr SPRN_PID, r8
+
+ .if \flags & NEED_EMU
+ lwz r9, VCPU_KVM(r4)
+ .endif
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+ /* save exit time */
+1: mfspr r7, SPRN_TBRU
+ mfspr r8, SPRN_TBRL
+ mfspr r9, SPRN_TBRU
+ cmpw r9, r7
+ PPC_STL r8, VCPU_TIMING_EXIT_TBL(r4)
+ bne- 1b
+ PPC_STL r9, VCPU_TIMING_EXIT_TBU(r4)
+#endif
+
+ oris r8, r6, MSR_CE@h
+#ifndef CONFIG_64BIT
+ stw r6, (VCPU_SHARED_MSR + 4)(r11)
+#else
+ std r6, (VCPU_SHARED_MSR)(r11)
+#endif
+ ori r8, r8, MSR_ME | MSR_RI
+ PPC_STL r5, VCPU_PC(r4)
+
+ /*
+ * Make sure CE/ME/RI are set (if appropriate for exception type)
+ * whether or not the guest had it set. Since mfmsr/mtmsr are
+ * somewhat expensive, skip in the common case where the guest
+ * had all these bits set (and thus they're still set if
+ * appropriate for the exception type).
+ */
+ cmpw r6, r8
+ .if \flags & NEED_EMU
+ lwz r9, KVM_LPID(r9)
+ .endif
+ beq 1f
+ mfmsr r7
+ .if \srr0 != SPRN_MCSRR0 && \srr0 != SPRN_CSRR0
+ oris r7, r7, MSR_CE@h
+ .endif
+ .if \srr0 != SPRN_MCSRR0
+ ori r7, r7, MSR_ME | MSR_RI
+ .endif
+ mtmsr r7
+1:
+
+ .if \flags & NEED_EMU
+ /*
+ * This assumes you have external PID support.
+ * To support a bookehv CPU without external PID, you'll
+ * need to look up the TLB entry and create a temporary mapping.
+ *
+ * FIXME: we don't currently handle if the lwepx faults. PR-mode
+ * booke doesn't handle it either. Since Linux doesn't use
+ * broadcast tlbivax anymore, the only way this should happen is
+ * if the guest maps its memory execute-but-not-read, or if we
+ * somehow take a TLB miss in the middle of this entry code and
+ * evict the relevant entry. On e500mc, all kernel lowmem is
+ * bolted into TLB1 large page mappings, and we don't use
+ * broadcast invalidates, so we should not take a TLB miss here.
+ *
+ * Later we'll need to deal with faults here. Disallowing guest
+ * mappings that are execute-but-not-read could be an option on
+ * e500mc, but not on chips with an LRAT if it is used.
+ */
+
+ mfspr r3, SPRN_EPLC /* will already have correct ELPID and EGS */
+ PPC_STL r15, VCPU_GPR(r15)(r4)
+ PPC_STL r16, VCPU_GPR(r16)(r4)
+ PPC_STL r17, VCPU_GPR(r17)(r4)
+ PPC_STL r18, VCPU_GPR(r18)(r4)
+ PPC_STL r19, VCPU_GPR(r19)(r4)
+ mr r8, r3
+ PPC_STL r20, VCPU_GPR(r20)(r4)
+ rlwimi r8, r6, EPC_EAS_SHIFT - MSR_IR_LG, EPC_EAS
+ PPC_STL r21, VCPU_GPR(r21)(r4)
+ rlwimi r8, r6, EPC_EPR_SHIFT - MSR_PR_LG, EPC_EPR
+ PPC_STL r22, VCPU_GPR(r22)(r4)
+ rlwimi r8, r10, EPC_EPID_SHIFT, EPC_EPID
+ PPC_STL r23, VCPU_GPR(r23)(r4)
+ PPC_STL r24, VCPU_GPR(r24)(r4)
+ PPC_STL r25, VCPU_GPR(r25)(r4)
+ PPC_STL r26, VCPU_GPR(r26)(r4)
+ PPC_STL r27, VCPU_GPR(r27)(r4)
+ PPC_STL r28, VCPU_GPR(r28)(r4)
+ PPC_STL r29, VCPU_GPR(r29)(r4)
+ PPC_STL r30, VCPU_GPR(r30)(r4)
+ PPC_STL r31, VCPU_GPR(r31)(r4)
+ mtspr SPRN_EPLC, r8
+ isync
+ lwepx r9, 0, r5
+ mtspr SPRN_EPLC, r3
+ stw r9, VCPU_LAST_INST(r4)
+ .endif
+
+ .if \flags & NEED_ESR
+ mfspr r8, SPRN_ESR
+ PPC_STL r8, VCPU_FAULT_ESR(r4)
+ .endif
+
+ .if \flags & NEED_DEAR
+ mfspr r9, SPRN_DEAR
+ PPC_STL r9, VCPU_FAULT_DEAR(r4)
+ .endif
+
+ b kvmppc_resume_host
+.endm
+
+/*
+ * For input register values, see arch/powerpc/include/asm/kvm_booke_hv_asm.h
+ */
+.macro kvm_handler intno srr0, srr1, flags
+_GLOBAL(kvmppc_handler_\intno\()_\srr1)
+ GET_VCPU(r11, r10)
+ PPC_STL r3, VCPU_GPR(r3)(r11)
+ mfspr r3, SPRN_SPRG_RSCRATCH0
+ PPC_STL r4, VCPU_GPR(r4)(r11)
+ PPC_LL r4, THREAD_NORMSAVE(0)(r10)
+ PPC_STL r5, VCPU_GPR(r5)(r11)
+ PPC_STL r13, VCPU_CR(r11)
+ mfspr r5, \srr0
+ PPC_STL r3, VCPU_GPR(r10)(r11)
+ PPC_LL r3, THREAD_NORMSAVE(2)(r10)
+ PPC_STL r6, VCPU_GPR(r6)(r11)
+ PPC_STL r4, VCPU_GPR(r11)(r11)
+ mfspr r6, \srr1
+ PPC_STL r7, VCPU_GPR(r7)(r11)
+ PPC_STL r8, VCPU_GPR(r8)(r11)
+ PPC_STL r9, VCPU_GPR(r9)(r11)
+ PPC_STL r3, VCPU_GPR(r13)(r11)
+ mfctr r7
+ PPC_STL r12, VCPU_GPR(r12)(r11)
+ PPC_STL r7, VCPU_CTR(r11)
+ mr r4, r11
+ kvm_handler_common \intno, \srr0, \flags
+.endm
+
+.macro kvm_lvl_handler intno scratch srr0, srr1, flags
+_GLOBAL(kvmppc_handler_\intno\()_\srr1)
+ mfspr r10, SPRN_SPRG_THREAD
+ GET_VCPU(r11, r10)
+ PPC_STL r3, VCPU_GPR(r3)(r11)
+ mfspr r3, \scratch
+ PPC_STL r4, VCPU_GPR(r4)(r11)
+ PPC_LL r4, GPR9(r8)
+ PPC_STL r5, VCPU_GPR(r5)(r11)
+ PPC_STL r9, VCPU_CR(r11)
+ mfspr r5, \srr0
+ PPC_STL r3, VCPU_GPR(r8)(r11)
+ PPC_LL r3, GPR10(r8)
+ PPC_STL r6, VCPU_GPR(r6)(r11)
+ PPC_STL r4, VCPU_GPR(r9)(r11)
+ mfspr r6, \srr1
+ PPC_LL r4, GPR11(r8)
+ PPC_STL r7, VCPU_GPR(r7)(r11)
+ PPC_STL r8, VCPU_GPR(r8)(r11)
+ PPC_STL r3, VCPU_GPR(r10)(r11)
+ mfctr r7
+ PPC_STL r12, VCPU_GPR(r12)(r11)
+ PPC_STL r4, VCPU_GPR(r11)(r11)
+ PPC_STL r7, VCPU_CTR(r11)
+ mr r4, r11
+ kvm_handler_common \intno, \srr0, \flags
+.endm
+
+kvm_lvl_handler BOOKE_INTERRUPT_CRITICAL, \
+ SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \
+ SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \
+ SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR)
+kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR
+kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \
+ SPRN_SRR0, SPRN_SRR1, (NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_PROGRAM, SPRN_SRR0, SPRN_SRR1, NEED_ESR
+kvm_handler BOOKE_INTERRUPT_FP_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SYSCALL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_AP_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DECREMENTER, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_FIT, SPRN_SRR0, SPRN_SRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_WATCHDOG, \
+ SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DTLB_MISS, \
+ SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_ITLB_MISS, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_FP_DATA, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_FP_ROUND, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_PERFORMANCE_MONITOR, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DOORBELL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_DOORBELL_CRITICAL, \
+ SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_HV_PRIV, SPRN_SRR0, SPRN_SRR1, NEED_EMU
+kvm_handler BOOKE_INTERRUPT_HV_SYSCALL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_GUEST_DBELL, SPRN_GSRR0, SPRN_GSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_GUEST_DBELL_CRIT, \
+ SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
+ SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
+ SPRN_SPRG_RSCRATCH_DBG, SPRN_DSRR0, SPRN_DSRR1, 0
+
+
+/* Registers:
+ * SPRG_SCRATCH0: guest r10
+ * r4: vcpu pointer
+ * r11: vcpu->arch.shared
+ * r14: KVM exit number
+ */
+_GLOBAL(kvmppc_resume_host)
+ /* Save remaining volatile guest register state to vcpu. */
+ mfspr r3, SPRN_VRSAVE
+ PPC_STL r0, VCPU_GPR(r0)(r4)
+ PPC_STL r1, VCPU_GPR(r1)(r4)
+ mflr r5
+ mfspr r6, SPRN_SPRG4
+ PPC_STL r2, VCPU_GPR(r2)(r4)
+ PPC_STL r5, VCPU_LR(r4)
+ mfspr r7, SPRN_SPRG5
+ PPC_STL r3, VCPU_VRSAVE(r4)
+ PPC_STL r6, VCPU_SHARED_SPRG4(r11)
+ mfspr r8, SPRN_SPRG6
+ PPC_STL r7, VCPU_SHARED_SPRG5(r11)
+ mfspr r9, SPRN_SPRG7
+ PPC_STL r8, VCPU_SHARED_SPRG6(r11)
+ mfxer r3
+ PPC_STL r9, VCPU_SHARED_SPRG7(r11)
+
+ /* save guest MAS registers and restore host mas4 & mas6 */
+ mfspr r5, SPRN_MAS0
+ PPC_STL r3, VCPU_XER(r4)
+ mfspr r6, SPRN_MAS1
+ stw r5, VCPU_SHARED_MAS0(r11)
+ mfspr r7, SPRN_MAS2
+ stw r6, VCPU_SHARED_MAS1(r11)
+#ifndef CONFIG_64BIT
+ stw r7, (VCPU_SHARED_MAS2 + 4)(r11)
+#else
+ std r7, (VCPU_SHARED_MAS2)(r11)
+#endif
+ mfspr r5, SPRN_MAS3
+ mfspr r6, SPRN_MAS4
+ stw r5, VCPU_SHARED_MAS7_3+4(r11)
+ mfspr r7, SPRN_MAS6
+ stw r6, VCPU_SHARED_MAS4(r11)
+ mfspr r5, SPRN_MAS7
+ lwz r6, VCPU_HOST_MAS4(r4)
+ stw r7, VCPU_SHARED_MAS6(r11)
+ lwz r8, VCPU_HOST_MAS6(r4)
+ mtspr SPRN_MAS4, r6
+ stw r5, VCPU_SHARED_MAS7_3+0(r11)
+ mtspr SPRN_MAS6, r8
+ mfspr r3, SPRN_EPCR
+ rlwinm r3, r3, 0, ~SPRN_EPCR_DMIUH
+ mtspr SPRN_EPCR, r3
+ isync
+
+ /* Restore host stack pointer */
+ PPC_LL r1, VCPU_HOST_STACK(r4)
+ PPC_LL r2, HOST_R2(r1)
+
+ /* Switch to kernel stack and jump to handler. */
+ PPC_LL r3, HOST_RUN(r1)
+ mr r5, r14 /* intno */
+ mr r14, r4 /* Save vcpu pointer. */
+ bl kvmppc_handle_exit
+
+ /* Restore vcpu pointer and the nonvolatiles we used. */
+ mr r4, r14
+ PPC_LL r14, VCPU_GPR(r14)(r4)
+
+ andi. r5, r3, RESUME_FLAG_NV
+ beq skip_nv_load
+ PPC_LL r15, VCPU_GPR(r15)(r4)
+ PPC_LL r16, VCPU_GPR(r16)(r4)
+ PPC_LL r17, VCPU_GPR(r17)(r4)
+ PPC_LL r18, VCPU_GPR(r18)(r4)
+ PPC_LL r19, VCPU_GPR(r19)(r4)
+ PPC_LL r20, VCPU_GPR(r20)(r4)
+ PPC_LL r21, VCPU_GPR(r21)(r4)
+ PPC_LL r22, VCPU_GPR(r22)(r4)
+ PPC_LL r23, VCPU_GPR(r23)(r4)
+ PPC_LL r24, VCPU_GPR(r24)(r4)
+ PPC_LL r25, VCPU_GPR(r25)(r4)
+ PPC_LL r26, VCPU_GPR(r26)(r4)
+ PPC_LL r27, VCPU_GPR(r27)(r4)
+ PPC_LL r28, VCPU_GPR(r28)(r4)
+ PPC_LL r29, VCPU_GPR(r29)(r4)
+ PPC_LL r30, VCPU_GPR(r30)(r4)
+ PPC_LL r31, VCPU_GPR(r31)(r4)
+skip_nv_load:
+ /* Should we return to the guest? */
+ andi. r5, r3, RESUME_FLAG_HOST
+ beq lightweight_exit
+
+ srawi r3, r3, 2 /* Shift -ERR back down. */
+
+heavyweight_exit:
+ /* Not returning to guest. */
+ PPC_LL r5, HOST_STACK_LR(r1)
+
+ /*
+ * We already saved guest volatile register state; now save the
+ * non-volatiles.
+ */
+
+ PPC_STL r15, VCPU_GPR(r15)(r4)
+ PPC_STL r16, VCPU_GPR(r16)(r4)
+ PPC_STL r17, VCPU_GPR(r17)(r4)
+ PPC_STL r18, VCPU_GPR(r18)(r4)
+ PPC_STL r19, VCPU_GPR(r19)(r4)
+ PPC_STL r20, VCPU_GPR(r20)(r4)
+ PPC_STL r21, VCPU_GPR(r21)(r4)
+ PPC_STL r22, VCPU_GPR(r22)(r4)
+ PPC_STL r23, VCPU_GPR(r23)(r4)
+ PPC_STL r24, VCPU_GPR(r24)(r4)
+ PPC_STL r25, VCPU_GPR(r25)(r4)
+ PPC_STL r26, VCPU_GPR(r26)(r4)
+ PPC_STL r27, VCPU_GPR(r27)(r4)
+ PPC_STL r28, VCPU_GPR(r28)(r4)
+ PPC_STL r29, VCPU_GPR(r29)(r4)
+ PPC_STL r30, VCPU_GPR(r30)(r4)
+ PPC_STL r31, VCPU_GPR(r31)(r4)
+
+ /* Load host non-volatile register state from host stack. */
+ PPC_LL r14, HOST_NV_GPR(r14)(r1)
+ PPC_LL r15, HOST_NV_GPR(r15)(r1)
+ PPC_LL r16, HOST_NV_GPR(r16)(r1)
+ PPC_LL r17, HOST_NV_GPR(r17)(r1)
+ PPC_LL r18, HOST_NV_GPR(r18)(r1)
+ PPC_LL r19, HOST_NV_GPR(r19)(r1)
+ PPC_LL r20, HOST_NV_GPR(r20)(r1)
+ PPC_LL r21, HOST_NV_GPR(r21)(r1)
+ PPC_LL r22, HOST_NV_GPR(r22)(r1)
+ PPC_LL r23, HOST_NV_GPR(r23)(r1)
+ PPC_LL r24, HOST_NV_GPR(r24)(r1)
+ PPC_LL r25, HOST_NV_GPR(r25)(r1)
+ PPC_LL r26, HOST_NV_GPR(r26)(r1)
+ PPC_LL r27, HOST_NV_GPR(r27)(r1)
+ PPC_LL r28, HOST_NV_GPR(r28)(r1)
+ PPC_LL r29, HOST_NV_GPR(r29)(r1)
+ PPC_LL r30, HOST_NV_GPR(r30)(r1)
+ PPC_LL r31, HOST_NV_GPR(r31)(r1)
+
+ /* Return to kvm_vcpu_run(). */
+ mtlr r5
+ addi r1, r1, HOST_STACK_SIZE
+ /* r3 still contains the return code from kvmppc_handle_exit(). */
+ blr
+
+/* Registers:
+ * r3: kvm_run pointer
+ * r4: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcpu_run)
+ stwu r1, -HOST_STACK_SIZE(r1)
+ PPC_STL r1, VCPU_HOST_STACK(r4) /* Save stack pointer to vcpu. */
+
+ /* Save host state to stack. */
+ PPC_STL r3, HOST_RUN(r1)
+ mflr r3
+ PPC_STL r3, HOST_STACK_LR(r1)
+
+ /* Save host non-volatile register state to stack. */
+ PPC_STL r14, HOST_NV_GPR(r14)(r1)
+ PPC_STL r15, HOST_NV_GPR(r15)(r1)
+ PPC_STL r16, HOST_NV_GPR(r16)(r1)
+ PPC_STL r17, HOST_NV_GPR(r17)(r1)
+ PPC_STL r18, HOST_NV_GPR(r18)(r1)
+ PPC_STL r19, HOST_NV_GPR(r19)(r1)
+ PPC_STL r20, HOST_NV_GPR(r20)(r1)
+ PPC_STL r21, HOST_NV_GPR(r21)(r1)
+ PPC_STL r22, HOST_NV_GPR(r22)(r1)
+ PPC_STL r23, HOST_NV_GPR(r23)(r1)
+ PPC_STL r24, HOST_NV_GPR(r24)(r1)
+ PPC_STL r25, HOST_NV_GPR(r25)(r1)
+ PPC_STL r26, HOST_NV_GPR(r26)(r1)
+ PPC_STL r27, HOST_NV_GPR(r27)(r1)
+ PPC_STL r28, HOST_NV_GPR(r28)(r1)
+ PPC_STL r29, HOST_NV_GPR(r29)(r1)
+ PPC_STL r30, HOST_NV_GPR(r30)(r1)
+ PPC_STL r31, HOST_NV_GPR(r31)(r1)
+
+ /* Load guest non-volatiles. */
+ PPC_LL r14, VCPU_GPR(r14)(r4)
+ PPC_LL r15, VCPU_GPR(r15)(r4)
+ PPC_LL r16, VCPU_GPR(r16)(r4)
+ PPC_LL r17, VCPU_GPR(r17)(r4)
+ PPC_LL r18, VCPU_GPR(r18)(r4)
+ PPC_LL r19, VCPU_GPR(r19)(r4)
+ PPC_LL r20, VCPU_GPR(r20)(r4)
+ PPC_LL r21, VCPU_GPR(r21)(r4)
+ PPC_LL r22, VCPU_GPR(r22)(r4)
+ PPC_LL r23, VCPU_GPR(r23)(r4)
+ PPC_LL r24, VCPU_GPR(r24)(r4)
+ PPC_LL r25, VCPU_GPR(r25)(r4)
+ PPC_LL r26, VCPU_GPR(r26)(r4)
+ PPC_LL r27, VCPU_GPR(r27)(r4)
+ PPC_LL r28, VCPU_GPR(r28)(r4)
+ PPC_LL r29, VCPU_GPR(r29)(r4)
+ PPC_LL r30, VCPU_GPR(r30)(r4)
+ PPC_LL r31, VCPU_GPR(r31)(r4)
+
+
+lightweight_exit:
+ PPC_STL r2, HOST_R2(r1)
+
+ mfspr r3, SPRN_PID
+ stw r3, VCPU_HOST_PID(r4)
+ lwz r3, VCPU_GUEST_PID(r4)
+ mtspr SPRN_PID, r3
+
+ /* Save vcpu pointer for the exception handlers
+ * must be done before loading guest r2.
+ */
+// SET_VCPU(r4)
+
+ PPC_LL r11, VCPU_SHARED(r4)
+ /* Save host mas4 and mas6 and load guest MAS registers */
+ mfspr r3, SPRN_MAS4
+ stw r3, VCPU_HOST_MAS4(r4)
+ mfspr r3, SPRN_MAS6
+ stw r3, VCPU_HOST_MAS6(r4)
+ lwz r3, VCPU_SHARED_MAS0(r11)
+ lwz r5, VCPU_SHARED_MAS1(r11)
+#ifndef CONFIG_64BIT
+ lwz r6, (VCPU_SHARED_MAS2 + 4)(r11)
+#else
+ ld r6, (VCPU_SHARED_MAS2)(r11)
+#endif
+ lwz r7, VCPU_SHARED_MAS7_3+4(r11)
+ lwz r8, VCPU_SHARED_MAS4(r11)
+ mtspr SPRN_MAS0, r3
+ mtspr SPRN_MAS1, r5
+ mtspr SPRN_MAS2, r6
+ mtspr SPRN_MAS3, r7
+ mtspr SPRN_MAS4, r8
+ lwz r3, VCPU_SHARED_MAS6(r11)
+ lwz r5, VCPU_SHARED_MAS7_3+0(r11)
+ mtspr SPRN_MAS6, r3
+ mtspr SPRN_MAS7, r5
+ /* Disable MAS register updates via exception */
+ mfspr r3, SPRN_EPCR
+ oris r3, r3, SPRN_EPCR_DMIUH@h
+ mtspr SPRN_EPCR, r3
+
+ /*
+ * Host interrupt handlers may have clobbered these guest-readable
+ * SPRGs, so we need to reload them here with the guest's values.
+ */
+ lwz r3, VCPU_VRSAVE(r4)
+ lwz r5, VCPU_SHARED_SPRG4(r11)
+ mtspr SPRN_VRSAVE, r3
+ lwz r6, VCPU_SHARED_SPRG5(r11)
+ mtspr SPRN_SPRG4W, r5
+ lwz r7, VCPU_SHARED_SPRG6(r11)
+ mtspr SPRN_SPRG5W, r6
+ lwz r8, VCPU_SHARED_SPRG7(r11)
+ mtspr SPRN_SPRG6W, r7
+ mtspr SPRN_SPRG7W, r8
+
+ /* Load some guest volatiles. */
+ PPC_LL r3, VCPU_LR(r4)
+ PPC_LL r5, VCPU_XER(r4)
+ PPC_LL r6, VCPU_CTR(r4)
+ PPC_LL r7, VCPU_CR(r4)
+ PPC_LL r8, VCPU_PC(r4)
+#ifndef CONFIG_64BIT
+ lwz r9, (VCPU_SHARED_MSR + 4)(r11)
+#else
+ ld r9, (VCPU_SHARED_MSR)(r11)
+#endif
+ PPC_LL r0, VCPU_GPR(r0)(r4)
+ PPC_LL r1, VCPU_GPR(r1)(r4)
+ PPC_LL r2, VCPU_GPR(r2)(r4)
+ PPC_LL r10, VCPU_GPR(r10)(r4)
+ PPC_LL r11, VCPU_GPR(r11)(r4)
+ PPC_LL r12, VCPU_GPR(r12)(r4)
+ PPC_LL r13, VCPU_GPR(r13)(r4)
+ mtlr r3
+ mtxer r5
+ mtctr r6
+ mtcr r7
+ mtsrr0 r8
+ mtsrr1 r9
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+ /* save enter time */
+1:
+ mfspr r6, SPRN_TBRU
+ mfspr r7, SPRN_TBRL
+ mfspr r8, SPRN_TBRU
+ cmpw r8, r6
+ PPC_STL r7, VCPU_TIMING_LAST_ENTER_TBL(r4)
+ bne 1b
+ PPC_STL r8, VCPU_TIMING_LAST_ENTER_TBU(r4)
+#endif
+
+ /* Finish loading guest volatiles and jump to guest. */
+ PPC_LL r5, VCPU_GPR(r5)(r4)
+ PPC_LL r6, VCPU_GPR(r6)(r4)
+ PPC_LL r7, VCPU_GPR(r7)(r4)
+ PPC_LL r8, VCPU_GPR(r8)(r4)
+ PPC_LL r9, VCPU_GPR(r9)(r4)
+
+ PPC_LL r3, VCPU_GPR(r3)(r4)
+ PPC_LL r4, VCPU_GPR(r4)(r4)
+ rfi
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 42701e5..f9c62dd 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -109,6 +109,11 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
goto out;
#endif
+#ifdef CONFIG_KVM_BOOKE_HV
+ if (!cpu_has_feature(CPU_FTR_EMB_HV))
+ goto out;
+#endif
+
r = true;
out:
diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
index 8167d42..bf191e7 100644
--- a/arch/powerpc/kvm/timing.h
+++ b/arch/powerpc/kvm/timing.h
@@ -93,6 +93,12 @@ static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
case SIGNAL_EXITS:
vcpu->stat.signal_exits++;
break;
+ case DBELL_EXITS:
+ vcpu->stat.dbell_exits++;
+ break;
+ case GDBELL_EXITS:
+ vcpu->stat.gdbell_exits++;
+ break;
}
}
--
1.7.7.rc3.4.g8d714
^ permalink raw reply related
* [RFC PATCH 16/16] KVM: PPC: e500mc support
From: Scott Wood @ 2011-12-21 1:34 UTC (permalink / raw)
To: agraf; +Cc: linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <20111221013340.GA8368@schlenkerla.am.freescale.net>
Add processor support for e500mc, using hardware virtualization support
(GS-mode).
Current issues include:
- No support for external proxy (coreint) interrupt mode in the guest.
Includes work by Ashish Kalra <Ashish.Kalra@freescale.com>,
Varun Sethi <Varun.Sethi@freescale.com>, and
Liu Yu <yu.liu@freescale.com>.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/include/asm/cputable.h | 6 +-
arch/powerpc/include/asm/kvm.h | 1 +
arch/powerpc/kernel/cpu_setup_fsl_booke.S | 1 +
arch/powerpc/kernel/head_fsl_booke.S | 46 ++++
arch/powerpc/kvm/Kconfig | 17 ++-
arch/powerpc/kvm/Makefile | 11 +
arch/powerpc/kvm/e500.h | 13 +-
arch/powerpc/kvm/e500_emulate.c | 24 ++-
arch/powerpc/kvm/e500_tlb.c | 21 ++-
arch/powerpc/kvm/e500mc.c | 342 +++++++++++++++++++++++++++++
arch/powerpc/kvm/powerpc.c | 6 +-
11 files changed, 476 insertions(+), 12 deletions(-)
create mode 100644 arch/powerpc/kvm/e500mc.c
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index a80be60..eddb322 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -168,6 +168,7 @@ extern const char *powerpc_base_platform;
#define CPU_FTR_LWSYNC ASM_CONST(0x0000000008000000)
#define CPU_FTR_NOEXECUTE ASM_CONST(0x0000000010000000)
#define CPU_FTR_INDEXED_DCR ASM_CONST(0x0000000020000000)
+#define CPU_FTR_EMB_HV ASM_CONST(0x0000000040000000)
/*
* Add the 64-bit processor unique features in the top half of the word;
@@ -385,11 +386,11 @@ extern const char *powerpc_base_platform;
CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
#define CPU_FTRS_E500MC (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
- CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC)
+ CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
#define CPU_FTRS_E5500 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
- CPU_FTR_DEBUG_LVL_EXC)
+ CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
#define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
/* 64-bit CPUs */
@@ -534,6 +535,7 @@ enum {
#ifdef CONFIG_PPC_E500MC
CPU_FTRS_E500MC & CPU_FTRS_E5500 &
#endif
+ ~CPU_FTR_EMB_HV & /* can be removed at runtime */
CPU_FTRS_POSSIBLE,
};
#endif /* __powerpc64__ */
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index fb3fddc..98abdd0 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -280,6 +280,7 @@ struct kvm_guest_debug_arch {
#define KVM_CPU_E500V2 2
#define KVM_CPU_3S_32 3
#define KVM_CPU_3S_64 4
+#define KVM_CPU_E500MC 5
/* for KVM_CAP_SPAPR_TCE */
struct kvm_create_spapr_tce {
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 8053db0..69fdd23 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -73,6 +73,7 @@ _GLOBAL(__setup_cpu_e500v2)
mtlr r4
blr
_GLOBAL(__setup_cpu_e500mc)
+ mr r5, r4
mflr r4
bl __e500_icache_setup
bl __e500_dcache_setup
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 5701e87..b269b86 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -380,10 +380,16 @@ interrupt_base:
mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
mfspr r10, SPRN_SPRG_THREAD
stw r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mfspr r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
stw r12, THREAD_NORMSAVE(1)(r10)
stw r13, THREAD_NORMSAVE(2)(r10)
mfcr r13
stw r13, THREAD_NORMSAVE(3)(r10)
+ DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
mfspr r10, SPRN_DEAR /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
@@ -468,10 +474,16 @@ interrupt_base:
mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
mfspr r10, SPRN_SPRG_THREAD
stw r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mfspr r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
stw r12, THREAD_NORMSAVE(1)(r10)
stw r13, THREAD_NORMSAVE(2)(r10)
mfcr r13
stw r13, THREAD_NORMSAVE(3)(r10)
+ DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
mfspr r10, SPRN_SRR0 /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
@@ -580,6 +592,17 @@ interrupt_base:
DEBUG_DEBUG_EXCEPTION
DEBUG_CRIT_EXCEPTION
+ GUEST_DOORBELL_EXCEPTION
+
+ CRITICAL_EXCEPTION(0, GUEST_DBELL_CRIT, CriticalGuestDoorbell, \
+ unknown_exception)
+
+ /* Hypercall */
+ EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE)
+
+ /* Embedded Hypervisor Privilege */
+ EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE)
+
/*
* Local functions
*/
@@ -883,8 +906,31 @@ _GLOBAL(__setup_e500mc_ivors)
mtspr SPRN_IVOR36,r3
li r3,CriticalDoorbell@l
mtspr SPRN_IVOR37,r3
+
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r3, SPRN_MMUCFG
+ andis. r3, r3, MMUCFG_LPIDSIZE@h
+ beq no_hv
+ li r3,GuestDoorbell@l
+ mtspr SPRN_IVOR38,r3
+ li r3,CriticalGuestDoorbell@l
+ mtspr SPRN_IVOR39,r3
+ li r3,Hypercall@l
+ mtspr SPRN_IVOR40,r3
+ li r3,Ehvpriv@l
+ mtspr SPRN_IVOR41,r3
+skip_hv_ivors:
sync
blr
+no_hv:
+ lwz r3, CPU_SPEC_FEATURES(r5)
+ rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV
+ stw r3, CPU_SPEC_FEATURES(r5)
+ b skip_hv_ivors
/*
* extern void giveup_altivec(struct task_struct *prev)
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 2c33cd3..58f6e68 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -109,7 +109,7 @@ config KVM_440
config KVM_EXIT_TIMING
bool "Detailed exit timing"
- depends on KVM_440 || KVM_E500
+ depends on KVM_440 || KVM_E500 || KVM_E500MC
---help---
Calculate elapsed time for every exit/enter cycle. A per-vcpu
report is available in debugfs kvm/vm#_vcpu#_timing.
@@ -132,6 +132,21 @@ config KVM_E500
If unsure, say N.
+config KVM_E500MC
+ bool "KVM support for PowerPC E500MC/E5500 processors"
+ depends on EXPERIMENTAL && PPC_E500MC
+ select KVM
+ select KVM_MMIO
+ select KVM_BOOKE_HV
+ ---help---
+ Support running unmodified E500MC/E5500 (32-bit) guest kernels in
+ virtual machines on E500MC/E5500 host processors.
+
+ This module provides access to the hardware capabilities through
+ a character device node named /dev/kvm.
+
+ If unsure, say N.
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 3688aee..62febd7 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -38,6 +38,16 @@ kvm-e500-objs := \
e500_emulate.o
kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs)
+kvm-e500mc-objs := \
+ $(common-objs-y) \
+ booke.o \
+ booke_emulate.o \
+ bookehv_interrupts.o \
+ e500mc.o \
+ e500_tlb.o \
+ e500_emulate.o
+kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
+
kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
../../../virt/kvm/coalesced_mmio.o \
fpu.o \
@@ -89,6 +99,7 @@ kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
obj-$(CONFIG_KVM_440) += kvm.o
obj-$(CONFIG_KVM_E500) += kvm.o
+obj-$(CONFIG_KVM_E500MC) += kvm.o
obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index ce3f163..3143085 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -2,7 +2,9 @@
* Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu <yu.liu@freescale.com>
+ * Scott Wood <scottwood@freescale.com>
* Ashish Kalra <ashish.kalra@freescale.com>
+ * Varun Sethi <varun.sethi@freescale.com>
*
* Description:
* This file is based on arch/powerpc/kvm/44x_tlb.h and
@@ -100,6 +102,7 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
}
+
/* This geometry is the legacy default -- can be overridden by userspace */
#define KVM_E500_TLB0_WAY_SIZE 128
#define KVM_E500_TLB0_WAY_NUM 2
@@ -250,10 +253,12 @@ static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
if (!get_tlb_v(tlbe))
return 0;
+#ifndef CONFIG_KVM_BOOKE_HV
/* Does it match current guest AS? */
/* XXX what about IS != DS? */
if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
return 0;
+#endif
gpa = get_tlb_raddr(tlbe);
if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
@@ -274,7 +279,11 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
struct kvm_book3e_206_tlb_entry *gtlbe);
void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500);
-#ifdef CONFIG_KVM_E500
+#ifdef CONFIG_KVM_BOOKE_HV
+#define kvmppc_e500_get_tlb_stid(vcpu, gtlbe) get_tlb_tid(gtlbe)
+#define get_tlbmiss_tid(vcpu) get_cur_pid(vcpu)
+#define get_tlb_sts(gtlbe) (gtlbe->mas1 & MAS1_TS)
+#else
unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
struct kvm_book3e_206_tlb_entry *gtlbe);
@@ -288,6 +297,6 @@ static inline unsigned int get_tlbmiss_tid(struct kvm_vcpu *vcpu)
/* Force TS=1 for all guest mappings. */
#define get_tlb_sts(gtlbe) (MAS1_TS)
-#endif /* CONFIG_KVM_E500 */
+#endif /* !BOOKE_HV */
#endif /* KVM_E500_H */
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index af02c18..98b6c1c 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -85,6 +85,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
ulong spr_val = kvmppc_get_gpr(vcpu, rs);
switch (sprn) {
+#ifndef CONFIG_KVM_BOOKE_HV
case SPRN_PID:
kvmppc_set_pid(vcpu, spr_val);
break;
@@ -114,6 +115,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
vcpu->arch.shared->mas7_3 &= (u64)0xffffffff;
vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32;
break;
+#endif
case SPRN_L1CSR0:
vcpu_e500->l1csr0 = spr_val;
vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
@@ -143,7 +145,14 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
case SPRN_IVOR35:
vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val;
break;
-
+#ifdef CONFIG_KVM_BOOKE_HV
+ case SPRN_IVOR36:
+ vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL] = spr_val;
+ break;
+ case SPRN_IVOR37:
+ vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT] = spr_val;
+ break;
+#endif
default:
emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
}
@@ -155,9 +164,11 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
int emulated = EMULATE_DONE;
- unsigned long val;
switch (sprn) {
+#ifndef CONFIG_KVM_BOOKE_HV
+ unsigned long val;
+
case SPRN_PID:
kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break;
case SPRN_PID1:
@@ -182,6 +193,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
val = vcpu->arch.shared->mas7_3 >> 32;
kvmppc_set_gpr(vcpu, rt, val);
break;
+#endif
case SPRN_TLB0CFG:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[0]); break;
case SPRN_TLB1CFG:
@@ -216,6 +228,14 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
case SPRN_IVOR35:
kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]);
break;
+#ifdef CONFIG_KVM_BOOKE_HV
+ case SPRN_IVOR36:
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL]);
+ break;
+ case SPRN_IVOR37:
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT]);
+ break;
+#endif
default:
emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
}
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 121cd68..f1d7f21 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -2,7 +2,9 @@
* Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, yu.liu@freescale.com
+ * Scott Wood, scottwood@freescale.com
* Ashish Kalra, ashish.kalra@freescale.com
+ * Varun Sethi, varun.sethi@freescale.com
*
* Description:
* This file is based on arch/powerpc/kvm/44x_tlb.c,
@@ -64,6 +66,7 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
/* Mask off reserved bits. */
mas3 &= MAS3_ATTRIB_MASK;
+#ifndef CONFIG_KVM_BOOKE_HV
if (!usermode) {
/* Guest is in supervisor mode,
* so we need to translate guest
@@ -71,8 +74,9 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
mas3 &= ~E500_TLB_USER_PERM_MASK;
mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
}
-
- return mas3 | E500_TLB_SUPER_PERM_MASK;
+ mas3 |= E500_TLB_SUPER_PERM_MASK;
+#endif
+ return mas3;
}
static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
@@ -98,7 +102,16 @@ static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
+#ifdef CONFIG_KVM_BOOKE_HV
+ mtspr(SPRN_MAS8, stlbe->mas8);
+#endif
asm volatile("isync; tlbwe" : : : "memory");
+
+#ifdef CONFIG_KVM_BOOKE_HV
+ /* Must clear mas8 for other host tlbwe's */
+ mtspr(SPRN_MAS8, 0);
+ isync();
+#endif
local_irq_restore(flags);
trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
@@ -384,6 +397,10 @@ static inline void kvmppc_e500_setup_stlbe(
e500_shadow_mas2_attrib(gtlbe->mas2, pr);
stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+ stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
+#endif
}
static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
new file mode 100644
index 0000000..fe6c1de
--- /dev/null
+++ b/arch/powerpc/kvm/e500mc.c
@@ -0,0 +1,342 @@
+/*
+ * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Varun Sethi, <varun.sethi@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/e500.c,
+ * by Yu Liu <yu.liu@freescale.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/dbell.h>
+
+#include "booke.h"
+#include "e500.h"
+
+void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type)
+{
+ enum ppc_dbell dbell_type;
+ unsigned long tag;
+
+ switch (type) {
+ case INT_CLASS_NONCRIT:
+ dbell_type = PPC_G_DBELL;
+ break;
+ case INT_CLASS_CRIT:
+ dbell_type = PPC_G_DBELL_CRIT;
+ break;
+ case INT_CLASS_MC:
+ dbell_type = PPC_G_DBELL_MC;
+ break;
+ default:
+ WARN_ONCE(1, "%s: unknown int type %d\n", __func__, type);
+ return;
+ }
+
+
+ tag = PPC_DBELL_LPID(vcpu->kvm->arch.lpid) | vcpu->vcpu_id;
+ mb();
+ ppc_msgsnd(dbell_type, 0, tag);
+}
+
+/* gtlbe must not be mapped by more than one host tlb entry */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+ struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+ unsigned int tid, ts;
+ u32 val, eaddr, lpid;
+ unsigned long flags;
+
+ ts = get_tlb_ts(gtlbe);
+ tid = get_tlb_tid(gtlbe);
+ lpid = vcpu_e500->vcpu.kvm->arch.lpid;
+
+ /* We search the host TLB to invalidate its shadow TLB entry */
+ val = (tid << 16) | ts;
+ eaddr = get_tlb_eaddr(gtlbe);
+
+ local_irq_save(flags);
+
+ mtspr(SPRN_MAS6, val);
+ mtspr(SPRN_MAS5, MAS5_SGS | lpid);
+
+ asm volatile("tlbsx 0, %[eaddr]\n" : : [eaddr] "r" (eaddr));
+ val = mfspr(SPRN_MAS1);
+ if (val & MAS1_VALID) {
+ mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+ asm volatile("tlbwe");
+ }
+ mtspr(SPRN_MAS5, 0);
+ /* NOTE: tlbsx also updates mas8, so clear it for host tlbwe */
+ mtspr(SPRN_MAS8, 0);
+ isync();
+
+ local_irq_restore(flags);
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ mtspr(SPRN_MAS5, MAS5_SGS | vcpu_e500->vcpu.kvm->arch.lpid);
+ asm volatile("tlbilxlpid");
+ mtspr(SPRN_MAS5, 0);
+ local_irq_restore(flags);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+ vcpu->arch.pid = pid;
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+ kvmppc_booke_vcpu_load(vcpu, cpu);
+
+ mtspr(SPRN_LPID, vcpu->kvm->arch.lpid);
+ mtspr(SPRN_EPCR, vcpu->arch.shadow_epcr);
+ mtspr(SPRN_GPIR, vcpu->vcpu_id);
+ mtspr(SPRN_MSRP, vcpu->arch.shadow_msrp);
+ mtspr(SPRN_EPLC, vcpu->arch.eplc);
+ mtspr(SPRN_EPSC, vcpu->arch.epsc);
+
+ mtspr(SPRN_GIVPR, vcpu->arch.ivpr);
+ mtspr(SPRN_GIVOR2, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]);
+ mtspr(SPRN_GIVOR8, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]);
+ mtspr(SPRN_GSPRG0, (unsigned long)vcpu->arch.shared->sprg0);
+ mtspr(SPRN_GSPRG1, (unsigned long)vcpu->arch.shared->sprg1);
+ mtspr(SPRN_GSPRG2, (unsigned long)vcpu->arch.shared->sprg2);
+ mtspr(SPRN_GSPRG3, (unsigned long)vcpu->arch.shared->sprg3);
+
+ mtspr(SPRN_GSRR0, vcpu->arch.shared->srr0);
+ mtspr(SPRN_GSRR1, vcpu->arch.shared->srr1);
+
+ mtspr(SPRN_GEPR, vcpu->arch.epr);
+ mtspr(SPRN_GDEAR, vcpu->arch.shared->dar);
+ mtspr(SPRN_GESR, vcpu->arch.shared->esr);
+
+ if (vcpu->arch.oldpir != mfspr(SPRN_PIR))
+ kvmppc_e500_tlbil_all(vcpu_e500);
+
+ kvmppc_load_guest_fp(vcpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.eplc = mfspr(SPRN_EPLC);
+ vcpu->arch.epsc = mfspr(SPRN_EPSC);
+
+ vcpu->arch.shared->sprg0 = mfspr(SPRN_GSPRG0);
+ vcpu->arch.shared->sprg1 = mfspr(SPRN_GSPRG1);
+ vcpu->arch.shared->sprg2 = mfspr(SPRN_GSPRG2);
+ vcpu->arch.shared->sprg3 = mfspr(SPRN_GSPRG3);
+
+ vcpu->arch.shared->srr0 = mfspr(SPRN_GSRR0);
+ vcpu->arch.shared->srr1 = mfspr(SPRN_GSRR1);
+
+ vcpu->arch.epr = mfspr(SPRN_GEPR);
+ vcpu->arch.shared->dar = mfspr(SPRN_GDEAR);
+ vcpu->arch.shared->esr = mfspr(SPRN_GESR);
+
+ vcpu->arch.oldpir = mfspr(SPRN_PIR);
+
+ kvmppc_booke_vcpu_put(vcpu);
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+ int r;
+
+ if (strcmp(cur_cpu_spec->cpu_name, "e500mc") == 0)
+ r = 0;
+ else if (strcmp(cur_cpu_spec->cpu_name, "e5500") == 0)
+ r = 0;
+ else
+ r = -ENOTSUPP;
+
+ return r;
+}
+
+int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+ vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \
+ SPRN_EPCR_DUVD;
+ vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP;
+ vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT);
+ vcpu->arch.epsc = vcpu->arch.eplc;
+
+ vcpu->arch.pvr = mfspr(SPRN_PVR);
+ vcpu_e500->svr = mfspr(SPRN_SVR);
+
+ vcpu->arch.cpu_type = KVM_CPU_E500MC;
+
+ return 0;
+}
+
+void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+ sregs->u.e.features |= KVM_SREGS_E_ARCH206_MMU | KVM_SREGS_E_PM |
+ KVM_SREGS_E_PC;
+ sregs->u.e.impl_id = KVM_SREGS_E_IMPL_FSL;
+
+ sregs->u.e.impl.fsl.features = 0;
+ sregs->u.e.impl.fsl.svr = vcpu_e500->svr;
+ sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
+ sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
+
+ kvmppc_get_sregs_e500_tlb(vcpu, sregs);
+
+ sregs->u.e.ivor_high[3] =
+ vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+ sregs->u.e.ivor_high[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL];
+ sregs->u.e.ivor_high[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT];
+
+ kvmppc_get_sregs_ivor(vcpu, sregs);
+}
+
+int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ int ret;
+
+ if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
+ vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
+ vcpu_e500->hid0 = sregs->u.e.impl.fsl.hid0;
+ vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
+ }
+
+ ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+ if (ret < 0)
+ return ret;
+
+ if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
+ return 0;
+
+ if (sregs->u.e.features & KVM_SREGS_E_PM) {
+ vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] =
+ sregs->u.e.ivor_high[3];
+ }
+
+ if (sregs->u.e.features & KVM_SREGS_E_PC) {
+ vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL] =
+ sregs->u.e.ivor_high[4];
+ vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT] =
+ sregs->u.e.ivor_high[5];
+ }
+
+ return kvmppc_set_sregs_ivor(vcpu, sregs);
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500;
+ struct kvm_vcpu *vcpu;
+ int err;
+
+ vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+ if (!vcpu_e500) {
+ err = -ENOMEM;
+ goto out;
+ }
+ vcpu = &vcpu_e500->vcpu;
+
+ /* Invalid PIR value -- this LPID dosn't have valid state on any cpu */
+ vcpu->arch.oldpir = 0xffffffff;
+
+ err = kvm_vcpu_init(vcpu, kvm, id);
+ if (err)
+ goto free_vcpu;
+
+ err = kvmppc_e500_tlb_init(vcpu_e500);
+ if (err)
+ goto uninit_vcpu;
+
+ vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ if (!vcpu->arch.shared)
+ goto uninit_tlb;
+
+ return vcpu;
+
+uninit_tlb:
+ kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_vcpu:
+ kvm_vcpu_uninit(vcpu);
+
+free_vcpu:
+ kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+out:
+ return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+ free_page((unsigned long)vcpu->arch.shared);
+ kvmppc_e500_tlb_uninit(vcpu_e500);
+ kvm_vcpu_uninit(vcpu);
+ kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+ int lpid;
+
+ lpid = kvmppc_alloc_lpid();
+ if (lpid < 0)
+ return lpid;
+
+ kvm->arch.lpid = lpid;
+ return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+ kvmppc_free_lpid(kvm->arch.lpid);
+}
+
+static int __init kvmppc_e500mc_init(void)
+{
+ int r;
+
+ r = kvmppc_booke_init();
+ if (r)
+ return r;
+
+ kvmppc_init_lpid(64);
+ kvmppc_claim_lpid(0); /* host */
+
+ return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+}
+
+static void __exit kvmppc_e500mc_exit(void)
+{
+ kvmppc_booke_exit();
+}
+
+module_init(kvmppc_e500mc_init);
+module_exit(kvmppc_e500mc_exit);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f9c62dd..97aaf7f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -227,7 +227,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_PPC_PAIRED_SINGLES:
case KVM_CAP_PPC_OSI:
case KVM_CAP_PPC_GET_PVINFO:
-#ifdef CONFIG_KVM_E500
+#if defined(CONFIG_KVM_E500) || defined(CONFIG_KVM_E500MC)
case KVM_CAP_SW_TLB:
#endif
r = 1;
@@ -625,7 +625,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
r = 0;
vcpu->arch.papr_enabled = true;
break;
-#ifdef CONFIG_KVM_E500
+#if defined(CONFIG_KVM_E500) || defined(CONFIG_KVM_E500MC)
case KVM_CAP_SW_TLB: {
struct kvm_config_tlb cfg;
void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];
@@ -712,7 +712,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
}
-#ifdef CONFIG_KVM_E500
+#if defined(CONFIG_KVM_E500) || defined(CONFIG_KVM_E500MC)
case KVM_DIRTY_TLB: {
struct kvm_dirty_tlb dirty;
r = -EFAULT;
--
1.7.7.rc3.4.g8d714
^ permalink raw reply related
* [RFC PATCH 15/16] KVM: PPC: booke: standard PPC floating point support
From: Scott Wood @ 2011-12-21 1:34 UTC (permalink / raw)
To: agraf; +Cc: linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <20111221013340.GA8368@schlenkerla.am.freescale.net>
e500mc has a normal PPC FPU, rather than SPE which is found
on e500v1/v2.
Based on code from Liu Yu <yu.liu@freescale.com>.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/include/asm/system.h | 1 +
arch/powerpc/kvm/booke.c | 44 +++++++++++++++++++++++++++++++++++++
arch/powerpc/kvm/booke.h | 30 +++++++++++++++++++++++++
3 files changed, 75 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index e30a13d..0561356 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -140,6 +140,7 @@ extern void via_cuda_init(void);
extern void read_rtc_time(void);
extern void pmac_find_display(void);
extern void giveup_fpu(struct task_struct *);
+extern void load_up_fpu(void);
extern void disable_kernel_fp(void);
extern void enable_kernel_fp(void);
extern void flush_fp_to_thread(struct task_struct *);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index cf63b93..4bf43f9 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -460,6 +460,11 @@ void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
int ret;
+#ifdef CONFIG_PPC_FPU
+ unsigned int fpscr;
+ int fpexc_mode;
+ u64 fpr[32];
+#endif
if (!vcpu->arch.sane) {
kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -482,7 +487,46 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
}
kvm_guest_enter();
+
+#ifdef CONFIG_PPC_FPU
+ /* Save userspace FPU state in stack */
+ enable_kernel_fp();
+ memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
+ fpscr = current->thread.fpscr.val;
+ fpexc_mode = current->thread.fpexc_mode;
+
+ /* Restore guest FPU state to thread */
+ memcpy(current->thread.fpr, vcpu->arch.fpr, sizeof(vcpu->arch.fpr));
+ current->thread.fpscr.val = vcpu->arch.fpscr;
+
+ /*
+ * Since we can't trap on MSR_FP in GS-mode, we consider the guest
+ * as always using the FPU. Kernel usage of FP (via
+ * enable_kernel_fp()) in this thread must not occur while
+ * vcpu->fpu_active is set.
+ */
+ vcpu->fpu_active = 1;
+
+ kvmppc_load_guest_fp(vcpu);
+#endif
+
ret = __kvmppc_vcpu_run(kvm_run, vcpu);
+
+#ifdef CONFIG_PPC_FPU
+ kvmppc_save_guest_fp(vcpu);
+
+ vcpu->fpu_active = 0;
+
+ /* Save guest FPU state from thread */
+ memcpy(vcpu->arch.fpr, current->thread.fpr, sizeof(vcpu->arch.fpr));
+ vcpu->arch.fpscr = current->thread.fpscr.val;
+
+ /* Restore userspace FPU state from stack */
+ memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
+ current->thread.fpscr.val = fpscr;
+ current->thread.fpexc_mode = fpexc_mode;
+#endif
+
kvm_guest_exit();
out:
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index d53bcf2..3bf5eda 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -96,4 +96,34 @@ enum int_class {
void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type);
+/*
+ * Load up guest vcpu FP state if it's needed.
+ * It also set the MSR_FP in thread so that host know
+ * we're holding FPU, and then host can help to save
+ * guest vcpu FP state if other threads require to use FPU.
+ * This simulates an FP unavailable fault.
+ *
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_FPU
+ if (vcpu->fpu_active && !(current->thread.regs->msr & MSR_FP)) {
+ load_up_fpu();
+ current->thread.regs->msr |= MSR_FP;
+ }
+#endif
+}
+
+/*
+ * Save guest vcpu FP state into thread.
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_FPU
+ if (vcpu->fpu_active && (current->thread.regs->msr & MSR_FP))
+ giveup_fpu(current);
+#endif
+}
#endif /* __KVM_BOOKE_H__ */
--
1.7.7.rc3.4.g8d714
^ permalink raw reply related
* [RFC PATCH 12/16] KVM: PPC: e500: emulate tlbilx
From: Scott Wood @ 2011-12-21 1:34 UTC (permalink / raw)
To: agraf; +Cc: linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <20111221013340.GA8368@schlenkerla.am.freescale.net>
tlbilx is the new, preferred invalidation instruction. It is not
found on e500 prior to e500mc, but there should be no harm in
supporting it on all e500.
Based on code from Ashish Kalra <Ashish.Kalra@freescale.com>.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/kvm/e500.h | 1 +
arch/powerpc/kvm/e500_emulate.c | 9 ++++++
arch/powerpc/kvm/e500_tlb.c | 52 +++++++++++++++++++++++++++++++++++++++
3 files changed, 62 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index f4dee55..ce3f163 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -124,6 +124,7 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500,
int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu);
int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu);
int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb);
+int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int rt, int ra, int rb);
int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb);
int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500);
void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index c80794d..af02c18 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -22,6 +22,7 @@
#define XOP_TLBSX 914
#define XOP_TLBRE 946
#define XOP_TLBWE 978
+#define XOP_TLBILX 18
int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int inst, int *advance)
@@ -29,6 +30,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
int emulated = EMULATE_DONE;
int ra;
int rb;
+ int rt;
switch (get_op(inst)) {
case 31:
@@ -47,6 +49,13 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
break;
+ case XOP_TLBILX:
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+ rt = get_rt(inst);
+ emulated = kvmppc_e500_emul_tlbilx(vcpu, rt, ra, rb);
+ break;
+
case XOP_TLBIVAX:
ra = get_ra(inst);
rb = get_rb(inst);
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 031fd5b..121cd68 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -631,6 +631,58 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
return EMULATE_DONE;
}
+static void tlbilx_all(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
+ int pid, int rt)
+{
+ struct kvm_book3e_206_tlb_entry *tlbe;
+ int tid, esel;
+
+ /* invalidate all entries */
+ for (esel = 0; esel < vcpu_e500->gtlb_params[tlbsel].entries; esel++) {
+ tlbe = get_entry(vcpu_e500, tlbsel, esel);
+ tid = get_tlb_tid(tlbe);
+ if (rt == 0 || tid == pid) {
+ inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
+ kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+ }
+ }
+}
+
+static void tlbilx_one(struct kvmppc_vcpu_e500 *vcpu_e500, int pid,
+ int ra, int rb)
+{
+ int tlbsel, esel;
+ gva_t ea;
+
+ ea = kvmppc_get_gpr(&vcpu_e500->vcpu, rb);
+ if (ra)
+ ea += kvmppc_get_gpr(&vcpu_e500->vcpu, ra);
+
+ for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+ esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, -1);
+ if (esel >= 0) {
+ inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
+ kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+ break;
+ }
+ }
+}
+
+int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int rt, int ra, int rb)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ int pid = get_cur_spid(vcpu);
+
+ if (rt == 0 || rt == 1) {
+ tlbilx_all(vcpu_e500, 0, pid, rt);
+ tlbilx_all(vcpu_e500, 1, pid, rt);
+ } else if (rt == 3) {
+ tlbilx_one(vcpu_e500, pid, ra, rb);
+ }
+
+ return EMULATE_DONE;
+}
+
int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
--
1.7.7.rc3.4.g8d714
^ permalink raw reply related
* [RFC PATCH 13/16] powerpc/booke: Provide exception macros with interrupt name
From: Scott Wood @ 2011-12-21 1:34 UTC (permalink / raw)
To: agraf; +Cc: linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <20111221013340.GA8368@schlenkerla.am.freescale.net>
DO_KVM will need to identify the particular exception type.
There is an existing set of arbitrary numbers that Linux passes,
but it's an undocumented mess that sort of corresponds to server/classic
exception vectors but not really.
FIXME: Replace the existing trap numbering rather than add to it.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/kernel/head_44x.S | 23 +++++++++------
arch/powerpc/kernel/head_booke.h | 41 ++++++++++++++------------
arch/powerpc/kernel/head_fsl_booke.S | 52 +++++++++++++++++++++-------------
3 files changed, 68 insertions(+), 48 deletions(-)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index b725dab..51a49f6 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -160,10 +160,11 @@ _ENTRY(_start);
interrupt_base:
/* Critical Input Interrupt */
- CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception)
+ CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
/* Machine Check Interrupt */
- CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+ CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+ machine_check_exception)
MCHECK_EXCEPTION(0x0210, MachineCheckA, machine_check_exception)
/* Data Storage Interrupt */
@@ -173,7 +174,8 @@ interrupt_base:
INSTRUCTION_STORAGE_EXCEPTION
/* External Input Interrupt */
- EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+ EXCEPTION(0x0500, BOOKE_INTERRUPT_EXTERNAL, ExternalInput, \
+ do_IRQ, EXC_XFER_LITE)
/* Alignment Interrupt */
ALIGNMENT_EXCEPTION
@@ -185,29 +187,32 @@ interrupt_base:
#ifdef CONFIG_PPC_FPU
FP_UNAVAILABLE_EXCEPTION
#else
- EXCEPTION(0x2010, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \
+ FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
#endif
/* System Call Interrupt */
START_EXCEPTION(SystemCall)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(BOOKE_INTERRUPT_SYSCALL)
EXC_XFER_EE_LITE(0x0c00, DoSyscall)
/* Auxiliary Processor Unavailable Interrupt */
- EXCEPTION(0x2020, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \
+ AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
/* Decrementer Interrupt */
DECREMENTER_EXCEPTION
/* Fixed Internal Timer Interrupt */
/* TODO: Add FIT support */
- EXCEPTION(0x1010, FixedIntervalTimer, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, \
+ unknown_exception, EXC_XFER_EE)
/* Watchdog Timer Interrupt */
/* TODO: Add watchdog support */
#ifdef CONFIG_BOOKE_WDT
- CRITICAL_EXCEPTION(0x1020, WatchdogTimer, WatchdogException)
+ CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, WatchdogException)
#else
- CRITICAL_EXCEPTION(0x1020, WatchdogTimer, unknown_exception)
+ CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, unknown_exception)
#endif
/* Data TLB Error Interrupt */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index fc921bf..06ab353 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -2,6 +2,8 @@
#define __HEAD_BOOKE_H__
#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
+#include <asm/kvm_asm.h>
+
/*
* Macros used for common Book-e exception handling
*/
@@ -28,7 +30,7 @@
*/
#define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4))
-#define NORMAL_EXCEPTION_PROLOG \
+#define NORMAL_EXCEPTION_PROLOG(intno) \
mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \
mfspr r10, SPRN_SPRG_THREAD; \
stw r11, THREAD_NORMSAVE(0)(r10); \
@@ -113,7 +115,7 @@
* registers as the normal prolog above. Instead we use a portion of the
* critical/machine check exception stack at low physical addresses.
*/
-#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, exc_level_srr0, exc_level_srr1) \
+#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, intno, exc_level_srr0, exc_level_srr1) \
mtspr SPRN_SPRG_WSCRATCH_##exc_level,r8; \
BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);/* r8 points to the exc_level stack*/ \
stw r9,GPR9(r8); /* save various registers */\
@@ -162,12 +164,13 @@
SAVE_4GPRS(3, r11); \
SAVE_2GPRS(7, r11)
-#define CRITICAL_EXCEPTION_PROLOG \
- EXC_LEVEL_EXCEPTION_PROLOG(CRIT, SPRN_CSRR0, SPRN_CSRR1)
+#define CRITICAL_EXCEPTION_PROLOG(intno) \
+ EXC_LEVEL_EXCEPTION_PROLOG(CRIT, intno, SPRN_CSRR0, SPRN_CSRR1)
#define DEBUG_EXCEPTION_PROLOG \
- EXC_LEVEL_EXCEPTION_PROLOG(DBG, SPRN_DSRR0, SPRN_DSRR1)
+ EXC_LEVEL_EXCEPTION_PROLOG(DBG, DEBUG, SPRN_DSRR0, SPRN_DSRR1)
#define MCHECK_EXCEPTION_PROLOG \
- EXC_LEVEL_EXCEPTION_PROLOG(MC, SPRN_MCSRR0, SPRN_MCSRR1)
+ EXC_LEVEL_EXCEPTION_PROLOG(MC, MACHINE_CHECK, \
+ SPRN_MCSRR0, SPRN_MCSRR1)
/*
* Exception vectors.
@@ -181,16 +184,16 @@ label:
.long func; \
.long ret_from_except_full
-#define EXCEPTION(n, label, hdlr, xfer) \
+#define EXCEPTION(n, intno, label, hdlr, xfer) \
START_EXCEPTION(label); \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(intno); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
xfer(n, hdlr)
-#define CRITICAL_EXCEPTION(n, label, hdlr) \
- START_EXCEPTION(label); \
- CRITICAL_EXCEPTION_PROLOG; \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
+#define CRITICAL_EXCEPTION(n, intno, label, hdlr) \
+ START_EXCEPTION(label); \
+ CRITICAL_EXCEPTION_PROLOG(intno); \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
NOCOPY, crit_transfer_to_handler, \
ret_from_crit_exc)
@@ -302,7 +305,7 @@ label:
#define DEBUG_CRIT_EXCEPTION \
START_EXCEPTION(DebugCrit); \
- CRITICAL_EXCEPTION_PROLOG; \
+ CRITICAL_EXCEPTION_PROLOG(DEBUG); \
\
/* \
* If there is a single step or branch-taken exception in an \
@@ -355,7 +358,7 @@ label:
#define DATA_STORAGE_EXCEPTION \
START_EXCEPTION(DataStorage) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(DATA_STORAGE); \
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
mfspr r4,SPRN_DEAR; /* Grab the DEAR */ \
@@ -363,7 +366,7 @@ label:
#define INSTRUCTION_STORAGE_EXCEPTION \
START_EXCEPTION(InstructionStorage) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(INST_STORAGE); \
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
mr r4,r12; /* Pass SRR0 as arg2 */ \
@@ -372,7 +375,7 @@ label:
#define ALIGNMENT_EXCEPTION \
START_EXCEPTION(Alignment) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(ALIGNMENT); \
mfspr r4,SPRN_DEAR; /* Grab the DEAR and save it */ \
stw r4,_DEAR(r11); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -380,7 +383,7 @@ label:
#define PROGRAM_EXCEPTION \
START_EXCEPTION(Program) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(PROGRAM); \
mfspr r4,SPRN_ESR; /* Grab the ESR and save it */ \
stw r4,_ESR(r11); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -388,7 +391,7 @@ label:
#define DECREMENTER_EXCEPTION \
START_EXCEPTION(Decrementer) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(DECREMENTER); \
lis r0,TSR_DIS@h; /* Setup the DEC interrupt mask */ \
mtspr SPRN_TSR,r0; /* Clear the DEC interrupt */ \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -396,7 +399,7 @@ label:
#define FP_UNAVAILABLE_EXCEPTION \
START_EXCEPTION(FloatingPointUnavailable) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(FP_UNAVAIL); \
beq 1f; \
bl load_up_fpu; /* if from user, just load it up */ \
b fast_exception_return; \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 9f5d210..5701e87 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -301,19 +301,20 @@ _ENTRY(__early_start)
interrupt_base:
/* Critical Input Interrupt */
- CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception)
+ CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
/* Machine Check Interrupt */
#ifdef CONFIG_E200
/* no RFMCI, MCSRRs on E200 */
- CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+ CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+ machine_check_exception)
#else
MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
#endif
/* Data Storage Interrupt */
START_EXCEPTION(DataStorage)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(DATA_STORAGE)
mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
stw r5,_ESR(r11)
mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
@@ -328,7 +329,7 @@ interrupt_base:
INSTRUCTION_STORAGE_EXCEPTION
/* External Input Interrupt */
- EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+ EXCEPTION(0x0500, EXTERNAL, ExternalInput, do_IRQ, EXC_XFER_LITE)
/* Alignment Interrupt */
ALIGNMENT_EXCEPTION
@@ -342,32 +343,36 @@ interrupt_base:
#else
#ifdef CONFIG_E200
/* E200 treats 'normal' floating point instructions as FP Unavail exception */
- EXCEPTION(0x0800, FloatingPointUnavailable, program_check_exception, EXC_XFER_EE)
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
+ program_check_exception, EXC_XFER_EE)
#else
- EXCEPTION(0x0800, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
+ unknown_exception, EXC_XFER_EE)
#endif
#endif
/* System Call Interrupt */
START_EXCEPTION(SystemCall)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(SYSCALL)
EXC_XFER_EE_LITE(0x0c00, DoSyscall)
/* Auxiliary Processor Unavailable Interrupt */
- EXCEPTION(0x2900, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, \
+ unknown_exception, EXC_XFER_EE)
/* Decrementer Interrupt */
DECREMENTER_EXCEPTION
/* Fixed Internal Timer Interrupt */
/* TODO: Add FIT support */
- EXCEPTION(0x3100, FixedIntervalTimer, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x3100, FIT, FixedIntervalTimer, \
+ unknown_exception, EXC_XFER_EE)
/* Watchdog Timer Interrupt */
#ifdef CONFIG_BOOKE_WDT
- CRITICAL_EXCEPTION(0x3200, WatchdogTimer, WatchdogException)
+ CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, WatchdogException)
#else
- CRITICAL_EXCEPTION(0x3200, WatchdogTimer, unknown_exception)
+ CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, unknown_exception)
#endif
/* Data TLB Error Interrupt */
@@ -538,31 +543,38 @@ interrupt_base:
#ifdef CONFIG_SPE
/* SPE Unavailable */
START_EXCEPTION(SPEUnavailable)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(SPE_UNAVAIL)
bne load_up_spe
addi r3,r1,STACK_FRAME_OVERHEAD
EXC_XFER_EE_LITE(0x2010, KernelSPE)
#else
- EXCEPTION(0x2020, SPEUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \
+ unknown_exception, EXC_XFER_EE)
#endif /* CONFIG_SPE */
/* SPE Floating Point Data */
#ifdef CONFIG_SPE
- EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
+ EXCEPTION(0x2030, SPE_FP_DATA, SPEFloatingPointData, \
+ SPEFloatingPointException, EXC_XFER_EE);
/* SPE Floating Point Round */
- EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE)
+ EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
+ SPEFloatingPointRoundException, EXC_XFER_EE)
#else
- EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
- EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2040, SPE_FP_DATA, SPEFloatingPointData, \
+ unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
+ unknown_exception, EXC_XFER_EE)
#endif /* CONFIG_SPE */
/* Performance Monitor */
- EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
+ EXCEPTION(0x2060, PERFORMANCE_MONITOR, PerformanceMonitor, \
+ performance_monitor_exception, EXC_XFER_STD)
- EXCEPTION(0x2070, Doorbell, doorbell_exception, EXC_XFER_STD)
+ EXCEPTION(0x2070, DOORBELL, Doorbell, doorbell_exception, EXC_XFER_STD)
- CRITICAL_EXCEPTION(0x2080, CriticalDoorbell, unknown_exception)
+ CRITICAL_EXCEPTION(0x2080, DOORBELL_CRITICAL, \
+ CriticalDoorbell, unknown_exception)
/* Debug Interrupt */
DEBUG_DEBUG_EXCEPTION
--
1.7.7.rc3.4.g8d714
^ permalink raw reply related
* [RFC PATCH 10/16] KVM: PPC: e500: refactor core-specific TLB code
From: Scott Wood @ 2011-12-21 1:34 UTC (permalink / raw)
To: agraf; +Cc: linuxppc-dev, kvm, kvm-ppc
In-Reply-To: <20111221013340.GA8368@schlenkerla.am.freescale.net>
The PID handling is e500v1/v2-specific, and is moved to e500.c.
The MMU sregs code and kvmppc_core_vcpu_translate will be shared with
e500mc, and is moved from e500.c to e500_tlb.c.
Partially based on patches from Liu Yu <yu.liu@freescale.com>.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/include/asm/kvm_host.h | 2 +
arch/powerpc/kvm/e500.c | 358 +++++++++++++++++++++++----
arch/powerpc/kvm/e500.h | 55 ++++-
arch/powerpc/kvm/e500_emulate.c | 7 +-
arch/powerpc/kvm/e500_tlb.c | 461 +++++++++--------------------------
5 files changed, 473 insertions(+), 410 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 443f007..ad4d671 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -415,6 +415,8 @@ struct kvm_vcpu_arch {
ulong fault_esr;
ulong queued_dear;
ulong queued_esr;
+ u32 tlbcfg[4];
+ u32 mmucfg;
#endif
gpa_t paddr_accessed;
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index faa32df..77e3134 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -20,12 +20,283 @@
#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/tlbflush.h>
-#include <asm/kvm_e500.h>
#include <asm/kvm_ppc.h>
+#include "../mm/mmu_decl.h"
#include "booke.h"
#include "e500.h"
+struct id {
+ unsigned long val;
+ struct id **pentry;
+};
+
+#define NUM_TIDS 256
+
+/*
+ * This table provide mappings from:
+ * (guestAS,guestTID,guestPR) --> ID of physical cpu
+ * guestAS [0..1]
+ * guestTID [0..255]
+ * guestPR [0..1]
+ * ID [1..255]
+ * Each vcpu keeps one vcpu_id_table.
+ */
+struct vcpu_id_table {
+ struct id id[2][NUM_TIDS][2];
+};
+
+/*
+ * This table provide reversed mappings of vcpu_id_table:
+ * ID --> address of vcpu_id_table item.
+ * Each physical core has one pcpu_id_table.
+ */
+struct pcpu_id_table {
+ struct id *entry[NUM_TIDS];
+};
+
+static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
+
+/* This variable keeps last used shadow ID on local core.
+ * The valid range of shadow ID is [1..255] */
+static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
+
+/*
+ * Allocate a free shadow id and setup a valid sid mapping in given entry.
+ * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_setup_one(struct id *entry)
+{
+ unsigned long sid;
+ int ret = -1;
+
+ sid = ++(__get_cpu_var(pcpu_last_used_sid));
+ if (sid < NUM_TIDS) {
+ __get_cpu_var(pcpu_sids).entry[sid] = entry;
+ entry->val = sid;
+ entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
+ ret = sid;
+ }
+
+ /*
+ * If sid == NUM_TIDS, we've run out of sids. We return -1, and
+ * the caller will invalidate everything and start over.
+ *
+ * sid > NUM_TIDS indicates a race, which we disable preemption to
+ * avoid.
+ */
+ WARN_ON(sid > NUM_TIDS);
+
+ return ret;
+}
+
+/*
+ * Check if given entry contain a valid shadow id mapping.
+ * An ID mapping is considered valid only if
+ * both vcpu and pcpu know this mapping.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_lookup(struct id *entry)
+{
+ if (entry && entry->val != 0 &&
+ __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
+ entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
+ return entry->val;
+ return -1;
+}
+
+/* Invalidate all id mappings on local core -- call with preempt disabled */
+static inline void local_sid_destroy_all(void)
+{
+ __get_cpu_var(pcpu_last_used_sid) = 0;
+ memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
+}
+
+static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
+ return vcpu_e500->idt;
+}
+
+static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ kfree(vcpu_e500->idt);
+ vcpu_e500->idt = NULL;
+}
+
+/* Map guest pid to shadow.
+ * We use PID to keep shadow of current guest non-zero PID,
+ * and use PID1 to keep shadow of guest zero PID.
+ * So that guest tlbe with TID=0 can be accessed at any time */
+static void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ preempt_disable();
+ vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
+ get_cur_as(&vcpu_e500->vcpu),
+ get_cur_pid(&vcpu_e500->vcpu),
+ get_cur_pr(&vcpu_e500->vcpu), 1);
+ vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
+ get_cur_as(&vcpu_e500->vcpu), 0,
+ get_cur_pr(&vcpu_e500->vcpu), 1);
+ preempt_enable();
+}
+
+/* Invalidate all mappings on vcpu */
+static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
+
+ /* Update shadow pid when mappings are changed */
+ kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/* Invalidate one ID mapping on vcpu */
+static inline void kvmppc_e500_id_table_reset_one(
+ struct kvmppc_vcpu_e500 *vcpu_e500,
+ int as, int pid, int pr)
+{
+ struct vcpu_id_table *idt = vcpu_e500->idt;
+
+ BUG_ON(as >= 2);
+ BUG_ON(pid >= NUM_TIDS);
+ BUG_ON(pr >= 2);
+
+ idt->id[as][pid][pr].val = 0;
+ idt->id[as][pid][pr].pentry = NULL;
+
+ /* Update shadow pid when mappings are changed */
+ kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/*
+ * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
+ * This function first lookup if a valid mapping exists,
+ * if not, then creates a new one.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+ unsigned int as, unsigned int gid,
+ unsigned int pr, int avoid_recursion)
+{
+ struct vcpu_id_table *idt = vcpu_e500->idt;
+ int sid;
+
+ BUG_ON(as >= 2);
+ BUG_ON(gid >= NUM_TIDS);
+ BUG_ON(pr >= 2);
+
+ sid = local_sid_lookup(&idt->id[as][gid][pr]);
+
+ while (sid <= 0) {
+ /* No mapping yet */
+ sid = local_sid_setup_one(&idt->id[as][gid][pr]);
+ if (sid <= 0) {
+ _tlbil_all();
+ local_sid_destroy_all();
+ }
+
+ /* Update shadow pid when mappings are changed */
+ if (!avoid_recursion)
+ kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+ }
+
+ return sid;
+}
+
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+ struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+ return kvmppc_e500_get_sid(to_e500(vcpu), get_tlb_ts(gtlbe),
+ get_tlb_tid(gtlbe), get_cur_pr(vcpu), 0);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+ if (vcpu->arch.pid != pid) {
+ vcpu_e500->pid[0] = vcpu->arch.pid = pid;
+ kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+ }
+}
+
+/* gtlbe must not be mapped by more than one host tlbe */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+ struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+ struct vcpu_id_table *idt = vcpu_e500->idt;
+ unsigned int pr, tid, ts, pid;
+ u32 val, eaddr;
+ unsigned long flags;
+
+ ts = get_tlb_ts(gtlbe);
+ tid = get_tlb_tid(gtlbe);
+
+ preempt_disable();
+
+ /* One guest ID may be mapped to two shadow IDs */
+ for (pr = 0; pr < 2; pr++) {
+ /*
+ * The shadow PID can have a valid mapping on at most one
+ * host CPU. In the common case, it will be valid on this
+ * CPU, in which case we do a local invalidation of the
+ * specific address.
+ *
+ * If the shadow PID is not valid on the current host CPU,
+ * we invalidate the entire shadow PID.
+ */
+ pid = local_sid_lookup(&idt->id[ts][tid][pr]);
+ if (pid <= 0) {
+ kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
+ continue;
+ }
+
+ /*
+ * The guest is invalidating a 4K entry which is in a PID
+ * that has a valid shadow mapping on this host CPU. We
+ * search host TLB to invalidate it's shadow TLB entry,
+ * similar to __tlbil_va except that we need to look in AS1.
+ */
+ val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
+ eaddr = get_tlb_eaddr(gtlbe);
+
+ local_irq_save(flags);
+
+ mtspr(SPRN_MAS6, val);
+ asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
+ val = mfspr(SPRN_MAS1);
+ if (val & MAS1_VALID) {
+ mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+ asm volatile("tlbwe");
+ }
+
+ local_irq_restore(flags);
+ }
+
+ preempt_enable();
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ kvmppc_e500_id_table_reset_all(vcpu_e500);
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+ /* Recalc shadow pid since MSR changes */
+ kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
+}
+
void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
{
}
@@ -37,13 +308,13 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
kvmppc_booke_vcpu_load(vcpu, cpu);
- kvmppc_e500_tlb_load(vcpu, cpu);
+
+ /* Shadow PID may be expired on local core */
+ kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
}
void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
{
- kvmppc_e500_tlb_put(vcpu);
-
#ifdef CONFIG_SPE
if (vcpu->arch.shadow_msr & MSR_SPE)
kvmppc_vcpu_disable_spe(vcpu);
@@ -64,6 +335,23 @@ int kvmppc_core_check_processor_compat(void)
return r;
}
+static void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+ struct kvm_book3e_206_tlb_entry *tlbe;
+
+ /* Insert large initial mapping for guest. */
+ tlbe = get_entry(vcpu_e500, 1, 0);
+ tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
+ tlbe->mas2 = 0;
+ tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
+
+ /* 4K map for serial output. Used by kernel wrapper. */
+ tlbe = get_entry(vcpu_e500, 1, 1);
+ tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+ tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+ tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -79,32 +367,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
return 0;
}
-/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
-int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
- struct kvm_translation *tr)
-{
- int index;
- gva_t eaddr;
- u8 pid;
- u8 as;
-
- eaddr = tr->linear_address;
- pid = (tr->linear_address >> 32) & 0xff;
- as = (tr->linear_address >> 40) & 0x1;
-
- index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
- if (index < 0) {
- tr->valid = 0;
- return 0;
- }
-
- tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
- /* XXX what does "writeable" and "usermode" even mean? */
- tr->valid = 1;
-
- return 0;
-}
-
void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -118,19 +380,6 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
- sregs->u.e.mas0 = vcpu->arch.shared->mas0;
- sregs->u.e.mas1 = vcpu->arch.shared->mas1;
- sregs->u.e.mas2 = vcpu->arch.shared->mas2;
- sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
- sregs->u.e.mas4 = vcpu->arch.shared->mas4;
- sregs->u.e.mas6 = vcpu->arch.shared->mas6;
-
- sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
- sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
- sregs->u.e.tlbcfg[1] = vcpu_e500->tlb1cfg;
- sregs->u.e.tlbcfg[2] = 0;
- sregs->u.e.tlbcfg[3] = 0;
-
sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
@@ -138,11 +387,13 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
kvmppc_get_sregs_ivor(vcpu, sregs);
+ kvmppc_get_sregs_e500_tlb(vcpu, sregs);
}
int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ int ret;
if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
@@ -150,14 +401,9 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
}
- if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
- vcpu->arch.shared->mas0 = sregs->u.e.mas0;
- vcpu->arch.shared->mas1 = sregs->u.e.mas1;
- vcpu->arch.shared->mas2 = sregs->u.e.mas2;
- vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
- vcpu->arch.shared->mas4 = sregs->u.e.mas4;
- vcpu->arch.shared->mas6 = sregs->u.e.mas6;
- }
+ ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+ if (ret < 0)
+ return ret;
if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
return 0;
@@ -196,9 +442,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
if (err)
goto free_vcpu;
+ if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+ goto uninit_vcpu;
+
err = kvmppc_e500_tlb_init(vcpu_e500);
if (err)
- goto uninit_vcpu;
+ goto uninit_id;
vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
if (!vcpu->arch.shared)
@@ -208,6 +457,8 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
uninit_tlb:
kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_id:
+ kvmppc_e500_id_table_free(vcpu_e500);
uninit_vcpu:
kvm_vcpu_uninit(vcpu);
free_vcpu:
@@ -221,8 +472,9 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
free_page((unsigned long)vcpu->arch.shared);
- kvm_vcpu_uninit(vcpu);
kvmppc_e500_tlb_uninit(vcpu_e500);
+ kvmppc_e500_id_table_free(vcpu_e500);
+ kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
}
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 6b53a88..34cef08 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -35,7 +35,9 @@ struct tlbe_priv {
struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
};
+#ifdef CONFIG_KVM_E500
struct vcpu_id_table;
+#endif
struct kvmppc_e500_tlb_params {
int entries, ways, sets;
@@ -70,20 +72,22 @@ struct kvmppc_vcpu_e500 {
struct tlbe_ref *tlb_refs[E500_TLB_NUM];
unsigned int host_tlb1_nv;
- u32 host_pid[E500_PID_NUM];
- u32 pid[E500_PID_NUM];
u32 svr;
-
u32 l1csr0;
u32 l1csr1;
u32 hid0;
u32 hid1;
- u32 tlb0cfg;
- u32 tlb1cfg;
u64 mcar;
struct page **shared_tlb_pages;
int num_shared_tlb_pages;
+
+#ifdef CONFIG_KVM_E500
+ u32 pid[E500_PID_NUM];
+
+ /* vcpu id table */
+ struct vcpu_id_table *idt;
+#endif
};
static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
@@ -116,13 +120,19 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu);
int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu);
int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb);
int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb);
-int kvmppc_e500_tlb_search(struct kvm_vcpu *, gva_t, unsigned int, int);
int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500);
void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+
+#ifdef CONFIG_KVM_E500
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+ unsigned int as, unsigned int gid,
+ unsigned int pr, int avoid_recursion);
+#endif
+
/* TLB helper functions */
static inline unsigned int
get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
@@ -176,6 +186,12 @@ get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
return (tlbe->mas1 >> 30) & 0x1;
}
+static inline unsigned int
+get_tlb_tsize(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+ return (tlbe->mas1 & MAS1_TSIZE_MASK) >> MAS1_TSIZE_SHIFT;
+}
+
static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
{
return vcpu->arch.pid & 0xff;
@@ -241,4 +257,31 @@ static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
return 1;
}
+static inline struct kvm_book3e_206_tlb_entry *get_entry(
+ struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
+{
+ int offset = vcpu_e500->gtlb_offset[tlbsel];
+ return &vcpu_e500->gtlb_arch[offset + entry];
+}
+
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+ struct kvm_book3e_206_tlb_entry *gtlbe);
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500);
+
+#ifdef CONFIG_KVM_E500
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+ struct kvm_book3e_206_tlb_entry *gtlbe);
+
+static inline unsigned int get_tlbmiss_tid(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ unsigned int tidseld = (vcpu->arch.shared->mas4 >> 16) & 0xf;
+
+ return vcpu_e500->pid[tidseld];
+}
+
+/* Force TS=1 for all guest mappings. */
+#define get_tlb_sts(gtlbe) (MAS1_TS)
+#endif /* CONFIG_KVM_E500 */
+
#endif /* KVM_E500_H */
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 2a1a228..c80794d 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -14,7 +14,6 @@
#include <asm/kvm_ppc.h>
#include <asm/disassemble.h>
-#include <asm/kvm_e500.h>
#include "booke.h"
#include "e500.h"
@@ -175,9 +174,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
kvmppc_set_gpr(vcpu, rt, val);
break;
case SPRN_TLB0CFG:
- kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[0]); break;
case SPRN_TLB1CFG:
- kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb1cfg); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.tlbcfg[1]); break;
case SPRN_L1CSR0:
kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
case SPRN_L1CSR1:
@@ -193,7 +192,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
kvmppc_set_gpr(vcpu, rt, 0); break;
case SPRN_MMUCFG:
- kvmppc_set_gpr(vcpu, rt, mfspr(SPRN_MMUCFG)); break;
+ kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucfg); break;
/* extra exceptions */
case SPRN_IVOR32:
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 3ec3ad6..b306270 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -26,210 +26,15 @@
#include <linux/vmalloc.h>
#include <linux/hugetlb.h>
#include <asm/kvm_ppc.h>
-#include <asm/kvm_e500.h>
-#include "../mm/mmu_decl.h"
#include "e500.h"
#include "trace.h"
#include "timing.h"
#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
-struct id {
- unsigned long val;
- struct id **pentry;
-};
-
-#define NUM_TIDS 256
-
-/*
- * This table provide mappings from:
- * (guestAS,guestTID,guestPR) --> ID of physical cpu
- * guestAS [0..1]
- * guestTID [0..255]
- * guestPR [0..1]
- * ID [1..255]
- * Each vcpu keeps one vcpu_id_table.
- */
-struct vcpu_id_table {
- struct id id[2][NUM_TIDS][2];
-};
-
-/*
- * This table provide reversed mappings of vcpu_id_table:
- * ID --> address of vcpu_id_table item.
- * Each physical core has one pcpu_id_table.
- */
-struct pcpu_id_table {
- struct id *entry[NUM_TIDS];
-};
-
-static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
-
-/* This variable keeps last used shadow ID on local core.
- * The valid range of shadow ID is [1..255] */
-static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
-
static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
-static struct kvm_book3e_206_tlb_entry *get_entry(
- struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
-{
- int offset = vcpu_e500->gtlb_offset[tlbsel];
- return &vcpu_e500->gtlb_arch[offset + entry];
-}
-
-/*
- * Allocate a free shadow id and setup a valid sid mapping in given entry.
- * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static inline int local_sid_setup_one(struct id *entry)
-{
- unsigned long sid;
- int ret = -1;
-
- sid = ++(__get_cpu_var(pcpu_last_used_sid));
- if (sid < NUM_TIDS) {
- __get_cpu_var(pcpu_sids).entry[sid] = entry;
- entry->val = sid;
- entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
- ret = sid;
- }
-
- /*
- * If sid == NUM_TIDS, we've run out of sids. We return -1, and
- * the caller will invalidate everything and start over.
- *
- * sid > NUM_TIDS indicates a race, which we disable preemption to
- * avoid.
- */
- WARN_ON(sid > NUM_TIDS);
-
- return ret;
-}
-
-/*
- * Check if given entry contain a valid shadow id mapping.
- * An ID mapping is considered valid only if
- * both vcpu and pcpu know this mapping.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static inline int local_sid_lookup(struct id *entry)
-{
- if (entry && entry->val != 0 &&
- __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
- entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
- return entry->val;
- return -1;
-}
-
-/* Invalidate all id mappings on local core -- call with preempt disabled */
-static inline void local_sid_destroy_all(void)
-{
- __get_cpu_var(pcpu_last_used_sid) = 0;
- memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
-}
-
-static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
- vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
- return vcpu_e500->idt;
-}
-
-static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
- kfree(vcpu_e500->idt);
-}
-
-/* Invalidate all mappings on vcpu */
-static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
- memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
-
- /* Update shadow pid when mappings are changed */
- kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-/* Invalidate one ID mapping on vcpu */
-static inline void kvmppc_e500_id_table_reset_one(
- struct kvmppc_vcpu_e500 *vcpu_e500,
- int as, int pid, int pr)
-{
- struct vcpu_id_table *idt = vcpu_e500->idt;
-
- BUG_ON(as >= 2);
- BUG_ON(pid >= NUM_TIDS);
- BUG_ON(pr >= 2);
-
- idt->id[as][pid][pr].val = 0;
- idt->id[as][pid][pr].pentry = NULL;
-
- /* Update shadow pid when mappings are changed */
- kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-/*
- * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
- * This function first lookup if a valid mapping exists,
- * if not, then creates a new one.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
- unsigned int as, unsigned int gid,
- unsigned int pr, int avoid_recursion)
-{
- struct vcpu_id_table *idt = vcpu_e500->idt;
- int sid;
-
- BUG_ON(as >= 2);
- BUG_ON(gid >= NUM_TIDS);
- BUG_ON(pr >= 2);
-
- sid = local_sid_lookup(&idt->id[as][gid][pr]);
-
- while (sid <= 0) {
- /* No mapping yet */
- sid = local_sid_setup_one(&idt->id[as][gid][pr]);
- if (sid <= 0) {
- _tlbil_all();
- local_sid_destroy_all();
- }
-
- /* Update shadow pid when mappings are changed */
- if (!avoid_recursion)
- kvmppc_e500_recalc_shadow_pid(vcpu_e500);
- }
-
- return sid;
-}
-
-/* Map guest pid to shadow.
- * We use PID to keep shadow of current guest non-zero PID,
- * and use PID1 to keep shadow of guest zero PID.
- * So that guest tlbe with TID=0 can be accessed at any time */
-void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
- preempt_disable();
- vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
- get_cur_as(&vcpu_e500->vcpu),
- get_cur_pid(&vcpu_e500->vcpu),
- get_cur_pr(&vcpu_e500->vcpu), 1);
- vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
- get_cur_as(&vcpu_e500->vcpu), 0,
- get_cur_pr(&vcpu_e500->vcpu), 1);
- preempt_enable();
-}
-
static inline unsigned int gtlb0_get_next_victim(
struct kvmppc_vcpu_e500 *vcpu_e500)
{
@@ -337,6 +142,7 @@ static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
}
}
+#ifdef CONFIG_KVM_E500
void kvmppc_map_magic(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -361,75 +167,21 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu)
__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
preempt_enable();
}
-
-void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
-{
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
- /* Shadow PID may be expired on local core */
- kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
-{
-}
+#endif
static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
{
struct kvm_book3e_206_tlb_entry *gtlbe =
get_entry(vcpu_e500, tlbsel, esel);
- struct vcpu_id_table *idt = vcpu_e500->idt;
- unsigned int pr, tid, ts, pid;
- u32 val, eaddr;
- unsigned long flags;
- ts = get_tlb_ts(gtlbe);
- tid = get_tlb_tid(gtlbe);
-
- preempt_disable();
-
- /* One guest ID may be mapped to two shadow IDs */
- for (pr = 0; pr < 2; pr++) {
- /*
- * The shadow PID can have a valid mapping on at most one
- * host CPU. In the common case, it will be valid on this
- * CPU, in which case (for TLB0) we do a local invalidation
- * of the specific address.
- *
- * If the shadow PID is not valid on the current host CPU, or
- * if we're invalidating a TLB1 entry, we invalidate the
- * entire shadow PID.
- */
- if (tlbsel == 1 ||
- (pid = local_sid_lookup(&idt->id[ts][tid][pr])) <= 0) {
- kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
- continue;
- }
-
- /*
- * The guest is invalidating a TLB0 entry which is in a PID
- * that has a valid shadow mapping on this host CPU. We
- * search host TLB0 to invalidate it's shadow TLB entry,
- * similar to __tlbil_va except that we need to look in AS1.
- */
- val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
- eaddr = get_tlb_eaddr(gtlbe);
-
- local_irq_save(flags);
-
- mtspr(SPRN_MAS6, val);
- asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
- val = mfspr(SPRN_MAS1);
- if (val & MAS1_VALID) {
- mtspr(SPRN_MAS1, val & ~MAS1_VALID);
- asm volatile("tlbwe");
- }
-
- local_irq_restore(flags);
+ if (tlbsel == 1) {
+ kvmppc_e500_tlbil_all(vcpu_e500);
+ return;
}
- preempt_enable();
+ /* Guest tlbe is backed by at most one host tlbe per shadow pid. */
+ kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
}
static int tlb0_set_base(gva_t addr, int sets, int ways)
@@ -547,7 +299,7 @@ static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
int stlbsel = 1;
int i;
- kvmppc_e500_id_table_reset_all(vcpu_e500);
+ kvmppc_e500_tlbil_all(vcpu_e500);
for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
struct tlbe_ref *ref =
@@ -562,19 +314,18 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
unsigned int eaddr, int as)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- unsigned int victim, pidsel, tsized;
+ unsigned int victim, tsized;
int tlbsel;
/* since we only have two TLBs, only lower bit is used. */
tlbsel = (vcpu->arch.shared->mas4 >> 28) & 0x1;
victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
- pidsel = (vcpu->arch.shared->mas4 >> 16) & 0xf;
tsized = (vcpu->arch.shared->mas4 >> 7) & 0x1f;
vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
vcpu->arch.shared->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
- | MAS1_TID(vcpu_e500->pid[pidsel])
+ | MAS1_TID(get_tlbmiss_tid(vcpu))
| MAS1_TSIZE(tsized);
vcpu->arch.shared->mas2 = (eaddr & MAS2_EPN)
| (vcpu->arch.shared->mas4 & MAS2_ATTRIB_MASK);
@@ -586,23 +337,22 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
/* TID must be supplied by the caller */
static inline void kvmppc_e500_setup_stlbe(
- struct kvmppc_vcpu_e500 *vcpu_e500,
+ struct kvm_vcpu *vcpu,
struct kvm_book3e_206_tlb_entry *gtlbe,
int tsize, struct tlbe_ref *ref, u64 gvaddr,
struct kvm_book3e_206_tlb_entry *stlbe)
{
pfn_t pfn = ref->pfn;
+ u32 pr = vcpu->arch.shared->msr & MSR_PR;
BUG_ON(!(ref->flags & E500_TLB_VALID));
- /* Force TS=1 IPROT=0 for all guest mappings. */
- stlbe->mas1 = MAS1_TSIZE(tsize) | MAS1_TS | MAS1_VALID;
- stlbe->mas2 = (gvaddr & MAS2_EPN)
- | e500_shadow_mas2_attrib(gtlbe->mas2,
- vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
- stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT)
- | e500_shadow_mas3_attrib(gtlbe->mas7_3,
- vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
+ /* Force IPROT=0 for all guest mappings. */
+ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
+ stlbe->mas2 = (gvaddr & MAS2_EPN) |
+ e500_shadow_mas2_attrib(gtlbe->mas2, pr);
+ stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+ e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
}
static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -736,7 +486,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
kvmppc_e500_ref_release(ref);
kvmppc_e500_ref_setup(ref, gtlbe, pfn);
- kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, ref, gvaddr, stlbe);
+ kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
+ ref, gvaddr, stlbe);
}
/* XXX only map the one-one case, for now use TLB0 */
@@ -776,14 +527,6 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
return victim;
}
-void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
-{
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
- /* Recalc shadow pid since MSR changes */
- kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
static inline int kvmppc_e500_gtlbe_invalidate(
struct kvmppc_vcpu_e500 *vcpu_e500,
int tlbsel, int esel)
@@ -811,7 +554,7 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
/* Invalidate all vcpu id mappings */
- kvmppc_e500_id_table_reset_all(vcpu_e500);
+ kvmppc_e500_tlbil_all(vcpu_e500);
return EMULATE_DONE;
}
@@ -844,7 +587,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
}
/* Invalidate all vcpu id mappings */
- kvmppc_e500_id_table_reset_all(vcpu_e500);
+ kvmppc_e500_tlbil_all(vcpu_e500);
return EMULATE_DONE;
}
@@ -929,9 +672,7 @@ static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
int stid;
preempt_disable();
- stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
- get_tlb_tid(gtlbe),
- get_cur_pr(&vcpu_e500->vcpu), 0);
+ stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
stlbe->mas1 |= MAS1_TID(stid);
write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
@@ -941,8 +682,8 @@ static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- struct kvm_book3e_206_tlb_entry *gtlbe;
- int tlbsel, esel;
+ struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
+ int tlbsel, esel, stlbsel, sesel;
tlbsel = get_tlb_tlbsel(vcpu);
esel = get_tlb_esel(vcpu, tlbsel);
@@ -961,8 +702,6 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
if (tlbe_is_host_safe(vcpu, gtlbe)) {
- struct kvm_book3e_206_tlb_entry stlbe;
- int stlbsel, sesel;
u64 eaddr;
u64 raddr;
@@ -989,7 +728,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
* are mapped on the fly. */
stlbsel = 1;
sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
- raddr >> PAGE_SHIFT, gtlbe, &stlbe);
+ raddr >> PAGE_SHIFT, gtlbe, &stlbe);
break;
default:
@@ -1003,6 +742,48 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
return EMULATE_DONE;
}
+static int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
+ gva_t eaddr, unsigned int pid, int as)
+{
+ struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ int esel, tlbsel;
+
+ for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+ esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
+ if (esel >= 0)
+ return index_of(tlbsel, esel);
+ }
+
+ return -1;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr)
+{
+ int index;
+ gva_t eaddr;
+ u8 pid;
+ u8 as;
+
+ eaddr = tr->linear_address;
+ pid = (tr->linear_address >> 32) & 0xff;
+ as = (tr->linear_address >> 40) & 0x1;
+
+ index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
+ if (index < 0) {
+ tr->valid = 0;
+ return 0;
+ }
+
+ tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
+ /* XXX what does "writeable" and "usermode" even mean? */
+ tr->valid = 1;
+
+ return 0;
+}
+
+
int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
{
unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
@@ -1066,7 +847,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
sesel = 0; /* unused */
priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
- kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K,
+ kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
&priv->ref, eaddr, &stlbe);
break;
@@ -1087,48 +868,6 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
}
-int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
- gva_t eaddr, unsigned int pid, int as)
-{
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- int esel, tlbsel;
-
- for (tlbsel = 0; tlbsel < 2; tlbsel++) {
- esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
- if (esel >= 0)
- return index_of(tlbsel, esel);
- }
-
- return -1;
-}
-
-void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
-{
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
- if (vcpu->arch.pid != pid) {
- vcpu_e500->pid[0] = vcpu->arch.pid = pid;
- kvmppc_e500_recalc_shadow_pid(vcpu_e500);
- }
-}
-
-void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
- struct kvm_book3e_206_tlb_entry *tlbe;
-
- /* Insert large initial mapping for guest. */
- tlbe = get_entry(vcpu_e500, 1, 0);
- tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
- tlbe->mas2 = 0;
- tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
-
- /* 4K map for serial output. Used by kernel wrapper. */
- tlbe = get_entry(vcpu_e500, 1, 1);
- tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
- tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
- tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
-}
-
static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
{
int i;
@@ -1155,6 +894,36 @@ static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
vcpu_e500->gtlb_arch = NULL;
}
+void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ sregs->u.e.mas0 = vcpu->arch.shared->mas0;
+ sregs->u.e.mas1 = vcpu->arch.shared->mas1;
+ sregs->u.e.mas2 = vcpu->arch.shared->mas2;
+ sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
+ sregs->u.e.mas4 = vcpu->arch.shared->mas4;
+ sregs->u.e.mas6 = vcpu->arch.shared->mas6;
+
+ sregs->u.e.mmucfg = vcpu->arch.mmucfg;
+ sregs->u.e.tlbcfg[0] = vcpu->arch.tlbcfg[0];
+ sregs->u.e.tlbcfg[1] = vcpu->arch.tlbcfg[1];
+ sregs->u.e.tlbcfg[2] = 0;
+ sregs->u.e.tlbcfg[3] = 0;
+}
+
+int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+ if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
+ vcpu->arch.shared->mas0 = sregs->u.e.mas0;
+ vcpu->arch.shared->mas1 = sregs->u.e.mas1;
+ vcpu->arch.shared->mas2 = sregs->u.e.mas2;
+ vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
+ vcpu->arch.shared->mas4 = sregs->u.e.mas4;
+ vcpu->arch.shared->mas6 = sregs->u.e.mas6;
+ }
+
+ return 0;
+}
+
int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
struct kvm_config_tlb *cfg)
{
@@ -1238,14 +1007,16 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
vcpu_e500->gtlb_offset[0] = 0;
vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0];
- vcpu_e500->tlb0cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+ vcpu->arch.mmucfg = mfspr(SPRN_MMUCFG) & ~MMUCFG_LPIDSIZE;
+
+ vcpu->arch.tlbcfg[0] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
if (params.tlb_sizes[0] <= 2048)
- vcpu_e500->tlb0cfg |= params.tlb_sizes[0];
- vcpu_e500->tlb0cfg |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
+ vcpu->arch.tlbcfg[0] |= params.tlb_sizes[0];
+ vcpu->arch.tlbcfg[0] |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
- vcpu_e500->tlb1cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
- vcpu_e500->tlb1cfg |= params.tlb_sizes[1];
- vcpu_e500->tlb1cfg |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
+ vcpu->arch.tlbcfg[1] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+ vcpu->arch.tlbcfg[1] |= params.tlb_sizes[1];
+ vcpu->arch.tlbcfg[1] |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
vcpu_e500->shared_tlb_pages = pages;
vcpu_e500->num_shared_tlb_pages = num_pages;
@@ -1281,6 +1052,7 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
{
+ struct kvm_vcpu *vcpu = &vcpu_e500->vcpu;
int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
@@ -1357,20 +1129,17 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
if (!vcpu_e500->gtlb_priv[1])
goto err;
- if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
- goto err;
-
/* Init TLB configuration register */
- vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) &
+ vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) &
~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
- vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[0].entries;
- vcpu_e500->tlb0cfg |=
+ vcpu->arch.tlbcfg[0] |= vcpu_e500->gtlb_params[0].entries;
+ vcpu->arch.tlbcfg[0] |=
vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT;
- vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) &
+ vcpu->arch.tlbcfg[1] = mfspr(SPRN_TLB1CFG) &
~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
- vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[1].entries;
- vcpu_e500->tlb0cfg |=
+ vcpu->arch.tlbcfg[0] |= vcpu_e500->gtlb_params[1].entries;
+ vcpu->arch.tlbcfg[0] |=
vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;
return 0;
@@ -1385,8 +1154,6 @@ err:
void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
{
free_gtlb(vcpu_e500);
- kvmppc_e500_id_table_free(vcpu_e500);
-
kfree(vcpu_e500->tlb_refs[0]);
kfree(vcpu_e500->tlb_refs[1]);
}
--
1.7.7.rc3.4.g8d714
^ 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