summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/powerpc/Kconfig5
-rw-r--r--arch/powerpc/Kconfig.debug8
-rw-r--r--arch/powerpc/boot/Makefile2
-rw-r--r--arch/powerpc/boot/dts/hcu4.dts168
-rw-r--r--arch/powerpc/boot/dts/yosemite.dts36
-rw-r--r--arch/powerpc/configs/40x/hcu4_defconfig80
-rw-r--r--arch/powerpc/configs/ppc40x_defconfig1
-rw-r--r--arch/powerpc/include/asm/device.h2
-rw-r--r--arch/powerpc/include/asm/hugetlb.h63
-rw-r--r--arch/powerpc/include/asm/kexec.h2
-rw-r--r--arch/powerpc/include/asm/machdep.h3
-rw-r--r--arch/powerpc/include/asm/mmu-book3e.h7
-rw-r--r--arch/powerpc/include/asm/mmu-hash64.h3
-rw-r--r--arch/powerpc/include/asm/mmu.h18
-rw-r--r--arch/powerpc/include/asm/mpic.h2
-rw-r--r--arch/powerpc/include/asm/page.h31
-rw-r--r--arch/powerpc/include/asm/page_64.h11
-rw-r--r--arch/powerpc/include/asm/pte-book3e.h3
-rw-r--r--arch/powerpc/include/asm/rtas.h6
-rw-r--r--arch/powerpc/include/asm/udbg.h1
-rw-r--r--arch/powerpc/kernel/dma-iommu.c28
-rw-r--r--arch/powerpc/kernel/dma-swiotlb.c16
-rw-r--r--arch/powerpc/kernel/dma.c44
-rw-r--r--arch/powerpc/kernel/head_32.S7
-rw-r--r--arch/powerpc/kernel/head_40x.S15
-rw-r--r--arch/powerpc/kernel/head_44x.S16
-rw-r--r--arch/powerpc/kernel/head_8xx.S13
-rw-r--r--arch/powerpc/kernel/head_fsl_booke.S175
-rw-r--r--arch/powerpc/kernel/ibmebus.c22
-rw-r--r--arch/powerpc/kernel/legacy_serial.c25
-rw-r--r--arch/powerpc/kernel/misc_32.S171
-rw-r--r--arch/powerpc/kernel/setup_32.c2
-rw-r--r--arch/powerpc/kernel/swsusp.c2
-rw-r--r--arch/powerpc/kernel/udbg.c2
-rw-r--r--arch/powerpc/kernel/vio.c21
-rw-r--r--arch/powerpc/mm/Makefile1
-rw-r--r--arch/powerpc/mm/hash_utils_64.c3
-rw-r--r--arch/powerpc/mm/hugetlbpage-book3e.c121
-rw-r--r--arch/powerpc/mm/hugetlbpage.c379
-rw-r--r--arch/powerpc/mm/init_32.c9
-rw-r--r--arch/powerpc/mm/mem.c5
-rw-r--r--arch/powerpc/mm/mmu_context_nohash.c5
-rw-r--r--arch/powerpc/mm/pgtable.c3
-rw-r--r--arch/powerpc/mm/tlb_low_64e.S24
-rw-r--r--arch/powerpc/mm/tlb_nohash.c46
-rw-r--r--arch/powerpc/platforms/40x/Kconfig8
-rw-r--r--arch/powerpc/platforms/40x/Makefile1
-rw-r--r--arch/powerpc/platforms/40x/hcu4.c61
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype4
-rw-r--r--arch/powerpc/platforms/cell/iommu.c21
-rw-r--r--arch/powerpc/platforms/ps3/Kconfig12
-rw-r--r--arch/powerpc/platforms/ps3/Makefile1
-rw-r--r--arch/powerpc/platforms/ps3/gelic_udbg.c273
-rw-r--r--arch/powerpc/platforms/ps3/system-bus.c7
-rw-r--r--arch/powerpc/platforms/pseries/Kconfig1
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c4
-rw-r--r--arch/powerpc/platforms/pseries/eeh.c2
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c34
-rw-r--r--arch/powerpc/platforms/pseries/nvram.c171
-rw-r--r--arch/powerpc/platforms/wsp/Kconfig11
-rw-r--r--arch/powerpc/platforms/wsp/Makefile2
-rw-r--r--arch/powerpc/platforms/wsp/ics.c48
-rw-r--r--arch/powerpc/platforms/wsp/ics.h5
-rw-r--r--arch/powerpc/platforms/wsp/msi.c102
-rw-r--r--arch/powerpc/platforms/wsp/msi.h19
-rw-r--r--arch/powerpc/platforms/wsp/psr2.c4
-rw-r--r--arch/powerpc/platforms/wsp/wsp.h3
-rw-r--r--arch/powerpc/platforms/wsp/wsp_pci.c1133
-rw-r--r--arch/powerpc/platforms/wsp/wsp_pci.h268
-rw-r--r--arch/powerpc/sysdev/mpic.c24
-rw-r--r--arch/powerpc/sysdev/ppc4xx_pci.c101
-rw-r--r--arch/powerpc/sysdev/ppc4xx_pci.h12
-rw-r--r--arch/powerpc/sysdev/xics/icp-native.c2
-rw-r--r--drivers/edac/cpc925_edac.c67
-rw-r--r--drivers/edac/ppc4xx_edac.c2
-rw-r--r--drivers/net/ps3_gelic_net.c3
-rw-r--r--drivers/net/ps3_gelic_net.h6
-rw-r--r--drivers/tty/serial/8250.c23
-rw-r--r--include/linux/dma-mapping.h3
79 files changed, 3451 insertions, 594 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6926b61acfe..62711421cd6 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -345,7 +345,7 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
config KEXEC
bool "kexec system call (EXPERIMENTAL)"
- depends on (PPC_BOOK3S || FSL_BOOKE) && EXPERIMENTAL
+ depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !47x)) && EXPERIMENTAL
help
kexec is a system call that implements the ability to shutdown your
current kernel, and to start another kernel. It is like a reboot
@@ -429,8 +429,7 @@ config ARCH_POPULATES_NODE_MAP
def_bool y
config SYS_SUPPORTS_HUGETLBFS
- def_bool y
- depends on PPC_BOOK3S_64
+ bool
source "mm/Kconfig"
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 067cb848074..ab2335f160a 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -258,6 +258,14 @@ config PPC_EARLY_DEBUG_WSP
depends on PPC_WSP
select PPC_UDBG_16550
+config PPC_EARLY_DEBUG_PS3GELIC
+ bool "Early debugging through the PS3 Ethernet port"
+ depends on PPC_PS3
+ select PS3GELIC_UDBG
+ help
+ Select this to enable early debugging for the PlayStation3 via
+ UDP broadcasts sent out through the Ethernet port.
+
endchoice
config PPC_EARLY_DEBUG_HVSI_VTERMNO
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index c26200b40a4..ac6705e7571 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -58,7 +58,7 @@ $(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o prpmc2800.o): \
libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
libfdtheader := fdt.h libfdt.h libfdt_internal.h
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o): \
$(addprefix $(obj)/,$(libfdtheader))
src-wlib := string.S crt0.S crtsavres.S stdio.c main.c \
diff --git a/arch/powerpc/boot/dts/hcu4.dts b/arch/powerpc/boot/dts/hcu4.dts
deleted file mode 100644
index 7988598da4c..00000000000
--- a/arch/powerpc/boot/dts/hcu4.dts
+++ /dev/null
@@ -1,168 +0,0 @@
-/*
-* Device Tree Source for Netstal Maschinen HCU4
-* based on the IBM Walnut
-*
-* Copyright 2008
-* Niklaus Giger <niklaus.giger@member.fsf.org>
-*
-* Copyright 2007 IBM Corp.
-* Josh Boyer <jwboyer@linux.vnet.ibm.com>
-*
-* This file is licensed under the terms of the GNU General Public
-* License version 2. This program is licensed "as is" without
-* any warranty of any kind, whether express or implied.
-*/
-
-/dts-v1/;
-
-/ {
- #address-cells = <0x1>;
- #size-cells = <0x1>;
- model = "netstal,hcu4";
- compatible = "netstal,hcu4";
- dcr-parent = <0x1>;
-
- aliases {
- ethernet0 = "/plb/opb/ethernet@ef600800";
- serial0 = "/plb/opb/serial@ef600300";
- };
-
- cpus {
- #address-cells = <0x1>;
- #size-cells = <0x0>;
-
- cpu@0 {
- device_type = "cpu";
- model = "PowerPC,405GPr";
- reg = <0x0>;
- clock-frequency = <0>; /* Filled in by U-Boot */
- timebase-frequency = <0x0>; /* Filled in by U-Boot */
- i-cache-line-size = <0x20>;
- d-cache-line-size = <0x20>;
- i-cache-size = <0x4000>;
- d-cache-size = <0x4000>;
- dcr-controller;
- dcr-access-method = "native";
- linux,phandle = <0x1>;
- };
- };
-
- memory {
- device_type = "memory";
- reg = <0x0 0x0>; /* Filled in by U-Boot */
- };
-
- UIC0: interrupt-controller {
- compatible = "ibm,uic";
- interrupt-controller;
- cell-index = <0x0>;
- dcr-reg = <0xc0 0x9>;
- #address-cells = <0x0>;
- #size-cells = <0x0>;
- #interrupt-cells = <0x2>;
- linux,phandle = <0x2>;
- };
-
- plb {
- compatible = "ibm,plb3";
- #address-cells = <0x1>;
- #size-cells = <0x1>;
- ranges;
- clock-frequency = <0x0>; /* Filled in by U-Boot */
-
- SDRAM0: memory-controller {
- compatible = "ibm,sdram-405gp";
- dcr-reg = <0x10 0x2>;
- };
-
- MAL: mcmal {
- compatible = "ibm,mcmal-405gp", "ibm,mcmal";
- dcr-reg = <0x180 0x62>;
- num-tx-chans = <0x1>;
- num-rx-chans = <0x1>;
- interrupt-parent = <0x2>;
- interrupts = <0xb 0x4 0xc 0x4 0xa 0x4 0xd 0x4 0xe 0x4>;
- linux,phandle = <0x3>;
- };
-
- POB0: opb {
- compatible = "ibm,opb-405gp", "ibm,opb";
- #address-cells = <0x1>;
- #size-cells = <0x1>;
- ranges = <0xef600000 0xef600000 0xa00000>;
- dcr-reg = <0xa0 0x5>;
- clock-frequency = <0x0>; /* Filled in by U-Boot */
-
- UART0: serial@ef600300 {
- device_type = "serial";
- compatible = "ns16550";
- reg = <0xef600300 0x8>;
- virtual-reg = <0xef600300>;
- clock-frequency = <0x0>;/* Filled in by U-Boot */
- current-speed = <0>; /* Filled in by U-Boot */
- interrupt-parent = <0x2>;
- interrupts = <0x0 0x4>;
- };
-
- IIC: i2c@ef600500 {
- compatible = "ibm,iic-405gp", "ibm,iic";
- reg = <0xef600500 0x11>;
- interrupt-parent = <0x2>;
- interrupts = <0x2 0x4>;
- };
-
- GPIO: gpio@ef600700 {
- compatible = "ibm,gpio-405gp";
- reg = <0xef600700 0x20>;
- };
-
- EMAC: ethernet@ef600800 {
- device_type = "network";
- compatible = "ibm,emac-405gp", "ibm,emac";
- interrupt-parent = <0x2>;
- interrupts = <0xf 0x4 0x9 0x4>;
- local-mac-address = [00 00 00 00 00 00];
- reg = <0xef600800 0x70>;
- mal-device = <0x3>;
- mal-tx-channel = <0x0>;
- mal-rx-channel = <0x0>;
- cell-index = <0x0>;
- max-frame-size = <0x5dc>;
- rx-fifo-size = <0x1000>;
- tx-fifo-size = <0x800>;
- phy-mode = "rmii";
- phy-map = <0x1>;
- };
- };
-
- EBC0: ebc {
- compatible = "ibm,ebc-405gp", "ibm,ebc";
- dcr-reg = <0x12 0x2>;
- #address-cells = <0x2>;
- #size-cells = <0x1>;
- clock-frequency = <0x0>; /* Filled in by U-Boot */
-
- sram@0,0 {
- reg = <0x0 0x0 0x80000>;
- };
-
- flash@0,80000 {
- compatible = "jedec-flash";
- bank-width = <0x1>;
- reg = <0x0 0x80000 0x80000>;
- #address-cells = <0x1>;
- #size-cells = <0x1>;
-
- partition@0 {
- label = "OpenBIOS";
- reg = <0x0 0x80000>;
- read-only;
- };
- };
- };
- };
-
- chosen {
- linux,stdout-path = "/plb/opb/serial@ef600300";
- };
-};
diff --git a/arch/powerpc/boot/dts/yosemite.dts b/arch/powerpc/boot/dts/yosemite.dts
index 64923245f0e..30bb4753577 100644
--- a/arch/powerpc/boot/dts/yosemite.dts
+++ b/arch/powerpc/boot/dts/yosemite.dts
@@ -138,6 +138,42 @@
clock-frequency = <0>; /* Filled in by zImage */
interrupts = <0x5 0x1>;
interrupt-parent = <&UIC1>;
+
+ nor_flash@0,0 {
+ compatible = "amd,s29gl256n", "cfi-flash";
+ bank-width = <2>;
+ reg = <0x00000000 0x00000000 0x04000000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ partition@0 {
+ label = "kernel";
+ reg = <0x00000000 0x001e0000>;
+ };
+ partition@1e0000 {
+ label = "dtb";
+ reg = <0x001e0000 0x00020000>;
+ };
+ partition@200000 {
+ label = "ramdisk";
+ reg = <0x00200000 0x01400000>;
+ };
+ partition@1600000 {
+ label = "jffs2";
+ reg = <0x01600000 0x00400000>;
+ };
+ partition@1a00000 {
+ label = "user";
+ reg = <0x01a00000 0x02540000>;
+ };
+ partition@3f40000 {
+ label = "env";
+ reg = <0x03f40000 0x00040000>;
+ };
+ partition@3f80000 {
+ label = "u-boot";
+ reg = <0x03f80000 0x00080000>;
+ };
+ };
};
UART0: serial@ef600300 {
diff --git a/arch/powerpc/configs/40x/hcu4_defconfig b/arch/powerpc/configs/40x/hcu4_defconfig
deleted file mode 100644
index ebeb4accad6..00000000000
--- a/arch/powerpc/configs/40x/hcu4_defconfig
+++ /dev/null
@@ -1,80 +0,0 @@
-CONFIG_40x=y
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_HCU4=y
-# CONFIG_WALNUT is not set
-CONFIG_SPARSE_IRQ=y
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_OF_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_PROC_DEVICETREE=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_VIDEO_OUTPUT_CONTROL=m
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_ROOT_NFS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DETECT_HUNG_TASK=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
index bfd634b5ada..e9d920c5a87 100644
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ b/arch/powerpc/configs/ppc40x_defconfig
@@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y
CONFIG_PPC4xx_GPIO=y
CONFIG_ACADIA=y
CONFIG_EP405=y
-CONFIG_HCU4=y
CONFIG_HOTFOOT=y
CONFIG_KILAUEA=y
CONFIG_MAKALU=y
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 16d25c0974b..d57c08acedf 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -37,4 +37,6 @@ struct pdev_archdata {
u64 dma_mask;
};
+#define ARCH_HAS_DMA_GET_REQUIRED_MASK
+
#endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 5856a66ab40..86004930a78 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -1,15 +1,60 @@
#ifndef _ASM_POWERPC_HUGETLB_H
#define _ASM_POWERPC_HUGETLB_H
+#ifdef CONFIG_HUGETLB_PAGE
#include <asm/page.h>
+extern struct kmem_cache *hugepte_cache;
+extern void __init reserve_hugetlb_gpages(void);
+
+static inline pte_t *hugepd_page(hugepd_t hpd)
+{
+ BUG_ON(!hugepd_ok(hpd));
+ return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
+}
+
+static inline unsigned int hugepd_shift(hugepd_t hpd)
+{
+ return hpd.pd & HUGEPD_SHIFT_MASK;
+}
+
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+ unsigned pdshift)
+{
+ /*
+ * On 32-bit, we have multiple higher-level table entries that point to
+ * the same hugepte. Just use the first one since they're all
+ * identical. So for that case, idx=0.
+ */
+ unsigned long idx = 0;
+
+ pte_t *dir = hugepd_page(*hpdp);
+#ifdef CONFIG_PPC64
+ idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
+#endif
+
+ return dir + idx;
+}
+
pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
unsigned long addr, unsigned *shift);
void flush_dcache_icache_hugepage(struct page *page);
+#if defined(CONFIG_PPC_MM_SLICES) || defined(CONFIG_PPC_SUBPAGE_PROT)
int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
unsigned long len);
+#else
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+ unsigned long addr,
+ unsigned long len)
+{
+ return 0;
+}
+#endif
+
+void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte);
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
unsigned long end, unsigned long floor,
@@ -50,8 +95,11 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
- return __pte(old);
+#ifdef CONFIG_PPC64
+ return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+#else
+ return __pte(pte_update(ptep, ~0UL, 0));
+#endif
}
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -93,4 +141,15 @@ static inline void arch_release_hugepage(struct page *page)
{
}
+#else /* ! CONFIG_HUGETLB_PAGE */
+static inline void reserve_hugetlb_gpages(void)
+{
+ pr_err("Cannot reserve gpages without hugetlb enabled\n");
+}
+static inline void flush_hugetlb_page(struct vm_area_struct *vma,
+ unsigned long vmaddr)
+{
+}
+#endif
+
#endif /* _ASM_POWERPC_HUGETLB_H */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 8a33698c61b..f921eb121d3 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -2,7 +2,7 @@
#define _ASM_POWERPC_KEXEC_H
#ifdef __KERNEL__
-#ifdef CONFIG_FSL_BOOKE
+#if defined(CONFIG_FSL_BOOKE) || defined(CONFIG_44x)
/*
* On FSL-BookE we setup a 1:1 mapping which covers the first 2GiB of memory
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 47cacddb14c..58fc2162301 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -85,8 +85,9 @@ struct machdep_calls {
void (*pci_dma_dev_setup)(struct pci_dev *dev);
void (*pci_dma_bus_setup)(struct pci_bus *bus);
- /* Platform set_dma_mask override */
+ /* Platform set_dma_mask and dma_get_required_mask overrides */
int (*dma_set_mask)(struct device *dev, u64 dma_mask);
+ u64 (*dma_get_required_mask)(struct device *dev);
int (*probe)(void);
void (*setup_arch)(void); /* Optional, may be NULL */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 3ea0f9a259d..0260ea5ec3c 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -66,6 +66,7 @@
#define MAS2_M 0x00000004
#define MAS2_G 0x00000002
#define MAS2_E 0x00000001
+#define MAS2_WIMGE_MASK 0x0000001f
#define MAS2_EPN_MASK(size) (~0 << (size + 10))
#define MAS2_VAL(addr, size, flags) ((addr) & MAS2_EPN_MASK(size) | (flags))
@@ -80,6 +81,7 @@
#define MAS3_SW 0x00000004
#define MAS3_UR 0x00000002
#define MAS3_SR 0x00000001
+#define MAS3_BAP_MASK 0x0000003f
#define MAS3_SPSIZE 0x0000003e
#define MAS3_SPSIZE_SHIFT 1
@@ -212,6 +214,11 @@ typedef struct {
unsigned int id;
unsigned int active;
unsigned long vdso_base;
+#ifdef CONFIG_PPC_MM_SLICES
+ u64 low_slices_psize; /* SLB page size encodings */
+ u64 high_slices_psize; /* 4 bits per slice for now */
+ u16 user_psize; /* page size index */
+#endif
} mm_context_t;
/* Page size definitions, common between 32 and 64-bit
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index b445e0af4c2..db645ec842b 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -262,8 +262,7 @@ extern void hash_failure_debug(unsigned long ea, unsigned long access,
extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
unsigned long pstart, unsigned long prot,
int psize, int ssize);
-extern void add_gpage(unsigned long addr, unsigned long page_size,
- unsigned long number_of_pages);
+extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
extern void hpte_init_native(void);
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 698b3063868..f0145522cfb 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -175,14 +175,16 @@ extern u64 ppc64_rma_size;
#define MMU_PAGE_64K_AP 3 /* "Admixed pages" (hash64 only) */
#define MMU_PAGE_256K 4
#define MMU_PAGE_1M 5
-#define MMU_PAGE_8M 6
-#define MMU_PAGE_16M 7
-#define MMU_PAGE_256M 8
-#define MMU_PAGE_1G 9
-#define MMU_PAGE_16G 10
-#define MMU_PAGE_64G 11
-#define MMU_PAGE_COUNT 12
-
+#define MMU_PAGE_4M 6
+#define MMU_PAGE_8M 7
+#define MMU_PAGE_16M 8
+#define MMU_PAGE_64M 9
+#define MMU_PAGE_256M 10
+#define MMU_PAGE_1G 11
+#define MMU_PAGE_16G 12
+#define MMU_PAGE_64G 13
+
+#define MMU_PAGE_COUNT 14
#if defined(CONFIG_PPC_STD_MMU_64)
/* 64-bit classic hash table MMU */
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index df18989e78d..e6fae49e0b7 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -273,8 +273,6 @@ struct mpic
unsigned int irq_count;
/* Number of sources */
unsigned int num_sources;
- /* Number of CPUs */
- unsigned int num_cpus;
/* default senses array */
unsigned char *senses;
unsigned int senses_count;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 2cd664ef0a5..dd9c4fd038e 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -36,6 +36,18 @@
#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT)
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_HUGETLB_PAGE
+extern unsigned int HPAGE_SHIFT;
+#else
+#define HPAGE_SHIFT PAGE_SHIFT
+#endif
+#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
+#define HUGE_MAX_HSTATE (MMU_PAGE_COUNT-1)
+#endif
+
/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
#define __HAVE_ARCH_GATE_AREA 1
@@ -158,6 +170,24 @@ extern phys_addr_t kernstart_addr;
#define is_kernel_addr(x) ((x) >= PAGE_OFFSET)
#endif
+/*
+ * Use the top bit of the higher-level page table entries to indicate whether
+ * the entries we point to contain hugepages. This works because we know that
+ * the page tables live in kernel space. If we ever decide to support having
+ * page tables at arbitrary addresses, this breaks and will have to change.
+ */
+#ifdef CONFIG_PPC64
+#define PD_HUGE 0x8000000000000000
+#else
+#define PD_HUGE 0x80000000
+#endif
+
+/*
+ * Some number of bits at the level of the page table that points to
+ * a hugepte are used to encode the size. This masks those bits.
+ */
+#define HUGEPD_SHIFT_MASK 0x3f
+
#ifndef __ASSEMBLY__
#undef STRICT_MM_TYPECHECKS
@@ -243,7 +273,6 @@ typedef unsigned long pgprot_t;
#endif
typedef struct { signed long pd; } hugepd_t;
-#define HUGEPD_SHIFT_MASK 0x3f
#ifdef CONFIG_HUGETLB_PAGE
static inline int hugepd_ok(hugepd_t hpd)
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 9356262fd3c..fb40ede6bc0 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -64,17 +64,6 @@ extern void copy_page(void *to, void *from);
/* Log 2 of page table size */
extern u64 ppc64_pft_size;
-/* Large pages size */
-#ifdef CONFIG_HUGETLB_PAGE
-extern unsigned int HPAGE_SHIFT;
-#else
-#define HPAGE_SHIFT PAGE_SHIFT
-#endif
-#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT)
-#define HPAGE_MASK (~(HPAGE_SIZE - 1))
-#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
-#define HUGE_MAX_HSTATE (MMU_PAGE_COUNT-1)
-
#endif /* __ASSEMBLY__ */
#ifdef CONFIG_PPC_MM_SLICES
diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h
index 082d515930a..0156702ba24 100644
--- a/arch/powerpc/include/asm/pte-book3e.h
+++ b/arch/powerpc/include/asm/pte-book3e.h
@@ -72,6 +72,9 @@
#define PTE_RPN_SHIFT (24)
#endif
+#define PTE_WIMGE_SHIFT (19)
+#define PTE_BAP_SHIFT (2)
+
/* On 32-bit, we never clear the top part of the PTE */
#ifdef CONFIG_PPC32
#define _PTE_NONE_MASK 0xffffffff00000000ULL
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 58625d1e780..41f69ae79d4 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -249,10 +249,12 @@ extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
#define ERR_FLAG_ALREADY_LOGGED 0x0
#define ERR_FLAG_BOOT 0x1 /* log was pulled from NVRAM on boot */
#define ERR_TYPE_RTAS_LOG 0x2 /* from rtas event-scan */
-#define ERR_TYPE_KERNEL_PANIC 0x4 /* from panic() */
+#define ERR_TYPE_KERNEL_PANIC 0x4 /* from die()/panic() */
+#define ERR_TYPE_KERNEL_PANIC_GZ 0x8 /* ditto, compressed */
/* All the types and not flags */
-#define ERR_TYPE_MASK (ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC)
+#define ERR_TYPE_MASK \
+ (ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC | ERR_TYPE_KERNEL_PANIC_GZ)
#define RTAS_DEBUG KERN_DEBUG "RTAS: "
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 93e05d1b34b..7cf796fa03f 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -54,6 +54,7 @@ extern void __init udbg_init_40x_realmode(void);
extern void __init udbg_init_cpm(void);
extern void __init udbg_init_usbgecko(void);
extern void __init udbg_init_wsp(void);
+extern void __init udbg_init_ps3gelic(void);
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_UDBG_H */
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index e7554154a6d..6f04b9c383a 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -90,13 +90,27 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
return 1;
}
+static u64 dma_iommu_get_required_mask(struct device *dev)
+{
+ struct iommu_table *tbl = get_iommu_table_base(dev);
+ u64 mask;
+ if (!tbl)
+ return 0;
+
+ mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
+ mask += mask - 1;
+
+ return mask;
+}
+
struct dma_map_ops dma_iommu_ops = {
- .alloc_coherent = dma_iommu_alloc_coherent,
- .free_coherent = dma_iommu_free_coherent,
- .map_sg = dma_iommu_map_sg,
- .unmap_sg = dma_iommu_unmap_sg,
- .dma_supported = dma_iommu_dma_supported,
- .map_page = dma_iommu_map_page,
- .unmap_page = dma_iommu_unmap_page,
+ .alloc_coherent = dma_iommu_alloc_coherent,
+ .free_coherent = dma_iommu_free_coherent,
+ .map_sg = dma_iommu_map_sg,
+ .unmap_sg = dma_iommu_unmap_sg,
+ .dma_supported = dma_iommu_dma_supported,
+ .map_page = dma_iommu_map_page,
+ .unmap_page = dma_iommu_unmap_page,
+ .get_required_mask = dma_iommu_get_required_mask,
};
EXPORT_SYMBOL(dma_iommu_ops);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 4295e0b94b2..1ebc9189aad 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -24,6 +24,21 @@
unsigned int ppc_swiotlb_enable;
+static u64 swiotlb_powerpc_get_required(struct device *dev)
+{
+ u64 end, mask, max_direct_dma_addr = dev->archdata.max_direct_dma_addr;
+
+ end = memblock_end_of_DRAM();
+ if (max_direct_dma_addr && end > max_direct_dma_addr)
+ end = max_direct_dma_addr;
+ end += get_dma_offset(dev);
+
+ mask = 1ULL << (fls64(end) - 1);
+ mask += mask - 1;
+
+ return mask;
+}
+
/*
* At the moment, all platforms that use this code only require
* swiotlb to be used if we're operating on HIGHMEM. Since
@@ -44,6 +59,7 @@ struct dma_map_ops swiotlb_dma_ops = {
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
.sync_sg_for_device = swiotlb_sync_sg_for_device,
.mapping_error = swiotlb_dma_mapping_error,
+ .get_required_mask = swiotlb_powerpc_get_required,
};
void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 4f0959fbfbe..8593f53c4f6 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -96,6 +96,18 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask)
#endif
}
+static u64 dma_direct_get_required_mask(struct device *dev)
+{
+ u64 end, mask;
+
+ end = memblock_end_of_DRAM() + get_dma_offset(dev);
+
+ mask = 1ULL << (fls64(end) - 1);
+ mask += mask - 1;
+
+ return mask;
+}
+
static inline dma_addr_t dma_direct_map_page(struct device *dev,
struct page *page,
unsigned long offset,
@@ -137,13 +149,14 @@ static inline void dma_direct_sync_single(struct device *dev,
#endif
struct dma_map_ops dma_direct_ops = {
- .alloc_coherent = dma_direct_alloc_coherent,
- .free_coherent = dma_direct_free_coherent,
- .map_sg = dma_direct_map_sg,
- .unmap_sg = dma_direct_unmap_sg,
- .dma_supported = dma_direct_dma_supported,
- .map_page = dma_direct_map_page,
- .unmap_page = dma_direct_unmap_page,
+ .alloc_coherent = dma_direct_alloc_coherent,
+ .free_coherent = dma_direct_free_coherent,
+ .map_sg = dma_direct_map_sg,
+ .unmap_sg = dma_direct_unmap_sg,
+ .dma_supported = dma_direct_dma_supported,
+ .map_page = dma_direct_map_page,
+ .unmap_page = dma_direct_unmap_page,
+ .get_required_mask = dma_direct_get_required_mask,
#ifdef CONFIG_NOT_COHERENT_CACHE
.sync_single_for_cpu = dma_direct_sync_single,
.sync_single_for_device = dma_direct_sync_single,
@@ -170,6 +183,23 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
}
EXPORT_SYMBOL(dma_set_mask);
+u64 dma_get_required_mask(struct device *dev)
+{
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+ if (ppc_md.dma_get_required_mask)
+ return ppc_md.dma_get_required_mask(dev);
+
+ if (unlikely(dma_ops == NULL))
+ return 0;
+
+ if (dma_ops->get_required_mask)
+ return dma_ops->get_required_mask(dev);
+
+ return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
+}
+EXPORT_SYMBOL_GPL(dma_get_required_mask);
+
static int __init dma_init(void)
{
dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index ba250d505e0..0654dba2c1f 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -139,8 +139,7 @@ __start:
trap
#endif /* CONFIG_PPC_PMAC */
-1: mr r31,r3 /* save parameters */
- mr r30,r4
+1: mr r31,r3 /* save device tree ptr */
li r24,0 /* cpu # */
/*
@@ -964,8 +963,8 @@ start_here:
* Do early platform-specific initialization,
* and set up the MMU.
*/
- mr r3,r31
- mr r4,r30
+ li r3,0
+ mr r4,r31
bl machine_init
bl __save_cpu_setup
bl MMU_init
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index a91626d87fc..872a6af83ba 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -58,13 +58,7 @@
_ENTRY(_stext);
_ENTRY(_start);
- /* Save parameters we are passed.
- */
- mr r31,r3
- mr r30,r4
- mr r29,r5
- mr r28,r6
- mr r27,r7
+ mr r31,r3 /* save device tree ptr */
/* We have to turn on the MMU right away so we get cache modes
* set correctly.
@@ -849,11 +843,8 @@ start_here:
/*
* Decide what sort of machine this is and initialize the MMU.
*/
- mr r3,r31
- mr r4,r30
- mr r5,r29
- mr r6,r28
- mr r7,r27
+ li r3,0
+ mr r4,r31
bl machine_init
bl MMU_init
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index f8e971ba94f..b725dab0f88 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -61,14 +61,7 @@ _ENTRY(_start);
* of abatron_pteptrs
*/
nop
-/*
- * Save parameters we are passed
- */
- mr r31,r3
- mr r30,r4
- mr r29,r5
- mr r28,r6
- mr r27,r7
+ mr r31,r3 /* save device tree ptr */
li r24,0 /* CPU number */
bl init_cpu_state
@@ -120,11 +113,8 @@ _ENTRY(_start);
/*
* Decide what sort of machine this is and initialize the MMU.
*/
- mr r3,r31
- mr r4,r30
- mr r5,r29
- mr r6,r28
- mr r7,r27
+ li r3,0
+ mr r4,r31
bl machine_init
bl MMU_init
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 1cbf64e6b41..b68cb173ba2 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -76,11 +76,7 @@ _ENTRY(_start);
*/
.globl __start
__start:
- mr r31,r3 /* save parameters */
- mr r30,r4
- mr r29,r5
- mr r28,r6
- mr r27,r7
+ mr r31,r3 /* save device tree ptr */
/* We have to turn on the MMU right away so we get cache modes
* set correctly.
@@ -723,11 +719,8 @@ start_here:
/*
* Decide what sort of machine this is and initialize the MMU.
*/
- mr r3,r31
- mr r4,r30
- mr r5,r29
- mr r6,r28
- mr r7,r27
+ li r3,0
+ mr r4,r31
bl machine_init
bl MMU_init
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 50845924b7d..e1c699f3b7a 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -63,17 +63,30 @@ _ENTRY(_start);
* of abatron_pteptrs
*/
nop
-/*
- * Save parameters we are passed
- */
- mr r31,r3
- mr r30,r4
- mr r29,r5
- mr r28,r6
- mr r27,r7
- li r25,0 /* phys kernel start (low) */
- li r24,0 /* CPU number */
- li r23,0 /* phys kernel start (high) */
+
+ /* Translate device tree address to physical, save in r30/r31 */
+ mfmsr r16
+ mfspr r17,SPRN_PID
+ rlwinm r17,r17,16,0x3fff0000 /* turn PID into MAS6[SPID] */
+ rlwimi r17,r16,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */
+ mtspr SPRN_MAS6,r17
+
+ tlbsx 0,r3 /* must succeed */
+
+ mfspr r16,SPRN_MAS1
+ mfspr r20,SPRN_MAS3
+ rlwinm r17,r16,25,0x1f /* r17 = log2(page size) */
+ li r18,1024
+ slw r18,r18,r17 /* r18 = page size */
+ addi r18,r18,-1
+ and r19,r3,r18 /* r19 = page offset */
+ andc r31,r20,r18 /* r3 = page base */
+ or r31,r31,r19 /* r3 = devtree phys addr */
+ mfspr r30,SPRN_MAS7
+
+ li r25,0 /* phys kernel start (low) */
+ li r24,0 /* CPU number */
+ li r23,0 /* phys kernel start (high) */
/* We try to not make any assumptions about how the boot loader
* setup or used the TLBs. We invalidate all mappings from the
@@ -198,11 +211,8 @@ _ENTRY(__early_start)
/*
* Decide what sort of machine this is and initialize the MMU.
*/
- mr r3,r31
- mr r4,r30
- mr r5,r29
- mr r6,r28
- mr r7,r27
+ mr r3,r30
+ mr r4,r31
bl machine_init
bl MMU_init
@@ -236,8 +246,24 @@ _ENTRY(__early_start)
* if we find the pte (fall through):
* r11 is low pte word
* r12 is pointer to the pte
+ * r10 is the pshift from the PGD, if we're a hugepage
*/
#ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_HUGETLB_PAGE
+#define FIND_PTE \
+ rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \
+ lwzx r11, r12, r11; /* Get pgd/pmd entry */ \
+ rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \
+ blt 1000f; /* Normal non-huge page */ \
+ beq 2f; /* Bail if no table */ \
+ oris r11, r11, PD_HUGE@h; /* Put back address bit */ \
+ andi. r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */ \
+ xor r12, r10, r11; /* drop size bits from pointer */ \
+ b 1001f; \
+1000: rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \
+ li r10, 0; /* clear r10 */ \
+1001: lwz r11, 4(r12); /* Get pte entry */
+#else
#define FIND_PTE \
rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \
lwzx r11, r12, r11; /* Get pgd/pmd entry */ \
@@ -245,7 +271,8 @@ _ENTRY(__early_start)
beq 2f; /* Bail if no table */ \
rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \
lwz r11, 4(r12); /* Get pte entry */
-#else
+#endif /* HUGEPAGE */
+#else /* !PTE_64BIT */
#define FIND_PTE \
rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \
lwz r11, 0(r11); /* Get L1 entry */ \
@@ -402,8 +429,8 @@ interrupt_base:
#ifdef CONFIG_PTE_64BIT
#ifdef CONFIG_SMP
- subf r10,r11,r12 /* create false data dep */
- lwzx r13,r11,r10 /* Get upper pte bits */
+ subf r13,r11,r12 /* create false data dep */
+ lwzx r13,r11,r13 /* Get upper pte bits */
#else
lwz r13,0(r12) /* Get upper pte bits */
#endif
@@ -483,8 +510,8 @@ interrupt_base:
#ifdef CONFIG_PTE_64BIT
#ifdef CONFIG_SMP
- subf r10,r11,r12 /* create false data dep */
- lwzx r13,r11,r10 /* Get upper pte bits */
+ subf r13,r11,r12 /* create false data dep */
+ lwzx r13,r11,r13 /* Get upper pte bits */
#else
lwz r13,0(r12) /* Get upper pte bits */
#endif
@@ -548,7 +575,7 @@ interrupt_base:
/*
* Both the instruction and data TLB miss get to this
* point to load the TLB.
- * r10 - available to use
+ * r10 - tsize encoding (if HUGETLB_PAGE) or available to use
* r11 - TLB (info from Linux PTE)
* r12 - available to use
* r13 - upper bits of PTE (if PTE_64BIT) or available to use
@@ -558,21 +585,73 @@ interrupt_base:
* Upon exit, we reload everything and RFI.
*/
finish_tlb_load:
+#ifdef CONFIG_HUGETLB_PAGE
+ cmpwi 6, r10, 0 /* check for huge page */
+ beq 6, finish_tlb_load_cont /* !huge */
+
+ /* Alas, we need more scratch registers for hugepages */
+ mfspr r12, SPRN_SPRG_THREAD
+ stw r14, THREAD_NORMSAVE(4)(r12)
+ stw r15, THREAD_NORMSAVE(5)(r12)
+ stw r16, THREAD_NORMSAVE(6)(r12)
+ stw r17, THREAD_NORMSAVE(7)(r12)
+
+ /* Get the next_tlbcam_idx percpu var */
+#ifdef CONFIG_SMP
+ lwz r12, THREAD_INFO-THREAD(r12)
+ lwz r15, TI_CPU(r12)
+ lis r14, __per_cpu_offset@h
+ ori r14, r14, __per_cpu_offset@l
+ rlwinm r15, r15, 2, 0, 29
+ lwzx r16, r14, r15
+#else
+ li r16, 0
+#endif
+ lis r17, next_tlbcam_idx@h
+ ori r17, r17, next_tlbcam_idx@l
+ add r17, r17, r16 /* r17 = *next_tlbcam_idx */
+ lwz r15, 0(r17) /* r15 = next_tlbcam_idx */
+
+ lis r14, MAS0_TLBSEL(1)@h /* select TLB1 (TLBCAM) */
+ rlwimi r14, r15, 16, 4, 15 /* next_tlbcam_idx entry */
+ mtspr SPRN_MAS0, r14
+
+ /* Extract TLB1CFG(NENTRY) */
+ mfspr r16, SPRN_TLB1CFG
+ andi. r16, r16, 0xfff
+
+ /* Update next_tlbcam_idx, wrapping when necessary */
+ addi r15, r15, 1
+ cmpw r15, r16
+ blt 100f
+ lis r14, tlbcam_index@h
+ ori r14, r14, tlbcam_index@l
+ lwz r15, 0(r14)
+100: stw r15, 0(r17)
+
+ /*
+ * Calc MAS1_TSIZE from r10 (which has pshift encoded)
+ * tlb_enc = (pshift - 10).
+ */
+ subi r15, r10, 10
+ mfspr r16, SPRN_MAS1
+ rlwimi r16, r15, 7, 20, 24
+ mtspr SPRN_MAS1, r16
+
+ /* copy the pshift for use later */
+ mr r14, r10
+
+ /* fall through */
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
/*
* We set execute, because we don't have the granularity to
* properly set this at the page level (Linux problem).
* Many of these bits are software only. Bits we don't set
* here we (properly should) assume have the appropriate value.
*/
-
- mfspr r12, SPRN_MAS2
-#ifdef CONFIG_PTE_64BIT
- rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */
-#else
- rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */
-#endif
- mtspr SPRN_MAS2, r12
-
+finish_tlb_load_cont:
#ifdef CONFIG_PTE_64BIT
rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */
andi. r10, r11, _PAGE_DIRTY
@@ -581,22 +660,40 @@ finish_tlb_load:
andc r12, r12, r10
1: rlwimi r12, r13, 20, 0, 11 /* grab RPN[32:43] */
rlwimi r12, r11, 20, 12, 19 /* grab RPN[44:51] */
- mtspr SPRN_MAS3, r12
+2: mtspr SPRN_MAS3, r12
BEGIN_MMU_FTR_SECTION
srwi r10, r13, 12 /* grab RPN[12:31] */
mtspr SPRN_MAS7, r10
END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
#else
li r10, (_PAGE_EXEC | _PAGE_PRESENT)
+ mr r13, r11
rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */
and r12, r11, r10
andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */
slwi r10, r12, 1
or r10, r10, r12
iseleq r12, r12, r10
- rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */
- mtspr SPRN_MAS3, r11
+ rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */
+ mtspr SPRN_MAS3, r13
#endif
+
+ mfspr r12, SPRN_MAS2
+#ifdef CONFIG_PTE_64BIT
+ rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */
+#else
+ rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+ beq 6, 3f /* don't mask if page isn't huge */
+ li r13, 1
+ slw r13, r13, r14
+ subi r13, r13, 1
+ rlwinm r13, r13, 0, 0, 19 /* bottom bits used for WIMGE/etc */
+ andc r12, r12, r13 /* mask off ea bits within the page */
+#endif
+3: mtspr SPRN_MAS2, r12
+
#ifdef CONFIG_E200
/* Round robin TLB1 entries assignment */
mfspr r12, SPRN_MAS0
@@ -622,11 +719,19 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
mtspr SPRN_MAS0,r12
#endif /* CONFIG_E200 */
+tlb_write_entry:
tlbwe
/* Done...restore registers and get out of here. */
mfspr r10, SPRN_SPRG_THREAD
- lwz r11, THREAD_NORMSAVE(3)(r10)
+#ifdef CONFIG_HUGETLB_PAGE
+ beq 6, 8f /* skip restore for 4k page faults */
+ lwz r14, THREAD_NORMSAVE(4)(r10)
+ lwz r15, THREAD_NORMSAVE(5)(r10)
+ lwz r16, THREAD_NORMSAVE(6)(r10)
+ lwz r17, THREAD_NORMSAVE(7)(r10)
+#endif
+8: lwz r11, THREAD_NORMSAVE(3)(r10)
mtcr r11
lwz r13, THREAD_NORMSAVE(2)(r10)
lwz r12, THREAD_NORMSAVE(1)(r10)
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 28581f1ad2c..73110fb6bb6 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -125,17 +125,23 @@ static void ibmebus_unmap_sg(struct device *dev,
static int ibmebus_dma_supported(struct device *dev, u64 mask)
{
- return 1;
+ return mask == DMA_BIT_MASK(64);
+}
+
+static u64 ibmebus_dma_get_required_mask(struct device *dev)
+{
+ return DMA_BIT_MASK(64);
}
static struct dma_map_ops ibmebus_dma_ops = {
- .alloc_coherent = ibmebus_alloc_coherent,
- .free_coherent = ibmebus_free_coherent,
- .map_sg = ibmebus_map_sg,
- .unmap_sg = ibmebus_unmap_sg,
- .dma_supported = ibmebus_dma_supported,
- .map_page = ibmebus_map_page,
- .unmap_page = ibmebus_unmap_page,
+ .alloc_coherent = ibmebus_alloc_coherent,
+ .free_coherent = ibmebus_free_coherent,
+ .map_sg = ibmebus_map_sg,
+ .unmap_sg = ibmebus_unmap_sg,
+ .dma_supported = ibmebus_dma_supported,
+ .get_required_mask = ibmebus_dma_get_required_mask,
+ .map_page = ibmebus_map_page,
+ .unmap_page = ibmebus_unmap_page,
};
static int ibmebus_match_path(struct device *dev, void *data)
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 2b97b80d6d7..c7b5afeecaf 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -6,6 +6,7 @@
#include <linux/pci.h>
#include <linux/of_address.h>
#include <linux/of_device.h>
+#include <linux/serial_reg.h>
#include <asm/io.h>
#include <asm/mmu.h>
#include <asm/prom.h>
@@ -47,6 +48,24 @@ static struct __initdata of_device_id legacy_serial_parents[] = {
static unsigned int legacy_serial_count;
static int legacy_serial_console = -1;
+static unsigned int tsi_serial_in(struct uart_port *p, int offset)
+{
+ unsigned int tmp;
+ offset = offset << p->regshift;
+ if (offset == UART_IIR) {
+ tmp = readl(p->membase + (UART_IIR & ~3));
+ return (tmp >> 16) & 0xff; /* UART_IIR % 4 == 2 */
+ } else
+ return readb(p->membase + offset);
+}
+
+static void tsi_serial_out(struct uart_port *p, int offset, int value)
+{
+ offset = offset << p->regshift;
+ if (!((offset == UART_IER) && (value & UART_IER_UUE)))
+ writeb(value, p->membase + offset);
+}
+
static int __init add_legacy_port(struct device_node *np, int want_index,
int iotype, phys_addr_t base,
phys_addr_t taddr, unsigned long irq,
@@ -102,6 +121,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
legacy_serial_ports[index].iobase = base;
else
legacy_serial_ports[index].mapbase = base;
+
legacy_serial_ports[index].iotype = iotype;
legacy_serial_ports[index].uartclk = clock;
legacy_serial_ports[index].irq = irq;
@@ -112,6 +132,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0;
legacy_serial_infos[index].irq_check_parent = irq_check_parent;
+ if (iotype == UPIO_TSI) {
+ legacy_serial_ports[index].serial_in = tsi_serial_in;
+ legacy_serial_ports[index].serial_out = tsi_serial_out;
+ }
+
printk(KERN_DEBUG "Found legacy serial port %d for %s\n",
index, np->full_name);
printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n",
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 998a1002860..f7d760ab5ca 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -8,6 +8,8 @@
* kexec bits:
* Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com>
* GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ * PPC44x port. Copyright (C) 2011, IBM Corporation
+ * Author: Suzuki Poulose <suzuki@in.ibm.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -736,6 +738,175 @@ relocate_new_kernel:
mr r5, r31
li r0, 0
+#elif defined(CONFIG_44x) && !defined(CONFIG_47x)
+
+/*
+ * Code for setting up 1:1 mapping for PPC440x for KEXEC
+ *
+ * We cannot switch off the MMU on PPC44x.
+ * So we:
+ * 1) Invalidate all the mappings except the one we are running from.
+ * 2) Create a tmp mapping for our code in the other address space(TS) and
+ * jump to it. Invalidate the entry we started in.
+ * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS.
+ * 4) Jump to the 1:1 mapping in original TS.
+ * 5) Invalidate the tmp mapping.
+ *
+ * - Based on the kexec support code for FSL BookE
+ * - Doesn't support 47x yet.
+ *
+ */
+ /* Save our parameters */
+ mr r29, r3
+ mr r30, r4
+ mr r31, r5
+
+ /* Load our MSR_IS and TID to MMUCR for TLB search */
+ mfspr r3,SPRN_PID
+ mfmsr r4
+ andi. r4,r4,MSR_IS@l
+ beq wmmucr
+ oris r3,r3,PPC44x_MMUCR_STS@h
+wmmucr:
+ mtspr SPRN_MMUCR,r3
+ sync
+
+ /*
+ * Invalidate all the TLB entries except the current entry
+ * where we are running from
+ */
+ bl 0f /* Find our address */
+0: mflr r5 /* Make it accessible */
+ tlbsx r23,0,r5 /* Find entry we are in */
+ li r4,0 /* Start at TLB entry 0 */
+ li r3,0 /* Set PAGEID inval value */
+1: cmpw r23,r4 /* Is this our entry? */
+ beq skip /* If so, skip the inval */
+ tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */
+skip:
+ addi r4,r4,1 /* Increment */
+ cmpwi r4,64 /* Are we done? */
+ bne 1b /* If not, repeat */
+ isync
+
+ /* Create a temp mapping and jump to it */
+ andi. r6, r23, 1 /* Find the index to use */
+ addi r24, r6, 1 /* r24 will contain 1 or 2 */
+
+ mfmsr r9 /* get the MSR */
+ rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */
+ xori r7, r5, 1 /* Use the other address space */
+
+ /* Read the current mapping entries */
+ tlbre r3, r23, PPC44x_TLB_PAGEID
+ tlbre r4, r23, PPC44x_TLB_XLAT
+ tlbre r5, r23, PPC44x_TLB_ATTRIB
+
+ /* Save our current XLAT entry */
+ mr r25, r4
+
+ /* Extract the TLB PageSize */
+ li r10, 1 /* r10 will hold PageSize */
+ rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */
+
+ /* XXX: As of now we use 256M, 4K pages */
+ cmpwi r11, PPC44x_TLB_256M
+ bne tlb_4k
+ rotlwi r10, r10, 28 /* r10 = 256M */
+ b write_out
+tlb_4k:
+ cmpwi r11, PPC44x_TLB_4K
+ bne default
+ rotlwi r10, r10, 12 /* r10 = 4K */
+ b write_out
+default:
+ rotlwi r10, r10, 10 /* r10 = 1K */
+
+write_out:
+ /*
+ * Write out the tmp 1:1 mapping for this code in other address space
+ * Fixup EPN = RPN , TS=other address space
+ */
+ insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */
+
+ /* Write out the tmp mapping entries */
+ tlbwe r3, r24, PPC44x_TLB_PAGEID
+ tlbwe r4, r24, PPC44x_TLB_XLAT
+ tlbwe r5, r24, PPC44x_TLB_ATTRIB
+
+ subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */
+ not r10, r11 /* Mask for PageNum */
+
+ /* Switch to other address space in MSR */
+ insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */
+
+ bl 1f
+1: mflr r8
+ addi r8, r8, (2f-1b) /* Find the target offset */
+
+ /* Jump to the tmp mapping */
+ mtspr SPRN_SRR0, r8
+ mtspr SPRN_SRR1, r9
+ rfi
+
+2:
+ /* Invalidate the entry we were executing from */
+ li r3, 0
+ tlbwe r3, r23, PPC44x_TLB_PAGEID
+
+ /* attribute fields. rwx for SUPERVISOR mode */
+ li r5, 0
+ ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G)
+
+ /* Create 1:1 mapping in 256M pages */
+ xori r7, r7, 1 /* Revert back to Original TS */
+
+ li r8, 0 /* PageNumber */
+ li r6, 3 /* TLB Index, start at 3 */
+
+next_tlb:
+ rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */
+ mr r4, r3 /* RPN = EPN */
+ ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */
+ insrwi r3, r7, 1, 23 /* Set TS from r7 */
+
+ tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */
+ tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */
+ tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */
+
+ addi r8, r8, 1 /* Increment PN */
+ addi r6, r6, 1 /* Increment TLB Index */
+ cmpwi r8, 8 /* Are we done ? */
+ bne next_tlb
+ isync
+
+ /* Jump to the new mapping 1:1 */
+ li r9,0
+ insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */
+
+ bl 1f
+1: mflr r8
+ and r8, r8, r11 /* Get our offset within page */
+ addi r8, r8, (2f-1b)
+
+ and r5, r25, r10 /* Get our target PageNum */
+ or r8, r8, r5 /* Target jump address */
+
+ mtspr SPRN_SRR0, r8
+ mtspr SPRN_SRR1, r9
+ rfi
+2:
+ /* Invalidate the tmp entry we used */
+ li r3, 0
+ tlbwe r3, r24, PPC44x_TLB_PAGEID
+ sync
+
+ /* Restore the parameters */
+ mr r3, r29
+ mr r4, r30
+ mr r5, r31
+
+ li r0, 0
#else
li r0, 0
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 209135af0a4..c1ce86357ec 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -117,7 +117,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
* This is called very early on the boot process, after a minimal
* MMU environment has been set up but before MMU_init is called.
*/
-notrace void __init machine_init(unsigned long dt_ptr)
+notrace void __init machine_init(u64 dt_ptr)
{
lockdep_init();
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index aa17b76dd42..641f9adc620 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -33,6 +33,6 @@ void save_processor_state(void)
void restore_processor_state(void)
{
#ifdef CONFIG_PPC32
- switch_mmu_context(NULL, current->active_mm);
+ switch_mmu_context(current->active_mm, current->active_mm);
#endif
}
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index faa82c1f3f6..5b3e98e0315 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -67,6 +67,8 @@ void __init udbg_early_init(void)
udbg_init_usbgecko();
#elif defined(CONFIG_PPC_EARLY_DEBUG_WSP)
udbg_init_wsp();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC)
+ udbg_init_ps3gelic();
#endif
#ifdef CONFIG_PPC_EARLY_DEBUG
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 1b695fdc362..34d291d83ec 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -605,15 +605,20 @@ static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
return dma_iommu_ops.dma_supported(dev, mask);
}
-struct dma_map_ops vio_dma_mapping_ops = {
- .alloc_coherent = vio_dma_iommu_alloc_coherent,
- .free_coherent = vio_dma_iommu_free_coherent,
- .map_sg = vio_dma_iommu_map_sg,
- .unmap_sg = vio_dma_iommu_unmap_sg,
- .map_page = vio_dma_iommu_map_page,
- .unmap_page = vio_dma_iommu_unmap_page,
- .dma_supported = vio_dma_iommu_dma_supported,
+static u64 vio_dma_get_required_mask(struct device *dev)
+{
+ return dma_iommu_ops.get_required_mask(dev);
+}
+struct dma_map_ops vio_dma_mapping_ops = {
+ .alloc_coherent = vio_dma_iommu_alloc_coherent,
+ .free_coherent = vio_dma_iommu_free_coherent,
+ .map_sg = vio_dma_iommu_map_sg,
+ .unmap_sg = vio_dma_iommu_unmap_sg,
+ .map_page = vio_dma_iommu_map_page,
+ .unmap_page = vio_dma_iommu_unmap_page,
+ .dma_supported = vio_dma_iommu_dma_supported,
+ .get_required_mask = vio_dma_get_required_mask,
};
/**
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index bdca46e0838..991ee813d2a 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_PPC_MM_SLICES) += slice.o
ifeq ($(CONFIG_HUGETLB_PAGE),y)
obj-y += hugetlbpage.o
obj-$(CONFIG_PPC_STD_MMU_64) += hugetlbpage-hash64.o
+obj-$(CONFIG_PPC_BOOK3E_MMU) += hugetlbpage-book3e.o
endif
obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 26b2872b3d0..1f8b2a05e3d 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -105,9 +105,6 @@ int mmu_kernel_ssize = MMU_SEGSIZE_256M;
int mmu_highuser_ssize = MMU_SEGSIZE_256M;
u16 mmu_slb_size = 64;
EXPORT_SYMBOL_GPL(mmu_slb_size);
-#ifdef CONFIG_HUGETLB_PAGE
-unsigned int HPAGE_SHIFT;
-#endif
#ifdef CONFIG_PPC_64K_PAGES
int mmu_ci_restrictions;
#endif
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
new file mode 100644
index 00000000000..1295b7c1cda
--- /dev/null
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -0,0 +1,121 @@
+/*
+ * PPC Huge TLB Page Support for Book3E MMU
+ *
+ * Copyright (C) 2009 David Gibson, IBM Corporation.
+ * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
+ *
+ */
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+
+static inline int mmu_get_tsize(int psize)
+{
+ return mmu_psize_defs[psize].enc;
+}
+
+static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid)
+{
+ int found = 0;
+
+ mtspr(SPRN_MAS6, pid << 16);
+ if (mmu_has_feature(MMU_FTR_USE_TLBRSRV)) {
+ asm volatile(
+ "li %0,0\n"
+ "tlbsx. 0,%1\n"
+ "bne 1f\n"
+ "li %0,1\n"
+ "1:\n"
+ : "=&r"(found) : "r"(ea));
+ } else {
+ asm volatile(
+ "tlbsx 0,%1\n"
+ "mfspr %0,0x271\n"
+ "srwi %0,%0,31\n"
+ : "=&r"(found) : "r"(ea));
+ }
+
+ return found;
+}
+
+void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte)
+{
+ unsigned long mas1, mas2;
+ u64 mas7_3;
+ unsigned long psize, tsize, shift;
+ unsigned long flags;
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+ int index, lz, ncams;
+ struct vm_area_struct *vma;
+#endif
+
+ if (unlikely(is_kernel_addr(ea)))
+ return;
+
+#ifdef CONFIG_MM_SLICES
+ psize = mmu_get_tsize(get_slice_psize(mm, ea));
+ tsize = mmu_get_psize(psize);
+ shift = mmu_psize_defs[psize].shift;
+#else
+ vma = find_vma(mm, ea);
+ psize = vma_mmu_pagesize(vma); /* returns actual size in bytes */
+ asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (psize));
+ shift = 31 - lz;
+ tsize = 21 - lz;
+#endif
+
+ /*
+ * We can't be interrupted while we're setting up the MAS
+ * regusters or after we've confirmed that no tlb exists.
+ */
+ local_irq_save(flags);
+
+ if (unlikely(book3e_tlb_exists(ea, mm->context.id))) {
+ local_irq_restore(flags);
+ return;
+ }
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+ ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+ /* We have to use the CAM(TLB1) on FSL parts for hugepages */
+ index = __get_cpu_var(next_tlbcam_idx);
+ mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1));
+
+ /* Just round-robin the entries and wrap when we hit the end */
+ if (unlikely(index == ncams - 1))
+ __get_cpu_var(next_tlbcam_idx) = tlbcam_index;
+ else
+ __get_cpu_var(next_tlbcam_idx)++;
+#endif
+ mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize);
+ mas2 = ea & ~((1UL << shift) - 1);
+ mas2 |= (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
+ mas7_3 = (u64)pte_pfn(pte) << PAGE_SHIFT;
+ mas7_3 |= (pte_val(pte) >> PTE_BAP_SHIFT) & MAS3_BAP_MASK;
+ if (!pte_dirty(pte))
+ mas7_3 &= ~(MAS3_SW|MAS3_UW);
+
+ mtspr(SPRN_MAS1, mas1);
+ mtspr(SPRN_MAS2, mas2);
+
+ if (mmu_has_feature(MMU_FTR_USE_PAIRED_MAS)) {
+ mtspr(SPRN_MAS7_MAS3, mas7_3);
+ } else {
+ mtspr(SPRN_MAS7, upper_32_bits(mas7_3));
+ mtspr(SPRN_MAS3, lower_32_bits(mas7_3));
+ }
+
+ asm volatile ("tlbwe");
+
+ local_irq_restore(flags);
+}
+
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+ struct hstate *hstate = hstate_file(vma->vm_file);
+ unsigned long tsize = huge_page_shift(hstate) - 10;
+
+ __flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, tsize, 0);
+
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0b9a5c1901b..3a5f59dcbb3 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -1,7 +1,8 @@
/*
- * PPC64 (POWER4) Huge TLB Page Support for Kernel.
+ * PPC Huge TLB Page Support for Kernel.
*
* Copyright (C) 2003 David Gibson, IBM Corporation.
+ * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
*
* Based on the IA-32 version:
* Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
@@ -11,24 +12,39 @@
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/hugetlb.h>
+#include <linux/of_fdt.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
+#include <asm/setup.h>
#define PAGE_SHIFT_64K 16
#define PAGE_SHIFT_16M 24
#define PAGE_SHIFT_16G 34
-#define MAX_NUMBER_GPAGES 1024
+unsigned int HPAGE_SHIFT;
-/* Tracks the 16G pages after the device tree is scanned and before the
- * huge_boot_pages list is ready. */
-static unsigned long gpage_freearray[MAX_NUMBER_GPAGES];
+/*
+ * Tracks gpages after the device tree is scanned and before the
+ * huge_boot_pages list is ready. On 64-bit implementations, this is
+ * just used to track 16G pages and so is a single array. 32-bit
+ * implementations may have more than one gpage size due to limitations
+ * of the memory allocators, so we need multiple arrays
+ */
+#ifdef CONFIG_PPC64
+#define MAX_NUMBER_GPAGES 1024
+static u64 gpage_freearray[MAX_NUMBER_GPAGES];
static unsigned nr_gpages;
-
-/* Flag to mark huge PD pointers. This means pmd_bad() and pud_bad()
- * will choke on pointers to hugepte tables, which is handy for
- * catching screwups early. */
+#else
+#define MAX_NUMBER_GPAGES 128
+struct psize_gpages {
+ u64 gpage_list[MAX_NUMBER_GPAGES];
+ unsigned int nr_gpages;
+};
+static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
+#endif
static inline int shift_to_mmu_psize(unsigned int shift)
{
@@ -49,25 +65,6 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
#define hugepd_none(hpd) ((hpd).pd == 0)
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
- BUG_ON(!hugepd_ok(hpd));
- return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | 0xc000000000000000);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
- return hpd.pd & HUGEPD_SHIFT_MASK;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift)
-{
- unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
- pte_t *dir = hugepd_page(*hpdp);
-
- return dir + idx;
-}
-
pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
{
pgd_t *pg;
@@ -93,7 +90,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
if (is_hugepd(pm))
hpdp = (hugepd_t *)pm;
else if (!pmd_none(*pm)) {
- return pte_offset_map(pm, ea);
+ return pte_offset_kernel(pm, ea);
}
}
}
@@ -114,8 +111,18 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
unsigned long address, unsigned pdshift, unsigned pshift)
{
- pte_t *new = kmem_cache_zalloc(PGT_CACHE(pdshift - pshift),
- GFP_KERNEL|__GFP_REPEAT);
+ struct kmem_cache *cachep;
+ pte_t *new;
+
+#ifdef CONFIG_PPC64
+ cachep = PGT_CACHE(pdshift - pshift);
+#else
+ int i;
+ int num_hugepd = 1 << (pshift - pdshift);
+ cachep = hugepte_cache;
+#endif
+
+ new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
BUG_ON(pshift > HUGEPD_SHIFT_MASK);
BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
@@ -124,10 +131,31 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
return -ENOMEM;
spin_lock(&mm->page_table_lock);
+#ifdef CONFIG_PPC64
if (!hugepd_none(*hpdp))
- kmem_cache_free(PGT_CACHE(pdshift - pshift), new);
+ kmem_cache_free(cachep, new);
else
- hpdp->pd = ((unsigned long)new & ~0x8000000000000000) | pshift;
+ hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+#else
+ /*
+ * We have multiple higher-level entries that point to the same
+ * actual pte location. Fill in each as we go and backtrack on error.
+ * We need all of these so the DTLB pgtable walk code can find the
+ * right higher-level entry without knowing if it's a hugepage or not.
+ */
+ for (i = 0; i < num_hugepd; i++, hpdp++) {
+ if (unlikely(!hugepd_none(*hpdp)))
+ break;
+ else
+ hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+ }
+ /* If we bailed from the for loop early, an error occurred, clean up */
+ if (i < num_hugepd) {
+ for (i = i - 1 ; i >= 0; i--, hpdp--)
+ hpdp->pd = 0;
+ kmem_cache_free(cachep, new);
+ }
+#endif
spin_unlock(&mm->page_table_lock);
return 0;
}
@@ -169,11 +197,132 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
return hugepte_offset(hpdp, addr, pdshift);
}
+#ifdef CONFIG_PPC32
/* Build list of addresses of gigantic pages. This function is used in early
* boot before the buddy or bootmem allocator is setup.
*/
-void add_gpage(unsigned long addr, unsigned long page_size,
- unsigned long number_of_pages)
+void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
+{
+ unsigned int idx = shift_to_mmu_psize(__ffs(page_size));
+ int i;
+
+ if (addr == 0)
+ return;
+
+ gpage_freearray[idx].nr_gpages = number_of_pages;
+
+ for (i = 0; i < number_of_pages; i++) {
+ gpage_freearray[idx].gpage_list[i] = addr;
+ addr += page_size;
+ }
+}
+
+/*
+ * Moves the gigantic page addresses from the temporary list to the
+ * huge_boot_pages list.
+ */
+int alloc_bootmem_huge_page(struct hstate *hstate)
+{
+ struct huge_bootmem_page *m;
+ int idx = shift_to_mmu_psize(hstate->order + PAGE_SHIFT);
+ int nr_gpages = gpage_freearray[idx].nr_gpages;
+
+ if (nr_gpages == 0)
+ return 0;
+
+#ifdef CONFIG_HIGHMEM
+ /*
+ * If gpages can be in highmem we can't use the trick of storing the
+ * data structure in the page; allocate space for this
+ */
+ m = alloc_bootmem(sizeof(struct huge_bootmem_page));
+ m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
+#else
+ m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
+#endif
+
+ list_add(&m->list, &huge_boot_pages);
+ gpage_freearray[idx].nr_gpages = nr_gpages;
+ gpage_freearray[idx].gpage_list[nr_gpages] = 0;
+ m->hstate = hstate;
+
+ return 1;
+}
+/*
+ * Scan the command line hugepagesz= options for gigantic pages; store those in
+ * a list that we use to allocate the memory once all options are parsed.
+ */
+
+unsigned long gpage_npages[MMU_PAGE_COUNT];
+
+static int __init do_gpage_early_setup(char *param, char *val)
+{
+ static phys_addr_t size;
+ unsigned long npages;
+
+ /*
+ * The hugepagesz and hugepages cmdline options are interleaved. We
+ * use the size variable to keep track of whether or not this was done
+ * properly and skip over instances where it is incorrect. Other
+ * command-line parsing code will issue warnings, so we don't need to.
+ *
+ */
+ if ((strcmp(param, "default_hugepagesz") == 0) ||
+ (strcmp(param, "hugepagesz") == 0)) {
+ size = memparse(val, NULL);
+ } else if (strcmp(param, "hugepages") == 0) {
+ if (size != 0) {
+ if (sscanf(val, "%lu", &npages) <= 0)
+ npages = 0;
+ gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
+ size = 0;
+ }
+ }
+ return 0;
+}
+
+
+/*
+ * This function allocates physical space for pages that are larger than the
+ * buddy allocator can handle. We want to allocate these in highmem because
+ * the amount of lowmem is limited. This means that this function MUST be
+ * called before lowmem_end_addr is set up in MMU_init() in order for the lmb
+ * allocate to grab highmem.
+ */
+void __init reserve_hugetlb_gpages(void)
+{
+ static __initdata char cmdline[COMMAND_LINE_SIZE];
+ phys_addr_t size, base;
+ int i;
+
+ strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ parse_args("hugetlb gpages", cmdline, NULL, 0, &do_gpage_early_setup);
+
+ /*
+ * Walk gpage list in reverse, allocating larger page sizes first.
+ * Skip over unsupported sizes, or sizes that have 0 gpages allocated.
+ * When we reach the point in the list where pages are no longer
+ * considered gpages, we're done.
+ */
+ for (i = MMU_PAGE_COUNT-1; i >= 0; i--) {
+ if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0)
+ continue;
+ else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT))
+ break;
+
+ size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i));
+ base = memblock_alloc_base(size * gpage_npages[i], size,
+ MEMBLOCK_ALLOC_ANYWHERE);
+ add_gpage(base, size, gpage_npages[i]);
+ }
+}
+
+#else /* PPC64 */
+
+/* Build list of addresses of gigantic pages. This function is used in early
+ * boot before the buddy or bootmem allocator is setup.
+ */
+void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
{
if (!addr)
return;
@@ -199,19 +348,79 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
m->hstate = hstate;
return 1;
}
+#endif
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
{
return 0;
}
+#ifdef CONFIG_PPC32
+#define HUGEPD_FREELIST_SIZE \
+ ((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
+
+struct hugepd_freelist {
+ struct rcu_head rcu;
+ unsigned int index;
+ void *ptes[0];
+};
+
+static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
+
+static void hugepd_free_rcu_callback(struct rcu_head *head)
+{
+ struct hugepd_freelist *batch =
+ container_of(head, struct hugepd_freelist, rcu);
+ unsigned int i;
+
+ for (i = 0; i < batch->index; i++)
+ kmem_cache_free(hugepte_cache, batch->ptes[i]);
+
+ free_page((unsigned long)batch);
+}
+
+static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
+{
+ struct hugepd_freelist **batchp;
+
+ batchp = &__get_cpu_var(hugepd_freelist_cur);
+
+ if (atomic_read(&tlb->mm->mm_users) < 2 ||
+ cpumask_equal(mm_cpumask(tlb->mm),
+ cpumask_of(smp_processor_id()))) {
+ kmem_cache_free(hugepte_cache, hugepte);
+ return;
+ }
+
+ if (*batchp == NULL) {
+ *batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
+ (*batchp)->index = 0;
+ }
+
+ (*batchp)->ptes[(*batchp)->index++] = hugepte;
+ if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
+ call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback);
+ *batchp = NULL;
+ }
+}
+#endif
+
static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
unsigned long start, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pte_t *hugepte = hugepd_page(*hpdp);
- unsigned shift = hugepd_shift(*hpdp);
+ int i;
+
unsigned long pdmask = ~((1UL << pdshift) - 1);
+ unsigned int num_hugepd = 1;
+
+#ifdef CONFIG_PPC64
+ unsigned int shift = hugepd_shift(*hpdp);
+#else
+ /* Note: On 32-bit the hpdp may be the first of several */
+ num_hugepd = (1 << (hugepd_shift(*hpdp) - pdshift));
+#endif
start &= pdmask;
if (start < floor)
@@ -224,9 +433,15 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
if (end - 1 > ceiling - 1)
return;
- hpdp->pd = 0;
+ for (i = 0; i < num_hugepd; i++, hpdp++)
+ hpdp->pd = 0;
+
tlb->need_flush = 1;
+#ifdef CONFIG_PPC64
pgtable_free_tlb(tlb, hugepte, pdshift - shift);
+#else
+ hugepd_free(tlb, hugepte);
+#endif
}
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -331,18 +546,27 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
* too.
*/
- pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
+ pgd = pgd_offset(tlb->mm, addr);
if (!is_hugepd(pgd)) {
if (pgd_none_or_clear_bad(pgd))
continue;
hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
} else {
+#ifdef CONFIG_PPC32
+ /*
+ * Increment next by the size of the huge mapping since
+ * on 32-bit there may be more than one entry at the pgd
+ * level for a single hugepage, but all of them point to
+ * the same kmem cache that holds the hugepte.
+ */
+ next = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
+#endif
free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
addr, next, floor, ceiling);
}
- } while (pgd++, addr = next, addr != end);
+ } while (addr = next, addr != end);
}
struct page *
@@ -466,17 +690,35 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags)
{
+#ifdef CONFIG_MM_SLICES
struct hstate *hstate = hstate_file(file);
int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
+#else
+ return get_unmapped_area(file, addr, len, pgoff, flags);
+#endif
}
unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
+#ifdef CONFIG_MM_SLICES
unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
return 1UL << mmu_psize_to_shift(psize);
+#else
+ if (!is_vm_hugetlb_page(vma))
+ return PAGE_SIZE;
+
+ return huge_page_size(hstate_vma(vma));
+#endif
+}
+
+static inline bool is_power_of_4(unsigned long x)
+{
+ if (is_power_of_2(x))
+ return (__ilog2(x) % 2) ? false : true;
+ return false;
}
static int __init add_huge_page_size(unsigned long long size)
@@ -486,9 +728,14 @@ static int __init add_huge_page_size(unsigned long long size)
/* Check that it is a page size supported by the hardware and
* that it fits within pagetable and slice limits. */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+ if ((size < PAGE_SIZE) || !is_power_of_4(size))
+ return -EINVAL;
+#else
if (!is_power_of_2(size)
|| (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
return -EINVAL;
+#endif
if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
return -EINVAL;
@@ -525,6 +772,46 @@ static int __init hugepage_setup_sz(char *str)
}
__setup("hugepagesz=", hugepage_setup_sz);
+#ifdef CONFIG_FSL_BOOKE
+struct kmem_cache *hugepte_cache;
+static int __init hugetlbpage_init(void)
+{
+ int psize;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ unsigned shift;
+
+ if (!mmu_psize_defs[psize].shift)
+ continue;
+
+ shift = mmu_psize_to_shift(psize);
+
+ /* Don't treat normal page sizes as huge... */
+ if (shift != PAGE_SHIFT)
+ if (add_huge_page_size(1ULL << shift) < 0)
+ continue;
+ }
+
+ /*
+ * Create a kmem cache for hugeptes. The bottom bits in the pte have
+ * size information encoded in them, so align them to allow this
+ */
+ hugepte_cache = kmem_cache_create("hugepte-cache", sizeof(pte_t),
+ HUGEPD_SHIFT_MASK + 1, 0, NULL);
+ if (hugepte_cache == NULL)
+ panic("%s: Unable to create kmem cache for hugeptes\n",
+ __func__);
+
+ /* Default hpage size = 4M */
+ if (mmu_psize_defs[MMU_PAGE_4M].shift)
+ HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
+ else
+ panic("%s: Unable to set default huge page size\n", __func__);
+
+
+ return 0;
+}
+#else
static int __init hugetlbpage_init(void)
{
int psize;
@@ -567,15 +854,23 @@ static int __init hugetlbpage_init(void)
return 0;
}
-
+#endif
module_init(hugetlbpage_init);
void flush_dcache_icache_hugepage(struct page *page)
{
int i;
+ void *start;
BUG_ON(!PageCompound(page));
- for (i = 0; i < (1UL << compound_order(page)); i++)
- __flush_dcache_icache(page_address(page+i));
+ for (i = 0; i < (1UL << compound_order(page)); i++) {
+ if (!PageHighMem(page)) {
+ __flush_dcache_icache(page_address(page+i));
+ } else {
+ start = kmap_atomic(page+i, KM_PPC_SYNC_ICACHE);
+ __flush_dcache_icache(start);
+ kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+ }
+ }
}
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index c77fef56dad..161cefde5c1 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -32,6 +32,8 @@
#include <linux/pagemap.h>
#include <linux/memblock.h>
#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
#include <asm/pgalloc.h>
#include <asm/prom.h>
@@ -44,6 +46,7 @@
#include <asm/tlb.h>
#include <asm/sections.h>
#include <asm/system.h>
+#include <asm/hugetlb.h>
#include "mmu_decl.h"
@@ -123,6 +126,12 @@ void __init MMU_init(void)
/* parse args from command line */
MMU_setup();
+ /*
+ * Reserve gigantic pages for hugetlb. This MUST occur before
+ * lowmem_end_addr is initialized below.
+ */
+ reserve_hugetlb_gpages();
+
if (memblock.memory.cnt > 1) {
#ifndef CONFIG_WII
memblock.memory.cnt = 1;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index c781bbcf733..ad9cf49dfb8 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -548,4 +548,9 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
return;
hash_preload(vma->vm_mm, address, access, trap);
#endif /* CONFIG_PPC_STD_MMU */
+#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
+ && defined(CONFIG_HUGETLB_PAGE)
+ if (is_vm_hugetlb_page(vma))
+ book3e_hugetlb_preload(vma->vm_mm, address, *ptep);
+#endif
}
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 336807de550..5b63bd3da4a 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -292,6 +292,11 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
mm->context.id = MMU_NO_CONTEXT;
mm->context.active = 0;
+#ifdef CONFIG_PPC_MM_SLICES
+ if (slice_mm_new_context(mm))
+ slice_set_user_psize(mm, mmu_virtual_psize);
+#endif
+
return 0;
}
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index af40c8768a7..214130a4edc 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -27,6 +27,7 @@
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
+#include <linux/hugetlb.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
@@ -212,7 +213,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
entry = set_access_flags_filter(entry, vma, dirty);
changed = !pte_same(*(ptep), entry);
if (changed) {
- if (!(vma->vm_flags & VM_HUGETLB))
+ if (!is_vm_hugetlb_page(vma))
assert_pte_locked(vma->vm_mm, address);
__ptep_set_access_flags(ptep, entry);
flush_tlb_page_nohash(vma, address);
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 4ebb34bc01d..dc4a5f385e4 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -553,24 +553,24 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV)
rldicl r11,r16,64-VPTE_PGD_SHIFT,64-PGD_INDEX_SIZE-3
clrrdi r10,r11,3
ldx r15,r10,r15
- cmpldi cr0,r15,0
- beq virt_page_table_tlb_miss_fault
+ cmpdi cr0,r15,0
+ bge virt_page_table_tlb_miss_fault
#ifndef CONFIG_PPC_64K_PAGES
/* Get to PUD entry */
rldicl r11,r16,64-VPTE_PUD_SHIFT,64-PUD_INDEX_SIZE-3
clrrdi r10,r11,3
ldx r15,r10,r15
- cmpldi cr0,r15,0
- beq virt_page_table_tlb_miss_fault
+ cmpdi cr0,r15,0
+ bge virt_page_table_tlb_miss_fault
#endif /* CONFIG_PPC_64K_PAGES */
/* Get to PMD entry */
rldicl r11,r16,64-VPTE_PMD_SHIFT,64-PMD_INDEX_SIZE-3
clrrdi r10,r11,3
ldx r15,r10,r15
- cmpldi cr0,r15,0
- beq virt_page_table_tlb_miss_fault
+ cmpdi cr0,r15,0
+ bge virt_page_table_tlb_miss_fault
/* Ok, we're all right, we can now create a kernel translation for
* a 4K or 64K page from r16 -> r15.
@@ -802,24 +802,24 @@ htw_tlb_miss:
rldicl r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
clrrdi r10,r11,3
ldx r15,r10,r15
- cmpldi cr0,r15,0
- beq htw_tlb_miss_fault
+ cmpdi cr0,r15,0
+ bge htw_tlb_miss_fault
#ifndef CONFIG_PPC_64K_PAGES
/* Get to PUD entry */
rldicl r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
clrrdi r10,r11,3
ldx r15,r10,r15
- cmpldi cr0,r15,0
- beq htw_tlb_miss_fault
+ cmpdi cr0,r15,0
+ bge htw_tlb_miss_fault
#endif /* CONFIG_PPC_64K_PAGES */
/* Get to PMD entry */
rldicl r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
clrrdi r10,r11,3
ldx r15,r10,r15
- cmpldi cr0,r15,0
- beq htw_tlb_miss_fault
+ cmpdi cr0,r15,0
+ bge htw_tlb_miss_fault
/* Ok, we're all right, we can now create an indirect entry for
* a 1M or 256M page.
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index d32ec643c23..afc95c7304a 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -36,14 +36,49 @@
#include <linux/spinlock.h>
#include <linux/memblock.h>
#include <linux/of_fdt.h>
+#include <linux/hugetlb.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <asm/code-patching.h>
+#include <asm/hugetlb.h>
#include "mmu_decl.h"
-#ifdef CONFIG_PPC_BOOK3E
+/*
+ * This struct lists the sw-supported page sizes. The hardawre MMU may support
+ * other sizes not listed here. The .ind field is only used on MMUs that have
+ * indirect page table entries.
+ */
+#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_FSL_BOOKE
+struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+ [MMU_PAGE_4K] = {
+ .shift = 12,
+ .enc = BOOK3E_PAGESZ_4K,
+ },
+ [MMU_PAGE_4M] = {
+ .shift = 22,
+ .enc = BOOK3E_PAGESZ_4M,
+ },
+ [MMU_PAGE_16M] = {
+ .shift = 24,
+ .enc = BOOK3E_PAGESZ_16M,
+ },
+ [MMU_PAGE_64M] = {
+ .shift = 26,
+ .enc = BOOK3E_PAGESZ_64M,
+ },
+ [MMU_PAGE_256M] = {
+ .shift = 28,
+ .enc = BOOK3E_PAGESZ_256M,
+ },
+ [MMU_PAGE_1G] = {
+ .shift = 30,
+ .enc = BOOK3E_PAGESZ_1GB,
+ },
+};
+#else
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
[MMU_PAGE_4K] = {
.shift = 12,
@@ -77,6 +112,8 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
.enc = BOOK3E_PAGESZ_1GB,
},
};
+#endif /* CONFIG_FSL_BOOKE */
+
static inline int mmu_get_tsize(int psize)
{
return mmu_psize_defs[psize].enc;
@@ -87,7 +124,7 @@ static inline int mmu_get_tsize(int psize)
/* This isn't used on !Book3E for now */
return 0;
}
-#endif
+#endif /* CONFIG_PPC_BOOK3E_MMU */
/* The variables below are currently only used on 64-bit Book3E
* though this will probably be made common with other nohash
@@ -266,6 +303,11 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
+#ifdef CONFIG_HUGETLB_PAGE
+ if (is_vm_hugetlb_page(vma))
+ flush_hugetlb_page(vma, vmaddr);
+#endif
+
__flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
mmu_get_tsize(mmu_virtual_psize), 0);
}
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index d733d7ca939..ae5e0bfc023 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -32,14 +32,6 @@ config EP405
help
This option enables support for the EP405/EP405PC boards.
-config HCU4
- bool "Hcu4"
- depends on 40x
- default n
- select 405GPR
- help
- This option enables support for the Nestal Maschinen HCU4 board.
-
config HOTFOOT
bool "Hotfoot"
depends on 40x
diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile
index 56e89004c46..88c22de0c85 100644
--- a/arch/powerpc/platforms/40x/Makefile
+++ b/arch/powerpc/platforms/40x/Makefile
@@ -1,4 +1,3 @@
-obj-$(CONFIG_HCU4) += hcu4.o
obj-$(CONFIG_WALNUT) += walnut.o
obj-$(CONFIG_XILINX_VIRTEX_GENERIC_BOARD) += virtex.o
obj-$(CONFIG_EP405) += ep405.o
diff --git a/arch/powerpc/platforms/40x/hcu4.c b/arch/powerpc/platforms/40x/hcu4.c
deleted file mode 100644
index 60b2afecab7..00000000000
--- a/arch/powerpc/platforms/40x/hcu4.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Architecture- / platform-specific boot-time initialization code for
- * IBM PowerPC 4xx based boards. Adapted from original
- * code by Gary Thomas, Cort Dougan <cort@fsmlabs.com>, and Dan Malek
- * <dan@net4x.com>.
- *
- * Copyright(c) 1999-2000 Grant Erickson <grant@lcse.umn.edu>
- *
- * Rewritten and ported to the merged powerpc tree:
- * Copyright 2007 IBM Corporation
- * Josh Boyer <jwboyer@linux.vnet.ibm.com>
- *
- * 2002 (c) MontaVista, Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-
-#include <asm/machdep.h>
-#include <asm/prom.h>
-#include <asm/udbg.h>
-#include <asm/time.h>
-#include <asm/uic.h>
-#include <asm/ppc4xx.h>
-
-static __initdata struct of_device_id hcu4_of_bus[] = {
- { .compatible = "ibm,plb3", },
- { .compatible = "ibm,opb", },
- { .compatible = "ibm,ebc", },
- {},
-};
-
-static int __init hcu4_device_probe(void)
-{
- of_platform_bus_probe(NULL, hcu4_of_bus, NULL);
- return 0;
-}
-machine_device_initcall(hcu4, hcu4_device_probe);
-
-static int __init hcu4_probe(void)
-{
- unsigned long root = of_get_flat_dt_root();
-
- if (!of_flat_dt_is_compatible(root, "netstal,hcu4"))
- return 0;
-
- return 1;
-}
-
-define_machine(hcu4) {
- .name = "HCU4",
- .probe = hcu4_probe,
- .progress = udbg_progress,
- .init_IRQ = uic_init_tree,
- .get_irq = uic_get_irq,
- .restart = ppc4xx_reset_system,
- .calibrate_decr = generic_calibrate_decr,
-};
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index e06e39589a0..a85990c886e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -69,6 +69,7 @@ config PPC_BOOK3S_64
bool "Server processors"
select PPC_FPU
select PPC_HAVE_PMU_SUPPORT
+ select SYS_SUPPORTS_HUGETLBFS
config PPC_BOOK3E_64
bool "Embedded processors"
@@ -173,6 +174,7 @@ config BOOKE
config FSL_BOOKE
bool
depends on (E200 || E500) && PPC32
+ select SYS_SUPPORTS_HUGETLBFS if PHYS_64BIT
default y
# this is for common code between PPC32 & PPC64 FSL BOOKE
@@ -296,7 +298,7 @@ config PPC_BOOK3E_MMU
config PPC_MM_SLICES
bool
- default y if HUGETLB_PAGE || (PPC_STD_MMU_64 && PPC_64K_PAGES)
+ default y if (PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
default n
config VIRT_CPU_ACCOUNTING
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 26a067122a5..fc46fcac392 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -1159,6 +1159,26 @@ static int __init setup_iommu_fixed(char *str)
}
__setup("iommu_fixed=", setup_iommu_fixed);
+static u64 cell_dma_get_required_mask(struct device *dev)
+{
+ struct dma_map_ops *dma_ops;
+
+ if (!dev->dma_mask)
+ return 0;
+
+ if (!iommu_fixed_disabled &&
+ cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
+ return DMA_BIT_MASK(64);
+
+ dma_ops = get_dma_ops(dev);
+ if (dma_ops->get_required_mask)
+ return dma_ops->get_required_mask(dev);
+
+ WARN_ONCE(1, "no get_required_mask in %p ops", dma_ops);
+
+ return DMA_BIT_MASK(64);
+}
+
static int __init cell_iommu_init(void)
{
struct device_node *np;
@@ -1175,6 +1195,7 @@ static int __init cell_iommu_init(void)
/* Setup various ppc_md. callbacks */
ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup;
+ ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
ppc_md.tce_build = tce_build_cell;
ppc_md.tce_free = tce_free_cell;
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index dfe316b161a..476d9d9b240 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -148,4 +148,16 @@ config PS3_LPM
profiling support of the Cell processor with programs like
oprofile and perfmon2, then say Y or M, otherwise say N.
+config PS3GELIC_UDBG
+ bool "PS3 udbg output via UDP broadcasts on Ethernet"
+ depends on PPC_PS3
+ help
+ Enables udbg early debugging output by sending broadcast UDP
+ via the Ethernet port (UDP port number 18194).
+
+ This driver uses a trivial implementation and is independent
+ from the main network driver.
+
+ If in doubt, say N here.
+
endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
index ac1bdf844ec..02b9e636dab 100644
--- a/arch/powerpc/platforms/ps3/Makefile
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -2,6 +2,7 @@ obj-y += setup.o mm.o time.o hvcall.o htab.o repository.o
obj-y += interrupt.o exports.o os-area.o
obj-y += system-bus.o
+obj-$(CONFIG_PS3GELIC_UDBG) += gelic_udbg.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SPU_BASE) += spu.o
obj-y += device-init.o
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
new file mode 100644
index 00000000000..20b46a19a48
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -0,0 +1,273 @@
+/*
+ * udbg debug output routine via GELIC UDP broadcasts
+ *
+ * Copyright (C) 2007 Sony Computer Entertainment Inc.
+ * Copyright 2006, 2007 Sony Corporation
+ * Copyright (C) 2010 Hector Martin <hector@marcansoft.com>
+ * Copyright (C) 2011 Andre Heider <a.heider@gmail.com>
+ *
+ * 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/io.h>
+#include <asm/udbg.h>
+#include <asm/lv1call.h>
+
+#define GELIC_BUS_ID 1
+#define GELIC_DEVICE_ID 0
+#define GELIC_DEBUG_PORT 18194
+#define GELIC_MAX_MESSAGE_SIZE 1000
+
+#define GELIC_LV1_GET_MAC_ADDRESS 1
+#define GELIC_LV1_GET_VLAN_ID 4
+#define GELIC_LV1_VLAN_TX_ETHERNET_0 2
+
+#define GELIC_DESCR_DMA_STAT_MASK 0xf0000000
+#define GELIC_DESCR_DMA_CARDOWNED 0xa0000000
+
+#define GELIC_DESCR_TX_DMA_IKE 0x00080000
+#define GELIC_DESCR_TX_DMA_NO_CHKSUM 0x00000000
+#define GELIC_DESCR_TX_DMA_FRAME_TAIL 0x00040000
+
+#define GELIC_DESCR_DMA_CMD_NO_CHKSUM (GELIC_DESCR_DMA_CARDOWNED | \
+ GELIC_DESCR_TX_DMA_IKE | \
+ GELIC_DESCR_TX_DMA_NO_CHKSUM)
+
+static u64 bus_addr;
+
+struct gelic_descr {
+ /* as defined by the hardware */
+ __be32 buf_addr;
+ __be32 buf_size;
+ __be32 next_descr_addr;
+ __be32 dmac_cmd_status;
+ __be32 result_size;
+ __be32 valid_size; /* all zeroes for tx */
+ __be32 data_status;
+ __be32 data_error; /* all zeroes for tx */
+} __attribute__((aligned(32)));
+
+struct debug_block {
+ struct gelic_descr descr;
+ u8 pkt[1520];
+} __packed;
+
+struct ethhdr {
+ u8 dest[6];
+ u8 src[6];
+ u16 type;
+} __packed;
+
+struct vlantag {
+ u16 vlan;
+ u16 subtype;
+} __packed;
+
+struct iphdr {
+ u8 ver_len;
+ u8 dscp_ecn;
+ u16 total_length;
+ u16 ident;
+ u16 frag_off_flags;
+ u8 ttl;
+ u8 proto;
+ u16 checksum;
+ u32 src;
+ u32 dest;
+} __packed;
+
+struct udphdr {
+ u16 src;
+ u16 dest;
+ u16 len;
+ u16 checksum;
+} __packed;
+
+static __iomem struct ethhdr *h_eth;
+static __iomem struct vlantag *h_vlan;
+static __iomem struct iphdr *h_ip;
+static __iomem struct udphdr *h_udp;
+
+static __iomem char *pmsg;
+static __iomem char *pmsgc;
+
+static __iomem struct debug_block dbg __attribute__((aligned(32)));
+
+static int header_size;
+
+static void map_dma_mem(int bus_id, int dev_id, void *start, size_t len,
+ u64 *real_bus_addr)
+{
+ s64 result;
+ u64 real_addr = ((u64)start) & 0x0fffffffffffffffUL;
+ u64 real_end = real_addr + len;
+ u64 map_start = real_addr & ~0xfff;
+ u64 map_end = (real_end + 0xfff) & ~0xfff;
+ u64 bus_addr = 0;
+
+ u64 flags = 0xf800000000000000UL;
+
+ result = lv1_allocate_device_dma_region(bus_id, dev_id,
+ map_end - map_start, 12, 0,
+ &bus_addr);
+ if (result)
+ lv1_panic(0);
+
+ result = lv1_map_device_dma_region(bus_id, dev_id, map_start,
+ bus_addr, map_end - map_start,
+ flags);
+ if (result)
+ lv1_panic(0);
+
+ *real_bus_addr = bus_addr + real_addr - map_start;
+}
+
+static int unmap_dma_mem(int bus_id, int dev_id, u64 bus_addr, size_t len)
+{
+ s64 result;
+ u64 real_bus_addr;
+
+ real_bus_addr = bus_addr & ~0xfff;
+ len += bus_addr - real_bus_addr;
+ len = (len + 0xfff) & ~0xfff;
+
+ result = lv1_unmap_device_dma_region(bus_id, dev_id, real_bus_addr,
+ len);
+ if (result)
+ return result;
+
+ return lv1_free_device_dma_region(bus_id, dev_id, real_bus_addr);
+}
+
+static void gelic_debug_init(void)
+{
+ s64 result;
+ u64 v2;
+ u64 mac;
+ u64 vlan_id;
+
+ result = lv1_open_device(GELIC_BUS_ID, GELIC_DEVICE_ID, 0);
+ if (result)
+ lv1_panic(0);
+
+ map_dma_mem(GELIC_BUS_ID, GELIC_DEVICE_ID, &dbg, sizeof(dbg),
+ &bus_addr);
+
+ memset(&dbg, 0, sizeof(dbg));
+
+ dbg.descr.buf_addr = bus_addr + offsetof(struct debug_block, pkt);
+
+ wmb();
+
+ result = lv1_net_control(GELIC_BUS_ID, GELIC_DEVICE_ID,
+ GELIC_LV1_GET_MAC_ADDRESS, 0, 0, 0,
+ &mac, &v2);
+ if (result)
+ lv1_panic(0);
+
+ mac <<= 16;
+
+ h_eth = (struct ethhdr *)dbg.pkt;
+
+ memset(&h_eth->dest, 0xff, 6);
+ memcpy(&h_eth->src, &mac, 6);
+
+ header_size = sizeof(struct ethhdr);
+
+ result = lv1_net_control(GELIC_BUS_ID, GELIC_DEVICE_ID,
+ GELIC_LV1_GET_VLAN_ID,
+ GELIC_LV1_VLAN_TX_ETHERNET_0, 0, 0,
+ &vlan_id, &v2);
+ if (!result) {
+ h_eth->type = 0x8100;
+
+ header_size += sizeof(struct vlantag);
+ h_vlan = (struct vlantag *)(h_eth + 1);
+ h_vlan->vlan = vlan_id;
+ h_vlan->subtype = 0x0800;
+ h_ip = (struct iphdr *)(h_vlan + 1);
+ } else {
+ h_eth->type = 0x0800;
+ h_ip = (struct iphdr *)(h_eth + 1);
+ }
+
+ header_size += sizeof(struct iphdr);
+ h_ip->ver_len = 0x45;
+ h_ip->ttl = 10;
+ h_ip->proto = 0x11;
+ h_ip->src = 0x00000000;
+ h_ip->dest = 0xffffffff;
+
+ header_size += sizeof(struct udphdr);
+ h_udp = (struct udphdr *)(h_ip + 1);
+ h_udp->src = GELIC_DEBUG_PORT;
+ h_udp->dest = GELIC_DEBUG_PORT;
+
+ pmsgc = pmsg = (char *)(h_udp + 1);
+}
+
+static void gelic_debug_shutdown(void)
+{
+ if (bus_addr)
+ unmap_dma_mem(GELIC_BUS_ID, GELIC_DEVICE_ID,
+ bus_addr, sizeof(dbg));
+ lv1_close_device(GELIC_BUS_ID, GELIC_DEVICE_ID);
+}
+
+static void gelic_sendbuf(int msgsize)
+{
+ u16 *p;
+ u32 sum;
+ int i;
+
+ dbg.descr.buf_size = header_size + msgsize;
+ h_ip->total_length = msgsize + sizeof(struct udphdr) +
+ sizeof(struct iphdr);
+ h_udp->len = msgsize + sizeof(struct udphdr);
+
+ h_ip->checksum = 0;
+ sum = 0;
+ p = (u16 *)h_ip;
+ for (i = 0; i < 5; i++)
+ sum += *p++;
+ h_ip->checksum = ~(sum + (sum >> 16));
+
+ dbg.descr.dmac_cmd_status = GELIC_DESCR_DMA_CMD_NO_CHKSUM |
+ GELIC_DESCR_TX_DMA_FRAME_TAIL;
+ dbg.descr.result_size = 0;
+ dbg.descr.data_status = 0;
+
+ wmb();
+
+ lv1_net_start_tx_dma(GELIC_BUS_ID, GELIC_DEVICE_ID, bus_addr, 0);
+
+ while ((dbg.descr.dmac_cmd_status & GELIC_DESCR_DMA_STAT_MASK) ==
+ GELIC_DESCR_DMA_CARDOWNED)
+ cpu_relax();
+}
+
+static void ps3gelic_udbg_putc(char ch)
+{
+ *pmsgc++ = ch;
+ if (ch == '\n' || (pmsgc-pmsg) >= GELIC_MAX_MESSAGE_SIZE) {
+ gelic_sendbuf(pmsgc-pmsg);
+ pmsgc = pmsg;
+ }
+}
+
+void __init udbg_init_ps3gelic(void)
+{
+ gelic_debug_init();
+ udbg_putc = ps3gelic_udbg_putc;
+}
+
+void udbg_shutdown_ps3gelic(void)
+{
+ udbg_putc = NULL;
+ gelic_debug_shutdown();
+}
+EXPORT_SYMBOL(udbg_shutdown_ps3gelic);
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 23083c39752..688141c76e0 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -695,12 +695,18 @@ static int ps3_dma_supported(struct device *_dev, u64 mask)
return mask >= DMA_BIT_MASK(32);
}
+static u64 ps3_dma_get_required_mask(struct device *_dev)
+{
+ return DMA_BIT_MASK(32);
+}
+
static struct dma_map_ops ps3_sb_dma_ops = {
.alloc_coherent = ps3_alloc_coherent,
.free_coherent = ps3_free_coherent,
.map_sg = ps3_sb_map_sg,
.unmap_sg = ps3_sb_unmap_sg,
.dma_supported = ps3_dma_supported,
+ .get_required_mask = ps3_dma_get_required_mask,
.map_page = ps3_sb_map_page,
.unmap_page = ps3_unmap_page,
};
@@ -711,6 +717,7 @@ static struct dma_map_ops ps3_ioc0_dma_ops = {
.map_sg = ps3_ioc0_map_sg,
.unmap_sg = ps3_ioc0_unmap_sg,
.dma_supported = ps3_dma_supported,
+ .get_required_mask = ps3_dma_get_required_mask,
.map_page = ps3_ioc0_map_page,
.unmap_page = ps3_unmap_page,
};
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 05cf4769b88..c81f6bb9c10 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -15,6 +15,7 @@ config PPC_PSERIES
select PPC_UDBG_16550
select PPC_NATIVE
select PPC_PCI_CHOICE if EXPERT
+ select ZLIB_DEFLATE
default y
config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index e9be25bc571..0f1b706506e 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -112,6 +112,7 @@ void dlpar_free_cc_nodes(struct device_node *dn)
dlpar_free_one_cc_node(dn);
}
+#define COMPLETE 0
#define NEXT_SIBLING 1
#define NEXT_CHILD 2
#define NEXT_PROPERTY 3
@@ -158,6 +159,9 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
spin_unlock(&rtas_data_buf_lock);
switch (rc) {
+ case COMPLETE:
+ break;
+
case NEXT_SIBLING:
dn = dlpar_parse_cc_node(ccwa);
if (!dn)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ada6e07532e..d42f37d8a44 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -1338,7 +1338,7 @@ static const struct file_operations proc_eeh_operations = {
static int __init eeh_init_proc(void)
{
if (machine_is(pseries))
- proc_create("ppc64/eeh", 0, NULL, &proc_eeh_operations);
+ proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
return 0;
}
__initcall(eeh_init_proc);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 01faab9456c..5905a3b9f7e 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -939,14 +939,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
if (ret) {
dev_info(&dev->dev, "failed to map direct window for %s: %d\n",
dn->full_name, ret);
- goto out_clear_window;
+ goto out_free_window;
}
ret = prom_add_property(pdn, win64);
if (ret) {
dev_err(&dev->dev, "unable to add dma window property for %s: %d",
pdn->full_name, ret);
- goto out_clear_window;
+ goto out_free_window;
}
window->device = pdn;
@@ -958,6 +958,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
dma_addr = of_read_number(&create.addr_hi, 2);
goto out_unlock;
+out_free_window:
+ kfree(window);
+
out_clear_window:
remove_ddw(pdn);
@@ -1077,12 +1080,38 @@ check_mask:
return 0;
}
+static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
+{
+ if (!dev->dma_mask)
+ return 0;
+
+ if (!disable_ddw && dev_is_pci(dev)) {
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct device_node *dn;
+
+ dn = pci_device_to_OF_node(pdev);
+
+ /* search upwards for ibm,dma-window */
+ for (; dn && PCI_DN(dn) && !PCI_DN(dn)->iommu_table;
+ dn = dn->parent)
+ if (of_get_property(dn, "ibm,dma-window", NULL))
+ break;
+ /* if there is a ibm,ddw-applicable property require 64 bits */
+ if (dn && PCI_DN(dn) &&
+ of_get_property(dn, "ibm,ddw-applicable", NULL))
+ return DMA_BIT_MASK(64);
+ }
+
+ return dma_iommu_ops.get_required_mask(dev);
+}
+
#else /* CONFIG_PCI */
#define pci_dma_bus_setup_pSeries NULL
#define pci_dma_dev_setup_pSeries NULL
#define pci_dma_bus_setup_pSeriesLP NULL
#define pci_dma_dev_setup_pSeriesLP NULL
#define dma_set_mask_pSeriesLP NULL
+#define dma_get_required_mask_pSeriesLP NULL
#endif /* !CONFIG_PCI */
static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1186,6 +1215,7 @@ void iommu_init_early_pSeries(void)
ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
+ ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
} else {
ppc_md.tce_build = tce_build_pSeries;
ppc_md.tce_free = tce_free_pSeries;
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 00cc3a09488..a76b22844d1 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -18,6 +18,8 @@
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/kmsg_dump.h>
+#include <linux/ctype.h>
+#include <linux/zlib.h>
#include <asm/uaccess.h>
#include <asm/nvram.h>
#include <asm/rtas.h>
@@ -78,8 +80,41 @@ static struct kmsg_dumper nvram_kmsg_dumper = {
#define NVRAM_RTAS_READ_TIMEOUT 5 /* seconds */
static unsigned long last_unread_rtas_event; /* timestamp */
-/* We preallocate oops_buf during init to avoid kmalloc during oops/panic. */
-static char *oops_buf;
+/*
+ * For capturing and compressing an oops or panic report...
+
+ * big_oops_buf[] holds the uncompressed text we're capturing.
+ *
+ * oops_buf[] holds the compressed text, preceded by a prefix.
+ * The prefix is just a u16 holding the length of the compressed* text.
+ * (*Or uncompressed, if compression fails.) oops_buf[] gets written
+ * to NVRAM.
+ *
+ * oops_len points to the prefix. oops_data points to the compressed text.
+ *
+ * +- oops_buf
+ * | +- oops_data
+ * v v
+ * +------------+-----------------------------------------------+
+ * | length | text |
+ * | (2 bytes) | (oops_data_sz bytes) |
+ * +------------+-----------------------------------------------+
+ * ^
+ * +- oops_len
+ *
+ * We preallocate these buffers during init to avoid kmalloc during oops/panic.
+ */
+static size_t big_oops_buf_sz;
+static char *big_oops_buf, *oops_buf;
+static u16 *oops_len;
+static char *oops_data;
+static size_t oops_data_sz;
+
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
{
@@ -387,11 +422,44 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
sizeof(rtas_log_partition));
}
oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+ if (!oops_buf) {
+ pr_err("nvram: No memory for %s partition\n",
+ oops_log_partition.name);
+ return;
+ }
+ oops_len = (u16*) oops_buf;
+ oops_data = oops_buf + sizeof(u16);
+ oops_data_sz = oops_log_partition.size - sizeof(u16);
+
+ /*
+ * Figure compression (preceded by elimination of each line's <n>
+ * severity prefix) will reduce the oops/panic report to at most
+ * 45% of its original size.
+ */
+ big_oops_buf_sz = (oops_data_sz * 100) / 45;
+ big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+ if (big_oops_buf) {
+ stream.workspace = kmalloc(zlib_deflate_workspacesize(
+ WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+ if (!stream.workspace) {
+ pr_err("nvram: No memory for compression workspace; "
+ "skipping compression of %s partition data\n",
+ oops_log_partition.name);
+ kfree(big_oops_buf);
+ big_oops_buf = NULL;
+ }
+ } else {
+ pr_err("No memory for uncompressed %s data; "
+ "skipping compression\n", oops_log_partition.name);
+ stream.workspace = NULL;
+ }
+
rc = kmsg_dump_register(&nvram_kmsg_dumper);
if (rc != 0) {
pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
kfree(oops_buf);
- return;
+ kfree(big_oops_buf);
+ kfree(stream.workspace);
}
}
@@ -473,7 +541,83 @@ static int clobbering_unread_rtas_event(void)
NVRAM_RTAS_READ_TIMEOUT);
}
-/* our kmsg_dump callback */
+/* Squeeze out each line's <n> severity prefix. */
+static size_t elide_severities(char *buf, size_t len)
+{
+ char *in, *out, *buf_end = buf + len;
+ /* Assume a <n> at the very beginning marks the start of a line. */
+ int newline = 1;
+
+ in = out = buf;
+ while (in < buf_end) {
+ if (newline && in+3 <= buf_end &&
+ *in == '<' && isdigit(in[1]) && in[2] == '>') {
+ in += 3;
+ newline = 0;
+ } else {
+ newline = (*in == '\n');
+ *out++ = *in++;
+ }
+ }
+ return out - buf;
+}
+
+/* Derived from logfs_compress() */
+static int nvram_compress(const void *in, void *out, size_t inlen,
+ size_t outlen)
+{
+ int err, ret;
+
+ ret = -EIO;
+ err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+ MEM_LEVEL, Z_DEFAULT_STRATEGY);
+ if (err != Z_OK)
+ goto error;
+
+ stream.next_in = in;
+ stream.avail_in = inlen;
+ stream.total_in = 0;
+ stream.next_out = out;
+ stream.avail_out = outlen;
+ stream.total_out = 0;
+
+ err = zlib_deflate(&stream, Z_FINISH);
+ if (err != Z_STREAM_END)
+ goto error;
+
+ err = zlib_deflateEnd(&stream);
+ if (err != Z_OK)
+ goto error;
+
+ if (stream.total_out >= stream.total_in)
+ goto error;
+
+ ret = stream.total_out;
+error:
+ return ret;
+}
+
+/* Compress the text from big_oops_buf into oops_buf. */
+static int zip_oops(size_t text_len)
+{
+ int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
+ oops_data_sz);
+ if (zipped_len < 0) {
+ pr_err("nvram: compression failed; returned %d\n", zipped_len);
+ pr_err("nvram: logging uncompressed oops/panic report\n");
+ return -1;
+ }
+ *oops_len = (u16) zipped_len;
+ return 0;
+}
+
+/*
+ * This is our kmsg_dump callback, called after an oops or panic report
+ * has been written to the printk buffer. We want to capture as much
+ * of the printk buffer as possible. First, capture as much as we can
+ * that we think will compress sufficiently to fit in the lnx,oops-log
+ * partition. If that's too much, go back and capture uncompressed text.
+ */
static void oops_to_nvram(struct kmsg_dumper *dumper,
enum kmsg_dump_reason reason,
const char *old_msgs, unsigned long old_len,
@@ -482,6 +626,8 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
static unsigned int oops_count = 0;
static bool panicking = false;
size_t text_len;
+ unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+ int rc = -1;
switch (reason) {
case KMSG_DUMP_RESTART:
@@ -509,8 +655,19 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
if (clobbering_unread_rtas_event())
return;
- text_len = capture_last_msgs(old_msgs, old_len, new_msgs, new_len,
- oops_buf, oops_log_partition.size);
+ if (big_oops_buf) {
+ text_len = capture_last_msgs(old_msgs, old_len,
+ new_msgs, new_len, big_oops_buf, big_oops_buf_sz);
+ text_len = elide_severities(big_oops_buf, text_len);
+ rc = zip_oops(text_len);
+ }
+ if (rc != 0) {
+ text_len = capture_last_msgs(old_msgs, old_len,
+ new_msgs, new_len, oops_data, oops_data_sz);
+ err_type = ERR_TYPE_KERNEL_PANIC;
+ *oops_len = (u16) text_len;
+ }
+
(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
- (int) text_len, ERR_TYPE_KERNEL_PANIC, ++oops_count);
+ (int) (sizeof(*oops_len) + *oops_len), err_type, ++oops_count);
}
diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig
index c3c48eb62cc..f4fb837873f 100644
--- a/arch/powerpc/platforms/wsp/Kconfig
+++ b/arch/powerpc/platforms/wsp/Kconfig
@@ -1,5 +1,12 @@
config PPC_WSP
bool
+ select PPC_A2
+ select PPC_SCOM
+ select PPC_XICS
+ select PPC_ICP_NATIVE
+ select PCI
+ select PPC_IO_WORKAROUNDS if PCI
+ select PPC_INDIRECT_PIO if PCI
default n
menu "WSP platform selection"
@@ -7,13 +14,9 @@ menu "WSP platform selection"
config PPC_PSR2
bool "PSR-2 platform"
- select PPC_A2
select GENERIC_TBSYNC
- select PPC_SCOM
select EPAPR_BOOT
select PPC_WSP
- select PPC_XICS
- select PPC_ICP_NATIVE
default y
endmenu
diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile
index 095be73d6cd..a1486b436f0 100644
--- a/arch/powerpc/platforms/wsp/Makefile
+++ b/arch/powerpc/platforms/wsp/Makefile
@@ -4,3 +4,5 @@ obj-y += setup.o ics.o
obj-$(CONFIG_PPC_PSR2) += psr2.o opb_pic.o
obj-$(CONFIG_PPC_WSP) += scom_wsp.o
obj-$(CONFIG_SMP) += smp.o scom_smp.o
+obj-$(CONFIG_PCI) += wsp_pci.o
+obj-$(CONFIG_PCI_MSI) += msi.o \ No newline at end of file
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index e53bd9e7b12..57687439254 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -710,3 +710,51 @@ void __init wsp_init_irq(void)
/* We need to patch our irq chip's EOI to point to the right ICP */
wsp_irq_chip.irq_eoi = icp_ops->eoi;
}
+
+#ifdef CONFIG_PCI_MSI
+static void wsp_ics_msi_unmask_irq(struct irq_data *d)
+{
+ wsp_chip_unmask_irq(d);
+ unmask_msi_irq(d);
+}
+
+static unsigned int wsp_ics_msi_startup(struct irq_data *d)
+{
+ wsp_ics_msi_unmask_irq(d);
+ return 0;
+}
+
+static void wsp_ics_msi_mask_irq(struct irq_data *d)
+{
+ mask_msi_irq(d);
+ wsp_chip_mask_irq(d);
+}
+
+/*
+ * we do it this way because we reassinge default EOI handling in
+ * irq_init() above
+ */
+static void wsp_ics_eoi(struct irq_data *data)
+{
+ wsp_irq_chip.irq_eoi(data);
+}
+
+static struct irq_chip wsp_ics_msi = {
+ .name = "WSP ICS MSI",
+ .irq_startup = wsp_ics_msi_startup,
+ .irq_mask = wsp_ics_msi_mask_irq,
+ .irq_unmask = wsp_ics_msi_unmask_irq,
+ .irq_eoi = wsp_ics_eoi,
+ .irq_set_affinity = wsp_chip_set_affinity
+};
+
+void wsp_ics_set_msi_chip(unsigned int irq)
+{
+ irq_set_chip(irq, &wsp_ics_msi);
+}
+
+void wsp_ics_set_std_chip(unsigned int irq)
+{
+ irq_set_chip(irq, &wsp_irq_chip);
+}
+#endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h
index e34d5310264..07b644e0cf9 100644
--- a/arch/powerpc/platforms/wsp/ics.h
+++ b/arch/powerpc/platforms/wsp/ics.h
@@ -17,4 +17,9 @@ extern void wsp_init_irq(void);
extern int wsp_ics_alloc_irq(struct device_node *dn, int num);
extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq);
+#ifdef CONFIG_PCI_MSI
+extern void wsp_ics_set_msi_chip(unsigned int irq);
+extern void wsp_ics_set_std_chip(unsigned int irq);
+#endif /* CONFIG_PCI_MSI */
+
#endif /* __ICS_H */
diff --git a/arch/powerpc/platforms/wsp/msi.c b/arch/powerpc/platforms/wsp/msi.c
new file mode 100644
index 00000000000..380882f27ad
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/msi.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ * 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 <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include "msi.h"
+#include "ics.h"
+#include "wsp_pci.h"
+
+/* Magic addresses for 32 & 64-bit MSIs with hardcoded MVE 0 */
+#define MSI_ADDR_32 0xFFFF0000ul
+#define MSI_ADDR_64 0x1000000000000000ul
+
+int wsp_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ struct pci_controller *phb;
+ struct msi_desc *entry;
+ struct msi_msg msg;
+ unsigned int virq;
+ int hwirq;
+
+ phb = pci_bus_to_host(dev->bus);
+ if (!phb)
+ return -ENOENT;
+
+ entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+ if (entry->msi_attrib.is_64) {
+ msg.address_lo = 0;
+ msg.address_hi = MSI_ADDR_64 >> 32;
+ } else {
+ msg.address_lo = MSI_ADDR_32;
+ msg.address_hi = 0;
+ }
+
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ hwirq = wsp_ics_alloc_irq(phb->dn, 1);
+ if (hwirq < 0) {
+ dev_warn(&dev->dev, "wsp_msi: hwirq alloc failed!\n");
+ return hwirq;
+ }
+
+ virq = irq_create_mapping(NULL, hwirq);
+ if (virq == NO_IRQ) {
+ dev_warn(&dev->dev, "wsp_msi: virq alloc failed!\n");
+ return -1;
+ }
+
+ dev_dbg(&dev->dev, "wsp_msi: allocated irq %#x/%#x\n",
+ hwirq, virq);
+
+ wsp_ics_set_msi_chip(virq);
+ irq_set_msi_desc(virq, entry);
+ msg.data = hwirq & XIVE_ADDR_MASK;
+ write_msi_msg(virq, &msg);
+ }
+
+ return 0;
+}
+
+void wsp_teardown_msi_irqs(struct pci_dev *dev)
+{
+ struct pci_controller *phb;
+ struct msi_desc *entry;
+ int hwirq;
+
+ phb = pci_bus_to_host(dev->bus);
+
+ dev_dbg(&dev->dev, "wsp_msi: tearing down msi irqs\n");
+
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ if (entry->irq == NO_IRQ)
+ continue;
+
+ irq_set_msi_desc(entry->irq, NULL);
+ wsp_ics_set_std_chip(entry->irq);
+
+ hwirq = virq_to_hw(entry->irq);
+ /* In this order to avoid racing with irq_create_mapping() */
+ irq_dispose_mapping(entry->irq);
+ wsp_ics_free_irq(phb->dn, hwirq);
+ }
+}
+
+void wsp_setup_phb_msi(struct pci_controller *phb)
+{
+ /* Create a single MVE at offset 0 that matches everything */
+ out_be64(phb->cfg_data + PCIE_REG_IODA_ADDR, PCIE_REG_IODA_AD_TBL_MVT);
+ out_be64(phb->cfg_data + PCIE_REG_IODA_DATA0, 1ull << 63);
+
+ ppc_md.setup_msi_irqs = wsp_setup_msi_irqs;
+ ppc_md.teardown_msi_irqs = wsp_teardown_msi_irqs;
+}
diff --git a/arch/powerpc/platforms/wsp/msi.h b/arch/powerpc/platforms/wsp/msi.h
new file mode 100644
index 00000000000..0ab27b71b24
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/msi.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ * 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.
+ */
+
+#ifndef __WSP_MSI_H
+#define __WSP_MSI_H
+
+#ifdef CONFIG_PCI_MSI
+extern void wsp_setup_phb_msi(struct pci_controller *phb);
+#else
+static inline void wsp_setup_phb_msi(struct pci_controller *phb) { }
+#endif
+
+#endif /* __WSP_MSI_H */
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
index 40f28916ff6..166f2e4b4be 100644
--- a/arch/powerpc/platforms/wsp/psr2.c
+++ b/arch/powerpc/platforms/wsp/psr2.c
@@ -63,6 +63,10 @@ static void __init psr2_setup_arch(void)
#ifdef CONFIG_SMP
a2_setup_smp();
#endif
+#ifdef CONFIG_PCI
+ wsp_setup_pci();
+#endif
+
}
static int __init psr2_probe(void)
diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h
index 7c3e087fd2f..33479818f62 100644
--- a/arch/powerpc/platforms/wsp/wsp.h
+++ b/arch/powerpc/platforms/wsp/wsp.h
@@ -3,6 +3,9 @@
#include <asm/wsp.h>
+/* Devtree compatible strings for major devices */
+#define PCIE_COMPATIBLE "ibm,wsp-pciex"
+
extern void wsp_setup_pci(void);
extern void scom_init_wsp(void);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
new file mode 100644
index 00000000000..e0262cd0e2d
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -0,0 +1,1133 @@
+/*
+ * Copyright 2010 Ben Herrenschmidt, IBM Corporation
+ *
+ * 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.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/debugfs.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/iommu.h>
+#include <asm/io-workarounds.h>
+
+#include "wsp.h"
+#include "wsp_pci.h"
+#include "msi.h"
+
+
+/* Max number of TVTs for one table. Only 32-bit tables can use
+ * multiple TVTs and so the max currently supported is thus 8
+ * since only 2G of DMA space is supported
+ */
+#define MAX_TABLE_TVT_COUNT 8
+
+struct wsp_dma_table {
+ struct list_head link;
+ struct iommu_table table;
+ struct wsp_phb *phb;
+ struct page *tces[MAX_TABLE_TVT_COUNT];
+};
+
+/* We support DMA regions from 0...2G in 32bit space (no support for
+ * 64-bit DMA just yet). Each device gets a separate TCE table (TVT
+ * entry) with validation enabled (though not supported by SimiCS
+ * just yet).
+ *
+ * To simplify things, we divide this 2G space into N regions based
+ * on the constant below which could be turned into a tunable eventually
+ *
+ * We then assign dynamically those regions to devices as they show up.
+ *
+ * We use a bitmap as an allocator for these.
+ *
+ * Tables are allocated/created dynamically as devices are discovered,
+ * multiple TVT entries are used if needed
+ *
+ * When 64-bit DMA support is added we should simply use a separate set
+ * of larger regions (the HW supports 64 TVT entries). We can
+ * additionally create a bypass region in 64-bit space for performances
+ * though that would have a cost in term of security.
+ *
+ * If you set NUM_DMA32_REGIONS to 1, then a single table is shared
+ * for all devices and bus/dev/fn validation is disabled
+ *
+ * Note that a DMA32 region cannot be smaller than 256M so the max
+ * supported here for now is 8. We don't yet support sharing regions
+ * between multiple devices so the max number of devices supported
+ * is MAX_TABLE_TVT_COUNT.
+ */
+#define NUM_DMA32_REGIONS 1
+
+struct wsp_phb {
+ struct pci_controller *hose;
+
+ /* Lock controlling access to the list of dma tables.
+ * It does -not- protect against dma_* operations on
+ * those tables, those should be stopped before an entry
+ * is removed from the list.
+ *
+ * The lock is also used for error handling operations
+ */
+ spinlock_t lock;
+ struct list_head dma_tables;
+ unsigned long dma32_map;
+ unsigned long dma32_base;
+ unsigned int dma32_num_regions;
+ unsigned long dma32_region_size;
+
+ /* Debugfs stuff */
+ struct dentry *ddir;
+
+ struct list_head all;
+};
+static LIST_HEAD(wsp_phbs);
+
+//#define cfg_debug(fmt...) pr_debug(fmt)
+#define cfg_debug(fmt...)
+
+
+static int wsp_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+ int offset, int len, u32 *val)
+{
+ struct pci_controller *hose;
+ int suboff;
+ u64 addr;
+
+ hose = pci_bus_to_host(bus);
+ if (hose == NULL)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ if (offset >= 0x1000)
+ return PCIBIOS_BAD_REGISTER_NUMBER;
+ addr = PCIE_REG_CA_ENABLE |
+ ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
+ ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
+ ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
+ suboff = offset & 3;
+
+ /*
+ * Note: the caller has already checked that offset is
+ * suitably aligned and that len is 1, 2 or 4.
+ */
+
+ switch (len) {
+ case 1:
+ addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+ out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+ *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
+ >> (suboff << 3)) & 0xff;
+ cfg_debug("read 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
+ bus->number, devfn >> 3, devfn & 7,
+ offset, suboff, addr, *val);
+ break;
+ case 2:
+ addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+ out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+ *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
+ >> (suboff << 3)) & 0xffff;
+ cfg_debug("read 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
+ bus->number, devfn >> 3, devfn & 7,
+ offset, suboff, addr, *val);
+ break;
+ default:
+ addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
+ out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+ *val = in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA);
+ cfg_debug("read 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
+ bus->number, devfn >> 3, devfn & 7,
+ offset, suboff, addr, *val);
+ break;
+ }
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int wsp_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+ int offset, int len, u32 val)
+{
+ struct pci_controller *hose;
+ int suboff;
+ u64 addr;
+
+ hose = pci_bus_to_host(bus);
+ if (hose == NULL)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ if (offset >= 0x1000)
+ return PCIBIOS_BAD_REGISTER_NUMBER;
+ addr = PCIE_REG_CA_ENABLE |
+ ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
+ ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
+ ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
+ suboff = offset & 3;
+
+ /*
+ * Note: the caller has already checked that offset is
+ * suitably aligned and that len is 1, 2 or 4.
+ */
+ switch (len) {
+ case 1:
+ addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+ val <<= suboff << 3;
+ out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+ out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+ cfg_debug("write 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
+ bus->number, devfn >> 3, devfn & 7,
+ offset, suboff, addr, val);
+ break;
+ case 2:
+ addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+ val <<= suboff << 3;
+ out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+ out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+ cfg_debug("write 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
+ bus->number, devfn >> 3, devfn & 7,
+ offset, suboff, addr, val);
+ break;
+ default:
+ addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
+ out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+ out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+ cfg_debug("write 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
+ bus->number, devfn >> 3, devfn & 7,
+ offset, suboff, addr, val);
+ break;
+ }
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops wsp_pcie_pci_ops =
+{
+ .read = wsp_pcie_read_config,
+ .write = wsp_pcie_write_config,
+};
+
+#define TCE_SHIFT 12
+#define TCE_PAGE_SIZE (1 << TCE_SHIFT)
+#define TCE_PCI_WRITE 0x2 /* write from PCI allowed */
+#define TCE_PCI_READ 0x1 /* read from PCI allowed */
+#define TCE_RPN_MASK 0x3fffffffffful /* 42-bit RPN (4K pages) */
+#define TCE_RPN_SHIFT 12
+
+//#define dma_debug(fmt...) pr_debug(fmt)
+#define dma_debug(fmt...)
+
+static int tce_build_wsp(struct iommu_table *tbl, long index, long npages,
+ unsigned long uaddr, enum dma_data_direction direction,
+ struct dma_attrs *attrs)
+{
+ struct wsp_dma_table *ptbl = container_of(tbl,
+ struct wsp_dma_table,
+ table);
+ u64 proto_tce;
+ u64 *tcep;
+ u64 rpn;
+
+ proto_tce = TCE_PCI_READ;
+#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+ proto_tce |= TCE_PCI_WRITE;
+#else
+ if (direction != DMA_TO_DEVICE)
+ proto_tce |= TCE_PCI_WRITE;
+#endif
+
+ /* XXX Make this faster by factoring out the page address for
+ * within a TCE table
+ */
+ while (npages--) {
+ /* We don't use it->base as the table can be scattered */
+ tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
+ tcep += (index & 0xffff);
+
+ /* can't move this out since we might cross LMB boundary */
+ rpn = __pa(uaddr) >> TCE_SHIFT;
+ *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+
+ dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n",
+ tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT);
+
+ uaddr += TCE_PAGE_SIZE;
+ index++;
+ }
+ return 0;
+}
+
+static void tce_free_wsp(struct iommu_table *tbl, long index, long npages)
+{
+ struct wsp_dma_table *ptbl = container_of(tbl,
+ struct wsp_dma_table,
+ table);
+#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+ struct pci_controller *hose = ptbl->phb->hose;
+#endif
+ u64 *tcep;
+
+ /* XXX Make this faster by factoring out the page address for
+ * within a TCE table. Also use line-kill option to kill multiple
+ * TCEs at once
+ */
+ while (npages--) {
+ /* We don't use it->base as the table can be scattered */
+ tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
+ tcep += (index & 0xffff);
+ dma_debug("[DMA] TCE %p cleared\n", tcep);
+ *tcep = 0;
+#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+ /* Don't write there since it would pollute other MMIO accesses */
+ out_be64(hose->cfg_data + PCIE_REG_TCE_KILL,
+ PCIE_REG_TCEKILL_SINGLE | PCIE_REG_TCEKILL_PS_4K |
+ (__pa(tcep) & PCIE_REG_TCEKILL_ADDR_MASK));
+#endif
+ index++;
+ }
+}
+
+static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb,
+ unsigned int region,
+ struct pci_dev *validate)
+{
+ struct pci_controller *hose = phb->hose;
+ unsigned long size = phb->dma32_region_size;
+ unsigned long addr = phb->dma32_region_size * region + phb->dma32_base;
+ struct wsp_dma_table *tbl;
+ int tvts_per_table, i, tvt, nid;
+ unsigned long flags;
+
+ nid = of_node_to_nid(phb->hose->dn);
+
+ /* Calculate how many TVTs are needed */
+ tvts_per_table = size / 0x10000000;
+ if (tvts_per_table == 0)
+ tvts_per_table = 1;
+
+ /* Calculate the base TVT index. We know all tables have the same
+ * size so we just do a simple multiply here
+ */
+ tvt = region * tvts_per_table;
+
+ pr_debug(" Region : %d\n", region);
+ pr_debug(" DMA range : 0x%08lx..0x%08lx\n", addr, addr + size - 1);
+ pr_debug(" Number of TVTs : %d\n", tvts_per_table);
+ pr_debug(" Base TVT : %d\n", tvt);
+ pr_debug(" Node : %d\n", nid);
+
+ tbl = kzalloc_node(sizeof(struct wsp_dma_table), GFP_KERNEL, nid);
+ if (!tbl)
+ return ERR_PTR(-ENOMEM);
+ tbl->phb = phb;
+
+ /* Create as many TVTs as needed, each represents 256M at most */
+ for (i = 0; i < tvts_per_table; i++) {
+ u64 tvt_data1, tvt_data0;
+
+ /* Allocate table. We use a 4K TCE size for now always so
+ * one table is always 8 * (258M / 4K) == 512K
+ */
+ tbl->tces[i] = alloc_pages_node(nid, GFP_KERNEL, get_order(0x80000));
+ if (tbl->tces[i] == NULL)
+ goto fail;
+ memset(page_address(tbl->tces[i]), 0, 0x80000);
+
+ pr_debug(" TCE table %d at : %p\n", i, page_address(tbl->tces[i]));
+
+ /* Table size. We currently set it to be the whole 256M region */
+ tvt_data0 = 2ull << IODA_TVT0_TCE_TABLE_SIZE_SHIFT;
+ /* IO page size set to 4K */
+ tvt_data1 = 1ull << IODA_TVT1_IO_PAGE_SIZE_SHIFT;
+ /* Shift in the address */
+ tvt_data0 |= __pa(page_address(tbl->tces[i])) << IODA_TVT0_TTA_SHIFT;
+
+ /* Validation stuff. We only validate fully bus/dev/fn for now
+ * one day maybe we can group devices but that isn't the case
+ * at the moment
+ */
+ if (validate) {
+ tvt_data0 |= IODA_TVT0_BUSNUM_VALID_MASK;
+ tvt_data0 |= validate->bus->number;
+ tvt_data1 |= IODA_TVT1_DEVNUM_VALID;
+ tvt_data1 |= ((u64)PCI_SLOT(validate->devfn))
+ << IODA_TVT1_DEVNUM_VALUE_SHIFT;
+ tvt_data1 |= IODA_TVT1_FUNCNUM_VALID;
+ tvt_data1 |= ((u64)PCI_FUNC(validate->devfn))
+ << IODA_TVT1_FUNCNUM_VALUE_SHIFT;
+ }
+
+ /* XX PE number is always 0 for now */
+
+ /* Program the values using the PHB lock */
+ spin_lock_irqsave(&phb->lock, flags);
+ out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
+ (tvt + i) | PCIE_REG_IODA_AD_TBL_TVT);
+ out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, tvt_data1);
+ out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, tvt_data0);
+ spin_unlock_irqrestore(&phb->lock, flags);
+ }
+
+ /* Init bits and pieces */
+ tbl->table.it_blocksize = 16;
+ tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT;
+ tbl->table.it_size = size >> IOMMU_PAGE_SHIFT;
+
+ /*
+ * It's already blank but we clear it anyway.
+ * Consider an aditiona interface that makes cleaing optional
+ */
+ iommu_init_table(&tbl->table, nid);
+
+ list_add(&tbl->link, &phb->dma_tables);
+ return tbl;
+
+ fail:
+ pr_debug(" Failed to allocate a 256M TCE table !\n");
+ for (i = 0; i < tvts_per_table; i++)
+ if (tbl->tces[i])
+ __free_pages(tbl->tces[i], get_order(0x80000));
+ kfree(tbl);
+ return ERR_PTR(-ENOMEM);
+}
+
+static void __devinit wsp_pci_dma_dev_setup(struct pci_dev *pdev)
+{
+ struct dev_archdata *archdata = &pdev->dev.archdata;
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct wsp_phb *phb = hose->private_data;
+ struct wsp_dma_table *table = NULL;
+ unsigned long flags;
+ int i;
+
+ /* Don't assign an iommu table to a bridge */
+ if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+ return;
+
+ pr_debug("%s: Setting up DMA...\n", pci_name(pdev));
+
+ spin_lock_irqsave(&phb->lock, flags);
+
+ /* If only one region, check if it already exist */
+ if (phb->dma32_num_regions == 1) {
+ spin_unlock_irqrestore(&phb->lock, flags);
+ if (list_empty(&phb->dma_tables))
+ table = wsp_pci_create_dma32_table(phb, 0, NULL);
+ else
+ table = list_first_entry(&phb->dma_tables,
+ struct wsp_dma_table,
+ link);
+ } else {
+ /* else find a free region */
+ for (i = 0; i < phb->dma32_num_regions && !table; i++) {
+ if (__test_and_set_bit(i, &phb->dma32_map))
+ continue;
+ spin_unlock_irqrestore(&phb->lock, flags);
+ table = wsp_pci_create_dma32_table(phb, i, pdev);
+ }
+ }
+
+ /* Check if we got an error */
+ if (IS_ERR(table)) {
+ pr_err("%s: Failed to create DMA table, err %ld !\n",
+ pci_name(pdev), PTR_ERR(table));
+ return;
+ }
+
+ /* Or a valid table */
+ if (table) {
+ pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n",
+ pci_name(pdev),
+ table->table.it_offset << IOMMU_PAGE_SHIFT,
+ (table->table.it_offset << IOMMU_PAGE_SHIFT)
+ + phb->dma32_region_size - 1);
+ archdata->dma_data.iommu_table_base = &table->table;
+ return;
+ }
+
+ /* Or no room */
+ spin_unlock_irqrestore(&phb->lock, flags);
+ pr_err("%s: Out of DMA space !\n", pci_name(pdev));
+}
+
+static void __init wsp_pcie_configure_hw(struct pci_controller *hose)
+{
+ u64 val;
+ int i;
+
+#define DUMP_REG(x) \
+ pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x))
+
+#ifdef CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS
+ /* WSP DD1 has a bogus class code by default in the PCI-E
+ * root complex's built-in P2P bridge */
+ val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1);
+ pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val);
+ out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1,
+ (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8));
+ pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1));
+#endif /* CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS */
+
+#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+ /* XXX Disable TCE caching, it doesn't work on DD1 */
+ out_be64(hose->cfg_data + 0xe50,
+ in_be64(hose->cfg_data + 0xe50) | (3ull << 62));
+ printk("PCI-E DEBUG CONTROL 5 = 0x%llx\n", in_be64(hose->cfg_data + 0xe50));
+#endif
+
+ /* Configure M32A and IO. IO is hard wired to be 1M for now */
+ out_be64(hose->cfg_data + PCIE_REG_IO_BASE_ADDR, hose->io_base_phys);
+ out_be64(hose->cfg_data + PCIE_REG_IO_BASE_MASK,
+ (~(hose->io_resource.end - hose->io_resource.start)) &
+ 0x3fffffff000ul);
+ out_be64(hose->cfg_data + PCIE_REG_IO_START_ADDR, 0 | 1);
+
+ out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_ADDR,
+ hose->mem_resources[0].start);
+ printk("Want to write to M32A_BASE_MASK : 0x%llx\n",
+ (~(hose->mem_resources[0].end -
+ hose->mem_resources[0].start)) & 0x3ffffff0000ul);
+ out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_MASK,
+ (~(hose->mem_resources[0].end -
+ hose->mem_resources[0].start)) & 0x3ffffff0000ul);
+ out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR,
+ (hose->mem_resources[0].start - hose->pci_mem_offset) | 1);
+
+ /* Clear all TVT entries
+ *
+ * XX Might get TVT count from device-tree
+ */
+ for (i = 0; i < IODA_TVT_COUNT; i++) {
+ out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
+ PCIE_REG_IODA_AD_TBL_TVT | i);
+ out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, 0);
+ out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, 0);
+ }
+
+ /* Kill the TCE cache */
+ out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG,
+ in_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG) |
+ PCIE_REG_PHBC_64B_TCE_EN);
+
+ /* Enable 32 & 64-bit MSIs, IO space and M32A */
+ val = PCIE_REG_PHBC_32BIT_MSI_EN |
+ PCIE_REG_PHBC_IO_EN |
+ PCIE_REG_PHBC_64BIT_MSI_EN |
+ PCIE_REG_PHBC_M32A_EN;
+ if (iommu_is_off)
+ val |= PCIE_REG_PHBC_DMA_XLATE_BYPASS;
+ pr_debug("Will write config: 0x%llx\n", val);
+ out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, val);
+
+ /* Enable error reporting */
+ out_be64(hose->cfg_data + 0xe00,
+ in_be64(hose->cfg_data + 0xe00) | 0x0008000000000000ull);
+
+ /* Mask an error that's generated when doing config space probe
+ *
+ * XXX Maybe we should only mask it around config space cycles... that or
+ * ignore it when we know we had a config space cycle recently ?
+ */
+ out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS_MASK, 0x8000000000000000ull);
+ out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS_MASK, 0x8000000000000000ull);
+
+ /* Enable UTL errors, for now, all of them got to UTL irq 1
+ *
+ * We similarily mask one UTL error caused apparently during normal
+ * probing. We also mask the link up error
+ */
+ out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_ERR_SEV, 0);
+ out_be64(hose->cfg_data + PCIE_UTL_RC_ERR_SEVERITY, 0);
+ out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_ERROR_SEV, 0);
+ out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_IRQ_EN, 0xffffffff00000000ull);
+ out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_IRQ_EN, 0xff5fffff00000000ull);
+ out_be64(hose->cfg_data + PCIE_UTL_EP_ERR_IRQ_EN, 0xffffffff00000000ull);
+
+ DUMP_REG(PCIE_REG_IO_BASE_ADDR);
+ DUMP_REG(PCIE_REG_IO_BASE_MASK);
+ DUMP_REG(PCIE_REG_IO_START_ADDR);
+ DUMP_REG(PCIE_REG_M32A_BASE_ADDR);
+ DUMP_REG(PCIE_REG_M32A_BASE_MASK);
+ DUMP_REG(PCIE_REG_M32A_START_ADDR);
+ DUMP_REG(PCIE_REG_M32B_BASE_ADDR);
+ DUMP_REG(PCIE_REG_M32B_BASE_MASK);
+ DUMP_REG(PCIE_REG_M32B_START_ADDR);
+ DUMP_REG(PCIE_REG_M64_BASE_ADDR);
+ DUMP_REG(PCIE_REG_M64_BASE_MASK);
+ DUMP_REG(PCIE_REG_M64_START_ADDR);
+ DUMP_REG(PCIE_REG_PHB_CONFIG);
+}
+
+static void wsp_pci_wait_io_idle(struct wsp_phb *phb, unsigned long port)
+{
+ u64 val;
+ int i;
+
+ for (i = 0; i < 10000; i++) {
+ val = in_be64(phb->hose->cfg_data + 0xe08);
+ if ((val & 0x1900000000000000ull) == 0x0100000000000000ull)
+ return;
+ udelay(1);
+ }
+ pr_warning("PCI IO timeout on domain %d port 0x%lx\n",
+ phb->hose->global_number, port);
+}
+
+#define DEF_PCI_AC_RET_pio(name, ret, at, al, aa) \
+static ret wsp_pci_##name at \
+{ \
+ struct iowa_bus *bus; \
+ struct wsp_phb *phb; \
+ unsigned long flags; \
+ ret rval; \
+ bus = iowa_pio_find_bus(aa); \
+ WARN_ON(!bus); \
+ phb = bus->private; \
+ spin_lock_irqsave(&phb->lock, flags); \
+ wsp_pci_wait_io_idle(phb, aa); \
+ rval = __do_##name al; \
+ spin_unlock_irqrestore(&phb->lock, flags); \
+ return rval; \
+}
+
+#define DEF_PCI_AC_NORET_pio(name, at, al, aa) \
+static void wsp_pci_##name at \
+{ \
+ struct iowa_bus *bus; \
+ struct wsp_phb *phb; \
+ unsigned long flags; \
+ bus = iowa_pio_find_bus(aa); \
+ WARN_ON(!bus); \
+ phb = bus->private; \
+ spin_lock_irqsave(&phb->lock, flags); \
+ wsp_pci_wait_io_idle(phb, aa); \
+ __do_##name al; \
+ spin_unlock_irqrestore(&phb->lock, flags); \
+}
+
+#define DEF_PCI_AC_RET_mem(name, ret, at, al, aa)
+#define DEF_PCI_AC_NORET_mem(name, at, al, aa)
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \
+ DEF_PCI_AC_RET_##space(name, ret, at, al, aa)
+
+#define DEF_PCI_AC_NORET(name, at, al, space, aa) \
+ DEF_PCI_AC_NORET_##space(name, at, al, aa) \
+
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+static struct ppc_pci_io wsp_pci_iops = {
+ .inb = wsp_pci_inb,
+ .inw = wsp_pci_inw,
+ .inl = wsp_pci_inl,
+ .outb = wsp_pci_outb,
+ .outw = wsp_pci_outw,
+ .outl = wsp_pci_outl,
+ .insb = wsp_pci_insb,
+ .insw = wsp_pci_insw,
+ .insl = wsp_pci_insl,
+ .outsb = wsp_pci_outsb,
+ .outsw = wsp_pci_outsw,
+ .outsl = wsp_pci_outsl,
+};
+
+static int __init wsp_setup_one_phb(struct device_node *np)
+{
+ struct pci_controller *hose;
+ struct wsp_phb *phb;
+
+ pr_info("PCI: Setting up PCIe host bridge 0x%s\n", np->full_name);
+
+ phb = zalloc_maybe_bootmem(sizeof(struct wsp_phb), GFP_KERNEL);
+ if (!phb)
+ return -ENOMEM;
+ hose = pcibios_alloc_controller(np);
+ if (!hose) {
+ /* Can't really free the phb */
+ return -ENOMEM;
+ }
+ hose->private_data = phb;
+ phb->hose = hose;
+
+ INIT_LIST_HEAD(&phb->dma_tables);
+ spin_lock_init(&phb->lock);
+
+ /* XXX Use bus-range property ? */
+ hose->first_busno = 0;
+ hose->last_busno = 0xff;
+
+ /* We use cfg_data as the address for the whole bridge MMIO space
+ */
+ hose->cfg_data = of_iomap(hose->dn, 0);
+
+ pr_debug("PCIe registers mapped at 0x%p\n", hose->cfg_data);
+
+ /* Get the ranges of the device-tree */
+ pci_process_bridge_OF_ranges(hose, np, 0);
+
+ /* XXX Force re-assigning of everything for now */
+ pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC |
+ PCI_ENABLE_PROC_DOMAINS);
+ pci_probe_only = 0;
+
+ /* Calculate how the TCE space is divided */
+ phb->dma32_base = 0;
+ phb->dma32_num_regions = NUM_DMA32_REGIONS;
+ if (phb->dma32_num_regions > MAX_TABLE_TVT_COUNT) {
+ pr_warning("IOMMU: Clamped to %d DMA32 regions\n",
+ MAX_TABLE_TVT_COUNT);
+ phb->dma32_num_regions = MAX_TABLE_TVT_COUNT;
+ }
+ phb->dma32_region_size = 0x80000000 / phb->dma32_num_regions;
+
+ BUG_ON(!is_power_of_2(phb->dma32_region_size));
+
+ /* Setup config ops */
+ hose->ops = &wsp_pcie_pci_ops;
+
+ /* Configure the HW */
+ wsp_pcie_configure_hw(hose);
+
+ /* Instanciate IO workarounds */
+ iowa_register_bus(hose, &wsp_pci_iops, NULL, phb);
+#ifdef CONFIG_PCI_MSI
+ wsp_setup_phb_msi(hose);
+#endif
+
+ /* Add to global list */
+ list_add(&phb->all, &wsp_phbs);
+
+ return 0;
+}
+
+void __init wsp_setup_pci(void)
+{
+ struct device_node *np;
+ int rc;
+
+ /* Find host bridges */
+ for_each_compatible_node(np, "pciex", PCIE_COMPATIBLE) {
+ rc = wsp_setup_one_phb(np);
+ if (rc)
+ pr_err("Failed to setup PCIe bridge %s, rc=%d\n",
+ np->full_name, rc);
+ }
+
+ /* Establish device-tree linkage */
+ pci_devs_phb_init();
+
+ /* Set DMA ops to use TCEs */
+ if (iommu_is_off) {
+ pr_info("PCI-E: Disabled TCEs, using direct DMA\n");
+ set_pci_dma_ops(&dma_direct_ops);
+ } else {
+ ppc_md.pci_dma_dev_setup = wsp_pci_dma_dev_setup;
+ ppc_md.tce_build = tce_build_wsp;
+ ppc_md.tce_free = tce_free_wsp;
+ set_pci_dma_ops(&dma_iommu_ops);
+ }
+}
+
+#define err_debug(fmt...) pr_debug(fmt)
+//#define err_debug(fmt...)
+
+static int __init wsp_pci_get_err_irq_no_dt(struct device_node *np)
+{
+ const u32 *prop;
+ int hw_irq;
+
+ /* Ok, no interrupts property, let's try to find our child P2P */
+ np = of_get_next_child(np, NULL);
+ if (np == NULL)
+ return 0;
+
+ /* Grab it's interrupt map */
+ prop = of_get_property(np, "interrupt-map", NULL);
+ if (prop == NULL)
+ return 0;
+
+ /* Grab one of the interrupts in there, keep the low 4 bits */
+ hw_irq = prop[5] & 0xf;
+
+ /* 0..4 for PHB 0 and 5..9 for PHB 1 */
+ if (hw_irq < 5)
+ hw_irq = 4;
+ else
+ hw_irq = 9;
+ hw_irq |= prop[5] & ~0xf;
+
+ err_debug("PCI: Using 0x%x as error IRQ for %s\n",
+ hw_irq, np->parent->full_name);
+ return irq_create_mapping(NULL, hw_irq);
+}
+
+static const struct {
+ u32 offset;
+ const char *name;
+} wsp_pci_regs[] = {
+#define DREG(x) { PCIE_REG_##x, #x }
+#define DUTL(x) { PCIE_UTL_##x, "UTL_" #x }
+ /* Architected registers except CONFIG_ and IODA
+ * to avoid side effects
+ */
+ DREG(DMA_CHAN_STATUS),
+ DREG(CPU_LOADSTORE_STATUS),
+ DREG(LOCK0),
+ DREG(LOCK1),
+ DREG(PHB_CONFIG),
+ DREG(IO_BASE_ADDR),
+ DREG(IO_BASE_MASK),
+ DREG(IO_START_ADDR),
+ DREG(M32A_BASE_ADDR),
+ DREG(M32A_BASE_MASK),
+ DREG(M32A_START_ADDR),
+ DREG(M32B_BASE_ADDR),
+ DREG(M32B_BASE_MASK),
+ DREG(M32B_START_ADDR),
+ DREG(M64_BASE_ADDR),
+ DREG(M64_BASE_MASK),
+ DREG(M64_START_ADDR),
+ DREG(TCE_KILL),
+ DREG(LOCK2),
+ DREG(PHB_GEN_CAP),
+ DREG(PHB_TCE_CAP),
+ DREG(PHB_IRQ_CAP),
+ DREG(PHB_EEH_CAP),
+ DREG(PAPR_ERR_INJ_CONTROL),
+ DREG(PAPR_ERR_INJ_ADDR),
+ DREG(PAPR_ERR_INJ_MASK),
+
+ /* UTL core regs */
+ DUTL(SYS_BUS_CONTROL),
+ DUTL(STATUS),
+ DUTL(SYS_BUS_AGENT_STATUS),
+ DUTL(SYS_BUS_AGENT_ERR_SEV),
+ DUTL(SYS_BUS_AGENT_IRQ_EN),
+ DUTL(SYS_BUS_BURST_SZ_CONF),
+ DUTL(REVISION_ID),
+ DUTL(OUT_POST_HDR_BUF_ALLOC),
+ DUTL(OUT_POST_DAT_BUF_ALLOC),
+ DUTL(IN_POST_HDR_BUF_ALLOC),
+ DUTL(IN_POST_DAT_BUF_ALLOC),
+ DUTL(OUT_NP_BUF_ALLOC),
+ DUTL(IN_NP_BUF_ALLOC),
+ DUTL(PCIE_TAGS_ALLOC),
+ DUTL(GBIF_READ_TAGS_ALLOC),
+
+ DUTL(PCIE_PORT_CONTROL),
+ DUTL(PCIE_PORT_STATUS),
+ DUTL(PCIE_PORT_ERROR_SEV),
+ DUTL(PCIE_PORT_IRQ_EN),
+ DUTL(RC_STATUS),
+ DUTL(RC_ERR_SEVERITY),
+ DUTL(RC_IRQ_EN),
+ DUTL(EP_STATUS),
+ DUTL(EP_ERR_SEVERITY),
+ DUTL(EP_ERR_IRQ_EN),
+ DUTL(PCI_PM_CTRL1),
+ DUTL(PCI_PM_CTRL2),
+
+ /* PCIe stack regs */
+ DREG(SYSTEM_CONFIG1),
+ DREG(SYSTEM_CONFIG2),
+ DREG(EP_SYSTEM_CONFIG),
+ DREG(EP_FLR),
+ DREG(EP_BAR_CONFIG),
+ DREG(LINK_CONFIG),
+ DREG(PM_CONFIG),
+ DREG(DLP_CONTROL),
+ DREG(DLP_STATUS),
+ DREG(ERR_REPORT_CONTROL),
+ DREG(SLOT_CONTROL1),
+ DREG(SLOT_CONTROL2),
+ DREG(UTL_CONFIG),
+ DREG(BUFFERS_CONFIG),
+ DREG(ERROR_INJECT),
+ DREG(SRIOV_CONFIG),
+ DREG(PF0_SRIOV_STATUS),
+ DREG(PF1_SRIOV_STATUS),
+ DREG(PORT_NUMBER),
+ DREG(POR_SYSTEM_CONFIG),
+
+ /* Internal logic regs */
+ DREG(PHB_VERSION),
+ DREG(RESET),
+ DREG(PHB_CONTROL),
+ DREG(PHB_TIMEOUT_CONTROL1),
+ DREG(PHB_QUIESCE_DMA),
+ DREG(PHB_DMA_READ_TAG_ACTV),
+ DREG(PHB_TCE_READ_TAG_ACTV),
+
+ /* FIR registers */
+ DREG(LEM_FIR_ACCUM),
+ DREG(LEM_FIR_AND_MASK),
+ DREG(LEM_FIR_OR_MASK),
+ DREG(LEM_ACTION0),
+ DREG(LEM_ACTION1),
+ DREG(LEM_ERROR_MASK),
+ DREG(LEM_ERROR_AND_MASK),
+ DREG(LEM_ERROR_OR_MASK),
+
+ /* Error traps registers */
+ DREG(PHB_ERR_STATUS),
+ DREG(PHB_ERR_STATUS),
+ DREG(PHB_ERR1_STATUS),
+ DREG(PHB_ERR_INJECT),
+ DREG(PHB_ERR_LEM_ENABLE),
+ DREG(PHB_ERR_IRQ_ENABLE),
+ DREG(PHB_ERR_FREEZE_ENABLE),
+ DREG(PHB_ERR_SIDE_ENABLE),
+ DREG(PHB_ERR_LOG_0),
+ DREG(PHB_ERR_LOG_1),
+ DREG(PHB_ERR_STATUS_MASK),
+ DREG(PHB_ERR1_STATUS_MASK),
+ DREG(MMIO_ERR_STATUS),
+ DREG(MMIO_ERR1_STATUS),
+ DREG(MMIO_ERR_INJECT),
+ DREG(MMIO_ERR_LEM_ENABLE),
+ DREG(MMIO_ERR_IRQ_ENABLE),
+ DREG(MMIO_ERR_FREEZE_ENABLE),
+ DREG(MMIO_ERR_SIDE_ENABLE),
+ DREG(MMIO_ERR_LOG_0),
+ DREG(MMIO_ERR_LOG_1),
+ DREG(MMIO_ERR_STATUS_MASK),
+ DREG(MMIO_ERR1_STATUS_MASK),
+ DREG(DMA_ERR_STATUS),
+ DREG(DMA_ERR1_STATUS),
+ DREG(DMA_ERR_INJECT),
+ DREG(DMA_ERR_LEM_ENABLE),
+ DREG(DMA_ERR_IRQ_ENABLE),
+ DREG(DMA_ERR_FREEZE_ENABLE),
+ DREG(DMA_ERR_SIDE_ENABLE),
+ DREG(DMA_ERR_LOG_0),
+ DREG(DMA_ERR_LOG_1),
+ DREG(DMA_ERR_STATUS_MASK),
+ DREG(DMA_ERR1_STATUS_MASK),
+
+ /* Debug and Trace registers */
+ DREG(PHB_DEBUG_CONTROL0),
+ DREG(PHB_DEBUG_STATUS0),
+ DREG(PHB_DEBUG_CONTROL1),
+ DREG(PHB_DEBUG_STATUS1),
+ DREG(PHB_DEBUG_CONTROL2),
+ DREG(PHB_DEBUG_STATUS2),
+ DREG(PHB_DEBUG_CONTROL3),
+ DREG(PHB_DEBUG_STATUS3),
+ DREG(PHB_DEBUG_CONTROL4),
+ DREG(PHB_DEBUG_STATUS4),
+ DREG(PHB_DEBUG_CONTROL5),
+ DREG(PHB_DEBUG_STATUS5),
+
+ /* Don't seem to exist ...
+ DREG(PHB_DEBUG_CONTROL6),
+ DREG(PHB_DEBUG_STATUS6),
+ */
+};
+
+static int wsp_pci_regs_show(struct seq_file *m, void *private)
+{
+ struct wsp_phb *phb = m->private;
+ struct pci_controller *hose = phb->hose;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
+ /* Skip write-only regs */
+ if (wsp_pci_regs[i].offset == 0xc08 ||
+ wsp_pci_regs[i].offset == 0xc10 ||
+ wsp_pci_regs[i].offset == 0xc38 ||
+ wsp_pci_regs[i].offset == 0xc40)
+ continue;
+ seq_printf(m, "0x%03x: 0x%016llx %s\n",
+ wsp_pci_regs[i].offset,
+ in_be64(hose->cfg_data + wsp_pci_regs[i].offset),
+ wsp_pci_regs[i].name);
+ }
+ return 0;
+}
+
+static int wsp_pci_regs_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, wsp_pci_regs_show, inode->i_private);
+}
+
+static const struct file_operations wsp_pci_regs_fops = {
+ .open = wsp_pci_regs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int wsp_pci_reg_set(void *data, u64 val)
+{
+ out_be64((void __iomem *)data, val);
+ return 0;
+}
+
+static int wsp_pci_reg_get(void *data, u64 *val)
+{
+ *val = in_be64((void __iomem *)data);
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(wsp_pci_reg_fops, wsp_pci_reg_get, wsp_pci_reg_set, "0x%llx\n");
+
+static irqreturn_t wsp_pci_err_irq(int irq, void *dev_id)
+{
+ struct wsp_phb *phb = dev_id;
+ struct pci_controller *hose = phb->hose;
+ irqreturn_t handled = IRQ_NONE;
+ struct wsp_pcie_err_log_data ed;
+
+ pr_err("PCI: Error interrupt on %s (PHB %d)\n",
+ hose->dn->full_name, hose->global_number);
+ again:
+ memset(&ed, 0, sizeof(ed));
+
+ /* Read and clear UTL errors */
+ ed.utl_sys_err = in_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS);
+ if (ed.utl_sys_err)
+ out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS, ed.utl_sys_err);
+ ed.utl_port_err = in_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS);
+ if (ed.utl_port_err)
+ out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS, ed.utl_port_err);
+ ed.utl_rc_err = in_be64(hose->cfg_data + PCIE_UTL_RC_STATUS);
+ if (ed.utl_rc_err)
+ out_be64(hose->cfg_data + PCIE_UTL_RC_STATUS, ed.utl_rc_err);
+
+ /* Read and clear main trap errors */
+ ed.phb_err = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS);
+ if (ed.phb_err) {
+ ed.phb_err1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS);
+ ed.phb_log0 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_0);
+ ed.phb_log1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_1);
+ out_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS, 0);
+ out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS, 0);
+ }
+ ed.mmio_err = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS);
+ if (ed.mmio_err) {
+ ed.mmio_err1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS);
+ ed.mmio_log0 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_0);
+ ed.mmio_log1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_1);
+ out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS, 0);
+ out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS, 0);
+ }
+ ed.dma_err = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS);
+ if (ed.dma_err) {
+ ed.dma_err1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS);
+ ed.dma_log0 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_0);
+ ed.dma_log1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_1);
+ out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS, 0);
+ out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS, 0);
+ }
+
+ /* Now print things out */
+ if (ed.phb_err) {
+ pr_err(" PHB Error Status : 0x%016llx\n", ed.phb_err);
+ pr_err(" PHB First Error Status: 0x%016llx\n", ed.phb_err1);
+ pr_err(" PHB Error Log 0 : 0x%016llx\n", ed.phb_log0);
+ pr_err(" PHB Error Log 1 : 0x%016llx\n", ed.phb_log1);
+ }
+ if (ed.mmio_err) {
+ pr_err(" MMIO Error Status : 0x%016llx\n", ed.mmio_err);
+ pr_err(" MMIO First Error Status: 0x%016llx\n", ed.mmio_err1);
+ pr_err(" MMIO Error Log 0 : 0x%016llx\n", ed.mmio_log0);
+ pr_err(" MMIO Error Log 1 : 0x%016llx\n", ed.mmio_log1);
+ }
+ if (ed.dma_err) {
+ pr_err(" DMA Error Status : 0x%016llx\n", ed.dma_err);
+ pr_err(" DMA First Error Status: 0x%016llx\n", ed.dma_err1);
+ pr_err(" DMA Error Log 0 : 0x%016llx\n", ed.dma_log0);
+ pr_err(" DMA Error Log 1 : 0x%016llx\n", ed.dma_log1);
+ }
+ if (ed.utl_sys_err)
+ pr_err(" UTL Sys Error Status : 0x%016llx\n", ed.utl_sys_err);
+ if (ed.utl_port_err)
+ pr_err(" UTL Port Error Status : 0x%016llx\n", ed.utl_port_err);
+ if (ed.utl_rc_err)
+ pr_err(" UTL RC Error Status : 0x%016llx\n", ed.utl_rc_err);
+
+ /* Interrupts are caused by the error traps. If we had any error there
+ * we loop again in case the UTL buffered some new stuff between
+ * going there and going to the traps
+ */
+ if (ed.dma_err || ed.mmio_err || ed.phb_err) {
+ handled = IRQ_HANDLED;
+ goto again;
+ }
+ return handled;
+}
+
+static void __init wsp_setup_pci_err_reporting(struct wsp_phb *phb)
+{
+ struct pci_controller *hose = phb->hose;
+ int err_irq, i, rc;
+ char fname[16];
+
+ /* Create a debugfs file for that PHB */
+ sprintf(fname, "phb%d", phb->hose->global_number);
+ phb->ddir = debugfs_create_dir(fname, powerpc_debugfs_root);
+
+ /* Some useful debug output */
+ if (phb->ddir) {
+ struct dentry *d = debugfs_create_dir("regs", phb->ddir);
+ char tmp[64];
+
+ for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
+ sprintf(tmp, "%03x_%s", wsp_pci_regs[i].offset,
+ wsp_pci_regs[i].name);
+ debugfs_create_file(tmp, 0600, d,
+ hose->cfg_data + wsp_pci_regs[i].offset,
+ &wsp_pci_reg_fops);
+ }
+ debugfs_create_file("all_regs", 0600, phb->ddir, phb, &wsp_pci_regs_fops);
+ }
+
+ /* Find the IRQ number for that PHB */
+ err_irq = irq_of_parse_and_map(hose->dn, 0);
+ if (err_irq == 0)
+ /* XXX Error IRQ lacking from device-tree */
+ err_irq = wsp_pci_get_err_irq_no_dt(hose->dn);
+ if (err_irq == 0) {
+ pr_err("PCI: Failed to fetch error interrupt for %s\n",
+ hose->dn->full_name);
+ return;
+ }
+ /* Request it */
+ rc = request_irq(err_irq, wsp_pci_err_irq, 0, "wsp_pci error", phb);
+ if (rc) {
+ pr_err("PCI: Failed to request interrupt for %s\n",
+ hose->dn->full_name);
+ }
+ /* Enable interrupts for all errors for now */
+ out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+ out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+ out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+}
+
+/*
+ * This is called later to hookup with the error interrupt
+ */
+static int __init wsp_setup_pci_late(void)
+{
+ struct wsp_phb *phb;
+
+ list_for_each_entry(phb, &wsp_phbs, all)
+ wsp_setup_pci_err_reporting(phb);
+
+ return 0;
+}
+arch_initcall(wsp_setup_pci_late);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.h b/arch/powerpc/platforms/wsp/wsp_pci.h
new file mode 100644
index 00000000000..52e9bd95250
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp_pci.h
@@ -0,0 +1,268 @@
+/*
+ * Copyright 2010 Ben Herrenschmidt, IBM Corporation
+ *
+ * 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.
+ */
+
+#ifndef __WSP_PCI_H
+#define __WSP_PCI_H
+
+/* Architected registers */
+#define PCIE_REG_DMA_CHAN_STATUS 0x110
+#define PCIE_REG_CPU_LOADSTORE_STATUS 0x120
+
+#define PCIE_REG_CONFIG_DATA 0x130
+#define PCIE_REG_LOCK0 0x138
+#define PCIE_REG_CONFIG_ADDRESS 0x140
+#define PCIE_REG_CA_ENABLE 0x8000000000000000ull
+#define PCIE_REG_CA_BUS_MASK 0x0ff0000000000000ull
+#define PCIE_REG_CA_BUS_SHIFT (20+32)
+#define PCIE_REG_CA_DEV_MASK 0x000f800000000000ull
+#define PCIE_REG_CA_DEV_SHIFT (15+32)
+#define PCIE_REG_CA_FUNC_MASK 0x0000700000000000ull
+#define PCIE_REG_CA_FUNC_SHIFT (12+32)
+#define PCIE_REG_CA_REG_MASK 0x00000fff00000000ull
+#define PCIE_REG_CA_REG_SHIFT ( 0+32)
+#define PCIE_REG_CA_BE_MASK 0x00000000f0000000ull
+#define PCIE_REG_CA_BE_SHIFT ( 28)
+#define PCIE_REG_LOCK1 0x148
+
+#define PCIE_REG_PHB_CONFIG 0x160
+#define PCIE_REG_PHBC_64B_TCE_EN 0x2000000000000000ull
+#define PCIE_REG_PHBC_MMIO_DMA_FREEZE_EN 0x1000000000000000ull
+#define PCIE_REG_PHBC_32BIT_MSI_EN 0x0080000000000000ull
+#define PCIE_REG_PHBC_M64_EN 0x0040000000000000ull
+#define PCIE_REG_PHBC_IO_EN 0x0008000000000000ull
+#define PCIE_REG_PHBC_64BIT_MSI_EN 0x0002000000000000ull
+#define PCIE_REG_PHBC_M32A_EN 0x0000800000000000ull
+#define PCIE_REG_PHBC_M32B_EN 0x0000400000000000ull
+#define PCIE_REG_PHBC_MSI_PE_VALIDATE 0x0000200000000000ull
+#define PCIE_REG_PHBC_DMA_XLATE_BYPASS 0x0000100000000000ull
+
+#define PCIE_REG_IO_BASE_ADDR 0x170
+#define PCIE_REG_IO_BASE_MASK 0x178
+#define PCIE_REG_IO_START_ADDR 0x180
+
+#define PCIE_REG_M32A_BASE_ADDR 0x190
+#define PCIE_REG_M32A_BASE_MASK 0x198
+#define PCIE_REG_M32A_START_ADDR 0x1a0
+
+#define PCIE_REG_M32B_BASE_ADDR 0x1b0
+#define PCIE_REG_M32B_BASE_MASK 0x1b8
+#define PCIE_REG_M32B_START_ADDR 0x1c0
+
+#define PCIE_REG_M64_BASE_ADDR 0x1e0
+#define PCIE_REG_M64_BASE_MASK 0x1e8
+#define PCIE_REG_M64_START_ADDR 0x1f0
+
+#define PCIE_REG_TCE_KILL 0x210
+#define PCIE_REG_TCEKILL_SINGLE 0x8000000000000000ull
+#define PCIE_REG_TCEKILL_ADDR_MASK 0x000003fffffffff8ull
+#define PCIE_REG_TCEKILL_PS_4K 0
+#define PCIE_REG_TCEKILL_PS_64K 1
+#define PCIE_REG_TCEKILL_PS_16M 2
+#define PCIE_REG_TCEKILL_PS_16G 3
+
+#define PCIE_REG_IODA_ADDR 0x220
+#define PCIE_REG_IODA_AD_AUTOINC 0x8000000000000000ull
+#define PCIE_REG_IODA_AD_TBL_MVT 0x0005000000000000ull
+#define PCIE_REG_IODA_AD_TBL_PELT 0x0006000000000000ull
+#define PCIE_REG_IODA_AD_TBL_PESTA 0x0007000000000000ull
+#define PCIE_REG_IODA_AD_TBL_PESTB 0x0008000000000000ull
+#define PCIE_REG_IODA_AD_TBL_TVT 0x0009000000000000ull
+#define PCIE_REG_IODA_AD_TBL_TCE 0x000a000000000000ull
+#define PCIE_REG_IODA_DATA0 0x228
+#define PCIE_REG_IODA_DATA1 0x230
+
+#define PCIE_REG_LOCK2 0x240
+
+#define PCIE_REG_PHB_GEN_CAP 0x250
+#define PCIE_REG_PHB_TCE_CAP 0x258
+#define PCIE_REG_PHB_IRQ_CAP 0x260
+#define PCIE_REG_PHB_EEH_CAP 0x268
+
+#define PCIE_REG_PAPR_ERR_INJ_CONTROL 0x2b0
+#define PCIE_REG_PAPR_ERR_INJ_ADDR 0x2b8
+#define PCIE_REG_PAPR_ERR_INJ_MASK 0x2c0
+
+
+#define PCIE_REG_SYS_CFG1 0x600
+#define PCIE_REG_SYS_CFG1_CLASS_CODE 0x0000000000ffffffull
+
+#define IODA_TVT0_TTA_MASK 0x000fffffffff0000ull
+#define IODA_TVT0_TTA_SHIFT 4
+#define IODA_TVT0_BUSNUM_VALID_MASK 0x000000000000e000ull
+#define IODA_TVT0_TCE_TABLE_SIZE_MASK 0x0000000000001f00ull
+#define IODA_TVT0_TCE_TABLE_SIZE_SHIFT 8
+#define IODA_TVT0_BUSNUM_VALUE_MASK 0x00000000000000ffull
+#define IODA_TVT0_BUSNUM_VALID_SHIFT 0
+#define IODA_TVT1_DEVNUM_VALID 0x2000000000000000ull
+#define IODA_TVT1_DEVNUM_VALUE_MASK 0x1f00000000000000ull
+#define IODA_TVT1_DEVNUM_VALUE_SHIFT 56
+#define IODA_TVT1_FUNCNUM_VALID 0x0008000000000000ull
+#define IODA_TVT1_FUNCNUM_VALUE_MASK 0x0007000000000000ull
+#define IODA_TVT1_FUNCNUM_VALUE_SHIFT 48
+#define IODA_TVT1_IO_PAGE_SIZE_MASK 0x00001f0000000000ull
+#define IODA_TVT1_IO_PAGE_SIZE_SHIFT 40
+#define IODA_TVT1_PE_NUMBER_MASK 0x000000000000003full
+#define IODA_TVT1_PE_NUMBER_SHIFT 0
+
+#define IODA_TVT_COUNT 64
+
+/* UTL Core registers */
+#define PCIE_UTL_SYS_BUS_CONTROL 0x400
+#define PCIE_UTL_STATUS 0x408
+#define PCIE_UTL_SYS_BUS_AGENT_STATUS 0x410
+#define PCIE_UTL_SYS_BUS_AGENT_ERR_SEV 0x418
+#define PCIE_UTL_SYS_BUS_AGENT_IRQ_EN 0x420
+#define PCIE_UTL_SYS_BUS_BURST_SZ_CONF 0x440
+#define PCIE_UTL_REVISION_ID 0x448
+
+#define PCIE_UTL_OUT_POST_HDR_BUF_ALLOC 0x4c0
+#define PCIE_UTL_OUT_POST_DAT_BUF_ALLOC 0x4d0
+#define PCIE_UTL_IN_POST_HDR_BUF_ALLOC 0x4e0
+#define PCIE_UTL_IN_POST_DAT_BUF_ALLOC 0x4f0
+#define PCIE_UTL_OUT_NP_BUF_ALLOC 0x500
+#define PCIE_UTL_IN_NP_BUF_ALLOC 0x510
+#define PCIE_UTL_PCIE_TAGS_ALLOC 0x520
+#define PCIE_UTL_GBIF_READ_TAGS_ALLOC 0x530
+
+#define PCIE_UTL_PCIE_PORT_CONTROL 0x540
+#define PCIE_UTL_PCIE_PORT_STATUS 0x548
+#define PCIE_UTL_PCIE_PORT_ERROR_SEV 0x550
+#define PCIE_UTL_PCIE_PORT_IRQ_EN 0x558
+#define PCIE_UTL_RC_STATUS 0x560
+#define PCIE_UTL_RC_ERR_SEVERITY 0x568
+#define PCIE_UTL_RC_IRQ_EN 0x570
+#define PCIE_UTL_EP_STATUS 0x578
+#define PCIE_UTL_EP_ERR_SEVERITY 0x580
+#define PCIE_UTL_EP_ERR_IRQ_EN 0x588
+
+#define PCIE_UTL_PCI_PM_CTRL1 0x590
+#define PCIE_UTL_PCI_PM_CTRL2 0x598
+
+/* PCIe stack registers */
+#define PCIE_REG_SYSTEM_CONFIG1 0x600
+#define PCIE_REG_SYSTEM_CONFIG2 0x608
+#define PCIE_REG_EP_SYSTEM_CONFIG 0x618
+#define PCIE_REG_EP_FLR 0x620
+#define PCIE_REG_EP_BAR_CONFIG 0x628
+#define PCIE_REG_LINK_CONFIG 0x630
+#define PCIE_REG_PM_CONFIG 0x640
+#define PCIE_REG_DLP_CONTROL 0x650
+#define PCIE_REG_DLP_STATUS 0x658
+#define PCIE_REG_ERR_REPORT_CONTROL 0x660
+#define PCIE_REG_SLOT_CONTROL1 0x670
+#define PCIE_REG_SLOT_CONTROL2 0x678
+#define PCIE_REG_UTL_CONFIG 0x680
+#define PCIE_REG_BUFFERS_CONFIG 0x690
+#define PCIE_REG_ERROR_INJECT 0x698
+#define PCIE_REG_SRIOV_CONFIG 0x6a0
+#define PCIE_REG_PF0_SRIOV_STATUS 0x6a8
+#define PCIE_REG_PF1_SRIOV_STATUS 0x6b0
+#define PCIE_REG_PORT_NUMBER 0x700
+#define PCIE_REG_POR_SYSTEM_CONFIG 0x708
+
+/* PHB internal logic registers */
+#define PCIE_REG_PHB_VERSION 0x800
+#define PCIE_REG_RESET 0x808
+#define PCIE_REG_PHB_CONTROL 0x810
+#define PCIE_REG_PHB_TIMEOUT_CONTROL1 0x878
+#define PCIE_REG_PHB_QUIESCE_DMA 0x888
+#define PCIE_REG_PHB_DMA_READ_TAG_ACTV 0x900
+#define PCIE_REG_PHB_TCE_READ_TAG_ACTV 0x908
+
+/* FIR registers */
+#define PCIE_REG_LEM_FIR_ACCUM 0xc00
+#define PCIE_REG_LEM_FIR_AND_MASK 0xc08
+#define PCIE_REG_LEM_FIR_OR_MASK 0xc10
+#define PCIE_REG_LEM_ACTION0 0xc18
+#define PCIE_REG_LEM_ACTION1 0xc20
+#define PCIE_REG_LEM_ERROR_MASK 0xc30
+#define PCIE_REG_LEM_ERROR_AND_MASK 0xc38
+#define PCIE_REG_LEM_ERROR_OR_MASK 0xc40
+
+/* PHB Error registers */
+#define PCIE_REG_PHB_ERR_STATUS 0xc80
+#define PCIE_REG_PHB_ERR1_STATUS 0xc88
+#define PCIE_REG_PHB_ERR_INJECT 0xc90
+#define PCIE_REG_PHB_ERR_LEM_ENABLE 0xc98
+#define PCIE_REG_PHB_ERR_IRQ_ENABLE 0xca0
+#define PCIE_REG_PHB_ERR_FREEZE_ENABLE 0xca8
+#define PCIE_REG_PHB_ERR_SIDE_ENABLE 0xcb8
+#define PCIE_REG_PHB_ERR_LOG_0 0xcc0
+#define PCIE_REG_PHB_ERR_LOG_1 0xcc8
+#define PCIE_REG_PHB_ERR_STATUS_MASK 0xcd0
+#define PCIE_REG_PHB_ERR1_STATUS_MASK 0xcd8
+
+#define PCIE_REG_MMIO_ERR_STATUS 0xd00
+#define PCIE_REG_MMIO_ERR1_STATUS 0xd08
+#define PCIE_REG_MMIO_ERR_INJECT 0xd10
+#define PCIE_REG_MMIO_ERR_LEM_ENABLE 0xd18
+#define PCIE_REG_MMIO_ERR_IRQ_ENABLE 0xd20
+#define PCIE_REG_MMIO_ERR_FREEZE_ENABLE 0xd28
+#define PCIE_REG_MMIO_ERR_SIDE_ENABLE 0xd38
+#define PCIE_REG_MMIO_ERR_LOG_0 0xd40
+#define PCIE_REG_MMIO_ERR_LOG_1 0xd48
+#define PCIE_REG_MMIO_ERR_STATUS_MASK 0xd50
+#define PCIE_REG_MMIO_ERR1_STATUS_MASK 0xd58
+
+#define PCIE_REG_DMA_ERR_STATUS 0xd80
+#define PCIE_REG_DMA_ERR1_STATUS 0xd88
+#define PCIE_REG_DMA_ERR_INJECT 0xd90
+#define PCIE_REG_DMA_ERR_LEM_ENABLE 0xd98
+#define PCIE_REG_DMA_ERR_IRQ_ENABLE 0xda0
+#define PCIE_REG_DMA_ERR_FREEZE_ENABLE 0xda8
+#define PCIE_REG_DMA_ERR_SIDE_ENABLE 0xdb8
+#define PCIE_REG_DMA_ERR_LOG_0 0xdc0
+#define PCIE_REG_DMA_ERR_LOG_1 0xdc8
+#define PCIE_REG_DMA_ERR_STATUS_MASK 0xdd0
+#define PCIE_REG_DMA_ERR1_STATUS_MASK 0xdd8
+
+/* Shortcuts for access to the above using the PHB definitions
+ * with an offset
+ */
+#define PCIE_REG_ERR_PHB_OFFSET 0x0
+#define PCIE_REG_ERR_MMIO_OFFSET 0x80
+#define PCIE_REG_ERR_DMA_OFFSET 0x100
+
+/* Debug and Trace registers */
+#define PCIE_REG_PHB_DEBUG_CONTROL0 0xe00
+#define PCIE_REG_PHB_DEBUG_STATUS0 0xe08
+#define PCIE_REG_PHB_DEBUG_CONTROL1 0xe10
+#define PCIE_REG_PHB_DEBUG_STATUS1 0xe18
+#define PCIE_REG_PHB_DEBUG_CONTROL2 0xe20
+#define PCIE_REG_PHB_DEBUG_STATUS2 0xe28
+#define PCIE_REG_PHB_DEBUG_CONTROL3 0xe30
+#define PCIE_REG_PHB_DEBUG_STATUS3 0xe38
+#define PCIE_REG_PHB_DEBUG_CONTROL4 0xe40
+#define PCIE_REG_PHB_DEBUG_STATUS4 0xe48
+#define PCIE_REG_PHB_DEBUG_CONTROL5 0xe50
+#define PCIE_REG_PHB_DEBUG_STATUS5 0xe58
+#define PCIE_REG_PHB_DEBUG_CONTROL6 0xe60
+#define PCIE_REG_PHB_DEBUG_STATUS6 0xe68
+
+/* Definition for PCIe errors */
+struct wsp_pcie_err_log_data {
+ __u64 phb_err;
+ __u64 phb_err1;
+ __u64 phb_log0;
+ __u64 phb_log1;
+ __u64 mmio_err;
+ __u64 mmio_err1;
+ __u64 mmio_log0;
+ __u64 mmio_log1;
+ __u64 dma_err;
+ __u64 dma_err1;
+ __u64 dma_log0;
+ __u64 dma_log1;
+ __u64 utl_sys_err;
+ __u64 utl_port_err;
+ __u64 utl_rc_err;
+ __u64 unused;
+};
+
+#endif /* __WSP_PCI_H */
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index d5d3ff3d757..9678081dc4e 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1285,13 +1285,11 @@ struct mpic * __init mpic_alloc(struct device_node *node,
mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
| MPIC_GREG_GCONF_MCK);
- /* Read feature register, calculate num CPUs and, for non-ISU
- * MPICs, num sources as well. On ISU MPICs, sources are counted
- * as ISUs are added
+ /*
+ * Read feature register. For non-ISU MPICs, num sources as well. On
+ * ISU MPICs, sources are counted as ISUs are added
*/
greg_feature = mpic_read(mpic->gregs, MPIC_INFO(GREG_FEATURE_0));
- mpic->num_cpus = ((greg_feature & MPIC_GREG_FEATURE_LAST_CPU_MASK)
- >> MPIC_GREG_FEATURE_LAST_CPU_SHIFT) + 1;
if (isu_size == 0) {
if (flags & MPIC_BROKEN_FRR_NIRQS)
mpic->num_sources = mpic->irq_count;
@@ -1301,10 +1299,18 @@ struct mpic * __init mpic_alloc(struct device_node *node,
>> MPIC_GREG_FEATURE_LAST_SRC_SHIFT) + 1;
}
+ /*
+ * The MPIC driver will crash if there are more cores than we
+ * can initialize, so we may as well catch that problem here.
+ */
+ BUG_ON(num_possible_cpus() > MPIC_MAX_CPUS);
+
/* Map the per-CPU registers */
- for (i = 0; i < mpic->num_cpus; i++) {
- mpic_map(mpic, node, paddr, &mpic->cpuregs[i],
- MPIC_INFO(CPU_BASE) + i * MPIC_INFO(CPU_STRIDE),
+ for_each_possible_cpu(i) {
+ unsigned int cpu = get_hard_smp_processor_id(i);
+
+ mpic_map(mpic, node, paddr, &mpic->cpuregs[cpu],
+ MPIC_INFO(CPU_BASE) + cpu * MPIC_INFO(CPU_STRIDE),
0x1000);
}
@@ -1343,7 +1349,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
}
printk(KERN_INFO "mpic: Setting up MPIC \"%s\" version %s at %llx,"
" max %d CPUs\n",
- name, vers, (unsigned long long)paddr, mpic->num_cpus);
+ name, vers, (unsigned long long)paddr, num_possible_cpus());
printk(KERN_INFO "mpic: ISU size: %d, shift: %d, mask: %x\n",
mpic->isu_size, mpic->isu_shift, mpic->isu_mask);
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index dbfe96bc878..862f11b3821 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -834,7 +834,7 @@ static int __init ppc440spe_pciex_core_init(struct device_node *np)
return 3;
}
-static int ppc440spe_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc440spe_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
{
u32 val = 1 << 24;
@@ -872,12 +872,12 @@ static int ppc440spe_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
return ppc4xx_pciex_port_reset_sdr(port);
}
-static int ppc440speA_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc440speA_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
{
return ppc440spe_pciex_init_port_hw(port);
}
-static int ppc440speB_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc440speB_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
{
int rc = ppc440spe_pciex_init_port_hw(port);
@@ -936,7 +936,7 @@ static int __init ppc460ex_pciex_core_init(struct device_node *np)
return 2;
}
-static int ppc460ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc460ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
{
u32 val;
u32 utlset1;
@@ -1092,6 +1092,10 @@ static int __init ppc460sx_pciex_core_init(struct device_node *np)
mtdcri(SDR0, PESDR1_460SX_HSSSLEW, 0xFFFF0000);
mtdcri(SDR0, PESDR2_460SX_HSSSLEW, 0xFFFF0000);
+ /* Set HSS PRBS enabled */
+ mtdcri(SDR0, PESDR0_460SX_HSSCTLSET, 0x00001130);
+ mtdcri(SDR0, PESDR2_460SX_HSSCTLSET, 0x00001130);
+
udelay(100);
/* De-assert PLLRESET */
@@ -1122,7 +1126,7 @@ static int __init ppc460sx_pciex_core_init(struct device_node *np)
return 2;
}
-static int ppc460sx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc460sx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
{
if (port->endpoint)
@@ -1132,9 +1136,6 @@ static int ppc460sx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
dcri_clrset(SDR0, port->sdr_base + PESDRn_UTLSET2,
0, 0x01000000);
- /*Gen-1*/
- mtdcri(SDR0, port->sdr_base + PESDRn_460SX_RCEI, 0x08000000);
-
dcri_clrset(SDR0, port->sdr_base + PESDRn_RCSSET,
(PESDRx_RCSSET_RSTGU | PESDRx_RCSSET_RSTDL),
PESDRx_RCSSET_RSTPYN);
@@ -1148,14 +1149,42 @@ static int ppc460sx_pciex_init_utl(struct ppc4xx_pciex_port *port)
{
/* Max 128 Bytes */
out_be32 (port->utl_base + PEUTL_PBBSZ, 0x00000000);
+ /* Assert VRB and TXE - per datasheet turn off addr validation */
+ out_be32(port->utl_base + PEUTL_PCTL, 0x80800000);
return 0;
}
+static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port)
+{
+ void __iomem *mbase;
+ int attempt = 50;
+
+ port->link = 0;
+
+ mbase = ioremap(port->cfg_space.start + 0x10000000, 0x1000);
+ if (mbase == NULL) {
+ printk(KERN_ERR "%s: Can't map internal config space !",
+ port->node->full_name);
+ goto done;
+ }
+
+ while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA)
+ & PECFG_460SX_DLLSTA_LINKUP))) {
+ attempt--;
+ mdelay(10);
+ }
+ if (attempt)
+ port->link = 1;
+done:
+ iounmap(mbase);
+
+}
+
static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = {
.core_init = ppc460sx_pciex_core_init,
.port_init_hw = ppc460sx_pciex_init_port_hw,
.setup_utl = ppc460sx_pciex_init_utl,
- .check_link = ppc4xx_pciex_check_link_sdr,
+ .check_link = ppc460sx_pciex_check_link,
};
#endif /* CONFIG_44x */
@@ -1189,7 +1218,7 @@ static void ppc405ex_pcie_phy_reset(struct ppc4xx_pciex_port *port)
mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x00101000);
}
-static int ppc405ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc405ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
{
u32 val;
@@ -1338,15 +1367,15 @@ static int __init ppc4xx_pciex_port_init(struct ppc4xx_pciex_port *port)
if (rc != 0)
return rc;
- if (ppc4xx_pciex_hwops->check_link)
- ppc4xx_pciex_hwops->check_link(port);
-
/*
* Initialize mapping: disable all regions and configure
* CFG and REG regions based on resources in the device tree
*/
ppc4xx_pciex_port_init_mapping(port);
+ if (ppc4xx_pciex_hwops->check_link)
+ ppc4xx_pciex_hwops->check_link(port);
+
/*
* Map UTL
*/
@@ -1360,13 +1389,23 @@ static int __init ppc4xx_pciex_port_init(struct ppc4xx_pciex_port *port)
ppc4xx_pciex_hwops->setup_utl(port);
/*
- * Check for VC0 active and assert RDY.
+ * Check for VC0 active or PLL Locked and assert RDY.
*/
if (port->sdr_base) {
- if (port->link &&
- ppc4xx_pciex_wait_on_sdr(port, PESDRn_RCSSTS,
- 1 << 16, 1 << 16, 5000)) {
- printk(KERN_INFO "PCIE%d: VC0 not active\n", port->index);
+ if (of_device_is_compatible(port->node,
+ "ibm,plb-pciex-460sx")){
+ if (port->link && ppc4xx_pciex_wait_on_sdr(port,
+ PESDRn_RCSSTS,
+ 1 << 12, 1 << 12, 5000)) {
+ printk(KERN_INFO "PCIE%d: PLL not locked\n",
+ port->index);
+ port->link = 0;
+ }
+ } else if (port->link &&
+ ppc4xx_pciex_wait_on_sdr(port, PESDRn_RCSSTS,
+ 1 << 16, 1 << 16, 5000)) {
+ printk(KERN_INFO "PCIE%d: VC0 not active\n",
+ port->index);
port->link = 0;
}
@@ -1573,8 +1612,15 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port *port,
dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAH, lah);
dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAL, lal);
dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKH, 0x7fffffff);
- /* Note that 3 here means enabled | single region */
- dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | 3);
+ /*Enabled and single region */
+ if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx"))
+ dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL,
+ sa | DCRO_PEGPL_460SX_OMR1MSKL_UOT
+ | DCRO_PEGPL_OMRxMSKL_VAL);
+ else
+ dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL,
+ sa | DCRO_PEGPL_OMR1MSKL_UOT
+ | DCRO_PEGPL_OMRxMSKL_VAL);
break;
case 1:
out_le32(mbase + PECFG_POM1LAH, pciah);
@@ -1582,8 +1628,8 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port *port,
dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAH, lah);
dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAL, lal);
dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKH, 0x7fffffff);
- /* Note that 3 here means enabled | single region */
- dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL, sa | 3);
+ dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL,
+ sa | DCRO_PEGPL_OMRxMSKL_VAL);
break;
case 2:
out_le32(mbase + PECFG_POM2LAH, pciah);
@@ -1592,7 +1638,9 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port *port,
dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAL, lal);
dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKH, 0x7fffffff);
/* Note that 3 here means enabled | IO space !!! */
- dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL, sa | 3);
+ dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL,
+ sa | DCRO_PEGPL_OMR3MSKL_IO
+ | DCRO_PEGPL_OMRxMSKL_VAL);
break;
}
@@ -1693,6 +1741,9 @@ static void __init ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
if (res->flags & IORESOURCE_PREFETCH)
sa |= 0x8;
+ if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx"))
+ sa |= PCI_BASE_ADDRESS_MEM_TYPE_64;
+
out_le32(mbase + PECFG_BAR0HMPA, RES_TO_U32_HIGH(sa));
out_le32(mbase + PECFG_BAR0LMPA, RES_TO_U32_LOW(sa));
@@ -1854,6 +1905,10 @@ static void __init ppc4xx_pciex_port_setup_hose(struct ppc4xx_pciex_port *port)
}
out_le16(mbase + 0x202, val);
+ /* Enable Bus master, memory, and io space */
+ if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx"))
+ out_le16(mbase + 0x204, 0x7);
+
if (!port->endpoint) {
/* Set Class Code to PCI-PCI bridge and Revision Id to 1 */
out_le32(mbase + 0x208, 0x06040001);
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.h b/arch/powerpc/sysdev/ppc4xx_pci.h
index c39a134e868..32ce763a375 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.h
+++ b/arch/powerpc/sysdev/ppc4xx_pci.h
@@ -464,6 +464,18 @@
#define PECFG_POM2LAL 0x390
#define PECFG_POM2LAH 0x394
+/* 460sx only */
+#define PECFG_460SX_DLLSTA 0x3f8
+
+/* 460sx Bit Mappings */
+#define PECFG_460SX_DLLSTA_LINKUP 0x00000010
+#define DCRO_PEGPL_460SX_OMR1MSKL_UOT 0x00000004
+
+/* PEGPL Bit Mappings */
+#define DCRO_PEGPL_OMRxMSKL_VAL 0x00000001
+#define DCRO_PEGPL_OMR1MSKL_UOT 0x00000002
+#define DCRO_PEGPL_OMR3MSKL_IO 0x00000002
+
/* SDR Bit Mappings */
#define PESDRx_RCSSET_HLDPLB 0x10000000
#define PESDRx_RCSSET_RSTGU 0x01000000
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 50e32afe392..4c79b6fbee1 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -276,7 +276,7 @@ static const struct icp_ops icp_native_ops = {
#endif
};
-int icp_native_init(void)
+int __init icp_native_init(void)
{
struct device_node *np;
u32 indx = 0;
diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
index a687a0d1696..a774c0ddaf5 100644
--- a/drivers/edac/cpc925_edac.c
+++ b/drivers/edac/cpc925_edac.c
@@ -90,6 +90,7 @@ enum apimask_bits {
ECC_MASK_ENABLE = (APIMASK_ECC_UE_H | APIMASK_ECC_CE_H |
APIMASK_ECC_UE_L | APIMASK_ECC_CE_L),
};
+#define APIMASK_ADI(n) CPC925_BIT(((n)+1))
/************************************************************
* Processor Interface Exception Register (APIEXCP)
@@ -581,16 +582,73 @@ static void cpc925_mc_check(struct mem_ctl_info *mci)
}
/******************** CPU err device********************************/
+static u32 cpc925_cpu_mask_disabled(void)
+{
+ struct device_node *cpus;
+ struct device_node *cpunode = NULL;
+ static u32 mask = 0;
+
+ /* use cached value if available */
+ if (mask != 0)
+ return mask;
+
+ mask = APIMASK_ADI0 | APIMASK_ADI1;
+
+ cpus = of_find_node_by_path("/cpus");
+ if (cpus == NULL) {
+ cpc925_printk(KERN_DEBUG, "No /cpus node !\n");
+ return 0;
+ }
+
+ while ((cpunode = of_get_next_child(cpus, cpunode)) != NULL) {
+ const u32 *reg = of_get_property(cpunode, "reg", NULL);
+
+ if (strcmp(cpunode->type, "cpu")) {
+ cpc925_printk(KERN_ERR, "Not a cpu node in /cpus: %s\n", cpunode->name);
+ continue;
+ }
+
+ if (reg == NULL || *reg > 2) {
+ cpc925_printk(KERN_ERR, "Bad reg value at %s\n", cpunode->full_name);
+ continue;
+ }
+
+ mask &= ~APIMASK_ADI(*reg);
+ }
+
+ if (mask != (APIMASK_ADI0 | APIMASK_ADI1)) {
+ /* We assume that each CPU sits on it's own PI and that
+ * for present CPUs the reg property equals to the PI
+ * interface id */
+ cpc925_printk(KERN_WARNING,
+ "Assuming PI id is equal to CPU MPIC id!\n");
+ }
+
+ of_node_put(cpunode);
+ of_node_put(cpus);
+
+ return mask;
+}
+
/* Enable CPU Errors detection */
static void cpc925_cpu_init(struct cpc925_dev_info *dev_info)
{
u32 apimask;
+ u32 cpumask;
apimask = __raw_readl(dev_info->vbase + REG_APIMASK_OFFSET);
- if ((apimask & CPU_MASK_ENABLE) == 0) {
- apimask |= CPU_MASK_ENABLE;
- __raw_writel(apimask, dev_info->vbase + REG_APIMASK_OFFSET);
+
+ cpumask = cpc925_cpu_mask_disabled();
+ if (apimask & cpumask) {
+ cpc925_printk(KERN_WARNING, "CPU(s) not present, "
+ "but enabled in APIMASK, disabling\n");
+ apimask &= ~cpumask;
}
+
+ if ((apimask & CPU_MASK_ENABLE) == 0)
+ apimask |= CPU_MASK_ENABLE;
+
+ __raw_writel(apimask, dev_info->vbase + REG_APIMASK_OFFSET);
}
/* Disable CPU Errors detection */
@@ -622,6 +680,9 @@ static void cpc925_cpu_check(struct edac_device_ctl_info *edac_dev)
if ((apiexcp & CPU_EXCP_DETECTED) == 0)
return;
+ if ((apiexcp & ~cpc925_cpu_mask_disabled()) == 0)
+ return;
+
apimask = __raw_readl(dev_info->vbase + REG_APIMASK_OFFSET);
cpc925_printk(KERN_INFO, "Processor Interface Fault\n"
"Processor Interface register dump:\n");
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index 0de7d877089..38400963e24 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -205,7 +205,7 @@ static struct platform_driver ppc4xx_edac_driver = {
.remove = ppc4xx_edac_remove,
.driver = {
.owner = THIS_MODULE,
- .name = PPC4XX_EDAC_MODULE_NAME
+ .name = PPC4XX_EDAC_MODULE_NAME,
.of_match_table = ppc4xx_edac_match,
},
};
diff --git a/drivers/net/ps3_gelic_net.c b/drivers/net/ps3_gelic_net.c
index d82a82d9870..e743c9418ac 100644
--- a/drivers/net/ps3_gelic_net.c
+++ b/drivers/net/ps3_gelic_net.c
@@ -1674,6 +1674,9 @@ static int __devinit ps3_gelic_driver_probe(struct ps3_system_bus_device *dev)
int result;
pr_debug("%s: called\n", __func__);
+
+ udbg_shutdown_ps3gelic();
+
result = ps3_open_hv_device(dev);
if (result) {
diff --git a/drivers/net/ps3_gelic_net.h b/drivers/net/ps3_gelic_net.h
index d3fadfbc3bc..a93df6ac190 100644
--- a/drivers/net/ps3_gelic_net.h
+++ b/drivers/net/ps3_gelic_net.h
@@ -359,6 +359,12 @@ static inline void *port_priv(struct gelic_port *port)
return port->priv;
}
+#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC
+extern void udbg_shutdown_ps3gelic(void);
+#else
+static inline void udbg_shutdown_ps3gelic(void) {}
+#endif
+
extern int gelic_card_set_irq_mask(struct gelic_card *card, u64 mask);
/* shared netdev ops */
extern void gelic_card_up(struct gelic_card *card);
diff --git a/drivers/tty/serial/8250.c b/drivers/tty/serial/8250.c
index 7f50999eebc..610b8e63710 100644
--- a/drivers/tty/serial/8250.c
+++ b/drivers/tty/serial/8250.c
@@ -443,24 +443,6 @@ static void au_serial_out(struct uart_port *p, int offset, int value)
__raw_writel(value, p->membase + offset);
}
-static unsigned int tsi_serial_in(struct uart_port *p, int offset)
-{
- unsigned int tmp;
- offset = map_8250_in_reg(p, offset) << p->regshift;
- if (offset == UART_IIR) {
- tmp = readl(p->membase + (UART_IIR & ~3));
- return (tmp >> 16) & 0xff; /* UART_IIR % 4 == 2 */
- } else
- return readb(p->membase + offset);
-}
-
-static void tsi_serial_out(struct uart_port *p, int offset, int value)
-{
- offset = map_8250_out_reg(p, offset) << p->regshift;
- if (!((offset == UART_IER) && (value & UART_IER_UUE)))
- writeb(value, p->membase + offset);
-}
-
/* Save the LCR value so it can be re-written when a Busy Detect IRQ occurs. */
static inline void dwapb_save_out_value(struct uart_port *p, int offset,
int value)
@@ -535,11 +517,6 @@ static void set_io_from_upio(struct uart_port *p)
p->serial_out = au_serial_out;
break;
- case UPIO_TSI:
- p->serial_in = tsi_serial_in;
- p->serial_out = tsi_serial_out;
- break;
-
case UPIO_DWAPB:
p->serial_in = mem_serial_in;
p->serial_out = dwapb_serial_out;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 347fdc32177..aa32fecd1d3 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -41,6 +41,9 @@ struct dma_map_ops {
int (*mapping_error)(struct device *dev, dma_addr_t dma_addr);
int (*dma_supported)(struct device *dev, u64 mask);
int (*set_dma_mask)(struct device *dev, u64 mask);
+#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
+ u64 (*get_required_mask)(struct device *dev);
+#endif
int is_phys;
};