diff options
| author | David S. Miller <davem@davemloft.net> | 2016-08-18 01:17:32 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2016-08-18 01:17:32 -0400 |
| commit | 60747ef4d173c2747bf7f0377fb22846cb422195 (patch) | |
| tree | ea0faf33b952495c47909be1400c475a3f3821b0 /arch | |
| parent | 484334198f8ce9552e20930fff9408ebf6bcf94d (diff) | |
| parent | 184ca823481c99dadd7d946e5afd4bb921eab30d (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Minor overlapping changes for both merge conflicts.
Resolution work done by Stephen Rothwell was used
as a reference.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'arch')
474 files changed, 6704 insertions, 3201 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index bd8056b5b246..e9c9334507dd 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -461,6 +461,15 @@ config CC_STACKPROTECTOR_STRONG endchoice +config HAVE_ARCH_WITHIN_STACK_FRAMES + bool + help + An architecture should select this if it can walk the kernel stack + frames to determine if an object is part of either the arguments + or local variables (i.e. that it excludes saved return addresses, + and similar) by implementing an inline arch_within_stack_frames(), + which is used by CONFIG_HARDENED_USERCOPY. + config HAVE_CONTEXT_TRACKING bool help diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h index 3c3451f58ff4..c63b6ac19ee5 100644 --- a/arch/alpha/include/asm/dma-mapping.h +++ b/arch/alpha/include/asm/dma-mapping.h @@ -1,8 +1,6 @@ #ifndef _ALPHA_DMA_MAPPING_H #define _ALPHA_DMA_MAPPING_H -#include <linux/dma-attrs.h> - extern struct dma_map_ops *dma_ops; static inline struct dma_map_ops *get_dma_ops(struct device *dev) diff --git a/arch/alpha/include/asm/rtc.h b/arch/alpha/include/asm/rtc.h deleted file mode 100644 index f71c3b0ed360..000000000000 --- a/arch/alpha/include/asm/rtc.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/rtc.h> diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 53dd2f1a53aa..d5f0580746a5 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -24,7 +24,6 @@ #include <asm/gct.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> -#include <asm/rtc.h> #include <asm/vga.h> #include "proto.h" diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index 8e735b5e56bd..bb152e21e5ae 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -109,7 +109,7 @@ sys_pciconfig_write(unsigned long bus, unsigned long dfn, static void *alpha_noop_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret; diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 8969bf2dfe3a..451fc9cdd323 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -349,7 +349,7 @@ static struct pci_dev *alpha_gendev_to_pci(struct device *dev) static dma_addr_t alpha_pci_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_dev *pdev = alpha_gendev_to_pci(dev); int dac_allowed; @@ -369,7 +369,7 @@ static dma_addr_t alpha_pci_map_page(struct device *dev, struct page *page, static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long flags; struct pci_dev *pdev = alpha_gendev_to_pci(dev); @@ -433,7 +433,7 @@ static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr, static void *alpha_pci_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_dev *pdev = alpha_gendev_to_pci(dev); void *cpu_addr; @@ -478,7 +478,7 @@ try_again: static void alpha_pci_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_dev *pdev = alpha_gendev_to_pci(dev); pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL); @@ -651,7 +651,7 @@ sg_fill(struct device *dev, struct scatterlist *leader, struct scatterlist *end, static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_dev *pdev = alpha_gendev_to_pci(dev); struct scatterlist *start, *end, *out; @@ -729,7 +729,7 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg, static void alpha_pci_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_dev *pdev = alpha_gendev_to_pci(dev); unsigned long flags; diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c index f535a3fd0f60..ceed68c7500b 100644 --- a/arch/alpha/kernel/rtc.c +++ b/arch/alpha/kernel/rtc.c @@ -15,8 +15,6 @@ #include <linux/rtc.h> #include <linux/platform_device.h> -#include <asm/rtc.h> - #include "proto.h" @@ -81,7 +79,7 @@ init_rtc_epoch(void) static int alpha_rtc_read_time(struct device *dev, struct rtc_time *tm) { - __get_rtc_time(tm); + mc146818_get_time(tm); /* Adjust for non-default epochs. It's easier to depend on the generic __get_rtc_time and adjust the epoch here than create @@ -112,7 +110,7 @@ alpha_rtc_set_time(struct device *dev, struct rtc_time *tm) tm = &xtm; } - return __set_rtc_time(tm); + return mc146818_set_time(tm); } static int diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index ab74b5d9186c..20afc65e22dc 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -22,7 +22,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { unsigned long order = get_order(size); struct page *page; @@ -46,7 +46,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size, * (vs. always going to memory - thus are faster) */ if ((is_isa_arcv2() && ioc_exists) || - dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) + (attrs & DMA_ATTR_NON_CONSISTENT)) need_coh = 0; /* @@ -90,13 +90,13 @@ static void *arc_dma_alloc(struct device *dev, size_t size, } static void arc_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { phys_addr_t paddr = plat_dma_to_phys(dev, dma_handle); struct page *page = virt_to_page(paddr); int is_non_coh = 1; - is_non_coh = dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs) || + is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) || (is_isa_arcv2() && ioc_exists); if (PageHighMem(page) || !is_non_coh) @@ -130,7 +130,7 @@ static void _dma_cache_sync(phys_addr_t paddr, size_t size, static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { phys_addr_t paddr = page_to_phys(page) + offset; _dma_cache_sync(paddr, size, dir); @@ -138,7 +138,7 @@ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page, } static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *s; int i; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2d601d769a1c..a9c4e48bb7ec 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -35,6 +35,7 @@ config ARM select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_MMAP_RND_BITS if MMU diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 56ea5c60b318..61f6ccc19cfa 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -260,12 +260,14 @@ machdirs := $(patsubst %,arch/arm/mach-%/,$(machine-y)) platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y))) ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y) +ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y) ifeq ($(KBUILD_SRC),) KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs)) else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs)) endif endif +endif export TEXT_OFFSET GZFLAGS MMUEXT diff --git a/arch/arm/boot/dts/arm-realview-pbx-a9.dts b/arch/arm/boot/dts/arm-realview-pbx-a9.dts index db808f92dd79..90d00b407f85 100644 --- a/arch/arm/boot/dts/arm-realview-pbx-a9.dts +++ b/arch/arm/boot/dts/arm-realview-pbx-a9.dts @@ -70,13 +70,12 @@ * associativity as these may be erroneously set * up by boot loader(s). */ - cache-size = <1048576>; // 1MB - cache-sets = <4096>; + cache-size = <131072>; // 128KB + cache-sets = <512>; cache-line-size = <32>; arm,parity-disable; - arm,tag-latency = <1>; - arm,data-latency = <1 1>; - arm,dirty-latency = <1>; + arm,tag-latency = <1 1 1>; + arm,data-latency = <1 1 1>; }; scu: scu@1f000000 { diff --git a/arch/arm/boot/dts/integratorap.dts b/arch/arm/boot/dts/integratorap.dts index cf06e32ee108..4b34b54e09a1 100644 --- a/arch/arm/boot/dts/integratorap.dts +++ b/arch/arm/boot/dts/integratorap.dts @@ -42,7 +42,7 @@ }; syscon { - compatible = "arm,integrator-ap-syscon"; + compatible = "arm,integrator-ap-syscon", "syscon"; reg = <0x11000000 0x100>; interrupt-parent = <&pic>; /* These are the logical module IRQs */ diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts index d43f15b4f79a..79430fbfec3b 100644 --- a/arch/arm/boot/dts/integratorcp.dts +++ b/arch/arm/boot/dts/integratorcp.dts @@ -94,7 +94,7 @@ }; syscon { - compatible = "arm,integrator-cp-syscon"; + compatible = "arm,integrator-cp-syscon", "syscon"; reg = <0xcb000000 0x100>; }; diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi index 00cb314d5e4d..e23f46d15c80 100644 --- a/arch/arm/boot/dts/keystone.dtsi +++ b/arch/arm/boot/dts/keystone.dtsi @@ -70,14 +70,6 @@ cpu_on = <0x84000003>; }; - psci { - compatible = "arm,psci"; - method = "smc"; - cpu_suspend = <0x84000001>; - cpu_off = <0x84000002>; - cpu_on = <0x84000003>; - }; - soc { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts index e52b82449a79..6403e0de540e 100644 --- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts +++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts @@ -1382,7 +1382,7 @@ * Pin 41: BR_UART1_TXD * Pin 44: BR_UART1_RXD */ - serial@70006000 { + serial@0,70006000 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; @@ -1394,7 +1394,7 @@ * Pin 71: UART2_CTS_L * Pin 74: UART2_RTS_L */ - serial@70006040 { + serial@0,70006040 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 1143c4d5c567..301281645d08 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -310,7 +310,7 @@ static inline void unmap_single(struct device *dev, struct safe_buffer *buf, */ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dma_addr; int ret; @@ -344,7 +344,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page, * should be) */ static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct safe_buffer *buf; diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig index b6e54ee9bdbd..ca39c04fec6b 100644 --- a/arch/arm/configs/aspeed_g4_defconfig +++ b/arch/arm/configs/aspeed_g4_defconfig @@ -58,7 +58,7 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_FANOTIFY=y -CONFIG_PRINTK_TIME=1 +CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_STRIP_ASM_SYMS=y CONFIG_PAGE_POISONING=y diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig index 892605167357..4f366b0370e9 100644 --- a/arch/arm/configs/aspeed_g5_defconfig +++ b/arch/arm/configs/aspeed_g5_defconfig @@ -59,7 +59,7 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_FANOTIFY=y -CONFIG_PRINTK_TIME=1 +CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_STRIP_ASM_SYMS=y CONFIG_PAGE_POISONING=y diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index a83570f10124..d009f7911ffc 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -5,7 +5,6 @@ #include <linux/mm_types.h> #include <linux/scatterlist.h> -#include <linux/dma-attrs.h> #include <linux/dma-debug.h> #include <asm/memory.h> @@ -174,7 +173,7 @@ static inline void dma_mark_clean(void *addr, size_t size) { } * to be the device-viewed address. */ extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, struct dma_attrs *attrs); + gfp_t gfp, unsigned long attrs); /** * arm_dma_free - free memory allocated by arm_dma_alloc @@ -191,7 +190,7 @@ extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, * during and after this call executing are illegal. */ extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs); + dma_addr_t handle, unsigned long attrs); /** * arm_dma_mmap - map a coherent DMA allocation into user space @@ -208,7 +207,7 @@ extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, */ extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs); + unsigned long attrs); /* * This can be called during early boot to increase the size of the atomic @@ -262,16 +261,16 @@ extern void dmabounce_unregister_dev(struct device *); * The scatter list versions of the above methods. */ extern int arm_dma_map_sg(struct device *, struct scatterlist *, int, - enum dma_data_direction, struct dma_attrs *attrs); + enum dma_data_direction, unsigned long attrs); extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int, - enum dma_data_direction, struct dma_attrs *attrs); + enum dma_data_direction, unsigned long attrs); extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int, enum dma_data_direction); extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int, enum dma_data_direction); extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs); + unsigned long attrs); #endif /* __KERNEL__ */ #endif diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 62a6f65029e6..a93c0f99acf7 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -480,7 +480,10 @@ arm_copy_from_user(void *to, const void __user *from, unsigned long n); static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned int __ua_flags = uaccess_save_and_enable(); + unsigned int __ua_flags; + + check_object_size(to, n, false); + __ua_flags = uaccess_save_and_enable(); n = arm_copy_from_user(to, from, n); uaccess_restore(__ua_flags); return n; @@ -495,11 +498,15 @@ static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { #ifndef CONFIG_UACCESS_WITH_MEMCPY - unsigned int __ua_flags = uaccess_save_and_enable(); + unsigned int __ua_flags; + + check_object_size(from, n, true); + __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; #else + check_object_size(from, n, true); return arm_copy_to_user(to, from, n); #endif } diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 9408a994cc91..95ce6ac3a971 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -2,15 +2,14 @@ #define _ASM_ARM_XEN_PAGE_COHERENT_H #include <asm/page.h> -#include <linux/dma-attrs.h> #include <linux/dma-mapping.h> void __xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, unsigned long attrs); void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void __xen_dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir); @@ -18,22 +17,20 @@ void __xen_dma_sync_single_for_device(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir); static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) { return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); } static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) { __generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); } static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { unsigned long page_pfn = page_to_xen_pfn(page); unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); @@ -58,8 +55,7 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, } static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + size_t size, enum dma_data_direction dir, unsigned long attrs) { unsigned long pfn = PFN_DOWN(handle); /* diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 087acb569b63..5f221acd21ae 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd, mm_segment_t fs; long ret, err, i; - if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event))) + if (maxevents <= 0 || + maxevents > (INT_MAX/sizeof(*kbuf)) || + maxevents > (INT_MAX/sizeof(*events))) return -EINVAL; + if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents)) + return -EFAULT; kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL); if (!kbuf) return -ENOMEM; @@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid, if (nsops < 1 || nsops > SEMOPM) return -EINVAL; + if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops)) + return -EFAULT; sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL); if (!sops) return -ENOMEM; diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 99420fc1f066..d24e5dd2aa7a 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -44,7 +44,7 @@ #endif #if (defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)) || \ - defined(CONFIG_GENERIC_BUG) + defined(CONFIG_GENERIC_BUG) || defined(CONFIG_JUMP_LABEL) #define ARM_EXIT_KEEP(x) x #define ARM_EXIT_DISCARD(x) #else diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 95a000515e43..3e1cd0452d67 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -32,6 +32,8 @@ config KVM select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQ_ROUTING depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER ---help--- Support hosting virtualized guest machines. diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 5e28df80dca7..10d77a66cad5 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -29,4 +29,5 @@ obj-y += $(KVM)/arm/vgic/vgic-v2.o obj-y += $(KVM)/arm/vgic/vgic-mmio.o obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o +obj-y += $(KVM)/irqchip.o obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index d94bb9093ead..75f130ef6504 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1009,9 +1009,13 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { + int ret; if (!vgic_present) return -ENXIO; - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_lock(&kvm->lock); + ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_unlock(&kvm->lock); + return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; diff --git a/arch/arm/kvm/irq.h b/arch/arm/kvm/irq.h new file mode 100644 index 000000000000..b74099b905fd --- /dev/null +++ b/arch/arm/kvm/irq.h @@ -0,0 +1,19 @@ +/* + * irq.h: in kernel interrupt controller related definitions + * Copyright (c) 2016 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This header is included by irqchip.c. However, on ARM, interrupt + * controller declarations are located in include/kvm/arm_vgic.h since + * they are mostly shared between arm and arm64. + */ + +#ifndef __IRQ_H +#define __IRQ_H + +#include <kvm/arm_vgic.h> + +#endif diff --git a/arch/arm/mach-clps711x/Kconfig b/arch/arm/mach-clps711x/Kconfig index dc7c6edeab39..61284b9389cf 100644 --- a/arch/arm/mach-clps711x/Kconfig +++ b/arch/arm/mach-clps711x/Kconfig @@ -1,13 +1,13 @@ menuconfig ARCH_CLPS711X bool "Cirrus Logic EP721x/EP731x-based" depends on ARCH_MULTI_V4T - select ARCH_REQUIRE_GPIOLIB select AUTO_ZRELADDR select CLKSRC_OF select CLPS711X_TIMER select COMMON_CLK select CPU_ARM720T select GENERIC_CLOCKEVENTS + select GPIOLIB select MFD_SYSCON select OF_IRQ select USE_OF diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c index 45b81a2bcd4b..3b39ea353d30 100644 --- a/arch/arm/mach-ep93xx/ts72xx.c +++ b/arch/arm/mach-ep93xx/ts72xx.c @@ -16,7 +16,7 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/io.h> -#include <linux/m48t86.h> +#include <linux/platform_data/rtc-m48t86.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile index e53c6cfcab51..6c6497e80a7b 100644 --- a/arch/arm/mach-mvebu/Makefile +++ b/arch/arm/mach-mvebu/Makefile @@ -1,5 +1,4 @@ -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ - -I$(srctree)/arch/arm/plat-orion/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include AFLAGS_coherency_ll.o := -Wa,-march=armv7-a CFLAGS_pmsu.o := -march=armv7-a diff --git a/arch/arm/mach-orion5x/ts78xx-setup.c b/arch/arm/mach-orion5x/ts78xx-setup.c index 3a58a5d4a28a..8d597267d0c4 100644 --- a/arch/arm/mach-orion5x/ts78xx-setup.c +++ b/arch/arm/mach-orion5x/ts78xx-setup.c @@ -16,7 +16,7 @@ #include <linux/platform_device.h> #include <linux/mv643xx_eth.h> #include <linux/ata_platform.h> -#include <linux/m48t86.h> +#include <linux/platform_data/rtc-m48t86.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> #include <linux/timeriomem-rng.h> diff --git a/arch/arm/mach-oxnas/Kconfig b/arch/arm/mach-oxnas/Kconfig index 567496bd250a..29100beb2e7f 100644 --- a/arch/arm/mach-oxnas/Kconfig +++ b/arch/arm/mach-oxnas/Kconfig @@ -11,11 +11,13 @@ if ARCH_OXNAS config MACH_OX810SE bool "Support OX810SE Based Products" + select ARCH_HAS_RESET_CONTROLLER select COMMON_CLK_OXNAS select CPU_ARM926T select MFD_SYSCON select OXNAS_RPS_TIMER select PINCTRL_OXNAS + select RESET_CONTROLLER select RESET_OXNAS select VERSATILE_FPGA_IRQ help diff --git a/arch/arm/mach-pxa/cm-x270.c b/arch/arm/mach-pxa/cm-x270.c index fa5f51d633a3..be4a66166d61 100644 --- a/arch/arm/mach-pxa/cm-x270.c +++ b/arch/arm/mach-pxa/cm-x270.c @@ -14,7 +14,7 @@ #include <linux/gpio.h> #include <linux/delay.h> -#include <linux/rtc-v3020.h> +#include <linux/platform_data/rtc-v3020.h> #include <video/mbxfb.h> #include <linux/spi/spi.h> diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c index 5f5ac7c8faf0..868448d2cd82 100644 --- a/arch/arm/mach-pxa/cm-x300.c +++ b/arch/arm/mach-pxa/cm-x300.c @@ -25,7 +25,7 @@ #include <linux/gpio.h> #include <linux/dm9000.h> #include <linux/leds.h> -#include <linux/rtc-v3020.h> +#include <linux/platform_data/rtc-v3020.h> #include <linux/pwm.h> #include <linux/pwm_backlight.h> diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index dc109dc3a622..10bfdb169366 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -13,6 +13,7 @@ */ #include <linux/kernel.h> +#include <linux/module.h> /* symbol_get ; symbol_put */ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/major.h> diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 6e0268deec43..03354c21e1f2 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -14,7 +14,7 @@ #include <linux/delay.h> #include <linux/dm9000.h> -#include <linux/rtc-v3020.h> +#include <linux/platform_data/rtc-v3020.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> #include <linux/mtd/physmap.h> diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 1080580b1343..2c150bfc0cd5 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -13,6 +13,7 @@ */ #include <linux/kernel.h> +#include <linux/module.h> /* symbol_get ; symbol_put */ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/gpio_keys.h> diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile index dae8d86ef4cc..404882130956 100644 --- a/arch/arm/mach-realview/Makefile +++ b/arch/arm/mach-realview/Makefile @@ -1,8 +1,7 @@ # # Makefile for the linux kernel. # -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ - -I$(srctree)/arch/arm/plat-versatile/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include obj-y := core.o obj-$(CONFIG_REALVIEW_DT) += realview-dt.o diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile index 72b9e9671507..fa7fb716e388 100644 --- a/arch/arm/mach-s5pv210/Makefile +++ b/arch/arm/mach-s5pv210/Makefile @@ -5,7 +5,7 @@ # # Licensed under GPLv2 -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include # Core diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index f3dba6f356e2..02e21bceb085 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -40,5 +40,8 @@ bool shmobile_smp_cpu_can_disable(unsigned int cpu) bool __init shmobile_smp_init_fallback_ops(void) { /* fallback on PSCI/smp_ops if no other DT based method is detected */ + if (!IS_ENABLED(CONFIG_SMP)) + return false; + return platform_can_secondary_boot() ? true : false; } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index b7eed75960fe..c6834c0cfd1c 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -128,16 +128,16 @@ static void __dma_page_dev_to_cpu(struct page *, unsigned long, */ static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_cpu_to_dev(page, offset, size, dir); return pfn_to_dma(dev, page_to_pfn(page)) + offset; } static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { return pfn_to_dma(dev, page_to_pfn(page)) + offset; } @@ -157,10 +157,9 @@ static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *pag * whatever the device wrote there. */ static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)), handle & ~PAGE_MASK, size, dir); } @@ -198,12 +197,12 @@ struct dma_map_ops arm_dma_ops = { EXPORT_SYMBOL(arm_dma_ops); static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs); + dma_addr_t *handle, gfp_t gfp, unsigned long attrs); static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs); + dma_addr_t handle, unsigned long attrs); static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs); + unsigned long attrs); struct dma_map_ops arm_coherent_dma_ops = { .alloc = arm_coherent_dma_alloc, @@ -639,11 +638,11 @@ static void __free_from_contiguous(struct device *dev, struct page *page, dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); } -static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot) +static inline pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot) { - prot = dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs) ? - pgprot_writecombine(prot) : - pgprot_dmacoherent(prot); + prot = (attrs & DMA_ATTR_WRITE_COMBINE) ? + pgprot_writecombine(prot) : + pgprot_dmacoherent(prot); return prot; } @@ -751,7 +750,7 @@ static struct arm_dma_allocator remap_allocator = { static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, pgprot_t prot, bool is_coherent, - struct dma_attrs *attrs, const void *caller) + unsigned long attrs, const void *caller) { u64 mask = get_coherent_dma_mask(dev); struct page *page = NULL; @@ -764,7 +763,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, .gfp = gfp, .prot = prot, .caller = caller, - .want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs), + .want_vaddr = ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0), .coherent_flag = is_coherent ? COHERENT : NORMAL, }; @@ -834,7 +833,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, * virtual and bus address for that space. */ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, struct dma_attrs *attrs) + gfp_t gfp, unsigned long attrs) { pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); @@ -843,7 +842,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, } static void *arm_coherent_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true, attrs, __builtin_return_address(0)); @@ -851,7 +850,7 @@ static void *arm_coherent_dma_alloc(struct device *dev, size_t size, static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { int ret = -ENXIO; #ifdef CONFIG_MMU @@ -879,14 +878,14 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, */ static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef CONFIG_MMU vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); @@ -898,7 +897,7 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma, * Free a buffer as defined by the above mapping. */ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs, + dma_addr_t handle, unsigned long attrs, bool is_coherent) { struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); @@ -908,7 +907,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, .size = PAGE_ALIGN(size), .cpu_addr = cpu_addr, .page = page, - .want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs), + .want_vaddr = ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0), }; buf = arm_dma_buffer_find(cpu_addr); @@ -920,20 +919,20 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, } void arm_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs) + dma_addr_t handle, unsigned long attrs) { __arm_dma_free(dev, size, cpu_addr, handle, attrs, false); } static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs) + dma_addr_t handle, unsigned long attrs) { __arm_dma_free(dev, size, cpu_addr, handle, attrs, true); } int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t handle, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); int ret; @@ -1066,7 +1065,7 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, * here. */ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; @@ -1100,7 +1099,7 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, * rules concerning calls here are the same as for dma_unmap_single(). */ void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); struct scatterlist *s; @@ -1273,7 +1272,7 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping, static const int iommu_order_array[] = { 9, 8, 4, 0 }; static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, - gfp_t gfp, struct dma_attrs *attrs, + gfp_t gfp, unsigned long attrs, int coherent_flag) { struct page **pages; @@ -1289,7 +1288,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, if (!pages) return NULL; - if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs)) + if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { unsigned long order = get_order(size); struct page *page; @@ -1307,7 +1306,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, } /* Go straight to 4K chunks if caller says it's OK. */ - if (dma_get_attr(DMA_ATTR_ALLOC_SINGLE_PAGES, attrs)) + if (attrs & DMA_ATTR_ALLOC_SINGLE_PAGES) order_idx = ARRAY_SIZE(iommu_order_array) - 1; /* @@ -1363,12 +1362,12 @@ error: } static int __iommu_free_buffer(struct device *dev, struct page **pages, - size_t size, struct dma_attrs *attrs) + size_t size, unsigned long attrs) { int count = size >> PAGE_SHIFT; int i; - if (dma_get_attr(DMA_ATTR_FORCE_CONTIGUOUS, attrs)) { + if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { dma_release_from_contiguous(dev, pages[0], count); } else { for (i = 0; i < count; i++) @@ -1460,14 +1459,14 @@ static struct page **__atomic_get_pages(void *addr) return (struct page **)page; } -static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs) +static struct page **__iommu_get_pages(void *cpu_addr, unsigned long attrs) { struct vm_struct *area; if (__in_atomic_pool(cpu_addr, PAGE_SIZE)) return __atomic_get_pages(cpu_addr); - if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) + if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) return cpu_addr; area = find_vm_area(cpu_addr); @@ -1511,7 +1510,7 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr, } static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs, + dma_addr_t *handle, gfp_t gfp, unsigned long attrs, int coherent_flag) { pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); @@ -1542,7 +1541,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size, if (*handle == DMA_ERROR_CODE) goto err_buffer; - if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) + if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) return pages; addr = __iommu_alloc_remap(pages, size, gfp, prot, @@ -1560,20 +1559,20 @@ err_buffer: } static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL); } static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT); } static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long uaddr = vma->vm_start; unsigned long usize = vma->vm_end - vma->vm_start; @@ -1603,7 +1602,7 @@ static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma } static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, - dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) + dma_addr_t dma_addr, size_t size, unsigned long attrs) { vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot); @@ -1612,7 +1611,7 @@ static int arm_iommu_mmap_attrs(struct device *dev, static int arm_coherent_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, - dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) + dma_addr_t dma_addr, size_t size, unsigned long attrs) { return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs); } @@ -1622,7 +1621,7 @@ static int arm_coherent_iommu_mmap_attrs(struct device *dev, * Must not be called with IRQs disabled. */ void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs, int coherent_flag) + dma_addr_t handle, unsigned long attrs, int coherent_flag) { struct page **pages; size = PAGE_ALIGN(size); @@ -1638,7 +1637,7 @@ void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, return; } - if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) { + if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0) { dma_common_free_remap(cpu_addr, size, VM_ARM_DMA_CONSISTENT | VM_USERMAP); } @@ -1648,20 +1647,20 @@ void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, } void arm_iommu_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) + void *cpu_addr, dma_addr_t handle, unsigned long attrs) { __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL); } void arm_coherent_iommu_free_attrs(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) + void *cpu_addr, dma_addr_t handle, unsigned long attrs) { __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT); } static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, - size_t size, struct dma_attrs *attrs) + size_t size, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page **pages = __iommu_get_pages(cpu_addr, attrs); @@ -1699,7 +1698,7 @@ static int __dma_direction_to_prot(enum dma_data_direction dir) */ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, size_t size, dma_addr_t *handle, - enum dma_data_direction dir, struct dma_attrs *attrs, + enum dma_data_direction dir, unsigned long attrs, bool is_coherent) { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); @@ -1720,8 +1719,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); - if (!is_coherent && - !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); prot = __dma_direction_to_prot(dir); @@ -1742,7 +1740,7 @@ fail: } static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs, + enum dma_data_direction dir, unsigned long attrs, bool is_coherent) { struct scatterlist *s = sg, *dma = sg, *start = sg; @@ -1800,7 +1798,7 @@ bad_mapping: * obtained via sg_dma_{address,length}. */ int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, unsigned long attrs) { return __iommu_map_sg(dev, sg, nents, dir, attrs, true); } @@ -1818,14 +1816,14 @@ int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg, * sg_dma_{address,length}. */ int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, unsigned long attrs) { return __iommu_map_sg(dev, sg, nents, dir, attrs, false); } static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs, - bool is_coherent) + int nents, enum dma_data_direction dir, + unsigned long attrs, bool is_coherent) { struct scatterlist *s; int i; @@ -1834,8 +1832,7 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, if (sg_dma_len(s)) __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s)); - if (!is_coherent && - !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir); } @@ -1852,7 +1849,8 @@ static void __iommu_unmap_sg(struct device *dev, struct scatterlist *sg, * rules concerning calls here are the same as for dma_unmap_single(). */ void arm_coherent_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, + unsigned long attrs) { __iommu_unmap_sg(dev, sg, nents, dir, attrs, true); } @@ -1868,7 +1866,8 @@ void arm_coherent_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, * rules concerning calls here are the same as for dma_unmap_single(). */ void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, + unsigned long attrs) { __iommu_unmap_sg(dev, sg, nents, dir, attrs, false); } @@ -1921,7 +1920,7 @@ void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg, */ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t dma_addr; @@ -1955,9 +1954,9 @@ fail: */ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_cpu_to_dev(page, offset, size, dir); return arm_coherent_iommu_map_page(dev, page, offset, size, dir, attrs); @@ -1973,8 +1972,7 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, * Coherent IOMMU aware version of arm_dma_unmap_page() */ static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + size_t size, enum dma_data_direction dir, unsigned long attrs) { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; @@ -1998,8 +1996,7 @@ static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle, * IOMMU aware version of arm_dma_unmap_page() */ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + size_t size, enum dma_data_direction dir, unsigned long attrs) { struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); dma_addr_t iova = handle & PAGE_MASK; @@ -2010,7 +2007,7 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, if (!iova) return; - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_page_dev_to_cpu(page, offset, size, dir); iommu_unmap(mapping->domain, iova, len); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index c5f9a9e3d1f3..d062f08f5020 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -98,11 +98,11 @@ static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle, void __xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { if (is_device_dma_coherent(hwdev)) return; - if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) return; __xen_dma_page_cpu_to_dev(hwdev, dev_addr, size, dir); @@ -110,12 +110,12 @@ void __xen_dma_map_page(struct device *hwdev, struct page *page, void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { if (is_device_dma_coherent(hwdev)) return; - if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) return; __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 69c8787bec7d..bc3f00f586f1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -54,6 +54,7 @@ config ARM64 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index bb2616b16157..be5d824ebdba 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -8,7 +8,7 @@ config ARCH_SUNXI config ARCH_ALPINE bool "Annapurna Labs Alpine platform" - select ALPINE_MSI + select ALPINE_MSI if PCI help This enables support for the Annapurna Labs Alpine Soc family. @@ -66,7 +66,7 @@ config ARCH_LG1K config ARCH_HISI bool "Hisilicon SoC Family" select ARM_TIMER_SP804 - select HISILICON_IRQ_MBIGEN + select HISILICON_IRQ_MBIGEN if PCI help This enables support for Hisilicon ARMv8 SoC family diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index d59b6908a21a..5b54f8c021d8 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -15,7 +15,7 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) GZFLAGS :=-9 ifneq ($(CONFIG_RELOCATABLE),) -LDFLAGS_vmlinux += -pie +LDFLAGS_vmlinux += -pie -Bsymbolic endif KBUILD_DEFCONFIG := defconfig diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts index 299f3ce969ab..c528dd52ba2d 100644 --- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts +++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts @@ -12,6 +12,7 @@ /dts-v1/; #include "exynos7.dtsi" #include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/clock/samsung,s2mps11.h> / { model = "Samsung Exynos7 Espresso board based on EXYNOS7"; @@ -43,6 +44,8 @@ &rtc { status = "okay"; + clocks = <&clock_ccore PCLK_RTC>, <&s2mps15_osc S2MPS11_CLK_AP>; + clock-names = "rtc", "rtc_src"; }; &watchdog { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0555b7caaf2c..eadf4855ad2d 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1,4 +1,3 @@ -# CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y @@ -15,10 +14,14 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_HUGETLB=y -# CONFIG_UTS_NS is not set -# CONFIG_IPC_NS is not set -# CONFIG_NET_NS is not set +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y @@ -71,6 +74,7 @@ CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_SECCOMP=y CONFIG_XEN=y CONFIG_KEXEC=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set @@ -84,10 +88,37 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y +CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_IPV6 is not set +CONFIG_IPV6=m +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_MANGLE=m +CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m +CONFIG_BRIDGE=m +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_VLAN_8021Q_MVRP=y CONFIG_BPF_JIT=y CONFIG_CFG80211=m CONFIG_MAC80211=m @@ -103,6 +134,7 @@ CONFIG_MTD=y CONFIG_MTD_M25P80=y CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=m CONFIG_VIRTIO_BLK=y CONFIG_SRAM=y # CONFIG_SCSI_PROC_FS is not set @@ -120,7 +152,10 @@ CONFIG_SATA_SIL24=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m CONFIG_TUN=y +CONFIG_VETH=m CONFIG_VIRTIO_NET=y CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y @@ -350,12 +385,16 @@ CONFIG_EXYNOS_ADC=y CONFIG_PWM_SAMSUNG=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=y -CONFIG_CUSE=y +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_VFAT_FS=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 579b6e654f2d..a55384f4a5d7 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -140,6 +140,7 @@ typedef struct user_fpsimd_state elf_fpregset_t; #define SET_PERSONALITY(ex) clear_thread_flag(TIF_32BIT); +/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #define ARCH_DLINFO \ do { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 61b49150dfa3..1737aecfcc5e 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -22,7 +22,6 @@ #define __ARCH_WANT_KPROBES_INSN_SLOT #define MAX_INSN_SIZE 1 -#define MAX_STACK_SIZE 128 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 @@ -47,7 +46,6 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 46472a91b6df..e20bd431184a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -224,6 +224,23 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } +#define __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + pteval_t lhs, rhs; + + lhs = pte_val(pte_a); + rhs = pte_val(pte_b); + + if (pte_present(pte_a)) + lhs &= ~PTE_RDONLY; + + if (pte_present(pte_b)) + rhs &= ~PTE_RDONLY; + + return (lhs == rhs); +} + /* * Huge pte definitions. */ diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 5e834d10b291..c47257c91b77 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -265,22 +265,25 @@ extern unsigned long __must_check __clear_user(void __user *addr, unsigned long static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); - return __arch_copy_from_user(to, from, n); + check_object_size(to, n, false); + return __arch_copy_from_user(to, from, n); } static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); - return __arch_copy_to_user(to, from, n); + check_object_size(from, n, true); + return __arch_copy_to_user(to, from, n); } static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); - if (access_ok(VERIFY_READ, from, n)) + if (access_ok(VERIFY_READ, from, n)) { + check_object_size(to, n, false); n = __arch_copy_from_user(to, from, n); - else /* security hole - plug it */ + } else /* security hole - plug it */ memset(to, 0, n); return n; } @@ -289,8 +292,10 @@ static inline unsigned long __must_check copy_to_user(void __user *to, const voi { kasan_check_read(from, n); - if (access_ok(VERIFY_WRITE, to, n)) + if (access_ok(VERIFY_WRITE, to, n)) { + check_object_size(from, n, true); n = __arch_copy_to_user(to, from, n); + } return n; } diff --git a/arch/arm64/include/uapi/asm/auxvec.h b/arch/arm64/include/uapi/asm/auxvec.h index 22d6d8885854..4cf0c17787a8 100644 --- a/arch/arm64/include/uapi/asm/auxvec.h +++ b/arch/arm64/include/uapi/asm/auxvec.h @@ -19,4 +19,6 @@ /* vDSO location */ #define AT_SYSINFO_EHDR 33 +#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */ + #endif diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 96e4a2b64cc1..441420ca7d08 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -353,6 +353,8 @@ el1_sync: lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 b.eq el1_da + cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 + b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception @@ -364,6 +366,11 @@ el1_sync: cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 b.ge el1_dbg b el1_inv + +el1_ia: + /* + * Fall through to the Data abort case + */ el1_da: /* * Data abort handling diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 2c6e598a94dc..b77f58355da1 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -781,40 +781,25 @@ __primary_switch: * Iterate over each entry in the relocation table, and apply the * relocations in place. */ - ldr w8, =__dynsym_offset // offset to symbol table ldr w9, =__rela_offset // offset to reloc table ldr w10, =__rela_size // size of reloc table mov_q x11, KIMAGE_VADDR // default virtual offset add x11, x11, x23 // actual virtual offset - add x8, x8, x11 // __va(.dynsym) add x9, x9, x11 // __va(.rela) add x10, x9, x10 // __va(.rela) + sizeof(.rela) 0: cmp x9, x10 - b.hs 2f + b.hs 1f ldp x11, x12, [x9], #24 ldr x13, [x9, #-8] cmp w12, #R_AARCH64_RELATIVE - b.ne 1f + b.ne 0b add x13, x13, x23 // relocate str x13, [x11, x23] b 0b -1: cmp w12, #R_AARCH64_ABS64 - b.ne 0b - add x12, x12, x12, lsl #1 // symtab offset: 24x top word - add x12, x8, x12, lsr #(32 - 3) // ... shifted into bottom word - ldrsh w14, [x12, #6] // Elf64_Sym::st_shndx - ldr x15, [x12, #8] // Elf64_Sym::st_value - cmp w14, #-0xf // SHN_ABS (0xfff1) ? - add x14, x15, x23 // relocate - csel x15, x14, x15, ne - add x15, x13, x15 - str x15, [x11, x23] - b 0b - -2: +1: #endif ldr x8, =__primary_switched br x8 diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 21ab5df9fa76..65d81f965e74 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -35,6 +35,7 @@ #include <asm/sections.h> #include <asm/smp.h> #include <asm/suspend.h> +#include <asm/sysreg.h> #include <asm/virt.h> /* @@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length, set_pte(pte, __pte(virt_to_phys((void *)dst) | pgprot_val(PAGE_KERNEL_EXEC))); - /* Load our new page tables */ - asm volatile("msr ttbr0_el1, %0;" - "isb;" - "tlbi vmalle1is;" - "dsb ish;" - "isb" : : "r"(virt_to_phys(pgd))); + /* + * Load our new page tables. A strict BBM approach requires that we + * ensure that TLBs are free of any entries that may overlap with the + * global mappings we are about to install. + * + * For a real hibernate/resume cycle TTBR0 currently points to a zero + * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI + * runtime services), while for a userspace-driven test_resume cycle it + * points to userspace page tables (and we must point it at a zero page + * ourselves). Elsewhere we only (un)install the idmap with preemption + * disabled, so T0SZ should be as required regardless. + */ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + write_sysreg(virt_to_phys(pgd), ttbr0_el1); + isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -394,6 +405,38 @@ int swsusp_arch_resume(void) void *, phys_addr_t, phys_addr_t); /* + * Restoring the memory image will overwrite the ttbr1 page tables. + * Create a second copy of just the linear map, and use this when + * restoring. + */ + tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!tmp_pg_dir) { + pr_err("Failed to allocate memory for temporary page tables."); + rc = -ENOMEM; + goto out; + } + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + if (rc) + goto out; + + /* + * Since we only copied the linear map, we need to find restore_pblist's + * linear map address. + */ + lm_restore_pblist = LMADDR(restore_pblist); + + /* + * We need a zero page that is zero before & after resume in order to + * to break before make on the ttbr1 page tables. + */ + zero_page = (void *)get_safe_page(GFP_ATOMIC); + if (!zero_page) { + pr_err("Failed to allocate zero page."); + rc = -ENOMEM; + goto out; + } + + /* * Locate the exit code in the bottom-but-one page, so that *NULL * still has disastrous affects. */ @@ -419,27 +462,6 @@ int swsusp_arch_resume(void) __flush_dcache_area(hibernate_exit, exit_size); /* - * Restoring the memory image will overwrite the ttbr1 page tables. - * Create a second copy of just the linear map, and use this when - * restoring. - */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); - if (rc) - goto out; - - /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - - /* * KASLR will cause the el2 vectors to be in a different location in * the resumed kernel. Load hibernate's temporary copy into el2. * @@ -453,12 +475,6 @@ int swsusp_arch_resume(void) __hyp_set_vectors(el2_vectors); } - /* - * We need a zero page that is zero before & after resume in order to - * to break before make on the ttbr1 page tables. - */ - zero_page = (void *)get_safe_page(GFP_ATOMIC); - hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, resume_hdr.reenter_kernel, lm_restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index bf9768588288..c6b0f40620d8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -41,18 +41,6 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static inline unsigned long min_stack_size(unsigned long addr) -{ - unsigned long size; - - if (on_irq_stack(addr, raw_smp_processor_id())) - size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr; - else - size = (unsigned long)current_thread_info() + THREAD_START_SP - addr; - - return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack)); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { /* prepare insn slot */ @@ -489,20 +477,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_ptr = kernel_stack_pointer(regs); kcb->jprobe_saved_regs = *regs; /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. + * Since we can't be sure where in the stack frame "stacked" + * pass-by-value arguments are stored we just don't try to + * duplicate any of the stack. Do not use jprobes on functions that + * use more than 64 bytes (after padding each to an 8 byte boundary) + * of arguments, or pass individual arguments larger than 16 bytes. */ - kasan_disable_current(); - memcpy(kcb->jprobes_stack, (void *)stack_ptr, - min_stack_size(stack_ptr)); - kasan_enable_current(); instruction_pointer_set(regs, (unsigned long) jp->entry); preempt_disable(); @@ -554,10 +537,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - kasan_disable_current(); - memcpy((void *)stack_addr, kcb->jprobes_stack, - min_stack_size(stack_addr)); - kasan_enable_current(); preempt_enable_no_resched(); return 1; } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 76a6d9263908..d93d43352504 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -661,9 +661,9 @@ void __init smp_init_cpus(void) acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, acpi_parse_gic_cpu_interface, 0); - if (cpu_count > NR_CPUS) - pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu_count, NR_CPUS); + if (cpu_count > nr_cpu_ids) + pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n", + cpu_count, nr_cpu_ids); if (!bootcpu_valid) { pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); @@ -677,7 +677,7 @@ void __init smp_init_cpus(void) * with entries in cpu_logical_map while initializing the cpus. * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 1; i < NR_CPUS; i++) { + for (i = 1; i < nr_cpu_ids; i++) { if (cpu_logical_map(i) != INVALID_HWID) { if (smp_cpu_setup(i)) cpu_logical_map(i) = INVALID_HWID; diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 89d6e177ecbd..659963d40bb4 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -103,6 +103,7 @@ SECTIONS *(.discard) *(.discard.*) *(.interp .dynamic) + *(.dynsym .dynstr .hash) } . = KIMAGE_VADDR + TEXT_OFFSET; @@ -174,19 +175,9 @@ SECTIONS .rela : ALIGN(8) { *(.rela .rela*) } - .dynsym : ALIGN(8) { - *(.dynsym) - } - .dynstr : { - *(.dynstr) - } - .hash : { - *(.hash) - } - __rela_offset = ADDR(.rela) - KIMAGE_VADDR; + __rela_offset = ABSOLUTE(ADDR(.rela) - KIMAGE_VADDR); __rela_size = SIZEOF(.rela); - __dynsym_offset = ADDR(.dynsym) - KIMAGE_VADDR; . = ALIGN(SEGMENT_ALIGN); __init_end = .; diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 9d2eff0b3ad3..9c9edc98d271 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -37,6 +37,8 @@ config KVM select KVM_ARM_VGIC_V3 select KVM_ARM_PMU if HW_PERF_EVENTS select HAVE_KVM_MSI + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQ_ROUTING ---help--- Support hosting virtualized guest machines. We don't support KVM with 16K page tables yet, due to the multiple diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index a5b96642a9cb..695eb3c7ef41 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -30,5 +30,6 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/irqchip.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index e9e0e6db73f6..898c0e6aedd4 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -132,16 +132,14 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type) static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) { unsigned long cpsr = *vcpu_cpsr(vcpu); - bool is_aarch32; + bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u32 esr = 0; - is_aarch32 = vcpu_mode_is_32bit(vcpu); - - *vcpu_spsr(vcpu) = cpsr; *vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu); - *vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync); + *vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64; + *vcpu_spsr(vcpu) = cpsr; vcpu_sys_reg(vcpu, FAR_EL1) = addr; @@ -172,11 +170,11 @@ static void inject_undef64(struct kvm_vcpu *vcpu) unsigned long cpsr = *vcpu_cpsr(vcpu); u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); - *vcpu_spsr(vcpu) = cpsr; *vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu); - *vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync); + *vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64; + *vcpu_spsr(vcpu) = cpsr; /* * Build an unknown exception, depending on the instruction diff --git a/arch/arm64/kvm/irq.h b/arch/arm64/kvm/irq.h new file mode 100644 index 000000000000..b74099b905fd --- /dev/null +++ b/arch/arm64/kvm/irq.h @@ -0,0 +1,19 @@ +/* + * irq.h: in kernel interrupt controller related definitions + * Copyright (c) 2016 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This header is included by irqchip.c. However, on ARM, interrupt + * controller declarations are located in include/kvm/arm_vgic.h since + * they are mostly shared between arm and arm64. + */ + +#ifndef __IRQ_H +#define __IRQ_H + +#include <kvm/arm_vgic.h> + +#endif diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index f6c55afab3e2..c4284c432ae8 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -32,10 +32,10 @@ static int swiotlb __read_mostly; -static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, +static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot, bool coherent) { - if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) + if (!coherent || (attrs & DMA_ATTR_WRITE_COMBINE)) return pgprot_writecombine(prot); return prot; } @@ -91,7 +91,7 @@ static int __free_from_pool(void *start, size_t size) static void *__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { if (dev == NULL) { WARN_ONCE(1, "Use an actual device structure for DMA allocation\n"); @@ -121,7 +121,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, static void __dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { bool freed; phys_addr_t paddr = dma_to_phys(dev, dma_handle); @@ -140,7 +140,7 @@ static void __dma_free_coherent(struct device *dev, size_t size, static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { struct page *page; void *ptr, *coherent_ptr; @@ -188,7 +188,7 @@ no_mem: static void __dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); @@ -205,7 +205,7 @@ static void __dma_free(struct device *dev, size_t size, static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dev_addr; @@ -219,7 +219,7 @@ static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { if (!is_device_dma_coherent(dev)) __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); @@ -228,7 +228,7 @@ static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr, static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i, ret; @@ -245,7 +245,7 @@ static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, static void __swiotlb_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -306,7 +306,7 @@ static void __swiotlb_sync_sg_for_device(struct device *dev, static int __swiotlb_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { int ret = -ENXIO; unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> @@ -333,7 +333,7 @@ static int __swiotlb_mmap(struct device *dev, static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t handle, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { int ret = sg_alloc_table(sgt, 1, GFP_KERNEL); @@ -435,21 +435,21 @@ out: static void *__dummy_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { return NULL; } static void __dummy_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { } static int __dummy_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { return -ENXIO; } @@ -457,20 +457,20 @@ static int __dummy_mmap(struct device *dev, static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { return DMA_ERROR_CODE; } static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { } static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { return 0; } @@ -478,7 +478,7 @@ static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, static void __dummy_unmap_sg(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { } @@ -553,7 +553,7 @@ static void flush_page(struct device *dev, const void *virt, phys_addr_t phys) static void *__iommu_alloc_attrs(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { bool coherent = is_device_dma_coherent(dev); int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent); @@ -613,7 +613,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, } static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, struct dma_attrs *attrs) + dma_addr_t handle, unsigned long attrs) { size_t iosize = size; @@ -629,7 +629,7 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * Hence how dodgy the below logic looks... */ if (__in_atomic_pool(cpu_addr, size)) { - iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, 0); __free_from_pool(cpu_addr, size); } else if (is_vmalloc_addr(cpu_addr)){ struct vm_struct *area = find_vm_area(cpu_addr); @@ -639,14 +639,14 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, iommu_dma_free(dev, area->pages, iosize, &handle); dma_common_free_remap(cpu_addr, size, VM_USERMAP); } else { - iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, 0); __free_pages(virt_to_page(cpu_addr), get_order(size)); } } static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { struct vm_struct *area; int ret; @@ -666,7 +666,7 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, - size_t size, struct dma_attrs *attrs) + size_t size, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct vm_struct *area = find_vm_area(cpu_addr); @@ -707,14 +707,14 @@ static void __iommu_sync_single_for_device(struct device *dev, static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { bool coherent = is_device_dma_coherent(dev); int prot = dma_direction_to_prot(dir, coherent); dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); if (!iommu_dma_mapping_error(dev, dev_addr) && - !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __iommu_sync_single_for_device(dev, dev_addr, size, dir); return dev_addr; @@ -722,9 +722,9 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __iommu_sync_single_for_cpu(dev, dev_addr, size, dir); iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs); @@ -760,11 +760,11 @@ static void __iommu_sync_sg_for_device(struct device *dev, static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { bool coherent = is_device_dma_coherent(dev); - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __iommu_sync_sg_for_device(dev, sgl, nelems, dir); return iommu_dma_map_sg(dev, sgl, nelems, @@ -774,9 +774,9 @@ static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl, static void __iommu_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { - if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir); iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c8beaa0da7df..05d2bd776c69 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -153,6 +153,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma, } #endif +static bool is_el1_instruction_abort(unsigned int esr) +{ + return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; +} + /* * The kernel tried to access some page that wasn't present. */ @@ -161,8 +166,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, { /* * Are we prepared to handle this kernel fault? + * We are almost certainly not prepared to handle instruction faults. */ - if (fixup_exception(regs)) + if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; /* @@ -267,7 +273,8 @@ static inline bool is_permission_fault(unsigned int esr) unsigned int ec = ESR_ELx_EC(esr); unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; - return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); + return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) || + (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM); } static bool is_el0_instruction_abort(unsigned int esr) @@ -312,6 +319,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); + if (is_el1_instruction_abort(esr)) + die("Attempting to execute userspace memory", regs, esr); + if (!search_exception_tables(regs->pc)) die("Accessing user space memory outside uaccess.h routines", regs, esr); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 51a558195bb9..4989948d1feb 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -686,9 +686,9 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be - * at least 8 bytes so that we can always access the size field of the - * FDT header after mapping the first chunk, double check here if that - * is indeed the case. + * at least 8 bytes so that we can always access the magic and size + * fields of the FDT header after mapping the first chunk, double check + * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) @@ -716,7 +716,7 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, SWAPPER_BLOCK_SIZE, prot); - if (fdt_check_header(dt_virt) != 0) + if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; *size = fdt_totalsize(dt_virt); diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c index 92cf1fb2b3e6..58610d0df7ed 100644 --- a/arch/avr32/mm/dma-coherent.c +++ b/arch/avr32/mm/dma-coherent.c @@ -99,7 +99,7 @@ static void __dma_free(struct device *dev, size_t size, } static void *avr32_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { struct page *page; dma_addr_t phys; @@ -109,7 +109,7 @@ static void *avr32_dma_alloc(struct device *dev, size_t size, return NULL; phys = page_to_phys(page); - if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) { + if (attrs & DMA_ATTR_WRITE_COMBINE) { /* Now, map the page into P3 with write-combining turned on */ *handle = phys; return __ioremap(phys, size, _PAGE_BUFFER); @@ -119,11 +119,11 @@ static void *avr32_dma_alloc(struct device *dev, size_t size, } static void avr32_dma_free(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) + void *cpu_addr, dma_addr_t handle, unsigned long attrs) { struct page *page; - if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) { + if (attrs & DMA_ATTR_WRITE_COMBINE) { iounmap(cpu_addr); page = phys_to_page(handle); @@ -142,7 +142,7 @@ static void avr32_dma_free(struct device *dev, size_t size, static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { void *cpu_addr = page_address(page) + offset; @@ -152,7 +152,7 @@ static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page, static int avr32_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; struct scatterlist *sg; diff --git a/arch/blackfin/kernel/dma-mapping.c b/arch/blackfin/kernel/dma-mapping.c index 771afe6e4264..53fbbb61aa86 100644 --- a/arch/blackfin/kernel/dma-mapping.c +++ b/arch/blackfin/kernel/dma-mapping.c @@ -79,7 +79,7 @@ static void __free_dma_pages(unsigned long addr, unsigned int pages) } static void *bfin_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; @@ -94,7 +94,7 @@ static void *bfin_dma_alloc(struct device *dev, size_t size, } static void bfin_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { __free_dma_pages((unsigned long)vaddr, get_pages(size)); } @@ -111,7 +111,7 @@ EXPORT_SYMBOL(__dma_sync); static int bfin_dma_map_sg(struct device *dev, struct scatterlist *sg_list, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -139,7 +139,7 @@ static void bfin_dma_sync_sg_for_device(struct device *dev, static dma_addr_t bfin_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t handle = (dma_addr_t)(page_address(page) + offset); diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h index 6b5cd7b0cf32..5717b1e52d96 100644 --- a/arch/c6x/include/asm/dma-mapping.h +++ b/arch/c6x/include/asm/dma-mapping.h @@ -26,8 +26,8 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) extern void coherent_mem_init(u32 start, u32 size); void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, struct dma_attrs *attrs); + gfp_t gfp, unsigned long attrs); void c6x_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs); + dma_addr_t dma_handle, unsigned long attrs); #endif /* _ASM_C6X_DMA_MAPPING_H */ diff --git a/arch/c6x/kernel/dma.c b/arch/c6x/kernel/dma.c index 8a80f3a250c0..db4a6a301f5e 100644 --- a/arch/c6x/kernel/dma.c +++ b/arch/c6x/kernel/dma.c @@ -38,7 +38,7 @@ static void c6x_dma_sync(dma_addr_t handle, size_t size, static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t handle = virt_to_phys(page_address(page) + offset); @@ -47,13 +47,13 @@ static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page, } static void c6x_dma_unmap_page(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) + size_t size, enum dma_data_direction dir, unsigned long attrs) { c6x_dma_sync(handle, size, dir); } static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *sg; int i; @@ -67,8 +67,7 @@ static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist, } static void c6x_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *sg; int i; diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c index f7ee63af2541..95e38ad27c69 100644 --- a/arch/c6x/mm/dma-coherent.c +++ b/arch/c6x/mm/dma-coherent.c @@ -74,7 +74,7 @@ static void __free_dma_pages(u32 addr, int order) * virtual and DMA address for that space. */ void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, struct dma_attrs *attrs) + gfp_t gfp, unsigned long attrs) { u32 paddr; int order; @@ -99,7 +99,7 @@ void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, * Free DMA coherent memory as defined by the above mapping. */ void c6x_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { int order; diff --git a/arch/cris/arch-v32/drivers/pci/dma.c b/arch/cris/arch-v32/drivers/pci/dma.c index 8d5efa58cce1..1f0636793f0c 100644 --- a/arch/cris/arch-v32/drivers/pci/dma.c +++ b/arch/cris/arch-v32/drivers/pci/dma.c @@ -17,7 +17,7 @@ #include <asm/io.h> static void *v32_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; @@ -37,22 +37,21 @@ static void *v32_dma_alloc(struct device *dev, size_t size, } static void v32_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); } static inline dma_addr_t v32_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, - struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { return page_to_phys(page) + offset; } static inline int v32_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { printk("Map sg\n"); return nents; diff --git a/arch/frv/include/asm/mc146818rtc.h b/arch/frv/include/asm/mc146818rtc.h deleted file mode 100644 index 90dfb7a633d1..000000000000 --- a/arch/frv/include/asm/mc146818rtc.h +++ /dev/null @@ -1,16 +0,0 @@ -/* mc146818rtc.h: RTC defs - * - * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.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. - */ - -#ifndef _ASM_MC146818RTC_H -#define _ASM_MC146818RTC_H - - -#endif /* _ASM_MC146818RTC_H */ diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c index 082be49b5df0..90f2e4cb33d6 100644 --- a/arch/frv/mb93090-mb00/pci-dma-nommu.c +++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c @@ -35,7 +35,7 @@ static DEFINE_SPINLOCK(dma_alloc_lock); static LIST_HEAD(dma_alloc_list); static void *frv_dma_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, struct dma_attrs *attrs) + gfp_t gfp, unsigned long attrs) { struct dma_alloc_record *new; struct list_head *this = &dma_alloc_list; @@ -86,7 +86,7 @@ static void *frv_dma_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_ha } static void frv_dma_free(struct device *hwdev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { struct dma_alloc_record *rec; unsigned long flags; @@ -107,7 +107,7 @@ static void frv_dma_free(struct device *hwdev, size_t size, void *vaddr, static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; struct scatterlist *sg; @@ -124,7 +124,7 @@ static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist, static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { BUG_ON(direction == DMA_NONE); flush_dcache_page(page); diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c index 316b7b65348d..f585745b1abc 100644 --- a/arch/frv/mb93090-mb00/pci-dma.c +++ b/arch/frv/mb93090-mb00/pci-dma.c @@ -19,8 +19,7 @@ #include <asm/io.h> static void *frv_dma_alloc(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; @@ -32,14 +31,14 @@ static void *frv_dma_alloc(struct device *hwdev, size_t size, } static void frv_dma_free(struct device *hwdev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { consistent_free(vaddr); } static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long dampr2; void *vaddr; @@ -69,7 +68,7 @@ static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist, static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { flush_dcache_page(page); return (dma_addr_t) page_to_phys(page) + offset; diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index 2e221c5f0203..f86918aed9e1 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include <linux/types.h> + /* H8/300 internal I/O functions */ #define __raw_readb __raw_readb diff --git a/arch/h8300/include/asm/mc146818rtc.h b/arch/h8300/include/asm/mc146818rtc.h deleted file mode 100644 index ab9d9646d241..000000000000 --- a/arch/h8300/include/asm/mc146818rtc.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Machine dependent access functions for RTC registers. - */ -#ifndef _H8300_MC146818RTC_H -#define _H8300_MC146818RTC_H - -/* empty include file to satisfy the include in genrtc.c/ide-geometry.c */ - -#endif /* _H8300_MC146818RTC_H */ diff --git a/arch/h8300/kernel/dma.c b/arch/h8300/kernel/dma.c index eeb13d3f2424..3651da045806 100644 --- a/arch/h8300/kernel/dma.c +++ b/arch/h8300/kernel/dma.c @@ -12,7 +12,7 @@ static void *dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret; @@ -32,7 +32,7 @@ static void *dma_alloc(struct device *dev, size_t size, static void dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); @@ -41,14 +41,14 @@ static void dma_free(struct device *dev, size_t size, static dma_addr_t map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return page_to_phys(page) + offset; } static int map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h index aa6203464520..7ef58df909fc 100644 --- a/arch/hexagon/include/asm/dma-mapping.h +++ b/arch/hexagon/include/asm/dma-mapping.h @@ -26,7 +26,6 @@ #include <linux/mm.h> #include <linux/scatterlist.h> #include <linux/dma-debug.h> -#include <linux/dma-attrs.h> #include <asm/io.h> struct device; diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 9e3ddf792bd3..b9017785fb71 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -51,7 +51,7 @@ static struct gen_pool *coherent_pool; static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret; @@ -84,7 +84,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, } static void hexagon_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, struct dma_attrs *attrs) + dma_addr_t dma_addr, unsigned long attrs) { gen_pool_free(coherent_pool, (unsigned long) vaddr, size); } @@ -105,7 +105,7 @@ static int check_addr(const char *name, struct device *hwdev, static int hexagon_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; @@ -172,7 +172,7 @@ static inline void dma_sync(void *addr, size_t size, static dma_addr_t hexagon_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t bus = page_to_phys(page) + offset; WARN_ON(size == 0); diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 6a15083cc366..18ca6a9ce566 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -52,6 +52,7 @@ config IA64 select MODULES_USE_ELF_RELA select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HARDENED_USERCOPY default y help The Itanium Processor Family is Intel's 64-bit successor to diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index a6d6190c9d24..630ee8073899 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -919,7 +919,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt) static dma_addr_t sba_map_page(struct device *dev, struct page *page, unsigned long poff, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct ioc *ioc; void *addr = page_address(page) + poff; @@ -1005,7 +1005,7 @@ static dma_addr_t sba_map_page(struct device *dev, struct page *page, static dma_addr_t sba_map_single_attrs(struct device *dev, void *addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { return sba_map_page(dev, virt_to_page(addr), (unsigned long)addr & ~PAGE_MASK, size, dir, attrs); @@ -1046,7 +1046,7 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size) * See Documentation/DMA-API-HOWTO.txt */ static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct ioc *ioc; #if DELAYED_RESOURCE_CNT > 0 @@ -1115,7 +1115,7 @@ static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size, } void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { sba_unmap_page(dev, iova, size, dir, attrs); } @@ -1130,7 +1130,7 @@ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, */ static void * sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, struct dma_attrs *attrs) + gfp_t flags, unsigned long attrs) { struct ioc *ioc; void *addr; @@ -1175,7 +1175,7 @@ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, * device to map single to get an iova mapping. */ *dma_handle = sba_map_single_attrs(&ioc->sac_only_dev->dev, addr, - size, 0, NULL); + size, 0, 0); return addr; } @@ -1191,9 +1191,9 @@ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, * See Documentation/DMA-API-HOWTO.txt */ static void sba_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { - sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL); + sba_unmap_single_attrs(dev, dma_handle, size, 0, 0); free_pages((unsigned long) vaddr, get_order(size)); } @@ -1442,7 +1442,7 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev, static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); /** * sba_map_sg - map Scatter/Gather list * @dev: instance of PCI owned by the driver that's asking. @@ -1455,7 +1455,7 @@ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, */ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct ioc *ioc; int coalesced, filled = 0; @@ -1551,7 +1551,7 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, */ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef ASSERT_PDIR_SANITY struct ioc *ioc; diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h index 9c39bdfc2da8..ed7f09089f12 100644 --- a/arch/ia64/include/asm/machvec.h +++ b/arch/ia64/include/asm/machvec.h @@ -22,7 +22,6 @@ struct pci_bus; struct task_struct; struct pci_dev; struct msi_desc; -struct dma_attrs; typedef void ia64_mv_setup_t (char **); typedef void ia64_mv_cpu_init_t (void); diff --git a/arch/ia64/include/asm/mc146818rtc.h b/arch/ia64/include/asm/mc146818rtc.h deleted file mode 100644 index 407787a237ba..000000000000 --- a/arch/ia64/include/asm/mc146818rtc.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _ASM_IA64_MC146818RTC_H -#define _ASM_IA64_MC146818RTC_H - -/* - * Machine dependent access functions for RTC registers. - */ - -/* empty include file to satisfy the include in genrtc.c */ - -#endif /* _ASM_IA64_MC146818RTC_H */ diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 2189d5ddc1ee..465c70982f40 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -241,12 +241,18 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use static inline unsigned long __copy_to_user (void __user *to, const void *from, unsigned long count) { + if (!__builtin_constant_p(count)) + check_object_size(from, count, true); + return __copy_user(to, (__force void __user *) from, count); } static inline unsigned long __copy_from_user (void *to, const void __user *from, unsigned long count) { + if (!__builtin_constant_p(count)) + check_object_size(to, count, false); + return __copy_user((__force void __user *) to, from, count); } @@ -258,8 +264,11 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) const void *__cu_from = (from); \ long __cu_len = (n); \ \ - if (__access_ok(__cu_to, __cu_len, get_fs())) \ - __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ + if (__access_ok(__cu_to, __cu_len, get_fs())) { \ + if (!__builtin_constant_p(n)) \ + check_object_size(__cu_from, __cu_len, true); \ + __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ + } \ __cu_len; \ }) @@ -270,8 +279,11 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) long __cu_len = (n); \ \ __chk_user_ptr(__cu_from); \ - if (__access_ok(__cu_from, __cu_len, get_fs())) \ + if (__access_ok(__cu_from, __cu_len, get_fs())) { \ + if (!__builtin_constant_p(n)) \ + check_object_size(__cu_to, __cu_len, false); \ __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \ + } \ __cu_len; \ }) diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c index 939260aeac98..2933208c0285 100644 --- a/arch/ia64/kernel/pci-swiotlb.c +++ b/arch/ia64/kernel/pci-swiotlb.c @@ -16,7 +16,7 @@ EXPORT_SYMBOL(swiotlb); static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { if (dev->coherent_dma_mask != DMA_BIT_MASK(64)) gfp |= GFP_DMA; @@ -25,7 +25,7 @@ static void *ia64_swiotlb_alloc_coherent(struct device *dev, size_t size, static void ia64_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, - struct dma_attrs *attrs) + unsigned long attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_addr); } diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index 8f59907007cb..74c934a997bb 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -77,7 +77,7 @@ EXPORT_SYMBOL(sn_dma_set_mask); */ static void *sn_dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t * dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { void *cpuaddr; unsigned long phys_addr; @@ -138,7 +138,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size, * any associated IOMMU mappings. */ static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); @@ -176,21 +176,18 @@ static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr static dma_addr_t sn_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { void *cpu_addr = page_address(page) + offset; dma_addr_t dma_addr; unsigned long phys_addr; struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); - int dmabarr; - - dmabarr = dma_get_attr(DMA_ATTR_WRITE_BARRIER, attrs); BUG_ON(!dev_is_pci(dev)); phys_addr = __pa(cpu_addr); - if (dmabarr) + if (attrs & DMA_ATTR_WRITE_BARRIER) dma_addr = provider->dma_map_consistent(pdev, phys_addr, size, SN_DMA_ADDR_PHYS); else @@ -218,7 +215,7 @@ static dma_addr_t sn_dma_map_page(struct device *dev, struct page *page, */ static void sn_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); @@ -240,7 +237,7 @@ static void sn_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, */ static void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl, int nhwentries, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { int i; struct pci_dev *pdev = to_pci_dev(dev); @@ -273,16 +270,13 @@ static void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl, */ static int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long phys_addr; struct scatterlist *saved_sg = sgl, *sg; struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); int i; - int dmabarr; - - dmabarr = dma_get_attr(DMA_ATTR_WRITE_BARRIER, attrs); BUG_ON(!dev_is_pci(dev)); @@ -292,7 +286,7 @@ static int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, for_each_sg(sgl, sg, nhwentries, i) { dma_addr_t dma_addr; phys_addr = SG_ENT_PHYS_ADDRESS(sg); - if (dmabarr) + if (attrs & DMA_ATTR_WRITE_BARRIER) dma_addr = provider->dma_map_consistent(pdev, phys_addr, sg->length, diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index 01693df7f2f6..ec9cc1fdd237 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -35,7 +35,6 @@ #include <asm/amigahw.h> #include <asm/amigaints.h> #include <asm/irq.h> -#include <asm/rtc.h> #include <asm/machdep.h> #include <asm/io.h> diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c index 6e62d66c396e..432bc8bacfc2 100644 --- a/arch/m68k/apollo/config.c +++ b/arch/m68k/apollo/config.c @@ -15,7 +15,6 @@ #include <asm/pgtable.h> #include <asm/apollohw.h> #include <asm/irq.h> -#include <asm/rtc.h> #include <asm/machdep.h> u_long sio01_physaddr; diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c index 478623dbb209..611d4d9ea2bd 100644 --- a/arch/m68k/bvme6000/config.c +++ b/arch/m68k/bvme6000/config.c @@ -34,7 +34,6 @@ #include <asm/setup.h> #include <asm/irq.h> #include <asm/traps.h> -#include <asm/rtc.h> #include <asm/machdep.h> #include <asm/bvme6000hw.h> diff --git a/arch/m68k/hp300/config.c b/arch/m68k/hp300/config.c index a9befe65adc4..7cfab158fb61 100644 --- a/arch/m68k/hp300/config.c +++ b/arch/m68k/hp300/config.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/console.h> +#include <linux/rtc.h> #include <asm/bootinfo.h> #include <asm/bootinfo-hp300.h> @@ -20,7 +21,6 @@ #include <asm/blinken.h> #include <asm/io.h> /* readb() and writeb() */ #include <asm/hp300hw.h> -#include <asm/rtc.h> #include "time.h" diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h index f9454b89a51b..00c392b0cabd 100644 --- a/arch/m68k/include/asm/flat.h +++ b/arch/m68k/include/asm/flat.h @@ -1,5 +1,5 @@ /* - * include/asm-m68knommu/flat.h -- uClinux flat-format executables + * flat.h -- uClinux flat-format executables */ #ifndef __M68KNOMMU_FLAT_H__ @@ -8,8 +8,9 @@ #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val,rp) +#define flat_get_addr_from_rp(rp, relval, flags, p) \ + ({ unsigned long __val; __get_user_unaligned(__val, rp); __val; }) +#define flat_put_addr_at_rp(rp, val, relval) __put_user_unaligned(val, rp) #define flat_get_relocate_addr(rel) (rel) static inline int flat_set_persistent(unsigned long relval, @@ -18,4 +19,10 @@ static inline int flat_set_persistent(unsigned long relval, return 0; } +#define FLAT_PLAT_INIT(regs) \ + do { \ + if (current->mm) \ + (regs)->d5 = current->mm->start_data; \ + } while (0) + #endif /* __M68KNOMMU_FLAT_H__ */ diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index a6ce2ec8d693..c84a2183b3f0 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -110,7 +110,6 @@ struct thread_struct { #define setframeformat(_regs) do { } while (0) #endif -#ifdef CONFIG_MMU /* * Do necessary setup to start up a newly executed thread. */ @@ -123,26 +122,14 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc, wrusp(usp); } +#ifdef CONFIG_MMU extern int handle_kernel_fault(struct pt_regs *regs); - #else - -#define start_thread(_regs, _pc, _usp) \ -do { \ - (_regs)->pc = (_pc); \ - setframeformat(_regs); \ - if (current->mm) \ - (_regs)->d5 = current->mm->start_data; \ - (_regs)->sr &= ~0x2000; \ - wrusp(_usp); \ -} while(0) - static inline int handle_kernel_fault(struct pt_regs *regs) { /* Any fault in kernel is fatal on non-mmu */ return 0; } - #endif /* Forward declaration, a strange C thing */ diff --git a/arch/m68k/include/asm/rtc.h b/arch/m68k/include/asm/rtc.h deleted file mode 100644 index a4d08ea122ee..000000000000 --- a/arch/m68k/include/asm/rtc.h +++ /dev/null @@ -1,79 +0,0 @@ -/* include/asm-m68k/rtc.h - * - * Copyright Richard Zidlicky - * implementation details for genrtc/q40rtc driver - */ -/* permission is hereby granted to copy, modify and redistribute this code - * in terms of the GNU Library General Public License, Version 2 or later, - * at your option. - */ - -#ifndef _ASM_RTC_H -#define _ASM_RTC_H - -#ifdef __KERNEL__ - -#include <linux/rtc.h> -#include <asm/errno.h> -#include <asm/machdep.h> - -#define RTC_PIE 0x40 /* periodic interrupt enable */ -#define RTC_AIE 0x20 /* alarm interrupt enable */ -#define RTC_UIE 0x10 /* update-finished interrupt enable */ - -/* some dummy definitions */ -#define RTC_BATT_BAD 0x100 /* battery bad */ -#define RTC_SQWE 0x08 /* enable square-wave output */ -#define RTC_DM_BINARY 0x04 /* all time/date values are BCD if clear */ -#define RTC_24H 0x02 /* 24 hour mode - else hours bit 7 means pm */ -#define RTC_DST_EN 0x01 /* auto switch DST - works f. USA only */ - -static inline unsigned int get_rtc_time(struct rtc_time *time) -{ - /* - * Only the values that we read from the RTC are set. We leave - * tm_wday, tm_yday and tm_isdst untouched. Even though the - * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated - * by the RTC when initially set to a non-zero value. - */ - if (mach_hwclk) - mach_hwclk(0, time); - return RTC_24H; -} - -static inline int set_rtc_time(struct rtc_time *time) -{ - if (mach_hwclk) - return mach_hwclk(1, time); - return -EINVAL; -} - -static inline unsigned int get_rtc_ss(void) -{ - if (mach_get_ss) - return mach_get_ss(); - else{ - struct rtc_time h; - - get_rtc_time(&h); - return h.tm_sec; - } -} - -static inline int get_rtc_pll(struct rtc_pll_info *pll) -{ - if (mach_get_rtc_pll) - return mach_get_rtc_pll(pll); - else - return -EINVAL; -} -static inline int set_rtc_pll(struct rtc_pll_info *pll) -{ - if (mach_set_rtc_pll) - return mach_set_rtc_pll(pll); - else - return -EINVAL; -} -#endif /* __KERNEL__ */ - -#endif /* _ASM__RTC_H */ diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index cbc78b4117b5..8cf97cbadc91 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -19,7 +19,7 @@ #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE) static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t flag, struct dma_attrs *attrs) + gfp_t flag, unsigned long attrs) { struct page *page, **map; pgprot_t pgprot; @@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, } static void m68k_dma_free(struct device *dev, size_t size, void *addr, - dma_addr_t handle, struct dma_attrs *attrs) + dma_addr_t handle, unsigned long attrs) { pr_debug("dma_free_coherent: %p, %x\n", addr, handle); vfree(addr); @@ -73,7 +73,7 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr, #include <asm/cacheflush.h> static void *m68k_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; /* ignore region specifiers */ @@ -91,7 +91,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, } static void m68k_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); } @@ -130,7 +130,7 @@ static void m68k_dma_sync_sg_for_device(struct device *dev, static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t handle = page_to_phys(page) + offset; @@ -139,7 +139,7 @@ static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page, } static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, unsigned long attrs) { int i; struct scatterlist *sg; diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 2dcee3a88867..9202f82dfce6 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -213,7 +213,6 @@ static inline int frame_extra_sizes(int f) static inline void adjustformat(struct pt_regs *regs) { - ((struct switch_stack *)regs - 1)->a5 = current->mm->start_data; /* * set format byte to make stack appear modulo 4, which it will * be when doing the rte diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c index 3857737e3958..4e5aa2f4f522 100644 --- a/arch/m68k/kernel/time.c +++ b/arch/m68k/kernel/time.c @@ -86,7 +86,49 @@ void read_persistent_clock(struct timespec *ts) } } -#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET +#if defined(CONFIG_ARCH_USES_GETTIMEOFFSET) && IS_ENABLED(CONFIG_RTC_DRV_GENERIC) +static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) +{ + mach_hwclk(0, tm); + return rtc_valid_tm(tm); +} + +static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) +{ + if (mach_hwclk(1, tm) < 0) + return -EOPNOTSUPP; + return 0; +} + +static int rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +{ + struct rtc_pll_info pll; + struct rtc_pll_info __user *argp = (void __user *)arg; + + switch (cmd) { + case RTC_PLL_GET: + if (!mach_get_rtc_pll || mach_get_rtc_pll(&pll)) + return -EINVAL; + return copy_to_user(argp, &pll, sizeof pll) ? -EFAULT : 0; + + case RTC_PLL_SET: + if (!mach_set_rtc_pll) + return -EINVAL; + if (!capable(CAP_SYS_TIME)) + return -EACCES; + if (copy_from_user(&pll, argp, sizeof(pll))) + return -EFAULT; + return mach_set_rtc_pll(&pll); + } + + return -ENOIOCTLCMD; +} + +static const struct rtc_class_ops generic_rtc_ops = { + .ioctl = rtc_ioctl, + .read_time = rtc_generic_get_time, + .set_time = rtc_generic_set_time, +}; static int __init rtc_init(void) { @@ -95,7 +137,9 @@ static int __init rtc_init(void) if (!mach_hwclk) return -ENODEV; - pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); + pdev = platform_device_register_data(NULL, "rtc-generic", -1, + &generic_rtc_ops, + sizeof(generic_rtc_ops)); return PTR_ERR_OR_ZERO(pdev); } diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 689b47d292ac..2f33a33001e5 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -10,6 +10,7 @@ * Miscellaneous linux stuff */ +#include <linux/errno.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> @@ -25,6 +26,7 @@ #include <linux/platform_device.h> #include <linux/adb.h> #include <linux/cuda.h> +#include <linux/rtc.h> #include <asm/setup.h> #include <asm/bootinfo.h> @@ -34,7 +36,6 @@ #include <asm/io.h> #include <asm/irq.h> #include <asm/pgtable.h> -#include <asm/rtc.h> #include <asm/machdep.h> #include <asm/macintosh.h> diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 707b61aea203..0fb54a90eac2 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -18,7 +18,6 @@ #include <asm/uaccess.h> #include <asm/io.h> -#include <asm/rtc.h> #include <asm/segment.h> #include <asm/setup.h> #include <asm/macintosh.h> diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c index e6a3b56c6481..c11d38dfad08 100644 --- a/arch/m68k/mvme147/config.c +++ b/arch/m68k/mvme147/config.c @@ -32,7 +32,6 @@ #include <asm/setup.h> #include <asm/irq.h> #include <asm/traps.h> -#include <asm/rtc.h> #include <asm/machdep.h> #include <asm/mvme147hw.h> diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c index a53803cc66cd..58e240939d26 100644 --- a/arch/m68k/mvme16x/config.c +++ b/arch/m68k/mvme16x/config.c @@ -35,7 +35,6 @@ #include <asm/setup.h> #include <asm/irq.h> #include <asm/traps.h> -#include <asm/rtc.h> #include <asm/machdep.h> #include <asm/mvme16xhw.h> diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index e90fe903613e..fcb7f05b60b6 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -12,6 +12,7 @@ * for more details. */ +#include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -27,7 +28,6 @@ #include <linux/platform_device.h> #include <asm/io.h> -#include <asm/rtc.h> #include <asm/bootinfo.h> #include <asm/pgtable.h> #include <asm/setup.h> diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 71884bf01d72..3af34fa3a344 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -26,7 +26,6 @@ #include <asm/pgalloc.h> #include <asm/sun3-head.h> #include <asm/sun3mmu.h> -#include <asm/rtc.h> #include <asm/machdep.h> #include <asm/machines.h> #include <asm/idprom.h> diff --git a/arch/m68k/sun3/intersil.c b/arch/m68k/sun3/intersil.c index 889829e11f1d..2cd0bcbe6f30 100644 --- a/arch/m68k/sun3/intersil.c +++ b/arch/m68k/sun3/intersil.c @@ -14,8 +14,8 @@ #include <linux/rtc.h> #include <asm/errno.h> -#include <asm/rtc.h> #include <asm/intersil.h> +#include <asm/machdep.h> /* bits to set for start/run of the intersil */ diff --git a/arch/m68k/sun3x/time.c b/arch/m68k/sun3x/time.c index c8eb08add6b0..431d3c4306dd 100644 --- a/arch/m68k/sun3x/time.c +++ b/arch/m68k/sun3x/time.c @@ -15,10 +15,10 @@ #include <asm/irq.h> #include <asm/io.h> +#include <asm/machdep.h> #include <asm/traps.h> #include <asm/sun3x.h> #include <asm/sun3ints.h> -#include <asm/rtc.h> #include "time.h" diff --git a/arch/metag/include/asm/cmpxchg_lnkget.h b/arch/metag/include/asm/cmpxchg_lnkget.h index 0154e2807ebb..2369ad394876 100644 --- a/arch/metag/include/asm/cmpxchg_lnkget.h +++ b/arch/metag/include/asm/cmpxchg_lnkget.h @@ -73,7 +73,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old, " DCACHE [%2], %0\n" #endif "2:\n" - : "=&d" (temp), "=&da" (retval) + : "=&d" (temp), "=&d" (retval) : "da" (m), "bd" (old), "da" (new) : "cc" ); diff --git a/arch/metag/include/asm/metag_mem.h b/arch/metag/include/asm/metag_mem.h index aa5a076df439..7848bc6d3b61 100644 --- a/arch/metag/include/asm/metag_mem.h +++ b/arch/metag/include/asm/metag_mem.h @@ -881,7 +881,7 @@ #define PERFCTRL_DCSTALL 11 /* Dcache+TLB o/p delayed (per-thread) */ #define PERFCTRL_ICSTALL 12 /* Icache+TLB o/p delayed (per-thread) */ -#define PERFCTRL_INT 13 /* Internal core delailed events (see next) */ +#define PERFCTRL_INT 13 /* Internal core detailed events (see next) */ #define PERFCTRL_EXT 15 /* External source in core periphery */ #endif /* METAC_2_1 */ diff --git a/arch/metag/include/asm/metag_regs.h b/arch/metag/include/asm/metag_regs.h index 40c3f679c5b8..60b750971d8a 100644 --- a/arch/metag/include/asm/metag_regs.h +++ b/arch/metag/include/asm/metag_regs.h @@ -179,7 +179,7 @@ ; is best to dump these registers immediately at the start of a routine ; using a MSETL or SETL instruction- ; -; MSETL [A0StP],D0Ar6,D0Ar4,D0Ar2; Only dump argments expected +; MSETL [A0StP],D0Ar6,D0Ar4,D0Ar2; Only dump arguments expected ;or SETL [A0StP+#8++],D0Ar2 ; Up to two 32-bit args expected ; ; For non-leaf routines it is always necessary to save and restore at least diff --git a/arch/metag/kernel/cachepart.c b/arch/metag/kernel/cachepart.c index 04b7d4f8429a..db944c2e7d88 100644 --- a/arch/metag/kernel/cachepart.c +++ b/arch/metag/kernel/cachepart.c @@ -15,7 +15,7 @@ #define SYSC_DCPART(n) (SYSC_DCPART0 + SYSC_xCPARTn_STRIDE * (n)) #define SYSC_ICPART(n) (SYSC_ICPART0 + SYSC_xCPARTn_STRIDE * (n)) -#define CACHE_ASSOCIATIVITY 4 /* 4 way set-assosiative */ +#define CACHE_ASSOCIATIVITY 4 /* 4 way set-associative */ #define ICACHE 0 #define DCACHE 1 diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c index e12368d02155..0db31e24c541 100644 --- a/arch/metag/kernel/dma.c +++ b/arch/metag/kernel/dma.c @@ -172,7 +172,7 @@ out: * virtual and bus address for that space. */ static void *metag_dma_alloc(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *handle, gfp_t gfp, unsigned long attrs) { struct page *page; struct metag_vm_region *c; @@ -268,7 +268,7 @@ no_page: * free a page as defined by the above mapping. */ static void metag_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { struct metag_vm_region *c; unsigned long flags, addr; @@ -331,13 +331,13 @@ no_area: static int metag_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long flags, user_size, kern_size; struct metag_vm_region *c; int ret = -ENXIO; - if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) + if (attrs & DMA_ATTR_WRITE_COMBINE) vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); else vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); @@ -482,7 +482,7 @@ static void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction) static dma_addr_t metag_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { dma_sync_for_device((void *)(page_to_phys(page) + offset), size, direction); @@ -491,14 +491,14 @@ static dma_addr_t metag_dma_map_page(struct device *dev, struct page *page, static void metag_dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); } static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -516,7 +516,7 @@ static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist, static void metag_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nhwentries, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; diff --git a/arch/metag/lib/divsi3.S b/arch/metag/lib/divsi3.S index 7c8a8ae9a0a1..11124cc93dee 100644 --- a/arch/metag/lib/divsi3.S +++ b/arch/metag/lib/divsi3.S @@ -50,7 +50,7 @@ $LIDMCQuick: ADDCC D0Re0,D0Re0,#1 ! If yes result += 1 SUBCC D1Ar1,D1Ar1,D1Re0 ! and A -= Bu ORS D0Ar4,D0Ar4,D0Ar4 ! Return neg result? - NEG D0Ar2,D0Re0 ! Calulate neg result + NEG D0Ar2,D0Re0 ! Calculate neg result MOVMI D0Re0,D0Ar2 ! Yes: Take neg result $LIDMCRet: MOV PC,D1RtP @@ -94,7 +94,7 @@ $LIDMCLoop: LSR D1Re0, D1Re0, #1 ! Shift down B BNZ $LIDMCLoop ! Was single bit in curbit lost? ORS D0Ar4,D0Ar4,D0Ar4 ! Return neg result? - NEG D0Ar2,D0Re0 ! Calulate neg result + NEG D0Ar2,D0Re0 ! Calculate neg result MOVMI D0Re0,D0Ar2 ! Yes: Take neg result MOV PC,D1RtP .size ___divsi3,.-___divsi3 diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 372783a67dda..c765b3621b9b 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -187,7 +187,7 @@ bad_area_nosemaphore: if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && printk_ratelimit()) { - pr_info("%s%s[%d]: segfault at %lx pc %08x sp %08x write %d trap %#x (%s)", + printk("%s%s[%d]: segfault at %lx pc %08x sp %08x write %d trap %#x (%s)", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, regs->ctx.CurrPC, regs->ctx.AX[0].U0, diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c index 11fa51c89617..c0ec116b3993 100644 --- a/arch/metag/mm/init.c +++ b/arch/metag/mm/init.c @@ -390,7 +390,6 @@ void __init mem_init(void) free_all_bootmem(); mem_init_print_info(NULL); - show_mem(0); } void free_initmem(void) diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h index 1884783d15c0..1768d4bdc8d3 100644 --- a/arch/microblaze/include/asm/dma-mapping.h +++ b/arch/microblaze/include/asm/dma-mapping.h @@ -25,7 +25,6 @@ #include <linux/mm.h> #include <linux/scatterlist.h> #include <linux/dma-debug.h> -#include <linux/dma-attrs.h> #include <asm/io.h> #include <asm/cacheflush.h> diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index bf4dec229437..ec04dc1e2527 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -17,7 +17,7 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef NOT_COHERENT_CACHE return consistent_alloc(flag, size, dma_handle); @@ -42,7 +42,7 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size, static void dma_direct_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef NOT_COHERENT_CACHE consistent_free(size, vaddr); @@ -53,7 +53,7 @@ static void dma_direct_free_coherent(struct device *dev, size_t size, static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -78,7 +78,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { __dma_sync(page_to_phys(page) + offset, size, direction); return page_to_phys(page) + offset; @@ -88,7 +88,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { /* There is not necessary to do cache cleanup * @@ -157,7 +157,7 @@ dma_direct_sync_sg_for_device(struct device *dev, static int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t handle, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef CONFIG_MMU unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 29867139851e..26388562e300 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -64,6 +64,7 @@ config MIPS select GENERIC_TIME_VSYSCALL select ARCH_CLOCKSOURCE_DATA select HANDLE_DOMAIN_IRQ + select HAVE_EXIT_THREAD menu "Machine selection" @@ -384,7 +385,7 @@ config MACH_PISTACHIO select CLKSRC_MIPS_GIC select COMMON_CLK select CSRC_R4K - select DMA_MAYBE_COHERENT + select DMA_NONCOHERENT select GPIOLIB select IRQ_MIPS_CPU select LIBFDT @@ -880,7 +881,6 @@ config CAVIUM_OCTEON_SOC select SYS_SUPPORTS_HOTPLUG_CPU if CPU_BIG_ENDIAN select SYS_HAS_EARLY_PRINTK select SYS_HAS_CPU_CAVIUM_OCTEON - select SWAP_IO_SPACE select HW_HAS_PCI select ZONE_DMA32 select HOLES_IN_ZONE @@ -1111,16 +1111,6 @@ config NEED_DMA_MAP_STATE config SYS_HAS_EARLY_PRINTK bool -config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" - depends on SMP && SYS_SUPPORTS_HOTPLUG_CPU - help - Say Y here to allow turning CPUs off and on. CPUs can be - controlled through /sys/devices/system/cpu. - (Note: power management support will enable this option - automatically on SMP systems. ) - Say N if you want to disable CPU hotplug. - config SYS_SUPPORTS_HOTPLUG_CPU bool @@ -1406,7 +1396,6 @@ config CPU_LOONGSON1B bool "Loongson 1B" depends on SYS_HAS_CPU_LOONGSON1B select CPU_LOONGSON1 - select ARCH_WANT_OPTIONAL_GPIOLIB select LEDS_GPIO_REGISTER help The Loongson 1B is a 32-bit SoC, which implements the MIPS32 @@ -2636,6 +2625,16 @@ config SMP If you don't know what to do here, say N. +config HOTPLUG_CPU + bool "Support for hot-pluggable CPUs" + depends on SMP && SYS_SUPPORTS_HOTPLUG_CPU + help + Say Y here to allow turning CPUs off and on. CPUs can be + controlled through /sys/devices/system/cpu. + (Note: power management support will enable this option + automatically on SMP systems. ) + Say N if you want to disable CPU hotplug. + config SMP_UP bool @@ -2887,10 +2886,10 @@ choice the documented boot protocol using a device tree. config MIPS_RAW_APPENDED_DTB - bool "vmlinux.bin" + bool "vmlinux.bin or vmlinuz.bin" help With this option, the boot code will look for a device tree binary - DTB) appended to raw vmlinux.bin (without decompressor). + DTB) appended to raw vmlinux.bin or vmlinuz.bin. (e.g. cat vmlinux.bin <filename>.dtb > vmlinux_w_dtb). This is meant as a backward compatibility convenience for those @@ -2902,24 +2901,6 @@ choice look like a DTB header after a reboot if no actual DTB is appended to vmlinux.bin. Do not leave this option active in a production kernel if you don't intend to always append a DTB. - - config MIPS_ZBOOT_APPENDED_DTB - bool "vmlinuz.bin" - depends on SYS_SUPPORTS_ZBOOT - help - With this option, the boot code will look for a device tree binary - DTB) appended to raw vmlinuz.bin (with decompressor). - (e.g. cat vmlinuz.bin <filename>.dtb > vmlinuz_w_dtb). - - This is meant as a backward compatibility convenience for those - systems with a bootloader that can't be upgraded to accommodate - the documented boot protocol using a device tree. - - Beware that there is very little in terms of protection against - this option being confused by leftover garbage in memory that might - look like a DTB header after a reboot if no actual DTB is appended - to vmlinuz.bin. Do not leave this option active in a production kernel - if you don't intend to always append a DTB. endchoice choice diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 3a0019deb7f7..f206dafbb0a3 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -203,8 +203,8 @@ void __init plat_mem_setup(void) fdt_start = fw_getenvl("fdt_start"); if (fdt_start) __dt_setup_arch((void *)KSEG0ADDR(fdt_start)); - else if (fw_arg0 == -2) - __dt_setup_arch((void *)KSEG0ADDR(fw_arg1)); + else if (fw_passed_dtb) + __dt_setup_arch((void *)KSEG0ADDR(fw_passed_dtb)); if (mips_machtype != ATH79_MACH_GENERIC_OF) { ath79_reset_base = ioremap_nocache(AR71XX_RESET_BASE, diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index f146d1219bde..6776042679dd 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -162,8 +162,8 @@ void __init plat_mem_setup(void) /* intended to somewhat resemble ARM; see Documentation/arm/Booting */ if (fw_arg0 == 0 && fw_arg1 == 0xffffffff) dtb = phys_to_virt(fw_arg2); - else if (fw_arg0 == -2) /* UHI interface */ - dtb = (void *)fw_arg1; + else if (fw_passed_dtb) /* UHI interface */ + dtb = (void *)fw_passed_dtb; else if (__dtb_start != __dtb_end) dtb = (void *)__dtb_start; else diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index 080cd53bac36..fdf99e9dd4c3 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> +#include <linux/libfdt.h> #include <asm/addrspace.h> @@ -36,6 +37,8 @@ extern void puthex(unsigned long long val); #define puthex(val) do {} while (0) #endif +extern char __appended_dtb[]; + void error(char *x) { puts("\n\n"); @@ -114,6 +117,20 @@ void decompress_kernel(unsigned long boot_heap_start) __decompress((char *)zimage_start, zimage_size, 0, 0, (void *)VMLINUX_LOAD_ADDRESS_ULL, 0, 0, error); + if (IS_ENABLED(CONFIG_MIPS_RAW_APPENDED_DTB) && + fdt_magic((void *)&__appended_dtb) == FDT_MAGIC) { + unsigned int image_size, dtb_size; + + dtb_size = fdt_totalsize((void *)&__appended_dtb); + + /* last four bytes is always image size in little endian */ + image_size = le32_to_cpup((void *)&__image_end - 4); + + /* copy dtb to where the booted kernel will expect it */ + memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, + __appended_dtb, dtb_size); + } + /* FIXME: should we flush cache here? */ puts("Now, booting the kernel...\n"); } diff --git a/arch/mips/boot/compressed/head.S b/arch/mips/boot/compressed/head.S index c580e853b9fb..409cb483a9ff 100644 --- a/arch/mips/boot/compressed/head.S +++ b/arch/mips/boot/compressed/head.S @@ -25,22 +25,6 @@ start: move s2, a2 move s3, a3 -#ifdef CONFIG_MIPS_ZBOOT_APPENDED_DTB - PTR_LA t0, __appended_dtb -#ifdef CONFIG_CPU_BIG_ENDIAN - li t1, 0xd00dfeed -#else - li t1, 0xedfe0dd0 -#endif - lw t2, (t0) - bne t1, t2, not_found - nop - - move s1, t0 - PTR_LI s0, -2 -not_found: -#endif - /* Clear BSS */ PTR_LA a0, _edata PTR_LA a2, _end diff --git a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts index d6bc994f736f..b134798a0fd7 100644 --- a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts +++ b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts @@ -9,6 +9,7 @@ */ /include/ "octeon_3xxx.dtsi" +#include <dt-bindings/gpio/gpio.h> / { model = "dlink,dsr-1000n"; @@ -63,12 +64,27 @@ usb1 { label = "usb1"; - gpios = <&gpio 9 1>; /* Active low */ + gpios = <&gpio 9 GPIO_ACTIVE_LOW>; }; usb2 { label = "usb2"; - gpios = <&gpio 10 1>; /* Active low */ + gpios = <&gpio 10 GPIO_ACTIVE_LOW>; + }; + + wps { + label = "wps"; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; + }; + + wireless1 { + label = "5g"; + gpios = <&gpio 17 GPIO_ACTIVE_LOW>; + }; + + wireless2 { + label = "2.4g"; + gpios = <&gpio 18 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts b/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts index de61f02d3ef6..ca6b4467bcd3 100644 --- a/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts +++ b/arch/mips/boot/dts/cavium-octeon/octeon_3xxx.dts @@ -388,16 +388,4 @@ usbn = &usbn; led0 = &led0; }; - - dsr1000n-leds { - compatible = "gpio-leds"; - usb1 { - label = "usb1"; - gpios = <&gpio 9 1>; /* Active low */ - }; - usb2 { - label = "usb2"; - gpios = <&gpio 10 1>; /* Active low */ - }; - }; }; diff --git a/arch/mips/boot/tools/relocs_64.c b/arch/mips/boot/tools/relocs_64.c index b671b5e2dcd8..06066e6ac2f9 100644 --- a/arch/mips/boot/tools/relocs_64.c +++ b/arch/mips/boot/tools/relocs_64.c @@ -9,17 +9,20 @@ typedef uint8_t Elf64_Byte; -typedef struct { - Elf64_Word r_sym; /* Symbol index. */ - Elf64_Byte r_ssym; /* Special symbol. */ - Elf64_Byte r_type3; /* Third relocation. */ - Elf64_Byte r_type2; /* Second relocation. */ - Elf64_Byte r_type; /* First relocation. */ +typedef union { + struct { + Elf64_Word r_sym; /* Symbol index. */ + Elf64_Byte r_ssym; /* Special symbol. */ + Elf64_Byte r_type3; /* Third relocation. */ + Elf64_Byte r_type2; /* Second relocation. */ + Elf64_Byte r_type; /* First relocation. */ + } fields; + Elf64_Xword unused; } Elf64_Mips_Rela; #define ELF_CLASS ELFCLASS64 -#define ELF_R_SYM(val) (((Elf64_Mips_Rela *)(&val))->r_sym) -#define ELF_R_TYPE(val) (((Elf64_Mips_Rela *)(&val))->r_type) +#define ELF_R_SYM(val) (((Elf64_Mips_Rela *)(&val))->fields.r_sym) +#define ELF_R_TYPE(val) (((Elf64_Mips_Rela *)(&val))->fields.r_type) #define ELF_ST_TYPE(o) ELF64_ST_TYPE(o) #define ELF_ST_BIND(o) ELF64_ST_BIND(o) #define ELF_ST_VISIBILITY(o) ELF64_ST_VISIBILITY(o) diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index 2cd45f5f9481..fd69528b24fb 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -125,7 +125,7 @@ static phys_addr_t octeon_small_dma_to_phys(struct device *dev, static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size, direction, attrs); @@ -135,7 +135,7 @@ static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page, } static int octeon_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction, struct dma_attrs *attrs) + int nents, enum dma_data_direction direction, unsigned long attrs) { int r = swiotlb_map_sg_attrs(dev, sg, nents, direction, attrs); mb(); @@ -157,7 +157,7 @@ static void octeon_dma_sync_sg_for_device(struct device *dev, } static void *octeon_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; @@ -189,7 +189,7 @@ static void *octeon_dma_alloc_coherent(struct device *dev, size_t size, } static void octeon_dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs) + void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_handle); } diff --git a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c index 504ed61a47cd..b65a6c1ac016 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-bootmem.c +++ b/arch/mips/cavium-octeon/executive/cvmx-bootmem.c @@ -668,7 +668,7 @@ int64_t cvmx_bootmem_phy_named_block_alloc(uint64_t size, uint64_t min_addr, /* * Round size up to mult of minimum alignment bytes We need * the actual size allocated to allow for blocks to be - * coallesced when they are freed. The alloc routine does the + * coalesced when they are freed. The alloc routine does the * same rounding up on all allocations. */ size = ALIGN(size, CVMX_BOOTMEM_ALIGNMENT_SIZE); diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c index 36e30d65ba05..ff49fc04500c 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c @@ -186,15 +186,6 @@ int cvmx_helper_board_get_mii_address(int ipd_port) return 7 - ipd_port; else return -1; - case CVMX_BOARD_TYPE_CUST_DSR1000N: - /* - * Port 2 connects to Broadcom PHY (B5081). Other ports (0-1) - * connect to a switch (BCM53115). - */ - if (ipd_port == 2) - return 8; - else - return -1; case CVMX_BOARD_TYPE_KONTRON_S1901: if (ipd_port == CVMX_HELPER_BOARD_MGMT_IPD_PORT) return 1; @@ -289,18 +280,6 @@ cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port) return result; } break; - case CVMX_BOARD_TYPE_CUST_DSR1000N: - if (ipd_port == 0 || ipd_port == 1) { - /* Ports 0 and 1 connect to a switch (BCM53115). */ - result.s.link_up = 1; - result.s.full_duplex = 1; - result.s.speed = 1000; - return result; - } else { - /* Port 2 uses a Broadcom PHY (B5081). */ - is_broadcom_phy = 1; - } - break; } phy_addr = cvmx_helper_board_get_mii_address(ipd_port); @@ -765,7 +744,6 @@ enum cvmx_helper_board_usb_clock_types __cvmx_helper_board_usb_get_clock_type(vo case CVMX_BOARD_TYPE_LANAI2_G: case CVMX_BOARD_TYPE_NIC10E_66: case CVMX_BOARD_TYPE_UBNT_E100: - case CVMX_BOARD_TYPE_CUST_DSR1000N: return USB_CLOCK_TYPE_CRYSTAL_12; case CVMX_BOARD_TYPE_NIC10E: return USB_CLOCK_TYPE_REF_12; diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 368eb490354c..5a9b87b7993e 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1260,7 +1260,7 @@ static int octeon_irq_gpio_map(struct irq_domain *d, line = (hw + gpiod->base_hwirq) >> 6; bit = (hw + gpiod->base_hwirq) & 63; - if (line > ARRAY_SIZE(octeon_irq_ciu_to_irq) || + if (line >= ARRAY_SIZE(octeon_irq_ciu_to_irq) || octeon_irq_ciu_to_irq[line][bit] != 0) return -EINVAL; @@ -1542,10 +1542,6 @@ static int __init octeon_irq_init_ciu( goto err; } - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 0, 56); - if (r) - goto err; - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_TWSI2, 0, 59); if (r) goto err; @@ -1559,10 +1555,6 @@ static int __init octeon_irq_init_ciu( goto err; } - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB1, 1, 17); - if (r) - goto err; - /* Enable the CIU lines */ set_c0_status(STATUSF_IP3 | STATUSF_IP2); if (octeon_irq_use_ip4) @@ -2077,10 +2069,6 @@ static int __init octeon_irq_init_ciu2( goto err; } - r = octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 3, 44); - if (r) - goto err; - for (i = 0; i < 4; i++) { r = octeon_irq_force_ciu_mapping( ciu_domain, i + OCTEON_IRQ_PCI_INT0, 4, i); diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c index 7aeafedff94e..b31fbc9d6eae 100644 --- a/arch/mips/cavium-octeon/octeon-platform.c +++ b/arch/mips/cavium-octeon/octeon-platform.c @@ -3,33 +3,27 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 2004-2011 Cavium Networks + * Copyright (C) 2004-2016 Cavium Networks * Copyright (C) 2008 Wind River Systems */ -#include <linux/delay.h> #include <linux/init.h> -#include <linux/irq.h> -#include <linux/i2c.h> -#include <linux/usb.h> -#include <linux/dma-mapping.h> +#include <linux/delay.h> #include <linux/etherdevice.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <linux/slab.h> -#include <linux/platform_device.h> #include <linux/of_platform.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> +#include <linux/usb/ehci_def.h> #include <linux/usb/ehci_pdriver.h> #include <linux/usb/ohci_pdriver.h> #include <asm/octeon/octeon.h> -#include <asm/octeon/cvmx-rnm-defs.h> -#include <asm/octeon/cvmx-helper.h> #include <asm/octeon/cvmx-helper-board.h> #include <asm/octeon/cvmx-uctlx-defs.h> +#define CVMX_UAHCX_EHCI_USBCMD (CVMX_ADD_IO_SEG(0x00016F0000000010ull)) +#define CVMX_UAHCX_OHCI_USBCMD (CVMX_ADD_IO_SEG(0x00016F0000000408ull)) + /* Octeon Random Number Generator. */ static int __init octeon_rng_device_init(void) { @@ -78,12 +72,36 @@ static DEFINE_MUTEX(octeon2_usb_clocks_mutex); static int octeon2_usb_clock_start_cnt; +static int __init octeon2_usb_reset(void) +{ + union cvmx_uctlx_clk_rst_ctl clk_rst_ctl; + u32 ucmd; + + if (!OCTEON_IS_OCTEON2()) + return 0; + + clk_rst_ctl.u64 = cvmx_read_csr(CVMX_UCTLX_CLK_RST_CTL(0)); + if (clk_rst_ctl.s.hrst) { + ucmd = cvmx_read64_uint32(CVMX_UAHCX_EHCI_USBCMD); + ucmd &= ~CMD_RUN; + cvmx_write64_uint32(CVMX_UAHCX_EHCI_USBCMD, ucmd); + mdelay(2); + ucmd |= CMD_RESET; + cvmx_write64_uint32(CVMX_UAHCX_EHCI_USBCMD, ucmd); + ucmd = cvmx_read64_uint32(CVMX_UAHCX_OHCI_USBCMD); + ucmd |= CMD_RUN; + cvmx_write64_uint32(CVMX_UAHCX_OHCI_USBCMD, ucmd); + } + + return 0; +} +arch_initcall(octeon2_usb_reset); + static void octeon2_usb_clocks_start(struct device *dev) { u64 div; union cvmx_uctlx_if_ena if_ena; union cvmx_uctlx_clk_rst_ctl clk_rst_ctl; - union cvmx_uctlx_uphy_ctl_status uphy_ctl_status; union cvmx_uctlx_uphy_portx_ctl_status port_ctl_status; int i; unsigned long io_clk_64_to_ns; @@ -131,6 +149,17 @@ static void octeon2_usb_clocks_start(struct device *dev) if_ena.s.en = 1; cvmx_write_csr(CVMX_UCTLX_IF_ENA(0), if_ena.u64); + for (i = 0; i <= 1; i++) { + port_ctl_status.u64 = + cvmx_read_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0)); + /* Set txvreftune to 15 to obtain compliant 'eye' diagram. */ + port_ctl_status.s.txvreftune = 15; + port_ctl_status.s.txrisetune = 1; + port_ctl_status.s.txpreemphasistune = 1; + cvmx_write_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0), + port_ctl_status.u64); + } + /* Step 3: Configure the reference clock, PHY, and HCLK */ clk_rst_ctl.u64 = cvmx_read_csr(CVMX_UCTLX_CLK_RST_CTL(0)); @@ -218,29 +247,10 @@ static void octeon2_usb_clocks_start(struct device *dev) clk_rst_ctl.s.p_por = 0; cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); - /* Step 5: Wait 1 ms for the PHY clock to start. */ - mdelay(1); + /* Step 5: Wait 3 ms for the PHY clock to start. */ + mdelay(3); - /* - * Step 6: Program the reset input from automatic test - * equipment field in the UPHY CSR - */ - uphy_ctl_status.u64 = cvmx_read_csr(CVMX_UCTLX_UPHY_CTL_STATUS(0)); - uphy_ctl_status.s.ate_reset = 1; - cvmx_write_csr(CVMX_UCTLX_UPHY_CTL_STATUS(0), uphy_ctl_status.u64); - - /* Step 7: Wait for at least 10ns. */ - ndelay(10); - - /* Step 8: Clear the ATE_RESET field in the UPHY CSR. */ - uphy_ctl_status.s.ate_reset = 0; - cvmx_write_csr(CVMX_UCTLX_UPHY_CTL_STATUS(0), uphy_ctl_status.u64); - - /* - * Step 9: Wait for at least 20ns for UPHY to output PHY clock - * signals and OHCI_CLK48 - */ - ndelay(20); + /* Steps 6..9 for ATE only, are skipped. */ /* Step 10: Configure the OHCI_CLK48 and OHCI_CLK12 clocks. */ /* 10a */ @@ -261,6 +271,20 @@ static void octeon2_usb_clocks_start(struct device *dev) clk_rst_ctl.s.p_prst = 1; cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); + /* Step 11b */ + udelay(1); + + /* Step 11c */ + clk_rst_ctl.s.p_prst = 0; + cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); + + /* Step 11d */ + mdelay(1); + + /* Step 11e */ + clk_rst_ctl.s.p_prst = 1; + cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); + /* Step 12: Wait 1 uS. */ udelay(1); @@ -269,21 +293,9 @@ static void octeon2_usb_clocks_start(struct device *dev) cvmx_write_csr(CVMX_UCTLX_CLK_RST_CTL(0), clk_rst_ctl.u64); end_clock: - /* Now we can set some other registers. */ - - for (i = 0; i <= 1; i++) { - port_ctl_status.u64 = - cvmx_read_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0)); - /* Set txvreftune to 15 to obtain compliant 'eye' diagram. */ - port_ctl_status.s.txvreftune = 15; - port_ctl_status.s.txrisetune = 1; - port_ctl_status.s.txpreemphasistune = 1; - cvmx_write_csr(CVMX_UCTLX_UPHY_PORTX_CTL_STATUS(i, 0), - port_ctl_status.u64); - } - /* Set uSOF cycle period to 60,000 bits. */ cvmx_write_csr(CVMX_UCTLX_EHCI_FLA(0), 0x20ull); + exit: mutex_unlock(&octeon2_usb_clocks_mutex); } @@ -311,7 +323,11 @@ static struct usb_ehci_pdata octeon_ehci_pdata = { #ifdef __BIG_ENDIAN .big_endian_mmio = 1, #endif - .dma_mask_64 = 1, + /* + * We can DMA from anywhere. But the descriptors must be in + * the lower 4GB. + */ + .dma_mask_64 = 0, .power_on = octeon_ehci_power_on, .power_off = octeon_ehci_power_off, }; @@ -689,6 +705,10 @@ int __init octeon_prune_device_tree(void) if (fdt_check_header(initial_boot_params)) panic("Corrupt Device Tree."); + WARN(octeon_bootinfo->board_type == CVMX_BOARD_TYPE_CUST_DSR1000N, + "Built-in DTB booting is deprecated on %s. Please switch to use appended DTB.", + cvmx_board_type_to_string(octeon_bootinfo->board_type)); + aliases = fdt_path_offset(initial_boot_params, "/aliases"); if (aliases < 0) { pr_err("Error: No /aliases node in device tree."); @@ -1032,13 +1052,6 @@ end_led: } } - if (octeon_bootinfo->board_type != CVMX_BOARD_TYPE_CUST_DSR1000N) { - int dsr1000n_leds = fdt_path_offset(initial_boot_params, - "/dsr1000n-leds"); - if (dsr1000n_leds >= 0) - fdt_nop_node(initial_boot_params, dsr1000n_leds); - } - return 0; } diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 64f852b063a8..cb16fcc5f8f0 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -40,9 +40,27 @@ #include <asm/octeon/octeon.h> #include <asm/octeon/pci-octeon.h> -#include <asm/octeon/cvmx-mio-defs.h> #include <asm/octeon/cvmx-rst-defs.h> +/* + * TRUE for devices having registers with little-endian byte + * order, FALSE for registers with native-endian byte order. + * PCI mandates little-endian, USB and SATA are configuraable, + * but we chose little-endian for these. + */ +const bool octeon_should_swizzle_table[256] = { + [0x00] = true, /* bootbus/CF */ + [0x1b] = true, /* PCI mmio window */ + [0x1c] = true, /* PCI mmio window */ + [0x1d] = true, /* PCI mmio window */ + [0x1e] = true, /* PCI mmio window */ + [0x68] = true, /* OCTEON III USB */ + [0x69] = true, /* OCTEON III USB */ + [0x6c] = true, /* OCTEON III SATA */ + [0x6f] = true, /* OCTEON II USB */ +}; +EXPORT_SYMBOL(octeon_should_swizzle_table); + #ifdef CONFIG_PCI extern void pci_console_init(const char *arg); #endif diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 33aab89259f3..4d457d602d3b 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -271,6 +271,7 @@ static int octeon_cpu_disable(void) return -ENOTSUPP; set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); octeon_fixup_irqs(); diff --git a/arch/mips/cobalt/setup.c b/arch/mips/cobalt/setup.c index 9a8c2fe8d334..c136a18c7221 100644 --- a/arch/mips/cobalt/setup.c +++ b/arch/mips/cobalt/setup.c @@ -42,8 +42,8 @@ const char *get_system_type(void) /* * Cobalt doesn't have PS/2 keyboard/mouse interfaces, - * keyboard conntroller is never used. - * Also PCI-ISA bridge DMA contoroller is never used. + * keyboard controller is never used. + * Also PCI-ISA bridge DMA controller is never used. */ static struct resource cobalt_reserved_resources[] = { { /* dma1 */ diff --git a/arch/mips/configs/ath25_defconfig b/arch/mips/configs/ath25_defconfig new file mode 100644 index 000000000000..2c829950be17 --- /dev/null +++ b/arch/mips/configs/ath25_defconfig @@ -0,0 +1,119 @@ +CONFIG_ATH25=y +# CONFIG_COMPACTION is not set +CONFIG_HZ_100=y +# CONFIG_SECCOMP is not set +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set +# CONFIG_FHANDLE is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_AIO is not set +CONFIG_EMBEDDED=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_CFQ is not set +# CONFIG_SUSPEND is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=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_IPV6 is not set +CONFIG_CFG80211=m +CONFIG_MAC80211=m +CONFIG_MAC80211_DEBUGFS=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_MTD=y +CONFIG_MTD_REDBOOT_PARTS=y +CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-2 +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_ADV_OPTIONS=y +CONFIG_MTD_CFI_GEOMETRY=y +# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set +# CONFIG_MTD_CFI_I2 is not set +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_COMPLEX_MAPPINGS=y +CONFIG_MTD_PHYSMAP=y +CONFIG_NETDEVICES=y +# CONFIG_ETHERNET is not set +# CONFIG_WLAN_VENDOR_ADMTEK is not set +CONFIG_ATH5K=m +# CONFIG_WLAN_VENDOR_ATMEL is not set +# CONFIG_WLAN_VENDOR_BROADCOM is not set +# CONFIG_WLAN_VENDOR_CISCO is not set +# CONFIG_WLAN_VENDOR_INTEL is not set +# CONFIG_WLAN_VENDOR_INTERSIL is not set +# CONFIG_WLAN_VENDOR_MARVELL is not set +# CONFIG_WLAN_VENDOR_MEDIATEK is not set +# CONFIG_WLAN_VENDOR_RALINK is not set +# CONFIG_WLAN_VENDOR_REALTEK is not set +# CONFIG_WLAN_VENDOR_RSI is not set +# CONFIG_WLAN_VENDOR_ST is not set +# CONFIG_WLAN_VENDOR_TI is not set +# CONFIG_WLAN_VENDOR_ZYDAS is not set +CONFIG_INPUT=m +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +# CONFIG_SERIAL_8250_PCI is not set +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_VGA_ARB is not set +CONFIG_USB=m +CONFIG_USB_EHCI_HCD=m +CONFIG_LEDS_CLASS=y +# CONFIG_IOMMU_SUPPORT is not set +# CONFIG_DNOTIFY is not set +# CONFIG_PROC_PAGE_MONITOR is not set +CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_SUMMARY=y +CONFIG_JFFS2_FS_XATTR=y +# CONFIG_JFFS2_FS_POSIX_ACL is not set +# CONFIG_JFFS2_FS_SECURITY is not set +CONFIG_JFFS2_COMPRESSION_OPTIONS=y +# CONFIG_JFFS2_ZLIB is not set +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_FILE_DIRECT=y +CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU=y +# CONFIG_SQUASHFS_ZLIB is not set +CONFIG_SQUASHFS_XZ=y +CONFIG_PRINTK_TIME=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_STRIP_ASM_SYMS=y +CONFIG_DEBUG_FS=y +# CONFIG_SCHED_DEBUG is not set +# CONFIG_FTRACE is not set +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig index dcac308cec39..d470d08362c0 100644 --- a/arch/mips/configs/cavium_octeon_defconfig +++ b/arch/mips/configs/cavium_octeon_defconfig @@ -59,6 +59,8 @@ CONFIG_EEPROM_AT25=y CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_SATA_AHCI=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_OCTEON=y CONFIG_PATA_OCTEON_CF=y CONFIG_SATA_SIL=y CONFIG_NETDEVICES=y diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index 9f67033961a6..ee9f5f2d18fc 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -127,6 +127,10 @@ extern char arcs_cmdline[COMMAND_LINE_SIZE]; */ extern unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3; +#ifdef CONFIG_USE_OF +extern unsigned long fw_passed_dtb; +#endif + /* * Platform memory detection hook called by setup_arch */ diff --git a/arch/mips/include/asm/dsemul.h b/arch/mips/include/asm/dsemul.h new file mode 100644 index 000000000000..a6e067801f23 --- /dev/null +++ b/arch/mips/include/asm/dsemul.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.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. + */ + +#ifndef __MIPS_ASM_DSEMUL_H__ +#define __MIPS_ASM_DSEMUL_H__ + +#include <asm/break.h> +#include <asm/inst.h> + +/* Break instruction with special math emu break code set */ +#define BREAK_MATH(micromips) (((micromips) ? 0x7 : 0xd) | (BRK_MEMU << 16)) + +/* When used as a frame index, indicates the lack of a frame */ +#define BD_EMUFRAME_NONE ((int)BIT(31)) + +struct mm_struct; +struct pt_regs; +struct task_struct; + +/** + * mips_dsemul() - 'Emulate' an instruction from a branch delay slot + * @regs: User thread register context. + * @ir: The instruction to be 'emulated'. + * @branch_pc: The PC of the branch instruction. + * @cont_pc: The PC to continue at following 'emulation'. + * + * Emulate or execute an arbitrary MIPS instruction within the context of + * the current user thread. This is used primarily to handle instructions + * in the delay slots of emulated branch instructions, for example FP + * branch instructions on systems without an FPU. + * + * Return: Zero on success, negative if ir is a NOP, signal number on failure. + */ +extern int mips_dsemul(struct pt_regs *regs, mips_instruction ir, + unsigned long branch_pc, unsigned long cont_pc); + +/** + * do_dsemulret() - Return from a delay slot 'emulation' frame + * @xcp: User thread register context. + * + * Call in response to the BRK_MEMU break instruction used to return to + * the kernel from branch delay slot 'emulation' frames following a call + * to mips_dsemul(). Restores the user thread PC to the value that was + * passed as the cpc parameter to mips_dsemul(). + * + * Return: True if an emulation frame was returned from, else false. + */ +extern bool do_dsemulret(struct pt_regs *xcp); + +/** + * dsemul_thread_cleanup() - Cleanup thread 'emulation' frame + * @tsk: The task structure associated with the thread + * + * If the thread @tsk has a branch delay slot 'emulation' frame + * allocated to it then free that frame. + * + * Return: True if a frame was freed, else false. + */ +extern bool dsemul_thread_cleanup(struct task_struct *tsk); + +/** + * dsemul_thread_rollback() - Rollback from an 'emulation' frame + * @regs: User thread register context. + * + * If the current thread, whose register context is represented by @regs, + * is executing within a delay slot 'emulation' frame then exit that + * frame. The PC will be rolled back to the branch if the instruction + * that was being 'emulated' has not yet executed, or advanced to the + * continuation PC if it has. + * + * Return: True if a frame was exited, else false. + */ +extern bool dsemul_thread_rollback(struct pt_regs *regs); + +/** + * dsemul_mm_cleanup() - Cleanup per-mm delay slot 'emulation' state + * @mm: The struct mm_struct to cleanup state for. + * + * Cleanup state for the given @mm, ensuring that any memory allocated + * for delay slot 'emulation' book-keeping is freed. This is to be called + * before @mm is freed in order to avoid memory leaks. + */ +extern void dsemul_mm_cleanup(struct mm_struct *mm); + +#endif /* __MIPS_ASM_DSEMUL_H__ */ diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index f5f45717968e..2b3dc2973670 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -458,6 +458,7 @@ extern const char *__elf_platform; #define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) #endif +/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #define ARCH_DLINFO \ do { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ @@ -498,4 +499,7 @@ extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr, extern void mips_set_personality_nan(struct arch_elf_state *state); extern void mips_set_personality_fp(struct arch_elf_state *state); +#define elf_read_implies_exec(ex, stk) mips_elf_read_implies_exec(&(ex), stk) +extern int mips_elf_read_implies_exec(void *elf_ex, int exstack); + #endif /* _ASM_ELF_H */ diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h index 3225c3c0724b..355dc25172e7 100644 --- a/arch/mips/include/asm/fpu_emulator.h +++ b/arch/mips/include/asm/fpu_emulator.h @@ -24,7 +24,7 @@ #define _ASM_FPU_EMULATOR_H #include <linux/sched.h> -#include <asm/break.h> +#include <asm/dsemul.h> #include <asm/thread_info.h> #include <asm/inst.h> #include <asm/local.h> @@ -60,27 +60,16 @@ do { \ #define MIPS_FPU_EMU_INC_STATS(M) do { } while (0) #endif /* CONFIG_DEBUG_FS */ -extern int mips_dsemul(struct pt_regs *regs, mips_instruction ir, - unsigned long cpc); -extern int do_dsemulret(struct pt_regs *xcp); extern int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr); int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31); +int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc); int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, unsigned long *contpc); -/* - * Instruction inserted following the badinst to further tag the sequence - */ -#define BD_COOKIE 0x0000bd36 /* tne $0, $0 with baggage */ - -/* - * Break instruction with special math emu break code set - */ -#define BREAK_MATH(micromips) (((micromips) ? 0x7 : 0xd) | (BRK_MEMU << 16)) - #define SIGNALLING_NAN 0x7ff800007ff80000LL static inline void fpu_emulator_init_fpu(void) diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h index cceae32a0732..64b86b9d30fe 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/irq.h +++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h @@ -42,8 +42,6 @@ enum octeon_irq { OCTEON_IRQ_TIMER1, OCTEON_IRQ_TIMER2, OCTEON_IRQ_TIMER3, - OCTEON_IRQ_USB0, - OCTEON_IRQ_USB1, #ifndef CONFIG_PCI_MSI OCTEON_IRQ_LAST = 127 #endif diff --git a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h index 374eefafb320..0cf5ac1f7245 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h +++ b/arch/mips/include/asm/mach-cavium-octeon/mangle-port.h @@ -12,6 +12,14 @@ #ifdef __BIG_ENDIAN +static inline bool __should_swizzle_bits(volatile void *a) +{ + extern const bool octeon_should_swizzle_table[]; + + unsigned long did = ((unsigned long)a >> 40) & 0xff; + return octeon_should_swizzle_table[did]; +} + # define __swizzle_addr_b(port) (port) # define __swizzle_addr_w(port) (port) # define __swizzle_addr_l(port) (port) @@ -19,6 +27,8 @@ #else /* __LITTLE_ENDIAN */ +#define __should_swizzle_bits(a) false + static inline bool __should_swizzle_addr(unsigned long p) { /* boot bus? */ @@ -35,40 +45,14 @@ static inline bool __should_swizzle_addr(unsigned long p) #endif /* __BIG_ENDIAN */ -/* - * Sane hardware offers swapping of PCI/ISA I/O space accesses in hardware; - * less sane hardware forces software to fiddle with this... - * - * Regardless, if the host bus endianness mismatches that of PCI/ISA, then - * you can't have the numerical value of data and byte addresses within - * multibyte quantities both preserved at the same time. Hence two - * variations of functions: non-prefixed ones that preserve the value - * and prefixed ones that preserve byte addresses. The latters are - * typically used for moving raw data between a peripheral and memory (cf. - * string I/O functions), hence the "__mem_" prefix. - */ -#if defined(CONFIG_SWAP_IO_SPACE) # define ioswabb(a, x) (x) # define __mem_ioswabb(a, x) (x) -# define ioswabw(a, x) le16_to_cpu(x) +# define ioswabw(a, x) (__should_swizzle_bits(a) ? le16_to_cpu(x) : x) # define __mem_ioswabw(a, x) (x) -# define ioswabl(a, x) le32_to_cpu(x) +# define ioswabl(a, x) (__should_swizzle_bits(a) ? le32_to_cpu(x) : x) # define __mem_ioswabl(a, x) (x) -# define ioswabq(a, x) le64_to_cpu(x) +# define ioswabq(a, x) (__should_swizzle_bits(a) ? le64_to_cpu(x) : x) # define __mem_ioswabq(a, x) (x) -#else - -# define ioswabb(a, x) (x) -# define __mem_ioswabb(a, x) (x) -# define ioswabw(a, x) (x) -# define __mem_ioswabw(a, x) cpu_to_le16(x) -# define ioswabl(a, x) (x) -# define __mem_ioswabl(a, x) cpu_to_le32(x) -# define ioswabq(a, x) (x) -# define __mem_ioswabq(a, x) cpu_to_le32(x) - -#endif - #endif /* __ASM_MACH_GENERIC_MANGLE_PORT_H */ diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 9411a4c0bdad..58e7874e9347 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -462,7 +462,7 @@ static inline unsigned int mips_cm_max_vp_width(void) if (mips_cm_revision() >= CM_REV_CM3) return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK; - if (config_enabled(CONFIG_SMP)) + if (IS_ENABLED(CONFIG_SMP)) return smp_num_siblings; return 1; diff --git a/arch/mips/include/asm/mmu.h b/arch/mips/include/asm/mmu.h index 1afa1f986df8..f6ba08d77931 100644 --- a/arch/mips/include/asm/mmu.h +++ b/arch/mips/include/asm/mmu.h @@ -2,11 +2,20 @@ #define __ASM_MMU_H #include <linux/atomic.h> +#include <linux/spinlock.h> +#include <linux/wait.h> typedef struct { unsigned long asid[NR_CPUS]; void *vdso; atomic_t fp_mode_switching; + + /* lock to be held whilst modifying fp_bd_emupage_allocmap */ + spinlock_t bd_emupage_lock; + /* bitmap tracking allocation of fp_bd_emupage */ + unsigned long *bd_emupage_allocmap; + /* wait queue for threads requiring an emuframe */ + wait_queue_head_t bd_emupage_queue; } mm_context_t; #endif /* __ASM_MMU_H */ diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index fc57e135cb0a..ddd57ade1aa8 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -16,6 +16,7 @@ #include <linux/smp.h> #include <linux/slab.h> #include <asm/cacheflush.h> +#include <asm/dsemul.h> #include <asm/hazards.h> #include <asm/tlbflush.h> #include <asm-generic/mm_hooks.h> @@ -128,6 +129,10 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) atomic_set(&mm->context.fp_mode_switching, 0); + mm->context.bd_emupage_allocmap = NULL; + spin_lock_init(&mm->context.bd_emupage_lock); + init_waitqueue_head(&mm->context.bd_emupage_queue); + return 0; } @@ -162,6 +167,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void destroy_context(struct mm_struct *mm) { + dsemul_mm_cleanup(mm); } #define deactivate_mm(tsk, mm) do { } while (0) diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h index ddf496cb2a2a..8967b475ab10 100644 --- a/arch/mips/include/asm/msa.h +++ b/arch/mips/include/asm/msa.h @@ -168,6 +168,7 @@ static inline unsigned int read_msa_##name(void) \ unsigned int reg; \ __asm__ __volatile__( \ " .set push\n" \ + " .set fp=64\n" \ " .set msa\n" \ " cfcmsa %0, $" #cs "\n" \ " .set pop\n" \ @@ -179,6 +180,7 @@ static inline void write_msa_##name(unsigned int val) \ { \ __asm__ __volatile__( \ " .set push\n" \ + " .set fp=64\n" \ " .set msa\n" \ " ctcmsa $" #cs ", %0\n" \ " .set pop\n" \ diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 21ed7150fec3..ea0cd9773914 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -162,16 +162,34 @@ typedef struct { unsigned long pgprot; } pgprot_t; /* * __pa()/__va() should be used only during mem init. */ -#ifdef CONFIG_64BIT -#define __pa(x) \ -({ \ - unsigned long __x = (unsigned long)(x); \ - __x < CKSEG0 ? XPHYSADDR(__x) : CPHYSADDR(__x); \ -}) -#else -#define __pa(x) \ - ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET) -#endif +static inline unsigned long ___pa(unsigned long x) +{ + if (config_enabled(CONFIG_64BIT)) { + /* + * For MIPS64 the virtual address may either be in one of + * the compatibility segements ckseg0 or ckseg1, or it may + * be in xkphys. + */ + return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x); + } + + if (!config_enabled(CONFIG_EVA)) { + /* + * We're using the standard MIPS32 legacy memory map, ie. + * the address x is going to be in kseg0 or kseg1. We can + * handle either case by masking out the desired bits using + * CPHYSADDR. + */ + return CPHYSADDR(x); + } + + /* + * EVA is in use so the memory map could be anything, making it not + * safe to just mask out bits. + */ + return x - PAGE_OFFSET + PHYS_OFFSET; +} +#define __pa(x) ___pa((unsigned long)(x)) #define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET)) #include <asm/io.h> @@ -229,8 +247,10 @@ extern int __virt_addr_valid(const volatile void *kaddr); #define virt_addr_valid(kaddr) \ __virt_addr_valid((const volatile void *) (kaddr)) -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS \ + (VM_READ | VM_WRITE | \ + ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE) #define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 7d44e888134f..70128d3f770a 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -159,7 +159,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) * it better already be global) */ if (pte_none(*buddy)) { - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) buddy->pte_low |= _PAGE_GLOBAL; buddy->pte_high |= _PAGE_GLOBAL; } @@ -172,7 +172,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt htw_stop(); /* Preserve global status for the pair */ - if (config_enabled(CONFIG_XPA)) { + if (IS_ENABLED(CONFIG_XPA)) { if (ptep_buddy(ptep)->pte_high & _PAGE_GLOBAL) null.pte_high = _PAGE_GLOBAL; } else { @@ -319,7 +319,7 @@ static inline int pte_young(pte_t pte) { return pte.pte_low & _PAGE_ACCESSED; } static inline pte_t pte_wrprotect(pte_t pte) { pte.pte_low &= ~_PAGE_WRITE; - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) pte.pte_low &= ~_PAGE_SILENT_WRITE; pte.pte_high &= ~_PAGE_SILENT_WRITE; return pte; @@ -328,7 +328,7 @@ static inline pte_t pte_wrprotect(pte_t pte) static inline pte_t pte_mkclean(pte_t pte) { pte.pte_low &= ~_PAGE_MODIFIED; - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) pte.pte_low &= ~_PAGE_SILENT_WRITE; pte.pte_high &= ~_PAGE_SILENT_WRITE; return pte; @@ -337,7 +337,7 @@ static inline pte_t pte_mkclean(pte_t pte) static inline pte_t pte_mkold(pte_t pte) { pte.pte_low &= ~_PAGE_ACCESSED; - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) pte.pte_low &= ~_PAGE_SILENT_READ; pte.pte_high &= ~_PAGE_SILENT_READ; return pte; @@ -347,7 +347,7 @@ static inline pte_t pte_mkwrite(pte_t pte) { pte.pte_low |= _PAGE_WRITE; if (pte.pte_low & _PAGE_MODIFIED) { - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) pte.pte_low |= _PAGE_SILENT_WRITE; pte.pte_high |= _PAGE_SILENT_WRITE; } @@ -358,7 +358,7 @@ static inline pte_t pte_mkdirty(pte_t pte) { pte.pte_low |= _PAGE_MODIFIED; if (pte.pte_low & _PAGE_WRITE) { - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) pte.pte_low |= _PAGE_SILENT_WRITE; pte.pte_high |= _PAGE_SILENT_WRITE; } @@ -369,7 +369,7 @@ static inline pte_t pte_mkyoung(pte_t pte) { pte.pte_low |= _PAGE_ACCESSED; if (!(pte.pte_low & _PAGE_NO_READ)) { - if (!config_enabled(CONFIG_XPA)) + if (!IS_ENABLED(CONFIG_XPA)) pte.pte_low |= _PAGE_SILENT_READ; pte.pte_high |= _PAGE_SILENT_READ; } diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 7e78b6208d7d..0d36c87acbe2 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -11,12 +11,14 @@ #ifndef _ASM_PROCESSOR_H #define _ASM_PROCESSOR_H +#include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/threads.h> #include <asm/cachectl.h> #include <asm/cpu.h> #include <asm/cpu-info.h> +#include <asm/dsemul.h> #include <asm/mipsregs.h> #include <asm/prefetch.h> @@ -78,7 +80,11 @@ extern unsigned int vced_count, vcei_count; #endif -#define STACK_TOP (TASK_SIZE & PAGE_MASK) +/* + * One page above the stack is used for branch delay slot "emulation". + * See dsemul.c for details. + */ +#define STACK_TOP ((TASK_SIZE & PAGE_MASK) - PAGE_SIZE) /* * This decides where the kernel will search for a free chunk of vm @@ -256,6 +262,12 @@ struct thread_struct { /* Saved fpu/fpu emulator stuff. */ struct mips_fpu_struct fpu FPU_ALIGN; + /* Assigned branch delay slot 'emulation' frame */ + atomic_t bd_emu_frame; + /* PC of the branch from a branch delay slot 'emulation' */ + unsigned long bd_emu_branch_pc; + /* PC to continue from following a branch delay slot 'emulation' */ + unsigned long bd_emu_cont_pc; #ifdef CONFIG_MIPS_MT_FPAFF /* Emulated instruction count */ unsigned long emulated_fp; @@ -323,6 +335,10 @@ struct thread_struct { * FPU affinity state (null if not FPAFF) \ */ \ FPAFF_INIT \ + /* Delay slot emulation */ \ + .bd_emu_frame = ATOMIC_INIT(BD_EMUFRAME_NONE), \ + .bd_emu_branch_pc = 0, \ + .bd_emu_cont_pc = 0, \ /* \ * Saved DSP stuff \ */ \ diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index 38902bf97adc..667ca3c467b7 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -210,7 +210,11 @@ static inline void protected_writeback_dcache_line(unsigned long addr) static inline void protected_writeback_scache_line(unsigned long addr) { +#ifdef CONFIG_EVA + protected_cachee_op(Hit_Writeback_Inv_SD, addr); +#else protected_cache_op(Hit_Writeback_Inv_SD, addr); +#endif } /* diff --git a/arch/mips/include/asm/seccomp.h b/arch/mips/include/asm/seccomp.h index 684fb3a12ed3..d886d6f7687a 100644 --- a/arch/mips/include/asm/seccomp.h +++ b/arch/mips/include/asm/seccomp.h @@ -16,10 +16,10 @@ static inline const int *get_compat_mode1_syscalls(void) 0, /* null terminated */ }; - if (config_enabled(CONFIG_MIPS32_O32) && test_thread_flag(TIF_32BIT_REGS)) + if (IS_ENABLED(CONFIG_MIPS32_O32) && test_thread_flag(TIF_32BIT_REGS)) return syscalls_O32; - if (config_enabled(CONFIG_MIPS32_N32)) + if (IS_ENABLED(CONFIG_MIPS32_N32)) return syscalls_N32; BUG(); diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h index 2292373ff11a..23d6b8015c79 100644 --- a/arch/mips/include/asm/signal.h +++ b/arch/mips/include/asm/signal.h @@ -11,7 +11,7 @@ #include <uapi/asm/signal.h> -#ifdef CONFIG_MIPS32_COMPAT +#ifdef CONFIG_MIPS32_O32 extern struct mips_abi mips_abi_32; #define sig_uses_siginfo(ka, abi) \ @@ -19,8 +19,8 @@ extern struct mips_abi mips_abi_32; ((ka)->sa.sa_flags & SA_SIGINFO)) #else #define sig_uses_siginfo(ka, abi) \ - (config_enabled(CONFIG_64BIT) ? 1 : \ - (config_enabled(CONFIG_TRAD_SIGNALS) ? \ + (IS_ENABLED(CONFIG_64BIT) ? 1 : \ + (IS_ENABLED(CONFIG_TRAD_SIGNALS) ? \ ((ka)->sa.sa_flags & SA_SIGINFO) : 1) ) #endif diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 03722d4326a1..8bc6c70a4030 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -23,7 +23,7 @@ extern int smp_num_siblings; extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; -extern cpumask_t cpu_foreign_map; +extern cpumask_t cpu_foreign_map[]; #define raw_smp_processor_id() (current_thread_info()->cpu) @@ -53,6 +53,8 @@ extern cpumask_t cpu_coherent_mask; extern void asmlinkage smp_bootstrap(void); +extern void calculate_cpu_foreign_map(void); + /* * this function sends a 'reschedule' IPI to another CPU. * it goes straight through and wastes no time serializing diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 47bc45a67e9b..d87882513ee3 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -99,7 +99,7 @@ static inline void syscall_get_arguments(struct task_struct *task, { int ret; /* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */ - if ((config_enabled(CONFIG_32BIT) || + if ((IS_ENABLED(CONFIG_32BIT) || test_tsk_thread_flag(task, TIF_32BIT_REGS)) && (regs->regs[2] == __NR_syscall)) i++; diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 7f109d4f64a4..11b965f98d95 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -88,7 +88,7 @@ extern u64 __ua_limit; */ static inline bool eva_kernel_access(void) { - if (!config_enabled(CONFIG_EVA)) + if (!IS_ENABLED(CONFIG_EVA)) return false; return segment_eq(get_fs(), get_ds()); diff --git a/arch/mips/include/uapi/asm/auxvec.h b/arch/mips/include/uapi/asm/auxvec.h index c9c7195272c4..45ba259a3618 100644 --- a/arch/mips/include/uapi/asm/auxvec.h +++ b/arch/mips/include/uapi/asm/auxvec.h @@ -14,4 +14,6 @@ /* Location of VDSO image. */ #define AT_SYSINFO_EHDR 33 +#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */ + #endif /* __ASM_AUXVEC_H */ diff --git a/arch/mips/jz4740/setup.c b/arch/mips/jz4740/setup.c index 0914ef775b5f..6d0152321819 100644 --- a/arch/mips/jz4740/setup.c +++ b/arch/mips/jz4740/setup.c @@ -75,7 +75,7 @@ void __init device_tree_init(void) const char *get_system_type(void) { - if (config_enabled(CONFIG_MACH_JZ4780)) + if (IS_ENABLED(CONFIG_MACH_JZ4780)) return "JZ4780"; return "JZ4740"; diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index e6053d07072f..4a603a3ea657 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -71,7 +71,7 @@ obj-$(CONFIG_32BIT) += scall32-o32.o obj-$(CONFIG_64BIT) += scall64-64.o obj-$(CONFIG_MIPS32_COMPAT) += linux32.o ptrace32.o signal32.o obj-$(CONFIG_MIPS32_N32) += binfmt_elfn32.o scall64-n32.o signal_n32.o -obj-$(CONFIG_MIPS32_O32) += binfmt_elfo32.o scall64-o32.o +obj-$(CONFIG_MIPS32_O32) += binfmt_elfo32.o scall64-o32.o signal_o32.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_PROC_FS) += proc.o diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index e4c21bbf9422..804d2a2a19fe 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -276,12 +276,7 @@ int r4k_clockevent_init(void) CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_PERCPU; - clockevent_set_clock(cd, mips_hpt_frequency); - - /* Calculate the min / max delta */ - cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd); min_delta = calculate_min_delta(); - cd->min_delta_ns = clockevent_delta2ns(min_delta, cd); cd->rating = 300; cd->irq = irq; @@ -289,7 +284,7 @@ int r4k_clockevent_init(void) cd->set_next_event = mips_next_event; cd->event_handler = mips_event_handler; - clockevents_register_device(cd); + clockevents_config_and_register(cd, mips_hpt_frequency, min_delta, 0x7fffffff); if (cp0_timer_irq_installed) return 0; diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c index 6392dbe504fb..a378e44688f5 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/cpu-bugs64.c @@ -244,7 +244,7 @@ static inline void check_daddi(void) panic(bug64hit, !DADDI_WAR ? daddiwar : nowar); } -int daddiu_bug = config_enabled(CONFIG_CPU_MIPSR6) ? 0 : -1; +int daddiu_bug = IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1; static inline void check_daddiu(void) { @@ -314,7 +314,7 @@ static inline void check_daddiu(void) void __init check_bugs64_early(void) { - if (!config_enabled(CONFIG_CPU_MIPSR6)) { + if (!IS_ENABLED(CONFIG_CPU_MIPSR6)) { check_mult_sh(); check_daddiu(); } @@ -322,6 +322,6 @@ void __init check_bugs64_early(void) void __init check_bugs64(void) { - if (!config_enabled(CONFIG_CPU_MIPSR6)) + if (!IS_ENABLED(CONFIG_CPU_MIPSR6)) check_daddi(); } diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c index 1f910563fdf6..d76275da54cb 100644 --- a/arch/mips/kernel/csrc-r4k.c +++ b/arch/mips/kernel/csrc-r4k.c @@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static u64 notrace r4k_read_sched_clock(void) +static u64 __maybe_unused notrace r4k_read_sched_clock(void) { return read_c0_count(); } @@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void) clocksource_register_hz(&clocksource_mips, mips_hpt_frequency); +#ifndef CONFIG_CPU_FREQ sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency); +#endif return 0; } diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 891f5ee63983..6430bff21fff 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -8,9 +8,12 @@ * option) any later version. */ +#include <linux/binfmts.h> #include <linux/elf.h> +#include <linux/export.h> #include <linux/sched.h> +#include <asm/cpu-features.h> #include <asm/cpu-info.h> /* Whether to accept legacy-NaN and 2008-NaN user binaries. */ @@ -179,7 +182,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr, return -ELIBBAD; } - if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) + if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT)) return 0; fp_abi = state->fp_abi; @@ -285,7 +288,7 @@ void mips_set_personality_fp(struct arch_elf_state *state) * not be worried about N32/N64 binaries. */ - if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) + if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT)) return; switch (state->overall_fp_mode) { @@ -326,3 +329,19 @@ void mips_set_personality_nan(struct arch_elf_state *state) BUG(); } } + +int mips_elf_read_implies_exec(void *elf_ex, int exstack) +{ + if (exstack != EXSTACK_DISABLE_X) { + /* The binary doesn't request a non-executable stack */ + return 1; + } + + if (!cpu_has_rixi) { + /* The CPU doesn't support non-executable memory */ + return 1; + } + + return 0; +} +EXPORT_SYMBOL(mips_elf_read_implies_exec); diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index 56e8fede3fd8..cf052204eb0a 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -93,21 +93,24 @@ NESTED(kernel_entry, 16, sp) # kernel entry point jr t0 0: +#ifdef CONFIG_USE_OF #ifdef CONFIG_MIPS_RAW_APPENDED_DTB - PTR_LA t0, __appended_dtb + PTR_LA t2, __appended_dtb #ifdef CONFIG_CPU_BIG_ENDIAN li t1, 0xd00dfeed #else li t1, 0xedfe0dd0 #endif - lw t2, (t0) - bne t1, t2, not_found - nop + lw t0, (t2) + beq t0, t1, dtb_found +#endif + li t1, -2 + beq a0, t1, dtb_found + move t2, a1 - move a1, t0 - PTR_LI a0, -2 -not_found: + li t2, 0 +dtb_found: #endif PTR_LA t0, __bss_start # clear .bss LONG_S zero, (t0) @@ -122,6 +125,10 @@ not_found: LONG_S a2, fw_arg2 LONG_S a3, fw_arg3 +#ifdef CONFIG_USE_OF + LONG_S t2, fw_passed_dtb +#endif + MTC0 zero, CP0_CONTEXT # clear context register PTR_LA $28, init_thread_union /* Set the SP after an empty pt_regs. */ diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 760217bbb2fa..659e6d3ae335 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -251,7 +251,7 @@ int mips_cm_probe(void) mips_cm_probe_l2sync(); /* determine register width for this CM */ - mips_cm_is64 = config_enabled(CONFIG_64BIT) && (mips_cm_revision() >= CM_REV_CM3); + mips_cm_is64 = IS_ENABLED(CONFIG_64BIT) && (mips_cm_revision() >= CM_REV_CM3); for_each_possible_cpu(cpu) spin_lock_init(&per_cpu(cm_core_lock, cpu)); diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index 7ff2a557f4aa..c3372cac6db2 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -84,7 +84,7 @@ static inline int mipsr6_emul(struct pt_regs *regs, u32 ir) (s32)MIPSInst_SIMM(ir); return 0; case daddiu_op: - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) break; if (MIPSInst_RT(ir)) @@ -143,7 +143,7 @@ static inline int mipsr6_emul(struct pt_regs *regs, u32 ir) (u32)regs->regs[MIPSInst_RT(ir)]); return 0; case dsll_op: - if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir)) + if (IS_ENABLED(CONFIG_32BIT) || MIPSInst_RS(ir)) break; if (MIPSInst_RD(ir)) @@ -152,7 +152,7 @@ static inline int mipsr6_emul(struct pt_regs *regs, u32 ir) MIPSInst_FD(ir)); return 0; case dsrl_op: - if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir)) + if (IS_ENABLED(CONFIG_32BIT) || MIPSInst_RS(ir)) break; if (MIPSInst_RD(ir)) @@ -161,7 +161,7 @@ static inline int mipsr6_emul(struct pt_regs *regs, u32 ir) MIPSInst_FD(ir)); return 0; case daddu_op: - if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir)) + if (IS_ENABLED(CONFIG_32BIT) || MIPSInst_FD(ir)) break; if (MIPSInst_RD(ir)) @@ -170,7 +170,7 @@ static inline int mipsr6_emul(struct pt_regs *regs, u32 ir) (u64)regs->regs[MIPSInst_RT(ir)]; return 0; case dsubu_op: - if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir)) + if (IS_ENABLED(CONFIG_32BIT) || MIPSInst_FD(ir)) break; if (MIPSInst_RD(ir)) @@ -283,7 +283,7 @@ static int jr_func(struct pt_regs *regs, u32 ir) err = mipsr6_emul(regs, nir); if (err > 0) { regs->cp0_epc = nepc; - err = mips_dsemul(regs, nir, cepc); + err = mips_dsemul(regs, nir, epc, cepc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -498,7 +498,7 @@ static int dmult_func(struct pt_regs *regs, u32 ir) s64 res; s64 rt, rs; - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) return SIGILL; rt = regs->regs[MIPSInst_RT(ir)]; @@ -530,7 +530,7 @@ static int dmultu_func(struct pt_regs *regs, u32 ir) u64 res; u64 rt, rs; - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) return SIGILL; rt = regs->regs[MIPSInst_RT(ir)]; @@ -561,7 +561,7 @@ static int ddiv_func(struct pt_regs *regs, u32 ir) { s64 rt, rs; - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) return SIGILL; rt = regs->regs[MIPSInst_RT(ir)]; @@ -586,7 +586,7 @@ static int ddivu_func(struct pt_regs *regs, u32 ir) { u64 rt, rs; - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) return SIGILL; rt = regs->regs[MIPSInst_RT(ir)]; @@ -825,7 +825,7 @@ static int dclz_func(struct pt_regs *regs, u32 ir) u64 res; u64 rs; - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) return SIGILL; if (!MIPSInst_RD(ir)) @@ -852,7 +852,7 @@ static int dclo_func(struct pt_regs *regs, u32 ir) u64 res; u64 rs; - if (config_enabled(CONFIG_32BIT)) + if (IS_ENABLED(CONFIG_32BIT)) return SIGILL; if (!MIPSInst_RD(ir)) @@ -1033,7 +1033,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1082,7 +1082,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1149,7 +1149,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1484,7 +1484,7 @@ fpu_emul: break; case ldl_op: - if (config_enabled(CONFIG_32BIT)) { + if (IS_ENABLED(CONFIG_32BIT)) { err = SIGILL; break; } @@ -1603,7 +1603,7 @@ fpu_emul: break; case ldr_op: - if (config_enabled(CONFIG_32BIT)) { + if (IS_ENABLED(CONFIG_32BIT)) { err = SIGILL; break; } @@ -1722,7 +1722,7 @@ fpu_emul: break; case sdl_op: - if (config_enabled(CONFIG_32BIT)) { + if (IS_ENABLED(CONFIG_32BIT)) { err = SIGILL; break; } @@ -1840,7 +1840,7 @@ fpu_emul: break; case sdr_op: - if (config_enabled(CONFIG_32BIT)) { + if (IS_ENABLED(CONFIG_32BIT)) { err = SIGILL; break; } @@ -2072,7 +2072,7 @@ fpu_emul: break; case lld_op: - if (config_enabled(CONFIG_32BIT)) { + if (IS_ENABLED(CONFIG_32BIT)) { err = SIGILL; break; } @@ -2133,7 +2133,7 @@ fpu_emul: break; case scd_op: - if (config_enabled(CONFIG_32BIT)) { + if (IS_ENABLED(CONFIG_32BIT)) { err = SIGILL; break; } diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index adda3ffb9b78..5b31a9405ebc 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -148,7 +148,7 @@ int cps_pm_enter_state(enum cps_pm_state state) } /* Setup the VPE to run mips_cps_pm_restore when started again */ - if (config_enabled(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) { + if (IS_ENABLED(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) { /* Power gating relies upon CPS SMP */ if (!mips_cps_smp_in_use()) return -EINVAL; @@ -387,7 +387,7 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) memset(labels, 0, sizeof(labels)); memset(relocs, 0, sizeof(relocs)); - if (config_enabled(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) { + if (IS_ENABLED(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) { /* Power gating relies upon CPS SMP */ if (!mips_cps_smp_in_use()) goto out_err; diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 813ed7829c61..7429ad09fbe3 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -30,6 +30,7 @@ #include <asm/asm.h> #include <asm/bootinfo.h> #include <asm/cpu.h> +#include <asm/dsemul.h> #include <asm/dsp.h> #include <asm/fpu.h> #include <asm/msa.h> @@ -68,11 +69,22 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) lose_fpu(0); clear_thread_flag(TIF_MSA_CTX_LIVE); clear_used_math(); + atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); init_dsp(); regs->cp0_epc = pc; regs->regs[29] = sp; } +void exit_thread(struct task_struct *tsk) +{ + /* + * User threads may have allocated a delay slot emulation frame. + * If so, clean up that allocation. + */ + if (!(current->flags & PF_KTHREAD)) + dsemul_thread_cleanup(tsk); +} + int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { /* @@ -159,6 +171,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, clear_tsk_thread_flag(p, TIF_FPUBOUND); #endif /* CONFIG_MIPS_MT_FPAFF */ + atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE); + if (clone_flags & CLONE_SETTLS) ti->tp_value = regs->regs[7]; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 9c0b387d6427..51d3988933f8 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -348,7 +348,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key PTR sys_request_key - PTR sys_keyctl /* 6245 */ + PTR compat_sys_keyctl /* 6245 */ PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f4f28b1580de..6efa7136748f 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -504,7 +504,7 @@ EXPORT(sys32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key /* 4280 */ PTR sys_request_key - PTR sys_keyctl + PTR compat_sys_keyctl PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch /* 4285 */ diff --git a/arch/mips/kernel/segment.c b/arch/mips/kernel/segment.c index 87bc74a5a518..2703f218202e 100644 --- a/arch/mips/kernel/segment.c +++ b/arch/mips/kernel/segment.c @@ -26,17 +26,20 @@ static void build_segment_config(char *str, unsigned int cfg) /* * Access modes MK, MSK and MUSK are mapped segments. Therefore - * there is no direct physical address mapping. + * there is no direct physical address mapping unless it becomes + * unmapped uncached at error level due to EU. */ - if ((am == 0) || (am > 3)) { + if ((am == 0) || (am > 3) || (cfg & MIPS_SEGCFG_EU)) str += sprintf(str, " %03lx", ((cfg & MIPS_SEGCFG_PA) >> MIPS_SEGCFG_PA_SHIFT)); + else + str += sprintf(str, " UND"); + + if ((am == 0) || (am > 3)) str += sprintf(str, " %01ld", ((cfg & MIPS_SEGCFG_C) >> MIPS_SEGCFG_C_SHIFT)); - } else { - str += sprintf(str, " UND"); + else str += sprintf(str, " U"); - } /* Exception configuration. */ str += sprintf(str, " %01ld\n", diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index ef408a03e818..36cf8d65c47d 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -875,6 +875,10 @@ void __init setup_arch(char **cmdline_p) unsigned long kernelsp[NR_CPUS]; unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3; +#ifdef CONFIG_USE_OF +unsigned long fw_passed_dtb; +#endif + #ifdef CONFIG_DEBUG_FS struct dentry *mips_debugfs_dir; static int __init debugfs_mips(void) diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index ae4231452115..9e224469c788 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -165,7 +165,7 @@ static int save_msa_extcontext(void __user *buf) * should already have been done when handling scalar FP * context. */ - BUG_ON(config_enabled(CONFIG_EVA)); + BUG_ON(IS_ENABLED(CONFIG_EVA)); err = __put_user(read_msa_csr(), &msa->csr); err |= _save_msa_all_upper(&msa->wr); @@ -195,7 +195,7 @@ static int restore_msa_extcontext(void __user *buf, unsigned int size) unsigned int csr; int i, err; - if (!config_enabled(CONFIG_CPU_HAS_MSA)) + if (!IS_ENABLED(CONFIG_CPU_HAS_MSA)) return SIGSYS; if (size != sizeof(*msa)) @@ -215,7 +215,7 @@ static int restore_msa_extcontext(void __user *buf, unsigned int size) * scalar FP context, so FPU & MSA should have already been * disabled whilst handling scalar FP context. */ - BUG_ON(config_enabled(CONFIG_EVA)); + BUG_ON(IS_ENABLED(CONFIG_EVA)); write_msa_csr(csr); err |= _restore_msa_all_upper(&msa->wr); @@ -315,7 +315,7 @@ int protected_save_fp_context(void __user *sc) * EVA does not have userland equivalents of ldc1 or sdc1, so * save to the kernel FP context & copy that to userland below. */ - if (config_enabled(CONFIG_EVA)) + if (IS_ENABLED(CONFIG_EVA)) lose_fpu(1); while (1) { @@ -378,7 +378,7 @@ int protected_restore_fp_context(void __user *sc) * disable the FPU here such that the code below simply copies to * the kernel FP context. */ - if (config_enabled(CONFIG_EVA)) + if (IS_ENABLED(CONFIG_EVA)) lose_fpu(0); while (1) { @@ -772,6 +772,14 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) struct mips_abi *abi = current->thread.abi; void *vdso = current->mm->context.vdso; + /* + * If we were emulating a delay slot instruction, exit that frame such + * that addresses in the sigframe are as expected for userland and we + * don't have a problem if we reuse the thread's frame for an + * instruction within the signal handler. + */ + dsemul_thread_rollback(regs); + if (regs->regs[0]) { switch(regs->regs[2]) { case ERESTART_RESTARTBLOCK: diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index 78c8349d151c..97b7c51b8251 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -6,129 +6,26 @@ * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994 - 2000, 2006 Ralf Baechle * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2016, Imagination Technologies Ltd. */ -#include <linux/cache.h> -#include <linux/compat.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/smp.h> +#include <linux/compiler.h> +#include <linux/errno.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/syscalls.h> -#include <linux/errno.h> -#include <linux/wait.h> -#include <linux/ptrace.h> -#include <linux/suspend.h> -#include <linux/compiler.h> -#include <linux/uaccess.h> -#include <asm/abi.h> -#include <asm/asm.h> +#include <asm/compat.h> #include <asm/compat-signal.h> -#include <linux/bitops.h> -#include <asm/cacheflush.h> -#include <asm/sim.h> -#include <asm/ucontext.h> -#include <asm/fpu.h> -#include <asm/war.h> -#include <asm/dsp.h> +#include <asm/uaccess.h> +#include <asm/unistd.h> #include "signal-common.h" -/* - * Including <asm/unistd.h> would give use the 64-bit syscall numbers ... - */ -#define __NR_O32_restart_syscall 4253 - /* 32-bit compatibility types */ typedef unsigned int __sighandler32_t; typedef void (*vfptr_t)(void); -struct ucontext32 { - u32 uc_flags; - s32 uc_link; - compat_stack_t uc_stack; - struct sigcontext32 uc_mcontext; - compat_sigset_t uc_sigmask; /* mask last for extensibility */ -}; - -struct sigframe32 { - u32 sf_ass[4]; /* argument save space for o32 */ - u32 sf_pad[2]; /* Was: signal trampoline */ - struct sigcontext32 sf_sc; - compat_sigset_t sf_mask; -}; - -struct rt_sigframe32 { - u32 rs_ass[4]; /* argument save space for o32 */ - u32 rs_pad[2]; /* Was: signal trampoline */ - compat_siginfo_t rs_info; - struct ucontext32 rs_uc; -}; - -static int setup_sigcontext32(struct pt_regs *regs, - struct sigcontext32 __user *sc) -{ - int err = 0; - int i; - - err |= __put_user(regs->cp0_epc, &sc->sc_pc); - - err |= __put_user(0, &sc->sc_regs[0]); - for (i = 1; i < 32; i++) - err |= __put_user(regs->regs[i], &sc->sc_regs[i]); - - err |= __put_user(regs->hi, &sc->sc_mdhi); - err |= __put_user(regs->lo, &sc->sc_mdlo); - if (cpu_has_dsp) { - err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp); - err |= __put_user(mfhi1(), &sc->sc_hi1); - err |= __put_user(mflo1(), &sc->sc_lo1); - err |= __put_user(mfhi2(), &sc->sc_hi2); - err |= __put_user(mflo2(), &sc->sc_lo2); - err |= __put_user(mfhi3(), &sc->sc_hi3); - err |= __put_user(mflo3(), &sc->sc_lo3); - } - - /* - * Save FPU state to signal context. Signal handler - * will "inherit" current FPU state. - */ - err |= protected_save_fp_context(sc); - - return err; -} - -static int restore_sigcontext32(struct pt_regs *regs, - struct sigcontext32 __user *sc) -{ - int err = 0; - s32 treg; - int i; - - /* Always make any pending restarted system calls return -EINTR */ - current->restart_block.fn = do_no_restart_syscall; - - err |= __get_user(regs->cp0_epc, &sc->sc_pc); - err |= __get_user(regs->hi, &sc->sc_mdhi); - err |= __get_user(regs->lo, &sc->sc_mdlo); - if (cpu_has_dsp) { - err |= __get_user(treg, &sc->sc_hi1); mthi1(treg); - err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg); - err |= __get_user(treg, &sc->sc_hi2); mthi2(treg); - err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg); - err |= __get_user(treg, &sc->sc_hi3); mthi3(treg); - err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg); - err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK); - } - - for (i = 1; i < 32; i++) - err |= __get_user(regs->regs[i], &sc->sc_regs[i]); - - return err ?: protected_restore_fp_context(sc); -} - /* * Atomically swap in the new signal mask, and wait for a signal. */ @@ -247,176 +144,3 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return 0; } - -asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) -{ - struct sigframe32 __user *frame; - sigset_t blocked; - int sig; - - frame = (struct sigframe32 __user *) regs.regs[29]; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; - if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask)) - goto badframe; - - set_current_blocked(&blocked); - - sig = restore_sigcontext32(®s, &frame->sf_sc); - if (sig < 0) - goto badframe; - else if (sig) - force_sig(sig, current); - - /* - * Don't let your children do this ... - */ - __asm__ __volatile__( - "move\t$29, %0\n\t" - "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); - /* Unreached */ - -badframe: - force_sig(SIGSEGV, current); -} - -asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) -{ - struct rt_sigframe32 __user *frame; - sigset_t set; - int sig; - - frame = (struct rt_sigframe32 __user *) regs.regs[29]; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; - if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask)) - goto badframe; - - set_current_blocked(&set); - - sig = restore_sigcontext32(®s, &frame->rs_uc.uc_mcontext); - if (sig < 0) - goto badframe; - else if (sig) - force_sig(sig, current); - - if (compat_restore_altstack(&frame->rs_uc.uc_stack)) - goto badframe; - - /* - * Don't let your children do this ... - */ - __asm__ __volatile__( - "move\t$29, %0\n\t" - "j\tsyscall_exit" - :/* no outputs */ - :"r" (®s)); - /* Unreached */ - -badframe: - force_sig(SIGSEGV, current); -} - -static int setup_frame_32(void *sig_return, struct ksignal *ksig, - struct pt_regs *regs, sigset_t *set) -{ - struct sigframe32 __user *frame; - int err = 0; - - frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) - return -EFAULT; - - err |= setup_sigcontext32(regs, &frame->sf_sc); - err |= __copy_conv_sigset_to_user(&frame->sf_mask, set); - - if (err) - return -EFAULT; - - /* - * Arguments to signal handler: - * - * a0 = signal number - * a1 = 0 (should be cause) - * a2 = pointer to struct sigcontext - * - * $25 and c0_epc point to the signal handler, $29 points to the - * struct sigframe. - */ - regs->regs[ 4] = ksig->sig; - regs->regs[ 5] = 0; - regs->regs[ 6] = (unsigned long) &frame->sf_sc; - regs->regs[29] = (unsigned long) frame; - regs->regs[31] = (unsigned long) sig_return; - regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; - - DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", - current->comm, current->pid, - frame, regs->cp0_epc, regs->regs[31]); - - return 0; -} - -static int setup_rt_frame_32(void *sig_return, struct ksignal *ksig, - struct pt_regs *regs, sigset_t *set) -{ - struct rt_sigframe32 __user *frame; - int err = 0; - - frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) - return -EFAULT; - - /* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */ - err |= copy_siginfo_to_user32(&frame->rs_info, &ksig->info); - - /* Create the ucontext. */ - err |= __put_user(0, &frame->rs_uc.uc_flags); - err |= __put_user(0, &frame->rs_uc.uc_link); - err |= __compat_save_altstack(&frame->rs_uc.uc_stack, regs->regs[29]); - err |= setup_sigcontext32(regs, &frame->rs_uc.uc_mcontext); - err |= __copy_conv_sigset_to_user(&frame->rs_uc.uc_sigmask, set); - - if (err) - return -EFAULT; - - /* - * Arguments to signal handler: - * - * a0 = signal number - * a1 = 0 (should be cause) - * a2 = pointer to ucontext - * - * $25 and c0_epc point to the signal handler, $29 points to - * the struct rt_sigframe32. - */ - regs->regs[ 4] = ksig->sig; - regs->regs[ 5] = (unsigned long) &frame->rs_info; - regs->regs[ 6] = (unsigned long) &frame->rs_uc; - regs->regs[29] = (unsigned long) frame; - regs->regs[31] = (unsigned long) sig_return; - regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; - - DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", - current->comm, current->pid, - frame, regs->cp0_epc, regs->regs[31]); - - return 0; -} - -/* - * o32 compatibility on 64-bit kernels, without DSP ASE - */ -struct mips_abi mips_abi_32 = { - .setup_frame = setup_frame_32, - .setup_rt_frame = setup_rt_frame_32, - .restart = __NR_O32_restart_syscall, - - .off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs), - .off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr), - .off_sc_used_math = offsetof(struct sigcontext32, sc_used_math), - - .vdso = &vdso_image_o32, -}; diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c new file mode 100644 index 000000000000..5e169fc5ca5c --- /dev/null +++ b/arch/mips/kernel/signal_o32.c @@ -0,0 +1,285 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 1994 - 2000, 2006 Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2016, Imagination Technologies Ltd. + */ +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/signal.h> +#include <linux/uaccess.h> + +#include <asm/abi.h> +#include <asm/compat-signal.h> +#include <asm/dsp.h> +#include <asm/sim.h> +#include <asm/unistd.h> + +#include "signal-common.h" + +/* + * Including <asm/unistd.h> would give use the 64-bit syscall numbers ... + */ +#define __NR_O32_restart_syscall 4253 + +struct sigframe32 { + u32 sf_ass[4]; /* argument save space for o32 */ + u32 sf_pad[2]; /* Was: signal trampoline */ + struct sigcontext32 sf_sc; + compat_sigset_t sf_mask; +}; + +struct ucontext32 { + u32 uc_flags; + s32 uc_link; + compat_stack_t uc_stack; + struct sigcontext32 uc_mcontext; + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + +struct rt_sigframe32 { + u32 rs_ass[4]; /* argument save space for o32 */ + u32 rs_pad[2]; /* Was: signal trampoline */ + compat_siginfo_t rs_info; + struct ucontext32 rs_uc; +}; + +static int setup_sigcontext32(struct pt_regs *regs, + struct sigcontext32 __user *sc) +{ + int err = 0; + int i; + + err |= __put_user(regs->cp0_epc, &sc->sc_pc); + + err |= __put_user(0, &sc->sc_regs[0]); + for (i = 1; i < 32; i++) + err |= __put_user(regs->regs[i], &sc->sc_regs[i]); + + err |= __put_user(regs->hi, &sc->sc_mdhi); + err |= __put_user(regs->lo, &sc->sc_mdlo); + if (cpu_has_dsp) { + err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp); + err |= __put_user(mfhi1(), &sc->sc_hi1); + err |= __put_user(mflo1(), &sc->sc_lo1); + err |= __put_user(mfhi2(), &sc->sc_hi2); + err |= __put_user(mflo2(), &sc->sc_lo2); + err |= __put_user(mfhi3(), &sc->sc_hi3); + err |= __put_user(mflo3(), &sc->sc_lo3); + } + + /* + * Save FPU state to signal context. Signal handler + * will "inherit" current FPU state. + */ + err |= protected_save_fp_context(sc); + + return err; +} + +static int restore_sigcontext32(struct pt_regs *regs, + struct sigcontext32 __user *sc) +{ + int err = 0; + s32 treg; + int i; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + err |= __get_user(regs->cp0_epc, &sc->sc_pc); + err |= __get_user(regs->hi, &sc->sc_mdhi); + err |= __get_user(regs->lo, &sc->sc_mdlo); + if (cpu_has_dsp) { + err |= __get_user(treg, &sc->sc_hi1); mthi1(treg); + err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg); + err |= __get_user(treg, &sc->sc_hi2); mthi2(treg); + err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg); + err |= __get_user(treg, &sc->sc_hi3); mthi3(treg); + err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg); + err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK); + } + + for (i = 1; i < 32; i++) + err |= __get_user(regs->regs[i], &sc->sc_regs[i]); + + return err ?: protected_restore_fp_context(sc); +} + +static int setup_frame_32(void *sig_return, struct ksignal *ksig, + struct pt_regs *regs, sigset_t *set) +{ + struct sigframe32 __user *frame; + int err = 0; + + frame = get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) + return -EFAULT; + + err |= setup_sigcontext32(regs, &frame->sf_sc); + err |= __copy_conv_sigset_to_user(&frame->sf_mask, set); + + if (err) + return -EFAULT; + + /* + * Arguments to signal handler: + * + * a0 = signal number + * a1 = 0 (should be cause) + * a2 = pointer to struct sigcontext + * + * $25 and c0_epc point to the signal handler, $29 points to the + * struct sigframe. + */ + regs->regs[ 4] = ksig->sig; + regs->regs[ 5] = 0; + regs->regs[ 6] = (unsigned long) &frame->sf_sc; + regs->regs[29] = (unsigned long) frame; + regs->regs[31] = (unsigned long) sig_return; + regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; + + DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", + current->comm, current->pid, + frame, regs->cp0_epc, regs->regs[31]); + + return 0; +} + +asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) +{ + struct rt_sigframe32 __user *frame; + sigset_t set; + int sig; + + frame = (struct rt_sigframe32 __user *) regs.regs[29]; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask)) + goto badframe; + + set_current_blocked(&set); + + sig = restore_sigcontext32(®s, &frame->rs_uc.uc_mcontext); + if (sig < 0) + goto badframe; + else if (sig) + force_sig(sig, current); + + if (compat_restore_altstack(&frame->rs_uc.uc_stack)) + goto badframe; + + /* + * Don't let your children do this ... + */ + __asm__ __volatile__( + "move\t$29, %0\n\t" + "j\tsyscall_exit" + :/* no outputs */ + :"r" (®s)); + /* Unreached */ + +badframe: + force_sig(SIGSEGV, current); +} + +static int setup_rt_frame_32(void *sig_return, struct ksignal *ksig, + struct pt_regs *regs, sigset_t *set) +{ + struct rt_sigframe32 __user *frame; + int err = 0; + + frame = get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame))) + return -EFAULT; + + /* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */ + err |= copy_siginfo_to_user32(&frame->rs_info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->rs_uc.uc_flags); + err |= __put_user(0, &frame->rs_uc.uc_link); + err |= __compat_save_altstack(&frame->rs_uc.uc_stack, regs->regs[29]); + err |= setup_sigcontext32(regs, &frame->rs_uc.uc_mcontext); + err |= __copy_conv_sigset_to_user(&frame->rs_uc.uc_sigmask, set); + + if (err) + return -EFAULT; + + /* + * Arguments to signal handler: + * + * a0 = signal number + * a1 = 0 (should be cause) + * a2 = pointer to ucontext + * + * $25 and c0_epc point to the signal handler, $29 points to + * the struct rt_sigframe32. + */ + regs->regs[ 4] = ksig->sig; + regs->regs[ 5] = (unsigned long) &frame->rs_info; + regs->regs[ 6] = (unsigned long) &frame->rs_uc; + regs->regs[29] = (unsigned long) frame; + regs->regs[31] = (unsigned long) sig_return; + regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler; + + DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n", + current->comm, current->pid, + frame, regs->cp0_epc, regs->regs[31]); + + return 0; +} + +/* + * o32 compatibility on 64-bit kernels, without DSP ASE + */ +struct mips_abi mips_abi_32 = { + .setup_frame = setup_frame_32, + .setup_rt_frame = setup_rt_frame_32, + .restart = __NR_O32_restart_syscall, + + .off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs), + .off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr), + .off_sc_used_math = offsetof(struct sigcontext32, sc_used_math), + + .vdso = &vdso_image_o32, +}; + + +asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs) +{ + struct sigframe32 __user *frame; + sigset_t blocked; + int sig; + + frame = (struct sigframe32 __user *) regs.regs[29]; + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask)) + goto badframe; + + set_current_blocked(&blocked); + + sig = restore_sigcontext32(®s, &frame->sf_sc); + if (sig < 0) + goto badframe; + else if (sig) + force_sig(sig, current); + + /* + * Don't let your children do this ... + */ + __asm__ __volatile__( + "move\t$29, %0\n\t" + "j\tsyscall_exit" + :/* no outputs */ + :"r" (®s)); + /* Unreached */ + +badframe: + force_sig(SIGSEGV, current); +} diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index e02addc0307f..6d0f1321e084 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -363,6 +363,7 @@ static int bmips_cpu_disable(void) pr_info("SMP: CPU%d is offline\n", cpu); set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); clear_c0_status(IE_IRQ5); diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 4ed36f288d64..e9d9fc6c754c 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -46,8 +46,8 @@ static unsigned core_vpe_count(unsigned core) if (threads_disabled) return 1; - if ((!config_enabled(CONFIG_MIPS_MT_SMP) || !cpu_has_mipsmt) - && (!config_enabled(CONFIG_CPU_MIPSR6) || !cpu_has_vp)) + if ((!IS_ENABLED(CONFIG_MIPS_MT_SMP) || !cpu_has_mipsmt) + && (!IS_ENABLED(CONFIG_CPU_MIPSR6) || !cpu_has_vp)) return 1; mips_cm_lock_other(core, 0); @@ -206,7 +206,7 @@ err_out: } } -static void boot_core(unsigned core) +static void boot_core(unsigned int core, unsigned int vpe_id) { u32 access, stat, seq_state; unsigned timeout; @@ -233,8 +233,9 @@ static void boot_core(unsigned core) mips_cpc_lock_other(core); if (mips_cm_revision() >= CM_REV_CM3) { - /* Run VP0 following the reset */ - write_cpc_co_vp_run(0x1); + /* Run only the requested VP following the reset */ + write_cpc_co_vp_stop(0xf); + write_cpc_co_vp_run(1 << vpe_id); /* * Ensure that the VP_RUN register is written before the @@ -306,7 +307,7 @@ static void cps_boot_secondary(int cpu, struct task_struct *idle) if (!test_bit(core, core_power)) { /* Boot a VPE on a powered down core */ - boot_core(core); + boot_core(core, vpe_id); goto out; } @@ -397,6 +398,7 @@ static int cps_cpu_disable(void) atomic_sub(1 << cpu_vpe_id(¤t_cpu_data), &core_cfg->vpe_mask); smp_mb__after_atomic(); set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); return 0; @@ -411,14 +413,16 @@ static enum { void play_dead(void) { - unsigned cpu, core; + unsigned int cpu, core, vpe_id; local_irq_disable(); idle_task_exit(); cpu = smp_processor_id(); cpu_death = CPU_DEATH_POWER; - if (cpu_has_mipsmt) { + pr_debug("CPU%d going offline\n", cpu); + + if (cpu_has_mipsmt || cpu_has_vp) { core = cpu_data[cpu].core; /* Look for another online VPE within the core */ @@ -439,10 +443,21 @@ void play_dead(void) complete(&cpu_death_chosen); if (cpu_death == CPU_DEATH_HALT) { - /* Halt this TC */ - write_c0_tchalt(TCHALT_H); - instruction_hazard(); + vpe_id = cpu_vpe_id(&cpu_data[cpu]); + + pr_debug("Halting core %d VP%d\n", core, vpe_id); + if (cpu_has_mipsmt) { + /* Halt this TC */ + write_c0_tchalt(TCHALT_H); + instruction_hazard(); + } else if (cpu_has_vp) { + write_cpc_cl_vp_stop(1 << vpe_id); + + /* Ensure that the VP_STOP register is written */ + wmb(); + } } else { + pr_debug("Gating power to core %d\n", core); /* Power down the core */ cps_pm_enter_state(CPS_PM_POWER_GATED); } @@ -469,6 +484,7 @@ static void wait_for_sibling_halt(void *ptr_cpu) static void cps_cpu_die(unsigned int cpu) { unsigned core = cpu_data[cpu].core; + unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]); unsigned stat; int err; @@ -497,10 +513,12 @@ static void cps_cpu_die(unsigned int cpu) * in which case the CPC will refuse to power down the core. */ do { + mips_cm_lock_other(core, vpe_id); mips_cpc_lock_other(core); stat = read_cpc_co_stat_conf(); stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; mips_cpc_unlock_other(); + mips_cm_unlock_other(); } while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 && stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 && stat != CPC_Cx_STAT_CONF_SEQSTATE_U2); @@ -517,6 +535,12 @@ static void cps_cpu_die(unsigned int cpu) (void *)(unsigned long)cpu, 1); if (err) panic("Failed to call remote sibling CPU\n"); + } else if (cpu_has_vp) { + do { + mips_cm_lock_other(core, vpe_id); + stat = read_cpc_co_vp_running(); + mips_cm_unlock_other(); + } while (stat & (1 << vpe_id)); } } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index f9d01e953acb..f95f094f36e4 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -72,7 +72,7 @@ EXPORT_SYMBOL(cpu_core_map); * A logcal cpu mask containing only one VPE per core to * reduce the number of IPIs on large MT systems. */ -cpumask_t cpu_foreign_map __read_mostly; +cpumask_t cpu_foreign_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_foreign_map); /* representing cpus for which sibling maps can be computed */ @@ -124,7 +124,7 @@ static inline void set_cpu_core_map(int cpu) * Calculate a new cpu_foreign_map mask whenever a * new cpu appears or disappears. */ -static inline void calculate_cpu_foreign_map(void) +void calculate_cpu_foreign_map(void) { int i, k, core_present; cpumask_t temp_foreign_map; @@ -141,7 +141,9 @@ static inline void calculate_cpu_foreign_map(void) cpumask_set_cpu(i, &temp_foreign_map); } - cpumask_copy(&cpu_foreign_map, &temp_foreign_map); + for_each_online_cpu(i) + cpumask_andnot(&cpu_foreign_map[i], + &temp_foreign_map, &cpu_sibling_map[i]); } struct plat_smp_ops *mp_ops; @@ -344,16 +346,9 @@ asmlinkage void start_secondary(void) static void stop_this_cpu(void *dummy) { /* - * Remove this CPU. Be a bit slow here and - * set the bits for every online CPU so we don't miss - * any IPI whilst taking this VPE down. + * Remove this CPU: */ - cpumask_copy(&cpu_foreign_map, cpu_online_mask); - - /* Make it visible to every other CPU */ - smp_mb(); - set_cpu_online(smp_processor_id(), false); calculate_cpu_foreign_map(); local_irq_disable(); @@ -512,10 +507,17 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned l smp_on_other_tlbs(flush_tlb_range_ipi, &fd); } else { unsigned int cpu; + int exec = vma->vm_flags & VM_EXEC; for_each_online_cpu(cpu) { + /* + * flush_cache_range() will only fully flush icache if + * the VMA is executable, otherwise we must invalidate + * ASID without it appearing to has_valid_asid() as if + * mm has been completely unused by that CPU. + */ if (cpu != smp_processor_id() && cpu_context(cpu, mm)) - cpu_context(cpu, mm) = 0; + cpu_context(cpu, mm) = !exec; } } local_flush_tlb_range(vma, start, end); @@ -560,8 +562,14 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page) unsigned int cpu; for_each_online_cpu(cpu) { + /* + * flush_cache_page() only does partial flushes, so + * invalidate ASID without it appearing to + * has_valid_asid() as if mm has been completely unused + * by that CPU. + */ if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm)) - cpu_context(cpu, vma->vm_mm) = 0; + cpu_context(cpu, vma->vm_mm) = 1; } } local_flush_tlb_page(vma, page); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 6fb4704bd156..3de85be2486a 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -704,6 +704,7 @@ asmlinkage void do_ov(struct pt_regs *regs) int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) { struct siginfo si = { 0 }; + struct vm_area_struct *vma; switch (sig) { case 0: @@ -744,7 +745,8 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) si.si_addr = fault_addr; si.si_signo = sig; down_read(¤t->mm->mmap_sem); - if (find_vma(current->mm, (unsigned long)fault_addr)) + vma = find_vma(current->mm, (unsigned long)fault_addr); + if (vma && (vma->vm_start <= (unsigned long)fault_addr)) si.si_code = SEGV_ACCERR; else si.si_code = SEGV_MAPERR; diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 28b3af73a17b..f1c308dbbc4a 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -1025,7 +1025,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, if (!access_ok(VERIFY_READ, addr, 2)) goto sigbus; - if (config_enabled(CONFIG_EVA)) { + if (IS_ENABLED(CONFIG_EVA)) { if (segment_eq(get_fs(), get_ds())) LoadHW(addr, value, res); else @@ -1044,7 +1044,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, if (!access_ok(VERIFY_READ, addr, 4)) goto sigbus; - if (config_enabled(CONFIG_EVA)) { + if (IS_ENABLED(CONFIG_EVA)) { if (segment_eq(get_fs(), get_ds())) LoadW(addr, value, res); else @@ -1063,7 +1063,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, if (!access_ok(VERIFY_READ, addr, 2)) goto sigbus; - if (config_enabled(CONFIG_EVA)) { + if (IS_ENABLED(CONFIG_EVA)) { if (segment_eq(get_fs(), get_ds())) LoadHWU(addr, value, res); else @@ -1131,7 +1131,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, compute_return_epc(regs); value = regs->regs[insn.i_format.rt]; - if (config_enabled(CONFIG_EVA)) { + if (IS_ENABLED(CONFIG_EVA)) { if (segment_eq(get_fs(), get_ds())) StoreHW(addr, value, res); else @@ -1151,7 +1151,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, compute_return_epc(regs); value = regs->regs[insn.i_format.rt]; - if (config_enabled(CONFIG_EVA)) { + if (IS_ENABLED(CONFIG_EVA)) { if (segment_eq(get_fs(), get_ds())) StoreW(addr, value, res); else diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 54e1663ce639..9abe447a4b48 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -107,6 +107,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (down_write_killable(&mm->mmap_sem)) return -EINTR; + /* Map delay slot emulation page */ + base = mmap_region(NULL, STACK_TOP, PAGE_SIZE, + VM_READ|VM_WRITE|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + 0); + if (IS_ERR_VALUE(base)) { + ret = base; + goto out; + } + /* * Determine total area size. This includes the VDSO data itself, the * data page, and the GIC user page if present. Always create a mapping diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 6eb52b9c9818..e788515f766b 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1642,8 +1642,14 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, preempt_disable(); if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - if (kvm_mips_host_tlb_lookup(vcpu, va) < 0) - kvm_mips_handle_kseg0_tlb_fault(va, vcpu); + if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 && + kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) { + kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n", + __func__, va, vcpu, read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; + } } else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) || KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { int index; @@ -1680,12 +1686,18 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, run, vcpu); preempt_enable(); goto dont_update_pc; - } else { - /* - * We fault an entry from the guest tlb to the - * shadow host TLB - */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + } + /* + * We fault an entry from the guest tlb to the + * shadow host TLB + */ + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; } } } else { @@ -2659,7 +2671,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, * OK we have a Guest TLB entry, now inject it into the * shadow host TLB */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + } } } diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 57319ee57c4f..6cfdcf55572d 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -99,7 +99,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, } gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT); - if (gfn >= kvm->arch.guest_pmap_npages) { + if ((gfn | 1) >= kvm->arch.guest_pmap_npages) { kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__, gfn, badvaddr); kvm_mips_dump_host_tlbs(); @@ -138,35 +138,49 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; kvm_pfn_t pfn0, pfn1; + gfn_t gfn0, gfn1; + long tlb_lo[2]; int ret; - if ((tlb->tlb_hi & VPN2_MASK) == 0) { - pfn0 = 0; - pfn1 = 0; - } else { - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) - >> PAGE_SHIFT) < 0) - return -1; - - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) - >> PAGE_SHIFT) < 0) - return -1; - - pfn0 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT]; - pfn1 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT]; + tlb_lo[0] = tlb->tlb_lo[0]; + tlb_lo[1] = tlb->tlb_lo[1]; + + /* + * The commpage address must not be mapped to anything else if the guest + * TLB contains entries nearby, or commpage accesses will break. + */ + if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) & + VPN2_MASK & (PAGE_MASK << 1))) + tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0; + + gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT; + gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT; + if (gfn0 >= kvm->arch.guest_pmap_npages || + gfn1 >= kvm->arch.guest_pmap_npages) { + kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n", + __func__, gfn0, gfn1, tlb->tlb_hi); + kvm_mips_dump_guest_tlbs(vcpu); + return -1; } + if (kvm_mips_map_page(kvm, gfn0) < 0) + return -1; + + if (kvm_mips_map_page(kvm, gfn1) < 0) + return -1; + + pfn0 = kvm->arch.guest_pmap[gfn0]; + pfn1 = kvm->arch.guest_pmap[gfn1]; + /* Get attributes from the Guest TLB */ entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[0] & ENTRYLO_D) | - (tlb->tlb_lo[0] & ENTRYLO_V); + (tlb_lo[0] & ENTRYLO_D) | + (tlb_lo[0] & ENTRYLO_V); entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[1] & ENTRYLO_D) | - (tlb->tlb_lo[1] & ENTRYLO_V); + (tlb_lo[1] & ENTRYLO_D) | + (tlb_lo[1] & ENTRYLO_V); kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc, tlb->tlb_lo[0], tlb->tlb_lo[1]); @@ -354,9 +368,15 @@ u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu) local_irq_restore(flags); return KVM_INVALID_INST; } - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, - &vcpu->arch. - guest_tlb[index]); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, + &vcpu->arch.guest_tlb[index])) { + kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, opc, index, vcpu, + read_c0_entryhi()); + kvm_mips_dump_guest_tlbs(vcpu); + local_irq_restore(flags); + return KVM_INVALID_INST; + } inst = *(opc); } local_irq_restore(flags); diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index ff17669e30a3..8ac0e5994ed2 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -66,7 +66,7 @@ int gic_present; #endif static int exin_avail; -static struct resource ltq_eiu_irq[MAX_EIU]; +static u32 ltq_eiu_irq[MAX_EIU]; static void __iomem *ltq_icu_membase[MAX_IM]; static void __iomem *ltq_eiu_membase; static struct irq_domain *ltq_domain; @@ -75,7 +75,7 @@ static int ltq_perfcount_irq; int ltq_eiu_get_irq(int exin) { if (exin < exin_avail) - return ltq_eiu_irq[exin].start; + return ltq_eiu_irq[exin]; return -1; } @@ -125,8 +125,8 @@ static int ltq_eiu_settype(struct irq_data *d, unsigned int type) { int i; - for (i = 0; i < MAX_EIU; i++) { - if (d->hwirq == ltq_eiu_irq[i].start) { + for (i = 0; i < exin_avail; i++) { + if (d->hwirq == ltq_eiu_irq[i]) { int val = 0; int edge = 0; @@ -173,8 +173,8 @@ static unsigned int ltq_startup_eiu_irq(struct irq_data *d) int i; ltq_enable_irq(d); - for (i = 0; i < MAX_EIU; i++) { - if (d->hwirq == ltq_eiu_irq[i].start) { + for (i = 0; i < exin_avail; i++) { + if (d->hwirq == ltq_eiu_irq[i]) { /* by default we are low level triggered */ ltq_eiu_settype(d, IRQF_TRIGGER_LOW); /* clear all pending */ @@ -195,8 +195,8 @@ static void ltq_shutdown_eiu_irq(struct irq_data *d) int i; ltq_disable_irq(d); - for (i = 0; i < MAX_EIU; i++) { - if (d->hwirq == ltq_eiu_irq[i].start) { + for (i = 0; i < exin_avail; i++) { + if (d->hwirq == ltq_eiu_irq[i]) { /* disable */ ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_INEN) & ~BIT(i), LTQ_EIU_EXIN_INEN); @@ -206,7 +206,7 @@ static void ltq_shutdown_eiu_irq(struct irq_data *d) } static struct irq_chip ltq_irq_type = { - "icu", + .name = "icu", .irq_enable = ltq_enable_irq, .irq_disable = ltq_disable_irq, .irq_unmask = ltq_enable_irq, @@ -216,7 +216,7 @@ static struct irq_chip ltq_irq_type = { }; static struct irq_chip ltq_eiu_type = { - "eiu", + .name = "eiu", .irq_startup = ltq_startup_eiu_irq, .irq_shutdown = ltq_shutdown_eiu_irq, .irq_enable = ltq_enable_irq, @@ -341,10 +341,10 @@ static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) return 0; for (i = 0; i < exin_avail; i++) - if (hw == ltq_eiu_irq[i].start) + if (hw == ltq_eiu_irq[i]) chip = <q_eiu_type; - irq_set_chip_and_handler(hw, chip, handle_level_irq); + irq_set_chip_and_handler(irq, chip, handle_level_irq); return 0; } @@ -439,14 +439,15 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent) eiu_node = of_find_compatible_node(NULL, NULL, "lantiq,eiu-xway"); if (eiu_node && !of_address_to_resource(eiu_node, 0, &res)) { /* find out how many external irq sources we have */ - exin_avail = of_irq_count(eiu_node); + exin_avail = of_property_count_u32_elems(eiu_node, + "lantiq,eiu-irqs"); if (exin_avail > MAX_EIU) exin_avail = MAX_EIU; - ret = of_irq_to_resource_table(eiu_node, + ret = of_property_read_u32_array(eiu_node, "lantiq,eiu-irqs", ltq_eiu_irq, exin_avail); - if (ret != exin_avail) + if (ret) panic("failed to load external irq resources"); if (!request_mem_region(res.start, resource_size(&res), diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index 5f693ac77a0d..4cbb000e778e 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -74,8 +74,8 @@ void __init plat_mem_setup(void) set_io_port_base((unsigned long) KSEG1); - if (fw_arg0 == -2) /* UHI interface */ - dtb = (void *)fw_arg1; + if (fw_passed_dtb) /* UHI interface */ + dtb = (void *)fw_passed_dtb; else if (__dtb_start != __dtb_end) dtb = (void *)__dtb_start; else diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c index 4ffa6fc81c8f..1a80b6f73ab2 100644 --- a/arch/mips/loongson64/common/dma-swiotlb.c +++ b/arch/mips/loongson64/common/dma-swiotlb.c @@ -10,7 +10,7 @@ #include <dma-coherence.h> static void *loongson_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; @@ -41,7 +41,7 @@ static void *loongson_dma_alloc_coherent(struct device *dev, size_t size, } static void loongson_dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs) + void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_handle); } @@ -49,7 +49,7 @@ static void loongson_dma_free_coherent(struct device *dev, size_t size, static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size, dir, attrs); @@ -59,9 +59,9 @@ static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page, static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { - int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, NULL); + int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, 0); mb(); return r; diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c index 249039af66c4..4788bea62a6a 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/loongson-3/hpet.c @@ -13,8 +13,8 @@ #define SMBUS_PCI_REG64 0x64 #define SMBUS_PCI_REGB4 0xb4 -#define HPET_MIN_CYCLES 64 -#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) +#define HPET_MIN_CYCLES 16 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES * 12) static DEFINE_SPINLOCK(hpet_lock); DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device); @@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt) static int hpet_next_event(unsigned long delta, struct clock_event_device *evt) { - unsigned int cnt; - int res; + u32 cnt; + s32 res; cnt = hpet_read(HPET_COUNTER); - cnt += delta; + cnt += (u32) delta; hpet_write(HPET_T0_CMP, cnt); - res = (int)(cnt - hpet_read(HPET_COUNTER)); + res = (s32)(cnt - hpet_read(HPET_COUNTER)); return res < HPET_MIN_CYCLES ? -ETIME : 0; } @@ -230,7 +230,7 @@ void __init setup_hpet_timer(void) cd = &per_cpu(hpet_clockevent_device, cpu); cd->name = "hpet"; - cd->rating = 320; + cd->rating = 100; cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; cd->set_state_shutdown = hpet_set_state_shutdown; cd->set_state_periodic = hpet_set_state_periodic; diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index e59759af63d9..2fec6f753a35 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -417,6 +417,7 @@ static int loongson3_cpu_disable(void) return -EBUSY; set_cpu_online(cpu, false); + calculate_cpu_foreign_map(); cpumask_clear_cpu(cpu, &cpu_callin_map); local_irq_save(flags); fixup_irqs(); diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 6dc07fba187f..36775d20b0e7 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -434,8 +434,8 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr) * a single subroutine should be used across both * modules. */ -static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, - unsigned long *contpc) +int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc) { union mips_instruction insn = (union mips_instruction)dec_insn.insn; unsigned int fcr31; @@ -784,10 +784,10 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, */ static inline int cop1_64bit(struct pt_regs *xcp) { - if (config_enabled(CONFIG_64BIT) && !config_enabled(CONFIG_MIPS32_O32)) + if (IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_MIPS32_O32)) return 1; - else if (config_enabled(CONFIG_32BIT) && - !config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) + else if (IS_ENABLED(CONFIG_32BIT) && + !IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT)) return 0; return !test_thread_flag(TIF_32BIT_FPREGS); @@ -1268,7 +1268,7 @@ branch_common: * instruction in the dslot. */ sig = mips_dsemul(xcp, ir, - contpc); + bcpc, contpc); if (sig < 0) break; if (sig) @@ -1323,7 +1323,7 @@ branch_common: * Single step the non-cp1 * instruction in the dslot */ - sig = mips_dsemul(xcp, ir, contpc); + sig = mips_dsemul(xcp, ir, bcpc, contpc); if (sig < 0) break; if (sig) diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c index 47074887e64c..72a4642eee2c 100644 --- a/arch/mips/math-emu/dsemul.c +++ b/arch/mips/math-emu/dsemul.c @@ -1,3 +1,6 @@ +#include <linux/err.h> +#include <linux/slab.h> + #include <asm/branch.h> #include <asm/cacheflush.h> #include <asm/fpu_emulator.h> @@ -5,43 +8,211 @@ #include <asm/mipsregs.h> #include <asm/uaccess.h> -#include "ieee754.h" - -/* - * Emulate the arbitrary instruction ir at xcp->cp0_epc. Required when - * we have to emulate the instruction in a COP1 branch delay slot. Do - * not change cp0_epc due to the instruction +/** + * struct emuframe - The 'emulation' frame structure + * @emul: The instruction to 'emulate'. + * @badinst: A break instruction to cause a return to the kernel. * - * According to the spec: - * 1) it shouldn't be a branch :-) - * 2) it can be a COP instruction :-( - * 3) if we are tring to run a protected memory space we must take - * special care on memory access instructions :-( - */ - -/* - * "Trampoline" return routine to catch exception following - * execution of delay-slot instruction execution. + * This structure defines the frames placed within the delay slot emulation + * page in response to a call to mips_dsemul(). Each thread may be allocated + * only one frame at any given time. The kernel stores within it the + * instruction to be 'emulated' followed by a break instruction, then + * executes the frame in user mode. The break causes a trap to the kernel + * which leads to do_dsemulret() being called unless the instruction in + * @emul causes a trap itself, is a branch, or a signal is delivered to + * the thread. In these cases the allocated frame will either be reused by + * a subsequent delay slot 'emulation', or be freed during signal delivery or + * upon thread exit. + * + * This approach is used because: + * + * - Actually emulating all instructions isn't feasible. We would need to + * be able to handle instructions from all revisions of the MIPS ISA, + * all ASEs & all vendor instruction set extensions. This would be a + * whole lot of work & continual maintenance burden as new instructions + * are introduced, and in the case of some vendor extensions may not + * even be possible. Thus we need to take the approach of actually + * executing the instruction. + * + * - We must execute the instruction within user context. If we were to + * execute the instruction in kernel mode then it would have access to + * kernel resources without very careful checks, leaving us with a + * high potential for security or stability issues to arise. + * + * - We used to place the frame on the users stack, but this requires + * that the stack be executable. This is bad for security so the + * per-process page is now used instead. + * + * - The instruction in @emul may be something entirely invalid for a + * delay slot. The user may (intentionally or otherwise) place a branch + * in a delay slot, or a kernel mode instruction, or something else + * which generates an exception. Thus we can't rely upon the break in + * @badinst always being hit. For this reason we track the index of the + * frame allocated to each thread, allowing us to clean it up at later + * points such as signal delivery or thread exit. + * + * - The user may generate a fake struct emuframe if they wish, invoking + * the BRK_MEMU break instruction themselves. We must therefore not + * trust that BRK_MEMU means there's actually a valid frame allocated + * to the thread, and must not allow the user to do anything they + * couldn't already. */ - struct emuframe { mips_instruction emul; mips_instruction badinst; - mips_instruction cookie; - unsigned long epc; }; -/* - * Set up an emulation frame for instruction IR, from a delay slot of - * a branch jumping to CPC. Return 0 if successful, -1 if no emulation - * required, otherwise a signal number causing a frame setup failure. - */ -int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) +static const int emupage_frame_count = PAGE_SIZE / sizeof(struct emuframe); + +static inline __user struct emuframe *dsemul_page(void) +{ + return (__user struct emuframe *)STACK_TOP; +} + +static int alloc_emuframe(void) +{ + mm_context_t *mm_ctx = ¤t->mm->context; + int idx; + +retry: + spin_lock(&mm_ctx->bd_emupage_lock); + + /* Ensure we have an allocation bitmap */ + if (!mm_ctx->bd_emupage_allocmap) { + mm_ctx->bd_emupage_allocmap = + kcalloc(BITS_TO_LONGS(emupage_frame_count), + sizeof(unsigned long), + GFP_ATOMIC); + + if (!mm_ctx->bd_emupage_allocmap) { + idx = BD_EMUFRAME_NONE; + goto out_unlock; + } + } + + /* Attempt to allocate a single bit/frame */ + idx = bitmap_find_free_region(mm_ctx->bd_emupage_allocmap, + emupage_frame_count, 0); + if (idx < 0) { + /* + * Failed to allocate a frame. We'll wait until one becomes + * available. We unlock the page so that other threads actually + * get the opportunity to free their frames, which means + * technically the result of bitmap_full may be incorrect. + * However the worst case is that we repeat all this and end up + * back here again. + */ + spin_unlock(&mm_ctx->bd_emupage_lock); + if (!wait_event_killable(mm_ctx->bd_emupage_queue, + !bitmap_full(mm_ctx->bd_emupage_allocmap, + emupage_frame_count))) + goto retry; + + /* Received a fatal signal - just give in */ + return BD_EMUFRAME_NONE; + } + + /* Success! */ + pr_debug("allocate emuframe %d to %d\n", idx, current->pid); +out_unlock: + spin_unlock(&mm_ctx->bd_emupage_lock); + return idx; +} + +static void free_emuframe(int idx, struct mm_struct *mm) +{ + mm_context_t *mm_ctx = &mm->context; + + spin_lock(&mm_ctx->bd_emupage_lock); + + pr_debug("free emuframe %d from %d\n", idx, current->pid); + bitmap_clear(mm_ctx->bd_emupage_allocmap, idx, 1); + + /* If some thread is waiting for a frame, now's its chance */ + wake_up(&mm_ctx->bd_emupage_queue); + + spin_unlock(&mm_ctx->bd_emupage_lock); +} + +static bool within_emuframe(struct pt_regs *regs) +{ + unsigned long base = (unsigned long)dsemul_page(); + + if (regs->cp0_epc < base) + return false; + if (regs->cp0_epc >= (base + PAGE_SIZE)) + return false; + + return true; +} + +bool dsemul_thread_cleanup(struct task_struct *tsk) +{ + int fr_idx; + + /* Clear any allocated frame, retrieving its index */ + fr_idx = atomic_xchg(&tsk->thread.bd_emu_frame, BD_EMUFRAME_NONE); + + /* If no frame was allocated, we're done */ + if (fr_idx == BD_EMUFRAME_NONE) + return false; + + task_lock(tsk); + + /* Free the frame that this thread had allocated */ + if (tsk->mm) + free_emuframe(fr_idx, tsk->mm); + + task_unlock(tsk); + return true; +} + +bool dsemul_thread_rollback(struct pt_regs *regs) +{ + struct emuframe __user *fr; + int fr_idx; + + /* Do nothing if we're not executing from a frame */ + if (!within_emuframe(regs)) + return false; + + /* Find the frame being executed */ + fr_idx = atomic_read(¤t->thread.bd_emu_frame); + if (fr_idx == BD_EMUFRAME_NONE) + return false; + fr = &dsemul_page()[fr_idx]; + + /* + * If the PC is at the emul instruction, roll back to the branch. If + * PC is at the badinst (break) instruction, we've already emulated the + * instruction so progress to the continue PC. If it's anything else + * then something is amiss & the user has branched into some other area + * of the emupage - we'll free the allocated frame anyway. + */ + if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->emul) + regs->cp0_epc = current->thread.bd_emu_branch_pc; + else if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->badinst) + regs->cp0_epc = current->thread.bd_emu_cont_pc; + + atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); + free_emuframe(fr_idx, current->mm); + return true; +} + +void dsemul_mm_cleanup(struct mm_struct *mm) +{ + mm_context_t *mm_ctx = &mm->context; + + kfree(mm_ctx->bd_emupage_allocmap); +} + +int mips_dsemul(struct pt_regs *regs, mips_instruction ir, + unsigned long branch_pc, unsigned long cont_pc) { int isa16 = get_isa16_mode(regs->cp0_epc); mips_instruction break_math; struct emuframe __user *fr; - int err; + int err, fr_idx; /* NOP is easy */ if (ir == 0) @@ -68,30 +239,20 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) } } - pr_debug("dsemul %lx %lx\n", regs->cp0_epc, cpc); + pr_debug("dsemul 0x%08lx cont at 0x%08lx\n", regs->cp0_epc, cont_pc); - /* - * The strategy is to push the instruction onto the user stack - * and put a trap after it which we can catch and jump to - * the required address any alternative apart from full - * instruction emulation!!. - * - * Algorithmics used a system call instruction, and - * borrowed that vector. MIPS/Linux version is a bit - * more heavyweight in the interests of portability and - * multiprocessor support. For Linux we use a BREAK 514 - * instruction causing a breakpoint exception. - */ - break_math = BREAK_MATH(isa16); - - /* Ensure that the two instructions are in the same cache line */ - fr = (struct emuframe __user *) - ((regs->regs[29] - sizeof(struct emuframe)) & ~0x7); - - /* Verify that the stack pointer is not completely insane */ - if (unlikely(!access_ok(VERIFY_WRITE, fr, sizeof(struct emuframe)))) + /* Allocate a frame if we don't already have one */ + fr_idx = atomic_read(¤t->thread.bd_emu_frame); + if (fr_idx == BD_EMUFRAME_NONE) + fr_idx = alloc_emuframe(); + if (fr_idx == BD_EMUFRAME_NONE) return SIGBUS; + fr = &dsemul_page()[fr_idx]; + + /* Retrieve the appropriately encoded break instruction */ + break_math = BREAK_MATH(isa16); + /* Write the instructions to the frame */ if (isa16) { err = __put_user(ir >> 16, (u16 __user *)(&fr->emul)); @@ -106,84 +267,36 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) err |= __put_user(break_math, &fr->badinst); } - err |= __put_user((mips_instruction)BD_COOKIE, &fr->cookie); - err |= __put_user(cpc, &fr->epc); - if (unlikely(err)) { MIPS_FPU_EMU_INC_STATS(errors); + free_emuframe(fr_idx, current->mm); return SIGBUS; } + /* Record the PC of the branch, PC to continue from & frame index */ + current->thread.bd_emu_branch_pc = branch_pc; + current->thread.bd_emu_cont_pc = cont_pc; + atomic_set(¤t->thread.bd_emu_frame, fr_idx); + + /* Change user register context to execute the frame */ regs->cp0_epc = (unsigned long)&fr->emul | isa16; + /* Ensure the icache observes our newly written frame */ flush_cache_sigtramp((unsigned long)&fr->emul); return 0; } -int do_dsemulret(struct pt_regs *xcp) +bool do_dsemulret(struct pt_regs *xcp) { - int isa16 = get_isa16_mode(xcp->cp0_epc); - struct emuframe __user *fr; - unsigned long epc; - u32 insn, cookie; - int err = 0; - u16 instr[2]; - - fr = (struct emuframe __user *) - (msk_isa16_mode(xcp->cp0_epc) - sizeof(mips_instruction)); - - /* - * If we can't even access the area, something is very wrong, but we'll - * leave that to the default handling - */ - if (!access_ok(VERIFY_READ, fr, sizeof(struct emuframe))) - return 0; - - /* - * Do some sanity checking on the stackframe: - * - * - Is the instruction pointed to by the EPC an BREAK_MATH? - * - Is the following memory word the BD_COOKIE? - */ - if (isa16) { - err = __get_user(instr[0], - (u16 __user *)(&fr->badinst)); - err |= __get_user(instr[1], - (u16 __user *)((long)(&fr->badinst) + 2)); - insn = (instr[0] << 16) | instr[1]; - } else { - err = __get_user(insn, &fr->badinst); - } - err |= __get_user(cookie, &fr->cookie); - - if (unlikely(err || - insn != BREAK_MATH(isa16) || cookie != BD_COOKIE)) { + /* Cleanup the allocated frame, returning if there wasn't one */ + if (!dsemul_thread_cleanup(current)) { MIPS_FPU_EMU_INC_STATS(errors); - return 0; - } - - /* - * At this point, we are satisfied that it's a BD emulation trap. Yes, - * a user might have deliberately put two malformed and useless - * instructions in a row in his program, in which case he's in for a - * nasty surprise - the next instruction will be treated as a - * continuation address! Alas, this seems to be the only way that we - * can handle signals, recursion, and longjmps() in the context of - * emulating the branch delay instruction. - */ - - pr_debug("dsemulret\n"); - - if (__get_user(epc, &fr->epc)) { /* Saved EPC */ - /* This is not a good situation to be in */ - force_sig(SIGBUS, current); - - return 0; + return false; } /* Set EPC to return to post-branch instruction */ - xcp->cp0_epc = epc; - MIPS_FPU_EMU_INC_STATS(ds_emul); - return 1; + xcp->cp0_epc = current->thread.bd_emu_cont_pc; + pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc); + return true; } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 7a9c345e87e5..cd72805b64a7 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -40,6 +40,51 @@ #include <asm/mips-cm.h> /* + * Bits describing what cache ops an SMP callback function may perform. + * + * R4K_HIT - Virtual user or kernel address based cache operations. The + * active_mm must be checked before using user addresses, falling + * back to kmap. + * R4K_INDEX - Index based cache operations. + */ + +#define R4K_HIT BIT(0) +#define R4K_INDEX BIT(1) + +/** + * r4k_op_needs_ipi() - Decide if a cache op needs to be done on every core. + * @type: Type of cache operations (R4K_HIT or R4K_INDEX). + * + * Decides whether a cache op needs to be performed on every core in the system. + * This may change depending on the @type of cache operation, as well as the set + * of online CPUs, so preemption should be disabled by the caller to prevent CPU + * hotplug from changing the result. + * + * Returns: 1 if the cache operation @type should be done on every core in + * the system. + * 0 if the cache operation @type is globalized and only needs to + * be performed on a simple CPU. + */ +static inline bool r4k_op_needs_ipi(unsigned int type) +{ + /* The MIPS Coherence Manager (CM) globalizes address-based cache ops */ + if (type == R4K_HIT && mips_cm_present()) + return false; + + /* + * Hardware doesn't globalize the required cache ops, so SMP calls may + * be needed, but only if there are foreign CPUs (non-siblings with + * separate caches). + */ + /* cpu_foreign_map[] undeclared when !CONFIG_SMP */ +#ifdef CONFIG_SMP + return !cpumask_empty(&cpu_foreign_map[0]); +#else + return false; +#endif +} + +/* * Special Variant of smp_call_function for use by cache functions: * * o No return value @@ -48,30 +93,17 @@ * primary cache. * o doesn't disable interrupts on the local CPU */ -static inline void r4k_on_each_cpu(void (*func) (void *info), void *info) +static inline void r4k_on_each_cpu(unsigned int type, + void (*func)(void *info), void *info) { preempt_disable(); - - /* - * The Coherent Manager propagates address-based cache ops to other - * cores but not index-based ops. However, r4k_on_each_cpu is used - * in both cases so there is no easy way to tell what kind of op is - * executed to the other cores. The best we can probably do is - * to restrict that call when a CM is not present because both - * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops. - */ - if (!mips_cm_present()) - smp_call_function_many(&cpu_foreign_map, func, info, 1); + if (r4k_op_needs_ipi(type)) + smp_call_function_many(&cpu_foreign_map[smp_processor_id()], + func, info, 1); func(info); preempt_enable(); } -#if defined(CONFIG_MIPS_CMP) || defined(CONFIG_MIPS_CPS) -#define cpu_has_safe_index_cacheops 0 -#else -#define cpu_has_safe_index_cacheops 1 -#endif - /* * Must die. */ @@ -462,22 +494,44 @@ static inline void local_r4k___flush_cache_all(void * args) static void r4k___flush_cache_all(void) { - r4k_on_each_cpu(local_r4k___flush_cache_all, NULL); + r4k_on_each_cpu(R4K_INDEX, local_r4k___flush_cache_all, NULL); } -static inline int has_valid_asid(const struct mm_struct *mm) +/** + * has_valid_asid() - Determine if an mm already has an ASID. + * @mm: Memory map. + * @type: R4K_HIT or R4K_INDEX, type of cache op. + * + * Determines whether @mm already has an ASID on any of the CPUs which cache ops + * of type @type within an r4k_on_each_cpu() call will affect. If + * r4k_on_each_cpu() does an SMP call to a single VPE in each core, then the + * scope of the operation is confined to sibling CPUs, otherwise all online CPUs + * will need to be checked. + * + * Must be called in non-preemptive context. + * + * Returns: 1 if the CPUs affected by @type cache ops have an ASID for @mm. + * 0 otherwise. + */ +static inline int has_valid_asid(const struct mm_struct *mm, unsigned int type) { -#ifdef CONFIG_MIPS_MT_SMP - int i; + unsigned int i; + const cpumask_t *mask = cpu_present_mask; - for_each_online_cpu(i) + /* cpu_sibling_map[] undeclared when !CONFIG_SMP */ +#ifdef CONFIG_SMP + /* + * If r4k_on_each_cpu does SMP calls, it does them to a single VPE in + * each foreign core, so we only need to worry about siblings. + * Otherwise we need to worry about all present CPUs. + */ + if (r4k_op_needs_ipi(type)) + mask = &cpu_sibling_map[smp_processor_id()]; +#endif + for_each_cpu(i, mask) if (cpu_context(i, mm)) return 1; - return 0; -#else - return cpu_context(smp_processor_id(), mm); -#endif } static void r4k__flush_cache_vmap(void) @@ -490,12 +544,16 @@ static void r4k__flush_cache_vunmap(void) r4k_blast_dcache(); } +/* + * Note: flush_tlb_range() assumes flush_cache_range() sufficiently flushes + * whole caches when vma is executable. + */ static inline void local_r4k_flush_cache_range(void * args) { struct vm_area_struct *vma = args; int exec = vma->vm_flags & VM_EXEC; - if (!(has_valid_asid(vma->vm_mm))) + if (!has_valid_asid(vma->vm_mm, R4K_INDEX)) return; /* @@ -516,14 +574,14 @@ static void r4k_flush_cache_range(struct vm_area_struct *vma, int exec = vma->vm_flags & VM_EXEC; if (cpu_has_dc_aliases || exec) - r4k_on_each_cpu(local_r4k_flush_cache_range, vma); + r4k_on_each_cpu(R4K_INDEX, local_r4k_flush_cache_range, vma); } static inline void local_r4k_flush_cache_mm(void * args) { struct mm_struct *mm = args; - if (!has_valid_asid(mm)) + if (!has_valid_asid(mm, R4K_INDEX)) return; /* @@ -548,7 +606,7 @@ static void r4k_flush_cache_mm(struct mm_struct *mm) if (!cpu_has_dc_aliases) return; - r4k_on_each_cpu(local_r4k_flush_cache_mm, mm); + r4k_on_each_cpu(R4K_INDEX, local_r4k_flush_cache_mm, mm); } struct flush_cache_page_args { @@ -573,10 +631,10 @@ static inline void local_r4k_flush_cache_page(void *args) void *vaddr; /* - * If ownes no valid ASID yet, cannot possibly have gotten + * If owns no valid ASID yet, cannot possibly have gotten * this page into the cache. */ - if (!has_valid_asid(mm)) + if (!has_valid_asid(mm, R4K_HIT)) return; addr &= PAGE_MASK; @@ -643,7 +701,7 @@ static void r4k_flush_cache_page(struct vm_area_struct *vma, args.addr = addr; args.pfn = pfn; - r4k_on_each_cpu(local_r4k_flush_cache_page, &args); + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_cache_page, &args); } static inline void local_r4k_flush_data_cache_page(void * addr) @@ -656,18 +714,23 @@ static void r4k_flush_data_cache_page(unsigned long addr) if (in_atomic()) local_r4k_flush_data_cache_page((void *)addr); else - r4k_on_each_cpu(local_r4k_flush_data_cache_page, (void *) addr); + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_data_cache_page, + (void *) addr); } struct flush_icache_range_args { unsigned long start; unsigned long end; + unsigned int type; }; -static inline void local_r4k_flush_icache_range(unsigned long start, unsigned long end) +static inline void __local_r4k_flush_icache_range(unsigned long start, + unsigned long end, + unsigned int type) { if (!cpu_has_ic_fills_f_dc) { - if (end - start >= dcache_size) { + if (type == R4K_INDEX || + (type & R4K_INDEX && end - start >= dcache_size)) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; @@ -675,7 +738,8 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo } } - if (end - start > icache_size) + if (type == R4K_INDEX || + (type & R4K_INDEX && end - start > icache_size)) r4k_blast_icache(); else { switch (boot_cpu_type()) { @@ -701,23 +765,52 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo #endif } +static inline void local_r4k_flush_icache_range(unsigned long start, + unsigned long end) +{ + __local_r4k_flush_icache_range(start, end, R4K_HIT | R4K_INDEX); +} + static inline void local_r4k_flush_icache_range_ipi(void *args) { struct flush_icache_range_args *fir_args = args; unsigned long start = fir_args->start; unsigned long end = fir_args->end; + unsigned int type = fir_args->type; - local_r4k_flush_icache_range(start, end); + __local_r4k_flush_icache_range(start, end, type); } static void r4k_flush_icache_range(unsigned long start, unsigned long end) { struct flush_icache_range_args args; + unsigned long size, cache_size; args.start = start; args.end = end; + args.type = R4K_HIT | R4K_INDEX; - r4k_on_each_cpu(local_r4k_flush_icache_range_ipi, &args); + /* + * Indexed cache ops require an SMP call. + * Consider if that can or should be avoided. + */ + preempt_disable(); + if (r4k_op_needs_ipi(R4K_INDEX) && !r4k_op_needs_ipi(R4K_HIT)) { + /* + * If address-based cache ops don't require an SMP call, then + * use them exclusively for small flushes. + */ + size = start - end; + cache_size = icache_size; + if (!cpu_has_ic_fills_f_dc) { + size *= 2; + cache_size += dcache_size; + } + if (size <= cache_size) + args.type &= ~R4K_INDEX; + } + r4k_on_each_cpu(args.type, local_r4k_flush_icache_range_ipi, &args); + preempt_enable(); instruction_hazard(); } @@ -744,7 +837,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) * subset property so we have to flush the primary caches * explicitly */ - if (cpu_has_safe_index_cacheops && size >= dcache_size) { + if (size >= dcache_size) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; @@ -781,7 +874,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) return; } - if (cpu_has_safe_index_cacheops && size >= dcache_size) { + if (size >= dcache_size) { r4k_blast_dcache(); } else { R4600_HIT_CACHEOP_WAR_IMPL; @@ -794,25 +887,76 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) } #endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */ +struct flush_cache_sigtramp_args { + struct mm_struct *mm; + struct page *page; + unsigned long addr; +}; + /* * While we're protected against bad userland addresses we don't care * very much about what happens in that case. Usually a segmentation * fault will dump the process later on anyway ... */ -static void local_r4k_flush_cache_sigtramp(void * arg) +static void local_r4k_flush_cache_sigtramp(void *args) { + struct flush_cache_sigtramp_args *fcs_args = args; + unsigned long addr = fcs_args->addr; + struct page *page = fcs_args->page; + struct mm_struct *mm = fcs_args->mm; + int map_coherent = 0; + void *vaddr; + unsigned long ic_lsize = cpu_icache_line_size(); unsigned long dc_lsize = cpu_dcache_line_size(); unsigned long sc_lsize = cpu_scache_line_size(); - unsigned long addr = (unsigned long) arg; + + /* + * If owns no valid ASID yet, cannot possibly have gotten + * this page into the cache. + */ + if (!has_valid_asid(mm, R4K_HIT)) + return; + + if (mm == current->active_mm) { + vaddr = NULL; + } else { + /* + * Use kmap_coherent or kmap_atomic to do flushes for + * another ASID than the current one. + */ + map_coherent = (cpu_has_dc_aliases && + page_mapcount(page) && + !Page_dcache_dirty(page)); + if (map_coherent) + vaddr = kmap_coherent(page, addr); + else + vaddr = kmap_atomic(page); + addr = (unsigned long)vaddr + (addr & ~PAGE_MASK); + } R4600_HIT_CACHEOP_WAR_IMPL; - if (dc_lsize) - protected_writeback_dcache_line(addr & ~(dc_lsize - 1)); - if (!cpu_icache_snoops_remote_store && scache_size) - protected_writeback_scache_line(addr & ~(sc_lsize - 1)); + if (!cpu_has_ic_fills_f_dc) { + if (dc_lsize) + vaddr ? flush_dcache_line(addr & ~(dc_lsize - 1)) + : protected_writeback_dcache_line( + addr & ~(dc_lsize - 1)); + if (!cpu_icache_snoops_remote_store && scache_size) + vaddr ? flush_scache_line(addr & ~(sc_lsize - 1)) + : protected_writeback_scache_line( + addr & ~(sc_lsize - 1)); + } if (ic_lsize) - protected_flush_icache_line(addr & ~(ic_lsize - 1)); + vaddr ? flush_icache_line(addr & ~(ic_lsize - 1)) + : protected_flush_icache_line(addr & ~(ic_lsize - 1)); + + if (vaddr) { + if (map_coherent) + kunmap_coherent(); + else + kunmap_atomic(vaddr); + } + if (MIPS4K_ICACHE_REFILL_WAR) { __asm__ __volatile__ ( ".set push\n\t" @@ -837,7 +981,23 @@ static void local_r4k_flush_cache_sigtramp(void * arg) static void r4k_flush_cache_sigtramp(unsigned long addr) { - r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, (void *) addr); + struct flush_cache_sigtramp_args args; + int npages; + + down_read(¤t->mm->mmap_sem); + + npages = get_user_pages_fast(addr, 1, 0, &args.page); + if (npages < 1) + goto out; + + args.mm = current->mm; + args.addr = addr; + + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_cache_sigtramp, &args); + + put_page(args.page); +out: + up_read(¤t->mm->mmap_sem); } static void r4k_flush_icache_all(void) @@ -851,6 +1011,15 @@ struct flush_kernel_vmap_range_args { int size; }; +static inline void local_r4k_flush_kernel_vmap_range_index(void *args) +{ + /* + * Aliases only affect the primary caches so don't bother with + * S-caches or T-caches. + */ + r4k_blast_dcache(); +} + static inline void local_r4k_flush_kernel_vmap_range(void *args) { struct flush_kernel_vmap_range_args *vmra = args; @@ -861,12 +1030,8 @@ static inline void local_r4k_flush_kernel_vmap_range(void *args) * Aliases only affect the primary caches so don't bother with * S-caches or T-caches. */ - if (cpu_has_safe_index_cacheops && size >= dcache_size) - r4k_blast_dcache(); - else { - R4600_HIT_CACHEOP_WAR_IMPL; - blast_dcache_range(vaddr, vaddr + size); - } + R4600_HIT_CACHEOP_WAR_IMPL; + blast_dcache_range(vaddr, vaddr + size); } static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size) @@ -876,7 +1041,12 @@ static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size) args.vaddr = (unsigned long) vaddr; args.size = size; - r4k_on_each_cpu(local_r4k_flush_kernel_vmap_range, &args); + if (size >= dcache_size) + r4k_on_each_cpu(R4K_INDEX, + local_r4k_flush_kernel_vmap_range_index, NULL); + else + r4k_on_each_cpu(R4K_HIT, local_r4k_flush_kernel_vmap_range, + &args); } static inline void rm7k_erratum31(void) diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index cb557d28cb21..b2eadd6fa9a1 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -131,7 +131,7 @@ static void *mips_dma_alloc_noncoherent(struct device *dev, size_t size, } static void *mips_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t * dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; struct page *page = NULL; @@ -141,7 +141,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size, * XXX: seems like the coherent and non-coherent implementations could * be consolidated. */ - if (dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) + if (attrs & DMA_ATTR_NON_CONSISTENT) return mips_dma_alloc_noncoherent(dev, size, dma_handle, gfp); gfp = massage_gfp_flags(dev, gfp); @@ -176,13 +176,13 @@ static void mips_dma_free_noncoherent(struct device *dev, size_t size, } static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { unsigned long addr = (unsigned long) vaddr; unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page *page = NULL; - if (dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) { + if (attrs & DMA_ATTR_NON_CONSISTENT) { mips_dma_free_noncoherent(dev, size, vaddr, dma_handle); return; } @@ -200,7 +200,7 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr, static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; @@ -214,7 +214,7 @@ static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma, pfn = page_to_pfn(virt_to_page((void *)addr)); - if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) + if (attrs & DMA_ATTR_WRITE_COMBINE) vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); else vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); @@ -291,7 +291,7 @@ static inline void __dma_sync(struct page *page, } static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction, struct dma_attrs *attrs) + size_t size, enum dma_data_direction direction, unsigned long attrs) { if (cpu_needs_post_dma_flush(dev)) __dma_sync(dma_addr_to_page(dev, dma_addr), @@ -301,7 +301,7 @@ static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, } static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist, - int nents, enum dma_data_direction direction, struct dma_attrs *attrs) + int nents, enum dma_data_direction direction, unsigned long attrs) { int i; struct scatterlist *sg; @@ -322,7 +322,7 @@ static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist, static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { if (!plat_device_is_coherent(dev)) __dma_sync(page, offset, size, direction); @@ -332,7 +332,7 @@ static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page, static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nhwentries, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; struct scatterlist *sg; diff --git a/arch/mips/mm/sc-debugfs.c b/arch/mips/mm/sc-debugfs.c index 5eefe3281b24..01f1154cdb0c 100644 --- a/arch/mips/mm/sc-debugfs.c +++ b/arch/mips/mm/sc-debugfs.c @@ -73,8 +73,8 @@ static int __init sc_debugfs_init(void) file = debugfs_create_file("prefetch", S_IRUGO | S_IWUSR, dir, NULL, &sc_prefetch_fops); - if (IS_ERR(file)) - return PTR_ERR(file); + if (!file) + return -ENOMEM; return 0; } diff --git a/arch/mips/mm/sc-rm7k.c b/arch/mips/mm/sc-rm7k.c index 9ac1efcfbcc7..78f900c59276 100644 --- a/arch/mips/mm/sc-rm7k.c +++ b/arch/mips/mm/sc-rm7k.c @@ -161,7 +161,7 @@ static void rm7k_tc_disable(void) local_irq_save(flags); blast_rm7k_tcache(); clear_c0_config(RM7K_CONF_TE); - local_irq_save(flags); + local_irq_restore(flags); } static void rm7k_sc_disable(void) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 4004b659ce50..55ce39606cb8 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -888,7 +888,7 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, } } if (!did_vmalloc_branch) { - if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) { + if (single_insn_swpd) { uasm_il_b(p, r, label_vmalloc_done); uasm_i_lui(p, ptr, uasm_rel_hi(swpd)); } else { @@ -1025,7 +1025,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep) pte_off_odd += offsetof(pte_t, pte_high); #endif - if (config_enabled(CONFIG_XPA)) { + if (IS_ENABLED(CONFIG_XPA)) { uasm_i_lw(p, tmp, pte_off_even, ptep); /* even pte */ UASM_i_ROTR(p, tmp, tmp, ilog2(_PAGE_GLOBAL)); UASM_i_MTC0(p, tmp, C0_ENTRYLO0); @@ -1643,7 +1643,7 @@ iPTE_SW(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr, unsigned int hwmode = mode & (_PAGE_VALID | _PAGE_DIRTY); unsigned int swmode = mode & ~hwmode; - if (config_enabled(CONFIG_XPA) && !cpu_has_64bits) { + if (IS_ENABLED(CONFIG_XPA) && !cpu_has_64bits) { uasm_i_lui(p, scratch, swmode >> 16); uasm_i_or(p, pte, pte, scratch); BUG_ON(swmode & 0xffff); @@ -2432,7 +2432,7 @@ static void config_htw_params(void) pwsize |= ilog2(PTRS_PER_PMD) << MIPS_PWSIZE_MDW_SHIFT; /* Set pointer size to size of directory pointers */ - if (config_enabled(CONFIG_64BIT)) + if (IS_ENABLED(CONFIG_64BIT)) pwsize |= MIPS_PWSIZE_PS_MASK; /* PTEs may be multiple pointers long (e.g. with XPA) */ pwsize |= ((PTE_T_LOG2 - PGD_T_LOG2) << MIPS_PWSIZE_PTEW_SHIFT) @@ -2448,7 +2448,7 @@ static void config_htw_params(void) * the pwctl fields. */ config = 1 << MIPS_PWCTL_PWEN_SHIFT; - if (config_enabled(CONFIG_64BIT)) + if (IS_ENABLED(CONFIG_64BIT)) config |= MIPS_PWCTL_XU_MASK; write_c0_pwctl(config); pr_info("Hardware Page Table Walker enabled\n"); @@ -2522,7 +2522,7 @@ void build_tlb_refill_handler(void) */ static int run_once = 0; - if (config_enabled(CONFIG_XPA) && !cpu_has_rixi) + if (IS_ENABLED(CONFIG_XPA) && !cpu_has_rixi) panic("Kernels supporting XPA currently require CPUs with RIXI"); output_pgtable_bits_defines(); diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index cec524167822..763d3f1edb8a 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -65,7 +65,7 @@ static struct insn insn_table[] = { #ifndef CONFIG_CPU_MIPSR6 { insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, #else - { insn_cache, M6(cache_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, + { insn_cache, M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, #endif { insn_cfc1, M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD }, { insn_cfcmsa, M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE }, diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index 3e0282d301d6..a82970442b8a 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -378,11 +378,7 @@ UASM_EXPORT_SYMBOL(ISAFUNC(uasm_build_label)); int ISAFUNC(uasm_in_compat_space_p)(long addr) { /* Is this address in 32bit compat space? */ -#ifdef CONFIG_64BIT - return (((addr) & 0xffffffff00000000L) == 0xffffffff00000000L); -#else - return 1; -#endif + return addr == (int)addr; } UASM_EXPORT_SYMBOL(ISAFUNC(uasm_in_compat_space_p)); diff --git a/arch/mips/mti-malta/malta-dtshim.c b/arch/mips/mti-malta/malta-dtshim.c index f7133efc5843..151f4882ec8a 100644 --- a/arch/mips/mti-malta/malta-dtshim.c +++ b/arch/mips/mti-malta/malta-dtshim.c @@ -31,7 +31,7 @@ static unsigned __init gen_fdt_mem_array(__be32 *mem_array, unsigned long size) entries = 1; mem_array[0] = cpu_to_be32(PHYS_OFFSET); - if (config_enabled(CONFIG_EVA)) { + if (IS_ENABLED(CONFIG_EVA)) { /* * The current Malta EVA configuration is "special" in that it * always makes use of addresses in the upper half of the 32 bit @@ -82,7 +82,7 @@ static void __init append_memory(void *fdt, int root_off) physical_memsize = 32 << 20; } - if (config_enabled(CONFIG_CPU_BIG_ENDIAN)) { + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) { /* * SOC-it swaps, or perhaps doesn't swap, when DMA'ing * the last word of physical memory. diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c index d5f8dae6a797..a47556723b85 100644 --- a/arch/mips/mti-malta/malta-memory.c +++ b/arch/mips/mti-malta/malta-memory.c @@ -32,7 +32,7 @@ static void free_init_pages_eva_malta(void *begin, void *end) void __init fw_meminit(void) { - bool eva = config_enabled(CONFIG_EVA); + bool eva = IS_ENABLED(CONFIG_EVA); free_init_pages_eva = eva ? free_init_pages_eva_malta : NULL; } diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index 33d5ff5069e5..ec5b21678fad 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -261,7 +261,7 @@ void __init plat_mem_setup(void) fdt = malta_dt_shim(fdt); __dt_setup_arch(fdt); - if (config_enabled(CONFIG_EVA)) + if (IS_ENABLED(CONFIG_EVA)) /* EVA has already been configured in mach-malta/kernel-init.h */ pr_info("Enhanced Virtual Addressing (EVA) activated\n"); diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 1a8c96035716..39e7b472f0d8 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -426,7 +426,7 @@ static inline void emit_load_ptr(unsigned int dst, unsigned int src, static inline void emit_load_func(unsigned int reg, ptr imm, struct jit_ctx *ctx) { - if (config_enabled(CONFIG_64BIT)) { + if (IS_ENABLED(CONFIG_64BIT)) { /* At this point imm is always 64-bit */ emit_load_imm(r_tmp, (u64)imm >> 32, ctx); emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */ @@ -516,7 +516,7 @@ static inline void emit_jr(unsigned int reg, struct jit_ctx *ctx) static inline u16 align_sp(unsigned int num) { /* Double word alignment for 32-bit, quadword for 64-bit */ - unsigned int align = config_enabled(CONFIG_64BIT) ? 16 : 8; + unsigned int align = IS_ENABLED(CONFIG_64BIT) ? 16 : 8; num = (num + (align - 1)) & -align; return num; } @@ -1199,7 +1199,7 @@ void bpf_jit_compile(struct bpf_prog *fp) memset(&ctx, 0, sizeof(ctx)); - ctx.offsets = kcalloc(fp->len, sizeof(*ctx.offsets), GFP_KERNEL); + ctx.offsets = kcalloc(fp->len + 1, sizeof(*ctx.offsets), GFP_KERNEL); if (ctx.offsets == NULL) return; diff --git a/arch/mips/netlogic/common/nlm-dma.c b/arch/mips/netlogic/common/nlm-dma.c index 3758715d4ab6..0630693bec2a 100644 --- a/arch/mips/netlogic/common/nlm-dma.c +++ b/arch/mips/netlogic/common/nlm-dma.c @@ -45,7 +45,7 @@ static char *nlm_swiotlb; static void *nlm_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { /* ignore region specifiers */ gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); @@ -62,7 +62,7 @@ static void *nlm_dma_alloc_coherent(struct device *dev, size_t size, } static void nlm_dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs) + void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_handle); } diff --git a/arch/mips/pic32/pic32mzda/init.c b/arch/mips/pic32/pic32mzda/init.c index 77ecf32ef3dc..51599710472b 100644 --- a/arch/mips/pic32/pic32mzda/init.c +++ b/arch/mips/pic32/pic32mzda/init.c @@ -33,8 +33,8 @@ static ulong get_fdtaddr(void) { ulong ftaddr = 0; - if ((fw_arg0 == -2) && fw_arg1 && !fw_arg2 && !fw_arg3) - return (ulong)fw_arg1; + if (fw_passed_dtb && !fw_arg2 && !fw_arg3) + return (ulong)fw_passed_dtb; if (__dtb_start < __dtb_end) ftaddr = (ulong)__dtb_start; diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c index c50a670e60d2..1c91cad7988f 100644 --- a/arch/mips/pistachio/init.c +++ b/arch/mips/pistachio/init.c @@ -59,29 +59,6 @@ const char *get_system_type(void) return sys_type; } -static void __init plat_setup_iocoherency(void) -{ - /* - * Kernel has been configured with software coherency - * but we might choose to turn it off and use hardware - * coherency instead. - */ - if (mips_cm_numiocu() != 0) { - /* Nothing special needs to be done to enable coherency */ - pr_info("CMP IOCU detected\n"); - hw_coherentio = 1; - if (coherentio == 0) - pr_info("Hardware DMA cache coherency disabled\n"); - else - pr_info("Hardware DMA cache coherency enabled\n"); - } else { - if (coherentio == 1) - pr_info("Hardware DMA cache coherency unsupported, but enabled from command line!\n"); - else - pr_info("Software DMA cache coherency enabled\n"); - } -} - void __init *plat_get_fdt(void) { if (fw_arg0 != -2) @@ -92,8 +69,6 @@ void __init *plat_get_fdt(void) void __init plat_mem_setup(void) { __dt_setup_arch(plat_get_fdt()); - - plat_setup_iocoherency(); } #define DEFAULT_CPC_BASE_ADDR 0x1bde0000 diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index d40edda0ca3b..3c7c9bf57bf3 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -175,7 +175,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = { }; static struct rt2880_pmx_func spis_grp_mt7628[] = { - FUNC("pwm", 3, 14, 4), + FUNC("pwm_uart2", 3, 14, 4), FUNC("util", 2, 14, 4), FUNC("gpio", 1, 14, 4), FUNC("spis", 0, 14, 4), diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c index 063c2dd31e72..2f45b0357021 100644 --- a/arch/mips/sgi-ip22/ip22-reset.c +++ b/arch/mips/sgi-ip22/ip22-reset.c @@ -7,7 +7,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> -#include <linux/ds1286.h> +#include <linux/rtc/ds1286.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/kernel.h> diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c index fb4b3520cdc6..7ee14f41fc25 100644 --- a/arch/mips/sni/time.c +++ b/arch/mips/sni/time.c @@ -8,7 +8,6 @@ #include <asm/sni.h> #include <asm/time.h> -#include <asm-generic/rtc.h> #define SNI_CLOCK_TICK_RATE 3686400 #define SNI_COUNTER2_DIV 64 diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 9627e81a6cbb..38e3494bfb63 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -236,7 +236,9 @@ source "kernel/Kconfig.hz" config MN10300_RTC bool "Using MN10300 RTC" depends on MN10300_PROC_MN103E010 || MN10300_PROC_MN2WS0050 - select GENERIC_CMOS_UPDATE + select RTC_CLASS + select RTC_DRV_CMOS + select RTC_SYSTOHC default n help This option enables support for the RTC, thus enabling time to be diff --git a/arch/mn10300/include/asm/rtc-regs.h b/arch/mn10300/include/asm/rtc-regs.h index c42deefaec11..c81cacecb6e3 100644 --- a/arch/mn10300/include/asm/rtc-regs.h +++ b/arch/mn10300/include/asm/rtc-regs.h @@ -75,9 +75,9 @@ #define RTC_PORT(x) 0xd8600000 #define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */ -#define CMOS_READ(addr) __SYSREG(0xd8600000 + (addr), u8) +#define CMOS_READ(addr) __SYSREG(0xd8600000 + (u32)(addr), u8) #define CMOS_WRITE(val, addr) \ - do { __SYSREG(0xd8600000 + (addr), u8) = val; } while (0) + do { __SYSREG(0xd8600000 + (u32)(addr), u8) = val; } while (0) #define RTC_IRQ RTIRQ diff --git a/arch/mn10300/include/asm/rtc.h b/arch/mn10300/include/asm/rtc.h index 6c14bb1d0d9b..07dc87656197 100644 --- a/arch/mn10300/include/asm/rtc.h +++ b/arch/mn10300/include/asm/rtc.h @@ -25,6 +25,4 @@ static inline void calibrate_clock(void) #endif /* !CONFIG_MN10300_RTC */ -#include <asm-generic/rtc.h> - #endif /* _ASM_RTC_H */ diff --git a/arch/mn10300/kernel/rtc.c b/arch/mn10300/kernel/rtc.c index 48d7058b3295..f81f37025072 100644 --- a/arch/mn10300/kernel/rtc.c +++ b/arch/mn10300/kernel/rtc.c @@ -12,107 +12,19 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/mc146818rtc.h> -#include <linux/bcd.h> -#include <linux/timex.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> + #include <asm/rtc-regs.h> #include <asm/rtc.h> DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); -/* - * Read the current RTC time - */ -void read_persistent_clock(struct timespec *ts) -{ - struct rtc_time tm; - - get_rtc_time(&tm); - - ts->tv_nsec = 0; - ts->tv_sec = mktime(tm.tm_year, tm.tm_mon, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec); - - /* if rtc is way off in the past, set something reasonable */ - if (ts->tv_sec < 0) - ts->tv_sec = mktime(2009, 1, 1, 12, 0, 0); -} - -/* - * In order to set the CMOS clock precisely, set_rtc_mmss has to be called 500 - * ms after the second nowtime has started, because when nowtime is written - * into the registers of the CMOS clock, it will jump to the next second - * precisely 500 ms later. Check the Motorola MC146818A or Dallas DS12887 data - * sheet for details. - * - * BUG: This routine does not handle hour overflow properly; it just - * sets the minutes. Usually you'll only notice that after reboot! - */ -static int set_rtc_mmss(unsigned long nowtime) -{ - unsigned char save_control, save_freq_select; - int retval = 0; - int real_seconds, real_minutes, cmos_minutes; - - /* gets recalled with irq locally disabled */ - spin_lock(&rtc_lock); - save_control = CMOS_READ(RTC_CONTROL); /* tell the clock it's being - * set */ - CMOS_WRITE(save_control | RTC_SET, RTC_CONTROL); - - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); /* stop and reset - * prescaler */ - CMOS_WRITE(save_freq_select | RTC_DIV_RESET2, RTC_FREQ_SELECT); - - cmos_minutes = CMOS_READ(RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - cmos_minutes = bcd2bin(cmos_minutes); - - /* - * since we're only adjusting minutes and seconds, - * don't interfere with hour overflow. This avoids - * messing with unknown time zones but requires your - * RTC not to be off by more than 15 minutes - */ - real_seconds = nowtime % 60; - real_minutes = nowtime / 60; - if (((abs(real_minutes - cmos_minutes) + 15) / 30) & 1) - /* correct for half hour time zone */ - real_minutes += 30; - real_minutes %= 60; - - if (abs(real_minutes - cmos_minutes) < 30) { - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - CMOS_WRITE(real_seconds, RTC_SECONDS); - CMOS_WRITE(real_minutes, RTC_MINUTES); - } else { - printk_once(KERN_NOTICE - "set_rtc_mmss: can't update from %d to %d\n", - cmos_minutes, real_minutes); - retval = -1; - } - - /* The following flags have to be released exactly in this order, - * otherwise the DS12887 (popular MC146818A clone with integrated - * battery and quartz) will not reset the oscillator and will not - * update precisely 500 ms later. You won't find this mentioned in - * the Dallas Semiconductor data sheets, but who believes data - * sheets anyway ... -- Markus Kuhn - */ - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - spin_unlock(&rtc_lock); - - return retval; -} - -int update_persistent_clock(struct timespec now) -{ - return set_rtc_mmss(now.tv_sec); -} +static const __initdata struct resource res[] = { + DEFINE_RES_IO(RTC_PORT(0), RTC_IO_EXTENT), + DEFINE_RES_IRQ(RTC_IRQ), +}; /* * calibrate the TSC clock against the RTC @@ -129,4 +41,6 @@ void __init calibrate_clock(void) RTCRA |= RTCRA_DVR; RTCRA &= ~RTCRA_DVR; RTCRB &= ~RTCRB_SET; + + platform_device_register_simple("rtc_cmos", -1, res, ARRAY_SIZE(res)); } diff --git a/arch/mn10300/mm/dma-alloc.c b/arch/mn10300/mm/dma-alloc.c index 8842394cb49a..4f4b9029f0ea 100644 --- a/arch/mn10300/mm/dma-alloc.c +++ b/arch/mn10300/mm/dma-alloc.c @@ -21,7 +21,7 @@ static unsigned long pci_sram_allocated = 0xbc000000; static void *mn10300_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { unsigned long addr; void *ret; @@ -63,7 +63,7 @@ done: } static void mn10300_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { unsigned long addr = (unsigned long) vaddr & ~0x20000000; @@ -75,7 +75,7 @@ static void mn10300_dma_free(struct device *dev, size_t size, void *vaddr, static int mn10300_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -92,7 +92,7 @@ static int mn10300_dma_map_sg(struct device *dev, struct scatterlist *sglist, static dma_addr_t mn10300_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { return page_to_bus(page) + offset; } diff --git a/arch/mn10300/proc-mn103e010/proc-init.c b/arch/mn10300/proc-mn103e010/proc-init.c index 27b97980dca4..102d86a6ae56 100644 --- a/arch/mn10300/proc-mn103e010/proc-init.c +++ b/arch/mn10300/proc-mn103e010/proc-init.c @@ -9,7 +9,10 @@ * 2 of the Licence, or (at your option) any later version. */ #include <linux/kernel.h> +#include <linux/irq.h> +#include <asm/cacheflush.h> #include <asm/fpu.h> +#include <asm/irq.h> #include <asm/rtc.h> #include <asm/busctl-regs.h> diff --git a/arch/mn10300/proc-mn2ws0050/proc-init.c b/arch/mn10300/proc-mn2ws0050/proc-init.c index ee6d03dbc8d8..950cc8dbb284 100644 --- a/arch/mn10300/proc-mn2ws0050/proc-init.c +++ b/arch/mn10300/proc-mn2ws0050/proc-init.c @@ -14,6 +14,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> +#include <asm/cacheflush.h> #include <asm/processor.h> #include <asm/uaccess.h> #include <asm/io.h> diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c index 90422c367ed3..d800fad87896 100644 --- a/arch/nios2/mm/dma-mapping.c +++ b/arch/nios2/mm/dma-mapping.c @@ -59,7 +59,7 @@ static inline void __dma_sync_for_cpu(void *vaddr, size_t size, } static void *nios2_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { void *ret; @@ -84,7 +84,7 @@ static void *nios2_dma_alloc(struct device *dev, size_t size, } static void nios2_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr); @@ -93,7 +93,7 @@ static void nios2_dma_free(struct device *dev, size_t size, void *vaddr, static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; @@ -113,7 +113,7 @@ static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg, static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { void *addr = page_address(page) + offset; @@ -123,14 +123,14 @@ static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page, static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { __dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); } static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { void *addr; int i; diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 0b77ddb1ee07..140c99140649 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -22,7 +22,6 @@ #include <linux/dma-mapping.h> #include <linux/dma-debug.h> #include <linux/export.h> -#include <linux/dma-attrs.h> #include <asm/cpuinfo.h> #include <asm/spr_defs.h> @@ -83,7 +82,7 @@ page_clear_nocache(pte_t *pte, unsigned long addr, static void * or1k_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long va; void *page; @@ -101,7 +100,7 @@ or1k_dma_alloc(struct device *dev, size_t size, va = (unsigned long)page; - if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) { + if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) { /* * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. @@ -117,7 +116,7 @@ or1k_dma_alloc(struct device *dev, size_t size, static void or1k_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { unsigned long va = (unsigned long)vaddr; struct mm_walk walk = { @@ -125,7 +124,7 @@ or1k_dma_free(struct device *dev, size_t size, void *vaddr, .mm = &init_mm }; - if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) { + if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) { /* walk_page_range shouldn't be able to fail here */ WARN_ON(walk_page_range(va, va + size, &walk)); } @@ -137,7 +136,7 @@ static dma_addr_t or1k_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long cl; dma_addr_t addr = page_to_phys(page) + offset; @@ -170,7 +169,7 @@ or1k_map_page(struct device *dev, struct page *page, static void or1k_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { /* Nothing special to do here... */ } @@ -178,14 +177,14 @@ or1k_unmap_page(struct device *dev, dma_addr_t dma_handle, static int or1k_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; for_each_sg(sg, s, nents, i) { s->dma_address = or1k_map_page(dev, sg_page(s), s->offset, - s->length, dir, NULL); + s->length, dir, 0); } return nents; @@ -194,13 +193,13 @@ or1k_map_sg(struct device *dev, struct scatterlist *sg, static void or1k_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; for_each_sg(sg, s, nents, i) { - or1k_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, NULL); + or1k_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, 0); } } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index dc117385ce2e..cd8778103165 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -31,6 +31,7 @@ config PARISC select TTY # Needed for pdc_cons.c select HAVE_DEBUG_STACKOVERFLOW select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HASH select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_UNSTABLE_SCHED_CLOCK if (SMP || !64BIT) diff --git a/arch/parisc/include/asm/hash.h b/arch/parisc/include/asm/hash.h new file mode 100644 index 000000000000..dbe93311aa26 --- /dev/null +++ b/arch/parisc/include/asm/hash.h @@ -0,0 +1,146 @@ +#ifndef _ASM_HASH_H +#define _ASM_HASH_H + +/* + * HP-PA only implements integer multiply in the FPU. However, for + * integer multiplies by constant, it has a number of shift-and-add + * (but no shift-and-subtract, sigh!) instructions that a compiler + * can synthesize a code sequence with. + * + * Unfortunately, GCC isn't very efficient at using them. For example + * it uses three instructions for "x *= 21" when only two are needed. + * But we can find a sequence manually. + */ + +#define HAVE_ARCH__HASH_32 1 + +/* + * This is a multiply by GOLDEN_RATIO_32 = 0x61C88647 optimized for the + * PA7100 pairing rules. This is an in-order 2-way superscalar processor. + * Only one instruction in a pair may be a shift (by more than 3 bits), + * but other than that, simple ALU ops (including shift-and-add by up + * to 3 bits) may be paired arbitrarily. + * + * PA8xxx processors also dual-issue ALU instructions, although with + * fewer constraints, so this schedule is good for them, too. + * + * This 6-step sequence was found by Yevgen Voronenko's implementation + * of the Hcub algorithm at http://spiral.ece.cmu.edu/mcm/gen.html. + */ +static inline u32 __attribute_const__ __hash_32(u32 x) +{ + u32 a, b, c; + + /* + * Phase 1: Compute a = (x << 19) + x, + * b = (x << 9) + a, c = (x << 23) + b. + */ + a = x << 19; /* Two shifts can't be paired */ + b = x << 9; a += x; + c = x << 23; b += a; + c += b; + /* Phase 2: Return (b<<11) + (c<<6) + (a<<3) - c */ + b <<= 11; + a += c << 3; b -= c; + return (a << 3) + b; +} + +#if BITS_PER_LONG == 64 + +#define HAVE_ARCH_HASH_64 1 + +/* + * Finding a good shift-and-add chain for GOLDEN_RATIO_64 is tricky, + * because available software for the purpose chokes on constants this + * large. (It's mostly designed for compiling FIR filter coefficients + * into FPGAs.) + * + * However, Jason Thong pointed out a work-around. The Hcub software + * (http://spiral.ece.cmu.edu/mcm/gen.html) is designed for *multiple* + * constant multiplication, and is good at finding shift-and-add chains + * which share common terms. + * + * Looking at 0x0x61C8864680B583EB in binary: + * 0110000111001000100001100100011010000000101101011000001111101011 + * \______________/ \__________/ \_______/ \________/ + * \____________________________/ \____________________/ + * you can see the non-zero bits are divided into several well-separated + * blocks. Hcub can find algorithms for those terms separately, which + * can then be shifted and added together. + * + * Dividing the input into 2, 3 or 4 blocks, Hcub can find solutions + * with 10, 9 or 8 adds, respectively, making a total of 11 for the + * whole number. + * + * Using just two large blocks, 0xC3910C8D << 31 in the high bits, + * and 0xB583EB in the low bits, produces as good an algorithm as any, + * and with one more small shift than alternatives. + * + * The high bits are a larger number and more work to compute, as well + * as needing one extra cycle to shift left 31 bits before the final + * addition, so they are the critical path for scheduling. The low bits + * can fit into the scheduling slots left over. + */ + + +/* + * This _ASSIGN(dst, src) macro performs "dst = src", but prevents GCC + * from inferring anything about the value assigned to "dest". + * + * This prevents it from mis-optimizing certain sequences. + * In particular, gcc is annoyingly eager to combine consecutive shifts. + * Given "x <<= 19; y += x; z += x << 1;", GCC will turn this into + * "y += x << 19; z += x << 20;" even though the latter sequence needs + * an additional instruction and temporary register. + * + * Because no actual assembly code is generated, this construct is + * usefully portable across all GCC platforms, and so can be test-compiled + * on non-PA systems. + * + * In two places, additional unused input dependencies are added. This + * forces GCC's scheduling so it does not rearrange instructions too much. + * Because the PA-8xxx is out of order, I'm not sure how much this matters, + * but why make it more difficult for the processor than necessary? + */ +#define _ASSIGN(dst, src, ...) asm("" : "=r" (dst) : "0" (src), ##__VA_ARGS__) + +/* + * Multiply by GOLDEN_RATIO_64 = 0x0x61C8864680B583EB using a heavily + * optimized shift-and-add sequence. + * + * Without the final shift, the multiply proper is 19 instructions, + * 10 cycles and uses only 4 temporaries. Whew! + * + * You are not expected to understand this. + */ +static __always_inline u32 __attribute_const__ +hash_64(u64 a, unsigned int bits) +{ + u64 b, c, d; + + /* + * Encourage GCC to move a dynamic shift to %sar early, + * thereby freeing up an additional temporary register. + */ + if (!__builtin_constant_p(bits)) + asm("" : "=q" (bits) : "0" (64 - bits)); + else + bits = 64 - bits; + + _ASSIGN(b, a*5); c = a << 13; + b = (b << 2) + a; _ASSIGN(d, a << 17); + a = b + (a << 1); c += d; + d = a << 10; _ASSIGN(a, a << 19); + d = a - d; _ASSIGN(a, a << 4, "X" (d)); + c += b; a += b; + d -= c; c += a << 1; + a += c << 3; _ASSIGN(b, b << (7+31), "X" (c), "X" (d)); + a <<= 31; b += d; + a += b; + return a >> bits; +} +#undef _ASSIGN /* We're a widely-used header file, so don't litter! */ + +#endif /* BITS_PER_LONG == 64 */ + +#endif /* _ASM_HASH_H */ diff --git a/arch/parisc/include/asm/mc146818rtc.h b/arch/parisc/include/asm/mc146818rtc.h deleted file mode 100644 index adf41631449f..000000000000 --- a/arch/parisc/include/asm/mc146818rtc.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Machine dependent access functions for RTC registers. - */ -#ifndef _ASM_MC146818RTC_H -#define _ASM_MC146818RTC_H - -/* empty include file to satisfy the include in genrtc.c */ - -#endif /* _ASM_MC146818RTC_H */ diff --git a/arch/parisc/include/asm/rtc.h b/arch/parisc/include/asm/rtc.h deleted file mode 100644 index 099d641a42c2..000000000000 --- a/arch/parisc/include/asm/rtc.h +++ /dev/null @@ -1,131 +0,0 @@ -/* - * include/asm-parisc/rtc.h - * - * Copyright 2002 Randolph CHung <tausq@debian.org> - * - * Based on: include/asm-ppc/rtc.h and the genrtc driver in the - * 2.4 parisc linux tree - */ - -#ifndef __ASM_RTC_H__ -#define __ASM_RTC_H__ - -#ifdef __KERNEL__ - -#include <linux/rtc.h> - -#include <asm/pdc.h> - -#define SECS_PER_HOUR (60 * 60) -#define SECS_PER_DAY (SECS_PER_HOUR * 24) - - -#define RTC_PIE 0x40 /* periodic interrupt enable */ -#define RTC_AIE 0x20 /* alarm interrupt enable */ -#define RTC_UIE 0x10 /* update-finished interrupt enable */ - -#define RTC_BATT_BAD 0x100 /* battery bad */ - -/* some dummy definitions */ -#define RTC_SQWE 0x08 /* enable square-wave output */ -#define RTC_DM_BINARY 0x04 /* all time/date values are BCD if clear */ -#define RTC_24H 0x02 /* 24 hour mode - else hours bit 7 means pm */ -#define RTC_DST_EN 0x01 /* auto switch DST - works f. USA only */ - -# define __isleap(year) \ - ((year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0)) - -/* How many days come before each month (0-12). */ -static const unsigned short int __mon_yday[2][13] = -{ - /* Normal years. */ - { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365 }, - /* Leap years. */ - { 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 } -}; - -static inline unsigned int get_rtc_time(struct rtc_time *wtime) -{ - struct pdc_tod tod_data; - long int days, rem, y; - const unsigned short int *ip; - - memset(wtime, 0, sizeof(*wtime)); - if (pdc_tod_read(&tod_data) < 0) - return RTC_24H | RTC_BATT_BAD; - - // most of the remainder of this function is: -// Copyright (C) 1991, 1993, 1997, 1998 Free Software Foundation, Inc. -// This was originally a part of the GNU C Library. -// It is distributed under the GPL, and was swiped from offtime.c - - - days = tod_data.tod_sec / SECS_PER_DAY; - rem = tod_data.tod_sec % SECS_PER_DAY; - - wtime->tm_hour = rem / SECS_PER_HOUR; - rem %= SECS_PER_HOUR; - wtime->tm_min = rem / 60; - wtime->tm_sec = rem % 60; - - y = 1970; - -#define DIV(a, b) ((a) / (b) - ((a) % (b) < 0)) -#define LEAPS_THRU_END_OF(y) (DIV (y, 4) - DIV (y, 100) + DIV (y, 400)) - - while (days < 0 || days >= (__isleap (y) ? 366 : 365)) - { - /* Guess a corrected year, assuming 365 days per year. */ - long int yg = y + days / 365 - (days % 365 < 0); - - /* Adjust DAYS and Y to match the guessed year. */ - days -= ((yg - y) * 365 - + LEAPS_THRU_END_OF (yg - 1) - - LEAPS_THRU_END_OF (y - 1)); - y = yg; - } - wtime->tm_year = y - 1900; - - ip = __mon_yday[__isleap(y)]; - for (y = 11; days < (long int) ip[y]; --y) - continue; - days -= ip[y]; - wtime->tm_mon = y; - wtime->tm_mday = days + 1; - - return RTC_24H; -} - -static int set_rtc_time(struct rtc_time *wtime) -{ - u_int32_t secs; - - secs = mktime(wtime->tm_year + 1900, wtime->tm_mon + 1, wtime->tm_mday, - wtime->tm_hour, wtime->tm_min, wtime->tm_sec); - - if(pdc_tod_set(secs, 0) < 0) - return -1; - else - return 0; - -} - -static inline unsigned int get_rtc_ss(void) -{ - struct rtc_time h; - - get_rtc_time(&h); - return h.tm_sec; -} - -static inline int get_rtc_pll(struct rtc_pll_info *pll) -{ - return -EINVAL; -} -static inline int set_rtc_pll(struct rtc_pll_info *pll) -{ - return -EINVAL; -} - -#endif /* __KERNEL__ */ -#endif /* __ASM_RTC_H__ */ diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 22395901d47b..e5d71905cad5 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1354,9 +1354,9 @@ int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *mem_addr) retval = mem_pdc_call(PDC_PAT_IO, PDC_PAT_IO_PCI_CONFIG_READ, __pa(pdc_result), pci_addr, pci_size); switch(pci_size) { - case 1: *(u8 *) mem_addr = (u8) pdc_result[0]; - case 2: *(u16 *)mem_addr = (u16) pdc_result[0]; - case 4: *(u32 *)mem_addr = (u32) pdc_result[0]; + case 1: *(u8 *) mem_addr = (u8) pdc_result[0]; break; + case 2: *(u16 *)mem_addr = (u16) pdc_result[0]; break; + case 4: *(u32 *)mem_addr = (u32) pdc_result[0]; break; } spin_unlock_irqrestore(&pdc_lock, flags); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index a27e4928bf73..02d9ed0f3949 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -414,7 +414,7 @@ pcxl_dma_init(void) __initcall(pcxl_dma_init); static void *pa11_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { unsigned long vaddr; unsigned long paddr; @@ -441,7 +441,7 @@ static void *pa11_dma_alloc(struct device *dev, size_t size, } static void pa11_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { int order; @@ -454,7 +454,7 @@ static void pa11_dma_free(struct device *dev, size_t size, void *vaddr, static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, - enum dma_data_direction direction, struct dma_attrs *attrs) + enum dma_data_direction direction, unsigned long attrs) { void *addr = page_address(page) + offset; BUG_ON(direction == DMA_NONE); @@ -465,7 +465,7 @@ static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page, static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(direction == DMA_NONE); @@ -484,7 +484,7 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; struct scatterlist *sg; @@ -503,7 +503,7 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; struct scatterlist *sg; @@ -577,11 +577,11 @@ struct dma_map_ops pcxl_dma_ops = { }; static void *pcx_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { void *addr; - if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) + if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) return NULL; addr = (void *)__get_free_pages(flag, get_order(size)); @@ -592,7 +592,7 @@ static void *pcx_dma_alloc(struct device *dev, size_t size, } static void pcx_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t iova, struct dma_attrs *attrs) + dma_addr_t iova, unsigned long attrs) { free_pages((unsigned long)vaddr, get_order(size)); return; diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 31ec99a5f119..505cf1ac5af2 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -12,6 +12,7 @@ */ #include <linux/errno.h> #include <linux/module.h> +#include <linux/rtc.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/param.h> @@ -248,14 +249,47 @@ void __init start_cpu_itimer(void) per_cpu(cpu_data, cpu).it_value = next_tick; } +#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC) +static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) +{ + struct pdc_tod tod_data; + + memset(tm, 0, sizeof(*tm)); + if (pdc_tod_read(&tod_data) < 0) + return -EOPNOTSUPP; + + /* we treat tod_sec as unsigned, so this can work until year 2106 */ + rtc_time64_to_tm(tod_data.tod_sec, tm); + return rtc_valid_tm(tm); +} + +static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) +{ + time64_t secs = rtc_tm_to_time64(tm); + + if (pdc_tod_set(secs, 0) < 0) + return -EOPNOTSUPP; + + return 0; +} + +static const struct rtc_class_ops rtc_generic_ops = { + .read_time = rtc_generic_get_time, + .set_time = rtc_generic_set_time, +}; + static int __init rtc_init(void) { struct platform_device *pdev; - pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); + pdev = platform_device_register_data(NULL, "rtc-generic", -1, + &rtc_generic_ops, + sizeof(rtc_generic_ops)); + return PTR_ERR_OR_ZERO(pdev); } device_initcall(rtc_init); +#endif void read_persistent_clock(struct timespec *ts) { diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c index fb8e10a4fb39..eaffbb90aa14 100644 --- a/arch/parisc/lib/iomap.c +++ b/arch/parisc/lib/iomap.c @@ -125,22 +125,22 @@ static void ioport_write32r(void __iomem *addr, const void *s, unsigned long n) } static const struct iomap_ops ioport_ops = { - ioport_read8, - ioport_read16, - ioport_read16, - ioport_read32, - ioport_read32, - ioport_write8, - ioport_write16, - ioport_write16, - ioport_write32, - ioport_write32, - ioport_read8r, - ioport_read16r, - ioport_read32r, - ioport_write8r, - ioport_write16r, - ioport_write32r, + .read8 = ioport_read8, + .read16 = ioport_read16, + .read16be = ioport_read16, + .read32 = ioport_read32, + .read32be = ioport_read32, + .write8 = ioport_write8, + .write16 = ioport_write16, + .write16be = ioport_write16, + .write32 = ioport_write32, + .write32be = ioport_write32, + .read8r = ioport_read8r, + .read16r = ioport_read16r, + .read32r = ioport_read32r, + .write8r = ioport_write8r, + .write16r = ioport_write16r, + .write32r = ioport_write32r, }; /* Legacy I/O memory ops */ @@ -244,22 +244,22 @@ static void iomem_write32r(void __iomem *addr, const void *s, unsigned long n) } static const struct iomap_ops iomem_ops = { - iomem_read8, - iomem_read16, - iomem_read16be, - iomem_read32, - iomem_read32be, - iomem_write8, - iomem_write16, - iomem_write16be, - iomem_write32, - iomem_write32be, - iomem_read8r, - iomem_read16r, - iomem_read32r, - iomem_write8r, - iomem_write16r, - iomem_write32r, + .read8 = iomem_read8, + .read16 = iomem_read16, + .read16be = iomem_read16be, + .read32 = iomem_read32, + .read32be = iomem_read32be, + .write8 = iomem_write8, + .write16 = iomem_write16, + .write16be = iomem_write16be, + .write32 = iomem_write32, + .write32be = iomem_write32be, + .read8r = iomem_read8r, + .read16r = iomem_read16r, + .read32r = iomem_read32r, + .write8r = iomem_write8r, + .write16r = iomem_write16r, + .write32r = iomem_write32r, }; static const struct iomap_ops *iomap_ops[8] = { diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ec4047e170a0..927d2ab2ce08 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -166,6 +166,7 @@ config PPC select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select GENERIC_CPU_AUTOPROBE select HAVE_VIRT_CPU_ACCOUNTING + select HAVE_ARCH_HARDENED_USERCOPY config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 171047822b56..63292f64b25a 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -60,6 +60,25 @@ config CODE_PATCHING_SELFTEST depends on DEBUG_KERNEL default n +config JUMP_LABEL_FEATURE_CHECKS + bool "Enable use of jump label for cpu/mmu_has_feature()" + depends on JUMP_LABEL + default y + help + Selecting this options enables use of jump labels for some internal + feature checks. This should generate more optimal code for those + checks. + +config JUMP_LABEL_FEATURE_CHECK_DEBUG + bool "Do extra check on feature fixup calls" + depends on DEBUG_KERNEL && JUMP_LABEL_FEATURE_CHECKS + default n + help + This tries to catch incorrect usage of cpu_has_feature() and + mmu_has_feature() in the code. + + If you don't know what this means, say N. + config FTR_FIXUP_SELFTEST bool "Run self-tests of the feature-fixup code" depends on DEBUG_KERNEL diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index ca254546cd05..1934707bf321 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -66,29 +66,28 @@ endif UTS_MACHINE := $(OLDARCH) ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -override CC += -mlittle-endian -ifneq ($(cc-name),clang) -override CC += -mno-strict-align -endif -override AS += -mlittle-endian override LD += -EL -override CROSS32CC += -mlittle-endian override CROSS32AS += -mlittle-endian LDEMULATION := lppc GNUTARGET := powerpcle MULTIPLEWORD := -mno-multiple KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect) else -ifeq ($(call cc-option-yn,-mbig-endian),y) -override CC += -mbig-endian -override AS += -mbig-endian -endif override LD += -EB LDEMULATION := ppc GNUTARGET := powerpc MULTIPLEWORD := -mmultiple endif +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian +ifneq ($(cc-name),clang) + cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align +endif + +aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian + ifeq ($(HAS_BIARCH),y) override AS += -a$(CONFIG_WORD_SIZE) override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION) @@ -232,6 +231,9 @@ cpu-as-$(CONFIG_E200) += -Wa,-me200 KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) +KBUILD_AFLAGS += $(aflags-y) +KBUILD_CFLAGS += $(cflags-y) + head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index bfe3d37a24ef..9fa046d56eba 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/cpufeature.h> #include <asm/switch_to.h> #define CHKSUM_BLOCK_SIZE 1 @@ -157,7 +158,7 @@ static void __exit crc32c_vpmsum_mod_fini(void) crypto_unregister_shash(&alg); } -module_init(crc32c_vpmsum_mod_init); +module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init); module_exit(crc32c_vpmsum_mod_fini); MODULE_AUTHOR("Anton Blanchard <anton@samba.org>"); diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h index 60f47649306f..c45189aa7476 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h @@ -11,4 +11,19 @@ extern unsigned long radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); + +static inline int hstate_get_psize(struct hstate *hstate) +{ + unsigned long shift; + + shift = huge_page_shift(hstate); + if (shift == mmu_psize_defs[MMU_PAGE_2M].shift) + return MMU_PAGE_2M; + else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift) + return MMU_PAGE_1G; + else { + WARN(1, "Wrong huge page shift\n"); + return mmu_virtual_psize; + } +} #endif diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 5eaf86ac143d..287a656ceb57 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -24,6 +24,7 @@ #include <asm/book3s/64/pgtable.h> #include <asm/bug.h> #include <asm/processor.h> +#include <asm/cpu_has_feature.h> /* * SLB @@ -190,6 +191,15 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) BUG(); } +static inline unsigned long get_sllp_encoding(int psize) +{ + unsigned long sllp; + + sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) | + ((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4); + return sllp; +} + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index d4eda6420523..8afb0e00f7d9 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -23,13 +23,6 @@ struct mmu_psize_def { }; extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; -#ifdef CONFIG_PPC_RADIX_MMU -#define radix_enabled() mmu_has_feature(MMU_FTR_RADIX) -#else -#define radix_enabled() (0) -#endif - - #endif /* __ASSEMBLY__ */ /* 64-bit classic hash table MMU */ @@ -107,6 +100,9 @@ extern int mmu_vmemmap_psize; extern int mmu_io_psize; /* MMU initialization */ +void mmu_early_init_devtree(void); +void hash__early_init_devtree(void); +void radix__early_init_devtree(void); extern void radix_init_native(void); extern void hash__early_init_mmu(void); extern void radix__early_init_mmu(void); @@ -132,11 +128,15 @@ extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { - if (radix_enabled()) + if (early_radix_enabled()) return radix__setup_initial_memory_limit(first_memblock_base, first_memblock_size); return hash__setup_initial_memory_limit(first_memblock_base, first_memblock_size); } + +extern int (*register_process_table)(unsigned long base, unsigned long page_size, + unsigned long tbl_size); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index f12ddf5e8de5..2f6373144e2c 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -75,11 +75,6 @@ static inline void hash__flush_tlb_page(struct vm_area_struct *vma, { } -static inline void hash__flush_tlb_page_nohash(struct vm_area_struct *vma, - unsigned long vmaddr) -{ -} - static inline void hash__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 00703e7e4c94..65037762b120 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -10,26 +10,32 @@ static inline int mmu_get_ap(int psize) return mmu_psize_defs[psize].ap; } +extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); +extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize); +extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end); extern void radix__local_flush_tlb_mm(struct mm_struct *mm); extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - unsigned long ap, int nid); extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); +extern void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize); extern void radix__tlb_flush(struct mmu_gather *tlb); #ifdef CONFIG_SMP extern void radix__flush_tlb_mm(struct mm_struct *mm); extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - unsigned long ap, int nid); extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); +extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize); #else #define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm) #define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr) -#define radix___flush_tlb_page(mm,addr,p,i) radix___local_flush_tlb_page(mm,addr,p,i) +#define radix__flush_tlb_page_psize(mm,addr,p) radix__local_flush_tlb_page_psize(mm,addr,p) #define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr) #endif extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa, diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 96e5769b18b0..72b925f97bab 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -7,6 +7,25 @@ #include <asm/book3s/64/tlbflush-hash.h> #include <asm/book3s/64/tlbflush-radix.h> +#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +static inline void flush_pmd_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + return radix__flush_pmd_tlb_range(vma, start, end); + return hash__flush_tlb_range(vma, start, end); +} + +#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) +{ + if (radix_enabled()) + return radix__flush_hugetlb_tlb_range(vma, start, end); + return hash__flush_tlb_range(vma, start, end); +} + static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { @@ -38,14 +57,6 @@ static inline void local_flush_tlb_page(struct vm_area_struct *vma, return hash__local_flush_tlb_page(vma, vmaddr); } -static inline void flush_tlb_page_nohash(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - if (radix_enabled()) - return radix__flush_tlb_page(vma, vmaddr); - return hash__flush_tlb_page_nohash(vma, vmaddr); -} - static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 69fb16d7a811..b77f0364df94 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -11,6 +11,7 @@ #include <linux/mm.h> #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> /* * No cache flushing is required when address mappings are changed, diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h new file mode 100644 index 000000000000..2ef55f8968a2 --- /dev/null +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -0,0 +1,53 @@ +#ifndef __ASM_POWERPC_CPUFEATURES_H +#define __ASM_POWERPC_CPUFEATURES_H + +#ifndef __ASSEMBLY__ + +#include <linux/bug.h> +#include <asm/cputable.h> + +static inline bool early_cpu_has_feature(unsigned long feature) +{ + return !!((CPU_FTRS_ALWAYS & feature) || + (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature)); +} + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +#include <linux/jump_label.h> + +#define NUM_CPU_FTR_KEYS 64 + +extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS]; + +static __always_inline bool cpu_has_feature(unsigned long feature) +{ + int i; + + BUILD_BUG_ON(!__builtin_constant_p(feature)); + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG + if (!static_key_initialized) { + printk("Warning! cpu_has_feature() used prior to jump label init!\n"); + dump_stack(); + return early_cpu_has_feature(feature); + } +#endif + + if (CPU_FTRS_ALWAYS & feature) + return true; + + if (!(CPU_FTRS_POSSIBLE & feature)) + return false; + + i = __builtin_ctzl(feature); + return static_branch_likely(&cpu_feature_keys[i]); +} +#else +static inline bool cpu_has_feature(unsigned long feature) +{ + return early_cpu_has_feature(feature); +} +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* __ASM_POWERPC_CPUFEATURE_H */ diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 3d7fc06532a1..01b8a13f0224 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -19,4 +19,17 @@ extern u64 pnv_first_deep_stop_state; #endif +/* Idle state entry routines */ +#ifdef CONFIG_PPC_P7_NAP +#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ + /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ + std r0,0(r1); \ + ptesync; \ + ld r0,0(r1); \ +1: cmp cr0,r0,r0; \ + bne 1b; \ + IDLE_INST; \ + b . +#endif /* CONFIG_PPC_P7_NAP */ + #endif diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index df4fb5faba43..82026b419341 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -2,6 +2,7 @@ #define __ASM_POWERPC_CPUTABLE_H +#include <linux/types.h> #include <asm/asm-compat.h> #include <asm/feature-fixups.h> #include <uapi/asm/cputable.h> @@ -122,6 +123,12 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start, extern const char *powerpc_base_platform; +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +extern void cpu_feature_keys_init(void); +#else +static inline void cpu_feature_keys_init(void) { } +#endif + /* TLB flush actions. Used as argument to cpu_spec.flush_tlb() hook */ enum { TLB_INVAL_SCOPE_GLOBAL = 0, /* invalidate all TLBs */ @@ -576,14 +583,6 @@ enum { }; #endif /* __powerpc64__ */ -static inline int cpu_has_feature(unsigned long feature) -{ - return (CPU_FTRS_ALWAYS & feature) || - (CPU_FTRS_POSSIBLE - & cur_cpu_spec->cpu_features - & feature); -} - #define HBP_NUM 1 #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 2dfd4fc41f3e..4f60db074725 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -28,6 +28,7 @@ static inline void setup_cputime_one_jiffy(void) { } #include <asm/div64.h> #include <asm/time.h> #include <asm/param.h> +#include <asm/cpu_has_feature.h> typedef u64 __nocast cputime_t; typedef u64 __nocast cputime64_t; diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 5fa6b20eba10..378167377065 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -16,6 +16,7 @@ #include <linux/threads.h> #include <asm/ppc-opcode.h> +#include <asm/cpu_has_feature.h> #define PPC_DBELL_MSG_BRDCAST (0x04000000) #define PPC_DBELL_TYPE(x) (((x) & 0xf) << (63-36)) diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 4efc11dacb98..4a2beef74277 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -24,6 +24,7 @@ #include <linux/spinlock.h> #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> typedef struct { unsigned int base; diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 77816acd4fd9..84e3f8dd5e4f 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -13,7 +13,6 @@ /* need struct page definitions */ #include <linux/mm.h> #include <linux/scatterlist.h> -#include <linux/dma-attrs.h> #include <linux/dma-debug.h> #include <asm/io.h> #include <asm/swiotlb.h> @@ -25,14 +24,14 @@ /* Some dma direct funcs must be visible for use in other dma_ops */ extern void *__dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs); + unsigned long attrs); extern void __dma_direct_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs); + unsigned long attrs); extern int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t handle, - size_t size, struct dma_attrs *attrs); + size_t size, unsigned long attrs); #ifdef CONFIG_NOT_COHERENT_CACHE /* diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 57fec8ac7b92..ddf54f5bbdd1 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -186,6 +186,7 @@ label##3: \ #ifndef __ASSEMBLY__ void apply_feature_fixups(void); +void setup_feature_keys(void); #endif #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index e2d9f4996e5c..c5517f463ec7 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -147,7 +147,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, { pte_t pte; pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); - flush_tlb_page(vma, addr); + flush_hugetlb_page(vma, addr); } static inline int huge_pte_none(pte_t pte) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f49a72a9062d..2c1d50792944 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -53,7 +53,7 @@ struct iommu_table_ops { long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs); + unsigned long attrs); #ifdef CONFIG_IOMMU_API /* * Exchanges existing TCE with new TCE plus direction bits; @@ -248,12 +248,12 @@ extern int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct scatterlist *sglist, int nelems, unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs); + unsigned long attrs); extern void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs); + unsigned long attrs); extern void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, size_t size, dma_addr_t *dma_handle, @@ -264,10 +264,10 @@ extern dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, struct page *page, unsigned long offset, size_t size, unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs); + unsigned long attrs); extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs); + unsigned long attrs); extern void iommu_init_early_pSeries(void); extern void iommu_init_early_dart(struct pci_controller_ops *controller_ops); diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h index 47e155f15433..9a287e0ac8b1 100644 --- a/arch/powerpc/include/asm/jump_label.h +++ b/arch/powerpc/include/asm/jump_label.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <asm/feature-fixups.h> +#include <asm/asm-compat.h> #define JUMP_ENTRY_TYPE stringify_in_c(FTR_ENTRY_LONG) #define JUMP_LABEL_NOP_SIZE 4 @@ -21,7 +22,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:\n\t" - "nop\n\t" + "nop # arch_static_branch\n\t" ".pushsection __jump_table, \"aw\"\n\t" JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t" ".popsection \n\t" @@ -35,7 +36,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("1:\n\t" - "b %l[l_yes]\n\t" + "b %l[l_yes] # arch_static_branch_jump\n\t" ".pushsection __jump_table, \"aw\"\n\t" JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t" ".popsection \n\t" diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 1f4497fb5b83..88d17b4ea9c8 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -181,8 +181,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, switch (b_psize) { case MMU_PAGE_4K: - sllp = ((mmu_psize_defs[a_psize].sllp & SLB_VSID_L) >> 6) | - ((mmu_psize_defs[a_psize].sllp & SLB_VSID_LP) >> 4); + sllp = get_sllp_encoding(a_psize); rb |= sllp << 5; /* AP field */ rb |= (va_low & 0x7ff) << 12; /* remaining 11 bits of AVA */ break; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 76f5398e7152..0420b388dd83 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -219,8 +219,6 @@ struct machdep_calls { #ifdef CONFIG_ARCH_RANDOM int (*get_random_seed)(unsigned long *v); #endif - int (*register_process_table)(unsigned long base, unsigned long page_size, - unsigned long tbl_size); }; extern void e500_idle(void); diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index fc420cedecae..30922f699341 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -13,6 +13,7 @@ #include <asm/cputable.h> #include <linux/mm.h> +#include <asm/cpu_has_feature.h> /* * This file is included by linux/mman.h, so we can't use cacl_vm_prot_bits() diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 54471228f7b8..e2fb408f8398 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -12,7 +12,7 @@ */ /* - * First half is MMU families + * MMU families */ #define MMU_FTR_HPTE_TABLE ASM_CONST(0x00000001) #define MMU_FTR_TYPE_8xx ASM_CONST(0x00000002) @@ -21,9 +21,13 @@ #define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010) #define MMU_FTR_TYPE_47x ASM_CONST(0x00000020) +/* Radix page table supported and enabled */ +#define MMU_FTR_TYPE_RADIX ASM_CONST(0x00000040) + /* - * This is individual features + * Individual features below. */ + /* * We need to clear top 16bits of va (from the remaining 64 bits )in * tlbie* instructions @@ -93,11 +97,6 @@ */ #define MMU_FTR_1T_SEGMENT ASM_CONST(0x40000000) -/* - * Radix page table available - */ -#define MMU_FTR_RADIX ASM_CONST(0x80000000) - /* MMU feature bit sets for various CPUs */ #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 \ MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2 @@ -113,6 +112,7 @@ #define MMU_FTRS_PA6T MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \ MMU_FTR_CI_LARGE_PAGE | MMU_FTR_NO_SLBIE_B #ifndef __ASSEMBLY__ +#include <linux/bug.h> #include <asm/cputable.h> #ifdef CONFIG_PPC_FSL_BOOK3E @@ -131,20 +131,71 @@ enum { MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE | MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA | #ifdef CONFIG_PPC_RADIX_MMU - MMU_FTR_RADIX | + MMU_FTR_TYPE_RADIX | #endif 0, }; -static inline int mmu_has_feature(unsigned long feature) +static inline bool early_mmu_has_feature(unsigned long feature) { - return (MMU_FTRS_POSSIBLE & cur_cpu_spec->mmu_features & feature); + return !!(MMU_FTRS_POSSIBLE & cur_cpu_spec->mmu_features & feature); +} + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +#include <linux/jump_label.h> + +#define NUM_MMU_FTR_KEYS 32 + +extern struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS]; + +extern void mmu_feature_keys_init(void); + +static __always_inline bool mmu_has_feature(unsigned long feature) +{ + int i; + + BUILD_BUG_ON(!__builtin_constant_p(feature)); + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG + if (!static_key_initialized) { + printk("Warning! mmu_has_feature() used prior to jump label init!\n"); + dump_stack(); + return early_mmu_has_feature(feature); + } +#endif + + if (!(MMU_FTRS_POSSIBLE & feature)) + return false; + + i = __builtin_ctzl(feature); + return static_branch_likely(&mmu_feature_keys[i]); } static inline void mmu_clear_feature(unsigned long feature) { + int i; + + i = __builtin_ctzl(feature); cur_cpu_spec->mmu_features &= ~feature; + static_branch_disable(&mmu_feature_keys[i]); } +#else + +static inline void mmu_feature_keys_init(void) +{ + +} + +static inline bool mmu_has_feature(unsigned long feature) +{ + return early_mmu_has_feature(feature); +} + +static inline void mmu_clear_feature(unsigned long feature) +{ + cur_cpu_spec->mmu_features &= ~feature; +} +#endif /* CONFIG_JUMP_LABEL */ extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup; @@ -164,6 +215,28 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr) } #endif /* !CONFIG_DEBUG_VM */ +#ifdef CONFIG_PPC_RADIX_MMU +static inline bool radix_enabled(void) +{ + return mmu_has_feature(MMU_FTR_TYPE_RADIX); +} + +static inline bool early_radix_enabled(void) +{ + return early_mmu_has_feature(MMU_FTR_TYPE_RADIX); +} +#else +static inline bool radix_enabled(void) +{ + return false; +} + +static inline bool early_radix_enabled(void) +{ + return false; +} +#endif + #endif /* !__ASSEMBLY__ */ /* The kernel use the constants below to index in the page sizes array. @@ -210,6 +283,7 @@ extern void early_init_mmu(void); extern void early_init_mmu_secondary(void); extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); +static inline void mmu_early_init_devtree(void) { } #endif /* __ASSEMBLY__ */ #endif @@ -230,9 +304,5 @@ extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, # include <asm/mmu-8xx.h> #endif -#ifndef radix_enabled -#define radix_enabled() (0) -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 40f3615bf940..f69f40f1519a 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1256,15 +1256,6 @@ static inline void msr_check_and_clear(unsigned long bits) __msr_check_and_clear(bits); } -static inline unsigned long mfvtb (void) -{ -#ifdef CONFIG_PPC_BOOK3S_64 - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - return mfspr(SPRN_VTB); -#endif - return 0; -} - #ifdef __powerpc64__ #if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) #define mftb() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/rtc.h b/arch/powerpc/include/asm/rtc.h deleted file mode 100644 index f5802926b6c0..000000000000 --- a/arch/powerpc/include/asm/rtc.h +++ /dev/null @@ -1,78 +0,0 @@ -/* - * Real-time clock definitions and interfaces - * - * Author: Tom Rini <trini@mvista.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. - * - * Based on: - * include/asm-m68k/rtc.h - * - * Copyright Richard Zidlicky - * implementation details for genrtc/q40rtc driver - * - * And the old drivers/macintosh/rtc.c which was heavily based on: - * Linux/SPARC Real Time Clock Driver - * Copyright (C) 1996 Thomas K. Dyas (tdyas@eden.rutgers.edu) - * - * With additional work by Paul Mackerras and Franz Sirl. - */ - -#ifndef __ASM_POWERPC_RTC_H__ -#define __ASM_POWERPC_RTC_H__ - -#ifdef __KERNEL__ - -#include <linux/rtc.h> - -#include <asm/machdep.h> -#include <asm/time.h> - -#define RTC_PIE 0x40 /* periodic interrupt enable */ -#define RTC_AIE 0x20 /* alarm interrupt enable */ -#define RTC_UIE 0x10 /* update-finished interrupt enable */ - -/* some dummy definitions */ -#define RTC_BATT_BAD 0x100 /* battery bad */ -#define RTC_SQWE 0x08 /* enable square-wave output */ -#define RTC_DM_BINARY 0x04 /* all time/date values are BCD if clear */ -#define RTC_24H 0x02 /* 24 hour mode - else hours bit 7 means pm */ -#define RTC_DST_EN 0x01 /* auto switch DST - works f. USA only */ - -static inline unsigned int get_rtc_time(struct rtc_time *time) -{ - if (ppc_md.get_rtc_time) - ppc_md.get_rtc_time(time); - return RTC_24H; -} - -/* Set the current date and time in the real time clock. */ -static inline int set_rtc_time(struct rtc_time *time) -{ - if (ppc_md.set_rtc_time) - return ppc_md.set_rtc_time(time); - return -EINVAL; -} - -static inline unsigned int get_rtc_ss(void) -{ - struct rtc_time h; - - get_rtc_time(&h); - return h.tm_sec; -} - -static inline int get_rtc_pll(struct rtc_pll_info *pll) -{ - return -EINVAL; -} -static inline int set_rtc_pll(struct rtc_pll_info *pll) -{ - return -EINVAL; -} - -#endif /* __KERNEL__ */ -#endif /* __ASM_POWERPC_RTC_H__ */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 09211640a0e0..b240666b7bc1 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -18,6 +18,7 @@ #include <linux/percpu.h> #include <asm/processor.h> +#include <asm/cpu_has_feature.h> /* time.c */ extern unsigned long tb_ticks_per_jiffy; @@ -103,7 +104,7 @@ static inline u64 get_vtb(void) { #ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_ARCH_207S)) - return mfvtb(); + return mfspr(SPRN_VTB); #endif return 0; } diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 20733fa518ae..f6f68f73e858 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -46,5 +46,18 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, #endif } +#ifdef CONFIG_SMP +static inline int mm_is_core_local(struct mm_struct *mm) +{ + return cpumask_subset(mm_cpumask(mm), + topology_sibling_cpumask(smp_processor_id())); +} +#else +static inline int mm_is_core_local(struct mm_struct *mm) +{ + return 1; +} +#endif + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_TLB_H */ diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 1b38eea28e5a..13dbcd41885e 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -54,7 +54,6 @@ extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, #define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr) #define __flush_tlb_page(mm,addr,p,i) __local_flush_tlb_page(mm,addr,p,i) #endif -#define flush_tlb_page_nohash(vma,addr) flush_tlb_page(vma,addr) #elif defined(CONFIG_PPC_STD_MMU_32) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index b7c20f0b8fbe..c1dc6c14deb8 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -310,10 +310,15 @@ static inline unsigned long copy_from_user(void *to, { unsigned long over; - if (access_ok(VERIFY_READ, from, n)) + if (access_ok(VERIFY_READ, from, n)) { + if (!__builtin_constant_p(n)) + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); + } if ((unsigned long)from < TASK_SIZE) { over = (unsigned long)from + n - TASK_SIZE; + if (!__builtin_constant_p(n - over)) + check_object_size(to, n - over, false); return __copy_tofrom_user((__force void __user *)to, from, n - over) + over; } @@ -325,10 +330,15 @@ static inline unsigned long copy_to_user(void __user *to, { unsigned long over; - if (access_ok(VERIFY_WRITE, to, n)) + if (access_ok(VERIFY_WRITE, to, n)) { + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force void __user *)from, n); + } if ((unsigned long)to < TASK_SIZE) { over = (unsigned long)to + n - TASK_SIZE; + if (!__builtin_constant_p(n)) + check_object_size(from, n - over, true); return __copy_tofrom_user(to, (__force void __user *)from, n - over) + over; } @@ -372,6 +382,10 @@ static inline unsigned long __copy_from_user_inatomic(void *to, if (ret == 0) return 0; } + + if (!__builtin_constant_p(n)) + check_object_size(to, n, false); + return __copy_tofrom_user((__force void __user *)to, from, n); } @@ -398,6 +412,9 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to, if (ret == 0) return 0; } + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); + return __copy_tofrom_user(to, (__force const void __user *)from, n); } diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f5f729c11578..f0b238516e9b 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -159,6 +159,8 @@ extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); extern void xics_migrate_irqs_away(void); extern void icp_native_eoi(struct irq_data *d); +extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type); +extern int xics_retrigger(struct irq_data *data); #ifdef CONFIG_SMP extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check); diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h index 0abb97f3be10..a36c2069d8ed 100644 --- a/arch/powerpc/include/asm/xor.h +++ b/arch/powerpc/include/asm/xor.h @@ -23,6 +23,7 @@ #ifdef CONFIG_ALTIVEC #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, unsigned long *v2_in); diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index c2d21d11c2d2..3a9e44c45c78 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -91,6 +91,11 @@ #define ELF_NGREG 48 /* includes nip, msr, lr, etc. */ #define ELF_NFPREG 33 /* includes fpscr */ +#define ELF_NVMX 34 /* includes all vector registers */ +#define ELF_NVSX 32 /* includes all VSX registers */ +#define ELF_NTMSPRREG 3 /* include tfhar, tfiar, texasr */ +#define ELF_NEBB 3 /* includes ebbrr, ebbhr, bescr */ +#define ELF_NPMU 5 /* includes siar, sdar, sier, mmcr2, mmcr0 */ typedef unsigned long elf_greg_t64; typedef elf_greg_t64 elf_gregset_t64[ELF_NGREG]; diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index c7097f933114..033f3385fa49 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -26,6 +26,7 @@ #include <asm/emulated_ops.h> #include <asm/switch_to.h> #include <asm/disassemble.h> +#include <asm/cpu_has_feature.h> struct aligninfo { unsigned char len; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index d81f826d1029..74248ab18e98 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -15,6 +15,7 @@ #include <linux/threads.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/jump_label.h> #include <asm/oprofile_impl.h> #include <asm/cputable.h> @@ -2224,3 +2225,39 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) return NULL; } + +#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS +struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS] = { + [0 ... NUM_CPU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT +}; +EXPORT_SYMBOL_GPL(cpu_feature_keys); + +void __init cpu_feature_keys_init(void) +{ + int i; + + for (i = 0; i < NUM_CPU_FTR_KEYS; i++) { + unsigned long f = 1ul << i; + + if (!(cur_cpu_spec->cpu_features & f)) + static_branch_disable(&cpu_feature_keys[i]); + } +} + +struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS] = { + [0 ... NUM_MMU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT +}; +EXPORT_SYMBOL_GPL(mmu_feature_keys); + +void __init mmu_feature_keys_init(void) +{ + int i; + + for (i = 0; i < NUM_MMU_FTR_KEYS; i++) { + unsigned long f = 1ul << i; + + if (!(cur_cpu_spec->mmu_features & f)) + static_branch_disable(&mmu_feature_keys[i]); + } +} +#endif diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 41a7d9d49a5a..fb7cbaa37658 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -18,7 +18,7 @@ */ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size, dma_handle, dev->coherent_dma_mask, flag, @@ -27,7 +27,7 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size, static void dma_iommu_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle); } @@ -40,7 +40,7 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size, static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return iommu_map_page(dev, get_iommu_table_base(dev), page, offset, size, device_to_mask(dev), direction, attrs); @@ -49,7 +49,7 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction, attrs); @@ -58,7 +58,7 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems, device_to_mask(dev), direction, attrs); @@ -66,7 +66,7 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction, attrs); diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 3f1472a78f39..e64a6016fba7 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -64,7 +64,7 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask) void *__dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret; #ifdef CONFIG_NOT_COHERENT_CACHE @@ -121,7 +121,7 @@ void *__dma_direct_alloc_coherent(struct device *dev, size_t size, void __dma_direct_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { #ifdef CONFIG_NOT_COHERENT_CACHE __dma_free_coherent(size, vaddr); @@ -132,7 +132,7 @@ void __dma_direct_free_coherent(struct device *dev, size_t size, static void *dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *iommu; @@ -156,7 +156,7 @@ static void *dma_direct_alloc_coherent(struct device *dev, size_t size, static void dma_direct_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *iommu; @@ -177,7 +177,7 @@ static void dma_direct_free_coherent(struct device *dev, size_t size, int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t handle, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long pfn; @@ -195,7 +195,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -211,7 +211,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { } @@ -232,7 +232,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(dir == DMA_NONE); __dma_sync_page(page, offset, size, dir); @@ -243,7 +243,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { } diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c9bc78e9c610..7429556eb8df 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) int n = 0, l = 0; char buffer[128]; - n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n", + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); - pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n", + pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index fcb2887f5a33..6b8bc0dd09d4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -532,7 +532,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 694def6c9d61..df6d45eb4115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -144,29 +144,14 @@ machine_check_pSeries_1: * vector */ SET_SCRATCH0(r13) /* save r13 */ -#ifdef CONFIG_PPC_P7_NAP -BEGIN_FTR_SECTION - /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + /* + * Running native on arch 2.06 or later, we may wakeup from winkle + * inside machine check. If yes, then last bit of HSPGR0 would be set + * to 1. Hence clear it unconditionally. */ - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - beq 9f - - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal. let's just stay stuck here */ - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - bgt cr1,. -9: - OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#endif /* CONFIG_PPC_P7_NAP */ + GET_PACA(r13) + clrrdi r13,r13,1 + SET_PACA(r13) EXCEPTION_PROLOG_0(PACA_EXMC) BEGIN_FTR_SECTION b machine_check_powernv_early @@ -940,7 +925,7 @@ BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) .align 7 .globl h_data_storage_common @@ -971,7 +956,7 @@ BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) @@ -1273,25 +1258,51 @@ machine_check_handle_early: * Check if thread was in power saving mode. We come here when any * of the following is true: * a. thread wasn't in power saving mode - * b. thread was in power saving mode with no state loss or - * supervisor state loss + * b. thread was in power saving mode with no state loss, + * supervisor state loss or hypervisor state loss. * - * Go back to nap again if (b) is true. + * Go back to nap/sleep/winkle mode again if (b) is true. */ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ beq 4f /* No, it wasn;t */ /* Thread was in power saving mode. Go back to nap again. */ cmpwi r11,2 - bne 3f - /* Supervisor state loss */ + blt 3f + /* Supervisor/Hypervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) 3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - li r3,PNV_THREAD_NAP - b pnv_enter_arch207_idle_mode + /* + * Check what idle state this CPU was in and go back to same mode + * again. + */ + lbz r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi r3,PNV_THREAD_NAP + bgt 10f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +10: + cmpwi r3,PNV_THREAD_SLEEP + bgt 2f + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + /* No return */ + +2: + /* + * Go back to winkle. Please note that this thread was woken up in + * machine check from winkle and have not restored the per-subcore + * state. Hence before going back to winkle, set last bit of HSPGR0 + * to 1. This will make sure that if this thread gets woken up + * again at reset vector 0x100 then it will get chance to restore + * the subcore state. + */ + ori r13,r13,1 + SET_PACA(r13) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + /* No return */ 4: #endif /* @@ -1392,7 +1403,7 @@ slb_miss_realmode: #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION bl slb_allocate_realmode -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) #endif /* All done -- return from exception. */ @@ -1406,7 +1417,7 @@ BEGIN_MMU_FTR_SECTION beq- 2f FTR_SECTION_ELSE b 2f -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) .machine push .machine "power4" diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index a89f4f7a66bd..c1ca9282f4a0 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -65,7 +65,7 @@ static void *ibmebus_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { void *mem; @@ -78,7 +78,7 @@ static void *ibmebus_alloc_coherent(struct device *dev, static void ibmebus_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { kfree(vaddr); } @@ -88,7 +88,7 @@ static dma_addr_t ibmebus_map_page(struct device *dev, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return (dma_addr_t)(page_address(page) + offset); } @@ -97,7 +97,7 @@ static void ibmebus_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return; } @@ -105,7 +105,7 @@ static void ibmebus_unmap_page(struct device *dev, static int ibmebus_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -121,7 +121,7 @@ static int ibmebus_map_sg(struct device *dev, static void ibmebus_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { return; } diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 8a56a51fc0cb..2265c6398a17 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -44,18 +44,6 @@ PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ PSSCR_MTL_MASK -/* Idle state entry routines */ - -#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ - /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ - std r0,0(r1); \ - ptesync; \ - ld r0,0(r1); \ -1: cmp cr0,r0,r0; \ - bne 1b; \ - IDLE_INST; \ - b . - .text /* @@ -363,8 +351,8 @@ _GLOBAL(power9_idle_stop) * cr3 - set to gt if waking up with partial/complete hypervisor state loss */ _GLOBAL(pnv_restore_hyp_resource) - ld r2,PACATOC(r13); BEGIN_FTR_SECTION + ld r2,PACATOC(r13); /* * POWER ISA 3. Use PSSCR to determine if we * are waking up from deep idle state @@ -395,6 +383,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) */ clrldi r5,r13,63 clrrdi r13,r13,1 + + /* Now that we are sure r13 is corrected, load TOC */ + ld r2,PACATOC(r13); cmpwi cr4,r5,1 mtspr SPRN_HSPRG0,r13 @@ -572,7 +563,7 @@ common_exit: BEGIN_MMU_FTR_SECTION b no_segments -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) /* Restore SLB from PACA */ ld r8,PACA_SLBSHADOWPTR(r13) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index a8e3490b54e3..37d6e741be82 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -307,7 +307,7 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, void *page, unsigned int npages, enum dma_data_direction direction, unsigned long mask, unsigned int align_order, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long entry; dma_addr_t ret = DMA_ERROR_CODE; @@ -431,7 +431,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct scatterlist *sglist, int nelems, unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dma_next = 0, dma_addr; struct scatterlist *s, *outs, *segstart; @@ -574,7 +574,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; @@ -753,7 +753,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, struct page *page, unsigned long offset, size_t size, unsigned long mask, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dma_handle = DMA_ERROR_CODE; void *vaddr; @@ -790,7 +790,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned int npages; @@ -845,7 +845,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, nio_pages = size >> tbl->it_page_shift; io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, - mask >> tbl->it_page_shift, io_order, NULL); + mask >> tbl->it_page_shift, io_order, 0); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); return NULL; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ac910d9982df..08887cf2b20e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -75,6 +75,7 @@ #endif #define CREATE_TRACE_POINTS #include <asm/trace.h> +#include <asm/cpu_has_feature.h> DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index ef267fd9dd22..5e7ece0fda9f 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->in_use = 1; mce->initiator = MCE_INITIATOR_CPU; - if (handled) + /* Mark it recovered if we have handled it and MSR(RI=1). */ + if (handled && (regs->msr & MSR_RI)) mce->disposition = MCE_DISPOSITION_RECOVERED; else mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 93dae296b6be..fa20060ff7a5 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -184,7 +184,7 @@ void setup_paca(struct paca_struct *new_paca) * if we do a GET_PACA() before the feature fixups have been * applied */ - if (cpu_has_feature(CPU_FTR_HVMODE)) + if (early_cpu_has_feature(CPU_FTR_HVMODE)) mtspr(SPRN_SPRG_HPACA, local_paca); #endif mtspr(SPRN_SPRG_PACA, local_paca); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index a5c0153ede37..7fdf324d5b51 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -78,6 +78,7 @@ EXPORT_SYMBOL(get_pci_dma_ops); static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; + u32 prop_32; u64 prop; /* @@ -86,8 +87,10 @@ static int get_phb_number(struct device_node *dn) * reading "ibm,opal-phbid", only present in OPAL environment. */ ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); - if (ret) - ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop); + if (ret) { + ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); + prop = prop_32; + } if (!ret) phb_id = (int)(prop & (MAX_PHBS - 1)); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a8cca88e972f..9ee2623e0f67 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -58,6 +58,7 @@ #include <asm/code-patching.h> #include <asm/exec.h> #include <asm/livepatch.h> +#include <asm/cpu_has_feature.h> #include <linux/kprobes.h> #include <linux/kdebug.h> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index bae3db791150..b0245bed6f54 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -170,7 +170,7 @@ static struct ibm_pa_feature { */ {CPU_FTR_TM_COMP, 0, 0, PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, - {0, MMU_FTR_RADIX, 0, 0, 40, 0, 0}, + {0, MMU_FTR_TYPE_RADIX, 0, 0, 40, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -647,14 +647,6 @@ static void __init early_reserve_mem(void) #endif } -static bool disable_radix; -static int __init parse_disable_radix(char *p) -{ - disable_radix = true; - return 0; -} -early_param("disable_radix", parse_disable_radix); - void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -744,11 +736,8 @@ void __init early_init_devtree(void *params) */ spinning_secondaries = boot_cpu_count - 1; #endif - /* - * now fixup radix MMU mode based on kernel command line - */ - if (disable_radix) - cur_cpu_spec->mmu_features &= ~MMU_FTR_RADIX; + + mmu_early_init_devtree(); #ifdef CONFIG_PPC_POWERNV /* Scan and build the list of machine check recoverable ranges */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6ee4b72cda42..4e74fc588a3f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2940,7 +2940,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { - prom_printf("Booting Linux via __start() ...\n"); + prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); prom_debug("->dt_header_start=0x%x\n", hdr); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 134bee9ac664..bf91658a8a40 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -38,6 +38,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/switch_to.h> +#include <asm/tm.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -64,6 +65,10 @@ struct pt_regs_offset { {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])} #define REG_OFFSET_END {.name = NULL, .offset = 0} +#define TVSO(f) (offsetof(struct thread_vr_state, f)) +#define TFSO(f) (offsetof(struct thread_fp_state, f)) +#define TSO(f) (offsetof(struct thread_struct, f)) + static const struct pt_regs_offset regoffset_table[] = { GPR_OFFSET_NAME(0), GPR_OFFSET_NAME(1), @@ -114,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = { REG_OFFSET_END, }; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void flush_tmregs_to_thread(struct task_struct *tsk) +{ + /* + * If task is not current, it will have been flushed already to + * it's thread_struct during __switch_to(). + * + * A reclaim flushes ALL the state. + */ + + if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(TM_CAUSE_SIGNAL); + +} +#else +static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } +#endif + /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register @@ -181,6 +204,26 @@ static int set_user_msr(struct task_struct *task, unsigned long msr) return 0; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static unsigned long get_user_ckpt_msr(struct task_struct *task) +{ + return task->thread.ckpt_regs.msr | task->thread.fpexc_mode; +} + +static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr) +{ + task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE; + task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE; + return 0; +} + +static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap) +{ + task->thread.ckpt_regs.trap = trap & 0xfff0; + return 0; +} +#endif + #ifdef CONFIG_PPC64 static int get_user_dscr(struct task_struct *task, unsigned long *data) { @@ -358,6 +401,29 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, return ret; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which returns the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + * }; + * + * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM + * which determines the final code in this function. All the combinations of + * these two config options are possible except the one below as transactional + * memory config pulls in CONFIG_VSX automatically. + * + * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -368,14 +434,31 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #endif flush_fp_to_thread(target); -#ifdef CONFIG_VSX +#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + /* copy to local buffer then write that out */ + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_TRANS_FPR(i); + buf[32] = target->thread.transact_fp.fpscr; + } else { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_FPR(i); + buf[32] = target->thread.fp_state.fpscr; + } + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +#endif + +#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) buf[i] = target->thread.TS_FPR(i); buf[32] = target->thread.fp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +#endif -#else +#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -384,6 +467,29 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #endif } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which setss the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + * }; + * + * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM + * which determines the final code in this function. All the combinations of + * these two config options are possible except the one below as transactional + * memory config pulls in CONFIG_VSX automatically. + * + * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) @@ -394,7 +500,27 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, #endif flush_fp_to_thread(target); -#ifdef CONFIG_VSX +#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) + /* copy to local buffer then write that out */ + i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); + if (i) + return i; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + for (i = 0; i < 32 ; i++) + target->thread.TS_TRANS_FPR(i) = buf[i]; + target->thread.transact_fp.fpscr = buf[32]; + } else { + for (i = 0; i < 32 ; i++) + target->thread.TS_FPR(i) = buf[i]; + target->thread.fp_state.fpscr = buf[32]; + } + return 0; +#endif + +#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) @@ -403,7 +529,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, target->thread.TS_FPR(i) = buf[i]; target->thread.fp_state.fpscr = buf[32]; return 0; -#else +#endif + +#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -433,10 +561,28 @@ static int vr_active(struct task_struct *target, return target->thread.used_vr ? regset->n : 0; } +/* + * When the transaction is active, 'transact_vr' holds the current running + * value of all the VMX registers and 'vr_state' holds the last checkpointed + * value of all the VMX registers for the current transaction to fall back + * on in case it aborts. When transaction is not active 'vr_state' holds + * the current running state of all the VMX registers. So this function which + * gets the current running values of all the VMX registers, needs to know + * whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + * }; + */ static int vr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -444,8 +590,19 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_fp_to_thread(target); + flush_tmregs_to_thread(target); + addr = &target->thread.transact_vr; + } else { + addr = &target->thread.vr_state; + } +#else + addr = &target->thread.vr_state; +#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + addr, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -456,7 +613,16 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + vrsave.word = target->thread.transact_vrsave; + else + vrsave.word = target->thread.vrsave; +#else vrsave.word = target->thread.vrsave; +#endif + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); } @@ -464,10 +630,28 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, return ret; } +/* + * When the transaction is active, 'transact_vr' holds the current running + * value of all the VMX registers and 'vr_state' holds the last checkpointed + * value of all the VMX registers for the current transaction to fall back + * on in case it aborts. When transaction is not active 'vr_state' holds + * the current running state of all the VMX registers. So this function which + * sets the current running values of all the VMX registers, needs to know + * whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + * }; + */ static int vr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { + struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -475,8 +659,19 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + flush_fp_to_thread(target); + flush_tmregs_to_thread(target); + addr = &target->thread.transact_vr; + } else { + addr = &target->thread.vr_state; + } +#else + addr = &target->thread.vr_state; +#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + addr, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -487,11 +682,28 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + vrsave.word = target->thread.transact_vrsave; + else + vrsave.word = target->thread.vrsave; +#else vrsave.word = target->thread.vrsave; +#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); - if (!ret) + if (!ret) { + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + target->thread.transact_vrsave = vrsave.word; + else + target->thread.vrsave = vrsave.word; +#else target->thread.vrsave = vrsave.word; +#endif + } } return ret; @@ -512,6 +724,21 @@ static int vsr_active(struct task_struct *target, return target->thread.used_vsr ? regset->n : 0; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which returns the current running values of + * all the FPR registers, needs to know whether any transaction is active + * or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 vsx[32]; + * }; + */ static int vsr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -519,16 +746,47 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret, i; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); +#endif flush_vsx_to_thread(target); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread. + transact_fp.fpr[i][TS_VSRLOWOFFSET]; + } else { + for (i = 0; i < 32 ; i++) + buf[i] = target->thread. + fp_state.fpr[i][TS_VSRLOWOFFSET]; + } +#else for (i = 0; i < 32 ; i++) buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; +#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); return ret; } +/* + * When the transaction is active, 'transact_fp' holds the current running + * value of all FPR registers and 'fp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. When transaction + * is not active 'fp_state' holds the current running state of all the FPR + * registers. So this function which sets the current running values of all + * the FPR registers, needs to know whether any transaction is active or not. + * + * Userspace interface buffer layout: + * + * struct data { + * u64 vsx[32]; + * }; + */ static int vsr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) @@ -536,12 +794,30 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret,i; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); +#endif flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(target->thread.regs->msr)) { + for (i = 0; i < 32 ; i++) + target->thread.transact_fp. + fpr[i][TS_VSRLOWOFFSET] = buf[i]; + } else { + for (i = 0; i < 32 ; i++) + target->thread.fp_state. + fpr[i][TS_VSRLOWOFFSET] = buf[i]; + } +#else for (i = 0; i < 32 ; i++) target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; +#endif return ret; @@ -614,8 +890,1030 @@ static int evr_set(struct task_struct *target, const struct user_regset *regset, } #endif /* CONFIG_SPE */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +/** + * tm_cgpr_active - get active number of registers in CGPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed GPR category. + */ +static int tm_cgpr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cgpr_get - get CGPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets transaction checkpointed GPR registers. + * + * When the transaction is active, 'ckpt_regs' holds all the checkpointed + * GPR register values for the current transaction to fall back on if it + * aborts in between. This function gets those checkpointed GPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * struct pt_regs ckpt_regs; + * }; + */ +static int tm_cgpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs, + 0, offsetof(struct pt_regs, msr)); + if (!ret) { + unsigned long msr = get_user_ckpt_msr(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr, + offsetof(struct pt_regs, msr), + offsetof(struct pt_regs, msr) + + sizeof(msr)); + } + + BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) != + offsetof(struct pt_regs, msr) + sizeof(long)); + + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs.orig_gpr3, + offsetof(struct pt_regs, orig_gpr3), + sizeof(struct pt_regs)); + if (!ret) + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + sizeof(struct pt_regs), -1); + + return ret; +} /* + * tm_cgpr_set - set the CGPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed GPR registers. + * + * When the transaction is active, 'ckpt_regs' holds the checkpointed + * GPR register values for the current transaction to fall back on if it + * aborts in between. This function sets those checkpointed GPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * struct pt_regs ckpt_regs; + * }; + */ +static int tm_cgpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned long reg; + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs, + 0, PT_MSR * sizeof(reg)); + + if (!ret && count > 0) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®, + PT_MSR * sizeof(reg), + (PT_MSR + 1) * sizeof(reg)); + if (!ret) + ret = set_user_ckpt_msr(target, reg); + } + + BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) != + offsetof(struct pt_regs, msr) + sizeof(long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ckpt_regs.orig_gpr3, + PT_ORIG_R3 * sizeof(reg), + (PT_MAX_PUT_REG + 1) * sizeof(reg)); + + if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret) + ret = user_regset_copyin_ignore( + &pos, &count, &kbuf, &ubuf, + (PT_MAX_PUT_REG + 1) * sizeof(reg), + PT_TRAP * sizeof(reg)); + + if (!ret && count > 0) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®, + PT_TRAP * sizeof(reg), + (PT_TRAP + 1) * sizeof(reg)); + if (!ret) + ret = set_user_ckpt_trap(target, reg); + } + + if (!ret) + ret = user_regset_copyin_ignore( + &pos, &count, &kbuf, &ubuf, + (PT_TRAP + 1) * sizeof(reg), -1); + + return ret; +} + +/** + * tm_cfpr_active - get active number of registers in CFPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed FPR category. + */ +static int tm_cfpr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cfpr_get - get CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed FPR registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * values for the current transaction to fall back on if it aborts + * in between. This function gets those checkpointed FPR registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + *}; + */ +static int tm_cfpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + u64 buf[33]; + int i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* copy to local buffer then write that out */ + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.TS_FPR(i); + buf[32] = target->thread.fp_state.fpscr; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); +} + +/** + * tm_cfpr_set - set CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed FPR registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * FPR register values for the current transaction to fall back on + * if it aborts in between. This function sets these checkpointed + * FPR registers. The userspace interface buffer layout is as follows. + * + * struct data { + * u64 fpr[32]; + * u64 fpscr; + *}; + */ +static int tm_cfpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 buf[33]; + int i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* copy to local buffer then write that out */ + i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); + if (i) + return i; + for (i = 0; i < 32 ; i++) + target->thread.TS_FPR(i) = buf[i]; + target->thread.fp_state.fpscr = buf[32]; + return 0; +} + +/** + * tm_cvmx_active - get active number of registers in CVMX + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in checkpointed VMX category. + */ +static int tm_cvmx_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + return regset->n; +} + +/** + * tm_cvmx_get - get CMVX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed VMX registers. + * + * When the transaction is active 'vr_state' and 'vr_save' hold + * the checkpointed values for the current transaction to fall + * back on if it aborts in between. The userspace interface buffer + * layout is as follows. + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + *}; + */ +static int tm_cvmx_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32])); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.vr_state, 0, + 33 * sizeof(vector128)); + if (!ret) { + /* + * Copy out only the low-order word of vrsave. + */ + union { + elf_vrreg_t reg; + u32 word; + } vrsave; + memset(&vrsave, 0, sizeof(vrsave)); + vrsave.word = target->thread.vrsave; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, + 33 * sizeof(vector128), -1); + } + + return ret; +} + +/** + * tm_cvmx_set - set CMVX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed VMX registers. + * + * When the transaction is active 'vr_state' and 'vr_save' hold + * the checkpointed values for the current transaction to fall + * back on if it aborts in between. The userspace interface buffer + * layout is as follows. + * + * struct data { + * vector128 vr[32]; + * vector128 vscr; + * vector128 vrsave; + *}; + */ +static int tm_cvmx_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32])); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.vr_state, 0, + 33 * sizeof(vector128)); + if (!ret && count > 0) { + /* + * We use only the low-order word of vrsave. + */ + union { + elf_vrreg_t reg; + u32 word; + } vrsave; + memset(&vrsave, 0, sizeof(vrsave)); + vrsave.word = target->thread.vrsave; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, + 33 * sizeof(vector128), -1); + if (!ret) + target->thread.vrsave = vrsave.word; + } + + return ret; +} + +/** + * tm_cvsx_active - get active number of registers in CVSX + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks for the active number of available + * regisers in transaction checkpointed VSX category. + */ +static int tm_cvsx_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return 0; + + flush_vsx_to_thread(target); + return target->thread.used_vsr ? regset->n : 0; +} + +/** + * tm_cvsx_get - get CVSX registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets in transaction checkpointed VSX registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * values for the current transaction to fall back on if it aborts + * in between. This function gets those checkpointed VSX registers. + * The userspace interface buffer layout is as follows. + * + * struct data { + * u64 vsx[32]; + *}; + */ +static int tm_cvsx_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + u64 buf[32]; + int ret, i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + flush_vsx_to_thread(target); + + for (i = 0; i < 32 ; i++) + buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + buf, 0, 32 * sizeof(double)); + + return ret; +} + +/** + * tm_cvsx_set - set CFPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets in transaction checkpointed VSX registers. + * + * When the transaction is active 'fp_state' holds the checkpointed + * VSX register values for the current transaction to fall back on + * if it aborts in between. This function sets these checkpointed + * FPR registers. The userspace interface buffer layout is as follows. + * + * struct data { + * u64 vsx[32]; + *}; + */ +static int tm_cvsx_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 buf[32]; + int ret, i; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + /* Flush the state */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + flush_vsx_to_thread(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + buf, 0, 32 * sizeof(double)); + for (i = 0; i < 32 ; i++) + target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + + return ret; +} + +/** + * tm_spr_active - get active number of registers in TM SPR + * @target: The target task. + * @regset: The user regset structure. + * + * This function checks the active number of available + * regisers in the transactional memory SPR category. + */ +static int tm_spr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + return regset->n; +} + +/** + * tm_spr_get - get the TM related SPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy from. + * @ubuf: User buffer to copy into. + * + * This function gets transactional memory related SPR registers. + * The userspace interface buffer layout is as follows. + * + * struct { + * u64 tm_tfhar; + * u64 tm_texasr; + * u64 tm_tfiar; + * }; + */ +static int tm_spr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + /* Build tests */ + BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr)); + BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar)); + BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs)); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + /* Flush the states */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* TFHAR register */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfhar, 0, sizeof(u64)); + + /* TEXASR register */ + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_texasr, sizeof(u64), + 2 * sizeof(u64)); + + /* TFIAR register */ + if (!ret) + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfiar, + 2 * sizeof(u64), 3 * sizeof(u64)); + return ret; +} + +/** + * tm_spr_set - set the TM related SPR registers + * @target: The target task. + * @regset: The user regset structure. + * @pos: The buffer position. + * @count: Number of bytes to copy. + * @kbuf: Kernel buffer to copy into. + * @ubuf: User buffer to copy from. + * + * This function sets transactional memory related SPR registers. + * The userspace interface buffer layout is as follows. + * + * struct { + * u64 tm_tfhar; + * u64 tm_texasr; + * u64 tm_tfiar; + * }; + */ +static int tm_spr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + /* Build tests */ + BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr)); + BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar)); + BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs)); + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + /* Flush the states */ + flush_fp_to_thread(target); + flush_altivec_to_thread(target); + flush_tmregs_to_thread(target); + + /* TFHAR register */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfhar, 0, sizeof(u64)); + + /* TEXASR register */ + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_texasr, sizeof(u64), + 2 * sizeof(u64)); + + /* TFIAR register */ + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tfiar, + 2 * sizeof(u64), 3 * sizeof(u64)); + return ret; +} + +static int tm_tar_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + +static int tm_tar_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tar, 0, sizeof(u64)); + return ret; +} + +static int tm_tar_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_tar, 0, sizeof(u64)); + return ret; +} + +static int tm_ppr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + + +static int tm_ppr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_ppr, 0, sizeof(u64)); + return ret; +} + +static int tm_ppr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_ppr, 0, sizeof(u64)); + return ret; +} + +static int tm_dscr_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (MSR_TM_ACTIVE(target->thread.regs->msr)) + return regset->n; + + return 0; +} + +static int tm_dscr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_dscr, 0, sizeof(u64)); + return ret; +} + +static int tm_dscr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!cpu_has_feature(CPU_FTR_TM)) + return -ENODEV; + + if (!MSR_TM_ACTIVE(target->thread.regs->msr)) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tm_dscr, 0, sizeof(u64)); + return ret; +} +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +#ifdef CONFIG_PPC64 +static int ppr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); + return ret; +} + +static int ppr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); + return ret; +} + +static int dscr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); + return ret; +} +static int dscr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); + return ret; +} +#endif +#ifdef CONFIG_PPC_BOOK3S_64 +static int tar_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); + return ret; +} +static int tar_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); + return ret; +} + +static int ebb_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (target->thread.used_ebb) + return regset->n; + + return 0; +} + +static int ebb_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* Build tests */ + BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr)); + BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (!target->thread.used_ebb) + return -ENODATA; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbrr, 0, 3 * sizeof(unsigned long)); +} + +static int ebb_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + /* Build tests */ + BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr)); + BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + if (target->thread.used_ebb) + return -ENODATA; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbrr, 0, sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ebbhr, sizeof(unsigned long), + 2 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.bescr, + 2 * sizeof(unsigned long), 3 * sizeof(unsigned long)); + + return ret; +} +static int pmu_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return regset->n; +} + +static int pmu_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* Build tests */ + BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar)); + BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier)); + BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2)); + BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.siar, 0, + 5 * sizeof(unsigned long)); +} + +static int pmu_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret = 0; + + /* Build tests */ + BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar)); + BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier)); + BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2)); + BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0)); + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return -ENODEV; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.siar, 0, + sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.sdar, sizeof(unsigned long), + 2 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.sier, 2 * sizeof(unsigned long), + 3 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.mmcr2, 3 * sizeof(unsigned long), + 4 * sizeof(unsigned long)); + + if (!ret) + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.mmcr0, 4 * sizeof(unsigned long), + 5 * sizeof(unsigned long)); + return ret; +} +#endif +/* * These are our native regset flavors. */ enum powerpc_regset { @@ -630,6 +1928,25 @@ enum powerpc_regset { #ifdef CONFIG_SPE REGSET_SPE, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + REGSET_TM_CGPR, /* TM checkpointed GPR registers */ + REGSET_TM_CFPR, /* TM checkpointed FPR registers */ + REGSET_TM_CVMX, /* TM checkpointed VMX registers */ + REGSET_TM_CVSX, /* TM checkpointed VSX registers */ + REGSET_TM_SPR, /* TM specific SPR registers */ + REGSET_TM_CTAR, /* TM checkpointed TAR register */ + REGSET_TM_CPPR, /* TM checkpointed PPR register */ + REGSET_TM_CDSCR, /* TM checkpointed DSCR register */ +#endif +#ifdef CONFIG_PPC64 + REGSET_PPR, /* PPR register */ + REGSET_DSCR, /* DSCR register */ +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + REGSET_TAR, /* TAR register */ + REGSET_EBB, /* EBB registers */ + REGSET_PMR, /* Performance Monitor Registers */ +#endif }; static const struct user_regset native_regsets[] = { @@ -664,6 +1981,77 @@ static const struct user_regset native_regsets[] = { .active = evr_active, .get = evr_get, .set = evr_set }, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + [REGSET_TM_CGPR] = { + .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + .size = sizeof(long), .align = sizeof(long), + .active = tm_cgpr_active, .get = tm_cgpr_get, .set = tm_cgpr_set + }, + [REGSET_TM_CFPR] = { + .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set + }, + [REGSET_TM_CVMX] = { + .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + .size = sizeof(vector128), .align = sizeof(vector128), + .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set + }, + [REGSET_TM_CVSX] = { + .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set + }, + [REGSET_TM_SPR] = { + .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set + }, + [REGSET_TM_CTAR] = { + .core_note_type = NT_PPC_TM_CTAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set + }, + [REGSET_TM_CPPR] = { + .core_note_type = NT_PPC_TM_CPPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set + }, + [REGSET_TM_CDSCR] = { + .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set + }, +#endif +#ifdef CONFIG_PPC64 + [REGSET_PPR] = { + .core_note_type = NT_PPC_PPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = ppr_get, .set = ppr_set + }, + [REGSET_DSCR] = { + .core_note_type = NT_PPC_DSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = dscr_get, .set = dscr_set + }, +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + [REGSET_TAR] = { + .core_note_type = NT_PPC_TAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = tar_get, .set = tar_set + }, + [REGSET_EBB] = { + .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + .size = sizeof(u64), .align = sizeof(u64), + .active = ebb_active, .get = ebb_get, .set = ebb_set + }, + [REGSET_PMR] = { + .core_note_type = NT_PPC_PMU, .n = ELF_NPMU, + .size = sizeof(u64), .align = sizeof(u64), + .active = pmu_active, .get = pmu_get, .set = pmu_set + }, +#endif }; static const struct user_regset_view user_ppc_native_view = { @@ -674,24 +2062,35 @@ static const struct user_regset_view user_ppc_native_view = { #ifdef CONFIG_PPC64 #include <linux/compat.h> -static int gpr32_get(struct task_struct *target, +static int gpr32_get_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + void *kbuf, void __user *ubuf, bool tm_active) { const unsigned long *regs = &target->thread.regs->gpr[0]; + const unsigned long *ckpt_regs; compat_ulong_t *k = kbuf; compat_ulong_t __user *u = ubuf; compat_ulong_t reg; int i; - if (target->thread.regs == NULL) - return -EIO; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ckpt_regs = &target->thread.ckpt_regs.gpr[0]; +#endif + if (tm_active) { + regs = ckpt_regs; + } else { + if (target->thread.regs == NULL) + return -EIO; - if (!FULL_REGS(target->thread.regs)) { - /* We have a partial register set. Fill 14-31 with bogus values */ - for (i = 14; i < 32; i++) - target->thread.regs->gpr[i] = NV_REG_POISON; + if (!FULL_REGS(target->thread.regs)) { + /* + * We have a partial register set. + * Fill 14-31 with bogus values. + */ + for (i = 14; i < 32; i++) + target->thread.regs->gpr[i] = NV_REG_POISON; + } } pos /= sizeof(reg); @@ -731,20 +2130,31 @@ static int gpr32_get(struct task_struct *target, PT_REGS_COUNT * sizeof(reg), -1); } -static int gpr32_set(struct task_struct *target, +static int gpr32_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + const void *kbuf, const void __user *ubuf, bool tm_active) { unsigned long *regs = &target->thread.regs->gpr[0]; + unsigned long *ckpt_regs; const compat_ulong_t *k = kbuf; const compat_ulong_t __user *u = ubuf; compat_ulong_t reg; - if (target->thread.regs == NULL) - return -EIO; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ckpt_regs = &target->thread.ckpt_regs.gpr[0]; +#endif - CHECK_FULL_REGS(target->thread.regs); + if (tm_active) { + regs = ckpt_regs; + } else { + regs = &target->thread.regs->gpr[0]; + + if (target->thread.regs == NULL) + return -EIO; + + CHECK_FULL_REGS(target->thread.regs); + } pos /= sizeof(reg); count /= sizeof(reg); @@ -804,6 +2214,40 @@ static int gpr32_set(struct task_struct *target, (PT_TRAP + 1) * sizeof(reg), -1); } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static int tm_cgpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 1); +} + +static int tm_cgpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 1); +} +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +static int gpr32_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 0); +} + +static int gpr32_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 0); +} + /* * These are the regset flavors matching the CONFIG_PPC32 native set. */ @@ -832,6 +2276,73 @@ static const struct user_regset compat_regsets[] = { .active = evr_active, .get = evr_get, .set = evr_set }, #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + [REGSET_TM_CGPR] = { + .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + .size = sizeof(long), .align = sizeof(long), + .active = tm_cgpr_active, + .get = tm_cgpr32_get, .set = tm_cgpr32_set + }, + [REGSET_TM_CFPR] = { + .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set + }, + [REGSET_TM_CVMX] = { + .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + .size = sizeof(vector128), .align = sizeof(vector128), + .active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set + }, + [REGSET_TM_CVSX] = { + .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + .size = sizeof(double), .align = sizeof(double), + .active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set + }, + [REGSET_TM_SPR] = { + .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set + }, + [REGSET_TM_CTAR] = { + .core_note_type = NT_PPC_TM_CTAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set + }, + [REGSET_TM_CPPR] = { + .core_note_type = NT_PPC_TM_CPPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set + }, + [REGSET_TM_CDSCR] = { + .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set + }, +#endif +#ifdef CONFIG_PPC64 + [REGSET_PPR] = { + .core_note_type = NT_PPC_PPR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = ppr_get, .set = ppr_set + }, + [REGSET_DSCR] = { + .core_note_type = NT_PPC_DSCR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = dscr_get, .set = dscr_set + }, +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + [REGSET_TAR] = { + .core_note_type = NT_PPC_TAR, .n = 1, + .size = sizeof(u64), .align = sizeof(u64), + .get = tar_get, .set = tar_set + }, + [REGSET_EBB] = { + .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + .size = sizeof(u64), .align = sizeof(u64), + .active = ebb_active, .get = ebb_get, .set = ebb_set + }, +#endif }; static const struct user_regset_view user_ppc_compat_view = { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 714b4ba7ab86..dba265c586df 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -66,6 +66,7 @@ #include <asm/hugetlb.h> #include <asm/livepatch.h> #include <asm/mmu_context.h> +#include <asm/cpu_has_feature.h> #include "setup.h" diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 00f57754407e..24ec3ea4b3a2 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -37,6 +37,7 @@ #include <asm/serial.h> #include <asm/udbg.h> #include <asm/code-patching.h> +#include <asm/cpu_has_feature.h> #define DBG(fmt...) @@ -92,15 +93,16 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * and we are running with enough of the MMU enabled to have our * proper kernel virtual addresses * - * Find out what kind of machine we're on and save any data we need - * from the early boot process (devtree is copied on pmac by prom_init()). - * This is called very early on the boot process, after a minimal - * MMU environment has been set up but before MMU_init is called. + * We do the initial parsing of the flat device-tree and prepares + * for the MMU to be fully initialized. */ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { + /* Configure static keys first, now that we're relocated. */ + setup_feature_keys(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index d8216aed22b7..7ac8e6eaab5b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -227,8 +227,8 @@ static void __init configure_exceptions(void) opal_configure_cores(); /* Enable AIL if supported, and we are in hypervisor mode */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) { + if (early_cpu_has_feature(CPU_FTR_HVMODE) && + early_cpu_has_feature(CPU_FTR_ARCH_207S)) { unsigned long lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); } @@ -298,11 +298,12 @@ void __init early_setup(unsigned long dt_ptr) */ configure_exceptions(); - /* Initialize the hash table or TLB handling */ - early_init_mmu(); - /* Apply all the dynamic patching */ apply_feature_fixups(); + setup_feature_keys(); + + /* Initialize the hash table or TLB handling */ + early_init_mmu(); /* * At this point, we can let interrupts switch to virtual mode diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5a1f015ea9f3..25a39052bf6b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -55,6 +55,7 @@ #include <asm/debug.h> #include <asm/kexec.h> #include <asm/asm-prototypes.h> +#include <asm/cpu_has_feature.h> #ifdef DEBUG #include <asm/udbg.h> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 4e7759c8ca30..3efbedefba6a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -56,6 +56,7 @@ #include <linux/irq_work.h> #include <linux/clk-provider.h> #include <linux/suspend.h> +#include <linux/rtc.h> #include <asm/trace.h> #include <asm/io.h> @@ -1159,6 +1160,29 @@ void calibrate_delay(void) loops_per_jiffy = tb_ticks_per_jiffy; } +#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC) +static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) +{ + ppc_md.get_rtc_time(tm); + return rtc_valid_tm(tm); +} + +static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) +{ + if (!ppc_md.set_rtc_time) + return -EOPNOTSUPP; + + if (ppc_md.set_rtc_time(tm) < 0) + return -EOPNOTSUPP; + + return 0; +} + +static const struct rtc_class_ops rtc_generic_ops = { + .read_time = rtc_generic_get_time, + .set_time = rtc_generic_set_time, +}; + static int __init rtc_init(void) { struct platform_device *pdev; @@ -1166,9 +1190,12 @@ static int __init rtc_init(void) if (!ppc_md.get_rtc_time) return -ENODEV; - pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); + pdev = platform_device_register_data(NULL, "rtc-generic", -1, + &rtc_generic_ops, + sizeof(rtc_generic_ops)); return PTR_ERR_OR_ZERO(pdev); } device_initcall(rtc_init); +#endif diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 6767605ea8da..4111d30badfa 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,6 +22,7 @@ #include <linux/security.h> #include <linux/memblock.h> +#include <asm/cpu_has_feature.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index cbabd143acae..78a7449bf489 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index c710802b8fb6..366ae09b14c1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 8d7358f3a273..b3813ddb2fb4 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -482,7 +482,7 @@ static void vio_cmo_balance(struct work_struct *work) static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); void *ret; @@ -503,7 +503,7 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); @@ -515,7 +515,7 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; @@ -539,7 +539,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; @@ -552,7 +552,7 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; @@ -588,7 +588,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, static void vio_dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a75ba38a2d81..05aa11399a78 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1329,20 +1329,16 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) xics->kvm = kvm; /* Already there ? */ - mutex_lock(&kvm->lock); if (kvm->arch.xics) ret = -EEXIST; else kvm->arch.xics = xics; - mutex_unlock(&kvm->lock); if (ret) { kfree(xics); return ret; } - xics_debugfs_init(xics); - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE if (cpu_has_feature(CPU_FTR_ARCH_206)) { /* Enable real mode support */ @@ -1354,9 +1350,17 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) return 0; } +static void kvmppc_xics_init(struct kvm_device *dev) +{ + struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private; + + xics_debugfs_init(xics); +} + struct kvm_device_ops kvm_xics_ops = { .name = "kvm-xics", .create = kvmppc_xics_create, + .init = kvmppc_xics_init, .destroy = kvmppc_xics_free, .set_attr = xics_set_attr, .get_attr = xics_get_attr, diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index d90870a66b60..0a57fe6d49cc 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -127,8 +127,9 @@ _GLOBAL(csum_partial_copy_generic) stw r7,12(r1) stw r8,8(r1) - andi. r0,r4,1 /* is destination address even ? */ - cmplwi cr7,r0,0 + rlwinm r0,r4,3,0x8 + rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */ + cmplwi cr7,r0,0 /* is destination address even ? */ addic r12,r6,0 addi r6,r4,-4 neg r0,r4 @@ -237,7 +238,7 @@ _GLOBAL(csum_partial_copy_generic) 66: addze r3,r12 addi r1,r1,16 beqlr+ cr7 - rlwinm r3,r3,8,0,31 /* swap bytes for odd destination */ + rlwinm r3,r3,8,0,31 /* odd destination address: rotate one byte */ blr /* read fault */ diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index defb2998b818..043415f0bdb1 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -13,6 +13,7 @@ */ #include <linux/types.h> +#include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> @@ -152,9 +153,18 @@ static void do_final_fixups(void) #endif } -void apply_feature_fixups(void) +static unsigned long __initdata saved_cpu_features; +static unsigned int __initdata saved_mmu_features; +#ifdef CONFIG_PPC64 +static unsigned long __initdata saved_firmware_features; +#endif + +void __init apply_feature_fixups(void) { - struct cpu_spec *spec = *PTRRELOC(&cur_cpu_spec); + struct cpu_spec *spec = PTRRELOC(*PTRRELOC(&cur_cpu_spec)); + + *PTRRELOC(&saved_cpu_features) = spec->cpu_features; + *PTRRELOC(&saved_mmu_features) = spec->mmu_features; /* * Apply the CPU-specific and firmware specific fixups to kernel text @@ -173,12 +183,40 @@ void apply_feature_fixups(void) PTRRELOC(&__stop___lwsync_fixup)); #ifdef CONFIG_PPC64 + saved_firmware_features = powerpc_firmware_features; do_feature_fixups(powerpc_firmware_features, &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); #endif do_final_fixups(); } +void __init setup_feature_keys(void) +{ + /* + * Initialise jump label. This causes all the cpu/mmu_has_feature() + * checks to take on their correct polarity based on the current set of + * CPU/MMU features. + */ + jump_label_init(); + cpu_feature_keys_init(); + mmu_feature_keys_init(); +} + +static int __init check_features(void) +{ + WARN(saved_cpu_features != cur_cpu_spec->cpu_features, + "CPU features changed after feature patching!\n"); + WARN(saved_mmu_features != cur_cpu_spec->mmu_features, + "MMU features changed after feature patching!\n"); +#ifdef CONFIG_PPC64 + WARN(saved_firmware_features != powerpc_firmware_features, + "Firmware features changed after feature patching!\n"); +#endif + + return 0; +} +late_initcall(check_features); + #ifdef CONFIG_FTR_FIXUP_SELFTEST #define check(x) \ diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 88ce7d212320..0e4e9654bd2c 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -72,8 +72,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) /* clear out bits after (52) [0....52.....63] */ va &= ~((1ul << (64 - 52)) - 1); va |= ssize << 8; - sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) | - ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4); + sllp = get_sllp_encoding(apsize); va |= sllp << 5; asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) @@ -122,8 +121,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) /* clear out bits after(52) [0....52.....63] */ va &= ~((1ul << (64 - 52)) - 1); va |= ssize << 8; - sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) | - ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4); + sllp = get_sllp_encoding(apsize); va |= sllp << 5; asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)" : : "r"(va) : "memory"); @@ -749,5 +747,5 @@ void __init hpte_init_native(void) mmu_hash_ops.hugepage_invalidate = native_hugepage_invalidate; if (cpu_has_feature(CPU_FTR_ARCH_300)) - ppc_md.register_process_table = native_register_proc_table; + register_process_table = native_register_proc_table; } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index b78b5d211278..0821556e16f4 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -363,11 +363,6 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node, return 0; } -static void __init htab_init_seg_sizes(void) -{ - of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL); -} - static int __init get_idx_from_shift(unsigned int shift) { int idx = -1; @@ -539,7 +534,7 @@ static bool might_have_hea(void) #endif /* #ifdef CONFIG_PPC_64K_PAGES */ -static void __init htab_init_page_sizes(void) +static void __init htab_scan_page_sizes(void) { int rc; @@ -554,17 +549,23 @@ static void __init htab_init_page_sizes(void) * Try to find the available page sizes in the device-tree */ rc = of_scan_flat_dt(htab_dt_scan_page_sizes, NULL); - if (rc != 0) /* Found */ - goto found; - - /* - * Not in the device-tree, let's fallback on known size - * list for 16M capable GP & GR - */ - if (mmu_has_feature(MMU_FTR_16M_PAGE)) + if (rc == 0 && early_mmu_has_feature(MMU_FTR_16M_PAGE)) { + /* + * Nothing in the device-tree, but the CPU supports 16M pages, + * so let's fallback on a known size list for 16M capable CPUs. + */ memcpy(mmu_psize_defs, mmu_psize_defaults_gp, sizeof(mmu_psize_defaults_gp)); -found: + } + +#ifdef CONFIG_HUGETLB_PAGE + /* Reserve 16G huge page memory sections for huge pages */ + of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); +#endif /* CONFIG_HUGETLB_PAGE */ +} + +static void __init htab_init_page_sizes(void) +{ if (!debug_pagealloc_enabled()) { /* * Pick a size for the linear mapping. Currently, we only @@ -630,11 +631,6 @@ found: ,mmu_psize_defs[mmu_vmemmap_psize].shift #endif ); - -#ifdef CONFIG_HUGETLB_PAGE - /* Reserve 16G huge page memory sections for huge pages */ - of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); -#endif /* CONFIG_HUGETLB_PAGE */ } static int __init htab_dt_scan_pftsize(unsigned long node, @@ -759,12 +755,6 @@ static void __init htab_initialize(void) DBG(" -> htab_initialize()\n"); - /* Initialize segment sizes */ - htab_init_seg_sizes(); - - /* Initialize page sizes */ - htab_init_page_sizes(); - if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) { mmu_kernel_ssize = MMU_SEGSIZE_1T; mmu_highuser_ssize = MMU_SEGSIZE_1T; @@ -885,8 +875,19 @@ static void __init htab_initialize(void) #undef KB #undef MB +void __init hash__early_init_devtree(void) +{ + /* Initialize segment sizes */ + of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL); + + /* Initialize page sizes */ + htab_scan_page_sizes(); +} + void __init hash__early_init_mmu(void) { + htab_init_page_sizes(); + /* * initialize page table size */ diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 1e11559e1aac..35254a678456 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -5,39 +5,34 @@ #include <asm/cacheflush.h> #include <asm/machdep.h> #include <asm/mman.h> +#include <asm/tlb.h> void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { - unsigned long ap, shift; + int psize; struct hstate *hstate = hstate_file(vma->vm_file); - shift = huge_page_shift(hstate); - if (shift == mmu_psize_defs[MMU_PAGE_2M].shift) - ap = mmu_get_ap(MMU_PAGE_2M); - else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift) - ap = mmu_get_ap(MMU_PAGE_1G); - else { - WARN(1, "Wrong huge page shift\n"); - return ; - } - radix___flush_tlb_page(vma->vm_mm, vmaddr, ap, 0); + psize = hstate_get_psize(hstate); + radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, psize); } void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { - unsigned long ap, shift; + int psize; struct hstate *hstate = hstate_file(vma->vm_file); - shift = huge_page_shift(hstate); - if (shift == mmu_psize_defs[MMU_PAGE_2M].shift) - ap = mmu_get_ap(MMU_PAGE_2M); - else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift) - ap = mmu_get_ap(MMU_PAGE_1G); - else { - WARN(1, "Wrong huge page shift\n"); - return ; - } - radix___local_flush_tlb_page(vma->vm_mm, vmaddr, ap, 0); + psize = hstate_get_psize(hstate); + radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, psize); +} + +void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + int psize; + struct hstate *hstate = hstate_file(vma->vm_file); + + psize = hstate_get_psize(hstate); + radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize); } /* diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 33709bdb0419..16ada1eb7e26 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -411,3 +411,25 @@ struct page *realmode_pfn_to_page(unsigned long pfn) EXPORT_SYMBOL_GPL(realmode_pfn_to_page); #endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */ + +#ifdef CONFIG_PPC_STD_MMU_64 +static bool disable_radix; +static int __init parse_disable_radix(char *p) +{ + disable_radix = true; + return 0; +} +early_param("disable_radix", parse_disable_radix); + +void __init mmu_early_init_devtree(void) +{ + /* Disable radix mode based on kernel command line. */ + if (disable_radix) + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + + if (early_radix_enabled()) + radix__early_init_devtree(); + else + hash__early_init_devtree(); +} +#endif /* CONFIG_PPC_STD_MMU_64 */ diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 670318766545..34079302cc17 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -14,6 +14,9 @@ #include "mmu_decl.h" #include <trace/events/thp.h> +int (*register_process_table)(unsigned long base, unsigned long page_size, + unsigned long tbl_size); + #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is called when relaxing access to a hugepage. It's also called in the page @@ -33,7 +36,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, changed = !pmd_same(*(pmdp), entry); if (changed) { __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } @@ -66,7 +69,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); /* * This ensures that generic code that rely on IRQ disabling * to prevent a parallel THP split work as expected. diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 003ff48a11b6..af897d91d09f 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -171,7 +171,7 @@ redo: * of process table here. But our linear mapping also enable us to use * physical address here. */ - ppc_md.register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); + register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd); } @@ -198,7 +198,7 @@ static void __init radix_init_partition_table(void) void __init radix_init_native(void) { - ppc_md.register_process_table = native_register_process_table; + register_process_table = native_register_process_table; } static int __init get_idx_from_shift(unsigned int shift) @@ -264,7 +264,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, return 1; } -static void __init radix_init_page_sizes(void) +void __init radix__early_init_devtree(void) { int rc; @@ -343,7 +343,6 @@ void __init radix__early_init_mmu(void) __pte_frag_nr = H_PTE_FRAG_NR; __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; - radix_init_page_sizes(); if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); lpcr = mfspr(SPRN_LPCR); diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 88a307504b5a..0b6fb244d0a1 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -225,7 +225,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, 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); + flush_tlb_page(vma, address); } return changed; } diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index e1f22700fb16..48df05ef5231 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -140,10 +140,11 @@ void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) } EXPORT_SYMBOL(radix__local_flush_tlb_pwc); -void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - unsigned long ap, int nid) +void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize) { unsigned long pid; + unsigned long ap = mmu_get_ap(psize); preempt_disable(); pid = mm ? mm->context.id : 0; @@ -159,18 +160,12 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd if (vma && is_vm_hugetlb_page(vma)) return __local_flush_hugetlb_page(vma, vmaddr); #endif - radix___local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, - mmu_get_ap(mmu_virtual_psize), 0); + radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr, + mmu_virtual_psize); } EXPORT_SYMBOL(radix__local_flush_tlb_page); #ifdef CONFIG_SMP -static int mm_is_core_local(struct mm_struct *mm) -{ - return cpumask_subset(mm_cpumask(mm), - topology_sibling_cpumask(smp_processor_id())); -} - void radix__flush_tlb_mm(struct mm_struct *mm) { unsigned long pid; @@ -221,10 +216,11 @@ no_context: } EXPORT_SYMBOL(radix__flush_tlb_pwc); -void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, - unsigned long ap, int nid) +void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize) { unsigned long pid; + unsigned long ap = mmu_get_ap(psize); preempt_disable(); pid = mm ? mm->context.id : 0; @@ -250,8 +246,8 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) if (vma && is_vm_hugetlb_page(vma)) return flush_hugetlb_page(vma, vmaddr); #endif - radix___flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, - mmu_get_ap(mmu_virtual_psize), 0); + radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr, + mmu_virtual_psize); } EXPORT_SYMBOL(radix__flush_tlb_page); @@ -299,8 +295,65 @@ static int radix_get_mmu_psize(int page_size) void radix__tlb_flush(struct mmu_gather *tlb) { + int psize = 0; struct mm_struct *mm = tlb->mm; - radix__flush_tlb_mm(mm); + int page_size = tlb->page_size; + + psize = radix_get_mmu_psize(page_size); + /* + * if page size is not something we understand, do a full mm flush + */ + if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all) + radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize); + else + radix__flush_tlb_mm(mm); +} + +#define TLB_FLUSH_ALL -1UL +/* + * Number of pages above which we will do a bcast tlbie. Just a + * number at this point copied from x86 + */ +static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; + +void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize) +{ + unsigned long pid; + unsigned long addr; + int local = mm_is_core_local(mm); + unsigned long ap = mmu_get_ap(psize); + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + unsigned long page_size = 1UL << mmu_psize_defs[psize].shift; + + + preempt_disable(); + pid = mm ? mm->context.id : 0; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto err_out; + + if (end == TLB_FLUSH_ALL || + (end - start) > tlb_single_page_flush_ceiling * page_size) { + if (local) + _tlbiel_pid(pid, RIC_FLUSH_TLB); + else + _tlbie_pid(pid, RIC_FLUSH_TLB); + goto err_out; + } + for (addr = start; addr < end; addr += page_size) { + + if (local) + _tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); + else { + if (lock_tlbie) + raw_spin_lock(&native_tlbie_lock); + _tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); + if (lock_tlbie) + raw_spin_unlock(&native_tlbie_lock); + } + } +err_out: + preempt_enable(); } void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa, @@ -340,3 +393,10 @@ void radix__flush_tlb_lpid(unsigned long lpid) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } EXPORT_SYMBOL(radix__flush_tlb_lpid); + +void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_2M); +} +EXPORT_SYMBOL(radix__flush_pmd_tlb_range); diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c index 558e30cce33e..702d7689d714 100644 --- a/arch/powerpc/mm/tlb_hash32.c +++ b/arch/powerpc/mm/tlb_hash32.c @@ -49,17 +49,6 @@ void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr) EXPORT_SYMBOL(flush_hash_entry); /* - * Called by ptep_set_access_flags, must flush on CPUs for which the - * DSI handler can't just "fixup" the TLB on a write fault - */ -void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr) -{ - if (Hash != 0) - return; - _tlbie(addr); -} - -/* * Called at the end of a mmu_gather operation to make sure the * TLB flush is completely done. */ diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index f4668488512c..050badc0ebd3 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -215,12 +215,6 @@ EXPORT_SYMBOL(local_flush_tlb_page); static DEFINE_RAW_SPINLOCK(tlbivax_lock); -static int mm_is_core_local(struct mm_struct *mm) -{ - return cpumask_subset(mm_cpumask(mm), - topology_sibling_cpumask(smp_processor_id())); -} - struct tlb_flush_param { unsigned long addr; unsigned int pid; diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h index cda6fcb809ca..6447dc1c3d89 100644 --- a/arch/powerpc/perf/power9-events-list.h +++ b/arch/powerpc/perf/power9-events-list.h @@ -34,15 +34,15 @@ EVENT(PM_L1_ICACHE_MISS, 0x200fd) /* Instruction Demand sectors wriittent into IL1 */ EVENT(PM_L1_DEMAND_WRITE, 0x0408c) /* Instruction prefetch written into IL1 */ -EVENT(PM_IC_PREF_WRITE, 0x0408e) +EVENT(PM_IC_PREF_WRITE, 0x0488c) /* The data cache was reloaded from local core's L3 due to a demand load */ EVENT(PM_DATA_FROM_L3, 0x4c042) /* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ EVENT(PM_DATA_FROM_L3MISS, 0x300fe) /* All successful D-side store dispatches for this thread */ -EVENT(PM_L2_ST, 0x16081) +EVENT(PM_L2_ST, 0x16880) /* All successful D-side store dispatches for this thread that were L2 Miss */ -EVENT(PM_L2_ST_MISS, 0x26081) +EVENT(PM_L2_ST_MISS, 0x26880) /* Total HW L3 prefetches(Load+store) */ EVENT(PM_L3_PREF_ALL, 0x4e052) /* Data PTEG reload */ diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 3663f71fd913..fbdae8377b71 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -321,6 +321,17 @@ config OF_RTC Uses information from the OF or flattened device tree to instantiate platform devices for direct mapped RTC chips like the DS1742 or DS1743. +config GEN_RTC + bool "Use the platform RTC operations from user space" + select RTC_CLASS + select RTC_DRV_GENERIC + help + This option provides backwards compatibility with the old gen_rtc.ko + module that was traditionally used for old PowerPC machines. + Platforms should migrate to enabling the RTC_DRV_GENERIC by hand + replacing their get_rtc_time/set_rtc_time callbacks with + a proper RTC device driver. + config SIMPLE_GPIO bool "Support for simple, memory-mapped GPIO controllers" depends on PPC diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 9027d7c48507..f7d1a4953ea0 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -166,7 +166,7 @@ static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte, static int tce_build_cell(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int i; unsigned long *io_pte, base_pte; @@ -193,7 +193,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, base_pte = CBE_IOPTE_PP_W | CBE_IOPTE_PP_R | CBE_IOPTE_M | CBE_IOPTE_SO_RW | (window->ioid & CBE_IOPTE_IOID_Mask); #endif - if (unlikely(dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))) + if (unlikely(attrs & DMA_ATTR_WEAK_ORDERING)) base_pte &= ~CBE_IOPTE_SO_RW; io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); @@ -526,7 +526,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, __set_bit(0, window->table.it_map); tce_build_cell(&window->table, window->table.it_offset, 1, - (unsigned long)iommu->pad_page, DMA_TO_DEVICE, NULL); + (unsigned long)iommu->pad_page, DMA_TO_DEVICE, 0); return window; } @@ -572,7 +572,7 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev) static void *dma_fixed_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { if (iommu_fixed_is_weak) return iommu_alloc_coherent(dev, cell_get_iommu_table(dev), @@ -586,7 +586,7 @@ static void *dma_fixed_alloc_coherent(struct device *dev, size_t size, static void dma_fixed_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { if (iommu_fixed_is_weak) iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr, @@ -598,9 +598,9 @@ static void dma_fixed_free_coherent(struct device *dev, size_t size, static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { - if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs)) + if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING)) return dma_direct_ops.map_page(dev, page, offset, size, direction, attrs); else @@ -611,9 +611,9 @@ static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page, static void dma_fixed_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { - if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs)) + if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING)) dma_direct_ops.unmap_page(dev, dma_addr, size, direction, attrs); else @@ -623,9 +623,9 @@ static void dma_fixed_unmap_page(struct device *dev, dma_addr_t dma_addr, static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { - if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs)) + if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING)) return dma_direct_ops.map_sg(dev, sg, nents, direction, attrs); else return ppc_iommu_map_sg(dev, cell_get_iommu_table(dev), sg, @@ -635,9 +635,9 @@ static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg, static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { - if (iommu_fixed_is_weak == dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs)) + if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING)) dma_direct_ops.unmap_sg(dev, sg, nents, direction, attrs); else ppc_iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents, @@ -1162,7 +1162,7 @@ static int __init setup_iommu_fixed(char *str) pciep = of_find_node_by_type(NULL, "pcie-endpoint"); if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0)) - iommu_fixed_is_weak = 1; + iommu_fixed_is_weak = DMA_ATTR_WEAK_ORDERING; of_node_put(pciep); diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c index d17e98bc0c10..e7d075077cb0 100644 --- a/arch/powerpc/platforms/cell/pervasive.c +++ b/arch/powerpc/platforms/cell/pervasive.c @@ -35,6 +35,7 @@ #include <asm/pgtable.h> #include <asm/reg.h> #include <asm/cell-regs.h> +#include <asm/cpu_has_feature.h> #include "pervasive.h" diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 5be15cff758d..2975754c65ea 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -496,8 +496,10 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode) gang = alloc_spu_gang(); SPUFS_I(inode)->i_ctx = NULL; SPUFS_I(inode)->i_gang = gang; - if (!gang) + if (!gang) { + ret = -ENOMEM; goto out_iput; + } inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 43dd3fb514e0..c61667e8bb06 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -88,7 +88,7 @@ static int iommu_table_iobmap_inited; static int iobmap_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { u32 *ip; u32 rpn; @@ -187,6 +187,11 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) if (dev->vendor == 0x1959 && dev->device == 0xa007 && !firmware_has_feature(FW_FEATURE_LPAR)) { dev->dev.archdata.dma_ops = &dma_direct_ops; + /* + * Set the coherent DMA mask to prevent the iommu + * being used unnecessarily + */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(44); return; } #endif diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 4383a5ff82ba..00e1a0195c78 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(pnv_pci_get_npu_dev); static void *dma_npu_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { NPU_DMA_OP_UNSUPPORTED(); return NULL; @@ -81,7 +81,7 @@ static void *dma_npu_alloc(struct device *dev, size_t size, static void dma_npu_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { NPU_DMA_OP_UNSUPPORTED(); } @@ -89,7 +89,7 @@ static void dma_npu_free(struct device *dev, size_t size, static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { NPU_DMA_OP_UNSUPPORTED(); return 0; @@ -97,7 +97,7 @@ static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page, static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { NPU_DMA_OP_UNSUPPORTED(); return 0; diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index e505223b4ec5..ed8bba68a162 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -228,7 +228,8 @@ int __init opal_event_init(void) } /* Install interrupt handler */ - rc = request_irq(virq, opal_interrupt, 0, "opal", NULL); + rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW, + "opal", NULL); if (rc) { irq_dispose_mapping(virq); pr_warn("Error %d requesting irq %d (0x%x)\n", diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 8b4fc68cebcb..6c9a65b52e63 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -399,6 +399,7 @@ static int opal_recover_mce(struct pt_regs *regs, if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ + pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { /* Platform corrected itself */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 891fc4a453df..fd9444f9fb0c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -111,10 +111,17 @@ static int __init iommu_setup(char *str) } early_param("iommu", iommu_setup); -static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) +static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) { - return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) == - (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)); + /* + * WARNING: We cannot rely on the resource flags. The Linux PCI + * allocation code sometimes decides to put a 64-bit prefetchable + * BAR in the 32-bit window, so we have to compare the addresses. + * + * For simplicity we only test resource start. + */ + return (r->start >= phb->ioda.m64_base && + r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); } static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no) @@ -229,7 +236,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev, sgsz = phb->ioda.m64_segsize; for (i = 0; i <= PCI_ROM_RESOURCE; i++) { r = &pdev->resource[i]; - if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags)) + if (!r->parent || !pnv_pci_is_m64(phb, r)) continue; start = _ALIGN_DOWN(r->start - base, sgsz); @@ -1806,7 +1813,7 @@ static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl, static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int ret = pnv_tce_build(tbl, index, npages, uaddr, direction, attrs); @@ -1877,7 +1884,7 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm, unsigned shift, unsigned long index, unsigned long npages) { - __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false); + __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm); unsigned long start, end, inc; /* We'll invalidate DMA address in PE scope */ @@ -1950,7 +1957,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl, static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { int ret = pnv_tce_build(tbl, index, npages, uaddr, direction, attrs); @@ -2863,7 +2870,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) { + if (!pnv_pci_is_m64(phb, res)) { dev_warn(&pdev->dev, "Don't support SR-IOV with" " non M64 VF BAR%d: %pR. \n", i, res); @@ -2958,7 +2965,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, index++; } } else if ((res->flags & IORESOURCE_MEM) && - !pnv_pci_is_mem_pref_64(res->flags)) { + !pnv_pci_is_m64(phb, res)) { region.start = res->start - phb->hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -3083,9 +3090,12 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, bridge = bridge->bus->self; } - /* We fail back to M32 if M64 isn't supported */ - if (phb->ioda.m64_segsize && - pnv_pci_is_mem_pref_64(type)) + /* + * We fall back to M32 if M64 isn't supported. We enforce the M64 + * alignment for any 64-bit resource, PCIe doesn't care and + * bridges only do 64-bit prefetchable anyway. + */ + if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64)) return phb->ioda.m64_segsize; if (type & IORESOURCE_MEM) return phb->ioda.m32_segsize; @@ -3125,7 +3135,7 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus, w = NULL; if (r->flags & type & IORESOURCE_IO) w = &hose->io_resource; - else if (pnv_pci_is_mem_pref_64(r->flags) && + else if (pnv_pci_is_m64(phb, r) && (type & IORESOURCE_PREFETCH) && phb->ioda.m64_segsize) w = &hose->mem_resources[1]; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 6701dd5ded20..a21d831c1114 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -704,7 +704,7 @@ static __be64 *pnv_tce(struct iommu_table *tbl, long idx) int pnv_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { u64 proto_tce = iommu_direction_to_tce_perm(direction); u64 rpn = __pa(uaddr) >> tbl->it_page_shift; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index d088d4f06116..e64df7894d6e 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -181,7 +181,7 @@ struct pnv_phb { extern struct pci_ops pnv_pci_ops; extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs); + unsigned long attrs); extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages); extern int pnv_tce_xchg(struct iommu_table *tbl, long index, unsigned long *hpa, enum dma_data_direction *direction); diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 5606fe36faf2..8af1c15aef85 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -516,7 +516,7 @@ core_initcall(ps3_system_bus_init); */ static void * ps3_alloc_coherent(struct device *_dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { int result; struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); @@ -553,7 +553,7 @@ clean_none: } static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); @@ -569,7 +569,7 @@ static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr, static dma_addr_t ps3_sb_map_page(struct device *_dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); int result; @@ -592,7 +592,7 @@ static dma_addr_t ps3_sb_map_page(struct device *_dev, struct page *page, static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); int result; @@ -626,7 +626,7 @@ static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page, } static void ps3_unmap_page(struct device *_dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction, struct dma_attrs *attrs) + size_t size, enum dma_data_direction direction, unsigned long attrs) { struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev); int result; @@ -640,7 +640,7 @@ static void ps3_unmap_page(struct device *_dev, dma_addr_t dma_addr, } static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sgl, - int nents, enum dma_data_direction direction, struct dma_attrs *attrs) + int nents, enum dma_data_direction direction, unsigned long attrs) { #if defined(CONFIG_PS3_DYNAMIC_DMA) BUG_ON("do"); @@ -670,14 +670,14 @@ static int ps3_sb_map_sg(struct device *_dev, struct scatterlist *sgl, static int ps3_ioc0_map_sg(struct device *_dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG(); return 0; } static void ps3_sb_unmap_sg(struct device *_dev, struct scatterlist *sg, - int nents, enum dma_data_direction direction, struct dma_attrs *attrs) + int nents, enum dma_data_direction direction, unsigned long attrs) { #if defined(CONFIG_PS3_DYNAMIC_DMA) BUG_ON("do"); @@ -686,7 +686,7 @@ static void ps3_sb_unmap_sg(struct device *_dev, struct scatterlist *sg, static void ps3_ioc0_unmap_sg(struct device *_dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG(); } diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c index 791c6142c4a7..11b45b58c81b 100644 --- a/arch/powerpc/platforms/ps3/time.c +++ b/arch/powerpc/platforms/ps3/time.c @@ -20,9 +20,9 @@ #include <linux/kernel.h> #include <linux/platform_device.h> +#include <linux/rtc.h> #include <asm/firmware.h> -#include <asm/rtc.h> #include <asm/lv1call.h> #include <asm/ps3.h> diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 43f7beb2902d..76ec104e88be 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -320,19 +320,6 @@ static int dlpar_remove_device_tree_lmb(struct of_drconf_cell *lmb) return dlpar_update_device_tree_lmb(lmb); } -static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) -{ - unsigned long section_nr; - struct mem_section *mem_sect; - struct memory_block *mem_block; - - section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - - mem_block = find_memory_block(mem_sect); - return mem_block; -} - #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -420,6 +407,19 @@ static bool lmb_is_removable(struct of_drconf_cell *lmb) static int dlpar_add_lmb(struct of_drconf_cell *); +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + static int dlpar_remove_lmb(struct of_drconf_cell *lmb) { struct memory_block *mem_block; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 770a753b52c9..0024e451bb36 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -123,7 +123,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group, static int tce_build_pSeries(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { u64 proto_tce; __be64 *tcep, *tces; @@ -173,7 +173,7 @@ static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long); static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { u64 rc = 0; u64 proto_tce, tce; @@ -216,7 +216,7 @@ static DEFINE_PER_CPU(__be64 *, tce_page); static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { u64 rc = 0; u64 proto_tce; diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 26904f4879ec..3573d54b2770 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -185,7 +185,7 @@ static void dart_flush(struct iommu_table *tbl) static int dart_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned int *dp, *orig_dp; unsigned int rpn; diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 984e816f3faf..68e7c0dd2e45 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -491,6 +491,7 @@ int fsl_rio_setup(struct platform_device *dev) rmu_node = of_parse_phandle(dev->dev.of_node, "fsl,srio-rmu-handle", 0); if (!rmu_node) { dev_err(&dev->dev, "No valid fsl,srio-rmu-handle property\n"); + rc = -ENOENT; goto err_rmu; } rc = of_address_to_resource(rmu_node, 0, &rmu_regs); diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig index 0031eda320c3..385e7aa9e273 100644 --- a/arch/powerpc/sysdev/xics/Kconfig +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -1,6 +1,7 @@ config PPC_XICS def_bool n select PPC_SMP_MUXED_IPI + select HARDIRQS_SW_RESEND config PPC_ICP_NATIVE def_bool n diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 27c936c080a6..1c6bf4b66f56 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -156,7 +156,9 @@ static struct irq_chip ics_opal_irq_chip = { .irq_mask = ics_opal_mask_irq, .irq_unmask = ics_opal_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_opal_set_affinity + .irq_set_affinity = ics_opal_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_opal_map(struct ics *ics, unsigned int virq); diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c index 3854dd41558d..78ee5c778ef8 100644 --- a/arch/powerpc/sysdev/xics/ics-rtas.c +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -163,7 +163,9 @@ static struct irq_chip ics_rtas_irq_chip = { .irq_mask = ics_rtas_mask_irq, .irq_unmask = ics_rtas_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_rtas_set_affinity + .irq_set_affinity = ics_rtas_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_rtas_map(struct ics *ics, unsigned int virq) diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index a795a5f0301c..9d530f479588 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -328,8 +328,12 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq, pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw); - /* They aren't all level sensitive but we just don't really know */ - irq_set_status_flags(virq, IRQ_LEVEL); + /* + * Mark interrupts as edge sensitive by default so that resend + * actually works. The device-tree parsing will turn the LSIs + * back to level. + */ + irq_clear_status_flags(virq, IRQ_LEVEL); /* Don't call into ICS for IPIs */ if (hw == XICS_IPI) { @@ -351,13 +355,54 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct, irq_hw_number_t *out_hwirq, unsigned int *out_flags) { - /* Current xics implementation translates everything - * to level. It is not technically right for MSIs but this - * is irrelevant at this point. We might get smarter in the future - */ *out_hwirq = intspec[0]; - *out_flags = IRQ_TYPE_LEVEL_LOW; + /* + * If intsize is at least 2, we look for the type in the second cell, + * we assume the LSB indicates a level interrupt. + */ + if (intsize > 1) { + if (intspec[1] & 1) + *out_flags = IRQ_TYPE_LEVEL_LOW; + else + *out_flags = IRQ_TYPE_EDGE_RISING; + } else + *out_flags = IRQ_TYPE_LEVEL_LOW; + + return 0; +} + +int xics_set_irq_type(struct irq_data *d, unsigned int flow_type) +{ + /* + * We only support these. This has really no effect other than setting + * the corresponding descriptor bits mind you but those will in turn + * affect the resend function when re-enabling an edge interrupt. + * + * Set set the default to edge as explained in map(). + */ + if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE) + flow_type = IRQ_TYPE_EDGE_RISING; + + if (flow_type != IRQ_TYPE_EDGE_RISING && + flow_type != IRQ_TYPE_LEVEL_LOW) + return -EINVAL; + + irqd_set_trigger_type(d, flow_type); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +int xics_retrigger(struct irq_data *data) +{ + /* + * We need to push a dummy CPPR when retriggering, since the subsequent + * EOI will try to pop it. Passing 0 works, as the function hard codes + * the priority value anyway. + */ + xics_push_cppr(0); + + /* Tell the core to do a soft retrigger */ return 0; } diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c index 89098f320ad5..ee9891734149 100644 --- a/arch/powerpc/xmon/ppc-dis.c +++ b/arch/powerpc/xmon/ppc-dis.c @@ -20,6 +20,7 @@ along with this file; see the file COPYING. If not, write to the Free Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA. */ #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> #include "nonstdio.h" #include "ansidecl.h" #include "ppc.h" diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9e607bf2d640..e751fe25d6ab 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -123,6 +123,7 @@ config S390 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_EARLY_PFN_TO_NID + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_JUMP_LABEL select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select HAVE_ARCH_SECCOMP_FILTER @@ -871,4 +872,17 @@ config S390_GUEST Select this option if you want to run the kernel as a guest under the KVM hypervisor. +config S390_GUEST_OLD_TRANSPORT + def_bool y + prompt "Guest support for old s390 virtio transport (DEPRECATED)" + depends on S390_GUEST + help + Enable this option to add support for the old s390-virtio + transport (i.e. virtio devices NOT based on virtio-ccw). This + type of virtio devices is only available on the experimental + kuli userspace or with old (< 2.6) qemu. If you are running + with a modern version of qemu (which supports virtio-ccw since + 1.4 and uses it by default since version 2.4), you probably won't + need this. + endmenu diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S index f86a4eef28a9..28c4f96a2d9c 100644 --- a/arch/s390/boot/compressed/head.S +++ b/arch/s390/boot/compressed/head.S @@ -21,16 +21,21 @@ ENTRY(startup_continue) lg %r15,.Lstack-.LPG1(%r13) aghi %r15,-160 brasl %r14,decompress_kernel - # setup registers for memory mover & branch to target + # Set up registers for memory mover. We move the decompressed image to + # 0x11000, starting at offset 0x11000 in the decompressed image so + # that code living at 0x11000 in the image will end up at 0x11000 in + # memory. lgr %r4,%r2 lg %r2,.Loffset-.LPG1(%r13) la %r4,0(%r2,%r4) lg %r3,.Lmvsize-.LPG1(%r13) lgr %r5,%r3 - # move the memory mover someplace safe + # Move the memory mover someplace safe so it doesn't overwrite itself. la %r1,0x200 mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13) - # decompress image is started at 0x11000 + # When the memory mover is done we pass control to + # arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in + # the decompressed image. lgr %r6,%r2 br %r1 mover: diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 889ea3450210..26e0c7f08814 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -678,7 +678,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 1bcfd764910a..24879dab47bc 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -616,7 +616,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 13ff090139c8..a5c1e5f2a0ca 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -615,7 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 577ae1d4ae89..2bad9d837029 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -51,6 +51,9 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); struct kernel_fpu vxstate; \ unsigned long prealign, aligned, remaining; \ \ + if (datalen < VX_MIN_LEN + VX_ALIGN_MASK) \ + return ___crc32_sw(crc, data, datalen); \ + \ if ((unsigned long)data & VX_ALIGN_MASK) { \ prealign = VX_ALIGNMENT - \ ((unsigned long)data & VX_ALIGN_MASK); \ @@ -59,9 +62,6 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); data = (void *)((unsigned long)data + prealign); \ } \ \ - if (datalen < VX_MIN_LEN) \ - return ___crc32_sw(crc, data, datalen); \ - \ aligned = datalen & ~VX_ALIGN_MASK; \ remaining = datalen & VX_ALIGN_MASK; \ \ diff --git a/arch/s390/defconfig b/arch/s390/defconfig index ccccebeeaaf6..73610f2e3b4f 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -234,7 +234,7 @@ CONFIG_CRYPTO_SHA256_S390=m CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRC7=m # CONFIG_XZ_DEC_X86 is not set # CONFIG_XZ_DEC_POWERPC is not set diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h index 3249b7464889..ffaba07f50ab 100644 --- a/arch/s390/include/asm/dma-mapping.h +++ b/arch/s390/include/asm/dma-mapping.h @@ -5,7 +5,6 @@ #include <linux/types.h> #include <linux/mm.h> #include <linux/scatterlist.h> -#include <linux/dma-attrs.h> #include <linux/dma-debug.h> #include <linux/io.h> diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 56e4d8234ef2..4431905f8cfa 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -309,7 +309,9 @@ ENTRY(startup_kdump) l %r15,.Lstack-.LPG0(%r13) ahi %r15,-STACK_FRAME_OVERHEAD brasl %r14,verify_facilities - /* Continue with startup code in head64.S */ +# For uncompressed images, continue in +# arch/s390/kernel/head64.S. For compressed images, continue in +# arch/s390/boot/compressed/head.S. jg startup_continue .Lstack: diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3f3ae4865d57..f142215ed30d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1672,6 +1672,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; /* fprs can be synchronized via vrs, even if the guest has no vx. With @@ -2361,8 +2362,10 @@ retry: rc = gmap_mprotect_notify(vcpu->arch.gmap, kvm_s390_get_prefix(vcpu), PAGE_SIZE * 2, PROT_WRITE); - if (rc) + if (rc) { + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); return rc; + } goto retry; } diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index e390bbb16443..48352bffbc92 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -237,11 +237,10 @@ char * strrchr(const char * s, int c) EXPORT_SYMBOL(strrchr); static inline int clcle(const char *s1, unsigned long l1, - const char *s2, unsigned long l2, - int *diff) + const char *s2, unsigned long l2) { register unsigned long r2 asm("2") = (unsigned long) s1; - register unsigned long r3 asm("3") = (unsigned long) l2; + register unsigned long r3 asm("3") = (unsigned long) l1; register unsigned long r4 asm("4") = (unsigned long) s2; register unsigned long r5 asm("5") = (unsigned long) l2; int cc; @@ -252,7 +251,6 @@ static inline int clcle(const char *s1, unsigned long l1, " srl %0,28" : "=&d" (cc), "+a" (r2), "+a" (r3), "+a" (r4), "+a" (r5) : : "cc"); - *diff = *(char *)r2 - *(char *)r4; return cc; } @@ -270,9 +268,9 @@ char * strstr(const char * s1,const char * s2) return (char *) s1; l1 = __strend(s1) - s1; while (l1-- >= l2) { - int cc, dummy; + int cc; - cc = clcle(s1, l1, s2, l2, &dummy); + cc = clcle(s1, l2, s2, l2); if (!cc) return (char *) s1; s1++; @@ -313,11 +311,11 @@ EXPORT_SYMBOL(memchr); */ int memcmp(const void *cs, const void *ct, size_t n) { - int ret, diff; + int ret; - ret = clcle(cs, n, ct, n, &diff); + ret = clcle(cs, n, ct, n); if (ret) - ret = diff; + ret = ret == 1 ? -1 : 1; return ret; } EXPORT_SYMBOL(memcmp); diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index d96596128e9f..f481fcde067b 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -104,6 +104,7 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr, unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { + check_object_size(to, n, false); if (static_branch_likely(&have_mvcos)) return copy_from_user_mvcos(to, from, n); return copy_from_user_mvcp(to, from, n); @@ -177,6 +178,7 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x, unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { + check_object_size(from, n, true); if (static_branch_likely(&have_mvcos)) return copy_to_user_mvcos(to, from, n); return copy_to_user_mvcs(to, from, n); diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 7104ffb5a67f..af7cf28cf97e 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -252,6 +252,8 @@ static int change_page_attr(unsigned long addr, unsigned long end, int rc = -EINVAL; pgd_t *pgdp; + if (addr == end) + return 0; if (end >= MODULES_END) return -EINVAL; mutex_lock(&cpa_mutex); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 070f1ae5cfad..7297fce9bf80 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -286,7 +286,7 @@ static inline void zpci_err_dma(unsigned long rc, unsigned long addr) static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); unsigned long nr_pages, iommu_page_index; @@ -332,7 +332,7 @@ out_err: static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); unsigned long iommu_page_index; @@ -355,7 +355,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, static void *s390_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); struct page *page; @@ -370,7 +370,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size, pa = page_to_phys(page); memset((void *) pa, 0, size); - map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, NULL); + map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, 0); if (dma_mapping_error(dev, map)) { free_pages(pa, get_order(size)); return NULL; @@ -384,19 +384,19 @@ static void *s390_dma_alloc(struct device *dev, size_t size, static void s390_dma_free(struct device *dev, size_t size, void *pa, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); size = PAGE_ALIGN(size); atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages); - s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL); + s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, 0); free_pages((unsigned long) pa, get_order(size)); } static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg, int nr_elements, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { int mapped_elements = 0; struct scatterlist *s; @@ -405,7 +405,7 @@ static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg, for_each_sg(sg, s, nr_elements, i) { struct page *page = sg_page(s); s->dma_address = s390_dma_map_pages(dev, page, s->offset, - s->length, dir, NULL); + s->length, dir, 0); if (!dma_mapping_error(dev, s->dma_address)) { s->dma_length = s->length; mapped_elements++; @@ -419,7 +419,7 @@ unmap: for_each_sg(sg, s, mapped_elements, i) { if (s->dma_address) s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, - dir, NULL); + dir, 0); s->dma_address = 0; s->dma_length = 0; } @@ -429,13 +429,14 @@ unmap: static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nr_elements, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; for_each_sg(sg, s, nr_elements, i) { - s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, dir, NULL); + s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, dir, + 0); s->dma_address = 0; s->dma_length = 0; } diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 0d5f3a9bb315..ee086958b2b2 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -38,6 +38,7 @@ config SUPERH select GENERIC_IDLE_POLL_SETUP select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST + select GENERIC_SCHED_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_MOD_ARCH_SPECIFIC if DWARF_UNWINDER @@ -45,6 +46,7 @@ config SUPERH select OLD_SIGSUSPEND select OLD_SIGACTION select HAVE_ARCH_AUDITSYSCALL + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_NMI help The SuperH is a RISC processor targeted for use in embedded systems @@ -184,6 +186,12 @@ config CPU_SH2A select CPU_SH2 select UNCACHED_MAPPING +config CPU_J2 + bool + select CPU_SH2 + select OF + select OF_EARLY_FLATTREE + config CPU_SH3 bool select CPU_HAS_INTEVT @@ -250,6 +258,12 @@ config CPU_SUBTYPE_SH7619 select CPU_SH2 select SYS_SUPPORTS_SH_CMT +config CPU_SUBTYPE_J2 + bool "Support J2 processor" + select CPU_J2 + select SYS_SUPPORTS_SMP + select GENERIC_CLOCKEVENTS_BROADCAST if SMP + # SH-2A Processor Support config CPU_SUBTYPE_SH7201 @@ -739,6 +753,26 @@ endmenu menu "Boot options" +config USE_BUILTIN_DTB + bool "Use builtin DTB" + default n + depends on SH_DEVICE_TREE + help + Link a device tree blob for particular hardware into the kernel, + suppressing use of the DTB pointer provided by the bootloader. + This option should only be used with legacy bootloaders that are + not capable of providing a DTB to the kernel, or for experimental + hardware without stable device tree bindings. + +config BUILTIN_DTB_SOURCE + string "Source file for builtin DTB" + default "" + depends on USE_BUILTIN_DTB + help + Base name (without suffix, relative to arch/sh/boot/dts) for the + a DTS file that will be used to produce the DTB linked into the + kernel. + config ZERO_PAGE_OFFSET hex default "0x00010000" if PAGE_SIZE_64KB || SH_RTS7751R2D || \ diff --git a/arch/sh/Makefile b/arch/sh/Makefile index bf5b3f5f4962..00476662ac2c 100644 --- a/arch/sh/Makefile +++ b/arch/sh/Makefile @@ -31,6 +31,7 @@ isa-y := $(isa-y)-up endif cflags-$(CONFIG_CPU_SH2) := $(call cc-option,-m2,) +cflags-$(CONFIG_CPU_J2) := $(call cc-option,-mj2,) cflags-$(CONFIG_CPU_SH2A) += $(call cc-option,-m2a,) \ $(call cc-option,-m2a-nofpu,) \ $(call cc-option,-m4-nofpu,) @@ -130,6 +131,8 @@ head-y := arch/sh/kernel/head_$(BITS).o core-y += arch/sh/kernel/ arch/sh/mm/ arch/sh/boards/ core-$(CONFIG_SH_FPU_EMU) += arch/sh/math-emu/ +core-$(CONFIG_USE_BUILTIN_DTB) += arch/sh/boot/dts/ + # Mach groups machdir-$(CONFIG_SOLUTION_ENGINE) += mach-se machdir-$(CONFIG_SH_HP6XX) += mach-hp6xx diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index e0db04664e2e..e9c2c42031fe 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -11,6 +11,7 @@ config SH_DEVICE_TREE select OF select OF_EARLY_FLATTREE select CLKSRC_OF + select COMMON_CLK select GENERIC_CALIBRATE_DELAY help Select Board Described by Device Tree to build a kernel that diff --git a/arch/sh/boards/board-secureedge5410.c b/arch/sh/boards/board-secureedge5410.c index 98b36205aa7b..97ec67ffec2b 100644 --- a/arch/sh/boards/board-secureedge5410.c +++ b/arch/sh/boards/board-secureedge5410.c @@ -14,7 +14,6 @@ #include <linux/interrupt.h> #include <linux/timer.h> #include <linux/delay.h> -#include <linux/module.h> #include <linux/sched.h> #include <asm/machvec.h> #include <mach/secureedge5410.h> @@ -49,7 +48,7 @@ static int __init eraseconfig_init(void) irq); return 0; } -module_init(eraseconfig_init); +device_initcall(eraseconfig_init); /* * Initialize IRQ setting diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c index 911ffb9f115b..1fb6d5714bae 100644 --- a/arch/sh/boards/of-generic.c +++ b/arch/sh/boards/of-generic.c @@ -124,13 +124,22 @@ static void __init sh_of_time_init(void) static void __init sh_of_setup(char **cmdline_p) { + struct device_node *root; + +#ifdef CONFIG_USE_BUILTIN_DTB + unflatten_and_copy_device_tree(); +#else unflatten_device_tree(); +#endif board_time_init = sh_of_time_init; - sh_mv.mv_name = of_flat_dt_get_machine_name(); - if (!sh_mv.mv_name) - sh_mv.mv_name = "Unknown SH model"; + sh_mv.mv_name = "Unknown SH model"; + root = of_find_node_by_path("/"); + if (root) { + of_property_read_string(root, "model", &sh_mv.mv_name); + of_node_put(root); + } sh_of_smp_probe(); } diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile new file mode 100644 index 000000000000..e5ce3a0de7f4 --- /dev/null +++ b/arch/sh/boot/dts/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o + +clean-files := *.dtb.S diff --git a/arch/sh/boot/dts/j2_mimas_v2.dts b/arch/sh/boot/dts/j2_mimas_v2.dts new file mode 100755 index 000000000000..880de75360b3 --- /dev/null +++ b/arch/sh/boot/dts/j2_mimas_v2.dts @@ -0,0 +1,96 @@ +/dts-v1/; + +/ { + compatible = "jcore,j2-soc"; + model = "J2 FPGA SoC on Mimas v2 board"; + + #address-cells = <1>; + #size-cells = <1>; + + interrupt-parent = <&aic>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "jcore,j2"; + reg = <0>; + clock-frequency = <50000000>; + d-cache-size = <8192>; + i-cache-size = <8192>; + d-cache-block-size = <16>; + i-cache-block-size = <16>; + }; + }; + + memory@10000000 { + device_type = "memory"; + reg = <0x10000000 0x4000000>; + }; + + aliases { + serial0 = &uart0; + spi0 = &spi0; + }; + + chosen { + stdout-path = "serial0"; + }; + + soc@abcd0000 { + compatible = "simple-bus"; + ranges = <0 0xabcd0000 0x100000>; + + #address-cells = <1>; + #size-cells = <1>; + + aic: interrupt-controller@200 { + compatible = "jcore,aic1"; + reg = <0x200 0x10>; + interrupt-controller; + #interrupt-cells = <1>; + }; + + cache-controller@c0 { + compatible = "jcore,cache"; + reg = <0xc0 4>; + }; + + timer@200 { + compatible = "jcore,pit"; + reg = <0x200 0x30>; + interrupts = <0x48>; + }; + + spi0: spi@40 { + compatible = "jcore,spi2"; + + #address-cells = <1>; + #size-cells = <0>; + + spi-max-frequency = <25000000>; + + reg = <0x40 0x8>; + + sdcard@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + spi-max-frequency = <25000000>; + voltage-ranges = <3200 3400>; + mode = <0>; + }; + }; + + uart0: serial@100 { + clock-frequency = <125000000>; + compatible = "xlnx,xps-uartlite-1.00.a"; + current-speed = <19200>; + device_type = "serial"; + interrupts = <0x12>; + port-number = <0>; + reg = <0x100 0x10>; + }; + }; +}; diff --git a/arch/sh/configs/j2_defconfig b/arch/sh/configs/j2_defconfig new file mode 100644 index 000000000000..94d1eca52f72 --- /dev/null +++ b/arch/sh/configs/j2_defconfig @@ -0,0 +1,40 @@ +CONFIG_SMP=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_CPU_SUBTYPE_J2=y +CONFIG_MEMORY_START=0x10000000 +CONFIG_MEMORY_SIZE=0x04000000 +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_SH_DEVICE_TREE=y +CONFIG_HZ_100=y +CONFIG_CMDLINE_OVERWRITE=y +CONFIG_CMDLINE="console=ttyUL0 earlycon" +CONFIG_BINFMT_ELF_FDPIC=y +CONFIG_BINFMT_FLAT=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_NETDEVICES=y +CONFIG_SERIAL_UARTLITE=y +CONFIG_SERIAL_UARTLITE_CONSOLE=y +CONFIG_I2C=y +CONFIG_SPI=y +CONFIG_SPI_JCORE=y +CONFIG_WATCHDOG=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y +CONFIG_CLKSRC_JCORE_PIT=y +CONFIG_JCORE_AIC=y +CONFIG_EXT4_FS=y +CONFIG_VFAT_FS=y +CONFIG_FAT_DEFAULT_IOCHARSET="ascii" +CONFIG_FAT_DEFAULT_UTF8=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_UTF8=y diff --git a/arch/sh/drivers/heartbeat.c b/arch/sh/drivers/heartbeat.c index 7efc9c354fc7..49bace446a1a 100644 --- a/arch/sh/drivers/heartbeat.c +++ b/arch/sh/drivers/heartbeat.c @@ -19,7 +19,6 @@ * for more details. */ #include <linux/init.h> -#include <linux/module.h> #include <linux/platform_device.h> #include <linux/sched.h> #include <linux/timer.h> @@ -139,26 +138,11 @@ static int heartbeat_drv_probe(struct platform_device *pdev) return mod_timer(&hd->timer, jiffies + 1); } -static int heartbeat_drv_remove(struct platform_device *pdev) -{ - struct heartbeat_data *hd = platform_get_drvdata(pdev); - - del_timer_sync(&hd->timer); - iounmap(hd->base); - - platform_set_drvdata(pdev, NULL); - - if (!pdev->dev.platform_data) - kfree(hd); - - return 0; -} - static struct platform_driver heartbeat_driver = { .probe = heartbeat_drv_probe, - .remove = heartbeat_drv_remove, .driver = { - .name = DRV_NAME, + .name = DRV_NAME, + .suppress_bind_attrs = true, }, }; @@ -167,14 +151,4 @@ static int __init heartbeat_init(void) printk(KERN_NOTICE DRV_NAME ": version %s loaded\n", DRV_VERSION); return platform_driver_register(&heartbeat_driver); } - -static void __exit heartbeat_exit(void) -{ - platform_driver_unregister(&heartbeat_driver); -} -module_init(heartbeat_init); -module_exit(heartbeat_exit); - -MODULE_VERSION(DRV_VERSION); -MODULE_AUTHOR("Paul Mundt"); -MODULE_LICENSE("GPL v2"); +device_initcall(heartbeat_init); diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index c399e1c55685..8a7bd80c8b33 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -1,6 +1,12 @@ #ifndef __ASM_SH_ATOMIC_H #define __ASM_SH_ATOMIC_H +#if defined(CONFIG_CPU_J2) + +#include <asm-generic/atomic.h> + +#else + /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. @@ -63,4 +69,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) return c; } +#endif /* CONFIG_CPU_J2 */ + #endif /* __ASM_SH_ATOMIC_H */ diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h index 8a84e05adb2e..3c30b6e166b6 100644 --- a/arch/sh/include/asm/barrier.h +++ b/arch/sh/include/asm/barrier.h @@ -29,6 +29,11 @@ #define wmb() mb() #define ctrl_barrier() __icbi(PAGE_OFFSET) #else +#if defined(CONFIG_CPU_J2) && defined(CONFIG_SMP) +#define __smp_mb() do { int tmp = 0; __asm__ __volatile__ ("cas.l %0,%0,@%1" : "+r"(tmp) : "z"(&tmp) : "memory", "t"); } while(0) +#define __smp_rmb() __smp_mb() +#define __smp_wmb() __smp_mb() +#endif #define ctrl_barrier() __asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop") #endif diff --git a/arch/sh/include/asm/bitops-cas.h b/arch/sh/include/asm/bitops-cas.h new file mode 100644 index 000000000000..88f793c04d3c --- /dev/null +++ b/arch/sh/include/asm/bitops-cas.h @@ -0,0 +1,93 @@ +#ifndef __ASM_SH_BITOPS_CAS_H +#define __ASM_SH_BITOPS_CAS_H + +static inline unsigned __bo_cas(volatile unsigned *p, unsigned old, unsigned new) +{ + __asm__ __volatile__("cas.l %1,%0,@r0" + : "+r"(new) + : "r"(old), "z"(p) + : "t", "memory" ); + return new; +} + +static inline void set_bit(int nr, volatile void *addr) +{ + unsigned mask, old; + volatile unsigned *a = addr; + + a += nr >> 5; + mask = 1U << (nr & 0x1f); + + do old = *a; + while (__bo_cas(a, old, old|mask) != old); +} + +static inline void clear_bit(int nr, volatile void *addr) +{ + unsigned mask, old; + volatile unsigned *a = addr; + + a += nr >> 5; + mask = 1U << (nr & 0x1f); + + do old = *a; + while (__bo_cas(a, old, old&~mask) != old); +} + +static inline void change_bit(int nr, volatile void *addr) +{ + unsigned mask, old; + volatile unsigned *a = addr; + + a += nr >> 5; + mask = 1U << (nr & 0x1f); + + do old = *a; + while (__bo_cas(a, old, old^mask) != old); +} + +static inline int test_and_set_bit(int nr, volatile void *addr) +{ + unsigned mask, old; + volatile unsigned *a = addr; + + a += nr >> 5; + mask = 1U << (nr & 0x1f); + + do old = *a; + while (__bo_cas(a, old, old|mask) != old); + + return !!(old & mask); +} + +static inline int test_and_clear_bit(int nr, volatile void *addr) +{ + unsigned mask, old; + volatile unsigned *a = addr; + + a += nr >> 5; + mask = 1U << (nr & 0x1f); + + do old = *a; + while (__bo_cas(a, old, old&~mask) != old); + + return !!(old & mask); +} + +static inline int test_and_change_bit(int nr, volatile void *addr) +{ + unsigned mask, old; + volatile unsigned *a = addr; + + a += nr >> 5; + mask = 1U << (nr & 0x1f); + + do old = *a; + while (__bo_cas(a, old, old^mask) != old); + + return !!(old & mask); +} + +#include <asm-generic/bitops/non-atomic.h> + +#endif /* __ASM_SH_BITOPS_CAS_H */ diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h index fc8e652cf173..a8699d60a8c4 100644 --- a/arch/sh/include/asm/bitops.h +++ b/arch/sh/include/asm/bitops.h @@ -18,6 +18,8 @@ #include <asm/bitops-op32.h> #elif defined(CONFIG_CPU_SH4A) #include <asm/bitops-llsc.h> +#elif defined(CONFIG_CPU_J2) && defined(CONFIG_SMP) +#include <asm/bitops-cas.h> #else #include <asm-generic/bitops/atomic.h> #include <asm-generic/bitops/non-atomic.h> diff --git a/arch/sh/include/asm/cmpxchg-cas.h b/arch/sh/include/asm/cmpxchg-cas.h new file mode 100644 index 000000000000..d0d86649e8c1 --- /dev/null +++ b/arch/sh/include/asm/cmpxchg-cas.h @@ -0,0 +1,24 @@ +#ifndef __ASM_SH_CMPXCHG_CAS_H +#define __ASM_SH_CMPXCHG_CAS_H + +static inline unsigned long +__cmpxchg_u32(volatile u32 *m, unsigned long old, unsigned long new) +{ + __asm__ __volatile__("cas.l %1,%0,@r0" + : "+r"(new) + : "r"(old), "z"(m) + : "t", "memory" ); + return new; +} + +static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val) +{ + unsigned long old; + do old = *m; + while (__cmpxchg_u32(m, old, val) != old); + return old; +} + +#include <asm/cmpxchg-xchg.h> + +#endif /* __ASM_SH_CMPXCHG_CAS_H */ diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h index 7219719c23a3..1e881f5db659 100644 --- a/arch/sh/include/asm/cmpxchg-xchg.h +++ b/arch/sh/include/asm/cmpxchg-xchg.h @@ -21,7 +21,7 @@ static inline u32 __xchg_cmpxchg(volatile void *ptr, u32 x, int size) int off = (unsigned long)ptr % sizeof(u32); volatile u32 *p = ptr - off; #ifdef __BIG_ENDIAN - int bitoff = (sizeof(u32) - 1 - off) * BITS_PER_BYTE; + int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE; #else int bitoff = off * BITS_PER_BYTE; #endif diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h index 5225916c1057..3dfe0467a773 100644 --- a/arch/sh/include/asm/cmpxchg.h +++ b/arch/sh/include/asm/cmpxchg.h @@ -13,6 +13,8 @@ #include <asm/cmpxchg-grb.h> #elif defined(CONFIG_CPU_SH4A) #include <asm/cmpxchg-llsc.h> +#elif defined(CONFIG_CPU_J2) && defined(CONFIG_SMP) +#include <asm/cmpxchg-cas.h> #else #include <asm/cmpxchg-irq.h> #endif diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h index e11cf0c8206b..0052ad40e86d 100644 --- a/arch/sh/include/asm/dma-mapping.h +++ b/arch/sh/include/asm/dma-mapping.h @@ -17,9 +17,9 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size, /* arch/sh/mm/consistent.c */ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, - struct dma_attrs *attrs); + unsigned long attrs); extern void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs); + unsigned long attrs); #endif /* __ASM_SH_DMA_MAPPING_H */ diff --git a/arch/sh/include/asm/futex-cas.h b/arch/sh/include/asm/futex-cas.h new file mode 100644 index 000000000000..267cb7a5f101 --- /dev/null +++ b/arch/sh/include/asm/futex-cas.h @@ -0,0 +1,34 @@ +#ifndef __ASM_SH_FUTEX_CAS_H +#define __ASM_SH_FUTEX_CAS_H + +static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval, + u32 __user *uaddr, + u32 oldval, u32 newval) +{ + int err = 0; + __asm__ __volatile__( + "1:\n\t" + "cas.l %2, %1, @r0\n" + "2:\n\t" +#ifdef CONFIG_MMU + ".section .fixup,\"ax\"\n" + "3:\n\t" + "mov.l 4f, %0\n\t" + "jmp @%0\n\t" + " mov %3, %0\n\t" + ".balign 4\n" + "4: .long 2b\n\t" + ".previous\n" + ".section __ex_table,\"a\"\n\t" + ".long 1b, 3b\n\t" + ".previous" +#endif + :"+r" (err), "+r" (newval) + :"r" (oldval), "i" (-EFAULT), "z" (uaddr) + :"t", "memory"); + if (err) return err; + *uval = newval; + return 0; +} + +#endif /* __ASM_SH_FUTEX_CAS_H */ diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h index 63d33129ea23..ab01dbee0a82 100644 --- a/arch/sh/include/asm/futex-irq.h +++ b/arch/sh/include/asm/futex-irq.h @@ -1,92 +1,6 @@ #ifndef __ASM_SH_FUTEX_IRQ_H #define __ASM_SH_FUTEX_IRQ_H - -static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr, - int *oldval) -{ - unsigned long flags; - int ret; - - local_irq_save(flags); - - ret = get_user(*oldval, uaddr); - if (!ret) - ret = put_user(oparg, uaddr); - - local_irq_restore(flags); - - return ret; -} - -static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr, - int *oldval) -{ - unsigned long flags; - int ret; - - local_irq_save(flags); - - ret = get_user(*oldval, uaddr); - if (!ret) - ret = put_user(*oldval + oparg, uaddr); - - local_irq_restore(flags); - - return ret; -} - -static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr, - int *oldval) -{ - unsigned long flags; - int ret; - - local_irq_save(flags); - - ret = get_user(*oldval, uaddr); - if (!ret) - ret = put_user(*oldval | oparg, uaddr); - - local_irq_restore(flags); - - return ret; -} - -static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr, - int *oldval) -{ - unsigned long flags; - int ret; - - local_irq_save(flags); - - ret = get_user(*oldval, uaddr); - if (!ret) - ret = put_user(*oldval & oparg, uaddr); - - local_irq_restore(flags); - - return ret; -} - -static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, - int *oldval) -{ - unsigned long flags; - int ret; - - local_irq_save(flags); - - ret = get_user(*oldval, uaddr); - if (!ret) - ret = put_user(*oldval ^ oparg, uaddr); - - local_irq_restore(flags); - - return ret; -} - static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) diff --git a/arch/sh/include/asm/futex-llsc.h b/arch/sh/include/asm/futex-llsc.h new file mode 100644 index 000000000000..23591703bec0 --- /dev/null +++ b/arch/sh/include/asm/futex-llsc.h @@ -0,0 +1,41 @@ +#ifndef __ASM_SH_FUTEX_LLSC_H +#define __ASM_SH_FUTEX_LLSC_H + +static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval, + u32 __user *uaddr, + u32 oldval, u32 newval) +{ + int err = 0; + __asm__ __volatile__( + "synco\n" + "1:\n\t" + "movli.l @%2, r0\n\t" + "mov r0, %1\n\t" + "cmp/eq %1, %4\n\t" + "bf 2f\n\t" + "mov %5, r0\n\t" + "movco.l r0, @%2\n\t" + "bf 1b\n" + "2:\n\t" + "synco\n\t" +#ifdef CONFIG_MMU + ".section .fixup,\"ax\"\n" + "3:\n\t" + "mov.l 4f, %0\n\t" + "jmp @%0\n\t" + " mov %3, %0\n\t" + ".balign 4\n" + "4: .long 2b\n\t" + ".previous\n" + ".section __ex_table,\"a\"\n\t" + ".long 1b, 3b\n\t" + ".previous" +#endif + :"+r" (err), "=&r" (*uval) + :"r" (uaddr), "i" (-EFAULT), "r" (oldval), "r" (newval) + :"t", "memory", "r0"); + if (err) return err; + return 0; +} + +#endif /* __ASM_SH_FUTEX_LLSC_H */ diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h index 7be39a646fbd..d0078747d308 100644 --- a/arch/sh/include/asm/futex.h +++ b/arch/sh/include/asm/futex.h @@ -7,16 +7,34 @@ #include <linux/uaccess.h> #include <asm/errno.h> -/* XXX: UP variants, fix for SH-4A and SMP.. */ +#if !defined(CONFIG_SMP) #include <asm/futex-irq.h> +#elif defined(CONFIG_CPU_J2) +#include <asm/futex-cas.h> +#elif defined(CONFIG_CPU_SH4A) +#include <asm/futex-llsc.h> +#else +#error SMP not supported on this configuration. +#endif + +static inline int +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) +{ + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + + return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval); +} static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; - int oldval = 0, ret; + u32 oparg = (encoded_op << 8) >> 20; + u32 cmparg = (encoded_op << 20) >> 20; + u32 oldval, newval, prev; + int ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; @@ -26,26 +44,39 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) pagefault_disable(); - switch (op) { - case FUTEX_OP_SET: - ret = atomic_futex_op_xchg_set(oparg, uaddr, &oldval); - break; - case FUTEX_OP_ADD: - ret = atomic_futex_op_xchg_add(oparg, uaddr, &oldval); - break; - case FUTEX_OP_OR: - ret = atomic_futex_op_xchg_or(oparg, uaddr, &oldval); - break; - case FUTEX_OP_ANDN: - ret = atomic_futex_op_xchg_and(~oparg, uaddr, &oldval); - break; - case FUTEX_OP_XOR: - ret = atomic_futex_op_xchg_xor(oparg, uaddr, &oldval); - break; - default: - ret = -ENOSYS; - break; - } + do { + if (op == FUTEX_OP_SET) + ret = oldval = 0; + else + ret = get_user(oldval, uaddr); + + if (ret) break; + + switch (op) { + case FUTEX_OP_SET: + newval = oparg; + break; + case FUTEX_OP_ADD: + newval = oldval + oparg; + break; + case FUTEX_OP_OR: + newval = oldval | oparg; + break; + case FUTEX_OP_ANDN: + newval = oldval & ~oparg; + break; + case FUTEX_OP_XOR: + newval = oldval ^ oparg; + break; + default: + ret = -ENOSYS; + break; + } + + if (ret) break; + + ret = futex_atomic_cmpxchg_inatomic(&prev, uaddr, oldval, newval); + } while (!ret && prev != oldval); pagefault_enable(); @@ -53,10 +84,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) switch (cmp) { case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; + case FUTEX_OP_CMP_LT: ret = ((int)oldval < (int)cmparg); break; + case FUTEX_OP_CMP_GE: ret = ((int)oldval >= (int)cmparg); break; + case FUTEX_OP_CMP_LE: ret = ((int)oldval <= (int)cmparg); break; + case FUTEX_OP_CMP_GT: ret = ((int)oldval > (int)cmparg); break; default: ret = -ENOSYS; } } @@ -64,15 +95,5 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) return ret; } -static inline int -futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) -{ - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - - return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval); -} - #endif /* __KERNEL__ */ #endif /* __ASM_SH_FUTEX_H */ diff --git a/arch/sh/include/asm/mc146818rtc.h b/arch/sh/include/asm/mc146818rtc.h deleted file mode 100644 index 0aee96a97330..000000000000 --- a/arch/sh/include/asm/mc146818rtc.h +++ /dev/null @@ -1,7 +0,0 @@ -/* - * Machine dependent access functions for RTC registers. - */ -#ifndef _ASM_MC146818RTC_H -#define _ASM_MC146818RTC_H - -#endif /* _ASM_MC146818RTC_H */ diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 1506897648aa..f9a09942a32d 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -15,7 +15,7 @@ */ enum cpu_type { /* SH-2 types */ - CPU_SH7619, + CPU_SH7619, CPU_J2, /* SH-2A types */ CPU_SH7201, CPU_SH7203, CPU_SH7206, CPU_SH7263, CPU_SH7264, CPU_SH7269, diff --git a/arch/sh/include/asm/rtc.h b/arch/sh/include/asm/rtc.h index 52b0c2dba979..f7b010d48af7 100644 --- a/arch/sh/include/asm/rtc.h +++ b/arch/sh/include/asm/rtc.h @@ -6,17 +6,6 @@ extern void (*board_time_init)(void); extern void (*rtc_sh_get_time)(struct timespec *); extern int (*rtc_sh_set_time)(const time_t); -/* some dummy definitions */ -#define RTC_BATT_BAD 0x100 /* battery bad */ -#define RTC_SQWE 0x08 /* enable square-wave output */ -#define RTC_DM_BINARY 0x04 /* all time/date values are BCD if clear */ -#define RTC_24H 0x02 /* 24 hour mode - else hours bit 7 means pm */ -#define RTC_DST_EN 0x01 /* auto switch DST - works f. USA only */ - -struct rtc_time; -unsigned int get_rtc_time(struct rtc_time *); -int set_rtc_time(struct rtc_time *); - #define RTC_CAP_4_DIGIT_YEAR (1 << 0) struct sh_rtc_platform_info { diff --git a/arch/sh/include/asm/spinlock-cas.h b/arch/sh/include/asm/spinlock-cas.h new file mode 100644 index 000000000000..c46e8cc7b515 --- /dev/null +++ b/arch/sh/include/asm/spinlock-cas.h @@ -0,0 +1,117 @@ +/* + * include/asm-sh/spinlock-cas.h + * + * Copyright (C) 2015 SEI + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#ifndef __ASM_SH_SPINLOCK_CAS_H +#define __ASM_SH_SPINLOCK_CAS_H + +#include <asm/barrier.h> +#include <asm/processor.h> + +static inline unsigned __sl_cas(volatile unsigned *p, unsigned old, unsigned new) +{ + __asm__ __volatile__("cas.l %1,%0,@r0" + : "+r"(new) + : "r"(old), "z"(p) + : "t", "memory" ); + return new; +} + +/* + * Your basic SMP spinlocks, allowing only a single CPU anywhere + */ + +#define arch_spin_is_locked(x) ((x)->lock <= 0) +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, VAL > 0); +} + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + while (!__sl_cas(&lock->lock, 1, 0)); +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + __sl_cas(&lock->lock, 0, 1); +} + +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + return __sl_cas(&lock->lock, 1, 0); +} + +/* + * Read-write spinlocks, allowing multiple readers but only one writer. + * + * NOTE! it is quite common to have readers in interrupts but no interrupt + * writers. For those circumstances we can "mix" irq-safe locks - any writer + * needs to get a irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + */ + +/** + * read_can_lock - would read_trylock() succeed? + * @lock: the rwlock in question. + */ +#define arch_read_can_lock(x) ((x)->lock > 0) + +/** + * write_can_lock - would write_trylock() succeed? + * @lock: the rwlock in question. + */ +#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + unsigned old; + do old = rw->lock; + while (!old || __sl_cas(&rw->lock, old, old-1) != old); +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + unsigned old; + do old = rw->lock; + while (__sl_cas(&rw->lock, old, old+1) != old); +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + while (__sl_cas(&rw->lock, RW_LOCK_BIAS, 0) != RW_LOCK_BIAS); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + __sl_cas(&rw->lock, 0, RW_LOCK_BIAS); +} + +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + unsigned old; + do old = rw->lock; + while (old && __sl_cas(&rw->lock, old, old-1) != old); + return !!old; +} + +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + return __sl_cas(&rw->lock, RW_LOCK_BIAS, 0) == RW_LOCK_BIAS; +} + +#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) +#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) + +#define arch_spin_relax(lock) cpu_relax() +#define arch_read_relax(lock) cpu_relax() +#define arch_write_relax(lock) cpu_relax() + +#endif /* __ASM_SH_SPINLOCK_CAS_H */ diff --git a/arch/sh/include/asm/spinlock-llsc.h b/arch/sh/include/asm/spinlock-llsc.h new file mode 100644 index 000000000000..cec78143fa83 --- /dev/null +++ b/arch/sh/include/asm/spinlock-llsc.h @@ -0,0 +1,224 @@ +/* + * include/asm-sh/spinlock-llsc.h + * + * Copyright (C) 2002, 2003 Paul Mundt + * Copyright (C) 2006, 2007 Akio Idehara + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#ifndef __ASM_SH_SPINLOCK_LLSC_H +#define __ASM_SH_SPINLOCK_LLSC_H + +#include <asm/barrier.h> +#include <asm/processor.h> + +/* + * Your basic SMP spinlocks, allowing only a single CPU anywhere + */ + +#define arch_spin_is_locked(x) ((x)->lock <= 0) +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, VAL > 0); +} + +/* + * Simple spin lock operations. There are two variants, one clears IRQ's + * on the local processor, one does not. + * + * We make no fairness assumptions. They have a cost. + */ +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + unsigned long tmp; + unsigned long oldval; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%2, %0 ! arch_spin_lock \n\t" + "mov %0, %1 \n\t" + "mov #0, %0 \n\t" + "movco.l %0, @%2 \n\t" + "bf 1b \n\t" + "cmp/pl %1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp), "=&r" (oldval) + : "r" (&lock->lock) + : "t", "memory" + ); +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + unsigned long tmp; + + __asm__ __volatile__ ( + "mov #1, %0 ! arch_spin_unlock \n\t" + "mov.l %0, @%1 \n\t" + : "=&z" (tmp) + : "r" (&lock->lock) + : "t", "memory" + ); +} + +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned long tmp, oldval; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%2, %0 ! arch_spin_trylock \n\t" + "mov %0, %1 \n\t" + "mov #0, %0 \n\t" + "movco.l %0, @%2 \n\t" + "bf 1b \n\t" + "synco \n\t" + : "=&z" (tmp), "=&r" (oldval) + : "r" (&lock->lock) + : "t", "memory" + ); + + return oldval; +} + +/* + * Read-write spinlocks, allowing multiple readers but only one writer. + * + * NOTE! it is quite common to have readers in interrupts but no interrupt + * writers. For those circumstances we can "mix" irq-safe locks - any writer + * needs to get a irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + */ + +/** + * read_can_lock - would read_trylock() succeed? + * @lock: the rwlock in question. + */ +#define arch_read_can_lock(x) ((x)->lock > 0) + +/** + * write_can_lock - would write_trylock() succeed? + * @lock: the rwlock in question. + */ +#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + unsigned long tmp; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! arch_read_lock \n\t" + "cmp/pl %0 \n\t" + "bf 1b \n\t" + "add #-1, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp) + : "r" (&rw->lock) + : "t", "memory" + ); +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + unsigned long tmp; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! arch_read_unlock \n\t" + "add #1, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp) + : "r" (&rw->lock) + : "t", "memory" + ); +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + unsigned long tmp; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%1, %0 ! arch_write_lock \n\t" + "cmp/hs %2, %0 \n\t" + "bf 1b \n\t" + "sub %2, %0 \n\t" + "movco.l %0, @%1 \n\t" + "bf 1b \n\t" + : "=&z" (tmp) + : "r" (&rw->lock), "r" (RW_LOCK_BIAS) + : "t", "memory" + ); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + __asm__ __volatile__ ( + "mov.l %1, @%0 ! arch_write_unlock \n\t" + : + : "r" (&rw->lock), "r" (RW_LOCK_BIAS) + : "t", "memory" + ); +} + +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + unsigned long tmp, oldval; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%2, %0 ! arch_read_trylock \n\t" + "mov %0, %1 \n\t" + "cmp/pl %0 \n\t" + "bf 2f \n\t" + "add #-1, %0 \n\t" + "movco.l %0, @%2 \n\t" + "bf 1b \n\t" + "2: \n\t" + "synco \n\t" + : "=&z" (tmp), "=&r" (oldval) + : "r" (&rw->lock) + : "t", "memory" + ); + + return (oldval > 0); +} + +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + unsigned long tmp, oldval; + + __asm__ __volatile__ ( + "1: \n\t" + "movli.l @%2, %0 ! arch_write_trylock \n\t" + "mov %0, %1 \n\t" + "cmp/hs %3, %0 \n\t" + "bf 2f \n\t" + "sub %3, %0 \n\t" + "2: \n\t" + "movco.l %0, @%2 \n\t" + "bf 1b \n\t" + "synco \n\t" + : "=&z" (tmp), "=&r" (oldval) + : "r" (&rw->lock), "r" (RW_LOCK_BIAS) + : "t", "memory" + ); + + return (oldval > (RW_LOCK_BIAS - 1)); +} + +#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) +#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) + +#define arch_spin_relax(lock) cpu_relax() +#define arch_read_relax(lock) cpu_relax() +#define arch_write_relax(lock) cpu_relax() + +#endif /* __ASM_SH_SPINLOCK_LLSC_H */ diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h index 416834b60ad0..c2c61ea6a8e2 100644 --- a/arch/sh/include/asm/spinlock.h +++ b/arch/sh/include/asm/spinlock.h @@ -11,222 +11,12 @@ #ifndef __ASM_SH_SPINLOCK_H #define __ASM_SH_SPINLOCK_H -/* - * The only locking implemented here uses SH-4A opcodes. For others, - * split this out as per atomic-*.h. - */ -#ifndef CONFIG_CPU_SH4A -#error "Need movli.l/movco.l for spinlocks" +#if defined(CONFIG_CPU_SH4A) +#include <asm/spinlock-llsc.h> +#elif defined(CONFIG_CPU_J2) +#include <asm/spinlock-cas.h> +#else +#error "The configured cpu type does not support spinlocks" #endif -#include <asm/barrier.h> -#include <asm/processor.h> - -/* - * Your basic SMP spinlocks, allowing only a single CPU anywhere - */ - -#define arch_spin_is_locked(x) ((x)->lock <= 0) -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - smp_cond_load_acquire(&lock->lock, VAL > 0); -} - -/* - * Simple spin lock operations. There are two variants, one clears IRQ's - * on the local processor, one does not. - * - * We make no fairness assumptions. They have a cost. - */ -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned long tmp; - unsigned long oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_spin_lock \n\t" - "mov %0, %1 \n\t" - "mov #0, %0 \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "cmp/pl %1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&lock->lock) - : "t", "memory" - ); -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "mov #1, %0 ! arch_spin_unlock \n\t" - "mov.l %0, @%1 \n\t" - : "=&z" (tmp) - : "r" (&lock->lock) - : "t", "memory" - ); -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned long tmp, oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_spin_trylock \n\t" - "mov %0, %1 \n\t" - "mov #0, %0 \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "synco \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&lock->lock) - : "t", "memory" - ); - - return oldval; -} - -/* - * Read-write spinlocks, allowing multiple readers but only one writer. - * - * NOTE! it is quite common to have readers in interrupts but no interrupt - * writers. For those circumstances we can "mix" irq-safe locks - any writer - * needs to get a irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ - -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(x) ((x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%1, %0 ! arch_read_lock \n\t" - "cmp/pl %0 \n\t" - "bf 1b \n\t" - "add #-1, %0 \n\t" - "movco.l %0, @%1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp) - : "r" (&rw->lock) - : "t", "memory" - ); -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%1, %0 ! arch_read_unlock \n\t" - "add #1, %0 \n\t" - "movco.l %0, @%1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp) - : "r" (&rw->lock) - : "t", "memory" - ); -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned long tmp; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%1, %0 ! arch_write_lock \n\t" - "cmp/hs %2, %0 \n\t" - "bf 1b \n\t" - "sub %2, %0 \n\t" - "movco.l %0, @%1 \n\t" - "bf 1b \n\t" - : "=&z" (tmp) - : "r" (&rw->lock), "r" (RW_LOCK_BIAS) - : "t", "memory" - ); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - __asm__ __volatile__ ( - "mov.l %1, @%0 ! arch_write_unlock \n\t" - : - : "r" (&rw->lock), "r" (RW_LOCK_BIAS) - : "t", "memory" - ); -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned long tmp, oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_read_trylock \n\t" - "mov %0, %1 \n\t" - "cmp/pl %0 \n\t" - "bf 2f \n\t" - "add #-1, %0 \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "2: \n\t" - "synco \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&rw->lock) - : "t", "memory" - ); - - return (oldval > 0); -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned long tmp, oldval; - - __asm__ __volatile__ ( - "1: \n\t" - "movli.l @%2, %0 ! arch_write_trylock \n\t" - "mov %0, %1 \n\t" - "cmp/hs %3, %0 \n\t" - "bf 2f \n\t" - "sub %3, %0 \n\t" - "2: \n\t" - "movco.l %0, @%2 \n\t" - "bf 1b \n\t" - "synco \n\t" - : "=&z" (tmp), "=&r" (oldval) - : "r" (&rw->lock), "r" (RW_LOCK_BIAS) - : "t", "memory" - ); - - return (oldval > (RW_LOCK_BIAS - 1)); -} - -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - -#define arch_spin_relax(lock) cpu_relax() -#define arch_read_relax(lock) cpu_relax() -#define arch_write_relax(lock) cpu_relax() - #endif /* __ASM_SH_SPINLOCK_H */ diff --git a/arch/sh/include/uapi/asm/cpu-features.h b/arch/sh/include/uapi/asm/cpu-features.h index 694abe490edb..2f1bc851042a 100644 --- a/arch/sh/include/uapi/asm/cpu-features.h +++ b/arch/sh/include/uapi/asm/cpu-features.h @@ -22,5 +22,6 @@ #define CPU_HAS_L2_CACHE 0x0080 /* Secondary cache / URAM */ #define CPU_HAS_OP32 0x0100 /* 32-bit instruction support */ #define CPU_HAS_PTEAEX 0x0200 /* PTE ASID Extension support */ +#define CPU_HAS_CAS_L 0x0400 /* cas.l atomic compare-and-swap */ #endif /* __ASM_SH_CPU_FEATURES_H */ diff --git a/arch/sh/include/uapi/asm/sigcontext.h b/arch/sh/include/uapi/asm/sigcontext.h index 8ce1435bc0bf..faa5d0833412 100644 --- a/arch/sh/include/uapi/asm/sigcontext.h +++ b/arch/sh/include/uapi/asm/sigcontext.h @@ -25,8 +25,6 @@ struct sigcontext { unsigned long sc_mach; unsigned long sc_macl; -#if defined(__SH4__) || defined(CONFIG_CPU_SH4) || \ - defined(__SH2A__) || defined(CONFIG_CPU_SH2A) /* FPU registers */ unsigned long sc_fpregs[16]; unsigned long sc_xfpregs[16]; @@ -34,7 +32,6 @@ struct sigcontext { unsigned int sc_fpul; unsigned int sc_ownedfp; #endif -#endif }; #endif /* __ASM_SH_SIGCONTEXT_H */ diff --git a/arch/sh/include/uapi/asm/unistd_32.h b/arch/sh/include/uapi/asm/unistd_32.h index d13a1d623736..c801bde9e6f5 100644 --- a/arch/sh/include/uapi/asm/unistd_32.h +++ b/arch/sh/include/uapi/asm/unistd_32.h @@ -380,7 +380,21 @@ #define __NR_process_vm_writev 366 #define __NR_kcmp 367 #define __NR_finit_module 368 +#define __NR_sched_getattr 369 +#define __NR_sched_setattr 370 +#define __NR_renameat2 371 +#define __NR_seccomp 372 +#define __NR_getrandom 373 +#define __NR_memfd_create 374 +#define __NR_bpf 375 +#define __NR_execveat 376 +#define __NR_userfaultfd 377 +#define __NR_membarrier 378 +#define __NR_mlock2 379 +#define __NR_copy_file_range 380 +#define __NR_preadv2 381 +#define __NR_pwritev2 382 -#define NR_syscalls 369 +#define NR_syscalls 383 #endif /* __ASM_SH_UNISTD_32_H */ diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h index 47ebd5b5ed55..ce0cb3598b62 100644 --- a/arch/sh/include/uapi/asm/unistd_64.h +++ b/arch/sh/include/uapi/asm/unistd_64.h @@ -400,7 +400,21 @@ #define __NR_process_vm_writev 377 #define __NR_kcmp 378 #define __NR_finit_module 379 +#define __NR_sched_getattr 380 +#define __NR_sched_setattr 381 +#define __NR_renameat2 382 +#define __NR_seccomp 383 +#define __NR_getrandom 384 +#define __NR_memfd_create 385 +#define __NR_bpf 386 +#define __NR_execveat 387 +#define __NR_userfaultfd 388 +#define __NR_membarrier 389 +#define __NR_mlock2 390 +#define __NR_copy_file_range 391 +#define __NR_preadv2 392 +#define __NR_pwritev2 393 -#define NR_syscalls 380 +#define NR_syscalls 394 #endif /* __ASM_SH_UNISTD_64_H */ diff --git a/arch/sh/kernel/cpu/clock.c b/arch/sh/kernel/cpu/clock.c index 4187cf4fe185..fca9b1e78a63 100644 --- a/arch/sh/kernel/cpu/clock.c +++ b/arch/sh/kernel/cpu/clock.c @@ -24,11 +24,13 @@ int __init clk_init(void) { int ret; +#ifndef CONFIG_COMMON_CLK ret = arch_clk_init(); if (unlikely(ret)) { pr_err("%s: CPU clock registration failed.\n", __func__); return ret; } +#endif if (sh_mv.mv_clk_init) { ret = sh_mv.mv_clk_init(); @@ -39,11 +41,13 @@ int __init clk_init(void) } } +#ifndef CONFIG_COMMON_CLK /* Kick the child clocks.. */ recalculate_root_clocks(); /* Enable the necessary init clocks */ clk_enable_init_clocks(); +#endif return ret; } diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c index 0d7360d549c1..c8b3be1b54e6 100644 --- a/arch/sh/kernel/cpu/init.c +++ b/arch/sh/kernel/cpu/init.c @@ -106,7 +106,7 @@ void __attribute__ ((weak)) l2_cache_init(void) /* * Generic first-level cache init */ -#ifdef CONFIG_SUPERH32 +#if defined(CONFIG_SUPERH32) && !defined(CONFIG_CPU_J2) static void cache_init(void) { unsigned long ccr, flags; @@ -323,9 +323,13 @@ asmlinkage void cpu_init(void) cache_init(); if (raw_smp_processor_id() == 0) { +#ifdef CONFIG_MMU shm_align_mask = max_t(unsigned long, current_cpu_data.dcache.way_size - 1, PAGE_SIZE - 1); +#else + shm_align_mask = PAGE_SIZE - 1; +#endif /* Boot CPU sets the cache shape */ detect_cache_shape(); diff --git a/arch/sh/kernel/cpu/proc.c b/arch/sh/kernel/cpu/proc.c index 9e6624c9108b..4df4b284f591 100644 --- a/arch/sh/kernel/cpu/proc.c +++ b/arch/sh/kernel/cpu/proc.c @@ -27,6 +27,7 @@ static const char *cpu_name[] = { [CPU_MXG] = "MX-G", [CPU_SH7723] = "SH7723", [CPU_SH7366] = "SH7366", [CPU_SH7724] = "SH7724", [CPU_SH7372] = "SH7372", [CPU_SH7734] = "SH7734", + [CPU_J2] = "J2", [CPU_SH_NONE] = "Unknown" }; diff --git a/arch/sh/kernel/cpu/sh2/Makefile b/arch/sh/kernel/cpu/sh2/Makefile index f0f059acfcfb..904c4283d923 100644 --- a/arch/sh/kernel/cpu/sh2/Makefile +++ b/arch/sh/kernel/cpu/sh2/Makefile @@ -5,3 +5,7 @@ obj-y := ex.o probe.o entry.o obj-$(CONFIG_CPU_SUBTYPE_SH7619) += setup-sh7619.o clock-sh7619.o + +# SMP setup +smp-$(CONFIG_CPU_J2) := smp-j2.o +obj-$(CONFIG_SMP) += $(smp-y) diff --git a/arch/sh/kernel/cpu/sh2/entry.S b/arch/sh/kernel/cpu/sh2/entry.S index a1505956ef28..1ee0a6e774c6 100644 --- a/arch/sh/kernel/cpu/sh2/entry.S +++ b/arch/sh/kernel/cpu/sh2/entry.S @@ -47,6 +47,13 @@ ENTRY(exception_handler) mov.l r3,@-sp cli mov.l $cpu_mode,r2 +#ifdef CONFIG_SMP + mov.l $cpuid,r3 + mov.l @r3,r3 + mov.l @r3,r3 + shll2 r3 + add r3,r2 +#endif mov.l @r2,r0 mov.l @(5*4,r15),r3 ! previous SR or r0,r3 ! set MD @@ -57,6 +64,13 @@ ENTRY(exception_handler) mov.l __md_bit,r0 mov.l r0,@r2 ! enter kernel mode mov.l $current_thread_info,r2 +#ifdef CONFIG_SMP + mov.l $cpuid,r0 + mov.l @r0,r0 + mov.l @r0,r0 + shll2 r0 + add r0,r2 +#endif mov.l @r2,r2 mov #(THREAD_SIZE >> 8),r0 shll8 r0 @@ -147,6 +161,11 @@ ENTRY(exception_handler) mov #31,r8 cmp/hs r8,r9 bt trap_entry ! 64 > vec >= 31 is trap +#ifdef CONFIG_CPU_J2 + mov #16,r8 + cmp/hs r8,r9 + bt interrupt_entry ! 31 > vec >= 16 is interrupt +#endif mov.l 4f,r8 mov r9,r4 @@ -260,6 +279,13 @@ restore_all: lds.l @r0+,macl mov r15,r0 mov.l $cpu_mode,r2 +#ifdef CONFIG_SMP + mov.l $cpuid,r3 + mov.l @r3,r3 + mov.l @r3,r3 + shll2 r3 + add r3,r2 +#endif mov #OFF_SR,r3 mov.l @(r0,r3),r1 mov.l __md_bit,r3 @@ -276,6 +302,13 @@ restore_all: mov.l r1,@r2 ! set pc get_current_thread_info r0, r1 mov.l $current_thread_info,r1 +#ifdef CONFIG_SMP + mov.l $cpuid,r3 + mov.l @r3,r3 + mov.l @r3,r3 + shll2 r3 + add r3,r1 +#endif mov.l r0,@r1 mov.l @r15+,r0 mov.l @r15+,r1 @@ -303,19 +336,41 @@ $current_thread_info: .long __current_thread_info $cpu_mode: .long __cpu_mode +#ifdef CONFIG_SMP +$cpuid: + .long sh2_cpuid_addr +#endif ! common exception handler #include "../../entry-common.S" + +#ifdef CONFIG_NR_CPUS +#define NR_CPUS CONFIG_NR_CPUS +#else +#define NR_CPUS 1 +#endif .data ! cpu operation mode ! bit30 = MD (compatible SH3/4) __cpu_mode: + .rept NR_CPUS .long 0x40000000 + .endr + +#ifdef CONFIG_SMP +.global sh2_cpuid_addr +sh2_cpuid_addr: + .long dummy_cpuid +dummy_cpuid: + .long 0 +#endif .section .bss __current_thread_info: + .rept NR_CPUS .long 0 + .endr ENTRY(exception_handling_table) .space 4*32 diff --git a/arch/sh/kernel/cpu/sh2/probe.c b/arch/sh/kernel/cpu/sh2/probe.c index 6c687ae812ef..4205f6d42b69 100644 --- a/arch/sh/kernel/cpu/sh2/probe.c +++ b/arch/sh/kernel/cpu/sh2/probe.c @@ -10,10 +10,27 @@ * for more details. */ #include <linux/init.h> +#include <linux/of_fdt.h> +#include <linux/smp.h> +#include <linux/io.h> #include <asm/processor.h> #include <asm/cache.h> -void cpu_probe(void) +#if defined(CONFIG_CPU_J2) +extern u32 __iomem *j2_ccr_base; +static int __init scan_cache(unsigned long node, const char *uname, + int depth, void *data) +{ + if (!of_flat_dt_is_compatible(node, "jcore,cache")) + return 0; + + j2_ccr_base = (u32 __iomem *)of_flat_dt_translate_address(node); + + return 1; +} +#endif + +void __ref cpu_probe(void) { #if defined(CONFIG_CPU_SUBTYPE_SH7619) boot_cpu_data.type = CPU_SH7619; @@ -24,10 +41,30 @@ void cpu_probe(void) boot_cpu_data.dcache.linesz = L1_CACHE_BYTES; boot_cpu_data.dcache.flags = 0; #endif + +#if defined(CONFIG_CPU_J2) + unsigned cpu = hard_smp_processor_id(); + if (cpu == 0) of_scan_flat_dt(scan_cache, NULL); + if (j2_ccr_base) __raw_writel(0x80000303, j2_ccr_base + 4*cpu); + if (cpu != 0) return; + boot_cpu_data.type = CPU_J2; + + /* These defaults are appropriate for the original/current + * J2 cache. Once there is a proper framework for getting cache + * info from device tree, we should switch to that. */ + boot_cpu_data.dcache.ways = 1; + boot_cpu_data.dcache.sets = 256; + boot_cpu_data.dcache.entry_shift = 5; + boot_cpu_data.dcache.linesz = 32; + boot_cpu_data.dcache.flags = 0; + + boot_cpu_data.flags |= CPU_HAS_CAS_L; +#else /* * SH-2 doesn't have separate caches */ boot_cpu_data.dcache.flags |= SH_CACHE_COMBINED; +#endif boot_cpu_data.icache = boot_cpu_data.dcache; boot_cpu_data.family = CPU_FAMILY_SH2; } diff --git a/arch/sh/kernel/cpu/sh2/smp-j2.c b/arch/sh/kernel/cpu/sh2/smp-j2.c new file mode 100644 index 000000000000..6ccd7e4dc008 --- /dev/null +++ b/arch/sh/kernel/cpu/sh2/smp-j2.c @@ -0,0 +1,139 @@ +/* + * SMP support for J2 processor + * + * Copyright (C) 2015-2016 Smart Energy Instruments, Inc. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <asm/cmpxchg.h> + +DEFINE_PER_CPU(unsigned, j2_ipi_messages); + +extern u32 *sh2_cpuid_addr; +static u32 *j2_ipi_trigger; +static int j2_ipi_irq; + +static irqreturn_t j2_ipi_interrupt_handler(int irq, void *arg) +{ + unsigned cpu = hard_smp_processor_id(); + volatile unsigned *pmsg = &per_cpu(j2_ipi_messages, cpu); + unsigned messages, i; + + do messages = *pmsg; + while (cmpxchg(pmsg, messages, 0) != messages); + + if (!messages) return IRQ_NONE; + + for (i=0; i<SMP_MSG_NR; i++) + if (messages & (1U<<i)) + smp_message_recv(i); + + return IRQ_HANDLED; +} + +static void j2_smp_setup(void) +{ +} + +static void j2_prepare_cpus(unsigned int max_cpus) +{ + struct device_node *np; + unsigned i, max = 1; + + np = of_find_compatible_node(NULL, NULL, "jcore,ipi-controller"); + if (!np) + goto out; + + j2_ipi_irq = irq_of_parse_and_map(np, 0); + j2_ipi_trigger = of_iomap(np, 0); + if (!j2_ipi_irq || !j2_ipi_trigger) + goto out; + + np = of_find_compatible_node(NULL, NULL, "jcore,cpuid-mmio"); + if (!np) + goto out; + + sh2_cpuid_addr = of_iomap(np, 0); + if (!sh2_cpuid_addr) + goto out; + + if (request_irq(j2_ipi_irq, j2_ipi_interrupt_handler, IRQF_PERCPU, + "ipi", (void *)j2_ipi_interrupt_handler) != 0) + goto out; + + max = max_cpus; +out: + /* Disable any cpus past max_cpus, or all secondaries if we didn't + * get the necessary resources to support SMP. */ + for (i=max; i<NR_CPUS; i++) { + set_cpu_possible(i, false); + set_cpu_present(i, false); + } +} + +static void j2_start_cpu(unsigned int cpu, unsigned long entry_point) +{ + struct device_node *np; + u32 regs[2]; + void __iomem *release, *initpc; + + if (!cpu) return; + + np = of_get_cpu_node(cpu, NULL); + if (!np) return; + + if (of_property_read_u32_array(np, "cpu-release-addr", regs, 2)) return; + release = ioremap_nocache(regs[0], sizeof(u32)); + initpc = ioremap_nocache(regs[1], sizeof(u32)); + + __raw_writel(entry_point, initpc); + __raw_writel(1, release); + + iounmap(initpc); + iounmap(release); + + pr_info("J2 SMP: requested start of cpu %u\n", cpu); +} + +static unsigned int j2_smp_processor_id(void) +{ + return __raw_readl(sh2_cpuid_addr); +} + +static void j2_send_ipi(unsigned int cpu, unsigned int message) +{ + volatile unsigned *pmsg; + unsigned old; + unsigned long val; + + /* There is only one IPI interrupt shared by all messages, so + * we keep a separate interrupt flag per message type in sw. */ + pmsg = &per_cpu(j2_ipi_messages, cpu); + do old = *pmsg; + while (cmpxchg(pmsg, old, old|(1U<<message)) != old); + + /* Generate the actual interrupt by writing to CCRn bit 28. */ + val = __raw_readl(j2_ipi_trigger + cpu); + __raw_writel(val | (1U<<28), j2_ipi_trigger + cpu); +} + +static struct plat_smp_ops j2_smp_ops = { + .smp_setup = j2_smp_setup, + .prepare_cpus = j2_prepare_cpus, + .start_cpu = j2_start_cpu, + .smp_processor_id = j2_smp_processor_id, + .send_ipi = j2_send_ipi, + .cpu_die = native_cpu_die, + .cpu_disable = native_cpu_disable, + .play_dead = native_play_dead, +}; + +CPU_METHOD_OF_DECLARE(j2_cpu_method, "jcore,spin-table", &j2_smp_ops); diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c index 5b0bfcda6d0b..eadb669a7329 100644 --- a/arch/sh/kernel/dma-nommu.c +++ b/arch/sh/kernel/dma-nommu.c @@ -13,7 +13,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t addr = page_to_phys(page) + offset; @@ -25,7 +25,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, static int nommu_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; diff --git a/arch/sh/kernel/dwarf.c b/arch/sh/kernel/dwarf.c index 9d209a07235e..e1d751ae2498 100644 --- a/arch/sh/kernel/dwarf.c +++ b/arch/sh/kernel/dwarf.c @@ -1009,10 +1009,8 @@ static void __init dwarf_unwinder_cleanup(void) rbtree_postorder_for_each_entry_safe(cie, next_cie, &cie_root, node) kfree(cie); - if (dwarf_reg_pool) - mempool_destroy(dwarf_reg_pool); - if (dwarf_frame_pool) - mempool_destroy(dwarf_frame_pool); + mempool_destroy(dwarf_reg_pool); + mempool_destroy(dwarf_frame_pool); kmem_cache_destroy(dwarf_reg_cachep); kmem_cache_destroy(dwarf_frame_cachep); } diff --git a/arch/sh/kernel/head_32.S b/arch/sh/kernel/head_32.S index 974bc152cc84..4e352c3f79e6 100644 --- a/arch/sh/kernel/head_32.S +++ b/arch/sh/kernel/head_32.S @@ -67,7 +67,7 @@ ENTRY(_stext) ldc r0, r6_bank #endif -#ifdef CONFIG_OF +#ifdef CONFIG_OF_FLATTREE mov r4, r12 ! Store device tree blob pointer in r12 #endif @@ -318,7 +318,7 @@ ENTRY(_stext) 10: #endif -#ifdef CONFIG_OF +#ifdef CONFIG_OF_FLATTREE mov.l 8f, r0 ! Make flat device tree available early. jsr @r0 mov r12, r4 @@ -349,7 +349,7 @@ ENTRY(stack_start) 5: .long start_kernel 6: .long cpu_init 7: .long init_thread_union -#if defined(CONFIG_OF) +#if defined(CONFIG_OF_FLATTREE) 8: .long sh_fdt_init #endif diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 5d34605b58b5..e7b49d81053e 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -242,7 +242,7 @@ void __init __weak plat_early_device_setup(void) { } -#ifdef CONFIG_OF +#ifdef CONFIG_OF_FLATTREE void __ref sh_fdt_init(phys_addr_t dt_phys) { static int done = 0; @@ -251,7 +251,11 @@ void __ref sh_fdt_init(phys_addr_t dt_phys) /* Avoid calling an __init function on secondary cpus. */ if (done) return; +#ifdef CONFIG_USE_BUILTIN_DTB + dt_virt = __dtb_start; +#else dt_virt = phys_to_virt(dt_phys); +#endif if (!dt_virt || !early_init_dt_scan(dt_virt)) { pr_crit("Error: invalid device tree blob" diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S index 734234be2f01..254bc22ee57d 100644 --- a/arch/sh/kernel/syscalls_32.S +++ b/arch/sh/kernel/syscalls_32.S @@ -386,3 +386,17 @@ ENTRY(sys_call_table) .long sys_process_vm_writev .long sys_kcmp .long sys_finit_module + .long sys_sched_getattr + .long sys_sched_setattr /* 370 */ + .long sys_renameat2 + .long sys_seccomp + .long sys_getrandom + .long sys_memfd_create + .long sys_bpf /* 375 */ + .long sys_execveat + .long sys_userfaultfd + .long sys_membarrier + .long sys_mlock2 + .long sys_copy_file_range /* 380 */ + .long sys_preadv2 + .long sys_pwritev2 diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S index 579fcb9a896b..d6a27f7a4c54 100644 --- a/arch/sh/kernel/syscalls_64.S +++ b/arch/sh/kernel/syscalls_64.S @@ -406,3 +406,17 @@ sys_call_table: .long sys_process_vm_writev .long sys_kcmp .long sys_finit_module + .long sys_sched_getattr /* 380 */ + .long sys_sched_setattr + .long sys_renameat2 + .long sys_seccomp + .long sys_getrandom + .long sys_memfd_create /* 385 */ + .long sys_bpf + .long sys_execveat + .long sys_userfaultfd + .long sys_membarrier + .long sys_mlock2 /* 390 */ + .long sys_copy_file_range + .long sys_preadv2 + .long sys_pwritev2 diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index d6d0a986c6e9..fcd5e41977d1 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -11,7 +11,6 @@ * for more details. */ #include <linux/kernel.h> -#include <linux/module.h> #include <linux/init.h> #include <linux/profile.h> #include <linux/timex.h> @@ -50,27 +49,31 @@ int update_persistent_clock(struct timespec now) } #endif -unsigned int get_rtc_time(struct rtc_time *tm) +static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) { - if (rtc_sh_get_time != null_rtc_get_time) { - struct timespec tv; + struct timespec tv; - rtc_sh_get_time(&tv); - rtc_time_to_tm(tv.tv_sec, tm); - } - - return RTC_24H; + rtc_sh_get_time(&tv); + rtc_time_to_tm(tv.tv_sec, tm); + return 0; } -EXPORT_SYMBOL(get_rtc_time); -int set_rtc_time(struct rtc_time *tm) +static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) { unsigned long secs; rtc_tm_to_time(tm, &secs); - return rtc_sh_set_time(secs); + if ((rtc_sh_set_time == null_rtc_set_time) || + (rtc_sh_set_time(secs) < 0)) + return -EOPNOTSUPP; + + return 0; } -EXPORT_SYMBOL(set_rtc_time); + +static const struct rtc_class_ops rtc_generic_ops = { + .read_time = rtc_generic_get_time, + .set_time = rtc_generic_set_time, +}; static int __init rtc_generic_init(void) { @@ -79,11 +82,14 @@ static int __init rtc_generic_init(void) if (rtc_sh_get_time == null_rtc_get_time) return -ENODEV; - pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); + pdev = platform_device_register_data(NULL, "rtc-generic", -1, + &rtc_generic_ops, + sizeof(rtc_generic_ops)); + return PTR_ERR_OR_ZERO(pdev); } -module_init(rtc_generic_init); +device_initcall(rtc_generic_init); void (*board_time_init)(void); diff --git a/arch/sh/mm/Makefile b/arch/sh/mm/Makefile index cee6b9999d86..92c3bd96aee5 100644 --- a/arch/sh/mm/Makefile +++ b/arch/sh/mm/Makefile @@ -4,7 +4,8 @@ obj-y := alignment.o cache.o init.o consistent.o mmap.o -cacheops-$(CONFIG_CPU_SH2) := cache-sh2.o +cacheops-$(CONFIG_CPU_J2) := cache-j2.o +cacheops-$(CONFIG_CPU_SUBTYPE_SH7619) := cache-sh2.o cacheops-$(CONFIG_CPU_SH2A) := cache-sh2a.o cacheops-$(CONFIG_CPU_SH3) := cache-sh3.o cacheops-$(CONFIG_CPU_SH4) := cache-sh4.o flush-sh4.o diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c index ecfc6b0c1da1..bf95fdaedd0c 100644 --- a/arch/sh/mm/asids-debugfs.c +++ b/arch/sh/mm/asids-debugfs.c @@ -17,7 +17,6 @@ * for more details. */ #include <linux/init.h> -#include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/spinlock.h> @@ -70,6 +69,4 @@ static int __init asids_debugfs_init(void) return PTR_ERR_OR_ZERO(asids_dentry); } -module_init(asids_debugfs_init); - -MODULE_LICENSE("GPL v2"); +device_initcall(asids_debugfs_init); diff --git a/arch/sh/mm/cache-j2.c b/arch/sh/mm/cache-j2.c new file mode 100644 index 000000000000..391698bcac5b --- /dev/null +++ b/arch/sh/mm/cache-j2.c @@ -0,0 +1,65 @@ +/* + * arch/sh/mm/cache-j2.c + * + * Copyright (C) 2015-2016 Smart Energy Instruments, Inc. + * + * Released under the terms of the GNU GPL v2.0. + */ + +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/cpumask.h> + +#include <asm/cache.h> +#include <asm/addrspace.h> +#include <asm/processor.h> +#include <asm/cacheflush.h> +#include <asm/io.h> + +#define ICACHE_ENABLE 0x1 +#define DCACHE_ENABLE 0x2 +#define CACHE_ENABLE (ICACHE_ENABLE | DCACHE_ENABLE) +#define ICACHE_FLUSH 0x100 +#define DCACHE_FLUSH 0x200 +#define CACHE_FLUSH (ICACHE_FLUSH | DCACHE_FLUSH) + +u32 __iomem *j2_ccr_base; + +static void j2_flush_icache(void *args) +{ + unsigned cpu; + for_each_possible_cpu(cpu) + __raw_writel(CACHE_ENABLE | ICACHE_FLUSH, j2_ccr_base + cpu); +} + +static void j2_flush_dcache(void *args) +{ + unsigned cpu; + for_each_possible_cpu(cpu) + __raw_writel(CACHE_ENABLE | DCACHE_FLUSH, j2_ccr_base + cpu); +} + +static void j2_flush_both(void *args) +{ + unsigned cpu; + for_each_possible_cpu(cpu) + __raw_writel(CACHE_ENABLE | CACHE_FLUSH, j2_ccr_base + cpu); +} + +void __init j2_cache_init(void) +{ + if (!j2_ccr_base) + return; + + local_flush_cache_all = j2_flush_both; + local_flush_cache_mm = j2_flush_both; + local_flush_cache_dup_mm = j2_flush_both; + local_flush_cache_page = j2_flush_both; + local_flush_cache_range = j2_flush_both; + local_flush_dcache_page = j2_flush_dcache; + local_flush_icache_range = j2_flush_icache; + local_flush_icache_page = j2_flush_icache; + local_flush_cache_sigtramp = j2_flush_icache; + + pr_info("Initial J2 CCR is %.8x\n", __raw_readl(j2_ccr_base)); +} diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index e58cfbf45150..36554a9ea99b 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -42,6 +42,8 @@ static inline void cacheop_on_each_cpu(void (*func) (void *info), void *info, { preempt_disable(); + /* Needing IPI for cross-core flush is SHX3-specific. */ +#ifdef CONFIG_CPU_SHX3 /* * It's possible that this gets called early on when IRQs are * still disabled due to ioremapping by the boot CPU, so don't @@ -49,6 +51,7 @@ static inline void cacheop_on_each_cpu(void (*func) (void *info), void *info, */ if (num_online_cpus() > 1) smp_call_function(func, info, wait); +#endif func(info); @@ -244,7 +247,11 @@ void flush_cache_sigtramp(unsigned long address) static void compute_alias(struct cache_info *c) { +#ifdef CONFIG_MMU c->alias_mask = ((c->sets - 1) << c->entry_shift) & ~(PAGE_SIZE - 1); +#else + c->alias_mask = 0; +#endif c->n_aliases = c->alias_mask ? (c->alias_mask >> PAGE_SHIFT) + 1 : 0; } @@ -305,7 +312,11 @@ void __init cpu_cache_init(void) if (unlikely(cache_disabled)) goto skip; - if (boot_cpu_data.family == CPU_FAMILY_SH2) { + if (boot_cpu_data.type == CPU_J2) { + extern void __weak j2_cache_init(void); + + j2_cache_init(); + } else if (boot_cpu_data.family == CPU_FAMILY_SH2) { extern void __weak sh2_cache_init(void); sh2_cache_init(); diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c index b81d9dbf9fef..92b6976fde59 100644 --- a/arch/sh/mm/consistent.c +++ b/arch/sh/mm/consistent.c @@ -34,7 +34,7 @@ fs_initcall(dma_init); void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret, *ret_nocache; int order = get_order(size); @@ -66,7 +66,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { int order = get_order(size); unsigned long pfn = dma_handle >> PAGE_SHIFT; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 546293d9e6c5..59b09600dd32 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,6 +43,7 @@ config SPARC select OLD_SIGSUSPEND select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS + select HAVE_ARCH_HARDENED_USERCOPY config SPARC32 def_bool !64BIT diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h index 57f26c398dc9..4dd268a3a8b0 100644 --- a/arch/sparc/include/asm/io_32.h +++ b/arch/sparc/include/asm/io_32.h @@ -140,16 +140,6 @@ void ioport_unmap(void __iomem *); struct pci_dev; void pci_iounmap(struct pci_dev *dev, void __iomem *); - - -/* - * At the moment, we do not use CMOS_READ anywhere outside of rtc.c, - * so rtc_port is static in it. This should not change unless a new - * hardware pops up. - */ -#define RTC_PORT(x) (rtc_port + (x)) -#define RTC_ALWAYS_BCD 0 - static inline int sbus_can_dma_64bit(void) { return 0; /* actually, sparc_cpu_model==sun4d */ diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index 57aca2792d29..341a5a133f48 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -248,22 +248,28 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { - if (n && __access_ok((unsigned long) to, n)) + if (n && __access_ok((unsigned long) to, n)) { + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); - else + } else return n; } static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { - if (n && __access_ok((unsigned long) from, n)) + if (n && __access_ok((unsigned long) from, n)) { + if (!__builtin_constant_p(n)) + check_object_size(to, n, false); return __copy_user((__force void __user *) to, from, n); - else + } else return n; } diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index e9a51d64974d..8bda94fab8e8 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -210,8 +210,12 @@ unsigned long copy_from_user_fixup(void *to, const void __user *from, static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long size) { - unsigned long ret = ___copy_from_user(to, from, size); + unsigned long ret; + if (!__builtin_constant_p(size)) + check_object_size(to, size, false); + + ret = ___copy_from_user(to, from, size); if (unlikely(ret)) ret = copy_from_user_fixup(to, from, size); @@ -227,8 +231,11 @@ unsigned long copy_to_user_fixup(void __user *to, const void *from, static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long size) { - unsigned long ret = ___copy_to_user(to, from, size); + unsigned long ret; + if (!__builtin_constant_p(size)) + check_object_size(from, size, true); + ret = ___copy_to_user(to, from, size); if (unlikely(ret)) ret = copy_to_user_fixup(to, from, size); return ret; diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 37686828c3d9..5c615abff030 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -196,7 +196,7 @@ static inline void iommu_free_ctx(struct iommu *iommu, int ctx) static void *dma_4u_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long order, first_page; struct iommu *iommu; @@ -245,7 +245,7 @@ static void *dma_4u_alloc_coherent(struct device *dev, size_t size, static void dma_4u_free_coherent(struct device *dev, size_t size, void *cpu, dma_addr_t dvma, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu *iommu; unsigned long order, npages; @@ -263,7 +263,7 @@ static void dma_4u_free_coherent(struct device *dev, size_t size, static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page, unsigned long offset, size_t sz, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu *iommu; struct strbuf *strbuf; @@ -385,7 +385,7 @@ do_flush_sync: static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr, size_t sz, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu *iommu; struct strbuf *strbuf; @@ -431,7 +431,7 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr, static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s, *outs, *segstart; unsigned long flags, handle, prot, ctx; @@ -607,7 +607,7 @@ static unsigned long fetch_sg_ctx(struct iommu *iommu, struct scatterlist *sg) static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long flags, ctx; struct scatterlist *sg; diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index ffd5ff4678cf..2344103414d1 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -260,7 +260,7 @@ EXPORT_SYMBOL(sbus_set_sbus64); */ static void *sbus_alloc_coherent(struct device *dev, size_t len, dma_addr_t *dma_addrp, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { struct platform_device *op = to_platform_device(dev); unsigned long len_total = PAGE_ALIGN(len); @@ -315,7 +315,7 @@ err_nopages: } static void sbus_free_coherent(struct device *dev, size_t n, void *p, - dma_addr_t ba, struct dma_attrs *attrs) + dma_addr_t ba, unsigned long attrs) { struct resource *res; struct page *pgv; @@ -355,7 +355,7 @@ static void sbus_free_coherent(struct device *dev, size_t n, void *p, static dma_addr_t sbus_map_page(struct device *dev, struct page *page, unsigned long offset, size_t len, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { void *va = page_address(page) + offset; @@ -371,20 +371,20 @@ static dma_addr_t sbus_map_page(struct device *dev, struct page *page, } static void sbus_unmap_page(struct device *dev, dma_addr_t ba, size_t n, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { mmu_release_scsi_one(dev, ba, n); } static int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { mmu_get_scsi_sgl(dev, sg, n); return n; } static void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { mmu_release_scsi_sgl(dev, sg, n); } @@ -429,7 +429,7 @@ arch_initcall(sparc_register_ioport); */ static void *pci32_alloc_coherent(struct device *dev, size_t len, dma_addr_t *pba, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long len_total = PAGE_ALIGN(len); void *va; @@ -482,7 +482,7 @@ err_nopages: * past this call are illegal. */ static void pci32_free_coherent(struct device *dev, size_t n, void *p, - dma_addr_t ba, struct dma_attrs *attrs) + dma_addr_t ba, unsigned long attrs) { struct resource *res; @@ -518,14 +518,14 @@ static void pci32_free_coherent(struct device *dev, size_t n, void *p, static dma_addr_t pci32_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { /* IIep is write-through, not flushing. */ return page_to_phys(page) + offset; } static void pci32_unmap_page(struct device *dev, dma_addr_t ba, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { if (dir != PCI_DMA_TODEVICE) dma_make_coherent(ba, PAGE_ALIGN(size)); @@ -548,7 +548,7 @@ static void pci32_unmap_page(struct device *dev, dma_addr_t ba, size_t size, */ static int pci32_map_sg(struct device *device, struct scatterlist *sgl, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int n; @@ -567,7 +567,7 @@ static int pci32_map_sg(struct device *device, struct scatterlist *sgl, */ static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int n; diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 836e8cef47e2..61c6f935accc 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -130,7 +130,7 @@ static inline long iommu_batch_end(void) static void *dma_4v_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long flags, order, first_page, npages, n; struct iommu *iommu; @@ -213,7 +213,7 @@ static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry, } static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu, - dma_addr_t dvma, struct dma_attrs *attrs) + dma_addr_t dvma, unsigned long attrs) { struct pci_pbm_info *pbm; struct iommu *iommu; @@ -235,7 +235,7 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu, static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, unsigned long offset, size_t sz, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu *iommu; unsigned long flags, npages, oaddr; @@ -294,7 +294,7 @@ iommu_map_fail: static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, size_t sz, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_pbm_info *pbm; struct iommu *iommu; @@ -322,7 +322,7 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr, static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s, *outs, *segstart; unsigned long flags, handle, prot; @@ -466,7 +466,7 @@ iommu_map_failed: static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct pci_pbm_info *pbm; struct scatterlist *sg; diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 7d02b1fef025..d79b3b734245 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -150,6 +150,13 @@ SECTIONS } PERCPU_SECTION(SMP_CACHE_BYTES) +#ifdef CONFIG_JUMP_LABEL + . = ALIGN(PAGE_SIZE); + .exit.text : { + EXIT_TEXT + } +#endif + . = ALIGN(PAGE_SIZE); __init_end = .; BSS_SECTION(0, 0, 0) diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c index b6bc0547a4f6..09bb774b39cd 100644 --- a/arch/tile/kernel/pci-dma.c +++ b/arch/tile/kernel/pci-dma.c @@ -34,7 +34,7 @@ static void *tile_dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { u64 dma_mask = (dev && dev->coherent_dma_mask) ? dev->coherent_dma_mask : DMA_BIT_MASK(32); @@ -78,7 +78,7 @@ static void *tile_dma_alloc_coherent(struct device *dev, size_t size, */ static void tile_dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { homecache_free_pages((unsigned long)vaddr, get_order(size)); } @@ -202,7 +202,7 @@ static void __dma_complete_pa_range(dma_addr_t dma_addr, size_t size, static int tile_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -224,7 +224,7 @@ static int tile_dma_map_sg(struct device *dev, struct scatterlist *sglist, static void tile_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -240,7 +240,7 @@ static void tile_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, static dma_addr_t tile_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(!valid_dma_direction(direction)); @@ -252,7 +252,7 @@ static dma_addr_t tile_dma_map_page(struct device *dev, struct page *page, static void tile_dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(!valid_dma_direction(direction)); @@ -343,7 +343,7 @@ EXPORT_SYMBOL(tile_dma_map_ops); static void *tile_pci_dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { int node = dev_to_node(dev); int order = get_order(size); @@ -368,14 +368,14 @@ static void *tile_pci_dma_alloc_coherent(struct device *dev, size_t size, */ static void tile_pci_dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { homecache_free_pages((unsigned long)vaddr, get_order(size)); } static int tile_pci_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -400,7 +400,7 @@ static int tile_pci_dma_map_sg(struct device *dev, struct scatterlist *sglist, static void tile_pci_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *sg; int i; @@ -416,7 +416,7 @@ static void tile_pci_dma_unmap_sg(struct device *dev, static dma_addr_t tile_pci_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(!valid_dma_direction(direction)); @@ -429,7 +429,7 @@ static dma_addr_t tile_pci_dma_map_page(struct device *dev, struct page *page, static void tile_pci_dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long attrs) { BUG_ON(!valid_dma_direction(direction)); @@ -531,7 +531,7 @@ EXPORT_SYMBOL(gx_pci_dma_map_ops); #ifdef CONFIG_SWIOTLB static void *tile_swiotlb_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { gfp |= GFP_DMA; return swiotlb_alloc_coherent(dev, size, dma_handle, gfp); @@ -539,7 +539,7 @@ static void *tile_swiotlb_alloc_coherent(struct device *dev, size_t size, static void tile_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, - struct dma_attrs *attrs) + unsigned long attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_addr); } diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S index 378f5d8d1ec8..9d449caf8910 100644 --- a/arch/tile/kernel/vmlinux.lds.S +++ b/arch/tile/kernel/vmlinux.lds.S @@ -60,6 +60,18 @@ SECTIONS /* "Init" is divided into two areas with very different virtual addresses. */ INIT_TEXT_SECTION(PAGE_SIZE) + /* + * Some things, like the __jump_table, may contain symbol references + * to __exit text, so include such text in the final image if so. + * In that case we also override the _einittext from INIT_TEXT_SECTION. + */ +#ifdef CONFIG_JUMP_LABEL + .exit.text : { + EXIT_TEXT + _einittext = .; + } +#endif + /* Now we skip back to PAGE_OFFSET for the data. */ . = (. - TEXT_OFFSET + PAGE_OFFSET); #undef LOAD_OFFSET diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common index 58650d098fb4..fd443852103c 100644 --- a/arch/um/Kconfig.common +++ b/arch/um/Kconfig.common @@ -1,10 +1,12 @@ config UML bool default y + select ARCH_HAS_KCOV select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_SECCOMP_FILTER select HAVE_UID16 select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_DEBUG_KMEMLEAK select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_IO @@ -31,10 +33,9 @@ config PCI config PCMCIA bool -# Yet to do! config TRACE_IRQFLAGS_SUPPORT bool - default n + default y config LOCKDEP_SUPPORT bool diff --git a/arch/um/include/asm/irqflags.h b/arch/um/include/asm/irqflags.h index c780d8a16773..3bb221e1d5a4 100644 --- a/arch/um/include/asm/irqflags.h +++ b/arch/um/include/asm/irqflags.h @@ -6,37 +6,33 @@ extern int set_signals(int enable); extern void block_signals(void); extern void unblock_signals(void); +#define arch_local_save_flags arch_local_save_flags static inline unsigned long arch_local_save_flags(void) { return get_signals(); } +#define arch_local_irq_restore arch_local_irq_restore static inline void arch_local_irq_restore(unsigned long flags) { set_signals(flags); } +#define arch_local_irq_enable arch_local_irq_enable static inline void arch_local_irq_enable(void) { unblock_signals(); } +#define arch_local_irq_disable arch_local_irq_disable static inline void arch_local_irq_disable(void) { block_signals(); } -static inline unsigned long arch_local_irq_save(void) -{ - unsigned long flags; - flags = arch_local_save_flags(); - arch_local_irq_disable(); - return flags; -} +#define ARCH_IRQ_DISABLED 0 +#define ARCh_IRQ_ENABLED (SIGIO|SIGVTALRM) -static inline bool arch_irqs_disabled(void) -{ - return arch_local_save_flags() == 0; -} +#include <asm-generic/irqflags.h> #endif diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index a6a5e42caaef..2f36d515762e 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -3,6 +3,11 @@ # Licensed under the GPL # +# Don't instrument UML-specific code; without this, we may crash when +# accessing the instrumentation buffer for the first time from the +# kernel. +KCOV_INSTRUMENT := n + CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START) \ -DELF_ARCH=$(LDS_ELF_ARCH) \ -DELF_FORMAT=$(LDS_ELF_FORMAT) \ diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c index 55cead809b18..48bae81f8dca 100644 --- a/arch/um/kernel/initrd.c +++ b/arch/um/kernel/initrd.c @@ -37,8 +37,6 @@ static int __init read_initrd(void) } area = alloc_bootmem(size); - if (area == NULL) - return 0; if (load_initrd(initrd, area, size) == -1) return 0; diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 16630e75f056..e8175a8aa22c 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -319,9 +319,6 @@ int __init linux_main(int argc, char **argv) start_vm = VMALLOC_START; - setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem); - mem_total_pages(physmem_size, iomem_size, highmem); - virtmem_size = physmem_size; stack = (unsigned long) argv; stack &= ~(1024 * 1024 - 1); @@ -334,7 +331,6 @@ int __init linux_main(int argc, char **argv) printf("Kernel virtual memory size shrunk to %lu bytes\n", virtmem_size); - stack_protections((unsigned long) &init_thread_info); os_flush_stdout(); return start_uml(); @@ -342,6 +338,10 @@ int __init linux_main(int argc, char **argv) void __init setup_arch(char **cmdline_p) { + stack_protections((unsigned long) &init_thread_info); + setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem); + mem_total_pages(physmem_size, iomem_size, highmem); + paging_init(); strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index 08ff5094fcdd..ada473bf6f46 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -3,6 +3,9 @@ # Licensed under the GPL # +# Don't instrument UML-specific code +KCOV_INSTRUMENT := n + obj-y = aio.o execvp.o file.o helper.o irq.o main.o mem.o process.o \ registers.o sigio.o signal.o start_up.o time.o tty.o \ umid.o user_syms.o util.o drivers/ skas/ diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 8acaf4e384c0..a86d7cc2c2d8 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -15,6 +15,7 @@ #include <kern_util.h> #include <os.h> #include <sysdep/mcontext.h> +#include <um_malloc.h> void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = { [SIGTRAP] = relay_signal, @@ -32,7 +33,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) struct uml_pt_regs *r; int save_errno = errno; - r = malloc(sizeof(struct uml_pt_regs)); + r = uml_kmalloc(sizeof(struct uml_pt_regs), UM_GFP_ATOMIC); if (!r) panic("out of memory"); @@ -91,7 +92,7 @@ static void timer_real_alarm_handler(mcontext_t *mc) { struct uml_pt_regs *regs; - regs = malloc(sizeof(struct uml_pt_regs)); + regs = uml_kmalloc(sizeof(struct uml_pt_regs), UM_GFP_ATOMIC); if (!regs) panic("out of memory"); diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index e35632ef23c7..62dfc644c908 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -98,7 +98,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, } static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, - bool write, bool foreign) + bool write, bool execute, bool foreign) { /* by default, allow everything */ return true; diff --git a/arch/unicore32/mm/dma-swiotlb.c b/arch/unicore32/mm/dma-swiotlb.c index 16c08b2143a7..3e9f6489ba38 100644 --- a/arch/unicore32/mm/dma-swiotlb.c +++ b/arch/unicore32/mm/dma-swiotlb.c @@ -19,14 +19,14 @@ static void *unicore_swiotlb_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); } static void unicore_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, - struct dma_attrs *attrs) + unsigned long attrs) { swiotlb_free_coherent(dev, size, vaddr, dma_addr); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3a9add58d794..c580d8c33562 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -80,6 +80,7 @@ config X86 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_AOUT if X86_32 select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP @@ -91,6 +92,7 @@ config X86 select HAVE_ARCH_SOFT_DIRTY if X86_64 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_EBPF_JIT if X86_64 select HAVE_CC_STACKPROTECTOR select HAVE_CMPXCHG_DOUBLE @@ -152,6 +154,7 @@ config X86 select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION select PERF_EVENTS select RTC_LIB + select RTC_MC146818_LIB select SPARSE_IRQ select SRCU select SYSCTL_EXCEPTION_TRACE diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index fe91c25092da..77f28ce9c646 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,6 +5,8 @@ OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y +CFLAGS_syscall_64.o += -Wno-override-init +CFLAGS_syscall_32.o += -Wno-override-init obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index a1e71d431fed..1433f6b4607d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -204,8 +204,12 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * handling, because syscall restart has a fixup for compat * syscalls. The fixup is exercised by the ptrace_syscall_32 * selftest. + * + * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer + * special case only applies after poking regs and before the + * very next return to user mode. */ - ti->status &= ~TS_COMPAT; + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b846875aeea6..d172c619c449 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -288,11 +288,15 @@ return_from_SYSCALL_64: jne opportunistic_sysret_failed /* - * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, - * restoring TF results in a trap from userspace immediately after - * SYSRET. This would cause an infinite loop whenever #DB happens - * with register state that satisfies the opportunistic SYSRET - * conditions. For example, single-stepping this user code: + * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot + * restore RF properly. If the slowpath sets it for whatever reason, we + * need to restore it correctly. + * + * SYSRET can restore TF, but unlike IRET, restoring TF results in a + * trap from userspace immediately after SYSRET. This would cause an + * infinite loop whenever #DB happens with register state that satisfies + * the opportunistic SYSRET conditions. For example, single-stepping + * this user code: * * movq $stuck_here, %rcx * pushfq @@ -601,9 +605,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym) .endm #endif +/* Make sure APIC interrupt handlers end up in the irqentry section: */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" +# define POP_SECTION_IRQENTRY .popsection +#else +# define PUSH_SECTION_IRQENTRY +# define POP_SECTION_IRQENTRY +#endif + .macro apicinterrupt num sym do_sym +PUSH_SECTION_IRQENTRY apicinterrupt3 \num \sym \do_sym trace_apicinterrupt \num \sym +POP_SECTION_IRQENTRY .endm #ifdef CONFIG_SMP diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 4cddd17153fb..f848572169ea 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -294,7 +294,7 @@ # 285 sys_setaltroot 286 i386 add_key sys_add_key 287 i386 request_key sys_request_key -288 i386 keyctl sys_keyctl +288 i386 keyctl sys_keyctl compat_sys_keyctl 289 i386 ioprio_set sys_ioprio_set 290 i386 ioprio_get sys_ioprio_get 291 i386 inotify_init sys_inotify_init diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 2f02d23a05ef..94d54d0defa7 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -96,9 +96,8 @@ static notrace cycle_t vread_pvclock(int *mode) { const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; cycle_t ret; - u64 tsc, pvti_tsc; - u64 last, delta, pvti_system_time; - u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift; + u64 last; + u32 version; /* * Note: The kernel and hypervisor must guarantee that cpu ID @@ -123,29 +122,15 @@ static notrace cycle_t vread_pvclock(int *mode) */ do { - version = pvti->version; - - smp_rmb(); + version = pvclock_read_begin(pvti); if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { *mode = VCLOCK_NONE; return 0; } - tsc = rdtsc_ordered(); - pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; - pvti_tsc_shift = pvti->tsc_shift; - pvti_system_time = pvti->system_time; - pvti_tsc = pvti->tsc_timestamp; - - /* Make sure that the version double-check is last. */ - smp_rmb(); - } while (unlikely((version & 1) || version != pvti->version)); - - delta = tsc - pvti_tsc; - ret = pvti_system_time + - pvclock_scale_delta(delta, pvti_tsc_to_system_mul, - pvti_tsc_shift); + ret = __pvclock_read_cycles(pvti); + } while (pvclock_read_retry(pvti, version)); /* refer to vread_tsc() comment for rationale */ last = gtod->cycle_last; diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 63a03bb91497..4f741192846d 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -22,6 +22,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff)); + if (hdr->e_type != ET_DYN) + fail("input is not a shared object\n"); + /* Walk the segment table. */ for (i = 0; i < GET_LE(&hdr->e_phnum); i++) { if (GET_LE(&pt[i].p_type) == PT_LOAD) { @@ -49,6 +52,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, if (stripped_len < load_size) fail("stripped input is too short\n"); + if (!dyn) + fail("input has no PT_DYNAMIC section -- your toolchain is buggy\n"); + /* Walk the dynamic table */ for (i = 0; dyn + i < dyn_end && GET_LE(&dyn[i].d_tag) != DT_NULL; i++) { diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index fad97886d8b1..d0efb5cb1b00 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -263,10 +263,13 @@ static bool check_hw_exists(void) return true; msr_fail: - pr_cont("Broken PMU hardware detected, using software events only.\n"); - printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", - boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, - reg, val_new); + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + pr_cont("PMU not available due to virtualization, using software events only.\n"); + } else { + pr_cont("Broken PMU hardware detected, using software events only.\n"); + pr_err("Failed to access perfctr msr (MSR %x is %Lx)\n", + reg, val_new); + } return false; } diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 97a69dbba649..9d35ec0cb8fc 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void snb_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); +} + static void snb_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = { static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, + .enable_box = snb_uncore_msr_enable_box, .exit_box = snb_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, @@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void skl_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL); +} + static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) static struct intel_uncore_ops skl_uncore_msr_ops = { .init_box = skl_uncore_msr_init_box, + .enable_box = skl_uncore_msr_enable_box, .exit_box = skl_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 824e54086e07..8aee83bcf71f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2626,7 +2626,7 @@ void hswep_uncore_cpu_init(void) static struct intel_uncore_type hswep_uncore_ha = { .name = "ha", - .num_counters = 5, + .num_counters = 4, .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), @@ -2645,7 +2645,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = { static struct intel_uncore_type hswep_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, @@ -2691,7 +2691,7 @@ static struct intel_uncore_type hswep_uncore_irp = { static struct intel_uncore_type hswep_uncore_qpi = { .name = "qpi", - .num_counters = 5, + .num_counters = 4, .num_boxes = 3, .perf_ctr_bits = 48, .perf_ctr = SNBEP_PCI_PMON_CTR0, @@ -2773,7 +2773,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = { static struct intel_uncore_type hswep_uncore_r3qpi = { .name = "r3qpi", - .num_counters = 4, + .num_counters = 3, .num_boxes = 3, .perf_ctr_bits = 44, .constraints = hswep_uncore_r3qpi_constraints, @@ -2972,7 +2972,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index f5befd4945f2..124357773ffa 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -135,6 +135,7 @@ extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); +extern void lapic_update_tsc_freq(void); extern int APIC_init_uniprocessor(void); #ifdef CONFIG_X86_64 @@ -170,6 +171,7 @@ static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop +static inline void lapic_update_tsc_freq(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 3a27b93e6261..44461626830e 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -9,7 +9,6 @@ #include <linux/kmemcheck.h> #include <linux/scatterlist.h> #include <linux/dma-debug.h> -#include <linux/dma-attrs.h> #include <asm/io.h> #include <asm/swiotlb.h> #include <linux/dma-contiguous.h> @@ -48,11 +47,11 @@ extern int dma_supported(struct device *hwdev, u64 mask); extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, - struct dma_attrs *attrs); + unsigned long attrs); extern void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, - struct dma_attrs *attrs); + unsigned long attrs); #ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */ extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index fea7724141a0..e7f155c3045e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -344,8 +344,8 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, */ static inline int mmap_is_ia32(void) { - return config_enabled(CONFIG_X86_32) || - (config_enabled(CONFIG_COMPAT) && + return IS_ENABLED(CONFIG_X86_32) || + (IS_ENABLED(CONFIG_COMPAT) && test_thread_flag(TIF_ADDR32)); } diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 116b58347501..2737366ea583 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -137,9 +137,9 @@ static inline int copy_fregs_to_user(struct fregs_state __user *fx) static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { - if (config_enabled(CONFIG_X86_32)) + if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) + else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); /* See comment in copy_fxregs_to_kernel() below. */ @@ -150,10 +150,10 @@ static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { int err; - if (config_enabled(CONFIG_X86_32)) { + if (IS_ENABLED(CONFIG_X86_32)) { err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { - if (config_enabled(CONFIG_AS_FXSAVEQ)) { + if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { /* See comment in copy_fxregs_to_kernel() below. */ @@ -166,9 +166,9 @@ static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { - if (config_enabled(CONFIG_X86_32)) + if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) + else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); /* See comment in copy_fxregs_to_kernel() below. */ @@ -190,9 +190,9 @@ static inline int copy_user_to_fregs(struct fregs_state __user *fx) static inline void copy_fxregs_to_kernel(struct fpu *fpu) { - if (config_enabled(CONFIG_X86_32)) + if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) + else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); else { /* Using "rex64; fxsave %0" is broken because, if the memory diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 7178043b0e1d..59405a248fc2 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,10 +22,6 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - /* - * irq_tlb_count is double-counted in irq_call_count, so it must be - * subtracted from irq_call_count when displaying irq_call_count - */ unsigned int irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 223042086f4e..737da62bfeb0 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -5,10 +5,10 @@ struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ unsigned long pmd_flag; /* page flag for PMD entry */ - bool kernel_mapping; /* kernel mapping or ident mapping */ + unsigned long offset; /* ident mapping offset */ }; int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end); + unsigned long pstart, unsigned long pend); #endif /* _ASM_X86_INIT_H */ diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 0f555cc31984..24acd9ba7837 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -6,7 +6,6 @@ #include <asm/io.h> #include <asm/processor.h> -#include <linux/mc146818rtc.h> #ifndef RTC_PORT #define RTC_PORT(x) (0x70 + (x)) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 396348196aa7..d8abfcf524d1 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -155,7 +155,7 @@ static inline void arch_exit_mmap(struct mm_struct *mm) #ifdef CONFIG_X86_64 static inline bool is_64bit_mm(struct mm_struct *mm) { - return !config_enabled(CONFIG_IA32_EMULATION) || + return !IS_ENABLED(CONFIG_IA32_EMULATION) || !(mm->context.ia32_compat == TIF_IA32); } #else diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e8ec7ae10fa..1cc82ece9ac1 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names - * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry + * | OFFSET (14->63) | TYPE (9-13) |0|X|X|X| X| X|X|X|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) #define SWP_TYPE_BITS 5 /* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1) +#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7c1c89598688..d019f0cc80ec 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -25,6 +25,24 @@ void pvclock_resume(void); void pvclock_touch_watchdogs(void); +static __always_inline +unsigned pvclock_read_begin(const struct pvclock_vcpu_time_info *src) +{ + unsigned version = src->version & ~1; + /* Make sure that the version is read before the data. */ + virt_rmb(); + return version; +} + +static __always_inline +bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src, + unsigned version) +{ + /* Make sure that the version is re-read after the data. */ + virt_rmb(); + return unlikely(version != src->version); +} + /* * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, * yielding a 64-bit result. @@ -69,23 +87,12 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) } static __always_inline -unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, - cycle_t *cycles, u8 *flags) +cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src) { - unsigned version; - cycle_t offset; - u64 delta; - - version = src->version; - /* Make the latest version visible */ - smp_rmb(); - - delta = rdtsc_ordered() - src->tsc_timestamp; - offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); - *cycles = src->system_time + offset; - *flags = src->flags; - return version; + u64 delta = rdtsc_ordered() - src->tsc_timestamp; + cycle_t offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + return src->system_time + offset; } struct pvclock_vsyscall_time_info { diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 9c6b890d5e7a..b2988c0ed829 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -58,7 +58,15 @@ extern unsigned char boot_gdt[]; extern unsigned char secondary_startup_64[]; #endif +static inline size_t real_mode_size_needed(void) +{ + if (real_mode_header) + return 0; /* already allocated. */ + + return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); +} + +void set_real_mode_mem(phys_addr_t mem, size_t size); void reserve_real_mode(void); -void setup_real_mode(void); #endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/rtc.h b/arch/x86/include/asm/rtc.h deleted file mode 100644 index f71c3b0ed360..000000000000 --- a/arch/x86/include/asm/rtc.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/rtc.h> diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index ab05d73e2bb7..d2f69b9ff732 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -31,9 +31,9 @@ static inline void dma_mark_clean(void *addr, size_t size) {} extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs); + unsigned long attrs); extern void x86_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, - struct dma_attrs *attrs); + unsigned long attrs); #endif /* _ASM_X86_SWIOTLB_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 999b7cd2e78c..4e23dd15c661 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task_thread_info(task)->status & TS_COMPAT) + if (task_thread_info(task)->status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -239,9 +239,6 @@ static inline int syscall_get_arch(void) * TS_COMPAT is set for 32-bit syscall entry and then * remains set until we return to user mode. * - * TIF_IA32 tasks should always have TS_COMPAT set at - * system call time. - * * x32 tasks should be considered AUDIT_ARCH_X86_64. */ if (task_thread_info(current)->status & TS_COMPAT) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index b45ffdda3549..8b7c8d8e0852 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -176,6 +176,50 @@ static inline unsigned long current_stack_pointer(void) return sp; } +/* + * Walks up the stack frames to make sure that the specified object is + * entirely contained by a single stack frame. + * + * Returns: + * 1 if within a frame + * -1 if placed across a frame boundary (or outside stack) + * 0 unable to determine (no frame pointers, etc) + */ +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ +#if defined(CONFIG_FRAME_POINTER) + const void *frame = NULL; + const void *oldframe; + + oldframe = __builtin_frame_address(1); + if (oldframe) + frame = __builtin_frame_address(2); + /* + * low ----------------------------------------------> high + * [saved bp][saved ip][args][local vars][saved bp][saved ip] + * ^----------------^ + * allow copies only within here + */ + while (stack <= frame && frame < stackend) { + /* + * If obj + len extends past the last frame, this + * check won't pass and the next frame will be 0, + * causing us to bail out and correctly report + * the copy as invalid. + */ + if (obj + len <= frame) + return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1; + oldframe = frame; + frame = *(const void * const *)frame; + } + return -1; +#else + return 0; +#endif +} + #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 @@ -219,6 +263,9 @@ static inline unsigned long current_stack_pointer(void) * have to worry about atomic accesses. */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ +#ifdef CONFIG_COMPAT +#define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ +#endif #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4e5be94e079a..6fa85944af83 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -135,7 +135,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) static inline void __native_flush_tlb(void) { + /* + * If current->mm == NULL then we borrow a mm which may change during a + * task switch and therefore we must not be preempted while we write CR3 + * back: + */ + preempt_disable(); native_write_cr3(native_read_cr3()); + preempt_enable(); } static inline void __native_flush_tlb_global_irq_disabled(void) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index c03bfb68c503..a0ae610b9280 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -761,9 +761,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) * case, and do only runtime checking for non-constant sizes. */ - if (likely(sz < 0 || sz >= n)) + if (likely(sz < 0 || sz >= n)) { + check_object_size(to, n, false); n = _copy_from_user(to, from, n); - else if(__builtin_constant_p(n)) + } else if (__builtin_constant_p(n)) copy_from_user_overflow(); else __copy_from_user_overflow(sz, n); @@ -781,9 +782,10 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); /* See the comment in copy_from_user() above. */ - if (likely(sz < 0 || sz >= n)) + if (likely(sz < 0 || sz >= n)) { + check_object_size(from, n, true); n = _copy_to_user(to, from, n); - else if(__builtin_constant_p(n)) + } else if (__builtin_constant_p(n)) copy_to_user_overflow(); else __copy_to_user_overflow(sz, n); @@ -812,21 +814,21 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #define user_access_begin() __uaccess_begin() #define user_access_end() __uaccess_end() -#define unsafe_put_user(x, ptr) \ -({ \ +#define unsafe_put_user(x, ptr, err_label) \ +do { \ int __pu_err; \ __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ - __builtin_expect(__pu_err, 0); \ -}) + if (unlikely(__pu_err)) goto err_label; \ +} while (0) -#define unsafe_get_user(x, ptr) \ -({ \ +#define unsafe_get_user(x, ptr, err_label) \ +do { \ int __gu_err; \ unsigned long __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __builtin_expect(__gu_err, 0); \ -}) + if (unlikely(__gu_err)) goto err_label; \ +} while (0) #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 4b32da24faaf..7d3bdd1ed697 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -37,6 +37,7 @@ unsigned long __must_check __copy_from_user_ll_nocache_nozero static __always_inline unsigned long __must_check __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { + check_object_size(from, n, true); return __copy_to_user_ll(to, from, n); } @@ -95,6 +96,7 @@ static __always_inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); + check_object_size(to, n, false); if (__builtin_constant_p(n)) { unsigned long ret; diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 2eac2aa3e37f..673059a109fe 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -54,6 +54,7 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) { int ret = 0; + check_object_size(dst, size, false); if (!__builtin_constant_p(size)) return copy_user_generic(dst, (__force void *)src, size); switch (size) { @@ -119,6 +120,7 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size) { int ret = 0; + check_object_size(src, size, true); if (!__builtin_constant_p(size)) return copy_user_generic((__force void *)dst, src, size); switch (size) { diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index c852590254d5..e652a7cc6186 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -79,7 +79,7 @@ struct uv_gam_range_entry { u16 nasid; /* HNasid */ u16 sockid; /* Socket ID, high bits of APIC ID */ u16 pnode; /* Index to MMR and GRU spaces */ - u32 pxm; /* ACPI proximity domain number */ + u32 unused2; u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */ }; @@ -88,7 +88,8 @@ struct uv_gam_range_entry { #define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */ #define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */ #define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */ -#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_2 +#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */ +#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3 #define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */ #define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */ diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h index acd844c017d3..f02f025ff988 100644 --- a/arch/x86/include/asm/xen/page-coherent.h +++ b/arch/x86/include/asm/xen/page-coherent.h @@ -2,12 +2,11 @@ #define _ASM_X86_XEN_PAGE_COHERENT_H #include <asm/page.h> -#include <linux/dma-attrs.h> #include <linux/dma-mapping.h> static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { void *vstart = (void*)__get_free_pages(flags, get_order(size)); *dma_handle = virt_to_phys(vstart); @@ -16,18 +15,18 @@ static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, void *cpu_addr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { free_pages((unsigned long) cpu_addr, get_order(size)); } static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) { } + enum dma_data_direction dir, unsigned long attrs) { } static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) { } + unsigned long attrs) { } static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { } diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 42d27a62a404..63ff468a7986 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -241,7 +241,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, static dma_addr_t gart_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long bus; phys_addr_t paddr = page_to_phys(page) + offset; @@ -263,7 +263,7 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page, */ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long iommu_page; int npages; @@ -285,7 +285,7 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, * Wrapper for pci_unmap_single working with scatterlists. */ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *s; int i; @@ -293,7 +293,7 @@ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, for_each_sg(sg, s, nents, i) { if (!s->dma_length || !s->length) break; - gart_unmap_page(dev, s->dma_address, s->dma_length, dir, NULL); + gart_unmap_page(dev, s->dma_address, s->dma_length, dir, 0); } } @@ -315,7 +315,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, addr = dma_map_area(dev, addr, s->length, dir, 0); if (addr == bad_dma_addr) { if (i > 0) - gart_unmap_sg(dev, sg, i, dir, NULL); + gart_unmap_sg(dev, sg, i, dir, 0); nents = 0; sg[0].dma_length = 0; break; @@ -386,7 +386,7 @@ dma_map_cont(struct device *dev, struct scatterlist *start, int nelems, * Merge chunks that have page aligned sizes into a continuous mapping. */ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *s, *ps, *start_sg, *sgmap; int need = 0, nextneed, i, out, start; @@ -456,7 +456,7 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, error: flush_gart(); - gart_unmap_sg(dev, sg, out, dir, NULL); + gart_unmap_sg(dev, sg, out, dir, 0); /* When it was forced or merged try again in a dumb way */ if (force_iommu || iommu_merge) { @@ -476,7 +476,7 @@ error: /* allocate and map a coherent mapping */ static void * gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, - gfp_t flag, struct dma_attrs *attrs) + gfp_t flag, unsigned long attrs) { dma_addr_t paddr; unsigned long align_mask; @@ -508,9 +508,9 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, /* free a coherent mapping */ static void gart_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, struct dma_attrs *attrs) + dma_addr_t dma_addr, unsigned long attrs) { - gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); + gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0); dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7943d38c57ca..cea4fc19e844 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -147,7 +147,7 @@ static int force_enable_local_apic __initdata; */ static int __init parse_lapic(char *arg) { - if (config_enabled(CONFIG_X86_32) && !arg) + if (IS_ENABLED(CONFIG_X86_32) && !arg) force_enable_local_apic = 1; else if (arg && !strncmp(arg, "notscdeadline", 13)) setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); @@ -313,7 +313,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 -#define TSC_DIVISOR 32 +#define TSC_DIVISOR 8 /* * This function sets up the local APIC timer, with a timeout of @@ -565,13 +565,37 @@ static void setup_APIC_timer(void) CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; clockevents_config_and_register(levt, - (tsc_khz / TSC_DIVISOR) * 1000, + tsc_khz * (1000 / TSC_DIVISOR), 0xF, ~0UL); } else clockevents_register_device(levt); } /* + * Install the updated TSC frequency from recalibration at the TSC + * deadline clockevent devices. + */ +static void __lapic_update_tsc_freq(void *info) +{ + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); + + if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR)); +} + +void lapic_update_tsc_freq(void) +{ + /* + * The clockevent device's ->mult and ->shift can both be + * changed. In order to avoid races, schedule the frequency + * update code on each CPU. + */ + on_each_cpu(__lapic_update_tsc_freq, NULL, 0); +} + +/* * In this functions we calibrate APIC bus clocks to the external timer. * * We want to do the calibration only once since we want to have local timer diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index a5e400afc563..6066d945c40e 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -523,7 +523,7 @@ static int apic_set_affinity(struct irq_data *irq_data, struct apic_chip_data *data = irq_data->chip_data; int err, irq = irq_data->irq; - if (!config_enabled(CONFIG_SMP)) + if (!IS_ENABLED(CONFIG_SMP)) return -EPERM; if (!cpumask_intersects(dest, cpu_online_mask)) diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 6368fa69d2af..54f35d988025 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -155,7 +155,7 @@ static void init_x2apic_ldr(void) /* * At CPU state changes, update the x2apic cluster sibling info. */ -int x2apic_prepare_cpu(unsigned int cpu) +static int x2apic_prepare_cpu(unsigned int cpu) { if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL)) return -ENOMEM; @@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu) return 0; } -int x2apic_dead_cpu(unsigned int this_cpu) +static int x2apic_dead_cpu(unsigned int this_cpu) { int cpu; @@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu) static int x2apic_cluster_probe(void) { int cpu = smp_processor_id(); + int ret; if (!x2apic_mode) return 0; + ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", + x2apic_prepare_cpu, x2apic_dead_cpu); + if (ret < 0) { + pr_err("Failed to register X2APIC_PREPARE\n"); + return 0; + } cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); - cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", - x2apic_prepare_cpu, x2apic_dead_cpu); return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 09b59adaea3f..cb0673c1e940 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -223,6 +223,11 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (strncmp(oem_id, "SGI", 3) != 0) return 0; + if (numa_off) { + pr_err("UV: NUMA is off, disabling UV support\n"); + return 0; + } + /* Setup early hub type field in uv_hub_info for Node 0 */ uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; @@ -325,7 +330,7 @@ static __init void build_uv_gr_table(void) struct uv_gam_range_entry *gre = uv_gre_table; struct uv_gam_range_s *grt; unsigned long last_limit = 0, ram_limit = 0; - int bytes, i, sid, lsid = -1; + int bytes, i, sid, lsid = -1, indx = 0, lindx = -1; if (!gre) return; @@ -356,11 +361,12 @@ static __init void build_uv_gr_table(void) } sid = gre->sockid - _min_socket; if (lsid < sid) { /* new range */ - grt = &_gr_table[sid]; - grt->base = lsid; + grt = &_gr_table[indx]; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; lsid = sid; + lindx = indx++; continue; } if (lsid == sid && !ram_limit) { /* update range */ @@ -371,7 +377,7 @@ static __init void build_uv_gr_table(void) } if (!ram_limit) { /* non-contiguous ram range */ grt++; - grt->base = sid - 1; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; continue; @@ -1155,19 +1161,18 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s %3s\n", + pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", - "SID", "PN", "PXM"); + "SID", "PN"); } pr_info( - "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x %3d\n", + "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, ((unsigned long)(gre->limit - lgre)) >> (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ - gre->type, gre->nasid, gre->sockid, - gre->pnode, gre->pxm); + gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; if (sock_min > gre->sockid) @@ -1286,7 +1291,7 @@ static void __init build_socket_tables(void) _pnode_to_socket[i] = SOCK_EMPTY; /* fill in pnode/node/addr conversion list values */ - pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n"); + pr_info("UV: GAM Building socket/pnode conversion tables\n"); for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) continue; @@ -1294,20 +1299,18 @@ static void __init build_socket_tables(void) if (_socket_to_pnode[i] != SOCK_EMPTY) continue; /* duplicate */ _socket_to_pnode[i] = gre->pnode; - _socket_to_node[i] = gre->pxm; i = gre->pnode - minpnode; _pnode_to_socket[i] = gre->sockid; pr_info( - "UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n", + "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", gre->sockid, gre->type, gre->nasid, _socket_to_pnode[gre->sockid - minsock], - _socket_to_node[gre->sockid - minsock], _pnode_to_socket[gre->pnode - minpnode]); } - /* check socket -> node values */ + /* Set socket -> node values */ lnid = -1; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); @@ -1318,14 +1321,9 @@ static void __init build_socket_tables(void) lnid = nid; apicid = per_cpu(x86_cpu_to_apicid, cpu); sockid = apicid >> uv_cpuid.socketid_shift; - i = sockid - minsock; - - if (nid != _socket_to_node[i]) { - pr_warn( - "UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n", - i, sockid, gre->type, _socket_to_node[i], nid); - _socket_to_node[i] = nid; - } + _socket_to_node[sockid - minsock] = nid; + pr_info("UV: sid:%02x: apicid:%04x node:%2d\n", + sockid, apicid, nid); } /* Setup physical blade to pnode translation from GAM Range Table */ diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 9e231d88bb33..a184c210efba 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -159,8 +159,8 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); + ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) || + IS_ENABLED(CONFIG_IA32_EMULATION)); if (!access_ok(VERIFY_WRITE, buf, size)) return -EACCES; @@ -268,8 +268,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) u64 xfeatures = 0; int fx_only = 0; - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); + ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) || + IS_ENABLED(CONFIG_IA32_EMULATION)); if (!buf) { fpu__clear(fpu); @@ -416,8 +416,8 @@ void fpu__init_prepare_fx_sw_frame(void) fx_sw_reserved.xfeatures = xfeatures_mask; fx_sw_reserved.xstate_size = fpu_user_xstate_size; - if (config_enabled(CONFIG_IA32_EMULATION) || - config_enabled(CONFIG_X86_32)) { + if (IS_ENABLED(CONFIG_IA32_EMULATION) || + IS_ENABLED(CONFIG_X86_32)) { int fsave_header_size = sizeof(struct fregs_state); fx_sw_reserved_ia32 = fx_sw_reserved; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 680049aa4593..01567aa87503 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -866,105 +866,17 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } - -/* - * Set xfeatures (aka XSTATE_BV) bit for a feature that we want - * to take out of its "init state". This will ensure that an - * XRSTOR actually restores the state. - */ -static void fpu__xfeature_set_non_init(struct xregs_state *xsave, - int xstate_feature_mask) -{ - xsave->header.xfeatures |= xstate_feature_mask; -} - -/* - * This function is safe to call whether the FPU is in use or not. - * - * Note that this only works on the current task. - * - * Inputs: - * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, - * XFEATURE_MASK_SSE, etc...) - * @xsave_state_ptr: a pointer to a copy of the state that you would - * like written in to the current task's FPU xsave state. This pointer - * must not be located in the current tasks's xsave area. - * Output: - * address of the state in the xsave area or NULL if the state - * is not present or is in its 'init state'. - */ -static void fpu__xfeature_set_state(int xstate_feature_mask, - void *xstate_feature_src, size_t len) -{ - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; - struct fpu *fpu = ¤t->thread.fpu; - void *dst; - - if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - WARN_ONCE(1, "%s() attempted with no xsave support", __func__); - return; - } - - /* - * Tell the FPU code that we need the FPU state to be in - * 'fpu' (not in the registers), and that we need it to - * be stable while we write to it. - */ - fpu__current_fpstate_write_begin(); - - /* - * This method *WILL* *NOT* work for compact-format - * buffers. If the 'xstate_feature_mask' is unset in - * xcomp_bv then we may need to move other feature state - * "up" in the buffer. - */ - if (xsave->header.xcomp_bv & xstate_feature_mask) { - WARN_ON_ONCE(1); - goto out; - } - - /* find the location in the xsave buffer of the desired state */ - dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask); - - /* - * Make sure that the pointer being passed in did not - * come from the xsave buffer itself. - */ - WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself"); - - /* put the caller-provided data in the location */ - memcpy(dst, xstate_feature_src, len); - - /* - * Mark the xfeature so that the CPU knows there is state - * in the buffer now. - */ - fpu__xfeature_set_non_init(xsave, xstate_feature_mask); -out: - /* - * We are done writing to the 'fpu'. Reenable preeption - * and (possibly) move the fpstate back in to the fpregs. - */ - fpu__current_fpstate_write_end(); -} - #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* - * This will go out and modify the XSAVE buffer so that PKRU is - * set to a particular state for access to 'pkey'. - * - * PKRU state does affect kernel access to user memory. We do - * not modfiy PKRU *itself* here, only the XSAVE state that will - * be restored in to PKRU when we return back to userspace. + * This will go out and modify PKRU register to set the access + * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; - struct pkru_state *old_pkru_state; - struct pkru_state new_pkru_state; + u32 old_pkru; int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); u32 new_pkru_bits = 0; @@ -974,6 +886,15 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * For most XSAVE components, this would be an arduous task: + * brining fpstate up to date with fpregs, updating fpstate, + * then re-populating fpregs. But, for components that are + * never lazily managed, we can just access the fpregs + * directly. PKRU is never managed lazily, so we can just + * manipulate it directly. Make sure it stays that way. + */ + WARN_ON_ONCE(!use_eager_fpu()); /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) @@ -984,37 +905,12 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, /* Shift the bits in to the correct place in PKRU for pkey: */ new_pkru_bits <<= pkey_shift; - /* Locate old copy of the state in the xsave buffer: */ - old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU); - - /* - * When state is not in the buffer, it is in the init - * state, set it manually. Otherwise, copy out the old - * state. - */ - if (!old_pkru_state) - new_pkru_state.pkru = 0; - else - new_pkru_state.pkru = old_pkru_state->pkru; - - /* Mask off any old bits in place: */ - new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - - /* Set the newly-requested bits: */ - new_pkru_state.pkru |= new_pkru_bits; - - /* - * We could theoretically live without zeroing pkru.pad. - * The current XSAVE feature state definition says that - * only bytes 0->3 are used. But we do not want to - * chance leaking kernel stack out to userspace in case a - * memcpy() of the whole xsave buffer was done. - * - * They're in the same cacheline anyway. - */ - new_pkru_state.pad = 0; + /* Get old PKRU and mask off any old bits in place: */ + old_pkru = read_pkru(); + old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state)); + /* Write old part along with new part: */ + write_pkru(old_pkru | new_pkru_bits); return 0; } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 2dda0bc4576e..f16c55bfc090 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -25,8 +25,6 @@ static void __init i386_default_early_setup(void) /* Initialize 32bit specific setup functions */ x86_init.resources.reserve_resources = i386_reserve_resources; x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; - - reserve_bios_regions(); } asmlinkage __visible void __init i386_start_kernel(void) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 99d48e7d2974..54a2372f5dbb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -183,7 +183,6 @@ void __init x86_64_start_reservations(char *real_mode_data) copy_bootdata(__va(real_mode_data)); x86_early_init_platform_quirks(); - reserve_bios_regions(); switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_INTEL_MID: diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 3d747070fe67..c6dfd801df97 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1019,7 +1019,6 @@ void hpet_disable(void) */ #include <linux/mc146818rtc.h> #include <linux/rtc.h> -#include <asm/rtc.h> #define DEFAULT_RTC_INT_FREQ 64 #define DEFAULT_RTC_SHIFT 6 @@ -1243,7 +1242,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) - get_rtc_time(&curr_time); + mc146818_get_time(&curr_time); if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 61521dc19c10..9f669fdd2010 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - - irq_stats(j)->irq_tlb_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 04b132a767f1..bfe4d6c96fbd 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -17,6 +17,7 @@ #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/hardirq.h> +#include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/export.h> diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 833b1d329c47..5d400ba1349d 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -340,7 +340,7 @@ static inline struct iommu_table *find_iommu_table(struct device *dev) static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems,enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -364,7 +364,7 @@ static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, static int calgary_map_sg(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -396,7 +396,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, return nelems; error: - calgary_unmap_sg(dev, sg, nelems, dir, NULL); + calgary_unmap_sg(dev, sg, nelems, dir, 0); for_each_sg(sg, s, nelems, i) { sg->dma_address = DMA_ERROR_CODE; sg->dma_length = 0; @@ -407,7 +407,7 @@ error: static dma_addr_t calgary_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { void *vaddr = page_address(page) + offset; unsigned long uaddr; @@ -422,7 +422,7 @@ static dma_addr_t calgary_map_page(struct device *dev, struct page *page, static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct iommu_table *tbl = find_iommu_table(dev); unsigned int npages; @@ -432,7 +432,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, } static void* calgary_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs) + dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { void *ret = NULL; dma_addr_t mapping; @@ -466,7 +466,7 @@ error: static void calgary_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned int npages; struct iommu_table *tbl = find_iommu_table(dev); diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 6ba014c61d62..d30c37750765 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -77,7 +77,7 @@ void __init pci_iommu_alloc(void) } void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long dma_mask; struct page *page; @@ -120,7 +120,7 @@ again: } void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, struct dma_attrs *attrs) + dma_addr_t dma_addr, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page *page = virt_to_page(vaddr); diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index da15918d1c81..00e71ce396a8 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -28,7 +28,7 @@ check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) static dma_addr_t nommu_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t bus = page_to_phys(page) + offset; WARN_ON(size == 0); @@ -55,7 +55,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, */ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 5069ef560d83..b47edb8f5256 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -16,7 +16,7 @@ int swiotlb __read_mostly; void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { void *vaddr; @@ -37,7 +37,7 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, void x86_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, - struct dma_attrs *attrs) + unsigned long attrs) { if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr))) swiotlb_free_coherent(dev, size, vaddr, dma_addr); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 600edd225e81..f79576a541ff 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -923,15 +923,18 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) case offsetof(struct user32, regs.orig_eax): /* - * A 32-bit debugger setting orig_eax means to restore - * the state of the task restarting a 32-bit syscall. - * Make sure we interpret the -ERESTART* codes correctly - * in case the task is not actually still sitting at the - * exit from a 32-bit syscall with TS_COMPAT still set. + * Warning: bizarre corner case fixup here. A 32-bit + * debugger setting orig_eax to -1 wants to disable + * syscall restart. Make sure that the syscall + * restart code sign-extends orig_ax. Also make sure + * we interpret the -ERESTART* codes correctly if + * loaded into regs->ax in case the task is not + * actually still sitting at the exit from a 32-bit + * syscall with TS_COMPAT still set. */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - task_thread_info(child)->status |= TS_COMPAT; + task_thread_info(child)->status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 06c58ce46762..3599404e3089 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -64,14 +64,9 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) u8 flags; do { - version = src->version; - /* Make the latest version visible */ - smp_rmb(); - + version = pvclock_read_begin(src); flags = src->flags; - /* Make sure that the version double-check is last. */ - smp_rmb(); - } while ((src->version & 1) || version != src->version); + } while (pvclock_read_retry(src, version)); return flags & valid_flags; } @@ -84,10 +79,10 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) u8 flags; do { - version = __pvclock_read_cycles(src, &ret, &flags); - /* Make sure that the version double-check is last. */ - smp_rmb(); - } while ((src->version & 1) || version != src->version); + version = pvclock_read_begin(src); + ret = __pvclock_read_cycles(src); + flags = src->flags; + } while (pvclock_read_retry(src, version)); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { src->flags &= ~PVCLOCK_GUEST_STOPPED; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index eceaa082ec3f..79c6311cd912 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -13,7 +13,6 @@ #include <asm/x86_init.h> #include <asm/time.h> #include <asm/intel-mid.h> -#include <asm/rtc.h> #include <asm/setup.h> #ifdef CONFIG_X86_32 @@ -47,7 +46,7 @@ int mach_set_rtc_mmss(const struct timespec *now) rtc_time_to_tm(nowtime, &tm); if (!rtc_valid_tm(&tm)) { - retval = set_rtc_time(&tm); + retval = mc146818_set_time(&tm); if (retval) printk(KERN_ERR "%s: RTC write failed with error %d\n", __func__, retval); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 991b77986d57..0fa60f5f5a16 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -936,8 +936,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); - kernel_randomize_memory(); - iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); @@ -1055,6 +1053,12 @@ void __init setup_arch(char **cmdline_p) max_possible_pfn = max_pfn; + /* + * Define random base addresses for memory sections after max_pfn is + * defined and before each memory section base is used. + */ + kernel_randomize_memory(); + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); @@ -1097,6 +1101,8 @@ void __init setup_arch(char **cmdline_p) efi_find_mirror(); } + reserve_bios_regions(); + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1125,7 +1131,15 @@ void __init setup_arch(char **cmdline_p) early_trap_pf_init(); - setup_real_mode(); + /* + * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) + * with the current CR4 value. This may not be necessary, but + * auditing all the early-boot CR4 manipulation would be needed to + * rule it out. + */ + if (boot_cpu_data.cpuid_level >= 0) + /* A CPU has %cr4 if and only if it has CPUID. */ + mmu_cr4_features = __read_cr4(); memblock_set_current_limit(get_max_mapped()); @@ -1174,13 +1188,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); - if (boot_cpu_data.cpuid_level >= 0) { - /* A CPU has %cr4 if and only if it has CPUID */ - mmu_cr4_features = __read_cr4(); - if (trampoline_cr4_features) - *trampoline_cr4_features = mmu_cr4_features; - } - #ifdef CONFIG_X86_32 /* sync back kernel address range */ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 22cc2f9f8aec..04cb3212db2d 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -146,7 +146,7 @@ static int restore_sigcontext(struct pt_regs *regs, buf = (void __user *)buf_val; } get_user_catch(err); - err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32)); + err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); force_iret(); @@ -245,14 +245,14 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, struct fpu *fpu = ¤t->thread.fpu; /* redzone */ - if (config_enabled(CONFIG_X86_64)) + if (IS_ENABLED(CONFIG_X86_64)) sp -= 128; /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { if (sas_ss_flags(sp) == 0) sp = current->sas_ss_sp + current->sas_ss_size; - } else if (config_enabled(CONFIG_X86_32) && + } else if (IS_ENABLED(CONFIG_X86_32) && !onsigstack && (regs->ss & 0xffff) != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && @@ -262,7 +262,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, } if (fpu->fpstate_active) { - sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -662,18 +662,18 @@ badframe: static inline int is_ia32_compat_frame(void) { - return config_enabled(CONFIG_IA32_EMULATION) && + return IS_ENABLED(CONFIG_IA32_EMULATION) && test_thread_flag(TIF_IA32); } static inline int is_ia32_frame(void) { - return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); + return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(); } static inline int is_x32_frame(void) { - return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); + return IS_ENABLED(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); } static int @@ -760,8 +760,30 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { -#ifdef CONFIG_X86_64 - if (in_ia32_syscall()) + /* + * This function is fundamentally broken as currently + * implemented. + * + * The idea is that we want to trigger a call to the + * restart_block() syscall and that we want in_ia32_syscall(), + * in_x32_syscall(), etc. to match whatever they were in the + * syscall being restarted. We assume that the syscall + * instruction at (regs->ip - 2) matches whatever syscall + * instruction we used to enter in the first place. + * + * The problem is that we can get here when ptrace pokes + * syscall-like values into regs even if we're not in a syscall + * at all. + * + * For now, we maintain historical behavior and guess based on + * stored state. We could do better by saving the actual + * syscall arch in restart_block or (with caveats on x32) by + * checking if regs->ip points to 'int $0x80'. The current + * behavior is incorrect if a tracer has a different bitness + * than the tracee. + */ +#ifdef CONFIG_IA32_EMULATION + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1ef87e887051..78b9cb5a26af 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -22,6 +22,7 @@ #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/geode.h> +#include <asm/apic.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1249,6 +1250,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); + /* Inform the TSC deadline clockevent devices about the recalibration */ + lapic_update_tsc_freq(); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 6c1ff31d99ff..495c776de4b4 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) *cursor &= 0xfe; } /* - * Similar treatment for VEX3 prefix. - * TODO: add XOP/EVEX treatment when insn decoder supports them + * Similar treatment for VEX3/EVEX prefix. + * TODO: add XOP treatment when insn decoder supports them */ - if (insn->vex_prefix.nbytes == 3) { + if (insn->vex_prefix.nbytes >= 3) { /* * vex2: c5 rvvvvLpp (has no b bit) * vex3/xop: c4/8f rxbmmmmm wvvvvLpp * evex: 62 rxbR00mm wvvvv1pp zllBVaaa - * (evex will need setting of both b and x since - * in non-sib encoding evex.x is 4th bit of MODRM.rm) - * Setting VEX3.b (setting because it has inverted meaning): + * Setting VEX3.b (setting because it has inverted meaning). + * Setting EVEX.x since (in non-SIB encoding) EVEX.x + * is the 4th bit of MODRM.rm, and needs the same treatment. + * For VEX3-encoded insns, VEX3.x value has no effect in + * non-SIB encoding, the change is superfluous but harmless. */ cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; - *cursor |= 0x20; + *cursor |= 0x60; } /* @@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) reg = MODRM_REG(insn); /* Fetch modrm.reg */ reg2 = 0xff; /* Fetch vex.vvvv */ - if (insn->vex_prefix.nbytes == 2) - reg2 = insn->vex_prefix.bytes[1]; - else if (insn->vex_prefix.nbytes == 3) + if (insn->vex_prefix.nbytes) reg2 = insn->vex_prefix.bytes[2]; /* - * TODO: add XOP, EXEV vvvv reading. + * TODO: add XOP vvvv reading. * * vex.vvvv field is in bits 6-3, bits are inverted. * But in 32-bit mode, high-order bit may be ignored. diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 61ebdc13a29a..035731eb3897 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -120,4 +120,7 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); +int kvm_setup_default_irq_routing(struct kvm *kvm); +int kvm_setup_empty_irq_routing(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 730cf174090a..b62c85229711 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1349,6 +1349,9 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) { + if (!lapic_in_kernel(vcpu)) + return false; + return vcpu->arch.apic->lapic_timer.hv_timer_in_use; } EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bc354f003ce1..a45d8580f91e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2809,12 +2809,8 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXECUTE_ONLY_BIT; vmx->nested.nested_vmx_ept_caps &= vmx_capability.ept; - /* - * For nested guests, we don't do anything specific - * for single context invalidation. Hence, only advertise - * support for global context invalidation. - */ - vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT; + vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | + VMX_EPT_EXTENT_CONTEXT_BIT; } else vmx->nested.nested_vmx_ept_caps = 0; @@ -2945,7 +2941,6 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) vmx->nested.nested_vmx_secondary_ctls_high); break; case MSR_IA32_VMX_EPT_VPID_CAP: - /* Currently, no nested vpid support */ *pdata = vmx->nested.nested_vmx_ept_caps | ((u64)vmx->nested.nested_vmx_vpid_caps << 32); break; @@ -7609,12 +7604,16 @@ static int handle_invept(struct kvm_vcpu *vcpu) switch (type) { case VMX_EPT_EXTENT_GLOBAL: + /* + * TODO: track mappings and invalidate + * single context requests appropriately + */ + case VMX_EPT_EXTENT_CONTEXT: kvm_mmu_sync_roots(vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); nested_vmx_succeed(vcpu); break; default: - /* Trap single context invalidation invept calls */ BUG_ON(1); break; } diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index 02de3d74d2c5..8a602a1e404a 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -35,6 +35,7 @@ ENDPROC(__sw_hweight32) ENTRY(__sw_hweight64) #ifdef CONFIG_X86_64 + pushq %rdi pushq %rdx movq %rdi, %rdx # w -> t @@ -60,6 +61,7 @@ ENTRY(__sw_hweight64) shrq $56, %rax # w = w_tmp >> 56 popq %rdx + popq %rdi ret #else /* CONFIG_X86_32 */ /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */ diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index f7dfeda83e5c..121f59c6ee54 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -19,7 +19,7 @@ #include <asm/cpufeature.h> #include <asm/setup.h> -#define debug_putstr(v) early_printk(v) +#define debug_putstr(v) early_printk("%s", v) #define has_cpuflag(f) boot_cpu_has(f) #define get_boot_seed() kaslr_offset() #endif diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index ec21796ac5fd..4473cb4f8b90 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -3,15 +3,17 @@ * included by both the compressed kernel and the regular kernel. */ -static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, +static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page, unsigned long addr, unsigned long end) { addr &= PMD_MASK; for (; addr < end; addr += PMD_SIZE) { pmd_t *pmd = pmd_page + pmd_index(addr); - if (!pmd_present(*pmd)) - set_pmd(pmd, __pmd(addr | pmd_flag)); + if (pmd_present(*pmd)) + continue; + + set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag)); } } @@ -30,13 +32,13 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, if (pud_present(*pud)) { pmd = pmd_offset(pud, 0); - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); continue; } pmd = (pmd_t *)info->alloc_pgt_page(info->context); if (!pmd) return -ENOMEM; - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); } @@ -44,14 +46,15 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, } int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end) + unsigned long pstart, unsigned long pend) { + unsigned long addr = pstart + info->offset; + unsigned long end = pend + info->offset; unsigned long next; int result; - int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; for (; addr < end; addr = next) { - pgd_t *pgd = pgd_page + pgd_index(addr) + off; + pgd_t *pgd = pgd_page + pgd_index(addr); pud_t *pud; next = (addr & PGDIR_MASK) + PGDIR_SIZE; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 620928903be3..d28a2d741f9e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -122,8 +122,18 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) +/* + * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS. + * With KASLR memory randomization, depending on the machine e820 memory + * and the PUD alignment. We may need twice more pages when KASLR memory + * randomization is enabled. + */ +#ifndef CONFIG_RANDOMIZE_MEMORY +#define INIT_PGD_PAGE_COUNT 6 +#else +#define INIT_PGD_PAGE_COUNT 12 +#endif +#define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 26dccd6c0df1..ec8654f117d8 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -97,7 +97,7 @@ void __init kernel_randomize_memory(void) * add padding if needed (especially for memory hotplug support). */ BUG_ON(kaslr_regions[0].base != &page_offset_base); - memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) + + memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; /* Adapt phyiscal memory region size based on available memory */ diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 5ceda85b8687..052c1cb76305 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -169,7 +169,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs) + unsigned long attrs) { void *vaddr; diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index e88b4176260f..b814ca675131 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -274,14 +274,14 @@ static struct dma_map_ops *vmd_dma_ops(struct device *dev) } static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, - gfp_t flag, struct dma_attrs *attrs) + gfp_t flag, unsigned long attrs) { return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag, attrs); } static void vmd_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t addr, struct dma_attrs *attrs) + dma_addr_t addr, unsigned long attrs) { return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr, attrs); @@ -289,7 +289,7 @@ static void vmd_free(struct device *dev, size_t size, void *vaddr, static int vmd_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr, size, attrs); @@ -297,7 +297,7 @@ static int vmd_mmap(struct device *dev, struct vm_area_struct *vma, static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t addr, size_t size, - struct dma_attrs *attrs) + unsigned long attrs) { return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr, addr, size, attrs); @@ -306,26 +306,26 @@ static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt, static dma_addr_t vmd_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size, dir, attrs); } static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs); } static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs); } static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 17c8bbd4e2f0..1fbb408e2e72 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -51,7 +51,6 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> -#include <asm/rtc.h> #include <asm/uv/uv.h> static struct efi efi_phys __initdata; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 04db6fbce96d..677e29e29473 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -25,6 +25,7 @@ #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/init.h> +#include <linux/mc146818rtc.h> #include <linux/efi.h> #include <linux/uaccess.h> #include <linux/io.h> diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 4480c06cade7..89d1146f5a6f 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -254,6 +254,7 @@ void __init efi_free_boot_services(void) for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + size_t rm_size; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) @@ -263,6 +264,26 @@ void __init efi_free_boot_services(void) if (md->attribute & EFI_MEMORY_RUNTIME) continue; + /* + * Nasty quirk: if all sub-1MB memory is used for boot + * services, we can get here without having allocated the + * real mode trampoline. It's too late to hand boot services + * memory back to the memblock allocator, so instead + * try to manually allocate the trampoline if needed. + * + * I've seen this on a Dell XPS 13 9350 with firmware + * 1.4.4 with SGX enabled booting Linux via Fedora 24's + * grub2-efi on a hard disk. (And no, I don't know why + * this happened, but Linux should still try to boot rather + * panicing early.) + */ + rm_size = real_mode_size_needed(); + if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { + set_real_mode_mem(start, rm_size); + start += rm_size; + size -= rm_size; + } + free_bootmem_late(start, size); } diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c index ee40fcb6e54d..58024862a7eb 100644 --- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c +++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c @@ -22,6 +22,7 @@ #include <linux/init.h> #include <linux/sfi.h> #include <linux/platform_device.h> +#include <linux/mc146818rtc.h> #include <asm/intel-mid.h> #include <asm/intel_mid_vrtc.h> diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 66b2166ea4a1..23f2f3e41c7f 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -187,7 +187,8 @@ EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target); void uv_bios_init(void) { uv_systab = NULL; - if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) { + if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || + !efi.uv_systab || efi_runtime_disabled()) { pr_crit("UV: UVsystab: missing\n"); return; } @@ -199,12 +200,14 @@ void uv_bios_init(void) return; } + /* Starting with UV4 the UV systab size is variable */ if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) { + int size = uv_systab->size; + iounmap(uv_systab); - uv_systab = ioremap(efi.uv_systab, uv_systab->size); + uv_systab = ioremap(efi.uv_systab, size); if (!uv_systab) { - pr_err("UV: UVsystab: ioremap(%d) failed!\n", - uv_systab->size); + pr_err("UV: UVsystab: ioremap(%d) failed!\n", size); return; } } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f2b5e6a5cf95..a3e3ccc87138 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -37,11 +37,11 @@ unsigned long jump_address_phys; */ unsigned long restore_cr3 __visible; -pgd_t *temp_level4_pgt __visible; +unsigned long temp_level4_pgt __visible; unsigned long relocated_restore_code __visible; -static int set_up_temporary_text_mapping(void) +static int set_up_temporary_text_mapping(pgd_t *pgd) { pmd_t *pmd; pud_t *pud; @@ -71,7 +71,7 @@ static int set_up_temporary_text_mapping(void) __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); set_pud(pud + pud_index(restore_jump_address), __pud(__pa(pmd) | _KERNPG_TABLE)); - set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(pud) | _KERNPG_TABLE)); return 0; @@ -87,18 +87,19 @@ static int set_up_temporary_mappings(void) struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, - .kernel_mapping = true, + .offset = __PAGE_OFFSET, }; unsigned long mstart, mend; + pgd_t *pgd; int result; int i; - temp_level4_pgt = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!temp_level4_pgt) + pgd = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!pgd) return -ENOMEM; /* Prepare a temporary mapping for the kernel text */ - result = set_up_temporary_text_mapping(); + result = set_up_temporary_text_mapping(pgd); if (result) return result; @@ -107,13 +108,12 @@ static int set_up_temporary_mappings(void) mstart = pfn_mapped[i].start << PAGE_SHIFT; mend = pfn_mapped[i].end << PAGE_SHIFT; - result = kernel_ident_mapping_init(&info, temp_level4_pgt, - mstart, mend); - + result = kernel_ident_mapping_init(&info, pgd, mstart, mend); if (result) return result; } + temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET; return 0; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 8eee0e9c93f0..ce8da3a0412c 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -72,8 +72,6 @@ ENTRY(restore_image) /* code below has been relocated to a safe page */ ENTRY(core_restore_code) /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rcx - subq %rcx, %rax movq %rax, %cr3 /* flush TLB */ movq %rbx, %rcx diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 705e3fffb4a1..5db706f14111 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,9 +1,11 @@ #include <linux/io.h> +#include <linux/slab.h> #include <linux/memblock.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> #include <asm/realmode.h> +#include <asm/tlbflush.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -11,25 +13,37 @@ u32 *trampoline_cr4_features; /* Hold the pgd entry used on booting additional CPUs */ pgd_t trampoline_pgd_entry; +void __init set_real_mode_mem(phys_addr_t mem, size_t size) +{ + void *base = __va(mem); + + real_mode_header = (struct real_mode_header *) base; + printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", + base, (unsigned long long)mem, size); +} + void __init reserve_real_mode(void) { phys_addr_t mem; - unsigned char *base; - size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); + size_t size = real_mode_size_needed(); + + if (!size) + return; + + WARN_ON(slab_is_available()); /* Has to be under 1M so we can execute real-mode AP code. */ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (!mem) - panic("Cannot allocate trampoline\n"); + if (!mem) { + pr_info("No sub-1M memory is available for the trampoline\n"); + return; + } - base = __va(mem); memblock_reserve(mem, size); - real_mode_header = (struct real_mode_header *) base; - printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", - base, (unsigned long long)mem, size); + set_real_mode_mem(mem, size); } -void __init setup_real_mode(void) +static void __init setup_real_mode(void) { u16 real_mode_seg; const u32 *rel; @@ -84,7 +98,7 @@ void __init setup_real_mode(void) trampoline_header->start = (u64) secondary_startup_64; trampoline_cr4_features = &trampoline_header->cr4; - *trampoline_cr4_features = __read_cr4(); + *trampoline_cr4_features = mmu_cr4_features; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; @@ -100,7 +114,7 @@ void __init setup_real_mode(void) * need to mark it executable at do_pre_smp_initcalls() at least, * thus run it as a early_initcall(). */ -static int __init set_real_mode_permissions(void) +static void __init set_real_mode_permissions(void) { unsigned char *base = (unsigned char *) real_mode_header; size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); @@ -119,7 +133,16 @@ static int __init set_real_mode_permissions(void) set_memory_nx((unsigned long) base, size >> PAGE_SHIFT); set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT); set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT); +} + +static int __init init_real_mode(void) +{ + if (!real_mode_header) + panic("Real mode trampoline was not allocated"); + + setup_real_mode(); + set_real_mode_permissions(); return 0; } -early_initcall(set_real_mode_permissions); +early_initcall(init_real_mode); diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 6c803ca49b5d..d72dec406ccb 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -2,6 +2,9 @@ # Building vDSO images for x86. # +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + VDSO64-y := y vdso-install-$(VDSO64-y) += vdso.so diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index cd66698348ca..1e68806d6695 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -142,7 +142,7 @@ static void xtensa_sync_sg_for_device(struct device *dev, static void *xtensa_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { unsigned long ret; unsigned long uncached = 0; @@ -171,7 +171,7 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size, } static void xtensa_dma_free(struct device *hwdev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) + dma_addr_t dma_handle, unsigned long attrs) { unsigned long addr = (unsigned long)vaddr + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR; @@ -185,7 +185,7 @@ static void xtensa_dma_free(struct device *hwdev, size_t size, void *vaddr, static dma_addr_t xtensa_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { dma_addr_t dma_handle = page_to_phys(page) + offset; @@ -195,14 +195,14 @@ static dma_addr_t xtensa_map_page(struct device *dev, struct page *page, static void xtensa_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { xtensa_sync_single_for_cpu(dev, dma_handle, size, dir); } static int xtensa_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; @@ -217,7 +217,7 @@ static int xtensa_map_sg(struct device *dev, struct scatterlist *sg, static void xtensa_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct scatterlist *s; int i; |