diff options
Diffstat (limited to 'arch')
168 files changed, 2542 insertions, 1563 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ecd12379e2cd..bd204bfa29ed 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -41,6 +41,8 @@ config ARC select PERF_USE_VMALLOC select HAVE_DEBUG_STACKOVERFLOW select HAVE_GENERIC_DMA_COHERENT + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZMA config MIGHT_HAVE_PCI bool @@ -186,14 +188,6 @@ if SMP config ARC_HAS_COH_CACHES def_bool n -config ARC_MCIP - bool "ARConnect Multicore IP (MCIP) Support " - depends on ISA_ARCV2 - help - This IP block enables SMP in ARC-HS38 cores. - It provides for cross-core interrupts, multi-core debug - hardware semaphores, shared memory,.... - config NR_CPUS int "Maximum number of CPUs (2-4096)" range 2 4096 @@ -211,6 +205,15 @@ config ARC_SMP_HALT_ON_RESET endif #SMP +config ARC_MCIP + bool "ARConnect Multicore IP (MCIP) Support " + depends on ISA_ARCV2 + default y if SMP + help + This IP block enables SMP in ARC-HS38 cores. + It provides for cross-core interrupts, multi-core debug + hardware semaphores, shared memory,.... + menuconfig ARC_CACHE bool "Enable Cache Support" default y @@ -537,14 +540,6 @@ config ARC_DBG_TLB_PARANOIA bool "Paranoia Checks in Low Level TLB Handlers" default n -config ARC_DBG_TLB_MISS_COUNT - bool "Profile TLB Misses" - default n - select DEBUG_FS - help - Counts number of I and D TLB Misses and exports them via Debugfs - The counters can be cleared via Debugfs as well - endif config ARC_UBOOT_SUPPORT diff --git a/arch/arc/Makefile b/arch/arc/Makefile index aa82d13d4213..19cce226d1a8 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -71,7 +71,9 @@ cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables $(cfi) ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE # Generic build system uses -O2, we want -O3 # Note: No need to add to cflags-y as that happens anyways -ARCH_CFLAGS += -O3 +# +# Disable the false maybe-uninitialized warings gcc spits out at -O3 +ARCH_CFLAGS += -O3 $(call cc-disable-warning,maybe-uninitialized,) endif # small data is default for elf32 tool-chain. If not usable, disable it diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile index e597cb34c16a..f94cf151e06a 100644 --- a/arch/arc/boot/Makefile +++ b/arch/arc/boot/Makefile @@ -14,9 +14,15 @@ UIMAGE_ENTRYADDR = $(LINUX_START_TEXT) suffix-y := bin suffix-$(CONFIG_KERNEL_GZIP) := gz +suffix-$(CONFIG_KERNEL_LZMA) := lzma -targets += uImage uImage.bin uImage.gz -extra-y += vmlinux.bin vmlinux.bin.gz +targets += uImage +targets += uImage.bin +targets += uImage.gz +targets += uImage.lzma +extra-y += vmlinux.bin +extra-y += vmlinux.bin.gz +extra-y += vmlinux.bin.lzma $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -24,12 +30,18 @@ $(obj)/vmlinux.bin: vmlinux FORCE $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzma) + $(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE $(call if_changed,uimage,none) $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE $(call if_changed,uimage,gzip) +$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE + $(call if_changed,uimage,lzma) + $(obj)/uImage: $(obj)/uImage.$(suffix-y) @ln -sf $(notdir $<) $@ @echo ' Image $@ is ready' diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 6ae2c476ad82..53ce226f77a5 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -71,7 +71,7 @@ reg-io-width = <4>; }; - arcpmu0: pmu { + arcpct0: pct { compatible = "snps,arc700-pct"; }; }; diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index ce0ccd20b5bf..5ee96b067c08 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -69,7 +69,7 @@ }; }; - arcpmu0: pmu { + arcpct0: pct { compatible = "snps,arc700-pct"; }; }; diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index bcf603142a33..3c391ba565ed 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -83,5 +83,9 @@ reg = <0xf0003000 0x44>; interrupts = <7>; }; + + arcpct0: pct { + compatible = "snps,arc700-pct"; + }; }; }; diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 7314f538847b..b0066a749d4c 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index 65ab9fbf83f2..ebe9ebb92933 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 3b3990cddbe1..4bde43278be6 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -12,6 +12,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 98cf20933bbb..f6fb3d26557e 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index ddf8b96d494e..b9f0fe00044b 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index ceb90745326e..6da71ba253a9 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -10,6 +10,7 @@ CONFIG_IKCONFIG_PROC=y # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" +CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y CONFIG_MODULES=y @@ -34,7 +35,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y @@ -72,7 +72,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HWMON is not set CONFIG_DRM=y CONFIG_DRM_ARCPGU=y -CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index db25c65155cb..1bd24ec3e350 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -43,12 +43,14 @@ #define STATUS_AE_BIT 5 /* Exception active */ #define STATUS_DE_BIT 6 /* PC is in delay slot */ #define STATUS_U_BIT 7 /* User/Kernel mode */ +#define STATUS_Z_BIT 11 #define STATUS_L_BIT 12 /* Loop inhibit */ /* These masks correspond to the status word(STATUS_32) bits */ #define STATUS_AE_MASK (1<<STATUS_AE_BIT) #define STATUS_DE_MASK (1<<STATUS_DE_BIT) #define STATUS_U_MASK (1<<STATUS_U_BIT) +#define STATUS_Z_MASK (1<<STATUS_Z_BIT) #define STATUS_L_MASK (1<<STATUS_L_BIT) /* @@ -349,10 +351,11 @@ struct cpuinfo_arc { struct cpuinfo_arc_bpu bpu; struct bcr_identity core; struct bcr_isa isa; + const char *details, *name; unsigned int vec_base; struct cpuinfo_arc_ccm iccm, dccm; struct { - unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3, + unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2, fpu_sp:1, fpu_dp:1, pad2:6, debug:1, ap:1, smart:1, rtt:1, pad3:4, timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4; diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index fb781e34f322..b3410ff6a62d 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -53,7 +53,7 @@ extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); extern void read_decode_cache_bcr(void); -extern int ioc_exists; +extern int ioc_enable; extern unsigned long perip_base, perip_end; #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h index 7096f97a1434..aa2d6da9d187 100644 --- a/arch/arc/include/asm/elf.h +++ b/arch/arc/include/asm/elf.h @@ -54,7 +54,7 @@ extern int elf_check_arch(const struct elf32_hdr *); * the loader. We need to make sure that it is out of the way of the program * that it will "exec", and that there is sufficient room for the brk. */ -#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3) +#define ELF_ET_DYN_BASE (2UL * TASK_SIZE / 3) /* * When the program starts, a1 contains a pointer to a function to be diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h index 847e3bbe387f..c8fbe4114bad 100644 --- a/arch/arc/include/asm/mcip.h +++ b/arch/arc/include/asm/mcip.h @@ -55,6 +55,22 @@ struct mcip_cmd { #define IDU_M_DISTRI_DEST 0x2 }; +struct mcip_bcr { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad3:8, + idu:1, llm:1, num_cores:6, + iocoh:1, gfrc:1, dbg:1, pad2:1, + msg:1, sem:1, ipi:1, pad:1, + ver:8; +#else + unsigned int ver:8, + pad:1, ipi:1, sem:1, msg:1, + pad2:1, dbg:1, gfrc:1, iocoh:1, + num_cores:6, llm:1, idu:1, + pad3:8; +#endif +}; + /* * MCIP programming model * diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h index 518222bb3f8e..6e91d8b339c3 100644 --- a/arch/arc/include/asm/module.h +++ b/arch/arc/include/asm/module.h @@ -18,6 +18,7 @@ struct mod_arch_specific { void *unw_info; int unw_sec_idx; + const char *secstr; }; #endif diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h index 48b37c693db3..cb954cdab070 100644 --- a/arch/arc/include/asm/setup.h +++ b/arch/arc/include/asm/setup.h @@ -27,11 +27,6 @@ struct id_to_str { const char *str; }; -struct cpuinfo_data { - struct id_to_str info; - int up_range; -}; - extern int root_mountflags, end_mem; void setup_processor(void); @@ -43,5 +38,6 @@ void __init setup_arch_memory(void); #define IS_USED_RUN(v) ((v) ? "" : "(not used) ") #define IS_USED_CFG(cfg) IS_USED_RUN(IS_ENABLED(cfg)) #define IS_AVAIL2(v, s, cfg) IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg)) +#define IS_AVAIL3(v, v2, s) IS_AVAIL1(v, s), IS_AVAIL1(v, IS_DISABLED_RUN(v2)) #endif /* __ASMARC_SETUP_H */ diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index 89fdd1b0a76e..0861007d9ef3 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -37,9 +37,9 @@ extern const char *arc_platform_smp_cpuinfo(void); * API expected BY platform smp code (FROM arch smp code) * * smp_ipi_irq_setup: - * Takes @cpu and @irq to which the arch-common ISR is hooked up + * Takes @cpu and @hwirq to which the arch-common ISR is hooked up */ -extern int smp_ipi_irq_setup(int cpu, int irq); +extern int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq); /* * struct plat_smp_ops - SMP callbacks provided by platform to ARC SMP diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h index e56f9fcc5581..772b67ca56e7 100644 --- a/arch/arc/include/asm/syscalls.h +++ b/arch/arc/include/asm/syscalls.h @@ -17,6 +17,7 @@ int sys_clone_wrapper(int, int, int, int, int); int sys_cacheflush(uint32_t, uint32_t uint32_t); int sys_arc_settls(void *); int sys_arc_gettls(void); +int sys_arc_usr_cmpxchg(int *, int, int); #include <asm-generic/syscalls.h> diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h index 41fa2ec9e02c..9a34136d84b2 100644 --- a/arch/arc/include/uapi/asm/unistd.h +++ b/arch/arc/include/uapi/asm/unistd.h @@ -27,18 +27,19 @@ #define NR_syscalls __NR_syscalls +/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */ +#define __NR_sysfs (__NR_arch_specific_syscall + 3) + /* ARC specific syscall */ #define __NR_cacheflush (__NR_arch_specific_syscall + 0) #define __NR_arc_settls (__NR_arch_specific_syscall + 1) #define __NR_arc_gettls (__NR_arch_specific_syscall + 2) +#define __NR_arc_usr_cmpxchg (__NR_arch_specific_syscall + 4) __SYSCALL(__NR_cacheflush, sys_cacheflush) __SYSCALL(__NR_arc_settls, sys_arc_settls) __SYSCALL(__NR_arc_gettls, sys_arc_gettls) - - -/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */ -#define __NR_sysfs (__NR_arch_specific_syscall + 3) +__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg) __SYSCALL(__NR_sysfs, sys_sysfs) #undef __SYSCALL diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c index f1e07c2344f8..3b67f538f142 100644 --- a/arch/arc/kernel/devtree.c +++ b/arch/arc/kernel/devtree.c @@ -31,6 +31,8 @@ static void __init arc_set_early_base_baud(unsigned long dt_root) arc_base_baud = 166666666; /* Fixed 166.6MHz clk (TB10x) */ else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp")) arc_base_baud = 33333333; /* Fixed 33MHz clk (AXS10x) */ + else if (of_flat_dt_is_compatible(dt_root, "ezchip,arc-nps")) + arc_base_baud = 800000000; /* Fixed 800MHz clk (NPS) */ else arc_base_baud = 50000000; /* Fixed default 50MHz */ } diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 72f9179b1a24..f39142acc89e 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -15,11 +15,12 @@ #include <asm/mcip.h> #include <asm/setup.h> -static char smp_cpuinfo_buf[128]; -static int idu_detected; - static DEFINE_RAW_SPINLOCK(mcip_lock); +#ifdef CONFIG_SMP + +static char smp_cpuinfo_buf[128]; + static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); @@ -86,21 +87,7 @@ static void mcip_ipi_clear(int irq) static void mcip_probe_n_setup(void) { - struct mcip_bcr { -#ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad3:8, - idu:1, llm:1, num_cores:6, - iocoh:1, gfrc:1, dbg:1, pad2:1, - msg:1, sem:1, ipi:1, pad:1, - ver:8; -#else - unsigned int ver:8, - pad:1, ipi:1, sem:1, msg:1, - pad2:1, dbg:1, gfrc:1, iocoh:1, - num_cores:6, llm:1, idu:1, - pad3:8; -#endif - } mp; + struct mcip_bcr mp; READ_BCR(ARC_REG_MCIP_BCR, mp); @@ -114,7 +101,6 @@ static void mcip_probe_n_setup(void) IS_AVAIL1(mp.gfrc, "GFRC")); cpuinfo_arc700[0].extn.gfrc = mp.gfrc; - idu_detected = mp.idu; if (mp.dbg) { __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf); @@ -130,6 +116,8 @@ struct plat_smp_ops plat_smp_ops = { .ipi_clear = mcip_ipi_clear, }; +#endif + /*************************************************************************** * ARCv2 Interrupt Distribution Unit (IDU) * @@ -193,6 +181,8 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, { unsigned long flags; cpumask_t online; + unsigned int destination_bits; + unsigned int distribution_mode; /* errout if no online cpu per @cpumask */ if (!cpumask_and(&online, cpumask, cpu_online_mask)) @@ -200,8 +190,15 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, raw_spin_lock_irqsave(&mcip_lock, flags); - idu_set_dest(data->hwirq, cpumask_bits(&online)[0]); - idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR); + destination_bits = cpumask_bits(&online)[0]; + idu_set_dest(data->hwirq, destination_bits); + + if (ffs(destination_bits) == fls(destination_bits)) + distribution_mode = IDU_M_DISTRI_DEST; + else + distribution_mode = IDU_M_DISTRI_RR; + + idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, distribution_mode); raw_spin_unlock_irqrestore(&mcip_lock, flags); @@ -219,16 +216,15 @@ static struct irq_chip idu_irq_chip = { }; -static int idu_first_irq; +static irq_hw_number_t idu_first_hwirq; static void idu_cascade_isr(struct irq_desc *desc) { - struct irq_domain *domain = irq_desc_get_handler_data(desc); - unsigned int core_irq = irq_desc_get_irq(desc); - unsigned int idu_irq; + struct irq_domain *idu_domain = irq_desc_get_handler_data(desc); + irq_hw_number_t core_hwirq = irqd_to_hwirq(irq_desc_get_irq_data(desc)); + irq_hw_number_t idu_hwirq = core_hwirq - idu_first_hwirq; - idu_irq = core_irq - idu_first_irq; - generic_handle_irq(irq_find_mapping(domain, idu_irq)); + generic_handle_irq(irq_find_mapping(idu_domain, idu_hwirq)); } static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq) @@ -294,9 +290,12 @@ idu_of_init(struct device_node *intc, struct device_node *parent) struct irq_domain *domain; /* Read IDU BCR to confirm nr_irqs */ int nr_irqs = of_irq_count(intc); - int i, irq; + int i, virq; + struct mcip_bcr mp; + + READ_BCR(ARC_REG_MCIP_BCR, mp); - if (!idu_detected) + if (!mp.idu) panic("IDU not detected, but DeviceTree using it"); pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs); @@ -312,11 +311,11 @@ idu_of_init(struct device_node *intc, struct device_node *parent) * however we need it to get the parent virq and set IDU handler * as first level isr */ - irq = irq_of_parse_and_map(intc, i); + virq = irq_of_parse_and_map(intc, i); if (!i) - idu_first_irq = irq; + idu_first_hwirq = irqd_to_hwirq(irq_get_irq_data(virq)); - irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain); + irq_set_chained_handler_and_data(virq, idu_cascade_isr, domain); } __mcip_cmd(CMD_IDU_ENABLE, 0); diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c index 9a2849756022..42e964db2967 100644 --- a/arch/arc/kernel/module.c +++ b/arch/arc/kernel/module.c @@ -30,17 +30,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, char *secstr, struct module *mod) { #ifdef CONFIG_ARC_DW2_UNWIND - int i; - mod->arch.unw_sec_idx = 0; mod->arch.unw_info = NULL; - - for (i = 1; i < hdr->e_shnum; i++) { - if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) { - mod->arch.unw_sec_idx = i; - break; - } - } + mod->arch.secstr = secstr; #endif return 0; } @@ -59,29 +51,33 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, unsigned int relsec, /* sec index for relo sec */ struct module *module) { - int i, n; + int i, n, relo_type; Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr; Elf32_Sym *sym_entry, *sym_sec; - Elf32_Addr relocation; - Elf32_Addr location; - Elf32_Addr sec_to_patch; - int relo_type; - - sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr; + Elf32_Addr relocation, location, tgt_addr; + unsigned int tgtsec; + + /* + * @relsec has relocations e.g. .rela.init.text + * @tgtsec is section to patch e.g. .init.text + */ + tgtsec = sechdrs[relsec].sh_info; + tgt_addr = sechdrs[tgtsec].sh_addr; sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr; n = sechdrs[relsec].sh_size / sizeof(*rel_entry); - pr_debug("\n========== Module Sym reloc ===========================\n"); - pr_debug("Section to fixup %x\n", sec_to_patch); + pr_debug("\nSection to fixup %s @%x\n", + module->arch.secstr + sechdrs[tgtsec].sh_name, tgt_addr); pr_debug("=========================================================\n"); - pr_debug("rela->r_off | rela->addend | sym->st_value | ADDR | VALUE\n"); + pr_debug("r_off\tr_add\tst_value ADDRESS VALUE\n"); pr_debug("=========================================================\n"); /* Loop thru entries in relocation section */ for (i = 0; i < n; i++) { + const char *s; /* This is where to make the change */ - location = sec_to_patch + rel_entry[i].r_offset; + location = tgt_addr + rel_entry[i].r_offset; /* This is the symbol it is referring to. Note that all undefined symbols have been resolved. */ @@ -89,10 +85,15 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, relocation = sym_entry->st_value + rel_entry[i].r_addend; - pr_debug("\t%x\t\t%x\t\t%x %x %x [%s]\n", - rel_entry[i].r_offset, rel_entry[i].r_addend, - sym_entry->st_value, location, relocation, - strtab + sym_entry->st_name); + if (sym_entry->st_name == 0 && ELF_ST_TYPE (sym_entry->st_info) == STT_SECTION) { + s = module->arch.secstr + sechdrs[sym_entry->st_shndx].sh_name; + } else { + s = strtab + sym_entry->st_name; + } + + pr_debug(" %x\t%x\t%x %x %x [%s]\n", + rel_entry[i].r_offset, rel_entry[i].r_addend, + sym_entry->st_value, location, relocation, s); /* This assumes modules are built with -mlong-calls * so any branches/jumps are absolute 32 bit jmps @@ -111,6 +112,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, goto relo_err; } + + if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0) + module->arch.unw_sec_idx = tgtsec; + return 0; relo_err: diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index be1972bd2729..a41a79a4f4fe 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -41,6 +41,41 @@ SYSCALL_DEFINE0(arc_gettls) return task_thread_info(current)->thr_ptr; } +SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) +{ + struct pt_regs *regs = current_pt_regs(); + int uval = -EFAULT; + + /* + * This is only for old cores lacking LLOCK/SCOND, which by defintion + * can't possibly be SMP. Thus doesn't need to be SMP safe. + * And this also helps reduce the overhead for serializing in + * the UP case + */ + WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP)); + + /* Z indicates to userspace if operation succeded */ + regs->status32 &= ~STATUS_Z_MASK; + + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + return -EFAULT; + + preempt_disable(); + + if (__get_user(uval, uaddr)) + goto done; + + if (uval == expected) { + if (!__put_user(new, uaddr)) + regs->status32 |= STATUS_Z_MASK; + } + +done: + preempt_enable(); + + return uval; +} + void arch_cpu_idle(void) { /* sleep, but enable all interrupts before committing */ diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 3df7f9c72f42..0385df77a697 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -40,6 +40,29 @@ struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; +static const struct id_to_str arc_cpu_rel[] = { +#ifdef CONFIG_ISA_ARCOMPACT + { 0x34, "R4.10"}, + { 0x35, "R4.11"}, +#else + { 0x51, "R2.0" }, + { 0x52, "R2.1" }, + { 0x53, "R3.0" }, +#endif + { 0x00, NULL } +}; + +static const struct id_to_str arc_cpu_nm[] = { +#ifdef CONFIG_ISA_ARCOMPACT + { 0x20, "ARC 600" }, + { 0x30, "ARC 770" }, /* 750 identified seperately */ +#else + { 0x40, "ARC EM" }, + { 0x50, "ARC HS38" }, +#endif + { 0x00, "Unknown" } +}; + static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu) { if (is_isa_arcompact()) { @@ -92,11 +115,26 @@ static void read_arc_build_cfg_regs(void) struct bcr_timer timer; struct bcr_generic bcr; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; + const struct id_to_str *tbl; + FIX_PTR(cpu); READ_BCR(AUX_IDENTITY, cpu->core); READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa); + for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) { + if (cpu->core.family == tbl->id) { + cpu->details = tbl->str; + break; + } + } + + for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) { + if ((cpu->core.family & 0xF0) == tbl->id) + break; + } + cpu->name = tbl->str; + READ_BCR(ARC_REG_TIMERS_BCR, timer); cpu->extn.timer0 = timer.t0; cpu->extn.timer1 = timer.t1; @@ -111,6 +149,9 @@ static void read_arc_build_cfg_regs(void) cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0; /* 1,3 */ cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0; cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */ + cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 : + IS_ENABLED(CONFIG_ARC_HAS_SWAPE); + READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem); /* Read CCM BCRs for boot reporting even if not enabled in Kconfig */ @@ -160,64 +201,38 @@ static void read_arc_build_cfg_regs(void) cpu->extn.rtt = bcr.ver ? 1 : 0; cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt; -} -static const struct cpuinfo_data arc_cpu_tbl[] = { -#ifdef CONFIG_ISA_ARCOMPACT - { {0x20, "ARC 600" }, 0x2F}, - { {0x30, "ARC 700" }, 0x33}, - { {0x34, "ARC 700 R4.10"}, 0x34}, - { {0x35, "ARC 700 R4.11"}, 0x35}, -#else - { {0x50, "ARC HS38 R2.0"}, 0x51}, - { {0x52, "ARC HS38 R2.1"}, 0x52}, - { {0x53, "ARC HS38 R3.0"}, 0x53}, -#endif - { {0x00, NULL } } -}; + /* some hacks for lack of feature BCR info in old ARC700 cores */ + if (is_isa_arcompact()) { + if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */ + cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); + else + cpu->isa.atomic = cpu->isa.atomic1; + cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + + /* there's no direct way to distinguish 750 vs. 770 */ + if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3)) + cpu->name = "ARC750"; + } +} static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; struct bcr_identity *core = &cpu->core; - const struct cpuinfo_data *tbl; - char *isa_nm; - int i, be, atomic; - int n = 0; + int i, n = 0; FIX_PTR(cpu); - if (is_isa_arcompact()) { - isa_nm = "ARCompact"; - be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); - - atomic = cpu->isa.atomic1; - if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */ - atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); - } else { - isa_nm = "ARCv2"; - be = cpu->isa.be; - atomic = cpu->isa.atomic; - } - n += scnprintf(buf + n, len - n, "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n", core->family, core->cpu_id, core->chip_id); - for (tbl = &arc_cpu_tbl[0]; tbl->info.id != 0; tbl++) { - if ((core->family >= tbl->info.id) && - (core->family <= tbl->up_range)) { - n += scnprintf(buf + n, len - n, - "processor [%d]\t: %s (%s ISA) %s\n", - cpu_id, tbl->info.str, isa_nm, - IS_AVAIL1(be, "[Big-Endian]")); - break; - } - } - - if (tbl->info.id == 0) - n += scnprintf(buf + n, len - n, "UNKNOWN ARC Processor\n"); + n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n", + cpu_id, cpu->name, cpu->details, + is_isa_arcompact() ? "ARCompact" : "ARCv2", + IS_AVAIL1(cpu->isa.be, "[Big-Endian]")); n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ", IS_AVAIL1(cpu->extn.timer0, "Timer0 "), @@ -226,7 +241,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) CONFIG_ARC_HAS_RTC)); n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s", - IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC), + IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC), IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64), IS_AVAIL1(cpu->isa.unalign, "unalign (not used)")); @@ -253,7 +268,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) IS_AVAIL1(cpu->extn.swap, "swap "), IS_AVAIL1(cpu->extn.minmax, "minmax "), IS_AVAIL1(cpu->extn.crc, "crc "), - IS_AVAIL2(1, "swape", CONFIG_ARC_HAS_SWAPE)); + IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE)); if (cpu->bpu.ver) n += scnprintf(buf + n, len - n, @@ -272,9 +287,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) FIX_PTR(cpu); - n += scnprintf(buf + n, len - n, - "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n", - cpu->vec_base, perip_base, perip_end); + n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\n", cpu->vec_base); if (cpu->extn.fpu_sp || cpu->extn.fpu_dp) n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n", @@ -507,7 +520,7 @@ static void *c_start(struct seq_file *m, loff_t *pos) * way to pass it w/o having to kmalloc/free a 2 byte string. * Encode cpu-id as 0xFFcccc, which is decoded by show routine. */ - return *pos < num_possible_cpus() ? cpu_to_ptr(*pos) : NULL; + return *pos < nr_cpu_ids ? cpu_to_ptr(*pos) : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index f183cc648851..88674d972c9d 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -22,6 +22,7 @@ #include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/reboot.h> +#include <linux/irqdomain.h> #include <asm/processor.h> #include <asm/setup.h> #include <asm/mach_desc.h> @@ -67,11 +68,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int i; /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. + * if platform didn't set the present map already, do it now + * boot cpu is set to present already by init/main.c */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); + if (num_present_cpus() <= 1) { + for (i = 0; i < max_cpus; i++) + set_cpu_present(i, true); + } } void __init smp_cpus_done(unsigned int max_cpus) @@ -351,20 +354,24 @@ irqreturn_t do_IPI(int irq, void *dev_id) */ static DEFINE_PER_CPU(int, ipi_dev); -int smp_ipi_irq_setup(int cpu, int irq) +int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq) { int *dev = per_cpu_ptr(&ipi_dev, cpu); + unsigned int virq = irq_find_mapping(NULL, hwirq); + + if (!virq) + panic("Cannot find virq for root domain and hwirq=%lu", hwirq); /* Boot cpu calls request, all call enable */ if (!cpu) { int rc; - rc = request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev); + rc = request_percpu_irq(virq, do_IPI, "IPI Interrupt", dev); if (rc) - panic("Percpu IRQ request failed for %d\n", irq); + panic("Percpu IRQ request failed for %u\n", virq); } - enable_percpu_irq(irq, 0); + enable_percpu_irq(virq, 0); return 0; } diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index f927b8dc6edd..c10390d1ddb6 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -152,14 +152,17 @@ static cycle_t arc_read_rtc(struct clocksource *cs) cycle_t full; } stamp; - - __asm__ __volatile( - "1: \n" - " lr %0, [AUX_RTC_LOW] \n" - " lr %1, [AUX_RTC_HIGH] \n" - " lr %2, [AUX_RTC_CTRL] \n" - " bbit0.nt %2, 31, 1b \n" - : "=r" (stamp.low), "=r" (stamp.high), "=r" (status)); + /* + * hardware has an internal state machine which tracks readout of + * low/high and updates the CTRL.status if + * - interrupt/exception taken between the two reads + * - high increments after low has been read + */ + do { + stamp.low = read_aux_reg(AUX_RTC_LOW); + stamp.high = read_aux_reg(AUX_RTC_HIGH); + status = read_aux_reg(AUX_RTC_CTRL); + } while (!(status & _BITUL(31))); return stamp.full; } diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 934150e7ac48..82f9bc819f4a 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -237,113 +237,3 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs, if (!user_mode(regs)) show_stacktrace(current, regs); } - -#ifdef CONFIG_DEBUG_FS - -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/mount.h> -#include <linux/pagemap.h> -#include <linux/init.h> -#include <linux/namei.h> -#include <linux/debugfs.h> - -static struct dentry *test_dentry; -static struct dentry *test_dir; -static struct dentry *test_u32_dentry; - -static u32 clr_on_read = 1; - -#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT -u32 numitlb, numdtlb, num_pte_not_present; - -static int fill_display_data(char *kbuf) -{ - size_t num = 0; - num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb); - num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb); - num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present); - - if (clr_on_read) - numitlb = numdtlb = num_pte_not_present = 0; - - return num; -} - -static int tlb_stats_open(struct inode *inode, struct file *file) -{ - file->private_data = (void *)__get_free_page(GFP_KERNEL); - return 0; -} - -/* called on user read(): display the counters */ -static ssize_t tlb_stats_output(struct file *file, /* file descriptor */ - char __user *user_buf, /* user buffer */ - size_t len, /* length of buffer */ - loff_t *offset) /* offset in the file */ -{ - size_t num; - char *kbuf = (char *)file->private_data; - - /* All of the data can he shoved in one iteration */ - if (*offset != 0) - return 0; - - num = fill_display_data(kbuf); - - /* simple_read_from_buffer() is helper for copy to user space - It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset - @3 (offset) into the user space address starting at @1 (user_buf). - @5 (len) is max size of user buffer - */ - return simple_read_from_buffer(user_buf, num, offset, kbuf, len); -} - -/* called on user write : clears the counters */ -static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf, - size_t length, loff_t *offset) -{ - numitlb = numdtlb = num_pte_not_present = 0; - return length; -} - -static int tlb_stats_close(struct inode *inode, struct file *file) -{ - free_page((unsigned long)(file->private_data)); - return 0; -} - -static const struct file_operations tlb_stats_file_ops = { - .read = tlb_stats_output, - .write = tlb_stats_clear, - .open = tlb_stats_open, - .release = tlb_stats_close -}; -#endif - -static int __init arc_debugfs_init(void) -{ - test_dir = debugfs_create_dir("arc", NULL); - -#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT - test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL, - &tlb_stats_file_ops); -#endif - - test_u32_dentry = - debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read); - - return 0; -} - -module_init(arc_debugfs_init); - -static void __exit arc_debugfs_exit(void) -{ - debugfs_remove(test_u32_dentry); - debugfs_remove(test_dentry); - debugfs_remove(test_dir); -} -module_exit(arc_debugfs_exit); - -#endif diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 97dddbefb86a..2b96cfc3be75 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -22,8 +22,8 @@ #include <asm/setup.h> static int l2_line_sz; -int ioc_exists; -volatile int slc_enable = 1, ioc_enable = 1; +static int ioc_exists; +int slc_enable = 1, ioc_enable = 1; unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */ unsigned long perip_end = 0xFFFFFFFF; /* legacy value */ @@ -53,18 +53,15 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache"); PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache"); - if (!is_isa_arcv2()) - return buf; - p = &cpuinfo_arc700[c].slc; if (p->ver) n += scnprintf(buf + n, len - n, "SLC\t\t: %uK, %uB Line%s\n", p->sz_k, p->line_len, IS_USED_RUN(slc_enable)); - if (ioc_exists) - n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n", - IS_DISABLED_RUN(ioc_enable)); + n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n", + perip_base, + IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency ")); return buf; } @@ -113,8 +110,10 @@ static void read_decode_cache_bcr_arcv2(int cpu) } READ_BCR(ARC_REG_CLUSTER_BCR, cbcr); - if (cbcr.c && ioc_enable) + if (cbcr.c) ioc_exists = 1; + else + ioc_enable = 0; /* HS 2.0 didn't have AUX_VOL */ if (cpuinfo_arc700[cpu].core.family > 0x51) { @@ -1002,7 +1001,7 @@ void arc_cache_init(void) read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE); } - if (is_isa_arcv2() && ioc_exists) { + if (is_isa_arcv2() && ioc_enable) { /* IO coherency base - 0x8z */ write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000); /* IO coherency aperture size - 512Mb: 0x8z-0xAz */ diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 20afc65e22dc..cd8aad8226dd 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -45,7 +45,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size, * -For coherent data, Read/Write to buffers terminate early in cache * (vs. always going to memory - thus are faster) */ - if ((is_isa_arcv2() && ioc_exists) || + if ((is_isa_arcv2() && ioc_enable) || (attrs & DMA_ATTR_NON_CONSISTENT)) need_coh = 0; @@ -97,7 +97,7 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr, int is_non_coh = 1; is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) || - (is_isa_arcv2() && ioc_exists); + (is_isa_arcv2() && ioc_enable); if (PageHighMem(page) || !is_non_coh) iounmap((void __force __iomem *)vaddr); @@ -105,6 +105,31 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr, __free_pages(page, get_order(size)); } +static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long pfn = __phys_to_pfn(plat_dma_to_phys(dev, dma_addr)); + unsigned long off = vma->vm_pgoff; + int ret = -ENXIO; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + if (off < count && user_count <= (count - off)) { + ret = remap_pfn_range(vma, vma->vm_start, + pfn + off, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + + return ret; +} + /* * streaming DMA Mapping API... * CPU accesses page via normal paddr, thus needs to explicitly made @@ -193,6 +218,7 @@ static int arc_dma_supported(struct device *dev, u64 dma_mask) struct dma_map_ops arc_dma_ops = { .alloc = arc_dma_alloc, .free = arc_dma_free, + .mmap = arc_dma_mmap, .map_page = arc_dma_map_page, .map_sg = arc_dma_map_sg, .sync_single_for_device = arc_dma_sync_single_for_device, diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index ec868a9081a1..bdb295e09160 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -793,16 +793,16 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len) char super_pg[64] = ""; if (p_mmu->s_pg_sz_m) - scnprintf(super_pg, 64, "%dM Super Page%s, ", + scnprintf(super_pg, 64, "%dM Super Page %s", p_mmu->s_pg_sz_m, IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE)); n += scnprintf(buf + n, len - n, - "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s%s\n", + "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n", p_mmu->ver, p_mmu->pg_sz_k, super_pg, p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways, p_mmu->u_dtlb, p_mmu->u_itlb, - IS_AVAIL2(p_mmu->pae, "PAE40 ", CONFIG_ARC_HAS_PAE40)); + IS_AVAIL2(p_mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40)); return buf; } diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index f1967eeb32e7..b30e4e36bb00 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -237,15 +237,6 @@ ex_saved_reg1: 2: -#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT - and.f 0, r0, _PAGE_PRESENT - bz 1f - ld r3, [num_pte_not_present] - add r3, r3, 1 - st r3, [num_pte_not_present] -1: -#endif - .endm ;----------------------------------------------------------------- @@ -309,12 +300,6 @@ ENTRY(EV_TLBMissI) TLBMISS_FREEUP_REGS -#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT - ld r0, [@numitlb] - add r0, r0, 1 - st r0, [@numitlb] -#endif - ;---------------------------------------------------------------- ; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA LOAD_FAULT_PTE @@ -349,12 +334,6 @@ ENTRY(EV_TLBMissD) TLBMISS_FREEUP_REGS -#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT - ld r0, [@numdtlb] - add r0, r0, 1 - st r0, [@numdtlb] -#endif - ;---------------------------------------------------------------- ; Get the PTE corresponding to V-addr accessed ; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA diff --git a/arch/arc/plat-eznps/smp.c b/arch/arc/plat-eznps/smp.c index 5e901f86e4bd..56a4c8522f11 100644 --- a/arch/arc/plat-eznps/smp.c +++ b/arch/arc/plat-eznps/smp.c @@ -140,16 +140,10 @@ static void eznps_init_per_cpu(int cpu) mtm_enable_core(cpu); } -static void eznps_ipi_clear(int irq) -{ - write_aux_reg(CTOP_AUX_IACK, 1 << irq); -} - struct plat_smp_ops plat_smp_ops = { .info = smp_cpuinfo_buf, .init_early_smp = eznps_init_cpumasks, .cpu_kick = eznps_smp_wakeup_cpu, .ipi_send = eznps_ipi_send, .init_per_cpu = eznps_init_per_cpu, - .ipi_clear = eznps_ipi_clear, }; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index b3df1c60d465..386eee6de232 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -239,14 +239,25 @@ arm,primecell-periphid = <0x10480180>; max-frequency = <100000000>; bus-width = <4>; + cap-sd-highspeed; cap-mmc-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + /* All direction control is used */ + st,sig-dir-cmd; + st,sig-dir-dat0; + st,sig-dir-dat2; + st,sig-dir-dat31; + st,sig-pin-fbclk; + full-pwr-cycle; vmmc-supply = <&ab8500_ldo_aux3_reg>; vqmmc-supply = <&vmmci>; pinctrl-names = "default", "sleep"; pinctrl-0 = <&sdi0_default_mode>; pinctrl-1 = <&sdi0_sleep_mode>; - cd-gpios = <&gpio6 26 GPIO_ACTIVE_LOW>; // 218 + /* GPIO218 MMC_CD */ + cd-gpios = <&gpio6 26 GPIO_ACTIVE_LOW>; status = "okay"; }; @@ -549,7 +560,7 @@ /* VMMCI level-shifter enable */ snowball_cfg3 { pins = "GPIO217_AH12"; - ste,config = <&gpio_out_lo>; + ste,config = <&gpio_out_hi>; }; /* VMMCI level-shifter voltage select */ snowball_cfg4 { diff --git a/arch/arm/boot/dts/uniphier-pro5.dtsi b/arch/arm/boot/dts/uniphier-pro5.dtsi index 2c49c3614bda..5357ea9c14b1 100644 --- a/arch/arm/boot/dts/uniphier-pro5.dtsi +++ b/arch/arm/boot/dts/uniphier-pro5.dtsi @@ -184,11 +184,11 @@ }; &mio_clk { - compatible = "socionext,uniphier-pro5-mio-clock"; + compatible = "socionext,uniphier-pro5-sd-clock"; }; &mio_rst { - compatible = "socionext,uniphier-pro5-mio-reset"; + compatible = "socionext,uniphier-pro5-sd-reset"; }; &peri_clk { diff --git a/arch/arm/boot/dts/uniphier-pxs2.dtsi b/arch/arm/boot/dts/uniphier-pxs2.dtsi index 8789cd518933..950f07ba0337 100644 --- a/arch/arm/boot/dts/uniphier-pxs2.dtsi +++ b/arch/arm/boot/dts/uniphier-pxs2.dtsi @@ -197,11 +197,11 @@ }; &mio_clk { - compatible = "socionext,uniphier-pxs2-mio-clock"; + compatible = "socionext,uniphier-pxs2-sd-clock"; }; &mio_rst { - compatible = "socionext,uniphier-pxs2-mio-reset"; + compatible = "socionext,uniphier-pxs2-sd-reset"; }; &peri_clk { diff --git a/arch/arm/boot/dts/vf500.dtsi b/arch/arm/boot/dts/vf500.dtsi index a3824e61bd72..d7fdb2a7d97b 100644 --- a/arch/arm/boot/dts/vf500.dtsi +++ b/arch/arm/boot/dts/vf500.dtsi @@ -70,7 +70,7 @@ global_timer: timer@40002200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x40002200 0x20>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; interrupt-parent = <&intc>; clocks = <&clks VF610_CLK_PLATFORM_BUS>; }; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 437d0740dec6..11f37ed1dbff 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -850,6 +850,7 @@ CONFIG_PWM_SUN4I=y CONFIG_PWM_TEGRA=y CONFIG_PWM_VT8500=y CONFIG_PHY_HIX5HD2_SATA=y +CONFIG_E1000E=y CONFIG_PWM_STI=y CONFIG_PWM_BCM2835=y CONFIG_PWM_BRCMSTB=m diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index d7ea6bcb29bf..8ef05381984b 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -66,6 +66,7 @@ extern char __kvm_hyp_vector[]; extern void __kvm_flush_vm_context(void); extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); extern void __kvm_tlb_flush_vmid(struct kvm *kvm); +extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 2d19e02d03fd..d5423ab15ed5 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -57,6 +57,9 @@ struct kvm_arch { /* VTTBR value associated with below pgd and vmid */ u64 vttbr; + /* The last vcpu id that ran on each physical CPU */ + int __percpu *last_vcpu_ran; + /* Timer */ struct arch_timer_kvm timer; diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h index 343135ede5fa..58508900c4bb 100644 --- a/arch/arm/include/asm/kvm_hyp.h +++ b/arch/arm/include/asm/kvm_hyp.h @@ -71,6 +71,7 @@ #define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0) #define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0) #define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0) +#define TLBIALL __ACCESS_CP15(c8, 0, c7, 0) #define TLBIALLNSNHIS __ACCESS_CP15(c8, 4, c3, 4) #define PRRR __ACCESS_CP15(c10, 0, c2, 0) #define NMRR __ACCESS_CP15(c10, 0, c2, 1) diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 194b69923389..ada0d29a660f 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -19,7 +19,7 @@ * This may need to be greater than __NR_last_syscall+1 in order to * account for the padding in the syscall table */ -#define __NR_syscalls (396) +#define __NR_syscalls (400) #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_GETHOSTNAME diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index 2cb9dc770e1d..314100a06ccb 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -420,6 +420,9 @@ #define __NR_copy_file_range (__NR_SYSCALL_BASE+391) #define __NR_preadv2 (__NR_SYSCALL_BASE+392) #define __NR_pwritev2 (__NR_SYSCALL_BASE+393) +#define __NR_pkey_mprotect (__NR_SYSCALL_BASE+394) +#define __NR_pkey_alloc (__NR_SYSCALL_BASE+395) +#define __NR_pkey_free (__NR_SYSCALL_BASE+396) /* * The following SWIs are ARM private. diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 703fa0f3cd8f..08030b18f10a 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -403,6 +403,9 @@ CALL(sys_copy_file_range) CALL(sys_preadv2) CALL(sys_pwritev2) + CALL(sys_pkey_mprotect) +/* 395 */ CALL(sys_pkey_alloc) + CALL(sys_pkey_free) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 08bb84f2ad58..19b5f5c1c0ff 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -114,11 +114,18 @@ void kvm_arch_check_processor_compat(void *rtn) */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - int ret = 0; + int ret, cpu; if (type) return -EINVAL; + kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran)); + if (!kvm->arch.last_vcpu_ran) + return -ENOMEM; + + for_each_possible_cpu(cpu) + *per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1; + ret = kvm_alloc_stage2_pgd(kvm); if (ret) goto out_fail_alloc; @@ -141,6 +148,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) out_free_stage2_pgd: kvm_free_stage2_pgd(kvm); out_fail_alloc: + free_percpu(kvm->arch.last_vcpu_ran); + kvm->arch.last_vcpu_ran = NULL; return ret; } @@ -168,6 +177,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) { int i; + free_percpu(kvm->arch.last_vcpu_ran); + kvm->arch.last_vcpu_ran = NULL; + for (i = 0; i < KVM_MAX_VCPUS; ++i) { if (kvm->vcpus[i]) { kvm_arch_vcpu_free(kvm->vcpus[i]); @@ -312,6 +324,19 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + int *last_ran; + + last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran); + + /* + * We might get preempted before the vCPU actually runs, but + * over-invalidation doesn't affect correctness. + */ + if (*last_ran != vcpu->vcpu_id) { + kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu); + *last_ran = vcpu->vcpu_id; + } + vcpu->cpu = cpu; vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state); diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c index 729652854f90..6d810af2d9fd 100644 --- a/arch/arm/kvm/hyp/tlb.c +++ b/arch/arm/kvm/hyp/tlb.c @@ -55,6 +55,21 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) __kvm_tlb_flush_vmid(kvm); } +void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); + + /* Switch to requested VMID */ + write_sysreg(kvm->arch.vttbr, VTTBR); + isb(); + + write_sysreg(0, TLBIALL); + dsb(nsh); + isb(); + + write_sysreg(0, VTTBR); +} + void __hyp_text __kvm_flush_vm_context(void) { write_sysreg(0, TLBIALLNSNHIS); diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index 0df062d8b2c9..b54db47f6f32 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -408,7 +408,7 @@ static struct genpd_onecell_data imx_gpc_onecell_data = { static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg) { struct clk *clk; - int i; + int i, ret; imx6q_pu_domain.reg = pu_reg; @@ -430,13 +430,22 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg) if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) return 0; - pm_genpd_init(&imx6q_pu_domain.base, NULL, false); - return of_genpd_add_provider_onecell(dev->of_node, + for (i = 0; i < ARRAY_SIZE(imx_gpc_domains); i++) + pm_genpd_init(imx_gpc_domains[i], NULL, false); + + ret = of_genpd_add_provider_onecell(dev->of_node, &imx_gpc_onecell_data); + if (ret) + goto power_off; + + return 0; +power_off: + imx6q_pm_pu_power_off(&imx6q_pu_domain.base); clk_err: while (i--) clk_put(imx6q_pu_domain.clk[i]); + imx6q_pu_domain.reg = NULL; return -EINVAL; } diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 97fd25105e2c..45801b27ee5c 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -173,7 +173,7 @@ static void __init imx6q_enet_phy_init(void) ksz9021rn_phy_fixup); phy_register_fixup_for_uid(PHY_ID_KSZ9031, MICREL_PHY_ID_MASK, ksz9031rn_phy_fixup); - phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffff, + phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffef, ar8031_phy_fixup); phy_register_fixup_for_uid(PHY_ID_AR8035, 0xffffffef, ar8035_phy_fixup); diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index f9b6bd306cfe..541647f57192 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -23,6 +23,7 @@ config MACH_MVEBU_V7 select CACHE_L2X0 select ARM_CPU_SUSPEND select MACH_MVEBU_ANY + select MVEBU_CLK_COREDIV config MACH_ARMADA_370 bool "Marvell Armada 370 boards" @@ -32,7 +33,6 @@ config MACH_ARMADA_370 select CPU_PJ4B select MACH_MVEBU_V7 select PINCTRL_ARMADA_370 - select MVEBU_CLK_COREDIV help Say 'Y' here if you want your kernel to support boards based on the Marvell Armada 370 SoC with device tree. @@ -50,7 +50,6 @@ config MACH_ARMADA_375 select HAVE_SMP select MACH_MVEBU_V7 select PINCTRL_ARMADA_375 - select MVEBU_CLK_COREDIV help Say 'Y' here if you want your kernel to support boards based on the Marvell Armada 375 SoC with device tree. @@ -68,7 +67,6 @@ config MACH_ARMADA_38X select HAVE_SMP select MACH_MVEBU_V7 select PINCTRL_ARMADA_38X - select MVEBU_CLK_COREDIV help Say 'Y' here if you want your kernel to support boards based on the Marvell Armada 380/385 SoC with device tree. diff --git a/arch/arm/mach-uniphier/Kconfig b/arch/arm/mach-uniphier/Kconfig index 82dddee3a469..3930fbba30b4 100644 --- a/arch/arm/mach-uniphier/Kconfig +++ b/arch/arm/mach-uniphier/Kconfig @@ -1,6 +1,7 @@ config ARCH_UNIPHIER bool "Socionext UniPhier SoCs" depends on ARCH_MULTI_V7 + select ARCH_HAS_RESET_CONTROLLER select ARM_AMBA select ARM_GLOBAL_TIMER select ARM_GIC diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index 6d8e8e3365d1..4cdfab31a0b6 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -7,7 +7,7 @@ * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r4-r5, r10-r11, r13 preserved + * Returns : r4-r5, r9-r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -48,7 +48,10 @@ ENTRY(v4t_late_abort) /* c */ b do_DataAbort @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m /* d */ b do_DataAbort @ ldc rd, [rn, #m] /* e */ b .data_unknown -/* f */ +/* f */ b .data_unknown + +.data_unknown_r9: + ldr r9, [sp], #4 .data_unknown: @ Part of jumptable mov r0, r4 mov r1, r8 @@ -57,6 +60,7 @@ ENTRY(v4t_late_abort) .data_arm_ldmstm: tst r8, #1 << 21 @ check writeback bit beq do_DataAbort @ no writeback -> no fixup + str r9, [sp, #-4]! mov r7, #0x11 orr r7, r7, #0x1100 and r6, r8, r7 @@ -75,12 +79,14 @@ ENTRY(v4t_late_abort) subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement str r7, [r2, r9, lsr #14] @ Put register 'Rn' + ldr r9, [sp], #4 b do_DataAbort .data_arm_lateldrhpre: tst r8, #1 << 21 @ Check writeback bit beq do_DataAbort @ No writeback -> no fixup .data_arm_lateldrhpost: + str r9, [sp, #-4]! and r9, r8, #0x00f @ get Rm / low nibble of immediate value tst r8, #1 << 22 @ if (immediate offset) andne r6, r8, #0xf00 @ { immediate high nibble @@ -93,6 +99,7 @@ ENTRY(v4t_late_abort) subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement str r7, [r2, r9, lsr #14] @ Put register 'Rn' + ldr r9, [sp], #4 b do_DataAbort .data_arm_lateldrpreconst: @@ -101,12 +108,14 @@ ENTRY(v4t_late_abort) .data_arm_lateldrpostconst: movs r6, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup + str r9, [sp, #-4]! and r9, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsr #20 @ Undo increment addeq r7, r7, r6, lsr #20 @ Undo decrement str r7, [r2, r9, lsr #14] @ Put register 'Rn' + ldr r9, [sp], #4 b do_DataAbort .data_arm_lateldrprereg: @@ -115,6 +124,7 @@ ENTRY(v4t_late_abort) .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction ldr r6, [r2, r7, lsl #2] @ Get register 'Rm' + str r9, [sp, #-4]! mov r9, r8, lsr #7 @ get shift count ands r9, r9, #31 and r7, r8, #0x70 @ get shift type @@ -126,33 +136,33 @@ ENTRY(v4t_late_abort) b .data_arm_apply_r6_and_rn b .data_arm_apply_r6_and_rn @ 1: LSL #0 nop - b .data_unknown @ 2: MUL? + b .data_unknown_r9 @ 2: MUL? nop - b .data_unknown @ 3: MUL? + b .data_unknown_r9 @ 3: MUL? nop mov r6, r6, lsr r9 @ 4: LSR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, lsr #32 @ 5: LSR #32 b .data_arm_apply_r6_and_rn - b .data_unknown @ 6: MUL? + b .data_unknown_r9 @ 6: MUL? nop - b .data_unknown @ 7: MUL? + b .data_unknown_r9 @ 7: MUL? nop mov r6, r6, asr r9 @ 8: ASR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, asr #32 @ 9: ASR #32 b .data_arm_apply_r6_and_rn - b .data_unknown @ A: MUL? + b .data_unknown_r9 @ A: MUL? nop - b .data_unknown @ B: MUL? + b .data_unknown_r9 @ B: MUL? nop mov r6, r6, ror r9 @ C: ROR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, rrx @ D: RRX b .data_arm_apply_r6_and_rn - b .data_unknown @ E: MUL? + b .data_unknown_r9 @ E: MUL? nop - b .data_unknown @ F: MUL? + b .data_unknown_r9 @ F: MUL? .data_thumb_abort: ldrh r8, [r4] @ read instruction @@ -190,6 +200,7 @@ ENTRY(v4t_late_abort) .data_thumb_pushpop: tst r8, #1 << 10 beq .data_unknown + str r9, [sp, #-4]! and r6, r8, #0x55 @ hweight8(r8) + R bit and r9, r8, #0xaa add r6, r6, r9, lsr #1 @@ -204,9 +215,11 @@ ENTRY(v4t_late_abort) addeq r7, r7, r6, lsl #2 @ increment SP if PUSH subne r7, r7, r6, lsl #2 @ decrement SP if POP str r7, [r2, #13 << 2] + ldr r9, [sp], #4 b do_DataAbort .data_thumb_ldmstm: + str r9, [sp, #-4]! and r6, r8, #0x55 @ hweight8(r8) and r9, r8, #0xaa add r6, r6, r9, lsr #1 @@ -219,4 +232,5 @@ ENTRY(v4t_late_abort) and r6, r6, #15 @ number of regs to transfer sub r7, r7, r6, lsl #2 @ always decrement str r7, [r2, r9, lsr #6] + ldr r9, [sp], #4 b do_DataAbort diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index cfbdf02ef566..101794f5ce10 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -190,6 +190,7 @@ config ARCH_THUNDER config ARCH_UNIPHIER bool "Socionext UniPhier SoC Family" + select ARCH_HAS_RESET_CONTROLLER select PINCTRL help This enables support for Socionext UniPhier SoC family. diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts index 2d7872a36b91..b09f3bc5c6c1 100644 --- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts +++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts @@ -164,6 +164,8 @@ nand-ecc-mode = "hw"; nand-ecc-strength = <8>; nand-ecc-step-size = <512>; + nand-bus-width = <16>; + brcm,nand-oob-sector-size = <16>; #address-cells = <1>; #size-cells = <1>; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index 220ac7057d12..97d331ec2500 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -123,6 +123,7 @@ <1 14 0xf08>, /* Physical Non-Secure PPI */ <1 11 0xf08>, /* Virtual PPI */ <1 10 0xf08>; /* Hypervisor PPI */ + fsl,erratum-a008585; }; pmu { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi index 337da90bd7da..7f0dc13b4087 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi @@ -195,6 +195,7 @@ <1 14 4>, /* Physical Non-Secure PPI, active-low */ <1 11 4>, /* Virtual PPI, active-low */ <1 10 4>; /* Hypervisor PPI, active-low */ + fsl,erratum-a008585; }; pmu { diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi index e5e3ed678b6f..602e2c2e9a4d 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi @@ -131,7 +131,7 @@ #address-cells = <0x1>; #size-cells = <0x0>; cell-index = <1>; - clocks = <&cpm_syscon0 0 3>; + clocks = <&cpm_syscon0 1 21>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts index 46cdddfcea6c..e5eeca2c2456 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts +++ b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts @@ -116,7 +116,6 @@ cap-mmc-highspeed; clock-frequency = <150000000>; disable-wp; - keep-power-in-suspend; non-removable; num-slots = <1>; vmmc-supply = <&vcc_io>; @@ -258,8 +257,6 @@ }; vcc_sd: SWITCH_REG1 { - regulator-always-on; - regulator-boot-on; regulator-name = "vcc_sd"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts index 5797933ef80e..ea0a8eceefd4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts +++ b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts @@ -152,8 +152,6 @@ gpio = <&gpio3 11 GPIO_ACTIVE_LOW>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; - regulator-always-on; - regulator-boot-on; vin-supply = <&vcc_io>; }; @@ -201,7 +199,6 @@ bus-width = <8>; cap-mmc-highspeed; disable-wp; - keep-power-in-suspend; mmc-pwrseq = <&emmc_pwrseq>; mmc-hs200-1_2v; mmc-hs200-1_8v; @@ -350,7 +347,6 @@ clock-freq-min-max = <400000 50000000>; cap-sd-highspeed; card-detect-delay = <200>; - keep-power-in-suspend; num-slots = <1>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index b65c193dc64e..7afbfb0f96a3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -300,8 +300,11 @@ ranges = <0x83000000 0x0 0xfa000000 0x0 0xfa000000 0x0 0x600000 0x81000000 0x0 0xfa600000 0x0 0xfa600000 0x0 0x100000>; resets = <&cru SRST_PCIE_CORE>, <&cru SRST_PCIE_MGMT>, - <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>; - reset-names = "core", "mgmt", "mgmt-sticky", "pipe"; + <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>, + <&cru SRST_PCIE_PM>, <&cru SRST_P_PCIE>, + <&cru SRST_A_PCIE>; + reset-names = "core", "mgmt", "mgmt-sticky", "pipe", + "pm", "pclk", "aclk"; status = "disabled"; pcie0_intc: interrupt-controller { diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi index 08fd7cf7769c..56a1b2e92cf3 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi +++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi @@ -257,18 +257,18 @@ reg = <0x59801000 0x400>; }; - mioctrl@59810000 { - compatible = "socionext,uniphier-mioctrl", + sdctrl@59810000 { + compatible = "socionext,uniphier-ld20-sdctrl", "simple-mfd", "syscon"; reg = <0x59810000 0x800>; - mio_clk: clock { - compatible = "socionext,uniphier-ld20-mio-clock"; + sd_clk: clock { + compatible = "socionext,uniphier-ld20-sd-clock"; #clock-cells = <1>; }; - mio_rst: reset { - compatible = "socionext,uniphier-ld20-mio-reset"; + sd_rst: reset { + compatible = "socionext,uniphier-ld20-sd-reset"; #reset-cells = <1>; }; }; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 39feb85a6931..6e1cb8c5af4d 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -1,7 +1,7 @@ #ifndef __ASM_ALTERNATIVE_H #define __ASM_ALTERNATIVE_H -#include <asm/cpufeature.h> +#include <asm/cpucaps.h> #include <asm/insn.h> #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h new file mode 100644 index 000000000000..87b446535185 --- /dev/null +++ b/arch/arm64/include/asm/cpucaps.h @@ -0,0 +1,40 @@ +/* + * arch/arm64/include/asm/cpucaps.h + * + * Copyright (C) 2016 ARM Ltd. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __ASM_CPUCAPS_H +#define __ASM_CPUCAPS_H + +#define ARM64_WORKAROUND_CLEAN_CACHE 0 +#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 +#define ARM64_WORKAROUND_845719 2 +#define ARM64_HAS_SYSREG_GIC_CPUIF 3 +#define ARM64_HAS_PAN 4 +#define ARM64_HAS_LSE_ATOMICS 5 +#define ARM64_WORKAROUND_CAVIUM_23154 6 +#define ARM64_WORKAROUND_834220 7 +#define ARM64_HAS_NO_HW_PREFETCH 8 +#define ARM64_HAS_UAO 9 +#define ARM64_ALT_PAN_NOT_UAO 10 +#define ARM64_HAS_VIRT_HOST_EXTN 11 +#define ARM64_WORKAROUND_CAVIUM_27456 12 +#define ARM64_HAS_32BIT_EL0 13 +#define ARM64_HYP_OFFSET_LOW 14 +#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15 + +#define ARM64_NCAPS 16 + +#endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index a27c3245ba21..0bc0b1de90c4 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -11,6 +11,7 @@ #include <linux/jump_label.h> +#include <asm/cpucaps.h> #include <asm/hwcap.h> #include <asm/sysreg.h> @@ -24,25 +25,6 @@ #define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap)) #define cpu_feature(x) ilog2(HWCAP_ ## x) -#define ARM64_WORKAROUND_CLEAN_CACHE 0 -#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 -#define ARM64_WORKAROUND_845719 2 -#define ARM64_HAS_SYSREG_GIC_CPUIF 3 -#define ARM64_HAS_PAN 4 -#define ARM64_HAS_LSE_ATOMICS 5 -#define ARM64_WORKAROUND_CAVIUM_23154 6 -#define ARM64_WORKAROUND_834220 7 -#define ARM64_HAS_NO_HW_PREFETCH 8 -#define ARM64_HAS_UAO 9 -#define ARM64_ALT_PAN_NOT_UAO 10 -#define ARM64_HAS_VIRT_HOST_EXTN 11 -#define ARM64_WORKAROUND_CAVIUM_27456 12 -#define ARM64_HAS_32BIT_EL0 13 -#define ARM64_HYP_OFFSET_LOW 14 -#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15 - -#define ARM64_NCAPS 16 - #ifndef __ASSEMBLY__ #include <linux/kernel.h> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 18f746551bf6..ec3553eb9349 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -54,6 +54,7 @@ extern char __kvm_hyp_vector[]; extern void __kvm_flush_vm_context(void); extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); extern void __kvm_tlb_flush_vmid(struct kvm *kvm); +extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bd94e6766759..e5050388e062 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -62,6 +62,9 @@ struct kvm_arch { /* VTTBR value associated with above pgd and vmid */ u64 vttbr; + /* The last vcpu id that ran on each physical CPU */ + int __percpu *last_vcpu_ran; + /* The maximum number of vCPUs depends on the used GIC model */ int max_vcpus; diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index a79b969c26fc..6f72fe8b0e3e 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -128,7 +128,7 @@ static inline unsigned long __kern_hyp_va(unsigned long v) return v; } -#define kern_hyp_va(v) (typeof(v))(__kern_hyp_va((unsigned long)(v))) +#define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) /* * We currently only support a 40bit IPA. diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index 23acc00be32d..fc756e22c84c 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -5,7 +5,6 @@ #include <linux/stringify.h> #include <asm/alternative.h> -#include <asm/cpufeature.h> #ifdef __ASSEMBLER__ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index ba62df8c6e35..b71086d25195 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -217,7 +217,7 @@ static inline void *phys_to_virt(phys_addr_t x) #define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) #else #define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page)) -#define __page_to_voff(kaddr) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page)) +#define __page_to_voff(page) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page)) #define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET)) #define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START)) diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 9cc0ea784ae6..88e2f2b938f0 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -64,6 +64,21 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) write_sysreg(0, vttbr_el2); } +void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); + + /* Switch to requested VMID */ + write_sysreg(kvm->arch.vttbr, vttbr_el2); + isb(); + + asm volatile("tlbi vmalle1" : : ); + dsb(nsh); + isb(); + + write_sysreg(0, vttbr_el2); +} + void __hyp_text __kvm_flush_vm_context(void) { dsb(ishst); diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 778a985c8a70..4b32168cf91a 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -147,7 +147,7 @@ static int __init early_cpu_to_node(int cpu) static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) { - return node_distance(from, to); + return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, @@ -223,8 +223,11 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) void *nd; int tnid; - pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", - nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); + if (start_pfn < end_pfn) + pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid, + start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); + else + pr_info("Initmem setup node %d [<memory-less node>]\n", nid); nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); nd = __va(nd_pa); diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c index 099e170a93ee..0068fd411a84 100644 --- a/arch/cris/arch-v32/drivers/cryptocop.c +++ b/arch/cris/arch-v32/drivers/cryptocop.c @@ -3149,7 +3149,7 @@ static void print_dma_descriptors(struct cryptocop_int_operation *iop) printk("print_dma_descriptors start\n"); printk("iop:\n"); - printk("\tsid: 0x%lld\n", iop->sid); + printk("\tsid: 0x%llx\n", iop->sid); printk("\tcdesc_out: 0x%p\n", iop->cdesc_out); printk("\tcdesc_in: 0x%p\n", iop->cdesc_in); diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h index b408fe660cf8..3cef06875f5c 100644 --- a/arch/h8300/include/asm/thread_info.h +++ b/arch/h8300/include/asm/thread_info.h @@ -31,7 +31,6 @@ struct thread_info { int cpu; /* cpu we're on */ int preempt_count; /* 0 => preemptable, <0 => BUG */ mm_segment_t addr_limit; - struct restart_block restart_block; }; /* @@ -44,9 +43,6 @@ struct thread_info { .cpu = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ - .restart_block = { \ - .fn = do_no_restart_syscall, \ - }, \ } #define init_thread_info (init_thread_union.thread_info) diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index ad1f81f574e5..7138303cbbf2 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -79,7 +79,7 @@ restore_sigcontext(struct sigcontext *usc, int *pd0) unsigned int er0; /* Always make any pending restarted system calls return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; + current->restart_block.fn = do_no_restart_syscall; /* restore passed registers */ #define COPY(r) do { err |= get_user(regs->r, &usc->sc_##r); } while (0) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index fbf40d3c8123..1a6bac7b076f 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -263,7 +263,7 @@ KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0) bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) \ VMLINUX_ENTRY_ADDRESS=$(entry-y) \ - PLATFORM=$(platform-y) + PLATFORM="$(platform-y)" ifdef CONFIG_32BIT bootvars-y += ADDR_BITS=32 endif diff --git a/arch/mips/boot/dts/mti/malta.dts b/arch/mips/boot/dts/mti/malta.dts index f604a272d91d..ffe3a1508e72 100644 --- a/arch/mips/boot/dts/mti/malta.dts +++ b/arch/mips/boot/dts/mti/malta.dts @@ -84,12 +84,13 @@ fpga_regs: system-controller@1f000000 { compatible = "mti,malta-fpga", "syscon", "simple-mfd"; reg = <0x1f000000 0x1000>; + native-endian; reboot { compatible = "syscon-reboot"; regmap = <&fpga_regs>; offset = <0x500>; - mask = <0x4d>; + mask = <0x42>; }; }; diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 0ea73e845440..d493ccbf274a 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -30,9 +30,19 @@ static __initdata const void *mach_match_data; void __init prom_init(void) { + plat_get_fdt(); + BUG_ON(!fdt); +} + +void __init *plat_get_fdt(void) +{ const struct mips_machine *check_mach; const struct of_device_id *match; + if (fdt) + /* Already set up */ + return (void *)fdt; + if ((fw_arg0 == -2) && !fdt_check_header((void *)fw_arg1)) { /* * We booted using the UHI boot protocol, so we have been @@ -75,12 +85,6 @@ void __init prom_init(void) /* Retrieve the machine's FDT */ fdt = mach->fdt; } - - BUG_ON(!fdt); -} - -void __init *plat_get_fdt(void) -{ return (void *)fdt; } diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h index 355dc25172e7..c05369e0b8d6 100644 --- a/arch/mips/include/asm/fpu_emulator.h +++ b/arch/mips/include/asm/fpu_emulator.h @@ -63,6 +63,8 @@ do { \ extern int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr); +void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr, + struct task_struct *tsk); 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, @@ -81,4 +83,15 @@ static inline void fpu_emulator_init_fpu(void) set_fpr64(&t->thread.fpu.fpr[i], 0, SIGNALLING_NAN); } +/* + * Mask the FCSR Cause bits according to the Enable bits, observing + * that Unimplemented is always enabled. + */ +static inline unsigned long mask_fcr31_x(unsigned long fcr31) +{ + return fcr31 & (FPU_CSR_UNI_X | + ((fcr31 & FPU_CSR_ALL_E) << + (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E)))); +} + #endif /* _ASM_FPU_EMULATOR_H */ diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index ebb5c0f2f90d..c0ae27971e31 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -76,6 +76,22 @@ do { if (cpu_has_rw_llb) { \ } while (0) /* + * Check FCSR for any unmasked exceptions pending set with `ptrace', + * clear them and send a signal. + */ +#define __sanitize_fcr31(next) \ +do { \ + unsigned long fcr31 = mask_fcr31_x(next->thread.fpu.fcr31); \ + void __user *pc; \ + \ + if (unlikely(fcr31)) { \ + pc = (void __user *)task_pt_regs(next)->cp0_epc; \ + next->thread.fpu.fcr31 &= ~fcr31; \ + force_fcr31_sig(fcr31, pc, next); \ + } \ +} while (0) + +/* * For newly created kernel threads switch_to() will return to * ret_from_kernel_thread, newly created user threads to ret_from_fork. * That is, everything following resume() will be skipped for new threads. @@ -85,6 +101,8 @@ do { if (cpu_has_rw_llb) { \ do { \ __mips_mt_fpaff_switch_to(prev); \ lose_fpu_inatomic(1, prev); \ + if (tsk_used_math(next)) \ + __sanitize_fcr31(next); \ if (cpu_has_dsp) { \ __save_dsp(prev); \ __restore_dsp(next); \ diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index 2a45867d3b4f..a4964c334cab 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -21,6 +21,11 @@ static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock); static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); +phys_addr_t __weak mips_cpc_default_phys_base(void) +{ + return 0; +} + /** * mips_cpc_phys_base - retrieve the physical base address of the CPC * @@ -43,8 +48,12 @@ static phys_addr_t mips_cpc_phys_base(void) if (cpc_base & CM_GCR_CPC_BASE_CPCEN_MSK) return cpc_base & CM_GCR_CPC_BASE_CPCBASE_MSK; - /* Otherwise, give it the default address & enable it */ + /* Otherwise, use the default address */ cpc_base = mips_cpc_default_phys_base(); + if (!cpc_base) + return cpc_base; + + /* Enable the CPC, mapped at the default address */ write_gcr_cpc_base(cpc_base | CM_GCR_CPC_BASE_CPCEN_MSK); return cpc_base; } diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index 22dedd62818a..bd09853aecdf 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -899,7 +899,7 @@ static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst, * mipsr2_decoder: Decode and emulate a MIPS R2 instruction * @regs: Process register set * @inst: Instruction to decode and emulate - * @fcr31: Floating Point Control and Status Register returned + * @fcr31: Floating Point Control and Status Register Cause bits returned */ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31) { @@ -1172,13 +1172,13 @@ fpu_emul: err = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0, &fault_addr); - *fcr31 = current->thread.fpu.fcr31; /* - * We can't allow the emulated instruction to leave any of - * the cause bits set in $fcr31. + * We can't allow the emulated instruction to leave any + * enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + *fcr31 = res = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~res; /* * this is a tricky issue - lose_fpu() uses LL/SC atomics diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 6103b24d1bfc..a92994d60e91 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -79,16 +79,15 @@ void ptrace_disable(struct task_struct *child) } /* - * Poke at FCSR according to its mask. Don't set the cause bits as - * this is currently not handled correctly in FP context restoration - * and will cause an oops if a corresponding enable bit is set. + * Poke at FCSR according to its mask. Set the Cause bits even + * if a corresponding Enable bit is set. This will be noticed at + * the time the thread is switched to and SIGFPE thrown accordingly. */ static void ptrace_setfcr31(struct task_struct *child, u32 value) { u32 fcr31; u32 mask; - value &= ~FPU_CSR_ALL_X; fcr31 = child->thread.fpu.fcr31; mask = boot_cpu_data.fpu_msk31; child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask); @@ -817,6 +816,7 @@ long arch_ptrace(struct task_struct *child, long request, break; #endif case FPC_CSR: + init_fp_ctx(child); ptrace_setfcr31(child, data); break; case DSP_BASE ... DSP_BASE + 5: { diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index b4ac6374a38f..918f2f6d3861 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -21,106 +21,84 @@ #define EX(a,b) \ 9: a,##b; \ .section __ex_table,"a"; \ + PTR 9b,fault; \ + .previous + +#define EX2(a,b) \ +9: a,##b; \ + .section __ex_table,"a"; \ PTR 9b,bad_stack; \ + PTR 9b+4,bad_stack; \ .previous .set noreorder .set mips1 - /* Save floating point context */ + +/** + * _save_fp_context() - save FP context from the FPU + * @a0 - pointer to fpregs field of sigcontext + * @a1 - pointer to fpc_csr field of sigcontext + * + * Save FP context, including the 32 FP data registers and the FP + * control & status register, from the FPU to signal context. + */ LEAF(_save_fp_context) .set push SET_HARDFLOAT li v0, 0 # assume success - cfc1 t1,fcr31 - EX(swc1 $f0,(SC_FPREGS+0)(a0)) - EX(swc1 $f1,(SC_FPREGS+8)(a0)) - EX(swc1 $f2,(SC_FPREGS+16)(a0)) - EX(swc1 $f3,(SC_FPREGS+24)(a0)) - EX(swc1 $f4,(SC_FPREGS+32)(a0)) - EX(swc1 $f5,(SC_FPREGS+40)(a0)) - EX(swc1 $f6,(SC_FPREGS+48)(a0)) - EX(swc1 $f7,(SC_FPREGS+56)(a0)) - EX(swc1 $f8,(SC_FPREGS+64)(a0)) - EX(swc1 $f9,(SC_FPREGS+72)(a0)) - EX(swc1 $f10,(SC_FPREGS+80)(a0)) - EX(swc1 $f11,(SC_FPREGS+88)(a0)) - EX(swc1 $f12,(SC_FPREGS+96)(a0)) - EX(swc1 $f13,(SC_FPREGS+104)(a0)) - EX(swc1 $f14,(SC_FPREGS+112)(a0)) - EX(swc1 $f15,(SC_FPREGS+120)(a0)) - EX(swc1 $f16,(SC_FPREGS+128)(a0)) - EX(swc1 $f17,(SC_FPREGS+136)(a0)) - EX(swc1 $f18,(SC_FPREGS+144)(a0)) - EX(swc1 $f19,(SC_FPREGS+152)(a0)) - EX(swc1 $f20,(SC_FPREGS+160)(a0)) - EX(swc1 $f21,(SC_FPREGS+168)(a0)) - EX(swc1 $f22,(SC_FPREGS+176)(a0)) - EX(swc1 $f23,(SC_FPREGS+184)(a0)) - EX(swc1 $f24,(SC_FPREGS+192)(a0)) - EX(swc1 $f25,(SC_FPREGS+200)(a0)) - EX(swc1 $f26,(SC_FPREGS+208)(a0)) - EX(swc1 $f27,(SC_FPREGS+216)(a0)) - EX(swc1 $f28,(SC_FPREGS+224)(a0)) - EX(swc1 $f29,(SC_FPREGS+232)(a0)) - EX(swc1 $f30,(SC_FPREGS+240)(a0)) - EX(swc1 $f31,(SC_FPREGS+248)(a0)) - EX(sw t1,(SC_FPC_CSR)(a0)) - cfc1 t0,$0 # implementation/version + cfc1 t1, fcr31 + EX2(s.d $f0, 0(a0)) + EX2(s.d $f2, 16(a0)) + EX2(s.d $f4, 32(a0)) + EX2(s.d $f6, 48(a0)) + EX2(s.d $f8, 64(a0)) + EX2(s.d $f10, 80(a0)) + EX2(s.d $f12, 96(a0)) + EX2(s.d $f14, 112(a0)) + EX2(s.d $f16, 128(a0)) + EX2(s.d $f18, 144(a0)) + EX2(s.d $f20, 160(a0)) + EX2(s.d $f22, 176(a0)) + EX2(s.d $f24, 192(a0)) + EX2(s.d $f26, 208(a0)) + EX2(s.d $f28, 224(a0)) + EX2(s.d $f30, 240(a0)) jr ra + EX(sw t1, (a1)) .set pop - .set nomacro - EX(sw t0,(SC_FPC_EIR)(a0)) - .set macro END(_save_fp_context) -/* - * Restore FPU state: - * - fp gp registers - * - cp1 status/control register +/** + * _restore_fp_context() - restore FP context to the FPU + * @a0 - pointer to fpregs field of sigcontext + * @a1 - pointer to fpc_csr field of sigcontext * - * We base the decision which registers to restore from the signal stack - * frame on the current content of c0_status, not on the content of the - * stack frame which might have been changed by the user. + * Restore FP context, including the 32 FP data registers and the FP + * control & status register, from signal context to the FPU. */ LEAF(_restore_fp_context) .set push SET_HARDFLOAT li v0, 0 # assume success - EX(lw t0,(SC_FPC_CSR)(a0)) - EX(lwc1 $f0,(SC_FPREGS+0)(a0)) - EX(lwc1 $f1,(SC_FPREGS+8)(a0)) - EX(lwc1 $f2,(SC_FPREGS+16)(a0)) - EX(lwc1 $f3,(SC_FPREGS+24)(a0)) - EX(lwc1 $f4,(SC_FPREGS+32)(a0)) - EX(lwc1 $f5,(SC_FPREGS+40)(a0)) - EX(lwc1 $f6,(SC_FPREGS+48)(a0)) - EX(lwc1 $f7,(SC_FPREGS+56)(a0)) - EX(lwc1 $f8,(SC_FPREGS+64)(a0)) - EX(lwc1 $f9,(SC_FPREGS+72)(a0)) - EX(lwc1 $f10,(SC_FPREGS+80)(a0)) - EX(lwc1 $f11,(SC_FPREGS+88)(a0)) - EX(lwc1 $f12,(SC_FPREGS+96)(a0)) - EX(lwc1 $f13,(SC_FPREGS+104)(a0)) - EX(lwc1 $f14,(SC_FPREGS+112)(a0)) - EX(lwc1 $f15,(SC_FPREGS+120)(a0)) - EX(lwc1 $f16,(SC_FPREGS+128)(a0)) - EX(lwc1 $f17,(SC_FPREGS+136)(a0)) - EX(lwc1 $f18,(SC_FPREGS+144)(a0)) - EX(lwc1 $f19,(SC_FPREGS+152)(a0)) - EX(lwc1 $f20,(SC_FPREGS+160)(a0)) - EX(lwc1 $f21,(SC_FPREGS+168)(a0)) - EX(lwc1 $f22,(SC_FPREGS+176)(a0)) - EX(lwc1 $f23,(SC_FPREGS+184)(a0)) - EX(lwc1 $f24,(SC_FPREGS+192)(a0)) - EX(lwc1 $f25,(SC_FPREGS+200)(a0)) - EX(lwc1 $f26,(SC_FPREGS+208)(a0)) - EX(lwc1 $f27,(SC_FPREGS+216)(a0)) - EX(lwc1 $f28,(SC_FPREGS+224)(a0)) - EX(lwc1 $f29,(SC_FPREGS+232)(a0)) - EX(lwc1 $f30,(SC_FPREGS+240)(a0)) - EX(lwc1 $f31,(SC_FPREGS+248)(a0)) + EX(lw t0, (a1)) + EX2(l.d $f0, 0(a0)) + EX2(l.d $f2, 16(a0)) + EX2(l.d $f4, 32(a0)) + EX2(l.d $f6, 48(a0)) + EX2(l.d $f8, 64(a0)) + EX2(l.d $f10, 80(a0)) + EX2(l.d $f12, 96(a0)) + EX2(l.d $f14, 112(a0)) + EX2(l.d $f16, 128(a0)) + EX2(l.d $f18, 144(a0)) + EX2(l.d $f20, 160(a0)) + EX2(l.d $f22, 176(a0)) + EX2(l.d $f24, 192(a0)) + EX2(l.d $f26, 208(a0)) + EX2(l.d $f28, 224(a0)) + EX2(l.d $f30, 240(a0)) jr ra - ctc1 t0,fcr31 + ctc1 t0, fcr31 .set pop END(_restore_fp_context) .set reorder diff --git a/arch/mips/kernel/r6000_fpu.S b/arch/mips/kernel/r6000_fpu.S index 47077380c15c..9cc7bfab3419 100644 --- a/arch/mips/kernel/r6000_fpu.S +++ b/arch/mips/kernel/r6000_fpu.S @@ -21,7 +21,14 @@ .set push SET_HARDFLOAT - /* Save floating point context */ +/** + * _save_fp_context() - save FP context from the FPU + * @a0 - pointer to fpregs field of sigcontext + * @a1 - pointer to fpc_csr field of sigcontext + * + * Save FP context, including the 32 FP data registers and the FP + * control & status register, from the FPU to signal context. + */ LEAF(_save_fp_context) mfc0 t0,CP0_STATUS sll t0,t0,2 @@ -30,59 +37,59 @@ cfc1 t1,fcr31 /* Store the 16 double precision registers */ - sdc1 $f0,(SC_FPREGS+0)(a0) - sdc1 $f2,(SC_FPREGS+16)(a0) - sdc1 $f4,(SC_FPREGS+32)(a0) - sdc1 $f6,(SC_FPREGS+48)(a0) - sdc1 $f8,(SC_FPREGS+64)(a0) - sdc1 $f10,(SC_FPREGS+80)(a0) - sdc1 $f12,(SC_FPREGS+96)(a0) - sdc1 $f14,(SC_FPREGS+112)(a0) - sdc1 $f16,(SC_FPREGS+128)(a0) - sdc1 $f18,(SC_FPREGS+144)(a0) - sdc1 $f20,(SC_FPREGS+160)(a0) - sdc1 $f22,(SC_FPREGS+176)(a0) - sdc1 $f24,(SC_FPREGS+192)(a0) - sdc1 $f26,(SC_FPREGS+208)(a0) - sdc1 $f28,(SC_FPREGS+224)(a0) - sdc1 $f30,(SC_FPREGS+240)(a0) + sdc1 $f0,0(a0) + sdc1 $f2,16(a0) + sdc1 $f4,32(a0) + sdc1 $f6,48(a0) + sdc1 $f8,64(a0) + sdc1 $f10,80(a0) + sdc1 $f12,96(a0) + sdc1 $f14,112(a0) + sdc1 $f16,128(a0) + sdc1 $f18,144(a0) + sdc1 $f20,160(a0) + sdc1 $f22,176(a0) + sdc1 $f24,192(a0) + sdc1 $f26,208(a0) + sdc1 $f28,224(a0) + sdc1 $f30,240(a0) jr ra - sw t0,SC_FPC_CSR(a0) + sw t0,(a1) 1: jr ra nop END(_save_fp_context) -/* Restore FPU state: - * - fp gp registers - * - cp1 status/control register +/** + * _restore_fp_context() - restore FP context to the FPU + * @a0 - pointer to fpregs field of sigcontext + * @a1 - pointer to fpc_csr field of sigcontext * - * We base the decision which registers to restore from the signal stack - * frame on the current content of c0_status, not on the content of the - * stack frame which might have been changed by the user. + * Restore FP context, including the 32 FP data registers and the FP + * control & status register, from signal context to the FPU. */ LEAF(_restore_fp_context) mfc0 t0,CP0_STATUS sll t0,t0,2 bgez t0,1f - lw t0,SC_FPC_CSR(a0) + lw t0,(a1) /* Restore the 16 double precision registers */ - ldc1 $f0,(SC_FPREGS+0)(a0) - ldc1 $f2,(SC_FPREGS+16)(a0) - ldc1 $f4,(SC_FPREGS+32)(a0) - ldc1 $f6,(SC_FPREGS+48)(a0) - ldc1 $f8,(SC_FPREGS+64)(a0) - ldc1 $f10,(SC_FPREGS+80)(a0) - ldc1 $f12,(SC_FPREGS+96)(a0) - ldc1 $f14,(SC_FPREGS+112)(a0) - ldc1 $f16,(SC_FPREGS+128)(a0) - ldc1 $f18,(SC_FPREGS+144)(a0) - ldc1 $f20,(SC_FPREGS+160)(a0) - ldc1 $f22,(SC_FPREGS+176)(a0) - ldc1 $f24,(SC_FPREGS+192)(a0) - ldc1 $f26,(SC_FPREGS+208)(a0) - ldc1 $f28,(SC_FPREGS+224)(a0) - ldc1 $f30,(SC_FPREGS+240)(a0) + ldc1 $f0,0(a0) + ldc1 $f2,16(a0) + ldc1 $f4,32(a0) + ldc1 $f6,48(a0) + ldc1 $f8,64(a0) + ldc1 $f10,80(a0) + ldc1 $f12,96(a0) + ldc1 $f14,112(a0) + ldc1 $f16,128(a0) + ldc1 $f18,144(a0) + ldc1 $f20,160(a0) + ldc1 $f22,176(a0) + ldc1 $f24,192(a0) + ldc1 $f26,208(a0) + ldc1 $f28,224(a0) + ldc1 $f30,240(a0) jr ra ctc1 t0,fcr31 1: jr ra diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index ca1cc30c0891..1958910b75c0 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -200,7 +200,7 @@ static inline __init unsigned long get_random_boot(void) #if defined(CONFIG_USE_OF) /* Get any additional entropy passed in device tree */ - { + if (initial_boot_params) { int node, len; u64 *prop; diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 0d57909d9026..f66e5ce505b2 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -368,6 +368,19 @@ static void __init bootmem_init(void) end = PFN_DOWN(boot_mem_map.map[i].addr + boot_mem_map.map[i].size); +#ifndef CONFIG_HIGHMEM + /* + * Skip highmem here so we get an accurate max_low_pfn if low + * memory stops short of high memory. + * If the region overlaps HIGHMEM_START, end is clipped so + * max_pfn excludes the highmem portion. + */ + if (start >= PFN_DOWN(HIGHMEM_START)) + continue; + if (end > PFN_DOWN(HIGHMEM_START)) + end = PFN_DOWN(HIGHMEM_START); +#endif + if (end > max_low_pfn) max_low_pfn = end; if (start < min_low_pfn) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 1f5fdee1dfc3..3905003dfe2b 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -156,7 +156,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs) print_ip_sym(pc); pc = unwind_stack(task, &sp, pc, &ra); } while (pc); - printk("\n"); + pr_cont("\n"); } /* @@ -174,22 +174,24 @@ static void show_stacktrace(struct task_struct *task, printk("Stack :"); i = 0; while ((unsigned long) sp & (PAGE_SIZE - 1)) { - if (i && ((i % (64 / field)) == 0)) - printk("\n "); + if (i && ((i % (64 / field)) == 0)) { + pr_cont("\n"); + printk(" "); + } if (i > 39) { - printk(" ..."); + pr_cont(" ..."); break; } if (__get_user(stackdata, sp++)) { - printk(" (Bad stack address)"); + pr_cont(" (Bad stack address)"); break; } - printk(" %0*lx", field, stackdata); + pr_cont(" %0*lx", field, stackdata); i++; } - printk("\n"); + pr_cont("\n"); show_backtrace(task, regs); } @@ -229,18 +231,19 @@ static void show_code(unsigned int __user *pc) long i; unsigned short __user *pc16 = NULL; - printk("\nCode:"); + printk("Code:"); if ((unsigned long)pc & 1) pc16 = (unsigned short __user *)((unsigned long)pc & ~1); for(i = -3 ; i < 6 ; i++) { unsigned int insn; if (pc16 ? __get_user(insn, pc16 + i) : __get_user(insn, pc + i)) { - printk(" (Bad address in epc)\n"); + pr_cont(" (Bad address in epc)\n"); break; } - printk("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>')); + pr_cont("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>')); } + pr_cont("\n"); } static void __show_regs(const struct pt_regs *regs) @@ -259,15 +262,15 @@ static void __show_regs(const struct pt_regs *regs) if ((i % 4) == 0) printk("$%2d :", i); if (i == 0) - printk(" %0*lx", field, 0UL); + pr_cont(" %0*lx", field, 0UL); else if (i == 26 || i == 27) - printk(" %*s", field, ""); + pr_cont(" %*s", field, ""); else - printk(" %0*lx", field, regs->regs[i]); + pr_cont(" %0*lx", field, regs->regs[i]); i++; if ((i % 4) == 0) - printk("\n"); + pr_cont("\n"); } #ifdef CONFIG_CPU_HAS_SMARTMIPS @@ -288,46 +291,46 @@ static void __show_regs(const struct pt_regs *regs) if (cpu_has_3kex) { if (regs->cp0_status & ST0_KUO) - printk("KUo "); + pr_cont("KUo "); if (regs->cp0_status & ST0_IEO) - printk("IEo "); + pr_cont("IEo "); if (regs->cp0_status & ST0_KUP) - printk("KUp "); + pr_cont("KUp "); if (regs->cp0_status & ST0_IEP) - printk("IEp "); + pr_cont("IEp "); if (regs->cp0_status & ST0_KUC) - printk("KUc "); + pr_cont("KUc "); if (regs->cp0_status & ST0_IEC) - printk("IEc "); + pr_cont("IEc "); } else if (cpu_has_4kex) { if (regs->cp0_status & ST0_KX) - printk("KX "); + pr_cont("KX "); if (regs->cp0_status & ST0_SX) - printk("SX "); + pr_cont("SX "); if (regs->cp0_status & ST0_UX) - printk("UX "); + pr_cont("UX "); switch (regs->cp0_status & ST0_KSU) { case KSU_USER: - printk("USER "); + pr_cont("USER "); break; case KSU_SUPERVISOR: - printk("SUPERVISOR "); + pr_cont("SUPERVISOR "); break; case KSU_KERNEL: - printk("KERNEL "); + pr_cont("KERNEL "); break; default: - printk("BAD_MODE "); + pr_cont("BAD_MODE "); break; } if (regs->cp0_status & ST0_ERL) - printk("ERL "); + pr_cont("ERL "); if (regs->cp0_status & ST0_EXL) - printk("EXL "); + pr_cont("EXL "); if (regs->cp0_status & ST0_IE) - printk("IE "); + pr_cont("IE "); } - printk("\n"); + pr_cont("\n"); exccode = (cause & CAUSEF_EXCCODE) >> CAUSEB_EXCCODE; printk("Cause : %08x (ExcCode %02x)\n", cause, exccode); @@ -705,6 +708,32 @@ asmlinkage void do_ov(struct pt_regs *regs) exception_exit(prev_state); } +/* + * Send SIGFPE according to FCSR Cause bits, which must have already + * been masked against Enable bits. This is impotant as Inexact can + * happen together with Overflow or Underflow, and `ptrace' can set + * any bits. + */ +void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr, + struct task_struct *tsk) +{ + struct siginfo si = { .si_addr = fault_addr, .si_signo = SIGFPE }; + + if (fcr31 & FPU_CSR_INV_X) + si.si_code = FPE_FLTINV; + else if (fcr31 & FPU_CSR_DIV_X) + si.si_code = FPE_FLTDIV; + else if (fcr31 & FPU_CSR_OVF_X) + si.si_code = FPE_FLTOVF; + else if (fcr31 & FPU_CSR_UDF_X) + si.si_code = FPE_FLTUND; + else if (fcr31 & FPU_CSR_INE_X) + si.si_code = FPE_FLTRES; + else + si.si_code = __SI_FAULT; + force_sig_info(SIGFPE, &si, tsk); +} + int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) { struct siginfo si = { 0 }; @@ -715,27 +744,7 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) return 0; case SIGFPE: - si.si_addr = fault_addr; - si.si_signo = sig; - /* - * Inexact can happen together with Overflow or Underflow. - * Respect the mask to deliver the correct exception. - */ - fcr31 &= (fcr31 & FPU_CSR_ALL_E) << - (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E)); - if (fcr31 & FPU_CSR_INV_X) - si.si_code = FPE_FLTINV; - else if (fcr31 & FPU_CSR_DIV_X) - si.si_code = FPE_FLTDIV; - else if (fcr31 & FPU_CSR_OVF_X) - si.si_code = FPE_FLTOVF; - else if (fcr31 & FPU_CSR_UDF_X) - si.si_code = FPE_FLTUND; - else if (fcr31 & FPU_CSR_INE_X) - si.si_code = FPE_FLTRES; - else - si.si_code = __SI_FAULT; - force_sig_info(sig, &si, current); + force_fcr31_sig(fcr31, fault_addr, current); return 1; case SIGBUS: @@ -799,13 +808,13 @@ static int simulate_fp(struct pt_regs *regs, unsigned int opcode, /* Run the emulator */ sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - fcr31 = current->thread.fpu.fcr31; /* - * We can't allow the emulated instruction to leave any of - * the cause bits set in $fcr31. + * We can't allow the emulated instruction to leave any + * enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + fcr31 = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~fcr31; /* Restore the hardware register state */ own_fpu(1); @@ -831,7 +840,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) goto out; /* Clear FCSR.Cause before enabling interrupts */ - write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X); + write_32bit_cp1_register(CP1_STATUS, fcr31 & ~mask_fcr31_x(fcr31)); local_irq_enable(); die_if_kernel("FP exception in kernel code", regs); @@ -853,13 +862,13 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) /* Run the emulator */ sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - fcr31 = current->thread.fpu.fcr31; /* - * We can't allow the emulated instruction to leave any of - * the cause bits set in $fcr31. + * We can't allow the emulated instruction to leave any + * enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + fcr31 = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~fcr31; /* Restore the hardware register state */ own_fpu(1); /* Using the FPU again. */ @@ -1424,13 +1433,13 @@ asmlinkage void do_cpu(struct pt_regs *regs) sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0, &fault_addr); - fcr31 = current->thread.fpu.fcr31; /* * We can't allow the emulated instruction to leave - * any of the cause bits set in $fcr31. + * any enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + fcr31 = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~fcr31; /* Send a signal if required. */ if (!process_fpemu_return(sig, fault_addr, fcr31) && !err) diff --git a/arch/mips/lib/dump_tlb.c b/arch/mips/lib/dump_tlb.c index 0f80b936e75e..6eb50a7137db 100644 --- a/arch/mips/lib/dump_tlb.c +++ b/arch/mips/lib/dump_tlb.c @@ -135,42 +135,42 @@ static void dump_tlb(int first, int last) c0 = (entrylo0 & ENTRYLO_C) >> ENTRYLO_C_SHIFT; c1 = (entrylo1 & ENTRYLO_C) >> ENTRYLO_C_SHIFT; - printk("va=%0*lx asid=%0*lx", - vwidth, (entryhi & ~0x1fffUL), - asidwidth, entryhi & asidmask); + pr_cont("va=%0*lx asid=%0*lx", + vwidth, (entryhi & ~0x1fffUL), + asidwidth, entryhi & asidmask); if (cpu_has_guestid) - printk(" gid=%02lx", - (guestctl1 & MIPS_GCTL1_RID) + pr_cont(" gid=%02lx", + (guestctl1 & MIPS_GCTL1_RID) >> MIPS_GCTL1_RID_SHIFT); /* RI/XI are in awkward places, so mask them off separately */ pa = entrylo0 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI); if (xpa) pa |= (unsigned long long)readx_c0_entrylo0() << 30; pa = (pa << 6) & PAGE_MASK; - printk("\n\t["); + pr_cont("\n\t["); if (cpu_has_rixi) - printk("ri=%d xi=%d ", - (entrylo0 & MIPS_ENTRYLO_RI) ? 1 : 0, - (entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0); - printk("pa=%0*llx c=%d d=%d v=%d g=%d] [", - pwidth, pa, c0, - (entrylo0 & ENTRYLO_D) ? 1 : 0, - (entrylo0 & ENTRYLO_V) ? 1 : 0, - (entrylo0 & ENTRYLO_G) ? 1 : 0); + pr_cont("ri=%d xi=%d ", + (entrylo0 & MIPS_ENTRYLO_RI) ? 1 : 0, + (entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0); + pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d] [", + pwidth, pa, c0, + (entrylo0 & ENTRYLO_D) ? 1 : 0, + (entrylo0 & ENTRYLO_V) ? 1 : 0, + (entrylo0 & ENTRYLO_G) ? 1 : 0); /* RI/XI are in awkward places, so mask them off separately */ pa = entrylo1 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI); if (xpa) pa |= (unsigned long long)readx_c0_entrylo1() << 30; pa = (pa << 6) & PAGE_MASK; if (cpu_has_rixi) - printk("ri=%d xi=%d ", - (entrylo1 & MIPS_ENTRYLO_RI) ? 1 : 0, - (entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0); - printk("pa=%0*llx c=%d d=%d v=%d g=%d]\n", - pwidth, pa, c1, - (entrylo1 & ENTRYLO_D) ? 1 : 0, - (entrylo1 & ENTRYLO_V) ? 1 : 0, - (entrylo1 & ENTRYLO_G) ? 1 : 0); + pr_cont("ri=%d xi=%d ", + (entrylo1 & MIPS_ENTRYLO_RI) ? 1 : 0, + (entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0); + pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d]\n", + pwidth, pa, c1, + (entrylo1 & ENTRYLO_D) ? 1 : 0, + (entrylo1 & ENTRYLO_V) ? 1 : 0, + (entrylo1 & ENTRYLO_G) ? 1 : 0); } printk("\n"); diff --git a/arch/mips/lib/r3k_dump_tlb.c b/arch/mips/lib/r3k_dump_tlb.c index 744f4a7bc49d..85b4086e553e 100644 --- a/arch/mips/lib/r3k_dump_tlb.c +++ b/arch/mips/lib/r3k_dump_tlb.c @@ -53,15 +53,15 @@ static void dump_tlb(int first, int last) */ printk("Index: %2d ", i); - printk("va=%08lx asid=%08lx" - " [pa=%06lx n=%d d=%d v=%d g=%d]", - entryhi & PAGE_MASK, - entryhi & asid_mask, - entrylo0 & PAGE_MASK, - (entrylo0 & R3K_ENTRYLO_N) ? 1 : 0, - (entrylo0 & R3K_ENTRYLO_D) ? 1 : 0, - (entrylo0 & R3K_ENTRYLO_V) ? 1 : 0, - (entrylo0 & R3K_ENTRYLO_G) ? 1 : 0); + pr_cont("va=%08lx asid=%08lx" + " [pa=%06lx n=%d d=%d v=%d g=%d]", + entryhi & PAGE_MASK, + entryhi & asid_mask, + entrylo0 & PAGE_MASK, + (entrylo0 & R3K_ENTRYLO_N) ? 1 : 0, + (entrylo0 & R3K_ENTRYLO_D) ? 1 : 0, + (entrylo0 & R3K_ENTRYLO_V) ? 1 : 0, + (entrylo0 & R3K_ENTRYLO_G) ? 1 : 0); } } printk("\n"); diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c index d9563ddb337e..746bf5caaffc 100644 --- a/arch/nios2/kernel/time.c +++ b/arch/nios2/kernel/time.c @@ -324,6 +324,7 @@ static int __init nios2_time_init(struct device_node *timer) ret = nios2_clocksource_init(timer); break; default: + ret = 0; break; } diff --git a/arch/openrisc/include/asm/cache.h b/arch/openrisc/include/asm/cache.h index 4ce7a01a252d..5f55da9cbfd5 100644 --- a/arch/openrisc/include/asm/cache.h +++ b/arch/openrisc/include/asm/cache.h @@ -23,6 +23,8 @@ * they shouldn't be hard-coded! */ +#define __ro_after_init __read_mostly + #define L1_CACHE_BYTES 16 #define L1_CACHE_SHIFT 4 diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index a9b9407f38f7..6b0741e7a7ed 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -368,7 +368,9 @@ #define __IGNORE_select /* newselect */ #define __IGNORE_fadvise64 /* fadvise64_64 */ - +#define __IGNORE_pkey_mprotect +#define __IGNORE_pkey_alloc +#define __IGNORE_pkey_free #define LINUX_GATEWAY_ADDR 0x100 diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index f8150669b8c6..700e2d2da096 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -873,11 +873,11 @@ static void print_parisc_device(struct parisc_device *dev) if (dev->num_addrs) { int k; - printk(", additional addresses: "); + pr_cont(", additional addresses: "); for (k = 0; k < dev->num_addrs; k++) - printk("0x%lx ", dev->addr[k]); + pr_cont("0x%lx ", dev->addr[k]); } - printk("\n"); + pr_cont("\n"); } /** diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index d03422e5f188..23de307c3052 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -100,14 +100,12 @@ set_thread_pointer: .endr /* This address must remain fixed at 0x100 for glibc's syscalls to work */ - .align 256 + .align LINUX_GATEWAY_ADDR linux_gateway_entry: gate .+8, %r0 /* become privileged */ mtsp %r0,%sr4 /* get kernel space into sr4 */ mtsp %r0,%sr5 /* get kernel space into sr5 */ mtsp %r0,%sr6 /* get kernel space into sr6 */ - mfsp %sr7,%r1 /* save user sr7 */ - mtsp %r1,%sr3 /* and store it in sr3 */ #ifdef CONFIG_64BIT /* for now we can *always* set the W bit on entry to the syscall @@ -133,6 +131,14 @@ linux_gateway_entry: depdi 0, 31, 32, %r21 1: #endif + + /* We use a rsm/ssm pair to prevent sr3 from being clobbered + * by external interrupts. + */ + mfsp %sr7,%r1 /* save user sr7 */ + rsm PSW_SM_I, %r0 /* disable interrupts */ + mtsp %r1,%sr3 /* and store it in sr3 */ + mfctl %cr30,%r1 xor %r1,%r30,%r30 /* ye olde xor trick */ xor %r1,%r30,%r1 @@ -147,6 +153,7 @@ linux_gateway_entry: */ mtsp %r0,%sr7 /* get kernel space into sr7 */ + ssm PSW_SM_I, %r0 /* enable interrupts */ STREGM %r1,FRAME_SIZE(%r30) /* save r1 (usp) here for now */ mfctl %cr30,%r1 /* get task ptr in %r1 */ LDREG TI_TASK(%r1),%r1 @@ -474,11 +481,6 @@ lws_start: comiclr,>> __NR_lws_entries, %r20, %r0 b,n lws_exit_nosys - /* WARNING: Trashing sr2 and sr3 */ - mfsp %sr7,%r1 /* get userspace into sr3 */ - mtsp %r1,%sr3 - mtsp %r0,%sr2 /* get kernel space into sr2 */ - /* Load table start */ ldil L%lws_table, %r1 ldo R%lws_table(%r1), %r28 /* Scratch use of r28 */ @@ -627,9 +629,9 @@ cas_action: stw %r1, 4(%sr2,%r20) #endif /* The load and store could fail */ -1: ldw,ma 0(%sr3,%r26), %r28 +1: ldw,ma 0(%r26), %r28 sub,<> %r28, %r25, %r0 -2: stw,ma %r24, 0(%sr3,%r26) +2: stw,ma %r24, 0(%r26) /* Free lock */ stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG @@ -706,9 +708,9 @@ lws_compare_and_swap_2: nop /* 8bit load */ -4: ldb 0(%sr3,%r25), %r25 +4: ldb 0(%r25), %r25 b cas2_lock_start -5: ldb 0(%sr3,%r24), %r24 +5: ldb 0(%r24), %r24 nop nop nop @@ -716,9 +718,9 @@ lws_compare_and_swap_2: nop /* 16bit load */ -6: ldh 0(%sr3,%r25), %r25 +6: ldh 0(%r25), %r25 b cas2_lock_start -7: ldh 0(%sr3,%r24), %r24 +7: ldh 0(%r24), %r24 nop nop nop @@ -726,9 +728,9 @@ lws_compare_and_swap_2: nop /* 32bit load */ -8: ldw 0(%sr3,%r25), %r25 +8: ldw 0(%r25), %r25 b cas2_lock_start -9: ldw 0(%sr3,%r24), %r24 +9: ldw 0(%r24), %r24 nop nop nop @@ -737,14 +739,14 @@ lws_compare_and_swap_2: /* 64bit load */ #ifdef CONFIG_64BIT -10: ldd 0(%sr3,%r25), %r25 -11: ldd 0(%sr3,%r24), %r24 +10: ldd 0(%r25), %r25 +11: ldd 0(%r24), %r24 #else /* Load new value into r22/r23 - high/low */ -10: ldw 0(%sr3,%r25), %r22 -11: ldw 4(%sr3,%r25), %r23 +10: ldw 0(%r25), %r22 +11: ldw 4(%r25), %r23 /* Load new value into fr4 for atomic store later */ -12: flddx 0(%sr3,%r24), %fr4 +12: flddx 0(%r24), %fr4 #endif cas2_lock_start: @@ -794,30 +796,30 @@ cas2_action: ldo 1(%r0),%r28 /* 8bit CAS */ -13: ldb,ma 0(%sr3,%r26), %r29 +13: ldb,ma 0(%r26), %r29 sub,= %r29, %r25, %r0 b,n cas2_end -14: stb,ma %r24, 0(%sr3,%r26) +14: stb,ma %r24, 0(%r26) b cas2_end copy %r0, %r28 nop nop /* 16bit CAS */ -15: ldh,ma 0(%sr3,%r26), %r29 +15: ldh,ma 0(%r26), %r29 sub,= %r29, %r25, %r0 b,n cas2_end -16: sth,ma %r24, 0(%sr3,%r26) +16: sth,ma %r24, 0(%r26) b cas2_end copy %r0, %r28 nop nop /* 32bit CAS */ -17: ldw,ma 0(%sr3,%r26), %r29 +17: ldw,ma 0(%r26), %r29 sub,= %r29, %r25, %r0 b,n cas2_end -18: stw,ma %r24, 0(%sr3,%r26) +18: stw,ma %r24, 0(%r26) b cas2_end copy %r0, %r28 nop @@ -825,22 +827,22 @@ cas2_action: /* 64bit CAS */ #ifdef CONFIG_64BIT -19: ldd,ma 0(%sr3,%r26), %r29 +19: ldd,ma 0(%r26), %r29 sub,*= %r29, %r25, %r0 b,n cas2_end -20: std,ma %r24, 0(%sr3,%r26) +20: std,ma %r24, 0(%r26) copy %r0, %r28 #else /* Compare first word */ -19: ldw,ma 0(%sr3,%r26), %r29 +19: ldw,ma 0(%r26), %r29 sub,= %r29, %r22, %r0 b,n cas2_end /* Compare second word */ -20: ldw,ma 4(%sr3,%r26), %r29 +20: ldw,ma 4(%r26), %r29 sub,= %r29, %r23, %r0 b,n cas2_end /* Perform the store */ -21: fstdx %fr4, 0(%sr3,%r26) +21: fstdx %fr4, 0(%r26) copy %r0, %r28 #endif diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index ee655ed1ff1b..1e8fceb308a5 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -53,10 +53,8 @@ static inline __sum16 csum_fold(__wsum sum) return (__force __sum16)(~((__force u32)sum + tmp) >> 16); } -static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, - unsigned short len, - unsigned short proto, - __wsum sum) +static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) { #ifdef __powerpc64__ unsigned long s = (__force u32)sum; @@ -83,10 +81,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, * computes the checksum of the TCP/UDP pseudo-header * returns a 16-bit checksum, already complemented */ -static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, - unsigned short len, - unsigned short proto, - __wsum sum) +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) { return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); } diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 01b8a13f0224..3919332965af 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -26,7 +26,7 @@ extern u64 pnv_first_deep_stop_state; std r0,0(r1); \ ptesync; \ ld r0,0(r1); \ -1: cmp cr0,r0,r0; \ +1: cmpd cr0,r0,r0; \ bne 1b; \ IDLE_INST; \ b . diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 2e4e7d878c8e..84d49b197c32 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -93,6 +93,10 @@ ld reg,PACAKBASE(r13); /* get high part of &label */ \ ori reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l; +#define __LOAD_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(label))@l; + /* Exception register prefixes */ #define EXC_HV H #define EXC_STD @@ -208,6 +212,18 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define kvmppc_interrupt kvmppc_interrupt_pr #endif +#ifdef CONFIG_RELOCATABLE +#define BRANCH_TO_COMMON(reg, label) \ + __LOAD_HANDLER(reg, label); \ + mtctr reg; \ + bctr + +#else +#define BRANCH_TO_COMMON(reg, label) \ + b label + +#endif + #define __KVM_HANDLER_PROLOG(area, n) \ BEGIN_FTR_SECTION_NESTED(947) \ ld r10,area+EX_CFAR(r13); \ diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index f6f68f73e858..99e1397b71da 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -52,11 +52,23 @@ static inline int mm_is_core_local(struct mm_struct *mm) return cpumask_subset(mm_cpumask(mm), topology_sibling_cpumask(smp_processor_id())); } + +static inline int mm_is_thread_local(struct mm_struct *mm) +{ + return cpumask_equal(mm_cpumask(mm), + cpumask_of(smp_processor_id())); +} + #else static inline int mm_is_core_local(struct mm_struct *mm) { return 1; } + +static inline int mm_is_thread_local(struct mm_struct *mm) +{ + return 1; +} #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f129408c6022..08ba447a4b3d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -95,19 +95,35 @@ __start_interrupts: /* No virt vectors corresponding with 0x0..0x100 */ EXC_VIRT_NONE(0x4000, 0x4100) -EXC_REAL_BEGIN(system_reset, 0x100, 0x200) - SET_SCRATCH0(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/sleep/winkle. + /* + * If running native on arch 2.06 or later, check if we are waking up + * from nap/sleep/winkle, and branch to idle handler. */ - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - beq 9f +#define IDLETEST(n) \ + BEGIN_FTR_SECTION ; \ + mfspr r10,SPRN_SRR1 ; \ + rlwinm. r10,r10,47-31,30,31 ; \ + beq- 1f ; \ + cmpwi cr3,r10,2 ; \ + BRANCH_TO_COMMON(r10, system_reset_idle_common) ; \ +1: \ + END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +#else +#define IDLETEST NOTEST +#endif - cmpwi cr3,r13,2 - GET_PACA(r13) +EXC_REAL_BEGIN(system_reset, 0x100, 0x200) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + IDLETEST, 0x100) + +EXC_REAL_END(system_reset, 0x100, 0x200) +EXC_VIRT_NONE(0x4100, 0x4200) + +#ifdef CONFIG_PPC_P7_NAP +EXC_COMMON_BEGIN(system_reset_idle_common) bl pnv_restore_hyp_resource li r0,PNV_THREAD_RUNNING @@ -130,14 +146,8 @@ BEGIN_FTR_SECTION blt cr3,2f b pnv_wakeup_loss 2: b pnv_wakeup_noloss +#endif -9: -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#endif /* CONFIG_PPC_P7_NAP */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, - NOTEST, 0x100) -EXC_REAL_END(system_reset, 0x100, 0x200) -EXC_VIRT_NONE(0x4100, 0x4200) EXC_COMMON(system_reset_common, 0x100, system_reset_exception) #ifdef CONFIG_PPC_PSERIES @@ -817,10 +827,8 @@ EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00) TRAMP_KVM(PACA_EXGEN, 0xb00) EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) - -#define LOAD_SYSCALL_HANDLER(reg) \ - ld reg,PACAKBASE(r13); \ - ori reg,reg,(ABS_ADDR(system_call_common))@l; +#define LOAD_SYSCALL_HANDLER(reg) \ + __LOAD_HANDLER(reg, system_call_common) /* Syscall routine is used twice, in reloc-off and reloc-on paths */ #define SYSCALL_PSERIES_1 \ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 9781c69eae57..03d089b3ed72 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -275,7 +275,7 @@ int hw_breakpoint_handler(struct die_args *args) if (!stepped) { WARN(1, "Unable to handle hardware breakpoint. Breakpoint at " "0x%lx will be disabled.", info->address); - perf_event_disable(bp); + perf_event_disable_inatomic(bp); goto out; } /* diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index bd739fed26e3..72dac0b58061 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -90,6 +90,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) * Threads will spin in HMT_LOW until the lock bit is cleared. * r14 - pointer to core_idle_state * r15 - used to load contents of core_idle_state + * r9 - used as a temporary variable */ core_idle_lock_held: @@ -99,6 +100,8 @@ core_idle_lock_held: bne 3b HMT_MEDIUM lwarx r15,0,r14 + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bne core_idle_lock_held blr /* @@ -163,12 +166,6 @@ _GLOBAL(pnv_powersave_common) std r9,_MSR(r1) std r1,PACAR1(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - /* Tell KVM we're entering idle */ - li r4,KVM_HWTHREAD_IN_IDLE - stb r4,HSTATE_HWTHREAD_STATE(r13) -#endif - /* * Go to real mode to do the nap, as required by the architecture. * Also, we need to be in real mode before setting hwthread_state, @@ -185,6 +182,26 @@ _GLOBAL(pnv_powersave_common) .globl pnv_enter_arch207_idle_mode pnv_enter_arch207_idle_mode: +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* Tell KVM we're entering idle */ + li r4,KVM_HWTHREAD_IN_IDLE + /******************************************************/ + /* N O T E W E L L ! ! ! N O T E W E L L */ + /* The following store to HSTATE_HWTHREAD_STATE(r13) */ + /* MUST occur in real mode, i.e. with the MMU off, */ + /* and the MMU must stay off until we clear this flag */ + /* and test HSTATE_HWTHREAD_REQ(r13) in the system */ + /* reset interrupt vector in exceptions-64s.S. */ + /* The reason is that another thread can switch the */ + /* MMU to a guest context whenever this flag is set */ + /* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on, */ + /* that would potentially cause this thread to start */ + /* executing instructions from guest memory in */ + /* hypervisor mode, leading to a host crash or data */ + /* corruption, or worse. */ + /******************************************************/ + stb r4,HSTATE_HWTHREAD_STATE(r13) +#endif stb r3,PACA_THREAD_IDLE_STATE(r13) cmpwi cr3,r3,PNV_THREAD_SLEEP bge cr3,2f @@ -250,6 +267,12 @@ enter_winkle: * r3 - requested stop state */ power_enter_stop: +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* Tell KVM we're entering idle */ + li r4,KVM_HWTHREAD_IN_IDLE + /* DO THIS IN REAL MODE! See comment above. */ + stb r4,HSTATE_HWTHREAD_STATE(r13) +#endif /* * Check if the requested state is a deep idle state. */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9e7c10fe205f..ce6dc61b15b2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1012,7 +1012,7 @@ void restore_tm_state(struct pt_regs *regs) /* Ensure that restore_math() will restore */ if (msr_diff & MSR_FP) current->thread.load_fp = 1; -#ifdef CONFIG_ALIVEC +#ifdef CONFIG_ALTIVEC if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC) current->thread.load_vec = 1; #endif diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 82ff5de8b1e7..a0ea63ac2b52 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -23,6 +23,7 @@ #include <asm/ppc-opcode.h> #include <asm/pnv-pci.h> #include <asm/opal.h> +#include <asm/smp.h> #include "book3s_xics.h" diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 0e49ec541ab5..bda8c43be78a 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -175,7 +175,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm) if (unlikely(pid == MMU_NO_CONTEXT)) goto no_context; - if (!mm_is_core_local(mm)) { + if (!mm_is_thread_local(mm)) { int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); if (lock_tlbie) @@ -201,7 +201,7 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) if (unlikely(pid == MMU_NO_CONTEXT)) goto no_context; - if (!mm_is_core_local(mm)) { + if (!mm_is_thread_local(mm)) { int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); if (lock_tlbie) @@ -226,7 +226,7 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, pid = mm ? mm->context.id : 0; if (unlikely(pid == MMU_NO_CONTEXT)) goto bail; - if (!mm_is_core_local(mm)) { + if (!mm_is_thread_local(mm)) { int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); if (lock_tlbie) @@ -321,7 +321,7 @@ void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, { unsigned long pid; unsigned long addr; - int local = mm_is_core_local(mm); + int local = mm_is_thread_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; diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 28f03ca60100..794bebb43d23 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -363,11 +363,11 @@ out: static int diag224_get_name_table(void) { /* memory must be below 2GB */ - diag224_cpu_names = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA); + diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA); if (!diag224_cpu_names) return -ENOMEM; if (diag224(diag224_cpu_names)) { - kfree(diag224_cpu_names); + free_page((unsigned long) diag224_cpu_names); return -EOPNOTSUPP; } EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16); @@ -376,7 +376,7 @@ static int diag224_get_name_table(void) static void diag224_delete_name_table(void) { - kfree(diag224_cpu_names); + free_page((unsigned long) diag224_cpu_names); } static int diag224_idx2name(int index, char *name) diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 64053d9ac3f2..836c56290499 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -12,9 +12,7 @@ #ifndef __ASSEMBLY__ -unsigned long return_address(int depth); - -#define ftrace_return_address(n) return_address(n) +#define ftrace_return_address(n) __builtin_return_address(n) void _mcount(void); void ftrace_caller(void); diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 03323175de30..602af692efdc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -192,7 +192,7 @@ struct task_struct; struct mm_struct; struct seq_file; -typedef int (*dump_trace_func_t)(void *data, unsigned long address); +typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable); void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task, unsigned long sp); diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 02613bad8bbb..3066031a73fe 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -9,6 +9,9 @@ #include <uapi/asm/unistd.h> #define __IGNORE_time +#define __IGNORE_pkey_mprotect +#define __IGNORE_pkey_alloc +#define __IGNORE_pkey_free #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_SYS_ALARM diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 43446fa2a4e5..c74c59236f44 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -2014,12 +2014,12 @@ void show_code(struct pt_regs *regs) *ptr++ = '\t'; ptr += print_insn(ptr, code + start, addr); start += opsize; - printk("%s", buffer); + pr_cont("%s", buffer); ptr = buffer; ptr += sprintf(ptr, "\n "); hops++; } - printk("\n"); + pr_cont("\n"); } void print_fn_code(unsigned char *code, unsigned long len) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 6693383bc01b..55d4fe174fd9 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -38,10 +38,10 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; + if (func(data, sf->gprs[8], 0)) + return sp; /* Follow the backchain. */ while (1) { - if (func(data, sf->gprs[8])) - return sp; low = sp; sp = sf->back_chain; if (!sp) @@ -49,6 +49,8 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; + if (func(data, sf->gprs[8], 1)) + return sp; } /* Zero backchain detected, check for interrupt frame. */ sp = (unsigned long) (sf + 1); @@ -56,7 +58,7 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, return sp; regs = (struct pt_regs *) sp; if (!user_mode(regs)) { - if (func(data, regs->psw.addr)) + if (func(data, regs->psw.addr, 1)) return sp; } low = sp; @@ -85,33 +87,12 @@ void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task, } EXPORT_SYMBOL_GPL(dump_trace); -struct return_address_data { - unsigned long address; - int depth; -}; - -static int __return_address(void *data, unsigned long address) -{ - struct return_address_data *rd = data; - - if (rd->depth--) - return 0; - rd->address = address; - return 1; -} - -unsigned long return_address(int depth) -{ - struct return_address_data rd = { .depth = depth + 2 }; - - dump_trace(__return_address, &rd, NULL, current_stack_pointer()); - return rd.address; -} -EXPORT_SYMBOL_GPL(return_address); - -static int show_address(void *data, unsigned long address) +static int show_address(void *data, unsigned long address, int reliable) { - printk("([<%016lx>] %pSR)\n", address, (void *)address); + if (reliable) + printk(" [<%016lx>] %pSR \n", address, (void *)address); + else + printk("([<%016lx>] %pSR)\n", address, (void *)address); return 0; } @@ -138,14 +119,14 @@ void show_stack(struct task_struct *task, unsigned long *sp) else stack = (unsigned long *)task->thread.ksp; } + printk(KERN_DEFAULT "Stack:\n"); for (i = 0; i < 20; i++) { if (((addr_t) stack & (THREAD_SIZE-1)) == 0) break; - if ((i * sizeof(long) % 32) == 0) - printk("%s ", i == 0 ? "" : "\n"); - printk("%016lx ", *stack++); + if (i % 4 == 0) + printk(KERN_DEFAULT " "); + pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' '); } - printk("\n"); show_trace(task, (unsigned long)sp); } @@ -163,13 +144,13 @@ void show_registers(struct pt_regs *regs) mode = user_mode(regs) ? "User" : "Krnl"; printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr); if (!user_mode(regs)) - printk(" (%pSR)", (void *)regs->psw.addr); - printk("\n"); + pr_cont(" (%pSR)", (void *)regs->psw.addr); + pr_cont("\n"); printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e, psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm); - printk(" RI:%x EA:%x", psw->ri, psw->eaba); - printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode, + pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba); + printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode, regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); printk(" %016lx %016lx %016lx %016lx\n", regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); @@ -205,14 +186,14 @@ void die(struct pt_regs *regs, const char *str) printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff, regs->int_code >> 17, ++die_counter); #ifdef CONFIG_PREEMPT - printk("PREEMPT "); + pr_cont("PREEMPT "); #endif #ifdef CONFIG_SMP - printk("SMP "); + pr_cont("SMP "); #endif if (debug_pagealloc_enabled()) - printk("DEBUG_PAGEALLOC"); - printk("\n"); + pr_cont("DEBUG_PAGEALLOC"); + pr_cont("\n"); notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); print_modules(); show_regs(regs); diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 17431f63de00..955a7b6fa0a4 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -222,7 +222,7 @@ static int __init service_level_perf_register(void) } arch_initcall(service_level_perf_register); -static int __perf_callchain_kernel(void *data, unsigned long address) +static int __perf_callchain_kernel(void *data, unsigned long address, int reliable) { struct perf_callchain_entry_ctx *entry = data; diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 44f84b23d4e5..355db9db8210 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -27,12 +27,12 @@ static int __save_address(void *data, unsigned long address, int nosched) return 1; } -static int save_address(void *data, unsigned long address) +static int save_address(void *data, unsigned long address, int reliable) { return __save_address(data, address, 0); } -static int save_address_nosched(void *data, unsigned long address) +static int save_address_nosched(void *data, unsigned long address, int reliable) { return __save_address(data, address, 1); } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 000e6e91f6a0..3667d20e997f 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -62,9 +62,11 @@ SECTIONS . = ALIGN(PAGE_SIZE); __start_ro_after_init = .; + __start_data_ro_after_init = .; .data..ro_after_init : { *(.data..ro_after_init) } + __end_data_ro_after_init = .; EXCEPTION_TABLE(16) . = ALIGN(PAGE_SIZE); __end_ro_after_init = .; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index cd404aa3931c..4a0c5bce3552 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -217,6 +217,7 @@ static __init int setup_hugepagesz(char *opt) } else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); } else { + hugetlb_bad_size(); pr_err("hugepagesz= specifies an unsupported page size %s\n", string); return 0; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index f56a39bd8ba6..b3e9d18f2ec6 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -151,36 +151,40 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { - unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM()); - unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS); + unsigned long zone_start_pfn, zone_end_pfn, nr_pages; unsigned long start_pfn = PFN_DOWN(start); unsigned long size_pages = PFN_DOWN(size); - unsigned long nr_pages; - int rc, zone_enum; + pg_data_t *pgdat = NODE_DATA(nid); + struct zone *zone; + int rc, i; rc = vmem_add_mapping(start, size); if (rc) return rc; - while (size_pages > 0) { - if (start_pfn < dma_end_pfn) { - nr_pages = (start_pfn + size_pages > dma_end_pfn) ? - dma_end_pfn - start_pfn : size_pages; - zone_enum = ZONE_DMA; - } else if (start_pfn < normal_end_pfn) { - nr_pages = (start_pfn + size_pages > normal_end_pfn) ? - normal_end_pfn - start_pfn : size_pages; - zone_enum = ZONE_NORMAL; + for (i = 0; i < MAX_NR_ZONES; i++) { + zone = pgdat->node_zones + i; + if (zone_idx(zone) != ZONE_MOVABLE) { + /* Add range within existing zone limits, if possible */ + zone_start_pfn = zone->zone_start_pfn; + zone_end_pfn = zone->zone_start_pfn + + zone->spanned_pages; } else { - nr_pages = size_pages; - zone_enum = ZONE_MOVABLE; + /* Add remaining range to ZONE_MOVABLE */ + zone_start_pfn = start_pfn; + zone_end_pfn = start_pfn + size_pages; } - rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum, - start_pfn, size_pages); + if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn) + continue; + nr_pages = (start_pfn + size_pages > zone_end_pfn) ? + zone_end_pfn - start_pfn : size_pages; + rc = __add_pages(nid, zone, start_pfn, nr_pages); if (rc) break; start_pfn += nr_pages; size_pages -= nr_pages; + if (!size_pages) + break; } if (rc) vmem_remove_mapping(start, size); diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 16f4c3960b87..9a4de4599c7b 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -13,7 +13,7 @@ #include <linux/init.h> #include <asm/processor.h> -static int __s390_backtrace(void *data, unsigned long address) +static int __s390_backtrace(void *data, unsigned long address, int reliable) { unsigned int *depth = data; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 7350c8bc13a2..6b2f72f523b9 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -423,7 +423,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg, dma_addr_t dma_addr_base, dma_addr; int flags = ZPCI_PTE_VALID; struct scatterlist *s; - unsigned long pa; + unsigned long pa = 0; int ret; size = PAGE_ALIGN(size); diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h index a6cfdabb6054..5b0ed48e5b0c 100644 --- a/arch/sparc/include/asm/cpudata_64.h +++ b/arch/sparc/include/asm/cpudata_64.h @@ -24,9 +24,10 @@ typedef struct { unsigned int icache_line_size; unsigned int ecache_size; unsigned int ecache_line_size; - unsigned short sock_id; + unsigned short sock_id; /* physical package */ unsigned short core_id; - int proc_id; + unsigned short max_cache_id; /* groupings of highest shared cache */ + unsigned short proc_id; /* strand (aka HW thread) id */ } cpuinfo_sparc; DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data); diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index d9c5876c6121..8011e79f59c9 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -134,7 +134,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw) *(volatile __u32 *)&lp->lock = ~0U; } -static void inline arch_write_unlock(arch_rwlock_t *lock) +static inline void arch_write_unlock(arch_rwlock_t *lock) { __asm__ __volatile__( " st %%g0, [%0]" diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 87990b7c6b0d..07c9f2e9bf57 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -96,7 +96,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long fla /* Multi-reader locks, these are much saner than the 32-bit Sparc ones... */ -static void inline arch_read_lock(arch_rwlock_t *lock) +static inline void arch_read_lock(arch_rwlock_t *lock) { unsigned long tmp1, tmp2; @@ -119,7 +119,7 @@ static void inline arch_read_lock(arch_rwlock_t *lock) : "memory"); } -static int inline arch_read_trylock(arch_rwlock_t *lock) +static inline int arch_read_trylock(arch_rwlock_t *lock) { int tmp1, tmp2; @@ -140,7 +140,7 @@ static int inline arch_read_trylock(arch_rwlock_t *lock) return tmp1; } -static void inline arch_read_unlock(arch_rwlock_t *lock) +static inline void arch_read_unlock(arch_rwlock_t *lock) { unsigned long tmp1, tmp2; @@ -156,7 +156,7 @@ static void inline arch_read_unlock(arch_rwlock_t *lock) : "memory"); } -static void inline arch_write_lock(arch_rwlock_t *lock) +static inline void arch_write_lock(arch_rwlock_t *lock) { unsigned long mask, tmp1, tmp2; @@ -181,7 +181,7 @@ static void inline arch_write_lock(arch_rwlock_t *lock) : "memory"); } -static void inline arch_write_unlock(arch_rwlock_t *lock) +static inline void arch_write_unlock(arch_rwlock_t *lock) { __asm__ __volatile__( " stw %%g0, [%0]" @@ -190,7 +190,7 @@ static void inline arch_write_unlock(arch_rwlock_t *lock) : "memory"); } -static int inline arch_write_trylock(arch_rwlock_t *lock) +static inline int arch_write_trylock(arch_rwlock_t *lock) { unsigned long mask, tmp1, tmp2, result; diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index bec481aaca16..7b4898a36eee 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -44,14 +44,20 @@ int __node_distance(int, int); #define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id) #define topology_core_id(cpu) (cpu_data(cpu).core_id) #define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu]) +#define topology_core_cache_cpumask(cpu) (&cpu_core_sib_cache_map[cpu]) #define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) #endif /* CONFIG_SMP */ extern cpumask_t cpu_core_map[NR_CPUS]; extern cpumask_t cpu_core_sib_map[NR_CPUS]; +extern cpumask_t cpu_core_sib_cache_map[NR_CPUS]; + +/** + * Return cores that shares the last level cache. + */ static inline const struct cpumask *cpu_coregroup_mask(int cpu) { - return &cpu_core_map[cpu]; + return &cpu_core_sib_cache_map[cpu]; } #endif /* _ASM_SPARC64_TOPOLOGY_H */ diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index b68acc563235..5373136c412b 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -82,7 +82,6 @@ static inline int access_ok(int type, const void __user * addr, unsigned long si return 1; } -void __ret_efault(void); void __retl_efault(void); /* Uh, these should become the main single-value transfer routines.. @@ -189,55 +188,34 @@ int __get_user_bad(void); unsigned long __must_check ___copy_from_user(void *to, const void __user *from, unsigned long size); -unsigned long copy_from_user_fixup(void *to, const void __user *from, - unsigned long size); static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long size) { - unsigned long ret; - check_object_size(to, size, false); - ret = ___copy_from_user(to, from, size); - if (unlikely(ret)) - ret = copy_from_user_fixup(to, from, size); - - return ret; + return ___copy_from_user(to, from, size); } #define __copy_from_user copy_from_user unsigned long __must_check ___copy_to_user(void __user *to, const void *from, unsigned long size); -unsigned long copy_to_user_fixup(void __user *to, const void *from, - unsigned long size); static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long size) { - unsigned long ret; - 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; + return ___copy_to_user(to, from, size); } #define __copy_to_user copy_to_user unsigned long __must_check ___copy_in_user(void __user *to, const void __user *from, unsigned long size); -unsigned long copy_in_user_fixup(void __user *to, void __user *from, - unsigned long size); static inline unsigned long __must_check copy_in_user(void __user *to, void __user *from, unsigned long size) { - unsigned long ret = ___copy_in_user(to, from, size); - - if (unlikely(ret)) - ret = copy_in_user_fixup(to, from, size); - return ret; + return ___copy_in_user(to, from, size); } #define __copy_in_user copy_in_user diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index beba6c11554c..6aa3da152c20 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -926,48 +926,11 @@ tlb_type: .word 0 /* Must NOT end up in BSS */ EXPORT_SYMBOL(tlb_type) .section ".fixup",#alloc,#execinstr - .globl __ret_efault, __retl_efault, __ret_one, __retl_one -ENTRY(__ret_efault) - ret - restore %g0, -EFAULT, %o0 -ENDPROC(__ret_efault) -EXPORT_SYMBOL(__ret_efault) - ENTRY(__retl_efault) retl mov -EFAULT, %o0 ENDPROC(__retl_efault) -ENTRY(__retl_one) - retl - mov 1, %o0 -ENDPROC(__retl_one) - -ENTRY(__retl_one_fp) - VISExitHalf - retl - mov 1, %o0 -ENDPROC(__retl_one_fp) - -ENTRY(__ret_one_asi) - wr %g0, ASI_AIUS, %asi - ret - restore %g0, 1, %o0 -ENDPROC(__ret_one_asi) - -ENTRY(__retl_one_asi) - wr %g0, ASI_AIUS, %asi - retl - mov 1, %o0 -ENDPROC(__retl_one_asi) - -ENTRY(__retl_one_asi_fp) - wr %g0, ASI_AIUS, %asi - VISExitHalf - retl - mov 1, %o0 -ENDPROC(__retl_one_asi_fp) - ENTRY(__retl_o1) retl mov %o1, %o0 diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c index 59bbeff55024..07933b9e9ce0 100644 --- a/arch/sparc/kernel/jump_label.c +++ b/arch/sparc/kernel/jump_label.c @@ -13,19 +13,30 @@ void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - u32 val; u32 *insn = (u32 *) (unsigned long) entry->code; + u32 val; if (type == JUMP_LABEL_JMP) { s32 off = (s32)entry->target - (s32)entry->code; + bool use_v9_branch = false; + + BUG_ON(off & 3); #ifdef CONFIG_SPARC64 - /* ba,pt %xcc, . + (off << 2) */ - val = 0x10680000 | ((u32) off >> 2); -#else - /* ba . + (off << 2) */ - val = 0x10800000 | ((u32) off >> 2); + if (off <= 0xfffff && off >= -0x100000) + use_v9_branch = true; #endif + if (use_v9_branch) { + /* WDISP19 - target is . + immed << 2 */ + /* ba,pt %xcc, . + off */ + val = 0x10680000 | (((u32) off >> 2) & 0x7ffff); + } else { + /* WDISP22 - target is . + immed << 2 */ + BUG_ON(off > 0x7fffff); + BUG_ON(off < -0x800000); + /* ba . + off */ + val = 0x10800000 | (((u32) off >> 2) & 0x3fffff); + } } else { val = 0x01000000; } diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 11228861d9b4..8a6982dfd733 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -645,13 +645,20 @@ static void __mark_core_id(struct mdesc_handle *hp, u64 node, cpu_data(*id).core_id = core_id; } -static void __mark_sock_id(struct mdesc_handle *hp, u64 node, - int sock_id) +static void __mark_max_cache_id(struct mdesc_handle *hp, u64 node, + int max_cache_id) { const u64 *id = mdesc_get_property(hp, node, "id", NULL); - if (*id < num_possible_cpus()) - cpu_data(*id).sock_id = sock_id; + if (*id < num_possible_cpus()) { + cpu_data(*id).max_cache_id = max_cache_id; + + /** + * On systems without explicit socket descriptions socket + * is max_cache_id + */ + cpu_data(*id).sock_id = max_cache_id; + } } static void mark_core_ids(struct mdesc_handle *hp, u64 mp, @@ -660,10 +667,11 @@ static void mark_core_ids(struct mdesc_handle *hp, u64 mp, find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10); } -static void mark_sock_ids(struct mdesc_handle *hp, u64 mp, - int sock_id) +static void mark_max_cache_ids(struct mdesc_handle *hp, u64 mp, + int max_cache_id) { - find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10); + find_back_node_value(hp, mp, "cpu", __mark_max_cache_id, + max_cache_id, 10); } static void set_core_ids(struct mdesc_handle *hp) @@ -694,14 +702,15 @@ static void set_core_ids(struct mdesc_handle *hp) } } -static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level) +static int set_max_cache_ids_by_cache(struct mdesc_handle *hp, int level) { u64 mp; int idx = 1; int fnd = 0; - /* Identify unique sockets by looking for cpus backpointed to by - * shared level n caches. + /** + * Identify unique highest level of shared cache by looking for cpus + * backpointed to by shared level N caches. */ mdesc_for_each_node_by_name(hp, mp, "cache") { const u64 *cur_lvl; @@ -709,8 +718,7 @@ static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level) cur_lvl = mdesc_get_property(hp, mp, "level", NULL); if (*cur_lvl != level) continue; - - mark_sock_ids(hp, mp, idx); + mark_max_cache_ids(hp, mp, idx); idx++; fnd = 1; } @@ -745,15 +753,17 @@ static void set_sock_ids(struct mdesc_handle *hp) { u64 mp; - /* If machine description exposes sockets data use it. - * Otherwise fallback to use shared L3 or L2 caches. + /** + * Find the highest level of shared cache which pre-T7 is also + * the socket. */ + if (!set_max_cache_ids_by_cache(hp, 3)) + set_max_cache_ids_by_cache(hp, 2); + + /* If machine description exposes sockets data use it.*/ mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets"); if (mp != MDESC_NODE_NULL) - return set_sock_ids_by_socket(hp, mp); - - if (!set_sock_ids_by_cache(hp, 3)) - set_sock_ids_by_cache(hp, 2); + set_sock_ids_by_socket(hp, mp); } static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index d3035ba6cd31..8182f7caf5b1 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -63,9 +63,13 @@ cpumask_t cpu_core_map[NR_CPUS] __read_mostly = cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = CPU_MASK_NONE }; +cpumask_t cpu_core_sib_cache_map[NR_CPUS] __read_mostly = { + [0 ... NR_CPUS - 1] = CPU_MASK_NONE }; + EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); EXPORT_SYMBOL(cpu_core_map); EXPORT_SYMBOL(cpu_core_sib_map); +EXPORT_SYMBOL(cpu_core_sib_cache_map); static cpumask_t smp_commenced_mask; @@ -1265,6 +1269,10 @@ void smp_fill_in_sib_core_maps(void) unsigned int j; for_each_present_cpu(j) { + if (cpu_data(i).max_cache_id == + cpu_data(j).max_cache_id) + cpumask_set_cpu(j, &cpu_core_sib_cache_map[i]); + if (cpu_data(i).sock_id == cpu_data(j).sock_id) cpumask_set_cpu(j, &cpu_core_sib_map[i]); } diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S index b7d0bd6b1406..69a439fa2fc1 100644 --- a/arch/sparc/lib/GENcopy_from_user.S +++ b/arch/sparc/lib/GENcopy_from_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S index 780550e1afc7..9947427ce354 100644 --- a/arch/sparc/lib/GENcopy_to_user.S +++ b/arch/sparc/lib/GENcopy_to_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/GENmemcpy.S b/arch/sparc/lib/GENmemcpy.S index 89358ee94851..059ea24ad73d 100644 --- a/arch/sparc/lib/GENmemcpy.S +++ b/arch/sparc/lib/GENmemcpy.S @@ -4,21 +4,18 @@ */ #ifdef __KERNEL__ +#include <linux/linkage.h> #define GLOBAL_SPARE %g7 #else #define GLOBAL_SPARE %g5 #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST(x,y) x #endif #ifndef LOAD @@ -45,6 +42,29 @@ .register %g3,#scratch .text + +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +ENTRY(GEN_retl_o4_1) + add %o4, %o2, %o4 + retl + add %o4, 1, %o0 +ENDPROC(GEN_retl_o4_1) +ENTRY(GEN_retl_g1_8) + add %g1, %o2, %g1 + retl + add %g1, 8, %o0 +ENDPROC(GEN_retl_g1_8) +ENTRY(GEN_retl_o2_4) + retl + add %o2, 4, %o0 +ENDPROC(GEN_retl_o2_4) +ENTRY(GEN_retl_o2_1) + retl + add %o2, 1, %o0 +ENDPROC(GEN_retl_o2_1) +#endif + .align 64 .globl FUNC_NAME @@ -73,8 +93,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %g0, %o4, %o4 sub %o2, %o4, %o2 1: subcc %o4, 1, %o4 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o0)) + EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1) + EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1) add %o1, 1, %o1 bne,pt %XCC, 1b add %o0, 1, %o0 @@ -82,8 +102,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0x7, %g1 sub %o2, %g1, %o2 1: subcc %g1, 0x8, %g1 - EX_LD(LOAD(ldx, %o1, %g2)) - EX_ST(STORE(stx, %g2, %o0)) + EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8) + EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8) add %o1, 0x8, %o1 bne,pt %XCC, 1b add %o0, 0x8, %o0 @@ -100,8 +120,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 1: subcc %o2, 4, %o2 - EX_LD(LOAD(lduw, %o1, %g1)) - EX_ST(STORE(stw, %g1, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4) + EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -111,8 +131,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o1 + %o3)) + EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1) + EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 885f00e81d1a..69912d2f8b54 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -38,7 +38,7 @@ lib-$(CONFIG_SPARC64) += NG4patch.o NG4copy_page.o NG4clear_page.o NG4memset.o lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o -lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o +lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-$(CONFIG_SPARC64) += iomap.o diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index d5242b8c4f94..b79a6998d87c 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index 4e962d993b10..dcec55f254ab 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2007 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index d5f585df2f3f..c629dbd121b6 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include <linux/linkage.h> #include <asm/visasm.h> #include <asm/asi.h> #define GLOBAL_SPARE %g7 @@ -32,21 +33,17 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST_FP(x,y) x #endif #ifndef LOAD @@ -140,45 +137,110 @@ fsrc2 %x6, %f12; \ fsrc2 %x7, %f14; #define FREG_LOAD_1(base, x0) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)) + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1) #define FREG_LOAD_2(base, x0, x1) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); #define FREG_LOAD_3(base, x0, x1, x2) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); #define FREG_LOAD_4(base, x0, x1, x2, x3) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \ - EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \ - EX_LD_FP(LOAD(ldd, base + 0x30, %x6)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \ + EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1); .register %g2,#scratch .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_fp: + VISExitHalf +__restore_asi: + retl + wr %g0, ASI_AIUS, %asi +ENTRY(NG2_retl_o2) + ba,pt %xcc, __restore_asi + mov %o2, %o0 +ENDPROC(NG2_retl_o2) +ENTRY(NG2_retl_o2_plus_1) + ba,pt %xcc, __restore_asi + add %o2, 1, %o0 +ENDPROC(NG2_retl_o2_plus_1) +ENTRY(NG2_retl_o2_plus_4) + ba,pt %xcc, __restore_asi + add %o2, 4, %o0 +ENDPROC(NG2_retl_o2_plus_4) +ENTRY(NG2_retl_o2_plus_8) + ba,pt %xcc, __restore_asi + add %o2, 8, %o0 +ENDPROC(NG2_retl_o2_plus_8) +ENTRY(NG2_retl_o2_plus_o4_plus_1) + add %o4, 1, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_plus_o4_plus_1) +ENTRY(NG2_retl_o2_plus_o4_plus_8) + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_plus_o4_plus_8) +ENTRY(NG2_retl_o2_plus_o4_plus_16) + add %o4, 16, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_plus_o4_plus_16) +ENTRY(NG2_retl_o2_plus_g1_fp) + ba,pt %xcc, __restore_fp + add %o2, %g1, %o0 +ENDPROC(NG2_retl_o2_plus_g1_fp) +ENTRY(NG2_retl_o2_plus_g1_plus_64_fp) + add %g1, 64, %g1 + ba,pt %xcc, __restore_fp + add %o2, %g1, %o0 +ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp) +ENTRY(NG2_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG2_retl_o2_plus_g1_plus_1) +ENTRY(NG2_retl_o2_and_7_plus_o4) + and %o2, 7, %o2 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_and_7_plus_o4) +ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8) + and %o2, 7, %o2 + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8) +#endif + .align 64 .globl FUNC_NAME @@ -230,8 +292,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %g0, %o4, %o4 ! bytes to align dst sub %o2, %o4, %o2 1: subcc %o4, 1, %o4 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o0)) + EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1) + EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1) add %o1, 1, %o1 bne,pt %XCC, 1b add %o0, 1, %o0 @@ -281,11 +343,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop /* fall through for 0 < low bits < 8 */ 110: sub %o4, 64, %g2 - EX_LD_FP(LOAD_BLK(%g2, %f0)) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) + EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -296,10 +358,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 120: sub %o4, 56, %g2 FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -310,10 +372,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 130: sub %o4, 48, %g2 FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_6(f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -324,10 +386,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 140: sub %o4, 40, %g2 FREG_LOAD_5(%g2, f0, f2, f4, f6, f8) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_5(f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -338,10 +400,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 150: sub %o4, 32, %g2 FREG_LOAD_4(%g2, f0, f2, f4, f6) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_4(f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -352,10 +414,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 160: sub %o4, 24, %g2 FREG_LOAD_3(%g2, f0, f2, f4) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_3(f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -366,10 +428,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 170: sub %o4, 16, %g2 FREG_LOAD_2(%g2, f0, f2) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_2(f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -380,10 +442,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 180: sub %o4, 8, %g2 FREG_LOAD_1(%g2, f0) -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) - EX_LD_FP(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) + EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1) FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1) FREG_MOVE_1(f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -393,10 +455,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop 190: -1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1) subcc %g1, 64, %g1 - EX_LD_FP(LOAD_BLK(%o4, %f0)) - EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64) add %o4, 64, %o4 bne,pt %xcc, 1b LOAD(prefetch, %o4 + 64, #one_read) @@ -423,28 +485,28 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0xf, %o4 and %o2, 0xf, %o2 1: subcc %o4, 0x10, %o4 - EX_LD(LOAD(ldx, %o1, %o5)) + EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16) add %o1, 0x08, %o1 - EX_LD(LOAD(ldx, %o1, %g1)) + EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16) sub %o1, 0x08, %o1 - EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE)) + EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16) add %o1, 0x8, %o1 - EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE)) + EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8) bgu,pt %XCC, 1b add %o1, 0x8, %o1 73: andcc %o2, 0x8, %g0 be,pt %XCC, 1f nop sub %o2, 0x8, %o2 - EX_LD(LOAD(ldx, %o1, %o5)) - EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8) + EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8) add %o1, 0x8, %o1 1: andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop sub %o2, 0x4, %o2 - EX_LD(LOAD(lduw, %o1, %o5)) - EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4) + EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4) add %o1, 0x4, %o1 1: cmp %o2, 0 be,pt %XCC, 85f @@ -460,8 +522,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g1, %o2 1: subcc %g1, 1, %g1 - EX_LD(LOAD(ldub, %o1, %o5)) - EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1) + EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1) bgu,pt %icc, 1b add %o1, 1, %o1 @@ -477,16 +539,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 8: mov 64, GLOBAL_SPARE andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1, %g2)) + EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2) sub GLOBAL_SPARE, %g1, GLOBAL_SPARE andn %o2, 0x7, %o4 sllx %g2, %g1, %g2 1: add %o1, 0x8, %o1 - EX_LD(LOAD(ldx, %o1, %g3)) + EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4) subcc %o4, 0x8, %o4 srlx %g3, GLOBAL_SPARE, %o5 or %o5, %g2, %o5 - EX_ST(STORE(stx, %o5, %o0)) + EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -506,8 +568,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 1: subcc %o2, 4, %o2 - EX_LD(LOAD(lduw, %o1, %g1)) - EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4) + EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -517,8 +579,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE)) + EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1) + EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S index 2e8ee7ad07a9..16a286c1a528 100644 --- a/arch/sparc/lib/NG4copy_from_user.S +++ b/arch/sparc/lib/NG4copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2012 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x, y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S index be0bf4590df8..6b0276ffc858 100644 --- a/arch/sparc/lib/NG4copy_to_user.S +++ b/arch/sparc/lib/NG4copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 2012 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi;\ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_asi_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 8e13ee1f4454..75bb93b1437f 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include <linux/linkage.h> #include <asm/visasm.h> #include <asm/asi.h> #define GLOBAL_SPARE %g7 @@ -46,22 +47,19 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x +#define EX_ST_FP(x,y) x #endif -#ifndef EX_RETVAL -#define EX_RETVAL(x) x -#endif #ifndef LOAD #define LOAD(type,addr,dest) type [addr], dest @@ -94,6 +92,158 @@ .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_asi_fp: + VISExitHalf +__restore_asi: + retl + wr %g0, ASI_AIUS, %asi + +ENTRY(NG4_retl_o2) + ba,pt %xcc, __restore_asi + mov %o2, %o0 +ENDPROC(NG4_retl_o2) +ENTRY(NG4_retl_o2_plus_1) + ba,pt %xcc, __restore_asi + add %o2, 1, %o0 +ENDPROC(NG4_retl_o2_plus_1) +ENTRY(NG4_retl_o2_plus_4) + ba,pt %xcc, __restore_asi + add %o2, 4, %o0 +ENDPROC(NG4_retl_o2_plus_4) +ENTRY(NG4_retl_o2_plus_o5) + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5) +ENTRY(NG4_retl_o2_plus_o5_plus_4) + add %o5, 4, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_4) +ENTRY(NG4_retl_o2_plus_o5_plus_8) + add %o5, 8, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_8) +ENTRY(NG4_retl_o2_plus_o5_plus_16) + add %o5, 16, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_16) +ENTRY(NG4_retl_o2_plus_o5_plus_24) + add %o5, 24, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_24) +ENTRY(NG4_retl_o2_plus_o5_plus_32) + add %o5, 32, %o5 + ba,pt %xcc, __restore_asi + add %o2, %o5, %o0 +ENDPROC(NG4_retl_o2_plus_o5_plus_32) +ENTRY(NG4_retl_o2_plus_g1) + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG4_retl_o2_plus_g1) +ENTRY(NG4_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG4_retl_o2_plus_g1_plus_1) +ENTRY(NG4_retl_o2_plus_g1_plus_8) + add %g1, 8, %g1 + ba,pt %xcc, __restore_asi + add %o2, %g1, %o0 +ENDPROC(NG4_retl_o2_plus_g1_plus_8) +ENTRY(NG4_retl_o2_plus_o4) + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4) +ENTRY(NG4_retl_o2_plus_o4_plus_8) + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_8) +ENTRY(NG4_retl_o2_plus_o4_plus_16) + add %o4, 16, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_16) +ENTRY(NG4_retl_o2_plus_o4_plus_24) + add %o4, 24, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_24) +ENTRY(NG4_retl_o2_plus_o4_plus_32) + add %o4, 32, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_32) +ENTRY(NG4_retl_o2_plus_o4_plus_40) + add %o4, 40, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_40) +ENTRY(NG4_retl_o2_plus_o4_plus_48) + add %o4, 48, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_48) +ENTRY(NG4_retl_o2_plus_o4_plus_56) + add %o4, 56, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_56) +ENTRY(NG4_retl_o2_plus_o4_plus_64) + add %o4, 64, %o4 + ba,pt %xcc, __restore_asi + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_64) +ENTRY(NG4_retl_o2_plus_o4_fp) + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_8_fp) + add %o4, 8, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_16_fp) + add %o4, 16, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_24_fp) + add %o4, 24, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_32_fp) + add %o4, 32, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_40_fp) + add %o4, 40, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_48_fp) + add %o4, 48, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_56_fp) + add %o4, 56, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp) +ENTRY(NG4_retl_o2_plus_o4_plus_64_fp) + add %o4, 64, %o4 + ba,pt %xcc, __restore_asi_fp + add %o2, %o4, %o0 +ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp) +#endif .align 64 .globl FUNC_NAME @@ -124,12 +274,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %g1, 51f sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2)) + +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1) add %o1, 1, %o1 subcc %g1, 1, %g1 add %o0, 1, %o0 bne,pt %icc, 1b - EX_ST(STORE(stb, %g2, %o0 - 0x01)) + EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1) 51: LOAD(prefetch, %o1 + 0x040, #n_reads_strong) LOAD(prefetch, %o1 + 0x080, #n_reads_strong) @@ -154,43 +305,43 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %g1, .Llarge_aligned sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1) add %o1, 8, %o1 subcc %g1, 8, %g1 add %o0, 8, %o0 bne,pt %icc, 1b - EX_ST(STORE(stx, %g2, %o0 - 0x08)) + EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8) .Llarge_aligned: /* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */ andn %o2, 0x3f, %o4 sub %o2, %o4, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4) add %o1, 0x40, %o1 - EX_LD(LOAD(ldx, %o1 - 0x38, %g2)) + EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4) subcc %o4, 0x40, %o4 - EX_LD(LOAD(ldx, %o1 - 0x30, %g3)) - EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE)) - EX_LD(LOAD(ldx, %o1 - 0x20, %o5)) - EX_ST(STORE_INIT(%g1, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64) + EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64) + EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64) + EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(%g2, %o0)) + EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56) add %o0, 0x08, %o0 - EX_LD(LOAD(ldx, %o1 - 0x18, %g2)) - EX_ST(STORE_INIT(%g3, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48) + EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48) add %o0, 0x08, %o0 - EX_LD(LOAD(ldx, %o1 - 0x10, %g3)) - EX_ST(STORE_INIT(GLOBAL_SPARE, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40) + EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40) add %o0, 0x08, %o0 - EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE)) - EX_ST(STORE_INIT(%o5, %o0)) + EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32) + EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(%g2, %o0)) + EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(%g3, %o0)) + EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16) add %o0, 0x08, %o0 - EX_ST(STORE_INIT(GLOBAL_SPARE, %o0)) + EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8) add %o0, 0x08, %o0 bne,pt %icc, 1b LOAD(prefetch, %o1 + 0x200, #n_reads_strong) @@ -216,17 +367,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %o4, %o2 alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 - EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0)) -1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2)) + EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4) +1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4) subcc %o4, 0x40, %o4 - EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4)) - EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6)) - EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8)) - EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10)) - EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12)) - EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14)) + EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64) faligndata %f0, %f2, %f16 - EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0)) + EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64) faligndata %f2, %f4, %f18 add %g1, 0x40, %g1 faligndata %f4, %f6, %f20 @@ -235,14 +386,14 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST_FP(STORE(std, %f16, %o0 + 0x00)) - EX_ST_FP(STORE(std, %f18, %o0 + 0x08)) - EX_ST_FP(STORE(std, %f20, %o0 + 0x10)) - EX_ST_FP(STORE(std, %f22, %o0 + 0x18)) - EX_ST_FP(STORE(std, %f24, %o0 + 0x20)) - EX_ST_FP(STORE(std, %f26, %o0 + 0x28)) - EX_ST_FP(STORE(std, %f28, %o0 + 0x30)) - EX_ST_FP(STORE(std, %f30, %o0 + 0x38)) + EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64) + EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56) + EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48) + EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40) + EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32) + EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24) + EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16) + EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8) add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) @@ -270,37 +421,38 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andncc %o2, 0x20 - 1, %o5 be,pn %icc, 2f sub %o2, %o5, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1)) - EX_LD(LOAD(ldx, %o1 + 0x08, %g2)) - EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE)) - EX_LD(LOAD(ldx, %o1 + 0x18, %o4)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5) add %o1, 0x20, %o1 subcc %o5, 0x20, %o5 - EX_ST(STORE(stx, %g1, %o0 + 0x00)) - EX_ST(STORE(stx, %g2, %o0 + 0x08)) - EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10)) - EX_ST(STORE(stx, %o4, %o0 + 0x18)) + EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32) + EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24) + EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24) + EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8) bne,pt %icc, 1b add %o0, 0x20, %o0 2: andcc %o2, 0x18, %o5 be,pt %icc, 3f sub %o2, %o5, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1)) + +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5) add %o1, 0x08, %o1 add %o0, 0x08, %o0 subcc %o5, 0x08, %o5 bne,pt %icc, 1b - EX_ST(STORE(stx, %g1, %o0 - 0x08)) + EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8) 3: brz,pt %o2, .Lexit cmp %o2, 0x04 bl,pn %icc, .Ltiny nop - EX_LD(LOAD(lduw, %o1 + 0x00, %g1)) + EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2) add %o1, 0x04, %o1 add %o0, 0x04, %o0 subcc %o2, 0x04, %o2 bne,pn %icc, .Ltiny - EX_ST(STORE(stw, %g1, %o0 - 0x04)) + EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4) ba,a,pt %icc, .Lexit .Lmedium_unaligned: /* First get dest 8 byte aligned. */ @@ -309,12 +461,12 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ brz,pt %g1, 2f sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2)) +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1) add %o1, 1, %o1 subcc %g1, 1, %g1 add %o0, 1, %o0 bne,pt %icc, 1b - EX_ST(STORE(stb, %g2, %o0 - 0x01)) + EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1) 2: and %o1, 0x7, %g1 brz,pn %g1, .Lmedium_noprefetch @@ -322,16 +474,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov 64, %g2 sub %g2, %g1, %g2 andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1 + 0x00, %o4)) + EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2) sllx %o4, %g1, %o4 andn %o2, 0x08 - 1, %o5 sub %o2, %o5, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3)) +1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5) add %o1, 0x08, %o1 subcc %o5, 0x08, %o5 srlx %g3, %g2, GLOBAL_SPARE or GLOBAL_SPARE, %o4, GLOBAL_SPARE - EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00)) + EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8) add %o0, 0x08, %o0 bne,pt %icc, 1b sllx %g3, %g1, %o4 @@ -342,17 +494,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ ba,pt %icc, .Lsmall_unaligned .Ltiny: - EX_LD(LOAD(ldub, %o1 + 0x00, %g1)) + EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2) subcc %o2, 1, %o2 be,pn %icc, .Lexit - EX_ST(STORE(stb, %g1, %o0 + 0x00)) - EX_LD(LOAD(ldub, %o1 + 0x01, %g1)) + EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1) + EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2) subcc %o2, 1, %o2 be,pn %icc, .Lexit - EX_ST(STORE(stb, %g1, %o0 + 0x01)) - EX_LD(LOAD(ldub, %o1 + 0x02, %g1)) + EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1) + EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2) ba,pt %icc, .Lexit - EX_ST(STORE(stb, %g1, %o0 + 0x02)) + EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2) .Lsmall: andcc %g2, 0x3, %g0 @@ -360,22 +512,22 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0x4 - 1, %o5 sub %o2, %o5, %o2 1: - EX_LD(LOAD(lduw, %o1 + 0x00, %g1)) + EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5) add %o1, 0x04, %o1 subcc %o5, 0x04, %o5 add %o0, 0x04, %o0 bne,pt %icc, 1b - EX_ST(STORE(stw, %g1, %o0 - 0x04)) + EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4) brz,pt %o2, .Lexit nop ba,a,pt %icc, .Ltiny .Lsmall_unaligned: -1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1)) +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2) add %o1, 1, %o1 add %o0, 1, %o0 subcc %o2, 1, %o2 bne,pt %icc, 1b - EX_ST(STORE(stb, %g1, %o0 - 0x01)) + EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1) ba,a,pt %icc, .Lexit .size FUNC_NAME, .-FUNC_NAME diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S index 5d1e4d1ac21e..9cd42fcbc781 100644 --- a/arch/sparc/lib/NGcopy_from_user.S +++ b/arch/sparc/lib/NGcopy_from_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __ret_one_asi;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S index ff630dcb273c..5c358afd464e 100644 --- a/arch/sparc/lib/NGcopy_to_user.S +++ b/arch/sparc/lib/NGcopy_to_user.S @@ -3,11 +3,11 @@ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __ret_one_asi;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S index 96a14caf6966..d88c4ed50a00 100644 --- a/arch/sparc/lib/NGmemcpy.S +++ b/arch/sparc/lib/NGmemcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include <linux/linkage.h> #include <asm/asi.h> #include <asm/thread_info.h> #define GLOBAL_SPARE %g7 @@ -27,15 +28,11 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST(x,y) x #endif #ifndef LOAD @@ -79,6 +76,92 @@ .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_asi: + ret + wr %g0, ASI_AIUS, %asi + restore +ENTRY(NG_ret_i2_plus_i4_plus_1) + ba,pt %xcc, __restore_asi + add %i2, %i5, %i0 +ENDPROC(NG_ret_i2_plus_i4_plus_1) +ENTRY(NG_ret_i2_plus_g1) + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1) +ENTRY(NG_ret_i2_plus_g1_minus_8) + sub %g1, 8, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_8) +ENTRY(NG_ret_i2_plus_g1_minus_16) + sub %g1, 16, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_16) +ENTRY(NG_ret_i2_plus_g1_minus_24) + sub %g1, 24, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_24) +ENTRY(NG_ret_i2_plus_g1_minus_32) + sub %g1, 32, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_32) +ENTRY(NG_ret_i2_plus_g1_minus_40) + sub %g1, 40, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_40) +ENTRY(NG_ret_i2_plus_g1_minus_48) + sub %g1, 48, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_48) +ENTRY(NG_ret_i2_plus_g1_minus_56) + sub %g1, 56, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_minus_56) +ENTRY(NG_ret_i2_plus_i4) + ba,pt %xcc, __restore_asi + add %i2, %i4, %i0 +ENDPROC(NG_ret_i2_plus_i4) +ENTRY(NG_ret_i2_plus_i4_minus_8) + sub %i4, 8, %i4 + ba,pt %xcc, __restore_asi + add %i2, %i4, %i0 +ENDPROC(NG_ret_i2_plus_i4_minus_8) +ENTRY(NG_ret_i2_plus_8) + ba,pt %xcc, __restore_asi + add %i2, 8, %i0 +ENDPROC(NG_ret_i2_plus_8) +ENTRY(NG_ret_i2_plus_4) + ba,pt %xcc, __restore_asi + add %i2, 4, %i0 +ENDPROC(NG_ret_i2_plus_4) +ENTRY(NG_ret_i2_plus_1) + ba,pt %xcc, __restore_asi + add %i2, 1, %i0 +ENDPROC(NG_ret_i2_plus_1) +ENTRY(NG_ret_i2_plus_g1_plus_1) + add %g1, 1, %g1 + ba,pt %xcc, __restore_asi + add %i2, %g1, %i0 +ENDPROC(NG_ret_i2_plus_g1_plus_1) +ENTRY(NG_ret_i2) + ba,pt %xcc, __restore_asi + mov %i2, %i0 +ENDPROC(NG_ret_i2) +ENTRY(NG_ret_i2_and_7_plus_i4) + and %i2, 7, %i2 + ba,pt %xcc, __restore_asi + add %i2, %i4, %i0 +ENDPROC(NG_ret_i2_and_7_plus_i4) +#endif + .align 64 .globl FUNC_NAME @@ -126,8 +209,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ sub %g0, %i4, %i4 ! bytes to align dst sub %i2, %i4, %i2 1: subcc %i4, 1, %i4 - EX_LD(LOAD(ldub, %i1, %g1)) - EX_ST(STORE(stb, %g1, %o0)) + EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1) + EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1) add %i1, 1, %i1 bne,pt %XCC, 1b add %o0, 1, %o0 @@ -160,7 +243,7 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ and %i4, 0x7, GLOBAL_SPARE sll GLOBAL_SPARE, 3, GLOBAL_SPARE mov 64, %i5 - EX_LD(LOAD_TWIN(%i1, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1) sub %i5, GLOBAL_SPARE, %i5 mov 16, %o4 mov 32, %o5 @@ -178,31 +261,31 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ srlx WORD3, PRE_SHIFT, TMP; \ or WORD2, TMP, WORD2; -8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3)) +8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1) MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1) LOAD(prefetch, %i1 + %i3, #one_read) - EX_ST(STORE_INIT(%g2, %o0 + 0x00)) - EX_ST(STORE_INIT(%g3, %o0 + 0x08)) + EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1) + EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) - EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16) MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o2, %o0 + 0x10)) - EX_ST(STORE_INIT(%o3, %o0 + 0x18)) + EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) - EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) + EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32) MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%g2, %o0 + 0x20)) - EX_ST(STORE_INIT(%g3, %o0 + 0x28)) + EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) - EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48) add %i1, 64, %i1 MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o2, %o0 + 0x30)) - EX_ST(STORE_INIT(%o3, %o0 + 0x38)) + EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 8b @@ -211,31 +294,31 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ ba,pt %XCC, 60f add %i1, %i4, %i1 -9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3)) +9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1) MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1) LOAD(prefetch, %i1 + %i3, #one_read) - EX_ST(STORE_INIT(%g3, %o0 + 0x00)) - EX_ST(STORE_INIT(%o2, %o0 + 0x08)) + EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1) + EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) - EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16) MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o3, %o0 + 0x10)) - EX_ST(STORE_INIT(%g2, %o0 + 0x18)) + EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) - EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) + EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32) MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%g3, %o0 + 0x20)) - EX_ST(STORE_INIT(%o2, %o0 + 0x28)) + EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) - EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3)) + EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48) add %i1, 64, %i1 MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1) - EX_ST(STORE_INIT(%o3, %o0 + 0x30)) - EX_ST(STORE_INIT(%g2, %o0 + 0x38)) + EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 9b @@ -249,25 +332,25 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ * one twin load ahead, then add 8 back into source when * we finish the loop. */ - EX_LD(LOAD_TWIN(%i1, %o4, %o5)) + EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1) mov 16, %o7 mov 32, %g2 mov 48, %g3 mov 64, %o1 -1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) +1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1) LOAD(prefetch, %i1 + %o1, #one_read) - EX_ST(STORE_INIT(%o5, %o0 + 0x00)) ! initializes cache line - EX_ST(STORE_INIT(%o2, %o0 + 0x08)) - EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5)) - EX_ST(STORE_INIT(%o3, %o0 + 0x10)) - EX_ST(STORE_INIT(%o4, %o0 + 0x18)) - EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3)) - EX_ST(STORE_INIT(%o5, %o0 + 0x20)) - EX_ST(STORE_INIT(%o2, %o0 + 0x28)) - EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5)) + EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line + EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) + EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) + EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) + EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48) add %i1, 64, %i1 - EX_ST(STORE_INIT(%o3, %o0 + 0x30)) - EX_ST(STORE_INIT(%o4, %o0 + 0x38)) + EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 1b add %o0, 64, %o0 @@ -282,20 +365,20 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ mov 32, %g2 mov 48, %g3 mov 64, %o1 -1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5)) - EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3)) +1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1) + EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1) LOAD(prefetch, %i1 + %o1, #one_read) - EX_ST(STORE_INIT(%o4, %o0 + 0x00)) ! initializes cache line - EX_ST(STORE_INIT(%o5, %o0 + 0x08)) - EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5)) - EX_ST(STORE_INIT(%o2, %o0 + 0x10)) - EX_ST(STORE_INIT(%o3, %o0 + 0x18)) - EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3)) + EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line + EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8) + EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16) + EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24) + EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32) add %i1, 64, %i1 - EX_ST(STORE_INIT(%o4, %o0 + 0x20)) - EX_ST(STORE_INIT(%o5, %o0 + 0x28)) - EX_ST(STORE_INIT(%o2, %o0 + 0x30)) - EX_ST(STORE_INIT(%o3, %o0 + 0x38)) + EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32) + EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40) + EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48) + EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56) subcc %g1, 64, %g1 bne,pt %XCC, 1b add %o0, 64, %o0 @@ -321,28 +404,28 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ andn %i2, 0xf, %i4 and %i2, 0xf, %i2 1: subcc %i4, 0x10, %i4 - EX_LD(LOAD(ldx, %i1, %o4)) + EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4) add %i1, 0x08, %i1 - EX_LD(LOAD(ldx, %i1, %g1)) + EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4) sub %i1, 0x08, %i1 - EX_ST(STORE(stx, %o4, %i1 + %i3)) + EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4) add %i1, 0x8, %i1 - EX_ST(STORE(stx, %g1, %i1 + %i3)) + EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8) bgu,pt %XCC, 1b add %i1, 0x8, %i1 73: andcc %i2, 0x8, %g0 be,pt %XCC, 1f nop sub %i2, 0x8, %i2 - EX_LD(LOAD(ldx, %i1, %o4)) - EX_ST(STORE(stx, %o4, %i1 + %i3)) + EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8) + EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8) add %i1, 0x8, %i1 1: andcc %i2, 0x4, %g0 be,pt %XCC, 1f nop sub %i2, 0x4, %i2 - EX_LD(LOAD(lduw, %i1, %i5)) - EX_ST(STORE(stw, %i5, %i1 + %i3)) + EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4) + EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4) add %i1, 0x4, %i1 1: cmp %i2, 0 be,pt %XCC, 85f @@ -358,8 +441,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ sub %i2, %g1, %i2 1: subcc %g1, 1, %g1 - EX_LD(LOAD(ldub, %i1, %i5)) - EX_ST(STORE(stb, %i5, %i1 + %i3)) + EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1) + EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1) bgu,pt %icc, 1b add %i1, 1, %i1 @@ -375,16 +458,16 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ 8: mov 64, %i3 andn %i1, 0x7, %i1 - EX_LD(LOAD(ldx, %i1, %g2)) + EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2) sub %i3, %g1, %i3 andn %i2, 0x7, %i4 sllx %g2, %g1, %g2 1: add %i1, 0x8, %i1 - EX_LD(LOAD(ldx, %i1, %g3)) + EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4) subcc %i4, 0x8, %i4 srlx %g3, %i3, %i5 or %i5, %g2, %i5 - EX_ST(STORE(stx, %i5, %o0)) + EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -404,8 +487,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ 1: subcc %i2, 4, %i2 - EX_LD(LOAD(lduw, %i1, %g1)) - EX_ST(STORE(stw, %g1, %i1 + %i3)) + EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4) + EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4) bgu,pt %XCC, 1b add %i1, 4, %i1 @@ -415,8 +498,8 @@ FUNC_NAME: /* %i0=dst, %i1=src, %i2=len */ .align 32 90: subcc %i2, 1, %i2 - EX_LD(LOAD(ldub, %i1, %g1)) - EX_ST(STORE(stb, %g1, %i1 + %i3)) + EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1) + EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1) bgu,pt %XCC, 90b add %i1, 1, %i1 ret diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index ecc5692fa2b4..bb6ff73229e3 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index 9eea392e44d4..ed92ce739558 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S index 97e1b211090c..4f0d50b33a72 100644 --- a/arch/sparc/lib/U1memcpy.S +++ b/arch/sparc/lib/U1memcpy.S @@ -5,6 +5,7 @@ */ #ifdef __KERNEL__ +#include <linux/linkage.h> #include <asm/visasm.h> #include <asm/asi.h> #include <asm/export.h> @@ -24,21 +25,17 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST_FP(x,y) x #endif #ifndef LOAD @@ -79,53 +76,169 @@ faligndata %f7, %f8, %f60; \ faligndata %f8, %f9, %f62; -#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \ - EX_LD_FP(LOAD_BLK(%src, %fdest)); \ - EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ - add %src, 0x40, %src; \ - subcc %len, 0x40, %len; \ - be,pn %xcc, jmptgt; \ - add %dest, 0x40, %dest; \ - -#define LOOP_CHUNK1(src, dest, len, branch_dest) \ - MAIN_LOOP_CHUNK(src, dest, f0, f48, len, branch_dest) -#define LOOP_CHUNK2(src, dest, len, branch_dest) \ - MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest) -#define LOOP_CHUNK3(src, dest, len, branch_dest) \ - MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest) +#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt) \ + EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \ + add %src, 0x40, %src; \ + subcc %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE; \ + be,pn %xcc, jmptgt; \ + add %dest, 0x40, %dest; \ + +#define LOOP_CHUNK1(src, dest, branch_dest) \ + MAIN_LOOP_CHUNK(src, dest, f0, f48, branch_dest) +#define LOOP_CHUNK2(src, dest, branch_dest) \ + MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest) +#define LOOP_CHUNK3(src, dest, branch_dest) \ + MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest) #define DO_SYNC membar #Sync; #define STORE_SYNC(dest, fsrc) \ - EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \ add %dest, 0x40, %dest; \ DO_SYNC #define STORE_JUMP(dest, fsrc, target) \ - EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp); \ add %dest, 0x40, %dest; \ ba,pt %xcc, target; \ nop; -#define FINISH_VISCHUNK(dest, f0, f1, left) \ - subcc %left, 8, %left;\ - bl,pn %xcc, 95f; \ - faligndata %f0, %f1, %f48; \ - EX_ST_FP(STORE(std, %f48, %dest)); \ +#define FINISH_VISCHUNK(dest, f0, f1) \ + subcc %g3, 8, %g3; \ + bl,pn %xcc, 95f; \ + faligndata %f0, %f1, %f48; \ + EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp); \ add %dest, 8, %dest; -#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ - subcc %left, 8, %left; \ - bl,pn %xcc, 95f; \ +#define UNEVEN_VISCHUNK_LAST(dest, f0, f1) \ + subcc %g3, 8, %g3; \ + bl,pn %xcc, 95f; \ fsrc2 %f0, %f1; -#define UNEVEN_VISCHUNK(dest, f0, f1, left) \ - UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ +#define UNEVEN_VISCHUNK(dest, f0, f1) \ + UNEVEN_VISCHUNK_LAST(dest, f0, f1) \ ba,a,pt %xcc, 93f; .register %g2,#scratch .register %g3,#scratch .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +ENTRY(U1_g1_1_fp) + VISExitHalf + add %g1, 1, %g1 + add %g1, %g2, %g1 + retl + add %g1, %o2, %o0 +ENDPROC(U1_g1_1_fp) +ENTRY(U1_g2_0_fp) + VISExitHalf + retl + add %g2, %o2, %o0 +ENDPROC(U1_g2_0_fp) +ENTRY(U1_g2_8_fp) + VISExitHalf + add %g2, 8, %g2 + retl + add %g2, %o2, %o0 +ENDPROC(U1_g2_8_fp) +ENTRY(U1_gs_0_fp) + VISExitHalf + add %GLOBAL_SPARE, %g3, %o0 + retl + add %o0, %o2, %o0 +ENDPROC(U1_gs_0_fp) +ENTRY(U1_gs_80_fp) + VISExitHalf + add %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE + add %GLOBAL_SPARE, %g3, %o0 + retl + add %o0, %o2, %o0 +ENDPROC(U1_gs_80_fp) +ENTRY(U1_gs_40_fp) + VISExitHalf + add %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE + add %GLOBAL_SPARE, %g3, %o0 + retl + add %o0, %o2, %o0 +ENDPROC(U1_gs_40_fp) +ENTRY(U1_g3_0_fp) + VISExitHalf + retl + add %g3, %o2, %o0 +ENDPROC(U1_g3_0_fp) +ENTRY(U1_g3_8_fp) + VISExitHalf + add %g3, 8, %g3 + retl + add %g3, %o2, %o0 +ENDPROC(U1_g3_8_fp) +ENTRY(U1_o2_0_fp) + VISExitHalf + retl + mov %o2, %o0 +ENDPROC(U1_o2_0_fp) +ENTRY(U1_o2_1_fp) + VISExitHalf + retl + add %o2, 1, %o0 +ENDPROC(U1_o2_1_fp) +ENTRY(U1_gs_0) + VISExitHalf + retl + add %GLOBAL_SPARE, %o2, %o0 +ENDPROC(U1_gs_0) +ENTRY(U1_gs_8) + VISExitHalf + add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE + retl + add %GLOBAL_SPARE, 0x8, %o0 +ENDPROC(U1_gs_8) +ENTRY(U1_gs_10) + VISExitHalf + add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE + retl + add %GLOBAL_SPARE, 0x10, %o0 +ENDPROC(U1_gs_10) +ENTRY(U1_o2_0) + retl + mov %o2, %o0 +ENDPROC(U1_o2_0) +ENTRY(U1_o2_8) + retl + add %o2, 8, %o0 +ENDPROC(U1_o2_8) +ENTRY(U1_o2_4) + retl + add %o2, 4, %o0 +ENDPROC(U1_o2_4) +ENTRY(U1_o2_1) + retl + add %o2, 1, %o0 +ENDPROC(U1_o2_1) +ENTRY(U1_g1_0) + retl + add %g1, %o2, %o0 +ENDPROC(U1_g1_0) +ENTRY(U1_g1_1) + add %g1, 1, %g1 + retl + add %g1, %o2, %o0 +ENDPROC(U1_g1_1) +ENTRY(U1_gs_0_o2_adj) + and %o2, 7, %o2 + retl + add %GLOBAL_SPARE, %o2, %o0 +ENDPROC(U1_gs_0_o2_adj) +ENTRY(U1_gs_8_o2_adj) + and %o2, 7, %o2 + add %GLOBAL_SPARE, 8, %GLOBAL_SPARE + retl + add %GLOBAL_SPARE, %o2, %o0 +ENDPROC(U1_gs_8_o2_adj) +#endif + .align 64 .globl FUNC_NAME @@ -167,8 +280,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp) + EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -179,20 +292,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD_FP(LOAD(ldd, %o1, %f4)) -1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST_FP(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f0 - EX_ST_FP(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -215,13 +328,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %g1, %GLOBAL_SPARE, %g1 subcc %o2, %g3, %o2 - EX_LD_FP(LOAD_BLK(%o1, %f0)) + EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp) add %o1, 0x40, %o1 add %g1, %g3, %g1 - EX_LD_FP(LOAD_BLK(%o1, %f16)) + EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp) add %o1, 0x40, %o1 sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE - EX_LD_FP(LOAD_BLK(%o1, %f32)) + EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp) add %o1, 0x40, %o1 /* There are 8 instances of the unrolled loop, @@ -241,11 +354,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f0, %f2, %f48 1: FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) @@ -262,11 +375,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 56f) 1: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f2, %f4, %f48 1: FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) @@ -283,11 +396,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 57f) 1: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f4, %f6, %f48 1: FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) @@ -304,11 +417,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 58f) 1: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f6, %f8, %f48 1: FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) @@ -325,11 +438,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 59f) 1: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f8, %f10, %f48 1: FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) @@ -346,11 +459,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 60f) 1: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f10, %f12, %f48 1: FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) @@ -367,11 +480,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 61f) 1: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f12, %f14, %f48 1: FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) @@ -388,11 +501,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ STORE_JUMP(o0, f48, 62f) 1: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30) - LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f) + LOOP_CHUNK1(o1, o0, 1f) FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) - LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f) + LOOP_CHUNK2(o1, o0, 2f) FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14) - LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f) + LOOP_CHUNK3(o1, o0, 3f) ba,pt %xcc, 1b+4 faligndata %f14, %f16, %f48 1: FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) @@ -408,53 +521,53 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) STORE_JUMP(o0, f48, 63f) -40: FINISH_VISCHUNK(o0, f0, f2, g3) -41: FINISH_VISCHUNK(o0, f2, f4, g3) -42: FINISH_VISCHUNK(o0, f4, f6, g3) -43: FINISH_VISCHUNK(o0, f6, f8, g3) -44: FINISH_VISCHUNK(o0, f8, f10, g3) -45: FINISH_VISCHUNK(o0, f10, f12, g3) -46: FINISH_VISCHUNK(o0, f12, f14, g3) -47: UNEVEN_VISCHUNK(o0, f14, f0, g3) -48: FINISH_VISCHUNK(o0, f16, f18, g3) -49: FINISH_VISCHUNK(o0, f18, f20, g3) -50: FINISH_VISCHUNK(o0, f20, f22, g3) -51: FINISH_VISCHUNK(o0, f22, f24, g3) -52: FINISH_VISCHUNK(o0, f24, f26, g3) -53: FINISH_VISCHUNK(o0, f26, f28, g3) -54: FINISH_VISCHUNK(o0, f28, f30, g3) -55: UNEVEN_VISCHUNK(o0, f30, f0, g3) -56: FINISH_VISCHUNK(o0, f32, f34, g3) -57: FINISH_VISCHUNK(o0, f34, f36, g3) -58: FINISH_VISCHUNK(o0, f36, f38, g3) -59: FINISH_VISCHUNK(o0, f38, f40, g3) -60: FINISH_VISCHUNK(o0, f40, f42, g3) -61: FINISH_VISCHUNK(o0, f42, f44, g3) -62: FINISH_VISCHUNK(o0, f44, f46, g3) -63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3) - -93: EX_LD_FP(LOAD(ldd, %o1, %f2)) +40: FINISH_VISCHUNK(o0, f0, f2) +41: FINISH_VISCHUNK(o0, f2, f4) +42: FINISH_VISCHUNK(o0, f4, f6) +43: FINISH_VISCHUNK(o0, f6, f8) +44: FINISH_VISCHUNK(o0, f8, f10) +45: FINISH_VISCHUNK(o0, f10, f12) +46: FINISH_VISCHUNK(o0, f12, f14) +47: UNEVEN_VISCHUNK(o0, f14, f0) +48: FINISH_VISCHUNK(o0, f16, f18) +49: FINISH_VISCHUNK(o0, f18, f20) +50: FINISH_VISCHUNK(o0, f20, f22) +51: FINISH_VISCHUNK(o0, f22, f24) +52: FINISH_VISCHUNK(o0, f24, f26) +53: FINISH_VISCHUNK(o0, f26, f28) +54: FINISH_VISCHUNK(o0, f28, f30) +55: UNEVEN_VISCHUNK(o0, f30, f0) +56: FINISH_VISCHUNK(o0, f32, f34) +57: FINISH_VISCHUNK(o0, f34, f36) +58: FINISH_VISCHUNK(o0, f36, f38) +59: FINISH_VISCHUNK(o0, f38, f40) +60: FINISH_VISCHUNK(o0, f40, f42) +61: FINISH_VISCHUNK(o0, f42, f44) +62: FINISH_VISCHUNK(o0, f44, f46) +63: UNEVEN_VISCHUNK_LAST(o0, f46, f0) + +93: EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f0, %f2, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp) bl,pn %xcc, 95f add %o0, 8, %o0 - EX_LD_FP(LOAD(ldd, %o1, %f0)) + EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f2, %f0, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp) bge,pt %xcc, 93b add %o0, 8, %o0 95: brz,pt %o2, 2f mov %g1, %o1 -1: EX_LD_FP(LOAD(ldub, %o1, %o3)) +1: EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp) add %o1, 1, %o1 subcc %o2, 1, %o2 - EX_ST_FP(STORE(stb, %o3, %o0)) + EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp) bne,pt %xcc, 1b add %o0, 1, %o0 @@ -470,27 +583,27 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 72: andn %o2, 0xf, %GLOBAL_SPARE and %o2, 0xf, %o2 -1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5)) - EX_LD(LOAD(ldx, %o1 + 0x08, %g1)) +1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0) + EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0) subcc %GLOBAL_SPARE, 0x10, %GLOBAL_SPARE - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10) add %o1, 0x8, %o1 - EX_ST(STORE(stx, %g1, %o1 + %o3)) + EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8) bgu,pt %XCC, 1b add %o1, 0x8, %o1 73: andcc %o2, 0x8, %g0 be,pt %XCC, 1f nop - EX_LD(LOAD(ldx, %o1, %o5)) + EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0) sub %o2, 0x8, %o2 - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8) add %o1, 0x8, %o1 1: andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop - EX_LD(LOAD(lduw, %o1, %o5)) + EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0) sub %o2, 0x4, %o2 - EX_ST(STORE(stw, %o5, %o1 + %o3)) + EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4) add %o1, 0x4, %o1 1: cmp %o2, 0 be,pt %XCC, 85f @@ -504,9 +617,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %g0, %g1, %g1 sub %o2, %g1, %o2 -1: EX_LD(LOAD(ldub, %o1, %o5)) +1: EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0) subcc %g1, 1, %g1 - EX_ST(STORE(stb, %o5, %o1 + %o3)) + EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1) bgu,pt %icc, 1b add %o1, 1, %o1 @@ -522,16 +635,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 8: mov 64, %o3 andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1, %g2)) + EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0) sub %o3, %g1, %o3 andn %o2, 0x7, %GLOBAL_SPARE sllx %g2, %g1, %g2 -1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3)) +1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj) subcc %GLOBAL_SPARE, 0x8, %GLOBAL_SPARE add %o1, 0x8, %o1 srlx %g3, %o3, %o5 or %o5, %g2, %o5 - EX_ST(STORE(stx, %o5, %o0)) + EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -549,9 +662,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ bne,pn %XCC, 90f sub %o0, %o1, %o3 -1: EX_LD(LOAD(lduw, %o1, %g1)) +1: EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0) subcc %o2, 4, %o2 - EX_ST(STORE(stw, %g1, %o1 + %o3)) + EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -559,9 +672,9 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ mov EX_RETVAL(%o4), %o0 .align 32 -90: EX_LD(LOAD(ldub, %o1, %g1)) +90: EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0) subcc %o2, 1, %o2 - EX_ST(STORE(stb, %g1, %o1 + %o3)) + EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S index 88ad73d86fe4..db73010a1af8 100644 --- a/arch/sparc/lib/U3copy_from_user.S +++ b/arch/sparc/lib/U3copy_from_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_LD(x) \ +#define EX_LD(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_LD_FP(x) \ +#define EX_LD_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index 845139d75537..c4ee858e352a 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -3,19 +3,19 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ -#define EX_ST(x) \ +#define EX_ST(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, y; \ .text; \ .align 4; -#define EX_ST_FP(x) \ +#define EX_ST_FP(x,y) \ 98: x; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one_fp;\ + .word 98b, y##_fp; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S index 491ee69e4995..54f98706b03b 100644 --- a/arch/sparc/lib/U3memcpy.S +++ b/arch/sparc/lib/U3memcpy.S @@ -4,6 +4,7 @@ */ #ifdef __KERNEL__ +#include <linux/linkage.h> #include <asm/visasm.h> #include <asm/asi.h> #define GLOBAL_SPARE %g7 @@ -22,21 +23,17 @@ #endif #ifndef EX_LD -#define EX_LD(x) x +#define EX_LD(x,y) x #endif #ifndef EX_LD_FP -#define EX_LD_FP(x) x +#define EX_LD_FP(x,y) x #endif #ifndef EX_ST -#define EX_ST(x) x +#define EX_ST(x,y) x #endif #ifndef EX_ST_FP -#define EX_ST_FP(x) x -#endif - -#ifndef EX_RETVAL -#define EX_RETVAL(x) x +#define EX_ST_FP(x,y) x #endif #ifndef LOAD @@ -77,6 +74,87 @@ */ .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_fp: + VISExitHalf + retl + nop +ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp) + add %g1, 1, %g1 + add %g2, %g1, %g2 + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp) +ENTRY(U3_retl_o2_plus_g2_fp) + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_fp) +ENTRY(U3_retl_o2_plus_g2_plus_8_fp) + add %g2, 8, %g2 + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_plus_8_fp) +ENTRY(U3_retl_o2) + retl + mov %o2, %o0 +ENDPROC(U3_retl_o2) +ENTRY(U3_retl_o2_plus_1) + retl + add %o2, 1, %o0 +ENDPROC(U3_retl_o2_plus_1) +ENTRY(U3_retl_o2_plus_4) + retl + add %o2, 4, %o0 +ENDPROC(U3_retl_o2_plus_4) +ENTRY(U3_retl_o2_plus_8) + retl + add %o2, 8, %o0 +ENDPROC(U3_retl_o2_plus_8) +ENTRY(U3_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + retl + add %o2, %g1, %o0 +ENDPROC(U3_retl_o2_plus_g1_plus_1) +ENTRY(U3_retl_o2_fp) + ba,pt %xcc, __restore_fp + mov %o2, %o0 +ENDPROC(U3_retl_o2_fp) +ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp) + sll %o3, 6, %o3 + add %o3, 0x80, %o3 + ba,pt %xcc, __restore_fp + add %o2, %o3, %o0 +ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp) +ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp) + sll %o3, 6, %o3 + add %o3, 0x40, %o3 + ba,pt %xcc, __restore_fp + add %o2, %o3, %o0 +ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp) +ENTRY(U3_retl_o2_plus_GS_plus_0x10) + add GLOBAL_SPARE, 0x10, GLOBAL_SPARE + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_plus_GS_plus_0x10) +ENTRY(U3_retl_o2_plus_GS_plus_0x08) + add GLOBAL_SPARE, 0x08, GLOBAL_SPARE + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_plus_GS_plus_0x08) +ENTRY(U3_retl_o2_and_7_plus_GS) + and %o2, 7, %o2 + retl + add %o2, GLOBAL_SPARE, %o2 +ENDPROC(U3_retl_o2_and_7_plus_GS) +ENTRY(U3_retl_o2_and_7_plus_GS_plus_8) + add GLOBAL_SPARE, 8, GLOBAL_SPARE + and %o2, 7, %o2 + retl + add %o2, GLOBAL_SPARE, %o2 +ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8) +#endif + .align 64 /* The cheetah's flexible spine, oversized liver, enlarged heart, @@ -126,8 +204,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1) + EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -138,20 +216,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD_FP(LOAD(ldd, %o1, %f4)) -1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST_FP(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f2 - EX_ST_FP(STORE(std, %f2, %o0)) + EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -161,25 +239,25 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ LOAD(prefetch, %o1 + 0x080, #one_read) LOAD(prefetch, %o1 + 0x0c0, #one_read) LOAD(prefetch, %o1 + 0x100, #one_read) - EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2) LOAD(prefetch, %o1 + 0x140, #one_read) - EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2) LOAD(prefetch, %o1 + 0x180, #one_read) - EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f0, %f2, %f16 - EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2) faligndata %f2, %f4, %f18 - EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2) faligndata %f4, %f6, %f20 - EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2) faligndata %f6, %f8, %f22 - EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2) faligndata %f8, %f10, %f24 - EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2) faligndata %f10, %f12, %f26 - EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2) subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE add %o1, 0x40, %o1 @@ -190,26 +268,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: - EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f12, %f14, %f28 - EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f14, %f0, %f30 - EX_ST_FP(STORE_BLK(%f16, %o0)) - EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f0, %f2, %f16 add %o0, 0x40, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f2, %f4, %f18 - EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f4, %f6, %f20 - EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40) subcc %o3, 0x01, %o3 faligndata %f6, %f8, %f22 - EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f8, %f10, %f24 - EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f10, %f12, %f26 bg,pt %XCC, 1b @@ -217,29 +295,29 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ /* Finally we copy the last full 64-byte block. */ 2: - EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f12, %f14, %f28 - EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80) faligndata %f14, %f0, %f30 - EX_ST_FP(STORE_BLK(%f16, %o0)) - EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f0, %f2, %f16 - EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f2, %f4, %f18 - EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f4, %f6, %f20 - EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f6, %f8, %f22 - EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40) faligndata %f8, %f10, %f24 cmp %g1, 0 be,pt %XCC, 1f add %o0, 0x40, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40) 1: faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40) add %o0, 0x40, %o0 add %o1, 0x40, %o1 membar #Sync @@ -259,20 +337,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g2, %o2 be,a,pt %XCC, 1f - EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2) -1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f0, %f2, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8) be,pn %XCC, 2f add %o0, 0x8, %o0 - EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f2, %f0, %f8 - EX_ST_FP(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8) bne,pn %XCC, 1b add %o0, 0x8, %o0 @@ -292,30 +370,33 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andcc %o2, 0x8, %g0 be,pt %icc, 1f nop - EX_LD(LOAD(ldx, %o1, %o5)) - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2) add %o1, 0x8, %o1 + sub %o2, 8, %o2 1: andcc %o2, 0x4, %g0 be,pt %icc, 1f nop - EX_LD(LOAD(lduw, %o1, %o5)) - EX_ST(STORE(stw, %o5, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2) + EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2) add %o1, 0x4, %o1 + sub %o2, 4, %o2 1: andcc %o2, 0x2, %g0 be,pt %icc, 1f nop - EX_LD(LOAD(lduh, %o1, %o5)) - EX_ST(STORE(sth, %o5, %o1 + %o3)) + EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2) + EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2) add %o1, 0x2, %o1 + sub %o2, 2, %o2 1: andcc %o2, 0x1, %g0 be,pt %icc, 85f nop - EX_LD(LOAD(ldub, %o1, %o5)) + EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2) ba,pt %xcc, 85f - EX_ST(STORE(stb, %o5, %o1 + %o3)) + EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2) .align 64 70: /* 16 < len <= 64 */ @@ -326,26 +407,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0xf, GLOBAL_SPARE and %o2, 0xf, %o2 1: subcc GLOBAL_SPARE, 0x10, GLOBAL_SPARE - EX_LD(LOAD(ldx, %o1 + 0x00, %o5)) - EX_LD(LOAD(ldx, %o1 + 0x08, %g1)) - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10) + EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10) add %o1, 0x8, %o1 - EX_ST(STORE(stx, %g1, %o1 + %o3)) + EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08) bgu,pt %XCC, 1b add %o1, 0x8, %o1 73: andcc %o2, 0x8, %g0 be,pt %XCC, 1f nop sub %o2, 0x8, %o2 - EX_LD(LOAD(ldx, %o1, %o5)) - EX_ST(STORE(stx, %o5, %o1 + %o3)) + EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8) add %o1, 0x8, %o1 1: andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop sub %o2, 0x4, %o2 - EX_LD(LOAD(lduw, %o1, %o5)) - EX_ST(STORE(stw, %o5, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4) + EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4) add %o1, 0x4, %o1 1: cmp %o2, 0 be,pt %XCC, 85f @@ -361,8 +442,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g1, %o2 1: subcc %g1, 1, %g1 - EX_LD(LOAD(ldub, %o1, %o5)) - EX_ST(STORE(stb, %o5, %o1 + %o3)) + EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1) + EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1) bgu,pt %icc, 1b add %o1, 1, %o1 @@ -378,16 +459,16 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 8: mov 64, %o3 andn %o1, 0x7, %o1 - EX_LD(LOAD(ldx, %o1, %g2)) + EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2) sub %o3, %g1, %o3 andn %o2, 0x7, GLOBAL_SPARE sllx %g2, %g1, %g2 -1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3)) +1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS) subcc GLOBAL_SPARE, 0x8, GLOBAL_SPARE add %o1, 0x8, %o1 srlx %g3, %o3, %o5 or %o5, %g2, %o5 - EX_ST(STORE(stx, %o5, %o0)) + EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8) add %o0, 0x8, %o0 bgu,pt %icc, 1b sllx %g3, %g1, %g2 @@ -407,8 +488,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 1: subcc %o2, 4, %o2 - EX_LD(LOAD(lduw, %o1, %g1)) - EX_ST(STORE(stw, %g1, %o1 + %o3)) + EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4) + EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4) bgu,pt %XCC, 1b add %o1, 4, %o1 @@ -418,8 +499,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX_LD(LOAD(ldub, %o1, %g1)) - EX_ST(STORE(stb, %g1, %o1 + %o3)) + EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1) + EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1) bgu,pt %XCC, 90b add %o1, 1, %o1 retl diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S index 482de093bdae..0252b218de45 100644 --- a/arch/sparc/lib/copy_in_user.S +++ b/arch/sparc/lib/copy_in_user.S @@ -9,18 +9,33 @@ #define XCC xcc -#define EX(x,y) \ +#define EX(x,y,z) \ 98: x,y; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, __retl_one; \ + .word 98b, z; \ .text; \ .align 4; +#define EX_O4(x,y) EX(x,y,__retl_o4_plus_8) +#define EX_O2_4(x,y) EX(x,y,__retl_o2_plus_4) +#define EX_O2_1(x,y) EX(x,y,__retl_o2_plus_1) + .register %g2,#scratch .register %g3,#scratch .text +__retl_o4_plus_8: + add %o4, %o2, %o4 + retl + add %o4, 8, %o0 +__retl_o2_plus_4: + retl + add %o2, 4, %o0 +__retl_o2_plus_1: + retl + add %o2, 1, %o0 + .align 32 /* Don't try to get too fancy here, just nice and @@ -45,8 +60,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ andn %o2, 0x7, %o4 and %o2, 0x7, %o2 1: subcc %o4, 0x8, %o4 - EX(ldxa [%o1] %asi, %o5) - EX(stxa %o5, [%o0] %asi) + EX_O4(ldxa [%o1] %asi, %o5) + EX_O4(stxa %o5, [%o0] %asi) add %o1, 0x8, %o1 bgu,pt %XCC, 1b add %o0, 0x8, %o0 @@ -54,8 +69,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ be,pt %XCC, 1f nop sub %o2, 0x4, %o2 - EX(lduwa [%o1] %asi, %o5) - EX(stwa %o5, [%o0] %asi) + EX_O2_4(lduwa [%o1] %asi, %o5) + EX_O2_4(stwa %o5, [%o0] %asi) add %o1, 0x4, %o1 add %o0, 0x4, %o0 1: cmp %o2, 0 @@ -71,8 +86,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ 82: subcc %o2, 4, %o2 - EX(lduwa [%o1] %asi, %g1) - EX(stwa %g1, [%o0] %asi) + EX_O2_4(lduwa [%o1] %asi, %g1) + EX_O2_4(stwa %g1, [%o0] %asi) add %o1, 4, %o1 bgu,pt %XCC, 82b add %o0, 4, %o0 @@ -83,8 +98,8 @@ ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ .align 32 90: subcc %o2, 1, %o2 - EX(lduba [%o1] %asi, %g1) - EX(stba %g1, [%o0] %asi) + EX_O2_1(lduba [%o1] %asi, %g1) + EX_O2_1(stba %g1, [%o0] %asi) add %o1, 1, %o1 bgu,pt %XCC, 90b add %o0, 1, %o0 diff --git a/arch/sparc/lib/user_fixup.c b/arch/sparc/lib/user_fixup.c deleted file mode 100644 index ac96ae236709..000000000000 --- a/arch/sparc/lib/user_fixup.c +++ /dev/null @@ -1,71 +0,0 @@ -/* user_fixup.c: Fix up user copy faults. - * - * Copyright (C) 2004 David S. Miller <davem@redhat.com> - */ - -#include <linux/compiler.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/module.h> - -#include <asm/uaccess.h> - -/* Calculating the exact fault address when using - * block loads and stores can be very complicated. - * - * Instead of trying to be clever and handling all - * of the cases, just fix things up simply here. - */ - -static unsigned long compute_size(unsigned long start, unsigned long size, unsigned long *offset) -{ - unsigned long fault_addr = current_thread_info()->fault_address; - unsigned long end = start + size; - - if (fault_addr < start || fault_addr >= end) { - *offset = 0; - } else { - *offset = fault_addr - start; - size = end - fault_addr; - } - return size; -} - -unsigned long copy_from_user_fixup(void *to, const void __user *from, unsigned long size) -{ - unsigned long offset; - - size = compute_size((unsigned long) from, size, &offset); - if (likely(size)) - memset(to + offset, 0, size); - - return size; -} -EXPORT_SYMBOL(copy_from_user_fixup); - -unsigned long copy_to_user_fixup(void __user *to, const void *from, unsigned long size) -{ - unsigned long offset; - - return compute_size((unsigned long) to, size, &offset); -} -EXPORT_SYMBOL(copy_to_user_fixup); - -unsigned long copy_in_user_fixup(void __user *to, void __user *from, unsigned long size) -{ - unsigned long fault_addr = current_thread_info()->fault_address; - unsigned long start = (unsigned long) to; - unsigned long end = start + size; - - if (fault_addr >= start && fault_addr < end) - return end - fault_addr; - - start = (unsigned long) from; - end = start + size; - if (fault_addr >= start && fault_addr < end) - return end - fault_addr; - - return size; -} -EXPORT_SYMBOL(copy_in_user_fixup); diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index f2b77112e9d8..e20fbbafb0b0 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr) return (tag == (vaddr >> 22)); } +static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end) +{ + unsigned long idx; + + for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) { + struct tsb *ent = &swapper_tsb[idx]; + unsigned long match = idx << 13; + + match |= (ent->tag << 22); + if (match >= start && match < end) + ent->tag = (1UL << TSB_TAG_INVALID_BIT); + } +} + /* TSB flushes need only occur on the processor initiating the address * space modification, not on each cpu the address space has run on. * Only the TLB flush needs that treatment. @@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) { unsigned long v; + if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES) + return flush_tsb_kernel_range_scan(start, end); + for (v = start; v < end; v += PAGE_SIZE) { unsigned long hash = tsb_hash(v, PAGE_SHIFT, KERNEL_TSB_NENTRIES); diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index b4f4733abc6e..5d2fd6cd3189 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -30,7 +30,7 @@ .text .align 32 .globl __flush_tlb_mm -__flush_tlb_mm: /* 18 insns */ +__flush_tlb_mm: /* 19 insns */ /* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */ ldxa [%o1] ASI_DMMU, %g2 cmp %g2, %o0 @@ -81,7 +81,7 @@ __flush_tlb_page: /* 22 insns */ .align 32 .globl __flush_tlb_pending -__flush_tlb_pending: /* 26 insns */ +__flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 sllx %o1, 3, %o1 @@ -113,12 +113,14 @@ __flush_tlb_pending: /* 26 insns */ .align 32 .globl __flush_tlb_kernel_range -__flush_tlb_kernel_range: /* 16 insns */ +__flush_tlb_kernel_range: /* 31 insns */ /* %o0=start, %o1=end */ cmp %o0, %o1 be,pn %xcc, 2f + sub %o1, %o0, %o3 + srlx %o3, 18, %o4 + brnz,pn %o4, __spitfire_flush_tlb_kernel_range_slow sethi %hi(PAGE_SIZE), %o4 - sub %o1, %o0, %o3 sub %o3, %o4, %o3 or %o0, 0x20, %o0 ! Nucleus 1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP @@ -131,6 +133,41 @@ __flush_tlb_kernel_range: /* 16 insns */ retl nop nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + +__spitfire_flush_tlb_kernel_range_slow: + mov 63 * 8, %o4 +1: ldxa [%o4] ASI_ITLB_DATA_ACCESS, %o3 + andcc %o3, 0x40, %g0 /* _PAGE_L_4U */ + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %o3 + stxa %g0, [%o3] ASI_IMMU + stxa %g0, [%o4] ASI_ITLB_DATA_ACCESS + membar #Sync +2: ldxa [%o4] ASI_DTLB_DATA_ACCESS, %o3 + andcc %o3, 0x40, %g0 + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %o3 + stxa %g0, [%o3] ASI_DMMU + stxa %g0, [%o4] ASI_DTLB_DATA_ACCESS + membar #Sync +2: sub %o4, 8, %o4 + brgez,pt %o4, 1b + nop + retl + nop __spitfire_flush_tlb_mm_slow: rdpr %pstate, %g1 @@ -285,6 +322,40 @@ __cheetah_flush_tlb_pending: /* 27 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_kernel_range: /* 31 insns */ + /* %o0=start, %o1=end */ + cmp %o0, %o1 + be,pn %xcc, 2f + sub %o1, %o0, %o3 + srlx %o3, 18, %o4 + brnz,pn %o4, 3f + sethi %hi(PAGE_SIZE), %o4 + sub %o3, %o4, %o3 + or %o0, 0x20, %o0 ! Nucleus +1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP + stxa %g0, [%o0 + %o3] ASI_IMMU_DEMAP + membar #Sync + brnz,pt %o3, 1b + sub %o3, %o4, %o3 +2: sethi %hi(KERNBASE), %o3 + flush %o3 + retl + nop +3: mov 0x80, %o4 + stxa %g0, [%o4] ASI_DMMU_DEMAP + membar #Sync + stxa %g0, [%o4] ASI_IMMU_DEMAP + membar #Sync + retl + nop + nop + nop + nop + nop + nop + nop + nop + #ifdef DCACHE_ALIASING_POSSIBLE __cheetah_flush_dcache_page: /* 11 insns */ sethi %hi(PAGE_OFFSET), %g1 @@ -309,19 +380,28 @@ __hypervisor_tlb_tl0_error: ret restore -__hypervisor_flush_tlb_mm: /* 10 insns */ +__hypervisor_flush_tlb_mm: /* 19 insns */ mov %o0, %o2 /* ARG2: mmu context */ mov 0, %o0 /* ARG0: CPU lists unimplemented */ mov 0, %o1 /* ARG1: CPU lists unimplemented */ mov HV_MMU_ALL, %o3 /* ARG3: flags */ mov HV_FAST_MMU_DEMAP_CTX, %o5 ta HV_FAST_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 1f mov HV_FAST_MMU_DEMAP_CTX, %o1 retl nop +1: sethi %hi(__hypervisor_tlb_tl0_error), %o5 + jmpl %o5 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop + nop + nop + nop + nop + nop + nop -__hypervisor_flush_tlb_page: /* 11 insns */ +__hypervisor_flush_tlb_page: /* 22 insns */ /* %o0 = context, %o1 = vaddr */ mov %o0, %g2 mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ @@ -330,12 +410,23 @@ __hypervisor_flush_tlb_page: /* 11 insns */ srlx %o0, PAGE_SHIFT, %o0 sllx %o0, PAGE_SHIFT, %o0 ta HV_MMU_UNMAP_ADDR_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 1f mov HV_MMU_UNMAP_ADDR_TRAP, %o1 retl nop +1: sethi %hi(__hypervisor_tlb_tl0_error), %o2 + jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop + nop + nop + nop + nop + nop + nop + nop + nop -__hypervisor_flush_tlb_pending: /* 16 insns */ +__hypervisor_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 mov %o2, %g2 @@ -347,31 +438,57 @@ __hypervisor_flush_tlb_pending: /* 16 insns */ srlx %o0, PAGE_SHIFT, %o0 sllx %o0, PAGE_SHIFT, %o0 ta HV_MMU_UNMAP_ADDR_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 1f mov HV_MMU_UNMAP_ADDR_TRAP, %o1 brnz,pt %g1, 1b nop retl nop +1: sethi %hi(__hypervisor_tlb_tl0_error), %o2 + jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop + nop + nop + nop + nop + nop + nop + nop + nop -__hypervisor_flush_tlb_kernel_range: /* 16 insns */ +__hypervisor_flush_tlb_kernel_range: /* 31 insns */ /* %o0=start, %o1=end */ cmp %o0, %o1 be,pn %xcc, 2f - sethi %hi(PAGE_SIZE), %g3 - mov %o0, %g1 - sub %o1, %g1, %g2 + sub %o1, %o0, %g2 + srlx %g2, 18, %g3 + brnz,pn %g3, 4f + mov %o0, %g1 + sethi %hi(PAGE_SIZE), %g3 sub %g2, %g3, %g2 1: add %g1, %g2, %o0 /* ARG0: virtual address */ mov 0, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ ta HV_MMU_UNMAP_ADDR_TRAP - brnz,pn %o0, __hypervisor_tlb_tl0_error + brnz,pn %o0, 3f mov HV_MMU_UNMAP_ADDR_TRAP, %o1 brnz,pt %g2, 1b sub %g2, %g3, %g2 2: retl nop +3: sethi %hi(__hypervisor_tlb_tl0_error), %o2 + jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0 + nop +4: mov 0, %o0 /* ARG0: CPU lists unimplemented */ + mov 0, %o1 /* ARG1: CPU lists unimplemented */ + mov 0, %o2 /* ARG2: mmu context == nucleus */ + mov HV_MMU_ALL, %o3 /* ARG3: flags */ + mov HV_FAST_MMU_DEMAP_CTX, %o5 + ta HV_FAST_TRAP + brnz,pn %o0, 3b + mov HV_FAST_MMU_DEMAP_CTX, %o1 + retl + nop #ifdef DCACHE_ALIASING_POSSIBLE /* XXX Niagara and friends have an 8K cache, so no aliasing is @@ -394,43 +511,6 @@ tlb_patch_one: retl nop - .globl cheetah_patch_cachetlbops -cheetah_patch_cachetlbops: - save %sp, -128, %sp - - sethi %hi(__flush_tlb_mm), %o0 - or %o0, %lo(__flush_tlb_mm), %o0 - sethi %hi(__cheetah_flush_tlb_mm), %o1 - or %o1, %lo(__cheetah_flush_tlb_mm), %o1 - call tlb_patch_one - mov 19, %o2 - - sethi %hi(__flush_tlb_page), %o0 - or %o0, %lo(__flush_tlb_page), %o0 - sethi %hi(__cheetah_flush_tlb_page), %o1 - or %o1, %lo(__cheetah_flush_tlb_page), %o1 - call tlb_patch_one - mov 22, %o2 - - sethi %hi(__flush_tlb_pending), %o0 - or %o0, %lo(__flush_tlb_pending), %o0 - sethi %hi(__cheetah_flush_tlb_pending), %o1 - or %o1, %lo(__cheetah_flush_tlb_pending), %o1 - call tlb_patch_one - mov 27, %o2 - -#ifdef DCACHE_ALIASING_POSSIBLE - sethi %hi(__flush_dcache_page), %o0 - or %o0, %lo(__flush_dcache_page), %o0 - sethi %hi(__cheetah_flush_dcache_page), %o1 - or %o1, %lo(__cheetah_flush_dcache_page), %o1 - call tlb_patch_one - mov 11, %o2 -#endif /* DCACHE_ALIASING_POSSIBLE */ - - ret - restore - #ifdef CONFIG_SMP /* These are all called by the slaves of a cross call, at * trap level 1, with interrupts fully disabled. @@ -447,7 +527,7 @@ cheetah_patch_cachetlbops: */ .align 32 .globl xcall_flush_tlb_mm -xcall_flush_tlb_mm: /* 21 insns */ +xcall_flush_tlb_mm: /* 24 insns */ mov PRIMARY_CONTEXT, %g2 ldxa [%g2] ASI_DMMU, %g3 srlx %g3, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -469,9 +549,12 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop nop + nop + nop + nop .globl xcall_flush_tlb_page -xcall_flush_tlb_page: /* 17 insns */ +xcall_flush_tlb_page: /* 20 insns */ /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 @@ -490,15 +573,20 @@ xcall_flush_tlb_page: /* 17 insns */ retry nop nop + nop + nop + nop .globl xcall_flush_tlb_kernel_range -xcall_flush_tlb_kernel_range: /* 25 insns */ +xcall_flush_tlb_kernel_range: /* 44 insns */ sethi %hi(PAGE_SIZE - 1), %g2 or %g2, %lo(PAGE_SIZE - 1), %g2 andn %g1, %g2, %g1 andn %g7, %g2, %g7 sub %g7, %g1, %g3 - add %g2, 1, %g2 + srlx %g3, 18, %g2 + brnz,pn %g2, 2f + add %g2, 1, %g2 sub %g3, %g2, %g3 or %g1, 0x20, %g1 ! Nucleus 1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP @@ -507,8 +595,25 @@ xcall_flush_tlb_kernel_range: /* 25 insns */ brnz,pt %g3, 1b sub %g3, %g2, %g3 retry - nop - nop +2: mov 63 * 8, %g1 +1: ldxa [%g1] ASI_ITLB_DATA_ACCESS, %g2 + andcc %g2, 0x40, %g0 /* _PAGE_L_4U */ + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %g2 + stxa %g0, [%g2] ASI_IMMU + stxa %g0, [%g1] ASI_ITLB_DATA_ACCESS + membar #Sync +2: ldxa [%g1] ASI_DTLB_DATA_ACCESS, %g2 + andcc %g2, 0x40, %g0 + bne,pn %xcc, 2f + mov TLB_TAG_ACCESS, %g2 + stxa %g0, [%g2] ASI_DMMU + stxa %g0, [%g1] ASI_DTLB_DATA_ACCESS + membar #Sync +2: sub %g1, 8, %g1 + brgez,pt %g1, 1b + nop + retry nop nop nop @@ -637,6 +742,52 @@ xcall_fetch_glob_pmu_n4: retry +__cheetah_xcall_flush_tlb_kernel_range: /* 44 insns */ + sethi %hi(PAGE_SIZE - 1), %g2 + or %g2, %lo(PAGE_SIZE - 1), %g2 + andn %g1, %g2, %g1 + andn %g7, %g2, %g7 + sub %g7, %g1, %g3 + srlx %g3, 18, %g2 + brnz,pn %g2, 2f + add %g2, 1, %g2 + sub %g3, %g2, %g3 + or %g1, 0x20, %g1 ! Nucleus +1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP + stxa %g0, [%g1 + %g3] ASI_IMMU_DEMAP + membar #Sync + brnz,pt %g3, 1b + sub %g3, %g2, %g3 + retry +2: mov 0x80, %g2 + stxa %g0, [%g2] ASI_DMMU_DEMAP + membar #Sync + stxa %g0, [%g2] ASI_IMMU_DEMAP + membar #Sync + retry + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + #ifdef DCACHE_ALIASING_POSSIBLE .align 32 .globl xcall_flush_dcache_page_cheetah @@ -700,7 +851,7 @@ __hypervisor_tlb_xcall_error: ba,a,pt %xcc, rtrap .globl __hypervisor_xcall_flush_tlb_mm -__hypervisor_xcall_flush_tlb_mm: /* 21 insns */ +__hypervisor_xcall_flush_tlb_mm: /* 24 insns */ /* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */ mov %o0, %g2 mov %o1, %g3 @@ -714,7 +865,7 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ mov HV_FAST_MMU_DEMAP_CTX, %o5 ta HV_FAST_TRAP mov HV_FAST_MMU_DEMAP_CTX, %g6 - brnz,pn %o0, __hypervisor_tlb_xcall_error + brnz,pn %o0, 1f mov %o0, %g5 mov %g2, %o0 mov %g3, %o1 @@ -723,9 +874,12 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ mov %g7, %o5 membar #Sync retry +1: sethi %hi(__hypervisor_tlb_xcall_error), %g4 + jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0 + nop .globl __hypervisor_xcall_flush_tlb_page -__hypervisor_xcall_flush_tlb_page: /* 17 insns */ +__hypervisor_xcall_flush_tlb_page: /* 20 insns */ /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 @@ -737,42 +891,64 @@ __hypervisor_xcall_flush_tlb_page: /* 17 insns */ sllx %o0, PAGE_SHIFT, %o0 ta HV_MMU_UNMAP_ADDR_TRAP mov HV_MMU_UNMAP_ADDR_TRAP, %g6 - brnz,a,pn %o0, __hypervisor_tlb_xcall_error + brnz,a,pn %o0, 1f mov %o0, %g5 mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 membar #Sync retry +1: sethi %hi(__hypervisor_tlb_xcall_error), %g4 + jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0 + nop .globl __hypervisor_xcall_flush_tlb_kernel_range -__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */ +__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */ /* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */ sethi %hi(PAGE_SIZE - 1), %g2 or %g2, %lo(PAGE_SIZE - 1), %g2 andn %g1, %g2, %g1 andn %g7, %g2, %g7 sub %g7, %g1, %g3 + srlx %g3, 18, %g7 add %g2, 1, %g2 sub %g3, %g2, %g3 mov %o0, %g2 mov %o1, %g4 - mov %o2, %g7 + brnz,pn %g7, 2f + mov %o2, %g7 1: add %g1, %g3, %o0 /* ARG0: virtual address */ mov 0, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ ta HV_MMU_UNMAP_ADDR_TRAP mov HV_MMU_UNMAP_ADDR_TRAP, %g6 - brnz,pn %o0, __hypervisor_tlb_xcall_error + brnz,pn %o0, 1f mov %o0, %g5 sethi %hi(PAGE_SIZE), %o2 brnz,pt %g3, 1b sub %g3, %o2, %g3 - mov %g2, %o0 +5: mov %g2, %o0 mov %g4, %o1 mov %g7, %o2 membar #Sync retry +1: sethi %hi(__hypervisor_tlb_xcall_error), %g4 + jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0 + nop +2: mov %o3, %g1 + mov %o5, %g3 + mov 0, %o0 /* ARG0: CPU lists unimplemented */ + mov 0, %o1 /* ARG1: CPU lists unimplemented */ + mov 0, %o2 /* ARG2: mmu context == nucleus */ + mov HV_MMU_ALL, %o3 /* ARG3: flags */ + mov HV_FAST_MMU_DEMAP_CTX, %o5 + ta HV_FAST_TRAP + mov %g1, %o3 + brz,pt %o0, 5b + mov %g3, %o5 + mov HV_FAST_MMU_DEMAP_CTX, %g6 + ba,pt %xcc, 1b + clr %g5 /* These just get rescheduled to PIL vectors. */ .globl xcall_call_function @@ -809,6 +985,58 @@ xcall_kgdb_capture: #endif /* CONFIG_SMP */ + .globl cheetah_patch_cachetlbops +cheetah_patch_cachetlbops: + save %sp, -128, %sp + + sethi %hi(__flush_tlb_mm), %o0 + or %o0, %lo(__flush_tlb_mm), %o0 + sethi %hi(__cheetah_flush_tlb_mm), %o1 + or %o1, %lo(__cheetah_flush_tlb_mm), %o1 + call tlb_patch_one + mov 19, %o2 + + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + + sethi %hi(__flush_tlb_pending), %o0 + or %o0, %lo(__flush_tlb_pending), %o0 + sethi %hi(__cheetah_flush_tlb_pending), %o1 + or %o1, %lo(__cheetah_flush_tlb_pending), %o1 + call tlb_patch_one + mov 27, %o2 + + sethi %hi(__flush_tlb_kernel_range), %o0 + or %o0, %lo(__flush_tlb_kernel_range), %o0 + sethi %hi(__cheetah_flush_tlb_kernel_range), %o1 + or %o1, %lo(__cheetah_flush_tlb_kernel_range), %o1 + call tlb_patch_one + mov 31, %o2 + +#ifdef DCACHE_ALIASING_POSSIBLE + sethi %hi(__flush_dcache_page), %o0 + or %o0, %lo(__flush_dcache_page), %o0 + sethi %hi(__cheetah_flush_dcache_page), %o1 + or %o1, %lo(__cheetah_flush_dcache_page), %o1 + call tlb_patch_one + mov 11, %o2 +#endif /* DCACHE_ALIASING_POSSIBLE */ + +#ifdef CONFIG_SMP + sethi %hi(xcall_flush_tlb_kernel_range), %o0 + or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 + sethi %hi(__cheetah_xcall_flush_tlb_kernel_range), %o1 + or %o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1 + call tlb_patch_one + mov 44, %o2 +#endif /* CONFIG_SMP */ + + ret + restore .globl hypervisor_patch_cachetlbops hypervisor_patch_cachetlbops: @@ -819,28 +1047,28 @@ hypervisor_patch_cachetlbops: sethi %hi(__hypervisor_flush_tlb_mm), %o1 or %o1, %lo(__hypervisor_flush_tlb_mm), %o1 call tlb_patch_one - mov 10, %o2 + mov 19, %o2 sethi %hi(__flush_tlb_page), %o0 or %o0, %lo(__flush_tlb_page), %o0 sethi %hi(__hypervisor_flush_tlb_page), %o1 or %o1, %lo(__hypervisor_flush_tlb_page), %o1 call tlb_patch_one - mov 11, %o2 + mov 22, %o2 sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 or %o1, %lo(__hypervisor_flush_tlb_pending), %o1 call tlb_patch_one - mov 16, %o2 + mov 27, %o2 sethi %hi(__flush_tlb_kernel_range), %o0 or %o0, %lo(__flush_tlb_kernel_range), %o0 sethi %hi(__hypervisor_flush_tlb_kernel_range), %o1 or %o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1 call tlb_patch_one - mov 16, %o2 + mov 31, %o2 #ifdef DCACHE_ALIASING_POSSIBLE sethi %hi(__flush_dcache_page), %o0 @@ -857,21 +1085,21 @@ hypervisor_patch_cachetlbops: sethi %hi(__hypervisor_xcall_flush_tlb_mm), %o1 or %o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1 call tlb_patch_one - mov 21, %o2 + mov 24, %o2 sethi %hi(xcall_flush_tlb_page), %o0 or %o0, %lo(xcall_flush_tlb_page), %o0 sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 17, %o2 + mov 20, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 sethi %hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1 or %o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1 call tlb_patch_one - mov 25, %o2 + mov 44, %o2 #endif /* CONFIG_SMP */ ret diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 0ab5ee1c26af..aa8b0672f87a 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -888,7 +888,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req) unsigned long auth_tag_len = crypto_aead_authsize(tfm); u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); struct scatter_walk src_sg_walk; - struct scatter_walk dst_sg_walk; + struct scatter_walk dst_sg_walk = {}; unsigned int i; /* Assuming we are supporting rfc4106 64-bit extended */ @@ -968,7 +968,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req) u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); u8 authTag[16]; struct scatter_walk src_sg_walk; - struct scatter_walk dst_sg_walk; + struct scatter_walk dst_sg_walk = {}; unsigned int i; if (unlikely(req->assoclen != 16 && req->assoclen != 20)) diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 77f28ce9c646..9976fcecd17e 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,8 +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 +CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index eab0915f5995..a74a2dbc0180 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3607,10 +3607,14 @@ __init int intel_pmu_init(void) /* * Quirk: v2 perfmon does not report fixed-purpose events, so - * assume at least 3 events: + * assume at least 3 events, when not running in a hypervisor: */ - if (version > 1) - x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); + if (version > 1) { + int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR); + + x86_pmu.num_counters_fixed = + max((int)edx.split.num_counters_fixed, assume); + } if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 3ca87b5a8677..4f5ac726335f 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -48,7 +48,8 @@ * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW + * SKL,KNL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -56,15 +57,16 @@ * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL + * Available model: SNB,IVB,HSW,BDW,SKL,KNL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW + * SKL,KNL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -118,6 +120,7 @@ struct cstate_model { /* Quirk flags */ #define SLM_PKG_C6_USE_C7_MSR (1UL << 0) +#define KNL_CORE_C6_MSR (1UL << 1) struct perf_cstate_msr { u64 msr; @@ -488,6 +491,18 @@ static const struct cstate_model slm_cstates __initconst = { .quirks = SLM_PKG_C6_USE_C7_MSR, }; + +static const struct cstate_model knl_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES), + .quirks = KNL_CORE_C6_MSR, +}; + + + #define X86_CSTATES_MODEL(model, states) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } @@ -523,6 +538,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); @@ -558,6 +575,11 @@ static int __init cstate_probe(const struct cstate_model *cm) if (cm->quirks & SLM_PKG_C6_USE_C7_MSR) pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + /* KNL has different MSR for CORE C6 */ + if (cm->quirks & KNL_CORE_C6_MSR) + pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY; + + has_cstate_core = cstate_probe_msr(cm->core_events, PERF_CSTATE_CORE_EVENT_MAX, core_msr, core_events_attrs); diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index c5047b8f777b..1c1b9fe705c8 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx); static struct pt_pmu pt_pmu; -enum cpuid_regs { - CR_EAX = 0, - CR_ECX, - CR_EDX, - CR_EBX -}; - /* * Capabilities of Intel PT hardware, such as number of address bits or * supported output schemes, are cached and exported to userspace as "caps" @@ -64,21 +57,21 @@ static struct pt_cap_desc { u8 reg; u32 mask; } pt_caps[] = { - PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), - PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), - PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)), - PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)), - PT_CAP(mtc, 0, CR_EBX, BIT(3)), - PT_CAP(ptwrite, 0, CR_EBX, BIT(4)), - PT_CAP(power_event_trace, 0, CR_EBX, BIT(5)), - PT_CAP(topa_output, 0, CR_ECX, BIT(0)), - PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), - PT_CAP(single_range_output, 0, CR_ECX, BIT(2)), - PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), - PT_CAP(num_address_ranges, 1, CR_EAX, 0x3), - PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000), - PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff), - PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000), + PT_CAP(max_subleaf, 0, CPUID_EAX, 0xffffffff), + PT_CAP(cr3_filtering, 0, CPUID_EBX, BIT(0)), + PT_CAP(psb_cyc, 0, CPUID_EBX, BIT(1)), + PT_CAP(ip_filtering, 0, CPUID_EBX, BIT(2)), + PT_CAP(mtc, 0, CPUID_EBX, BIT(3)), + PT_CAP(ptwrite, 0, CPUID_EBX, BIT(4)), + PT_CAP(power_event_trace, 0, CPUID_EBX, BIT(5)), + PT_CAP(topa_output, 0, CPUID_ECX, BIT(0)), + PT_CAP(topa_multiple_entries, 0, CPUID_ECX, BIT(1)), + PT_CAP(single_range_output, 0, CPUID_ECX, BIT(2)), + PT_CAP(payloads_lip, 0, CPUID_ECX, BIT(31)), + PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x3), + PT_CAP(mtc_periods, 1, CPUID_EAX, 0xffff0000), + PT_CAP(cycle_thresholds, 1, CPUID_EBX, 0xffff), + PT_CAP(psb_periods, 1, CPUID_EBX, 0xffff0000), }; static u32 pt_cap_get(enum pt_capabilities cap) @@ -213,10 +206,10 @@ static int __init pt_pmu_hw_init(void) for (i = 0; i < PT_CPUID_LEAVES; i++) { cpuid_count(20, i, - &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM], - &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM], - &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM], - &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]); + &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM]); } ret = -ENOMEM; diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index de25aad07853..d34bd370074b 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -351,4 +351,10 @@ extern void arch_phys_wc_del(int handle); #define arch_phys_wc_add arch_phys_wc_add #endif +#ifdef CONFIG_X86_PAT +extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size); +extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size); +#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc +#endif + #endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 984a7bf17f6a..e7f8c62701d4 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -137,6 +137,17 @@ struct cpuinfo_x86 { u32 microcode; }; +struct cpuid_regs { + u32 eax, ebx, ecx, edx; +}; + +enum cpuid_regs_idx { + CPUID_EAX = 0, + CPUID_EBX, + CPUID_ECX, + CPUID_EDX, +}; + #define X86_VENDOR_INTEL 0 #define X86_VENDOR_CYRIX 1 #define X86_VENDOR_AMD 2 @@ -178,6 +189,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); void print_cpu_msr(struct cpuinfo_x86 *); extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); +extern u32 get_scattered_cpuid_leaf(unsigned int level, + unsigned int sub_leaf, + enum cpuid_regs_idx reg); extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8a5abaa7d453..931ced8ca345 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -454,6 +454,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* * stash over-ride to indicate we've been here diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index c7364bd633e1..51287cd90bf6 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1042,8 +1042,11 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) if (apm_info.get_power_status_broken) return APM_32_UNSUPPORTED; - if (apm_bios_call(&call)) + if (apm_bios_call(&call)) { + if (!call.err) + return APM_NO_ERROR; return call.err; + } *status = call.ebx; *bat = call.ecx; if (apm_info.get_power_status_swabinminutes) { diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 620ab06bcf45..017bda12caae 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -429,7 +429,7 @@ int __init save_microcode_in_initrd_amd(void) * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa_nodebug(container); cont_va = container; #endif diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 1db8dc490b66..d1316f9c8329 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -17,11 +17,17 @@ struct cpuid_bit { u32 sub_leaf; }; -enum cpuid_regs { - CR_EAX = 0, - CR_ECX, - CR_EDX, - CR_EBX +/* Please keep the leaf sorted by cpuid_bit.level for faster search. */ +static const struct cpuid_bit cpuid_bits[] = { + { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, + { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 }, + { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, + { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, + { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, + { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, + { 0, 0, 0, 0, 0 } }; void init_scattered_cpuid_features(struct cpuinfo_x86 *c) @@ -30,18 +36,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) u32 regs[4]; const struct cpuid_bit *cb; - static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 }, - { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, - { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, - { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, - { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, - { 0, 0, 0, 0, 0 } - }; - for (cb = cpuid_bits; cb->feature; cb++) { /* Verify that the level is valid */ @@ -50,10 +44,35 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) max_level > (cb->level | 0xffff)) continue; - cpuid_count(cb->level, cb->sub_leaf, ®s[CR_EAX], - ®s[CR_EBX], ®s[CR_ECX], ®s[CR_EDX]); + cpuid_count(cb->level, cb->sub_leaf, ®s[CPUID_EAX], + ®s[CPUID_EBX], ®s[CPUID_ECX], + ®s[CPUID_EDX]); if (regs[cb->reg] & (1 << cb->bit)) set_cpu_cap(c, cb->feature); } } + +u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf, + enum cpuid_regs_idx reg) +{ + const struct cpuid_bit *cb; + u32 cpuid_val = 0; + + for (cb = cpuid_bits; cb->feature; cb++) { + + if (level > cb->level) + continue; + + if (level < cb->level) + break; + + if (reg == cb->reg && sub_leaf == cb->sub_leaf) { + if (cpu_has(&boot_cpu_data, cb->feature)) + cpuid_val |= BIT(cb->bit); + } + } + + return cpuid_val; +} +EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf); diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 2836de390f95..9095c80723d6 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -46,10 +46,6 @@ static struct class *cpuid_class; -struct cpuid_regs { - u32 eax, ebx, ecx, edx; -}; - static void cpuid_smp_cpuid(void *cmd_block) { struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block; diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index efe73aacf966..7b0d3da52fb4 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -18,8 +18,10 @@ #ifdef CC_USING_FENTRY # define function_hook __fentry__ +EXPORT_SYMBOL(__fentry__) #else # define function_hook mcount +EXPORT_SYMBOL(mcount) #endif /* All cases save the original rbp (8 bytes) */ @@ -295,7 +297,6 @@ trace: jmp fgraph_trace END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ -EXPORT_SYMBOL(function_hook) #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 51402a7e4ca6..0bee04d41bed 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -625,8 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, amd_disable_seq_and_redirect_scrub); -#endif - #if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) #include <linux/jump_label.h> #include <asm/string_64.h> @@ -657,3 +655,4 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); #endif +#endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bbfbca5fea0c..9c337b0e8ba7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1221,11 +1221,16 @@ void __init setup_arch(char **cmdline_p) */ get_smp_config(); + /* + * Systems w/o ACPI and mptables might not have it mapped the local + * APIC yet, but prefill_possible_map() might need to access it. + */ + init_apic_mappings(); + prefill_possible_map(); init_cpu_to_node(); - init_apic_mappings(); io_apic_init_mappings(); kvm_guest_init(); diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 9298993dc8b7..2d721e533cf4 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -47,7 +47,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, get_stack_info(first_frame, state->task, &state->stack_info, &state->stack_mask); - if (!__kernel_text_address(*first_frame)) + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + if (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + !__kernel_text_address(*first_frame))) unwind_next_frame(state); } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index ddd2661c4502..887e57182716 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -104,10 +104,10 @@ void __init kernel_randomize_memory(void) * consistent with the vaddr_start/vaddr_end variables. */ BUILD_BUG_ON(vaddr_start >= vaddr_end); - BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) && + BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) && vaddr_end >= EFI_VA_START); - BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) || - config_enabled(CONFIG_EFI)) && + BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) || + IS_ENABLED(CONFIG_EFI)) && vaddr_end >= __START_KERNEL_map); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 170cc4ff057b..83e701f160a9 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -730,6 +730,20 @@ void io_free_memtype(resource_size_t start, resource_size_t end) free_memtype(start, end); } +int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size) +{ + enum page_cache_mode type = _PAGE_CACHE_MODE_WC; + + return io_reserve_memtype(start, start + size, &type); +} +EXPORT_SYMBOL(arch_io_reserve_memtype_wc); + +void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) +{ + io_free_memtype(start, start + size); +} +EXPORT_SYMBOL(arch_io_free_memtype_wc); + pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c0fdd57da7aa..bdd855685403 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1837,6 +1837,7 @@ static void __init init_hvm_pv_info(void) xen_domain_type = XEN_HVM_DOMAIN; } +#endif static int xen_cpu_up_prepare(unsigned int cpu) { @@ -1887,6 +1888,7 @@ static int xen_cpu_up_online(unsigned int cpu) return 0; } +#ifdef CONFIG_XEN_PVHVM #ifdef CONFIG_KEXEC_CORE static void xen_hvm_shutdown(void) { |