From ac85fe8b21248054851e05bfaa352562e5b06dd3 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 28 Jul 2011 23:31:26 -0700 Subject: sparc: Sanitize cpu feature detection and reporting. Instead of evaluating the cpu features for ELF_HWCAP every exec, calculate it once at boot time. Add AV_SPARC_* capability flag bits, compatible with what Solaris reports to applications. Report these capabilities once in the kernel log, and also via /proc/cpuinfo in a new "cpucaps" entry. If available, fetch the cpu features from the machine description 'hwcap-list' property of the 'cpu' node. Signed-off-by: David S. Miller --- arch/sparc/include/asm/elf_64.h | 65 ++++++++++++++++++----------------------- 1 file changed, 29 insertions(+), 36 deletions(-) (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h index 64f7a00b374..7df8b7f544d 100644 --- a/arch/sparc/include/asm/elf_64.h +++ b/arch/sparc/include/asm/elf_64.h @@ -59,15 +59,33 @@ #define R_SPARC_6 45 /* Bits present in AT_HWCAP, primarily for Sparc32. */ - -#define HWCAP_SPARC_FLUSH 1 /* CPU supports flush instruction. */ -#define HWCAP_SPARC_STBAR 2 -#define HWCAP_SPARC_SWAP 4 -#define HWCAP_SPARC_MULDIV 8 -#define HWCAP_SPARC_V9 16 -#define HWCAP_SPARC_ULTRA3 32 -#define HWCAP_SPARC_BLKINIT 64 -#define HWCAP_SPARC_N2 128 +#define HWCAP_SPARC_FLUSH 0x00000001 +#define HWCAP_SPARC_STBAR 0x00000002 +#define HWCAP_SPARC_SWAP 0x00000004 +#define HWCAP_SPARC_MULDIV 0x00000008 +#define HWCAP_SPARC_V9 0x00000010 +#define HWCAP_SPARC_ULTRA3 0x00000020 +#define HWCAP_SPARC_BLKINIT 0x00000040 +#define HWCAP_SPARC_N2 0x00000080 + +/* Solaris compatible AT_HWCAP bits. */ +#define AV_SPARC_MUL32 0x00000100 /* 32x32 multiply is efficient */ +#define AV_SPARC_DIV32 0x00000200 /* 32x32 divide is efficient */ +#define AV_SPARC_FSMULD 0x00000400 /* 'fsmuld' is efficient */ +#define AV_SPARC_V8PLUS 0x00000800 /* v9 insn available to 32bit */ +#define AV_SPARC_POPC 0x00001000 /* 'popc' is efficient */ +#define AV_SPARC_VIS 0x00002000 /* VIS insns available */ +#define AV_SPARC_VIS2 0x00004000 /* VIS2 insns available */ +#define AV_SPARC_ASI_BLK_INIT 0x00008000 /* block init ASIs available */ +#define AV_SPARC_FMAF 0x00010000 /* fused multiply-add */ +#define AV_SPARC_VIS3 0x00020000 /* VIS3 insns available */ +#define AV_SPARC_HPC 0x00040000 /* HPC insns available */ +#define AV_SPARC_RANDOM 0x00080000 /* 'random' insn available */ +#define AV_SPARC_TRANS 0x00100000 /* transaction insns available */ +#define AV_SPARC_FJFMAU 0x00200000 /* unfused multiply-add */ +#define AV_SPARC_IMA 0x00400000 /* integer multiply-add */ +#define AV_SPARC_ASI_CACHE_SPARING \ + 0x00800000 /* cache sparing ASIs available */ #define CORE_DUMP_USE_REGSET @@ -162,33 +180,8 @@ typedef struct { #define ELF_ET_DYN_BASE 0x0000010000000000UL #define COMPAT_ELF_ET_DYN_BASE 0x0000000070000000UL - -/* This yields a mask that user programs can use to figure out what - instruction set this cpu supports. */ - -/* On Ultra, we support all of the v8 capabilities. */ -static inline unsigned int sparc64_elf_hwcap(void) -{ - unsigned int cap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | - HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV | - HWCAP_SPARC_V9); - - if (tlb_type == cheetah || tlb_type == cheetah_plus) - cap |= HWCAP_SPARC_ULTRA3; - else if (tlb_type == hypervisor) { - if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA3) - cap |= HWCAP_SPARC_BLKINIT; - if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA3) - cap |= HWCAP_SPARC_N2; - } - - return cap; -} - -#define ELF_HWCAP sparc64_elf_hwcap() +extern unsigned long sparc64_elf_hwcap; +#define ELF_HWCAP sparc64_elf_hwcap /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in -- cgit v1.2.3-70-g09d2 From ef7c4d4675d2a9206f913f26ca1a5cd41bff9d41 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 29 Jul 2011 09:42:07 -0700 Subject: sparc: Use popc if possible for hweight routines. Just like powerpc, we code patch at boot time. Signed-off-by: David S. Miller --- arch/sparc/include/asm/bitops_64.h | 42 +++---------------------------- arch/sparc/kernel/entry.h | 7 ++++++ arch/sparc/kernel/setup_64.c | 27 ++++++++++++++++++++ arch/sparc/kernel/sparc_ksyms_64.c | 7 ++++++ arch/sparc/kernel/vmlinux.lds.S | 6 ++++- arch/sparc/lib/Makefile | 2 +- arch/sparc/lib/hweight.S | 51 ++++++++++++++++++++++++++++++++++++++ 7 files changed, 102 insertions(+), 40 deletions(-) create mode 100644 arch/sparc/lib/hweight.S (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h index 325e295d60d..3588807baa6 100644 --- a/arch/sparc/include/asm/bitops_64.h +++ b/arch/sparc/include/asm/bitops_64.h @@ -42,45 +42,11 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr); * of bits set) of a N-bit word */ -#ifdef ULTRA_HAS_POPULATION_COUNT +extern unsigned long __arch_hweight64(__u64 w); +extern unsigned int __arch_hweight32(unsigned int w); +extern unsigned int __arch_hweight16(unsigned int w); +extern unsigned int __arch_hweight8(unsigned int w); -static inline unsigned int __arch_hweight64(unsigned long w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w)); - return res; -} - -static inline unsigned int __arch_hweight32(unsigned int w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffffffff)); - return res; -} - -static inline unsigned int __arch_hweight16(unsigned int w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffff)); - return res; -} - -static inline unsigned int __arch_hweight8(unsigned int w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xff)); - return res; -} - -#else - -#include - -#endif #include #include #endif /* __KERNEL__ */ diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index d1f1361c416..16d1545d84f 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -42,6 +42,13 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr, extern void fpload(unsigned long *fpregs, unsigned long *fsr); #else /* CONFIG_SPARC32 */ +struct popc_3insn_patch_entry { + unsigned int addr; + unsigned int insns[3]; +}; +extern struct popc_3insn_patch_entry __popc_3insn_patch, + __popc_3insn_patch_end; + extern void __init per_cpu_patch(void); extern void __init sun4v_patch(void); extern void __init boot_cpu_id_too_large(int cpu); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 242dbb3f31d..26d114187e1 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -272,6 +272,30 @@ void __init sun4v_patch(void) sun4v_hvapi_init(); } +static void __init popc_patch(void) +{ + struct popc_3insn_patch_entry *p3; + + p3 = &__popc_3insn_patch; + while (p3 < &__popc_3insn_patch_end) { + unsigned long addr = p3->addr; + + *(unsigned int *) (addr + 0) = p3->insns[0]; + wmb(); + __asm__ __volatile__("flush %0" : : "r" (addr + 0)); + + *(unsigned int *) (addr + 4) = p3->insns[1]; + wmb(); + __asm__ __volatile__("flush %0" : : "r" (addr + 4)); + + *(unsigned int *) (addr + 8) = p3->insns[2]; + wmb(); + __asm__ __volatile__("flush %0" : : "r" (addr + 4)); + + p3++; + } +} + #ifdef CONFIG_SMP void __init boot_cpu_id_too_large(int cpu) { @@ -424,6 +448,9 @@ static void __init init_sparc64_elf_hwcap(void) sparc64_elf_hwcap = cap | mdesc_caps; report_hwcaps(sparc64_elf_hwcap); + + if (sparc64_elf_hwcap & AV_SPARC_POPC) + popc_patch(); } void __init setup_arch(char **cmdline_p) diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index 372ad59c4cb..d0ee65aced0 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -38,5 +39,11 @@ EXPORT_SYMBOL(sun4v_niagara_setperf); EXPORT_SYMBOL(sun4v_niagara2_getperf); EXPORT_SYMBOL(sun4v_niagara2_setperf); +/* from hweight.S */ +EXPORT_SYMBOL(__arch_hweight8); +EXPORT_SYMBOL(__arch_hweight16); +EXPORT_SYMBOL(__arch_hweight32); +EXPORT_SYMBOL(__arch_hweight64); + /* Exporting a symbol from /init/main.c */ EXPORT_SYMBOL(saved_command_line); diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index c0220759003..de20c14625e 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -107,7 +107,11 @@ SECTIONS *(.sun4v_2insn_patch) __sun4v_2insn_patch_end = .; } - + .popc_3insn_patch : { + __popc_3insn_patch = .; + *(.popc_3insn_patch) + __popc_3insn_patch_end = .; + } PERCPU_SECTION(SMP_CACHE_BYTES) . = ALIGN(PAGE_SIZE); diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index c25f94d28df..11c850a9b66 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -37,7 +37,7 @@ 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) += mcount.o ipcsum.o xor.o +lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o obj-y += iomap.o obj-$(CONFIG_SPARC32) += atomic32.o diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S new file mode 100644 index 00000000000..95414e0a680 --- /dev/null +++ b/arch/sparc/lib/hweight.S @@ -0,0 +1,51 @@ +#include + + .text + .align 32 +ENTRY(__arch_hweight8) + ba,pt %xcc, __sw_hweight8 + nop + nop +ENDPROC(__arch_hweight8) + .section .popc_3insn_patch, "ax" + .word __arch_hweight8 + sllx %o0, 64-8, %g1 + retl + popc %g1, %o0 + .previous + +ENTRY(__arch_hweight16) + ba,pt %xcc, __sw_hweight16 + nop + nop +ENDPROC(__arch_hweight16) + .section .popc_3insn_patch, "ax" + .word __arch_hweight16 + sllx %o0, 64-16, %g1 + retl + popc %g1, %o0 + .previous + +ENTRY(__arch_hweight32) + ba,pt %xcc, __sw_hweight32 + nop + nop +ENDPROC(__arch_hweight32) + .section .popc_3insn_patch, "ax" + .word __arch_hweight32 + sllx %o0, 64-32, %g1 + retl + popc %g1, %o0 + .previous + +ENTRY(__arch_hweight64) + ba,pt %xcc, __sw_hweight64 + nop + nop +ENDPROC(__arch_hweight64) + .section .popc_3insn_patch, "ax" + .word __arch_hweight64 + retl + popc %o0, %o0 + nop + .previous -- cgit v1.2.3-70-g09d2 From e2eb9f8158ead43a88c0f0b4d74257b1be938a18 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 1 Aug 2011 22:45:18 -0700 Subject: sparc: Add some missing hypervisor API groups. Signed-off-by: David S. Miller --- arch/sparc/include/asm/hypervisor.h | 6 ++++++ arch/sparc/kernel/hvapi.c | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 7a5f80df15d..2b7da27ff17 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2940,11 +2940,17 @@ extern unsigned long sun4v_ncs_request(unsigned long request, #define HV_GRP_CORE 0x0001 #define HV_GRP_INTR 0x0002 #define HV_GRP_SOFT_STATE 0x0003 +#define HV_GRP_TM 0x0080 #define HV_GRP_PCI 0x0100 #define HV_GRP_LDOM 0x0101 #define HV_GRP_SVC_CHAN 0x0102 #define HV_GRP_NCS 0x0103 #define HV_GRP_RNG 0x0104 +#define HV_GRP_PBOOT 0x0105 +#define HV_GRP_TPM 0x0107 +#define HV_GRP_SDIO 0x0108 +#define HV_GRP_SDIO_ERR 0x0109 +#define HV_GRP_REBOOT_DATA 0x0110 #define HV_GRP_NIAG_PERF 0x0200 #define HV_GRP_FIRE_PERF 0x0201 #define HV_GRP_N2_CPU 0x0202 diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index d306e648c33..c2d055d8ba9 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -28,11 +28,17 @@ static struct api_info api_table[] = { { .group = HV_GRP_CORE, .flags = FLAG_PRE_API }, { .group = HV_GRP_INTR, }, { .group = HV_GRP_SOFT_STATE, }, + { .group = HV_GRP_TM, }, { .group = HV_GRP_PCI, .flags = FLAG_PRE_API }, { .group = HV_GRP_LDOM, }, { .group = HV_GRP_SVC_CHAN, .flags = FLAG_PRE_API }, { .group = HV_GRP_NCS, .flags = FLAG_PRE_API }, { .group = HV_GRP_RNG, }, + { .group = HV_GRP_PBOOT, }, + { .group = HV_GRP_TPM, }, + { .group = HV_GRP_SDIO, }, + { .group = HV_GRP_SDIO_ERR, }, + { .group = HV_GRP_REBOOT_DATA, }, { .group = HV_GRP_NIAG_PERF, .flags = FLAG_PRE_API }, { .group = HV_GRP_FIRE_PERF, }, { .group = HV_GRP_N2_CPU, }, -- cgit v1.2.3-70-g09d2 From ea5e7447ea9d555558e0f13798f5143dd51a915a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 1 Aug 2011 23:27:17 -0700 Subject: sparc: Set reboot-cmd using reboot data hypervisor call if available. Signed-off-by: David S. Miller --- arch/sparc/include/asm/hypervisor.h | 7 +++++++ arch/sparc/kernel/ds.c | 30 ++++++++++++++++++++++++++++-- arch/sparc/kernel/hvcalls.S | 7 +++++++ arch/sparc/kernel/kernel.h | 9 +++++++++ arch/sparc/kernel/sstate.c | 9 ++------- 5 files changed, 53 insertions(+), 9 deletions(-) (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 2b7da27ff17..015a761eaa3 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2927,6 +2927,13 @@ extern unsigned long sun4v_ncs_request(unsigned long request, #define HV_FAST_FIRE_GET_PERFREG 0x120 #define HV_FAST_FIRE_SET_PERFREG 0x121 +#define HV_FAST_REBOOT_DATA_SET 0x172 + +#ifndef __ASSEMBLY__ +extern unsigned long sun4v_reboot_data_set(unsigned long ra, + unsigned long len); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index dd1342c0a3b..490e5418740 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -15,12 +15,15 @@ #include #include +#include #include #include #include #include #include +#include "kernel.h" + #define DRV_MODULE_NAME "ds" #define PFX DRV_MODULE_NAME ": " #define DRV_MODULE_VERSION "1.0" @@ -828,18 +831,32 @@ void ldom_set_var(const char *var, const char *value) } } +static char full_boot_str[256] __attribute__((aligned(32))); +static int reboot_data_supported; + void ldom_reboot(const char *boot_command) { /* Don't bother with any of this if the boot_command * is empty. */ if (boot_command && strlen(boot_command)) { - char full_boot_str[256]; + unsigned long len; strcpy(full_boot_str, "boot "); strcpy(full_boot_str + strlen("boot "), boot_command); + len = strlen(full_boot_str); - ldom_set_var("reboot-command", full_boot_str); + if (reboot_data_supported) { + unsigned long ra = kimage_addr_to_ra(full_boot_str); + unsigned long hv_ret; + + hv_ret = sun4v_reboot_data_set(ra, len); + if (hv_ret != HV_EOK) + pr_err("SUN4V: Unable to set reboot data " + "hv_ret=%lu\n", hv_ret); + } else { + ldom_set_var("reboot-command", full_boot_str); + } } sun4v_mach_sir(); } @@ -1237,6 +1254,15 @@ static struct vio_driver ds_driver = { static int __init ds_init(void) { + unsigned long hv_ret, major, minor; + + hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor); + if (hv_ret == HV_EOK) { + pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n", + major, minor); + reboot_data_supported = 1; + } + kthread_run(ds_thread, NULL, "kldomd"); return vio_register_driver(&ds_driver); diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index 8a5f35ffb15..58d60de4d65 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -798,3 +798,10 @@ ENTRY(sun4v_niagara2_setperf) retl nop ENDPROC(sun4v_niagara2_setperf) + +ENTRY(sun4v_reboot_data_set) + mov HV_FAST_REBOOT_DATA_SET, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_reboot_data_set) diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h index 8325d775938..fd6c36b1df7 100644 --- a/arch/sparc/kernel/kernel.h +++ b/arch/sparc/kernel/kernel.h @@ -4,6 +4,8 @@ #include #include +#include +#include /* cpu.c */ extern const char *sparc_pmu_type; @@ -14,6 +16,13 @@ extern int ncpus_probed; /* setup_64.c */ struct seq_file; extern void cpucap_info(struct seq_file *); + +static inline unsigned long kimage_addr_to_ra(const char *p) +{ + unsigned long val = (unsigned long) p; + + return kern_base + (val - KERNBASE); +} #endif #ifdef CONFIG_SPARC32 diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c index 8cdbe5946b4..c59af546f52 100644 --- a/arch/sparc/kernel/sstate.c +++ b/arch/sparc/kernel/sstate.c @@ -14,14 +14,9 @@ #include #include -static int hv_supports_soft_state; - -static unsigned long kimage_addr_to_ra(const char *p) -{ - unsigned long val = (unsigned long) p; +#include "kernel.h" - return kern_base + (val - KERNBASE); -} +static int hv_supports_soft_state; static void do_set_sstate(unsigned long state, const char *msg) { -- cgit v1.2.3-70-g09d2 From 56d205cc5c0a3032a605121d4253e111193bf923 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 2 Aug 2011 20:23:34 -0700 Subject: sparc: Use popc when possible for ffs/__ffs/ffz. Signed-off-by: David S. Miller --- arch/sparc/include/asm/bitops_64.h | 7 ++-- arch/sparc/kernel/entry.h | 7 ++++ arch/sparc/kernel/setup_64.c | 32 ++++++++++----- arch/sparc/kernel/sparc_ksyms_64.c | 4 ++ arch/sparc/kernel/vmlinux.lds.S | 5 +++ arch/sparc/lib/Makefile | 2 +- arch/sparc/lib/ffs.S | 84 ++++++++++++++++++++++++++++++++++++++ 7 files changed, 126 insertions(+), 15 deletions(-) create mode 100644 arch/sparc/lib/ffs.S (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h index 3588807baa6..29011cc0e4b 100644 --- a/arch/sparc/include/asm/bitops_64.h +++ b/arch/sparc/include/asm/bitops_64.h @@ -26,16 +26,17 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr); #define smp_mb__before_clear_bit() barrier() #define smp_mb__after_clear_bit() barrier() -#include -#include #include #include #include #ifdef __KERNEL__ +extern int ffs(int x); +extern unsigned long __ffs(unsigned long); + +#include #include -#include /* * hweightN: returns the hamming weight (i.e. the number diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 16d1545d84f..e27f8ea8656 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -49,6 +49,13 @@ struct popc_3insn_patch_entry { extern struct popc_3insn_patch_entry __popc_3insn_patch, __popc_3insn_patch_end; +struct popc_6insn_patch_entry { + unsigned int addr; + unsigned int insns[6]; +}; +extern struct popc_6insn_patch_entry __popc_6insn_patch, + __popc_6insn_patch_end; + extern void __init per_cpu_patch(void); extern void __init sun4v_patch(void); extern void __init boot_cpu_id_too_large(int cpu); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 26d114187e1..3e9daea1653 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -275,24 +275,34 @@ void __init sun4v_patch(void) static void __init popc_patch(void) { struct popc_3insn_patch_entry *p3; + struct popc_6insn_patch_entry *p6; p3 = &__popc_3insn_patch; while (p3 < &__popc_3insn_patch_end) { - unsigned long addr = p3->addr; + unsigned long i, addr = p3->addr; - *(unsigned int *) (addr + 0) = p3->insns[0]; - wmb(); - __asm__ __volatile__("flush %0" : : "r" (addr + 0)); + for (i = 0; i < 3; i++) { + *(unsigned int *) (addr + (i * 4)) = p3->insns[i]; + wmb(); + __asm__ __volatile__("flush %0" + : : "r" (addr + (i * 4))); + } - *(unsigned int *) (addr + 4) = p3->insns[1]; - wmb(); - __asm__ __volatile__("flush %0" : : "r" (addr + 4)); + p3++; + } - *(unsigned int *) (addr + 8) = p3->insns[2]; - wmb(); - __asm__ __volatile__("flush %0" : : "r" (addr + 4)); + p6 = &__popc_6insn_patch; + while (p6 < &__popc_6insn_patch_end) { + unsigned long i, addr = p6->addr; - p3++; + for (i = 0; i < 6; i++) { + *(unsigned int *) (addr + (i * 4)) = p6->insns[i]; + wmb(); + __asm__ __volatile__("flush %0" + : : "r" (addr + (i * 4))); + } + + p6++; } } diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index d0ee65aced0..83b47ab02d9 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -45,5 +45,9 @@ EXPORT_SYMBOL(__arch_hweight16); EXPORT_SYMBOL(__arch_hweight32); EXPORT_SYMBOL(__arch_hweight64); +/* from ffs_ffz.S */ +EXPORT_SYMBOL(ffs); +EXPORT_SYMBOL(__ffs); + /* Exporting a symbol from /init/main.c */ EXPORT_SYMBOL(saved_command_line); diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index de20c14625e..94a954892d3 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -112,6 +112,11 @@ SECTIONS *(.popc_3insn_patch) __popc_3insn_patch_end = .; } + .popc_6insn_patch : { + __popc_6insn_patch = .; + *(.popc_6insn_patch) + __popc_6insn_patch_end = .; + } PERCPU_SECTION(SMP_CACHE_BYTES) . = ALIGN(PAGE_SIZE); diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 11c850a9b66..a3fc4375a15 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -37,7 +37,7 @@ 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) += mcount.o ipcsum.o xor.o hweight.o +lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-y += iomap.o obj-$(CONFIG_SPARC32) += atomic32.o diff --git a/arch/sparc/lib/ffs.S b/arch/sparc/lib/ffs.S new file mode 100644 index 00000000000..b39389f6989 --- /dev/null +++ b/arch/sparc/lib/ffs.S @@ -0,0 +1,84 @@ +#include + + .register %g2,#scratch + + .text + .align 32 + +ENTRY(ffs) + brnz,pt %o0, 1f + mov 1, %o1 + retl + clr %o0 + nop + nop +ENTRY(__ffs) + sllx %o0, 32, %g1 /* 1 */ + srlx %o0, 32, %g2 + + clr %o1 /* 2 */ + movrz %g1, %g2, %o0 + + movrz %g1, 32, %o1 /* 3 */ +1: clr %o2 + + sllx %o0, (64 - 16), %g1 /* 4 */ + srlx %o0, 16, %g2 + + movrz %g1, %g2, %o0 /* 5 */ + clr %o3 + + movrz %g1, 16, %o2 /* 6 */ + clr %o4 + + and %o0, 0xff, %g1 /* 7 */ + srlx %o0, 8, %g2 + + movrz %g1, %g2, %o0 /* 8 */ + clr %o5 + + movrz %g1, 8, %o3 /* 9 */ + add %o2, %o1, %o2 + + and %o0, 0xf, %g1 /* 10 */ + srlx %o0, 4, %g2 + + movrz %g1, %g2, %o0 /* 11 */ + add %o2, %o3, %o2 + + movrz %g1, 4, %o4 /* 12 */ + + and %o0, 0x3, %g1 /* 13 */ + srlx %o0, 2, %g2 + + movrz %g1, %g2, %o0 /* 14 */ + add %o2, %o4, %o2 + + movrz %g1, 2, %o5 /* 15 */ + + and %o0, 0x1, %g1 /* 16 */ + + add %o2, %o5, %o2 /* 17 */ + xor %g1, 0x1, %g1 + + retl /* 18 */ + add %o2, %g1, %o0 +ENDPROC(ffs) +ENDPROC(__ffs) + + .section .popc_6insn_patch, "ax" + .word ffs + brz,pn %o0, 98f + neg %o0, %g1 + xnor %o0, %g1, %o1 + popc %o1, %o0 +98: retl + nop + .word __ffs + neg %o0, %g1 + xnor %o0, %g1, %o1 + popc %o1, %o0 + retl + sub %o0, 1, %o0 + nop + .previous -- cgit v1.2.3-70-g09d2 From fabb5bd96d060da961d74531a0900da4da5ad2d4 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Thu, 4 Aug 2011 01:35:12 -0700 Subject: sparc: use kbuild-generic support for true asm-generic header files Signed-off-by: Sam Ravnborg Signed-off-by: David S. Miller --- arch/sparc/include/asm/Kbuild | 5 +++++ arch/sparc/include/asm/div64.h | 1 - arch/sparc/include/asm/irq_regs.h | 1 - arch/sparc/include/asm/local.h | 6 ------ arch/sparc/include/asm/local64.h | 1 - 5 files changed, 5 insertions(+), 9 deletions(-) delete mode 100644 arch/sparc/include/asm/div64.h delete mode 100644 arch/sparc/include/asm/irq_regs.h delete mode 100644 arch/sparc/include/asm/local.h delete mode 100644 arch/sparc/include/asm/local64.h (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 3c93f08ce18..2c2e38821f6 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -16,3 +16,8 @@ header-y += traps.h header-y += uctx.h header-y += utrap.h header-y += watchdog.h + +generic-y += div64.h +generic-y += local64.h +generic-y += irq_regs.h +generic-y += local.h diff --git a/arch/sparc/include/asm/div64.h b/arch/sparc/include/asm/div64.h deleted file mode 100644 index 6cd978cefb2..00000000000 --- a/arch/sparc/include/asm/div64.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/sparc/include/asm/irq_regs.h b/arch/sparc/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b7027..00000000000 --- a/arch/sparc/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/arch/sparc/include/asm/local.h b/arch/sparc/include/asm/local.h deleted file mode 100644 index bc80815a435..00000000000 --- a/arch/sparc/include/asm/local.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _SPARC_LOCAL_H -#define _SPARC_LOCAL_H - -#include - -#endif diff --git a/arch/sparc/include/asm/local64.h b/arch/sparc/include/asm/local64.h deleted file mode 100644 index 36c93b5cc23..00000000000 --- a/arch/sparc/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include -- cgit v1.2.3-70-g09d2 From 9076d0e7e02b98f7a65df10d1956326c8d8ba61a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 5 Aug 2011 00:53:57 -0700 Subject: sparc: Access kernel TSB using physical addressing when possible. On sun4v this is basically required since we point the hypervisor and the TSB walking hardware at these tables using physical addressing too. Signed-off-by: David S. Miller --- arch/sparc/include/asm/tsb.h | 51 +++++++++++++++++++---------------------- arch/sparc/kernel/ktlb.S | 24 +++++++++---------- arch/sparc/kernel/vmlinux.lds.S | 10 ++++++++ arch/sparc/mm/init_64.c | 40 +++++++++++++++++++++++++++++++- 4 files changed, 85 insertions(+), 40 deletions(-) (limited to 'arch/sparc/include') diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index 83c571d8c8a..1a8afd1ad04 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -133,29 +133,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; sub TSB, 0x8, TSB; \ TSB_STORE(TSB, TAG); -#define KTSB_LOAD_QUAD(TSB, REG) \ - ldda [TSB] ASI_NUCLEUS_QUAD_LDD, REG; - -#define KTSB_STORE(ADDR, VAL) \ - stxa VAL, [ADDR] ASI_N; - -#define KTSB_LOCK_TAG(TSB, REG1, REG2) \ -99: lduwa [TSB] ASI_N, REG1; \ - sethi %hi(TSB_TAG_LOCK_HIGH), REG2;\ - andcc REG1, REG2, %g0; \ - bne,pn %icc, 99b; \ - nop; \ - casa [TSB] ASI_N, REG1, REG2;\ - cmp REG1, REG2; \ - bne,pn %icc, 99b; \ - nop; \ - -#define KTSB_WRITE(TSB, TTE, TAG) \ - add TSB, 0x8, TSB; \ - stxa TTE, [TSB] ASI_N; \ - sub TSB, 0x8, TSB; \ - stxa TAG, [TSB] ASI_N; - /* Do a kernel page table walk. Leaves physical PTE pointer in * REG1. Jumps to FAIL_LABEL on early page table walk termination. * VADDR will not be clobbered, but REG2 will. @@ -239,6 +216,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; (KERNEL_TSB_SIZE_BYTES / 16) #define KERNEL_TSB4M_NENTRIES 4096 +#define KTSB_PHYS_SHIFT 15 + /* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL * on TSB hit. REG1, REG2, REG3, and REG4 are used as temporaries * and the found TTE will be left in REG1. REG3 and REG4 must @@ -247,13 +226,22 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * VADDR and TAG will be preserved and not clobbered by this macro. */ #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ - sethi %hi(swapper_tsb), REG1; \ +661: sethi %hi(swapper_tsb), REG1; \ or REG1, %lo(swapper_tsb), REG1; \ + .section .swapper_tsb_phys_patch, "ax"; \ + .word 661b; \ + .previous; \ +661: nop; \ + .section .tsb_ldquad_phys_patch, "ax"; \ + .word 661b; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + .previous; \ srlx VADDR, PAGE_SHIFT, REG2; \ and REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ - KTSB_LOAD_QUAD(REG2, REG3); \ + TSB_LOAD_QUAD(REG2, REG3); \ cmp REG3, TAG; \ be,a,pt %xcc, OK_LABEL; \ mov REG4, REG1; @@ -263,12 +251,21 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * we can make use of that for the index computation. */ #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ - sethi %hi(swapper_4m_tsb), REG1; \ +661: sethi %hi(swapper_4m_tsb), REG1; \ or REG1, %lo(swapper_4m_tsb), REG1; \ + .section .swapper_4m_tsb_phys_patch, "ax"; \ + .word 661b; \ + .previous; \ +661: nop; \ + .section .tsb_ldquad_phys_patch, "ax"; \ + .word 661b; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + .previous; \ and TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ - KTSB_LOAD_QUAD(REG2, REG3); \ + TSB_LOAD_QUAD(REG2, REG3); \ cmp REG3, TAG; \ be,a,pt %xcc, OK_LABEL; \ mov REG4, REG1; diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index 1d361477d7d..79f31036484 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -47,16 +47,16 @@ kvmap_itlb_tsb_miss: kvmap_itlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) /* Load and check PTE. */ ldxa [%g5] ASI_PHYS_USE_EC, %g5 mov 1, %g7 sllx %g7, TSB_TAG_INVALID_BIT, %g7 brgez,a,pn %g5, kvmap_itlb_longpath - KTSB_STORE(%g1, %g7) + TSB_STORE(%g1, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -102,9 +102,9 @@ kvmap_itlb_longpath: kvmap_itlb_obp: OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) ba,pt %xcc, kvmap_itlb_load nop @@ -112,17 +112,17 @@ kvmap_itlb_obp: kvmap_dtlb_obp: OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) ba,pt %xcc, kvmap_dtlb_load nop .align 32 kvmap_dtlb_tsb4m_load: - KTSB_LOCK_TAG(%g1, %g2, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_LOCK_TAG(%g1, %g2, %g7) + TSB_WRITE(%g1, %g5, %g6) ba,pt %xcc, kvmap_dtlb_load nop @@ -222,16 +222,16 @@ kvmap_linear_patch: kvmap_dtlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) /* Load and check PTE. */ ldxa [%g5] ASI_PHYS_USE_EC, %g5 mov 1, %g7 sllx %g7, TSB_TAG_INVALID_BIT, %g7 brgez,a,pn %g5, kvmap_dtlb_longpath - KTSB_STORE(%g1, %g7) + TSB_STORE(%g1, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 94a954892d3..0e1605697b4 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -107,6 +107,16 @@ SECTIONS *(.sun4v_2insn_patch) __sun4v_2insn_patch_end = .; } + .swapper_tsb_phys_patch : { + __swapper_tsb_phys_patch = .; + *(.swapper_tsb_phys_patch) + __swapper_tsb_phys_patch_end = .; + } + .swapper_4m_tsb_phys_patch : { + __swapper_4m_tsb_phys_patch = .; + *(.swapper_4m_tsb_phys_patch) + __swapper_4m_tsb_phys_patch_end = .; + } .popc_3insn_patch : { __popc_3insn_patch = .; *(.popc_3insn_patch) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 3fd8e18bed8..adfac23d976 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1597,6 +1597,42 @@ static void __init tsb_phys_patch(void) static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR]; extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; +static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa) +{ + pa >>= KTSB_PHYS_SHIFT; + + while (start < end) { + unsigned int *ia = (unsigned int *)(unsigned long)*start; + + ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10); + __asm__ __volatile__("flush %0" : : "r" (ia)); + + ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 1)); + + start++; + } +} + +static void ktsb_phys_patch(void) +{ + extern unsigned int __swapper_tsb_phys_patch; + extern unsigned int __swapper_tsb_phys_patch_end; + extern unsigned int __swapper_4m_tsb_phys_patch; + extern unsigned int __swapper_4m_tsb_phys_patch_end; + unsigned long ktsb_pa; + + ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE); + patch_one_ktsb_phys(&__swapper_tsb_phys_patch, + &__swapper_tsb_phys_patch_end, ktsb_pa); +#ifndef CONFIG_DEBUG_PAGEALLOC + ktsb_pa = (kern_base + + ((unsigned long)&swapper_4m_tsb[0] - KERNBASE)); + patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch, + &__swapper_4m_tsb_phys_patch_end, ktsb_pa); +#endif +} + static void __init sun4v_ktsb_init(void) { unsigned long ktsb_pa; @@ -1716,8 +1752,10 @@ void __init paging_init(void) sun4u_pgprot_init(); if (tlb_type == cheetah_plus || - tlb_type == hypervisor) + tlb_type == hypervisor) { tsb_phys_patch(); + ktsb_phys_patch(); + } if (tlb_type == hypervisor) { sun4v_patch_tlb_handlers(); -- cgit v1.2.3-70-g09d2