diff options
Diffstat (limited to 'arch')
317 files changed, 6934 insertions, 3382 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 72f2fa1..a62965d 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -222,6 +222,19 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_PERF_REGS + bool + help + Support selective register dumps for perf events. This includes + bit-mapping of each registers and a unique architecture id. + +config HAVE_PERF_USER_STACK_DUMP + bool + help + Support user stack dumps for perf event samples. This needs + access to the user stack pointer which is not unified across + architectures. + config HAVE_ARCH_JUMP_LABEL bool @@ -281,4 +294,23 @@ config SECCOMP_FILTER See Documentation/prctl/seccomp_filter.txt for details. +config HAVE_RCU_USER_QS + bool + help + Provide kernel entry/exit hooks necessary for userspace + RCU extended quiescent state. Syscalls need to be wrapped inside + rcu_user_exit()-rcu_user_enter() through the slow path using + TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs + are already protected inside rcu_irq_enter/rcu_irq_exit() but + preemption or signal handling on irq exit still need to be protected. + +config HAVE_VIRT_CPU_ACCOUNTING + bool + +config HAVE_IRQ_TIME_ACCOUNTING + bool + help + Archs need to ensure they use a high enough resolution clock to + support irq time accounting and then call enable_sched_clock_irqtime(). + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index d6fde98..83638aa 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -28,6 +28,7 @@ #include <linux/tty.h> #include <linux/console.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <asm/reg.h> #include <asm/uaccess.h> @@ -54,9 +55,12 @@ cpu_idle(void) /* FIXME -- EV6 and LCA45 know how to power down the CPU. */ + rcu_idle_enter(); while (!need_resched()) cpu_relax(); - schedule(); + + rcu_idle_exit(); + schedule_preempt_disabled(); } } diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 35ddc02..a41ad90 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -166,6 +166,7 @@ smp_callin(void) DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n", cpuid, current, current->active_mm)); + preempt_disable(); /* Do nothing. */ cpu_idle(); } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c5f9ae5..2f88d8d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -6,7 +6,7 @@ config ARM select HAVE_DMA_API_DEBUG select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7) + select HAVE_DMA_CONTIGUOUS if MMU select HAVE_MEMBLOCK select RTC_LIB select SYS_SUPPORTS_APM_EMULATION diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index f15f82b..e968a52 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -356,15 +356,15 @@ choice is nothing connected to read from the DCC. config DEBUG_SEMIHOSTING - bool "Kernel low-level debug output via semihosting I" + bool "Kernel low-level debug output via semihosting I/O" help Semihosting enables code running on an ARM target to use the I/O facilities on a host debugger/emulator through a - simple SVC calls. The host debugger or emulator must have + simple SVC call. The host debugger or emulator must have semihosting enabled for the special svc call to be trapped otherwise the kernel will crash. - This is known to work with OpenOCD, as wellas + This is known to work with OpenOCD, as well as ARM's Fast Models, or any other controlling environment that implements semihosting. diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 30eae87..a051dfb 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -284,10 +284,10 @@ zImage Image xipImage bootpImage uImage: vmlinux zinstall uinstall install: vmlinux $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@ -%.dtb: +%.dtb: scripts $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@ -dtbs: +dtbs: scripts $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@ # We use MRPROPER_FILES and CLEAN_FILES now diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index b8c64b8..bc67cbf 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -653,16 +653,21 @@ __armv7_mmu_cache_on: mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs #endif mrc p15, 0, r0, c1, c0, 0 @ read control reg + bic r0, r0, #1 << 28 @ clear SCTLR.TRE orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x003c @ write buffer #ifdef CONFIG_MMU #ifdef CONFIG_CPU_ENDIAN_BE8 orr r0, r0, #1 << 25 @ big-endian page tables #endif + mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg orrne r0, r0, #1 @ MMU enabled movne r1, #0xfffffffd @ domain 0 = client + bic r6, r6, #1 << 31 @ 32-bit translation system + bic r6, r6, #3 << 0 @ use only ttbr0 mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer mcrne p15, 0, r1, c3, c0, 0 @ load domain access control + mcrne p15, 0, r6, c2, c0, 2 @ load ttb control #endif mcr p15, 0, r0, c7, c5, 4 @ ISB mcr p15, 0, r0, c1, c0, 0 @ load control register diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi index 66389c1..7c95f76 100644 --- a/arch/arm/boot/dts/at91sam9260.dtsi +++ b/arch/arm/boot/dts/at91sam9260.dtsi @@ -104,6 +104,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff600 { @@ -113,6 +114,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff800 { @@ -122,6 +124,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@fffff200 { diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index b460d6c..195019b 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -95,6 +95,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff400 { @@ -104,6 +105,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff600 { @@ -113,6 +115,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffff800 { @@ -122,6 +125,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioE: gpio@fffffa00 { @@ -131,6 +135,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@ffffee00 { diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts index 7829a4d..96514c1 100644 --- a/arch/arm/boot/dts/at91sam9g25ek.dts +++ b/arch/arm/boot/dts/at91sam9g25ek.dts @@ -15,7 +15,7 @@ compatible = "atmel,at91sam9g25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9"; chosen { - bootargs = "128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs"; + bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs"; }; ahb { diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi index bafa880..63751b1 100644 --- a/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/arch/arm/boot/dts/at91sam9g45.dtsi @@ -113,6 +113,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff400 { @@ -122,6 +123,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff600 { @@ -131,6 +133,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffff800 { @@ -140,6 +143,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioE: gpio@fffffa00 { @@ -149,6 +153,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@ffffee00 { diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi index bfac0df..ef9336a 100644 --- a/arch/arm/boot/dts/at91sam9n12.dtsi +++ b/arch/arm/boot/dts/at91sam9n12.dtsi @@ -107,6 +107,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff600 { @@ -116,6 +117,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff800 { @@ -125,6 +127,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffffa00 { @@ -134,6 +137,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@fffff200 { diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 4a18c39..8a387a8 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -115,6 +115,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff600 { @@ -124,6 +125,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff800 { @@ -133,6 +135,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffffa00 { @@ -142,6 +145,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@fffff200 { diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig index 7d87184..90610c7 100644 --- a/arch/arm/configs/armadillo800eva_defconfig +++ b/arch/arm/configs/armadillo800eva_defconfig @@ -33,7 +33,7 @@ CONFIG_AEABI=y CONFIG_FORCE_MAX_ZONEORDER=13 CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096" +CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096 rw" CONFIG_CMDLINE_FORCE=y CONFIG_KEXEC=y CONFIG_VFP=y diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 03fb936..5c8b3bf4 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -320,4 +320,12 @@ .size \name , . - \name .endm + .macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req +#ifndef CONFIG_CPU_USE_DOMAINS + adds \tmp, \addr, #\size - 1 + sbcccs \tmp, \tmp, \limit + bcs \bad +#endif + .endm + #endif /* __ASM_ASSEMBLER_H__ */ diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 2ae842d..5c44dcb 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -203,6 +203,13 @@ static inline void dma_free_writecombine(struct device *dev, size_t size, } /* + * This can be called during early boot to increase the size of the atomic + * coherent DMA pool above the default value of 256KiB. It must be called + * before postcore_initcall. + */ +extern void __init init_dma_coherent_pool_size(unsigned long size); + +/* * This can be called during boot to increase the size of the consistent * DMA region above it's default value of 2MB. It must be called before the * memory allocator is initialised, i.e. before any core_initcall. diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index e965f1b..5f6ddcc 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -187,6 +187,7 @@ static inline unsigned long __phys_to_virt(unsigned long x) #define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET) #endif #endif +#endif /* __ASSEMBLY__ */ #ifndef PHYS_OFFSET #ifdef PLAT_PHYS_OFFSET @@ -196,6 +197,8 @@ static inline unsigned long __phys_to_virt(unsigned long x) #endif #endif +#ifndef __ASSEMBLY__ + /* * PFNs are used to describe any physical page; this means * PFN 0 == physical address 0. diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 314d466..99a1951 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -199,6 +199,9 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, { pgtable_page_dtor(pte); +#ifdef CONFIG_ARM_LPAE + tlb_add_flush(tlb, addr); +#else /* * With the classic ARM MMU, a pte page has two corresponding pmd * entries, each covering 1MB. @@ -206,6 +209,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, addr &= PMD_MASK; tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE); tlb_add_flush(tlb, addr + SZ_1M); +#endif tlb_remove_page(tlb, pte); } diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 479a635..77bd79f 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -101,28 +101,39 @@ extern int __get_user_1(void *); extern int __get_user_2(void *); extern int __get_user_4(void *); -#define __get_user_x(__r2,__p,__e,__s,__i...) \ +#define __GUP_CLOBBER_1 "lr", "cc" +#ifdef CONFIG_CPU_USE_DOMAINS +#define __GUP_CLOBBER_2 "ip", "lr", "cc" +#else +#define __GUP_CLOBBER_2 "lr", "cc" +#endif +#define __GUP_CLOBBER_4 "lr", "cc" + +#define __get_user_x(__r2,__p,__e,__l,__s) \ __asm__ __volatile__ ( \ __asmeq("%0", "r0") __asmeq("%1", "r2") \ + __asmeq("%3", "r1") \ "bl __get_user_" #__s \ : "=&r" (__e), "=r" (__r2) \ - : "0" (__p) \ - : __i, "cc") + : "0" (__p), "r" (__l) \ + : __GUP_CLOBBER_##__s) -#define get_user(x,p) \ +#define __get_user_check(x,p) \ ({ \ + unsigned long __limit = current_thread_info()->addr_limit - 1; \ register const typeof(*(p)) __user *__p asm("r0") = (p);\ register unsigned long __r2 asm("r2"); \ + register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ switch (sizeof(*(__p))) { \ case 1: \ - __get_user_x(__r2, __p, __e, 1, "lr"); \ - break; \ + __get_user_x(__r2, __p, __e, __l, 1); \ + break; \ case 2: \ - __get_user_x(__r2, __p, __e, 2, "r3", "lr"); \ + __get_user_x(__r2, __p, __e, __l, 2); \ break; \ case 4: \ - __get_user_x(__r2, __p, __e, 4, "lr"); \ + __get_user_x(__r2, __p, __e, __l, 4); \ break; \ default: __e = __get_user_bad(); break; \ } \ @@ -130,42 +141,57 @@ extern int __get_user_4(void *); __e; \ }) +#define get_user(x,p) \ + ({ \ + might_fault(); \ + __get_user_check(x,p); \ + }) + extern int __put_user_1(void *, unsigned int); extern int __put_user_2(void *, unsigned int); extern int __put_user_4(void *, unsigned int); extern int __put_user_8(void *, unsigned long long); -#define __put_user_x(__r2,__p,__e,__s) \ +#define __put_user_x(__r2,__p,__e,__l,__s) \ __asm__ __volatile__ ( \ __asmeq("%0", "r0") __asmeq("%2", "r2") \ + __asmeq("%3", "r1") \ "bl __put_user_" #__s \ : "=&r" (__e) \ - : "0" (__p), "r" (__r2) \ + : "0" (__p), "r" (__r2), "r" (__l) \ : "ip", "lr", "cc") -#define put_user(x,p) \ +#define __put_user_check(x,p) \ ({ \ + unsigned long __limit = current_thread_info()->addr_limit - 1; \ register const typeof(*(p)) __r2 asm("r2") = (x); \ register const typeof(*(p)) __user *__p asm("r0") = (p);\ + register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ switch (sizeof(*(__p))) { \ case 1: \ - __put_user_x(__r2, __p, __e, 1); \ + __put_user_x(__r2, __p, __e, __l, 1); \ break; \ case 2: \ - __put_user_x(__r2, __p, __e, 2); \ + __put_user_x(__r2, __p, __e, __l, 2); \ break; \ case 4: \ - __put_user_x(__r2, __p, __e, 4); \ + __put_user_x(__r2, __p, __e, __l, 4); \ break; \ case 8: \ - __put_user_x(__r2, __p, __e, 8); \ + __put_user_x(__r2, __p, __e, __l, 8); \ break; \ default: __e = __put_user_bad(); break; \ } \ __e; \ }) +#define put_user(x,p) \ + ({ \ + might_fault(); \ + __put_user_check(x,p); \ + }) + #else /* CONFIG_MMU */ /* @@ -219,6 +245,7 @@ do { \ unsigned long __gu_addr = (unsigned long)(ptr); \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ + might_fault(); \ switch (sizeof(*(ptr))) { \ case 1: __get_user_asm_byte(__gu_val,__gu_addr,err); break; \ case 2: __get_user_asm_half(__gu_val,__gu_addr,err); break; \ @@ -300,6 +327,7 @@ do { \ unsigned long __pu_addr = (unsigned long)(ptr); \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ + might_fault(); \ switch (sizeof(*(ptr))) { \ case 1: __put_user_asm_byte(__pu_val,__pu_addr,err); break; \ case 2: __put_user_asm_half(__pu_val,__pu_addr,err); break; \ diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 0cab47d..2fde5fd 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -404,6 +404,7 @@ #define __NR_setns (__NR_SYSCALL_BASE+375) #define __NR_process_vm_readv (__NR_SYSCALL_BASE+376) #define __NR_process_vm_writev (__NR_SYSCALL_BASE+377) + /* 378 for kcmp */ /* * The following SWIs are ARM private. @@ -483,6 +484,7 @@ */ #define __IGNORE_fadvise64_64 #define __IGNORE_migrate_pages +#define __IGNORE_kcmp #endif /* __KERNEL__ */ #endif /* __ASM_ARM_UNISTD_H */ diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 463ff4a..e337879 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -387,6 +387,7 @@ /* 375 */ CALL(sys_setns) CALL(sys_process_vm_readv) CALL(sys_process_vm_writev) + CALL(sys_ni_syscall) /* reserved for sys_kcmp */ #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index ba386bd..281bf33 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -159,6 +159,12 @@ static int debug_arch_supported(void) arch >= ARM_DEBUG_ARCH_V7_1; } +/* Can we determine the watchpoint access type from the fsr? */ +static int debug_exception_updates_fsr(void) +{ + return 0; +} + /* Determine number of WRP registers available. */ static int get_num_wrp_resources(void) { @@ -604,13 +610,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) /* Aligned */ break; case 1: - /* Allow single byte watchpoint. */ - if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) - break; case 2: /* Allow halfword watchpoints and breakpoints. */ if (info->ctrl.len == ARM_BREAKPOINT_LEN_2) break; + case 3: + /* Allow single byte watchpoint. */ + if (info->ctrl.len == ARM_BREAKPOINT_LEN_1) + break; default: ret = -EINVAL; goto out; @@ -619,18 +626,35 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) info->address &= ~alignment_mask; info->ctrl.len <<= offset; - /* - * Currently we rely on an overflow handler to take - * care of single-stepping the breakpoint when it fires. - * In the case of userspace breakpoints on a core with V7 debug, - * we can use the mismatch feature as a poor-man's hardware - * single-step, but this only works for per-task breakpoints. - */ - if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) || - !core_has_mismatch_brps() || !bp->hw.bp_target)) { - pr_warning("overflow handler required but none found\n"); - ret = -EINVAL; + if (!bp->overflow_handler) { + /* + * Mismatch breakpoints are required for single-stepping + * breakpoints. + */ + if (!core_has_mismatch_brps()) + return -EINVAL; + + /* We don't allow mismatch breakpoints in kernel space. */ + if (arch_check_bp_in_kernelspace(bp)) + return -EPERM; + + /* + * Per-cpu breakpoints are not supported by our stepping + * mechanism. + */ + if (!bp->hw.bp_target) + return -EINVAL; + + /* + * We only support specific access types if the fsr + * reports them. + */ + if (!debug_exception_updates_fsr() && + (info->ctrl.type == ARM_BREAKPOINT_LOAD || + info->ctrl.type == ARM_BREAKPOINT_STORE)) + return -EINVAL; } + out: return ret; } @@ -706,10 +730,12 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, goto unlock; /* Check that the access type matches. */ - access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W : - HW_BREAKPOINT_R; - if (!(access & hw_breakpoint_type(wp))) - goto unlock; + if (debug_exception_updates_fsr()) { + access = (fsr & ARM_FSR_ACCESS_MASK) ? + HW_BREAKPOINT_W : HW_BREAKPOINT_R; + if (!(access & hw_breakpoint_type(wp))) + goto unlock; + } /* We have a winner. */ info->trigger = addr; diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index fef42b2..e1f9069 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -11,7 +11,6 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/clk.h> -#include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/err.h> @@ -96,7 +95,52 @@ static void twd_timer_stop(struct clock_event_device *clk) disable_percpu_irq(clk->irq); } -#ifdef CONFIG_CPU_FREQ +#ifdef CONFIG_COMMON_CLK + +/* + * Updates clockevent frequency when the cpu frequency changes. + * Called on the cpu that is changing frequency with interrupts disabled. + */ +static void twd_update_frequency(void *new_rate) +{ + twd_timer_rate = *((unsigned long *) new_rate); + + clockevents_update_freq(*__this_cpu_ptr(twd_evt), twd_timer_rate); +} + +static int twd_rate_change(struct notifier_block *nb, + unsigned long flags, void *data) +{ + struct clk_notifier_data *cnd = data; + + /* + * The twd clock events must be reprogrammed to account for the new + * frequency. The timer is local to a cpu, so cross-call to the + * changing cpu. + */ + if (flags == POST_RATE_CHANGE) + smp_call_function(twd_update_frequency, + (void *)&cnd->new_rate, 1); + + return NOTIFY_OK; +} + +static struct notifier_block twd_clk_nb = { + .notifier_call = twd_rate_change, +}; + +static int twd_clk_init(void) +{ + if (twd_evt && *__this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) + return clk_notifier_register(twd_clk, &twd_clk_nb); + + return 0; +} +core_initcall(twd_clk_init); + +#elif defined (CONFIG_CPU_FREQ) + +#include <linux/cpufreq.h> /* * Updates clockevent frequency when the cpu frequency changes. diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index f794521..b0179b8 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -420,20 +420,23 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) #endif instr = *(u32 *) pc; } else if (thumb_mode(regs)) { - get_user(instr, (u16 __user *)pc); + if (get_user(instr, (u16 __user *)pc)) + goto die_sig; if (is_wide_instruction(instr)) { unsigned int instr2; - get_user(instr2, (u16 __user *)pc+1); + if (get_user(instr2, (u16 __user *)pc+1)) + goto die_sig; instr <<= 16; instr |= instr2; } - } else { - get_user(instr, (u32 __user *)pc); + } else if (get_user(instr, (u32 __user *)pc)) { + goto die_sig; } if (call_undef_hook(regs, instr) == 0) return; +die_sig: #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_UNDEFINED) { printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n", diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c index d6dacc6..395d5fb 100644 --- a/arch/arm/lib/delay.c +++ b/arch/arm/lib/delay.c @@ -59,6 +59,7 @@ void __init init_current_timer_delay(unsigned long freq) { pr_info("Switching to timer-based delay loop\n"); lpj_fine = freq / HZ; + loops_per_jiffy = lpj_fine; arm_delay_ops.delay = __timer_delay; arm_delay_ops.const_udelay = __timer_const_udelay; arm_delay_ops.udelay = __timer_udelay; diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index 11093a7..9b06bb4 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -16,8 +16,9 @@ * __get_user_X * * Inputs: r0 contains the address + * r1 contains the address limit, which must be preserved * Outputs: r0 is the error code - * r2, r3 contains the zero-extended value + * r2 contains the zero-extended value * lr corrupted * * No other registers must be altered. (see <asm/uaccess.h> @@ -27,33 +28,39 @@ * Note also that it is intended that __get_user_bad is not global. */ #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/errno.h> #include <asm/domain.h> ENTRY(__get_user_1) + check_uaccess r0, 1, r1, r2, __get_user_bad 1: TUSER(ldrb) r2, [r0] mov r0, #0 mov pc, lr ENDPROC(__get_user_1) ENTRY(__get_user_2) -#ifdef CONFIG_THUMB2_KERNEL -2: TUSER(ldrb) r2, [r0] -3: TUSER(ldrb) r3, [r0, #1] + check_uaccess r0, 2, r1, r2, __get_user_bad +#ifdef CONFIG_CPU_USE_DOMAINS +rb .req ip +2: ldrbt r2, [r0], #1 +3: ldrbt rb, [r0], #0 #else -2: TUSER(ldrb) r2, [r0], #1 -3: TUSER(ldrb) r3, [r0] +rb .req r0 +2: ldrb r2, [r0] +3: ldrb rb, [r0, #1] #endif #ifndef __ARMEB__ - orr r2, r2, r3, lsl #8 + orr r2, r2, rb, lsl #8 #else - orr r2, r3, r2, lsl #8 + orr r2, rb, r2, lsl #8 #endif mov r0, #0 mov pc, lr ENDPROC(__get_user_2) ENTRY(__get_user_4) + check_uaccess r0, 4, r1, r2, __get_user_bad 4: TUSER(ldr) r2, [r0] mov r0, #0 mov pc, lr diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S index 7db2599..3d73dcb 100644 --- a/arch/arm/lib/putuser.S +++ b/arch/arm/lib/putuser.S @@ -16,6 +16,7 @@ * __put_user_X * * Inputs: r0 contains the address + * r1 contains the address limit, which must be preserved * r2, r3 contains the value * Outputs: r0 is the error code * lr corrupted @@ -27,16 +28,19 @@ * Note also that it is intended that __put_user_bad is not global. */ #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/errno.h> #include <asm/domain.h> ENTRY(__put_user_1) + check_uaccess r0, 1, r1, ip, __put_user_bad 1: TUSER(strb) r2, [r0] mov r0, #0 mov pc, lr ENDPROC(__put_user_1) ENTRY(__put_user_2) + check_uaccess r0, 2, r1, ip, __put_user_bad mov ip, r2, lsr #8 #ifdef CONFIG_THUMB2_KERNEL #ifndef __ARMEB__ @@ -60,12 +64,14 @@ ENTRY(__put_user_2) ENDPROC(__put_user_2) ENTRY(__put_user_4) + check_uaccess r0, 4, r1, ip, __put_user_bad 4: TUSER(str) r2, [r0] mov r0, #0 mov pc, lr ENDPROC(__put_user_4) ENTRY(__put_user_8) + check_uaccess r0, 8, r1, ip, __put_user_bad #ifdef CONFIG_THUMB2_KERNEL 5: TUSER(str) r2, [r0] 6: TUSER(str) r3, [r0, #4] diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c index 104ca40..aaa443b 100644 --- a/arch/arm/mach-at91/at91rm9200_time.c +++ b/arch/arm/mach-at91/at91rm9200_time.c @@ -197,7 +197,7 @@ void __init at91rm9200_timer_init(void) at91_st_read(AT91_ST_SR); /* Make IRQs happen for the system timer */ - setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq); + setup_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq); /* The 32KiHz "Slow Clock" (tick every 30517.58 nanoseconds) is used * directly for the clocksource and all clockevents, after adjusting diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c index 7b9c2ba..bce572a 100644 --- a/arch/arm/mach-at91/at91sam9260_devices.c +++ b/arch/arm/mach-at91/at91sam9260_devices.c @@ -726,6 +726,8 @@ static struct resource rtt_resources[] = { .flags = IORESOURCE_MEM, }, { .flags = IORESOURCE_MEM, + }, { + .flags = IORESOURCE_IRQ, }, }; @@ -744,10 +746,12 @@ static void __init at91_add_device_rtt_rtc(void) * The second resource is needed: * GPBR will serve as the storage for RTC time offset */ - at91sam9260_rtt_device.num_resources = 2; + at91sam9260_rtt_device.num_resources = 3; rtt_resources[1].start = AT91SAM9260_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR; rtt_resources[1].end = rtt_resources[1].start + 3; + rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS; + rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS; } #else static void __init at91_add_device_rtt_rtc(void) diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c index 8df5c1bd..bc2590d 100644 --- a/arch/arm/mach-at91/at91sam9261_devices.c +++ b/arch/arm/mach-at91/at91sam9261_devices.c @@ -609,6 +609,8 @@ static struct resource rtt_resources[] = { .flags = IORESOURCE_MEM, }, { .flags = IORESOURCE_MEM, + }, { + .flags = IORESOURCE_IRQ, } }; @@ -626,10 +628,12 @@ static void __init at91_add_device_rtt_rtc(void) * The second resource is needed: * GPBR will serve as the storage for RTC time offset */ - at91sam9261_rtt_device.num_resources = 2; + at91sam9261_rtt_device.num_resources = 3; rtt_resources[1].start = AT91SAM9261_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR; rtt_resources[1].end = rtt_resources[1].start + 3; + rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS; + rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS; } #else static void __init at91_add_device_rtt_rtc(void) diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c index eb6bbf8..9b6ca73 100644 --- a/arch/arm/mach-at91/at91sam9263_devices.c +++ b/arch/arm/mach-at91/at91sam9263_devices.c @@ -990,6 +990,8 @@ static struct resource rtt0_resources[] = { .flags = IORESOURCE_MEM, }, { .flags = IORESOURCE_MEM, + }, { + .flags = IORESOURCE_IRQ, } }; @@ -1006,6 +1008,8 @@ static struct resource rtt1_resources[] = { .flags = IORESOURCE_MEM, }, { .flags = IORESOURCE_MEM, + }, { + .flags = IORESOURCE_IRQ, } }; @@ -1027,14 +1031,14 @@ static void __init at91_add_device_rtt_rtc(void) * The second resource is needed only for the chosen RTT: * GPBR will serve as the storage for RTC time offset */ - at91sam9263_rtt0_device.num_resources = 2; + at91sam9263_rtt0_device.num_resources = 3; at91sam9263_rtt1_device.num_resources = 1; pdev = &at91sam9263_rtt0_device; r = rtt0_resources; break; case 1: at91sam9263_rtt0_device.num_resources = 1; - at91sam9263_rtt1_device.num_resources = 2; + at91sam9263_rtt1_device.num_resources = 3; pdev = &at91sam9263_rtt1_device; r = rtt1_resources; break; @@ -1047,6 +1051,8 @@ static void __init at91_add_device_rtt_rtc(void) pdev->name = "rtc-at91sam9"; r[1].start = AT91SAM9263_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR; r[1].end = r[1].start + 3; + r[2].start = NR_IRQS_LEGACY + AT91_ID_SYS; + r[2].end = NR_IRQS_LEGACY + AT91_ID_SYS; } #else static void __init at91_add_device_rtt_rtc(void) diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c index 0607399..1b47319 100644 --- a/arch/arm/mach-at91/at91sam9g45_devices.c +++ b/arch/arm/mach-at91/at91sam9g45_devices.c @@ -1293,6 +1293,8 @@ static struct resource rtt_resources[] = { .flags = IORESOURCE_MEM, }, { .flags = IORESOURCE_MEM, + }, { + .flags = IORESOURCE_IRQ, } }; @@ -1310,10 +1312,12 @@ static void __init at91_add_device_rtt_rtc(void) * The second resource is needed: * GPBR will serve as the storage for RTC time offset */ - at91sam9g45_rtt_device.num_resources = 2; + at91sam9g45_rtt_device.num_resources = 3; rtt_resources[1].start = AT91SAM9G45_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR; rtt_resources[1].end = rtt_resources[1].start + 3; + rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS; + rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS; } #else static void __init at91_add_device_rtt_rtc(void) diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c index f09fff9..b3d365d 100644 --- a/arch/arm/mach-at91/at91sam9rl_devices.c +++ b/arch/arm/mach-at91/at91sam9rl_devices.c @@ -688,6 +688,8 @@ static struct resource rtt_resources[] = { .flags = IORESOURCE_MEM, }, { .flags = IORESOURCE_MEM, + }, { + .flags = IORESOURCE_IRQ, } }; @@ -705,10 +707,12 @@ static void __init at91_add_device_rtt_rtc(void) * The second resource is needed: * GPBR will serve as the storage for RTC time offset */ - at91sam9rl_rtt_device.num_resources = 2; + at91sam9rl_rtt_device.num_resources = 3; rtt_resources[1].start = AT91SAM9RL_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR; rtt_resources[1].end = rtt_resources[1].start + 3; + rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS; + rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS; } #else static void __init at91_add_device_rtt_rtc(void) diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c index de2ec6b..188c829 100644 --- a/arch/arm/mach-at91/clock.c +++ b/arch/arm/mach-at91/clock.c @@ -63,6 +63,12 @@ EXPORT_SYMBOL_GPL(at91_pmc_base); #define cpu_has_300M_plla() (cpu_is_at91sam9g10()) +#define cpu_has_240M_plla() (cpu_is_at91sam9261() \ + || cpu_is_at91sam9263() \ + || cpu_is_at91sam9rl()) + +#define cpu_has_210M_plla() (cpu_is_at91sam9260()) + #define cpu_has_pllb() (!(cpu_is_at91sam9rl() \ || cpu_is_at91sam9g45() \ || cpu_is_at91sam9x5() \ @@ -706,6 +712,12 @@ static int __init at91_pmc_init(unsigned long main_clock) } else if (cpu_has_800M_plla()) { if (plla.rate_hz > 800000000) pll_overclock = true; + } else if (cpu_has_240M_plla()) { + if (plla.rate_hz > 240000000) + pll_overclock = true; + } else if (cpu_has_210M_plla()) { + if (plla.rate_hz > 210000000) + pll_overclock = true; } else { if (plla.rate_hz > 209000000) pll_overclock = true; diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c index ca70e5f..020852d 100644 --- a/arch/arm/mach-gemini/irq.c +++ b/arch/arm/mach-gemini/irq.c @@ -17,6 +17,7 @@ #include <linux/sched.h> #include <asm/irq.h> #include <asm/mach/irq.h> +#include <asm/system_misc.h> #include <mach/hardware.h> #define IRQ_SOURCE(base_addr) (base_addr + 0x00) diff --git a/arch/arm/mach-imx/clk-imx25.c b/arch/arm/mach-imx/clk-imx25.c index fdd8cc8..d20d479 100644 --- a/arch/arm/mach-imx/clk-imx25.c +++ b/arch/arm/mach-imx/clk-imx25.c @@ -222,10 +222,8 @@ int __init mx25_clocks_init(void) clk_register_clkdev(clk[lcdc_ipg], "ipg", "imx-fb.0"); clk_register_clkdev(clk[lcdc_ahb], "ahb", "imx-fb.0"); clk_register_clkdev(clk[wdt_ipg], NULL, "imx2-wdt.0"); - clk_register_clkdev(clk[ssi1_ipg_per], "per", "imx-ssi.0"); - clk_register_clkdev(clk[ssi1_ipg], "ipg", "imx-ssi.0"); - clk_register_clkdev(clk[ssi2_ipg_per], "per", "imx-ssi.1"); - clk_register_clkdev(clk[ssi2_ipg], "ipg", "imx-ssi.1"); + clk_register_clkdev(clk[ssi1_ipg], NULL, "imx-ssi.0"); + clk_register_clkdev(clk[ssi2_ipg], NULL, "imx-ssi.1"); clk_register_clkdev(clk[esdhc1_ipg_per], "per", "sdhci-esdhc-imx25.0"); clk_register_clkdev(clk[esdhc1_ipg], "ipg", "sdhci-esdhc-imx25.0"); clk_register_clkdev(clk[esdhc1_ahb], "ahb", "sdhci-esdhc-imx25.0"); @@ -243,6 +241,6 @@ int __init mx25_clocks_init(void) clk_register_clkdev(clk[sdma_ahb], "ahb", "imx35-sdma"); clk_register_clkdev(clk[iim_ipg], "iim", NULL); - mxc_timer_init(MX25_IO_ADDRESS(MX25_GPT1_BASE_ADDR), 54); + mxc_timer_init(MX25_IO_ADDRESS(MX25_GPT1_BASE_ADDR), MX25_INT_GPT1); return 0; } diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index c6422fb..65fb8bc 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -230,10 +230,8 @@ int __init mx35_clocks_init() clk_register_clkdev(clk[ipu_gate], NULL, "mx3_sdc_fb"); clk_register_clkdev(clk[owire_gate], NULL, "mxc_w1"); clk_register_clkdev(clk[sdma_gate], NULL, "imx35-sdma"); - clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.0"); - clk_register_clkdev(clk[ssi1_div_post], "per", "imx-ssi.0"); - clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.1"); - clk_register_clkdev(clk[ssi2_div_post], "per", "imx-ssi.1"); + clk_register_clkdev(clk[ssi1_gate], NULL, "imx-ssi.0"); + clk_register_clkdev(clk[ssi2_gate], NULL, "imx-ssi.1"); /* i.mx35 has the i.mx21 type uart */ clk_register_clkdev(clk[uart1_gate], "per", "imx21-uart.0"); clk_register_clkdev(clk[ipg], "ipg", "imx21-uart.0"); diff --git a/arch/arm/mach-imx/mach-armadillo5x0.c b/arch/arm/mach-imx/mach-armadillo5x0.c index 2c6ab32..5985ed1 100644 --- a/arch/arm/mach-imx/mach-armadillo5x0.c +++ b/arch/arm/mach-imx/mach-armadillo5x0.c @@ -526,7 +526,8 @@ static void __init armadillo5x0_init(void) imx31_add_mxc_nand(&armadillo5x0_nand_board_info); /* set NAND page size to 2k if not configured via boot mode pins */ - __raw_writel(__raw_readl(MXC_CCM_RCSR) | (1 << 30), MXC_CCM_RCSR); + __raw_writel(__raw_readl(mx3_ccm_base + MXC_CCM_RCSR) | + (1 << 30), mx3_ccm_base + MXC_CCM_RCSR); /* RTC */ /* Get RTC IRQ and register the chip */ diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c index 3226077..1201191 100644 --- a/arch/arm/mach-kirkwood/common.c +++ b/arch/arm/mach-kirkwood/common.c @@ -517,6 +517,13 @@ void __init kirkwood_wdt_init(void) void __init kirkwood_init_early(void) { orion_time_set_base(TIMER_VIRT_BASE); + + /* + * Some Kirkwood devices allocate their coherent buffers from atomic + * context. Increase size of atomic coherent pool to make sure such + * the allocations won't fail. + */ + init_dma_coherent_pool_size(SZ_1M); } int kirkwood_tclk; diff --git a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c index d933593..be90b7d 100644 --- a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c +++ b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/init.h> +#include <linux/sizes.h> #include <linux/platform_device.h> #include <linux/mtd/partitions.h> #include <linux/ata_platform.h> diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index 8dabfe8..ff886e0 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -261,7 +261,7 @@ static void __init apx4devkit_init(void) enable_clk_enet_out(); if (IS_BUILTIN(CONFIG_PHYLIB)) - phy_register_fixup_for_uid(PHY_ID_KS8051, MICREL_PHY_ID_MASK, + phy_register_fixup_for_uid(PHY_ID_KSZ8051, MICREL_PHY_ID_MASK, apx4devkit_phy_fixup); mxsfb_pdata.mode_list = apx4devkit_video_modes; diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index fcd4e85..346fd26 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -232,10 +232,11 @@ config MACH_OMAP3_PANDORA select OMAP_PACKAGE_CBB select REGULATOR_FIXED_VOLTAGE if REGULATOR -config MACH_OMAP3_TOUCHBOOK +config MACH_TOUCHBOOK bool "OMAP3 Touch Book" depends on ARCH_OMAP3 default y + select OMAP_PACKAGE_CBB config MACH_OMAP_3430SDP bool "OMAP 3430 SDP board" diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index f6a24b3..34c2c7f 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -255,7 +255,7 @@ obj-$(CONFIG_MACH_OMAP_3630SDP) += board-zoom-display.o obj-$(CONFIG_MACH_CM_T35) += board-cm-t35.o obj-$(CONFIG_MACH_CM_T3517) += board-cm-t3517.o obj-$(CONFIG_MACH_IGEP0020) += board-igep0020.o -obj-$(CONFIG_MACH_OMAP3_TOUCHBOOK) += board-omap3touchbook.o +obj-$(CONFIG_MACH_TOUCHBOOK) += board-omap3touchbook.o obj-$(CONFIG_MACH_OMAP_4430SDP) += board-4430sdp.o obj-$(CONFIG_MACH_OMAP4_PANDA) += board-omap4panda.o diff --git a/arch/arm/mach-omap2/clock33xx_data.c b/arch/arm/mach-omap2/clock33xx_data.c index 25bbcc7..ae27de8 100644 --- a/arch/arm/mach-omap2/clock33xx_data.c +++ b/arch/arm/mach-omap2/clock33xx_data.c @@ -1036,13 +1036,13 @@ static struct omap_clk am33xx_clks[] = { CLK(NULL, "mmu_fck", &mmu_fck, CK_AM33XX), CLK(NULL, "smartreflex0_fck", &smartreflex0_fck, CK_AM33XX), CLK(NULL, "smartreflex1_fck", &smartreflex1_fck, CK_AM33XX), - CLK(NULL, "gpt1_fck", &timer1_fck, CK_AM33XX), - CLK(NULL, "gpt2_fck", &timer2_fck, CK_AM33XX), - CLK(NULL, "gpt3_fck", &timer3_fck, CK_AM33XX), - CLK(NULL, "gpt4_fck", &timer4_fck, CK_AM33XX), - CLK(NULL, "gpt5_fck", &timer5_fck, CK_AM33XX), - CLK(NULL, "gpt6_fck", &timer6_fck, CK_AM33XX), - CLK(NULL, "gpt7_fck", &timer7_fck, CK_AM33XX), + CLK(NULL, "timer1_fck", &timer1_fck, CK_AM33XX), + CLK(NULL, "timer2_fck", &timer2_fck, CK_AM33XX), + CLK(NULL, "timer3_fck", &timer3_fck, CK_AM33XX), + CLK(NULL, "timer4_fck", &timer4_fck, CK_AM33XX), + CLK(NULL, "timer5_fck", &timer5_fck, CK_AM33XX), + CLK(NULL, "timer6_fck", &timer6_fck, CK_AM33XX), + CLK(NULL, "timer7_fck", &timer7_fck, CK_AM33XX), CLK(NULL, "usbotg_fck", &usbotg_fck, CK_AM33XX), CLK(NULL, "ieee5000_fck", &ieee5000_fck, CK_AM33XX), CLK(NULL, "wdt1_fck", &wdt1_fck, CK_AM33XX), diff --git a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c index a0d68db..f99e65c 100644 --- a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c +++ b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c @@ -241,6 +241,52 @@ static void omap3_clkdm_deny_idle(struct clockdomain *clkdm) _clkdm_del_autodeps(clkdm); } +static int omap3xxx_clkdm_clk_enable(struct clockdomain *clkdm) +{ + bool hwsup = false; + + if (!clkdm->clktrctrl_mask) + return 0; + + hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs, + clkdm->clktrctrl_mask); + + if (hwsup) { + /* Disable HW transitions when we are changing deps */ + _disable_hwsup(clkdm); + _clkdm_add_autodeps(clkdm); + _enable_hwsup(clkdm); + } else { + if (clkdm->flags & CLKDM_CAN_FORCE_WAKEUP) + omap3_clkdm_wakeup(clkdm); + } + + return 0; +} + +static int omap3xxx_clkdm_clk_disable(struct clockdomain *clkdm) +{ + bool hwsup = false; + + if (!clkdm->clktrctrl_mask) + return 0; + + hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs, + clkdm->clktrctrl_mask); + + if (hwsup) { + /* Disable HW transitions when we are changing deps */ + _disable_hwsup(clkdm); + _clkdm_del_autodeps(clkdm); + _enable_hwsup(clkdm); + } else { + if (clkdm->flags & CLKDM_CAN_FORCE_SLEEP) + omap3_clkdm_sleep(clkdm); + } + + return 0; +} + struct clkdm_ops omap2_clkdm_operations = { .clkdm_add_wkdep = omap2_clkdm_add_wkdep, .clkdm_del_wkdep = omap2_clkdm_del_wkdep, @@ -267,6 +313,6 @@ struct clkdm_ops omap3_clkdm_operations = { .clkdm_wakeup = omap3_clkdm_wakeup, .clkdm_allow_idle = omap3_clkdm_allow_idle, .clkdm_deny_idle = omap3_clkdm_deny_idle, - .clkdm_clk_enable = omap2_clkdm_clk_enable, - .clkdm_clk_disable = omap2_clkdm_clk_disable, + .clkdm_clk_enable = omap3xxx_clkdm_clk_enable, + .clkdm_clk_disable = omap3xxx_clkdm_clk_disable, }; diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h index 766338f..975f6bd 100644 --- a/arch/arm/mach-omap2/cm-regbits-34xx.h +++ b/arch/arm/mach-omap2/cm-regbits-34xx.h @@ -67,6 +67,7 @@ #define OMAP3430_EN_IVA2_DPLL_MASK (0x7 << 0) /* CM_IDLEST_IVA2 */ +#define OMAP3430_ST_IVA2_SHIFT 0 #define OMAP3430_ST_IVA2_MASK (1 << 0) /* CM_IDLEST_PLL_IVA2 */ diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 05fdebf..330d4c6 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -46,7 +46,7 @@ static void __iomem *wakeupgen_base; static void __iomem *sar_base; static DEFINE_SPINLOCK(wakeupgen_lock); -static unsigned int irq_target_cpu[NR_IRQS]; +static unsigned int irq_target_cpu[MAX_IRQS]; static unsigned int irq_banks = MAX_NR_REG_BANKS; static unsigned int max_irqs = MAX_IRQS; static unsigned int omap_secure_apis; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 6ca8e51..37afbd1 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1889,6 +1889,7 @@ static int _enable(struct omap_hwmod *oh) _enable_sysc(oh); } } else { + _omap4_disable_module(oh); _disable_clocks(oh); pr_debug("omap_hwmod: %s: _wait_target_ready: %d\n", oh->name, r); diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index c9e3820..ce7e606 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -100,9 +100,9 @@ static struct omap_hwmod omap3xxx_mpu_hwmod = { /* IVA2 (IVA2) */ static struct omap_hwmod_rst_info omap3xxx_iva_resets[] = { - { .name = "logic", .rst_shift = 0 }, - { .name = "seq0", .rst_shift = 1 }, - { .name = "seq1", .rst_shift = 2 }, + { .name = "logic", .rst_shift = 0, .st_shift = 8 }, + { .name = "seq0", .rst_shift = 1, .st_shift = 9 }, + { .name = "seq1", .rst_shift = 2, .st_shift = 10 }, }; static struct omap_hwmod omap3xxx_iva_hwmod = { @@ -112,6 +112,15 @@ static struct omap_hwmod omap3xxx_iva_hwmod = { .rst_lines = omap3xxx_iva_resets, .rst_lines_cnt = ARRAY_SIZE(omap3xxx_iva_resets), .main_clk = "iva2_ck", + .prcm = { + .omap2 = { + .module_offs = OMAP3430_IVA2_MOD, + .prcm_reg_id = 1, + .module_bit = OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT, + .idlest_reg_id = 1, + .idlest_idle_bit = OMAP3430_ST_IVA2_SHIFT, + } + }, }; /* timer class */ diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 242aee4..afb6091 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -4210,7 +4210,7 @@ static struct omap_hwmod_ocp_if omap44xx_dsp__iva = { }; /* dsp -> sl2if */ -static struct omap_hwmod_ocp_if omap44xx_dsp__sl2if = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_dsp__sl2if = { .master = &omap44xx_dsp_hwmod, .slave = &omap44xx_sl2if_hwmod, .clk = "dpll_iva_m5x2_ck", @@ -4828,7 +4828,7 @@ static struct omap_hwmod_ocp_if omap44xx_l3_main_2__iss = { }; /* iva -> sl2if */ -static struct omap_hwmod_ocp_if omap44xx_iva__sl2if = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_iva__sl2if = { .master = &omap44xx_iva_hwmod, .slave = &omap44xx_sl2if_hwmod, .clk = "dpll_iva_m5x2_ck", @@ -5362,7 +5362,7 @@ static struct omap_hwmod_ocp_if omap44xx_l4_wkup__scrm = { }; /* l3_main_2 -> sl2if */ -static struct omap_hwmod_ocp_if omap44xx_l3_main_2__sl2if = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l3_main_2__sl2if = { .master = &omap44xx_l3_main_2_hwmod, .slave = &omap44xx_sl2if_hwmod, .clk = "l3_div_ck", @@ -6032,7 +6032,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = { &omap44xx_l4_abe__dmic, &omap44xx_l4_abe__dmic_dma, &omap44xx_dsp__iva, - &omap44xx_dsp__sl2if, + /* &omap44xx_dsp__sl2if, */ &omap44xx_l4_cfg__dsp, &omap44xx_l3_main_2__dss, &omap44xx_l4_per__dss, @@ -6068,7 +6068,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = { &omap44xx_l4_per__i2c4, &omap44xx_l3_main_2__ipu, &omap44xx_l3_main_2__iss, - &omap44xx_iva__sl2if, + /* &omap44xx_iva__sl2if, */ &omap44xx_l3_main_2__iva, &omap44xx_l4_wkup__kbd, &omap44xx_l4_cfg__mailbox, @@ -6099,7 +6099,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = { &omap44xx_l4_cfg__cm_core, &omap44xx_l4_wkup__prm, &omap44xx_l4_wkup__scrm, - &omap44xx_l3_main_2__sl2if, + /* &omap44xx_l3_main_2__sl2if, */ &omap44xx_l4_abe__slimbus1, &omap44xx_l4_abe__slimbus1_dma, &omap44xx_l4_per__slimbus2, diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 2ff6d41..2ba4f57 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -260,6 +260,7 @@ static u32 notrace dmtimer_read_sched_clock(void) return 0; } +#ifdef CONFIG_OMAP_32K_TIMER /* Setup free-running counter for clocksource */ static int __init omap2_sync32k_clocksource_init(void) { @@ -299,6 +300,12 @@ static int __init omap2_sync32k_clocksource_init(void) return ret; } +#else +static inline int omap2_sync32k_clocksource_init(void) +{ + return -ENODEV; +} +#endif static void __init omap2_gptimer_clocksource_init(int gptimer_id, const char *fck_source) diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 410291c..a6cd14a 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -204,6 +204,13 @@ void __init orion5x_wdt_init(void) void __init orion5x_init_early(void) { orion_time_set_base(TIMER_VIRT_BASE); + + /* + * Some Orion5x devices allocate their coherent buffers from atomic + * context. Increase size of atomic coherent pool to make sure such + * the allocations won't fail. + */ + init_dma_coherent_pool_size(SZ_1M); } int orion5x_tclk; diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index cf10f92..453a6e5 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -520,13 +520,14 @@ static struct platform_device hdmi_lcdc_device = { }; /* GPIO KEY */ -#define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 } +#define GPIO_KEY(c, g, d, ...) \ + { .code = c, .gpio = g, .desc = d, .active_low = 1, __VA_ARGS__ } static struct gpio_keys_button gpio_buttons[] = { - GPIO_KEY(KEY_POWER, GPIO_PORT99, "SW1"), - GPIO_KEY(KEY_BACK, GPIO_PORT100, "SW2"), - GPIO_KEY(KEY_MENU, GPIO_PORT97, "SW3"), - GPIO_KEY(KEY_HOME, GPIO_PORT98, "SW4"), + GPIO_KEY(KEY_POWER, GPIO_PORT99, "SW3", .wakeup = 1), + GPIO_KEY(KEY_BACK, GPIO_PORT100, "SW4"), + GPIO_KEY(KEY_MENU, GPIO_PORT97, "SW5"), + GPIO_KEY(KEY_HOME, GPIO_PORT98, "SW6"), }; static struct gpio_keys_platform_data gpio_key_info = { @@ -901,8 +902,8 @@ static struct platform_device *eva_devices[] __initdata = { &camera_device, &ceu0_device, &fsi_device, - &fsi_hdmi_device, &fsi_wm8978_device, + &fsi_hdmi_device, }; static void __init eva_clock_init(void) diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index 53b7ea9..3b8a017 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -346,11 +346,11 @@ static struct resource sh_mmcif_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = gic_spi(141), + .start = gic_spi(140), .flags = IORESOURCE_IRQ, }, [2] = { - .start = gic_spi(140), + .start = gic_spi(141), .flags = IORESOURCE_IRQ, }, }; diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index 7ea2b31..c129542 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -695,6 +695,7 @@ static struct platform_device usbhs0_device = { * - J30 "open" * - modify usbhs1_get_id() USBHS_HOST -> USBHS_GADGET * - add .get_vbus = usbhs_get_vbus in usbhs1_private + * - check usbhs0_device(pio)/usbhs1_device(irq) order in mackerel_devices. */ #define IRQ8 evt2irq(0x0300) #define USB_PHY_MODE (1 << 4) @@ -1325,8 +1326,8 @@ static struct platform_device *mackerel_devices[] __initdata = { &nor_flash_device, &smc911x_device, &lcdc_device, - &usbhs1_device, &usbhs0_device, + &usbhs1_device, &leds_device, &fsi_device, &fsi_ak4643_device, diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c index 3a528cf..fcf5a47 100644 --- a/arch/arm/mach-shmobile/board-marzen.c +++ b/arch/arm/mach-shmobile/board-marzen.c @@ -67,7 +67,7 @@ static struct smsc911x_platform_config smsc911x_platdata = { static struct platform_device eth_device = { .name = "smsc911x", - .id = 0, + .id = -1, .dev = { .platform_data = &smsc911x_platdata, }, diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c index ee44740..588555a 100644 --- a/arch/arm/mach-shmobile/intc-sh73a0.c +++ b/arch/arm/mach-shmobile/intc-sh73a0.c @@ -259,9 +259,9 @@ static int sh73a0_set_wake(struct irq_data *data, unsigned int on) return 0; /* always allow wakeup */ } -#define RELOC_BASE 0x1000 +#define RELOC_BASE 0x1200 -/* INTCA IRQ pins at INTCS + 0x1000 to make space for GIC+INTC handling */ +/* INTCA IRQ pins at INTCS + RELOC_BASE to make space for GIC+INTC handling */ #define INTCS_VECT_RELOC(n, vect) INTCS_VECT((n), (vect) + RELOC_BASE) INTC_IRQ_PINS_32(intca_irq_pins, 0xe6900000, diff --git a/arch/arm/mach-tegra/board-harmony-power.c b/arch/arm/mach-tegra/board-harmony-power.c index b7344be..94486e7 100644 --- a/arch/arm/mach-tegra/board-harmony-power.c +++ b/arch/arm/mach-tegra/board-harmony-power.c @@ -67,6 +67,13 @@ static struct regulator_init_data ldo0_data = { }, \ } +static struct regulator_init_data sys_data = { + .supply_regulator = "vdd_5v0", + .constraints = { + .name = "vdd_sys", + }, +}; + HARMONY_REGULATOR_INIT(sm0, "vdd_sm0", "vdd_sys", 725, 1500, 1); HARMONY_REGULATOR_INIT(sm1, "vdd_sm1", "vdd_sys", 725, 1500, 1); HARMONY_REGULATOR_INIT(sm2, "vdd_sm2", "vdd_sys", 3000, 4550, 1); @@ -74,7 +81,7 @@ HARMONY_REGULATOR_INIT(ldo1, "vdd_ldo1", "vdd_sm2", 725, 1500, 1); HARMONY_REGULATOR_INIT(ldo2, "vdd_ldo2", "vdd_sm2", 725, 1500, 0); HARMONY_REGULATOR_INIT(ldo3, "vdd_ldo3", "vdd_sm2", 1250, 3300, 1); HARMONY_REGULATOR_INIT(ldo4, "vdd_ldo4", "vdd_sm2", 1700, 2475, 1); -HARMONY_REGULATOR_INIT(ldo5, "vdd_ldo5", NULL, 1250, 3300, 1); +HARMONY_REGULATOR_INIT(ldo5, "vdd_ldo5", "vdd_sys", 1250, 3300, 1); HARMONY_REGULATOR_INIT(ldo6, "vdd_ldo6", "vdd_sm2", 1250, 3300, 0); HARMONY_REGULATOR_INIT(ldo7, "vdd_ldo7", "vdd_sm2", 1250, 3300, 0); HARMONY_REGULATOR_INIT(ldo8, "vdd_ldo8", "vdd_sm2", 1250, 3300, 0); @@ -88,6 +95,7 @@ HARMONY_REGULATOR_INIT(ldo9, "vdd_ldo9", "vdd_sm2", 1250, 3300, 1); } static struct tps6586x_subdev_info tps_devs[] = { + TPS_REG(SYS, &sys_data), TPS_REG(SM_0, &sm0_data), TPS_REG(SM_1, &sm1_data), TPS_REG(SM_2, &sm2_data), @@ -120,7 +128,7 @@ static struct i2c_board_info __initdata harmony_regulators[] = { int __init harmony_regulator_init(void) { - regulator_register_always_on(0, "vdd_sys", + regulator_register_always_on(0, "vdd_5v0", NULL, 0, 5000000); if (machine_is_harmony()) { diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 119bc52..4e07eec 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -63,10 +63,11 @@ static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd, pid = task_pid_nr(thread->task) << ASID_BITS; asm volatile( " mrc p15, 0, %0, c13, c0, 1\n" - " bfi %1, %0, #0, %2\n" - " mcr p15, 0, %1, c13, c0, 1\n" + " and %0, %0, %2\n" + " orr %0, %0, %1\n" + " mcr p15, 0, %0, c13, c0, 1\n" : "=r" (contextidr), "+r" (pid) - : "I" (ASID_BITS)); + : "I" (~ASID_MASK)); isb(); return NOTIFY_OK; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4e7d118..13f555d 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -267,17 +267,19 @@ static void __dma_free_remap(void *cpu_addr, size_t size) vunmap(cpu_addr); } +#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K + struct dma_pool { size_t size; spinlock_t lock; unsigned long *bitmap; unsigned long nr_pages; void *vaddr; - struct page *page; + struct page **pages; }; static struct dma_pool atomic_pool = { - .size = SZ_256K, + .size = DEFAULT_DMA_COHERENT_POOL_SIZE, }; static int __init early_coherent_pool(char *p) @@ -287,6 +289,21 @@ static int __init early_coherent_pool(char *p) } early_param("coherent_pool", early_coherent_pool); +void __init init_dma_coherent_pool_size(unsigned long size) +{ + /* + * Catch any attempt to set the pool size too late. + */ + BUG_ON(atomic_pool.vaddr); + + /* + * Set architecture specific coherent pool size only if + * it has not been changed by kernel command line parameter. + */ + if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE) + atomic_pool.size = size; +} + /* * Initialise the coherent pool for atomic allocations. */ @@ -297,6 +314,7 @@ static int __init atomic_pool_init(void) unsigned long nr_pages = pool->size >> PAGE_SHIFT; unsigned long *bitmap; struct page *page; + struct page **pages; void *ptr; int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long); @@ -304,21 +322,33 @@ static int __init atomic_pool_init(void) if (!bitmap) goto no_bitmap; + pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto no_pages; + if (IS_ENABLED(CONFIG_CMA)) ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page); else ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot, &page, NULL); if (ptr) { + int i; + + for (i = 0; i < nr_pages; i++) + pages[i] = page + i; + spin_lock_init(&pool->lock); pool->vaddr = ptr; - pool->page = page; + pool->pages = pages; pool->bitmap = bitmap; pool->nr_pages = nr_pages; pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n", (unsigned)pool->size / 1024); return 0; } + + kfree(pages); +no_pages: kfree(bitmap); no_bitmap: pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n", @@ -443,27 +473,45 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) if (pageno < pool->nr_pages) { bitmap_set(pool->bitmap, pageno, count); ptr = pool->vaddr + PAGE_SIZE * pageno; - *ret_page = pool->page + pageno; + *ret_page = pool->pages[pageno]; + } else { + pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n" + "Please increase it with coherent_pool= kernel parameter!\n", + (unsigned)pool->size / 1024); } spin_unlock_irqrestore(&pool->lock, flags); return ptr; } +static bool __in_atomic_pool(void *start, size_t size) +{ + struct dma_pool *pool = &atomic_pool; + void *end = start + size; + void *pool_start = pool->vaddr; + void *pool_end = pool->vaddr + pool->size; + + if (start < pool_start || start >= pool_end) + return false; + + if (end <= pool_end) + return true; + + WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n", + start, end - 1, pool_start, pool_end - 1); + + return false; +} + static int __free_from_pool(void *start, size_t size) { struct dma_pool *pool = &atomic_pool; unsigned long pageno, count; unsigned long flags; - if (start < pool->vaddr || start > pool->vaddr + pool->size) + if (!__in_atomic_pool(start, size)) return 0; - if (start + size > pool->vaddr + pool->size) { - WARN(1, "freeing wrong coherent size from pool\n"); - return 0; - } - pageno = (start - pool->vaddr) >> PAGE_SHIFT; count = size >> PAGE_SHIFT; @@ -1090,10 +1138,22 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si return 0; } +static struct page **__atomic_get_pages(void *addr) +{ + struct dma_pool *pool = &atomic_pool; + struct page **pages = pool->pages; + int offs = (addr - pool->vaddr) >> PAGE_SHIFT; + + return pages + offs; +} + static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs) { struct vm_struct *area; + if (__in_atomic_pool(cpu_addr, PAGE_SIZE)) + return __atomic_get_pages(cpu_addr); + if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) return cpu_addr; @@ -1103,6 +1163,34 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs) return NULL; } +static void *__iommu_alloc_atomic(struct device *dev, size_t size, + dma_addr_t *handle) +{ + struct page *page; + void *addr; + + addr = __alloc_from_pool(size, &page); + if (!addr) + return NULL; + + *handle = __iommu_create_mapping(dev, &page, size); + if (*handle == DMA_ERROR_CODE) + goto err_mapping; + + return addr; + +err_mapping: + __free_from_pool(addr, size); + return NULL; +} + +static void __iommu_free_atomic(struct device *dev, struct page **pages, + dma_addr_t handle, size_t size) +{ + __iommu_remove_mapping(dev, handle, size); + __free_from_pool(page_address(pages[0]), size); +} + static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { @@ -1113,6 +1201,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); + if (gfp & GFP_ATOMIC) + return __iommu_alloc_atomic(dev, size, handle); + pages = __iommu_alloc_buffer(dev, size, gfp); if (!pages) return NULL; @@ -1179,6 +1270,11 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, return; } + if (__in_atomic_pool(cpu_addr, size)) { + __iommu_free_atomic(dev, pages, handle, size); + return; + } + if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) { unmap_kernel_range((unsigned long)cpu_addr, size); vunmap(cpu_addr); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 6776160..a8ee92d 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -55,6 +55,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page /* permanent static mappings from iotable_init() */ #define VM_ARM_STATIC_MAPPING 0x40000000 +/* empty mapping */ +#define VM_ARM_EMPTY_MAPPING 0x20000000 + /* mapping type (attributes) for permanent static mappings */ #define VM_ARM_MTYPE(mt) ((mt) << 20) #define VM_ARM_MTYPE_MASK (0x1f << 20) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4c2d045..c2fa21d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -807,7 +807,7 @@ static void __init pmd_empty_section_gap(unsigned long addr) vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm)); vm->addr = (void *)addr; vm->size = SECTION_SIZE; - vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; + vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING; vm->caller = pmd_empty_section_gap; vm_area_add_early(vm); } @@ -820,7 +820,7 @@ static void __init fill_pmd_gaps(void) /* we're still single threaded hence no lock needed here */ for (vm = vmlist; vm; vm = vm->next) { - if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING))) continue; addr = (unsigned long)vm->addr; if (addr < next) @@ -961,8 +961,8 @@ void __init sanity_check_meminfo(void) * Check whether this memory bank would partially overlap * the vmalloc area. */ - if (__va(bank->start + bank->size) > vmalloc_min || - __va(bank->start + bank->size) < __va(bank->start)) { + if (__va(bank->start + bank->size - 1) >= vmalloc_min || + __va(bank->start + bank->size - 1) <= __va(bank->start)) { unsigned long newsize = vmalloc_min - __va(bank->start); printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx " "to -%.8llx (vmalloc region overlap).\n", diff --git a/arch/arm/plat-mxc/include/mach/mx25.h b/arch/arm/plat-mxc/include/mach/mx25.h index 627d94f..ec46640 100644 --- a/arch/arm/plat-mxc/include/mach/mx25.h +++ b/arch/arm/plat-mxc/include/mach/mx25.h @@ -98,6 +98,7 @@ #define MX25_INT_UART1 (NR_IRQS_LEGACY + 45) #define MX25_INT_GPIO2 (NR_IRQS_LEGACY + 51) #define MX25_INT_GPIO1 (NR_IRQS_LEGACY + 52) +#define MX25_INT_GPT1 (NR_IRQS_LEGACY + 54) #define MX25_INT_FEC (NR_IRQS_LEGACY + 57) #define MX25_DMA_REQ_SSI2_RX1 22 diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c index 766181c..024f3b0 100644 --- a/arch/arm/plat-omap/sram.c +++ b/arch/arm/plat-omap/sram.c @@ -68,6 +68,7 @@ static unsigned long omap_sram_start; static void __iomem *omap_sram_base; +static unsigned long omap_sram_skip; static unsigned long omap_sram_size; static void __iomem *omap_sram_ceil; @@ -106,6 +107,7 @@ static int is_sram_locked(void) */ static void __init omap_detect_sram(void) { + omap_sram_skip = SRAM_BOOTLOADER_SZ; if (cpu_class_is_omap2()) { if (is_sram_locked()) { if (cpu_is_omap34xx()) { @@ -113,6 +115,7 @@ static void __init omap_detect_sram(void) if ((omap_type() == OMAP2_DEVICE_TYPE_EMU) || (omap_type() == OMAP2_DEVICE_TYPE_SEC)) { omap_sram_size = 0x7000; /* 28K */ + omap_sram_skip += SZ_16K; } else { omap_sram_size = 0x8000; /* 32K */ } @@ -175,8 +178,10 @@ static void __init omap_map_sram(void) return; #ifdef CONFIG_OMAP4_ERRATA_I688 + if (cpu_is_omap44xx()) { omap_sram_start += PAGE_SIZE; omap_sram_size -= SZ_16K; + } #endif if (cpu_is_omap34xx()) { /* @@ -203,8 +208,8 @@ static void __init omap_map_sram(void) * Looks like we need to preserve some bootloader code at the * beginning of SRAM for jumping to flash for reboot to work... */ - memset_io(omap_sram_base + SRAM_BOOTLOADER_SZ, 0, - omap_sram_size - SRAM_BOOTLOADER_SZ); + memset_io(omap_sram_base + omap_sram_skip, 0, + omap_sram_size - omap_sram_skip); } /* @@ -218,7 +223,7 @@ void *omap_sram_push_address(unsigned long size) { unsigned long available, new_ceil = (unsigned long)omap_sram_ceil; - available = omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ); + available = omap_sram_ceil - (omap_sram_base + omap_sram_skip); if (size > available) { pr_err("Not enough space in SRAM\n"); diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c index 65c5eca..d1116e2 100644 --- a/arch/arm/plat-samsung/clock.c +++ b/arch/arm/plat-samsung/clock.c @@ -144,6 +144,7 @@ long clk_round_rate(struct clk *clk, unsigned long rate) int clk_set_rate(struct clk *clk, unsigned long rate) { + unsigned long flags; int ret; if (IS_ERR(clk)) @@ -159,9 +160,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate) if (clk->ops == NULL || clk->ops->set_rate == NULL) return -EINVAL; - spin_lock(&clocks_lock); + spin_lock_irqsave(&clocks_lock, flags); ret = (clk->ops->set_rate)(clk, rate); - spin_unlock(&clocks_lock); + spin_unlock_irqrestore(&clocks_lock, flags); return ret; } @@ -173,17 +174,18 @@ struct clk *clk_get_parent(struct clk *clk) int clk_set_parent(struct clk *clk, struct clk *parent) { + unsigned long flags; int ret = 0; if (IS_ERR(clk)) return -EINVAL; - spin_lock(&clocks_lock); + spin_lock_irqsave(&clocks_lock, flags); if (clk->ops && clk->ops->set_parent) ret = (clk->ops->set_parent)(clk, parent); - spin_unlock(&clocks_lock); + spin_unlock_irqrestore(&clocks_lock, flags); return ret; } diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index f348619..c7092e6 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -38,6 +38,7 @@ config BLACKFIN select GENERIC_ATOMIC64 select GENERIC_IRQ_PROBE select IRQ_PER_CPU if SMP + select USE_GENERIC_SMP_HELPERS if SMP select HAVE_NMI_WATCHDOG if NMI_WATCHDOG select GENERIC_SMP_IDLE_THREAD select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile index d3d7e64..66cf000 100644 --- a/arch/blackfin/Makefile +++ b/arch/blackfin/Makefile @@ -20,7 +20,6 @@ endif KBUILD_AFLAGS += $(call cc-option,-mno-fdpic) KBUILD_CFLAGS_MODULE += -mlong-calls LDFLAGS += -m elf32bfin -KALLSYMS += --symbol-prefix=_ KBUILD_DEFCONFIG := BF537-STAMP_defconfig diff --git a/arch/blackfin/include/asm/smp.h b/arch/blackfin/include/asm/smp.h index dc3d144..9631598 100644 --- a/arch/blackfin/include/asm/smp.h +++ b/arch/blackfin/include/asm/smp.h @@ -18,6 +18,8 @@ #define raw_smp_processor_id() blackfin_core_id() extern void bfin_relocate_coreb_l1_mem(void); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); #if defined(CONFIG_SMP) && defined(CONFIG_ICACHE_FLUSH_L1) asmlinkage void blackfin_icache_flush_range_l1(unsigned long *ptr); diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 00bbe67..a401513 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -48,10 +48,13 @@ unsigned long blackfin_iflush_l1_entry[NR_CPUS]; struct blackfin_initial_pda __cpuinitdata initial_pda_coreb; -#define BFIN_IPI_TIMER 0 -#define BFIN_IPI_RESCHEDULE 1 -#define BFIN_IPI_CALL_FUNC 2 -#define BFIN_IPI_CPU_STOP 3 +enum ipi_message_type { + BFIN_IPI_TIMER, + BFIN_IPI_RESCHEDULE, + BFIN_IPI_CALL_FUNC, + BFIN_IPI_CALL_FUNC_SINGLE, + BFIN_IPI_CPU_STOP, +}; struct blackfin_flush_data { unsigned long start; @@ -60,35 +63,20 @@ struct blackfin_flush_data { void *secondary_stack; - -struct smp_call_struct { - void (*func)(void *info); - void *info; - int wait; - cpumask_t *waitmask; -}; - static struct blackfin_flush_data smp_flush_data; static DEFINE_SPINLOCK(stop_lock); -struct ipi_message { - unsigned long type; - struct smp_call_struct call_struct; -}; - /* A magic number - stress test shows this is safe for common cases */ #define BFIN_IPI_MSGQ_LEN 5 /* Simple FIFO buffer, overflow leads to panic */ -struct ipi_message_queue { - spinlock_t lock; +struct ipi_data { unsigned long count; - unsigned long head; /* head of the queue */ - struct ipi_message ipi_message[BFIN_IPI_MSGQ_LEN]; + unsigned long bits; }; -static DEFINE_PER_CPU(struct ipi_message_queue, ipi_msg_queue); +static DEFINE_PER_CPU(struct ipi_data, bfin_ipi); static void ipi_cpu_stop(unsigned int cpu) { @@ -129,28 +117,6 @@ static void ipi_flush_icache(void *info) blackfin_icache_flush_range(fdata->start, fdata->end); } -static void ipi_call_function(unsigned int cpu, struct ipi_message *msg) -{ - int wait; - void (*func)(void *info); - void *info; - func = msg->call_struct.func; - info = msg->call_struct.info; - wait = msg->call_struct.wait; - func(info); - if (wait) { -#ifdef __ARCH_SYNC_CORE_DCACHE - /* - * 'wait' usually means synchronization between CPUs. - * Invalidate D cache in case shared data was changed - * by func() to ensure cache coherence. - */ - resync_core_dcache(); -#endif - cpumask_clear_cpu(cpu, msg->call_struct.waitmask); - } -} - /* Use IRQ_SUPPLE_0 to request reschedule. * When returning from interrupt to user space, * there is chance to reschedule */ @@ -172,152 +138,95 @@ void ipi_timer(void) static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) { - struct ipi_message *msg; - struct ipi_message_queue *msg_queue; + struct ipi_data *bfin_ipi_data; unsigned int cpu = smp_processor_id(); - unsigned long flags; + unsigned long pending; + unsigned long msg; platform_clear_ipi(cpu, IRQ_SUPPLE_1); - msg_queue = &__get_cpu_var(ipi_msg_queue); - - spin_lock_irqsave(&msg_queue->lock, flags); - - while (msg_queue->count) { - msg = &msg_queue->ipi_message[msg_queue->head]; - switch (msg->type) { - case BFIN_IPI_TIMER: - ipi_timer(); - break; - case BFIN_IPI_RESCHEDULE: - scheduler_ipi(); - break; - case BFIN_IPI_CALL_FUNC: - ipi_call_function(cpu, msg); - break; - case BFIN_IPI_CPU_STOP: - ipi_cpu_stop(cpu); - break; - default: - printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%lx\n", - cpu, msg->type); - break; - } - msg_queue->head++; - msg_queue->head %= BFIN_IPI_MSGQ_LEN; - msg_queue->count--; + bfin_ipi_data = &__get_cpu_var(bfin_ipi); + + while ((pending = xchg(&bfin_ipi_data->bits, 0)) != 0) { + msg = 0; + do { + msg = find_next_bit(&pending, BITS_PER_LONG, msg + 1); + switch (msg) { + case BFIN_IPI_TIMER: + ipi_timer(); + break; + case BFIN_IPI_RESCHEDULE: + scheduler_ipi(); + break; + case BFIN_IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; + + case BFIN_IPI_CALL_FUNC_SINGLE: + generic_smp_call_function_single_interrupt(); + break; + + case BFIN_IPI_CPU_STOP: + ipi_cpu_stop(cpu); + break; + } + } while (msg < BITS_PER_LONG); + + smp_mb(); } - spin_unlock_irqrestore(&msg_queue->lock, flags); return IRQ_HANDLED; } -static void ipi_queue_init(void) +static void bfin_ipi_init(void) { unsigned int cpu; - struct ipi_message_queue *msg_queue; + struct ipi_data *bfin_ipi_data; for_each_possible_cpu(cpu) { - msg_queue = &per_cpu(ipi_msg_queue, cpu); - spin_lock_init(&msg_queue->lock); - msg_queue->count = 0; - msg_queue->head = 0; + bfin_ipi_data = &per_cpu(bfin_ipi, cpu); + bfin_ipi_data->bits = 0; + bfin_ipi_data->count = 0; } } -static inline void smp_send_message(cpumask_t callmap, unsigned long type, - void (*func) (void *info), void *info, int wait) +void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg) { unsigned int cpu; - struct ipi_message_queue *msg_queue; - struct ipi_message *msg; - unsigned long flags, next_msg; - cpumask_t waitmask; /* waitmask is shared by all cpus */ - - cpumask_copy(&waitmask, &callmap); - for_each_cpu(cpu, &callmap) { - msg_queue = &per_cpu(ipi_msg_queue, cpu); - spin_lock_irqsave(&msg_queue->lock, flags); - if (msg_queue->count < BFIN_IPI_MSGQ_LEN) { - next_msg = (msg_queue->head + msg_queue->count) - % BFIN_IPI_MSGQ_LEN; - msg = &msg_queue->ipi_message[next_msg]; - msg->type = type; - if (type == BFIN_IPI_CALL_FUNC) { - msg->call_struct.func = func; - msg->call_struct.info = info; - msg->call_struct.wait = wait; - msg->call_struct.waitmask = &waitmask; - } - msg_queue->count++; - } else - panic("IPI message queue overflow\n"); - spin_unlock_irqrestore(&msg_queue->lock, flags); + struct ipi_data *bfin_ipi_data; + unsigned long flags; + + local_irq_save(flags); + + for_each_cpu(cpu, cpumask) { + bfin_ipi_data = &per_cpu(bfin_ipi, cpu); + smp_mb(); + set_bit(msg, &bfin_ipi_data->bits); + bfin_ipi_data->count++; platform_send_ipi_cpu(cpu, IRQ_SUPPLE_1); } - if (wait) { - while (!cpumask_empty(&waitmask)) - blackfin_dcache_invalidate_range( - (unsigned long)(&waitmask), - (unsigned long)(&waitmask)); -#ifdef __ARCH_SYNC_CORE_DCACHE - /* - * Invalidate D cache in case shared data was changed by - * other processors to ensure cache coherence. - */ - resync_core_dcache(); -#endif - } + local_irq_restore(flags); } -int smp_call_function(void (*func)(void *info), void *info, int wait) +void arch_send_call_function_single_ipi(int cpu) { - cpumask_t callmap; - - preempt_disable(); - cpumask_copy(&callmap, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), &callmap); - if (!cpumask_empty(&callmap)) - smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait); - - preempt_enable(); - - return 0; + send_ipi(cpumask_of(cpu), BFIN_IPI_CALL_FUNC_SINGLE); } -EXPORT_SYMBOL_GPL(smp_call_function); -int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, - int wait) +void arch_send_call_function_ipi_mask(const struct cpumask *mask) { - unsigned int cpu = cpuid; - cpumask_t callmap; - - if (cpu_is_offline(cpu)) - return 0; - cpumask_clear(&callmap); - cpumask_set_cpu(cpu, &callmap); - - smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait); - - return 0; + send_ipi(mask, BFIN_IPI_CALL_FUNC); } -EXPORT_SYMBOL_GPL(smp_call_function_single); void smp_send_reschedule(int cpu) { - cpumask_t callmap; - /* simply trigger an ipi */ - - cpumask_clear(&callmap); - cpumask_set_cpu(cpu, &callmap); - - smp_send_message(callmap, BFIN_IPI_RESCHEDULE, NULL, NULL, 0); + send_ipi(cpumask_of(cpu), BFIN_IPI_RESCHEDULE); return; } void smp_send_msg(const struct cpumask *mask, unsigned long type) { - smp_send_message(*mask, type, NULL, NULL, 0); + send_ipi(mask, type); } void smp_timer_broadcast(const struct cpumask *mask) @@ -333,7 +242,7 @@ void smp_send_stop(void) cpumask_copy(&callmap, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &callmap); if (!cpumask_empty(&callmap)) - smp_send_message(callmap, BFIN_IPI_CPU_STOP, NULL, NULL, 0); + send_ipi(&callmap, BFIN_IPI_CPU_STOP); preempt_enable(); @@ -436,7 +345,7 @@ void __init smp_prepare_boot_cpu(void) void __init smp_prepare_cpus(unsigned int max_cpus) { platform_prepare_cpus(max_cpus); - ipi_queue_init(); + bfin_ipi_init(); platform_request_ipi(IRQ_SUPPLE_0, ipi_handler_int0); platform_request_ipi(IRQ_SUPPLE_1, ipi_handler_int1); } diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 3af601e..f08e891 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -2,6 +2,7 @@ include include/asm-generic/Kbuild.asm generic-y += atomic.h generic-y += auxvec.h +generic-y += barrier.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += cputime.h diff --git a/arch/c6x/include/asm/barrier.h b/arch/c6x/include/asm/barrier.h deleted file mode 100644 index 538240e..0000000 --- a/arch/c6x/include/asm/barrier.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Port on Texas Instruments TMS320C6x architecture - * - * Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated - * Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef _ASM_C6X_BARRIER_H -#define _ASM_C6X_BARRIER_H - -#define nop() asm("NOP\n"); - -#define mb() barrier() -#define rmb() barrier() -#define wmb() barrier() -#define set_mb(var, value) do { var = value; mb(); } while (0) -#define set_wmb(var, value) do { var = value; wmb(); } while (0) - -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while (0) - -#endif /* _ASM_C6X_BARRIER_H */ diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index 66fd017..7f65be6 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -25,6 +25,7 @@ #include <linux/elfcore.h> #include <linux/mqueue.h> #include <linux/reboot.h> +#include <linux/rcupdate.h> //#define DEBUG @@ -74,6 +75,7 @@ void cpu_idle (void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) { void (*idle)(void); /* @@ -86,6 +88,7 @@ void cpu_idle (void) idle = default_idle; idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } } diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index ff95f50..2eb7fa5 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -25,6 +25,7 @@ #include <linux/reboot.h> #include <linux/interrupt.h> #include <linux/pagemap.h> +#include <linux/rcupdate.h> #include <asm/asm-offsets.h> #include <asm/uaccess.h> @@ -69,12 +70,14 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) { check_pgt_cache(); if (!frv_dma_inprogress && idle) idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 0e9c315..f153ed1 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -36,6 +36,7 @@ #include <linux/reboot.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/traps.h> @@ -78,8 +79,10 @@ void (*idle)(void) = default_idle; void cpu_idle(void) { while (1) { + rcu_idle_enter(); while (!need_resched()) idle(); + rcu_idle_exit(); schedule_preempt_disabled(); } } diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 310cf57..3c720ef 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -25,6 +25,7 @@ config IA64 select HAVE_GENERIC_HARDIRQS select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP + select HAVE_VIRT_CPU_ACCOUNTING select ARCH_DISCARD_MEMBLOCK select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP @@ -340,17 +341,6 @@ config FORCE_MAX_ZONEORDER default "17" if HUGETLB_PAGE default "11" -config VIRT_CPU_ACCOUNTING - bool "Deterministic task and CPU time accounting" - default n - help - Select this option to enable more accurate task and CPU time - accounting. This is done by reading a CPU counter on each - kernel entry and exit and on transitions within the kernel - between system, softirq and hardirq state, so there is a - small performance impact. - If in doubt, say N here. - config SMP bool "Symmetric multi-processing support" select USE_GENERIC_SMP_HELPERS diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h index cb2412f..d38c7ea 100644 --- a/arch/ia64/include/asm/switch_to.h +++ b/arch/ia64/include/asm/switch_to.h @@ -30,13 +30,6 @@ extern struct task_struct *ia64_switch_to (void *next_task); extern void ia64_save_extra (struct task_struct *task); extern void ia64_load_extra (struct task_struct *task); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next); -# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n) -#else -# define IA64_ACCOUNT_ON_SWITCH(p,n) -#endif - #ifdef CONFIG_PERFMON DECLARE_PER_CPU(unsigned long, pfm_syst_info); # define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1) @@ -49,7 +42,6 @@ extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct || PERFMON_IS_SYSWIDE()) #define __switch_to(prev,next,last) do { \ - IA64_ACCOUNT_ON_SWITCH(prev, next); \ if (IA64_HAS_EXTRA_STATE(prev)) \ ia64_save_extra(prev); \ if (IA64_HAS_EXTRA_STATE(next)) \ diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index dd6fc14..3e316ec 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -29,6 +29,7 @@ #include <linux/kdebug.h> #include <linux/utsname.h> #include <linux/tracehook.h> +#include <linux/rcupdate.h> #include <asm/cpu.h> #include <asm/delay.h> @@ -279,6 +280,7 @@ cpu_idle (void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); if (can_do_pal_halt) { current_thread_info()->status &= ~TS_POLLING; /* @@ -309,6 +311,7 @@ cpu_idle (void) normal_xtp(); #endif } + rcu_idle_exit(); schedule_preempt_disabled(); check_pgt_cache(); if (cpu_is_offline(cpu)) diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ecc904b..80ff9ac 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -83,32 +83,36 @@ static struct clocksource *itc_clocksource; extern cputime_t cycle_to_cputime(u64 cyc); +static void vtime_account_user(struct task_struct *tsk) +{ + cputime_t delta_utime; + struct thread_info *ti = task_thread_info(tsk); + + if (ti->ac_utime) { + delta_utime = cycle_to_cputime(ti->ac_utime); + account_user_time(tsk, delta_utime, delta_utime); + ti->ac_utime = 0; + } +} + /* * Called from the context switch with interrupts disabled, to charge all * accumulated times to the current process, and to prepare accounting on * the next process. */ -void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next) +void vtime_task_switch(struct task_struct *prev) { struct thread_info *pi = task_thread_info(prev); - struct thread_info *ni = task_thread_info(next); - cputime_t delta_stime, delta_utime; - __u64 now; + struct thread_info *ni = task_thread_info(current); - now = ia64_get_itc(); - - delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp)); if (idle_task(smp_processor_id()) != prev) - account_system_time(prev, 0, delta_stime, delta_stime); + vtime_account_system(prev); else - account_idle_time(delta_stime); + vtime_account_idle(prev); - if (pi->ac_utime) { - delta_utime = cycle_to_cputime(pi->ac_utime); - account_user_time(prev, delta_utime, delta_utime); - } + vtime_account_user(prev); - pi->ac_stamp = ni->ac_stamp = now; + pi->ac_stamp = ni->ac_stamp; ni->ac_stime = ni->ac_utime = 0; } @@ -116,29 +120,32 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next) * Account time for a transition between system, hard irq or soft irq state. * Note that this function is called with interrupts enabled. */ -void account_system_vtime(struct task_struct *tsk) +static cputime_t vtime_delta(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - unsigned long flags; cputime_t delta_stime; __u64 now; - local_irq_save(flags); - now = ia64_get_itc(); delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp)); - if (irq_count() || idle_task(smp_processor_id()) != tsk) - account_system_time(tsk, 0, delta_stime, delta_stime); - else - account_idle_time(delta_stime); ti->ac_stime = 0; - ti->ac_stamp = now; - local_irq_restore(flags); + return delta_stime; +} + +void vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta = vtime_delta(tsk); + + account_system_time(tsk, 0, delta, delta); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + account_idle_time(vtime_delta(tsk)); } -EXPORT_SYMBOL_GPL(account_system_vtime); /* * Called from the timer interrupt handler to charge accumulated user time @@ -146,14 +153,7 @@ EXPORT_SYMBOL_GPL(account_system_vtime); */ void account_process_tick(struct task_struct *p, int user_tick) { - struct thread_info *ti = task_thread_info(p); - cputime_t delta_utime; - - if (ti->ac_utime) { - delta_utime = cycle_to_cputime(ti->ac_utime); - account_user_time(p, delta_utime, delta_utime); - ti->ac_utime = 0; - } + vtime_account_user(p); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING */ diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 3a4a32b..384e63f 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -26,6 +26,7 @@ #include <linux/ptrace.h> #include <linux/unistd.h> #include <linux/hardirq.h> +#include <linux/rcupdate.h> #include <asm/io.h> #include <asm/uaccess.h> @@ -82,6 +83,7 @@ void cpu_idle (void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) { void (*idle)(void) = pm_idle; @@ -90,6 +92,7 @@ void cpu_idle (void) idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index c488e3c..ac2892e 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -25,6 +25,7 @@ #include <linux/reboot.h> #include <linux/init_task.h> #include <linux/mqueue.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/traps.h> @@ -75,8 +76,10 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) idle(); + rcu_idle_exit(); schedule_preempt_disabled(); } } diff --git a/arch/m68k/platform/coldfire/clk.c b/arch/m68k/platform/coldfire/clk.c index 75f9ee9..9cd13b4 100644 --- a/arch/m68k/platform/coldfire/clk.c +++ b/arch/m68k/platform/coldfire/clk.c @@ -146,9 +146,3 @@ struct clk_ops clk_ops1 = { }; #endif /* MCFPM_PPMCR1 */ #endif /* MCFPM_PPMCR0 */ - -struct clk *devm_clk_get(struct device *dev, const char *id) -{ - return NULL; -} -EXPORT_SYMBOL(devm_clk_get); diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index e7e03ec..afc379c 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -102,7 +102,7 @@ static void cmp_init_secondary(void) c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE; #endif #ifdef CONFIG_MIPS_MT_SMTC - c->tc_id = (read_c0_tcbind() >> TCBIND_CURTC_SHIFT) & TCBIND_CURTC; + c->tc_id = (read_c0_tcbind() & TCBIND_CURTC) >> TCBIND_CURTC_SHIFT; #endif } diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c index 33aadbc..dcfd573 100644 --- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -152,6 +152,8 @@ static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; + if (PageTail(page)) + get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 7b13a4c..fea823f 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -273,16 +273,19 @@ asmlinkage void plat_irq_dispatch(void) unsigned int pending = read_c0_cause() & read_c0_status() & ST0_IM; int irq; + if (unlikely(!pending)) { + spurious_interrupt(); + return; + } + irq = irq_ffs(pending); if (irq == MIPSCPU_INT_I8259A) malta_hw0_irqdispatch(); else if (gic_present && ((1 << irq) & ipi_map[smp_processor_id()])) malta_ipi_irqdispatch(); - else if (irq >= 0) - do_IRQ(MIPS_CPU_IRQ_BASE + irq); else - spurious_interrupt(); + do_IRQ(MIPS_CPU_IRQ_BASE + irq); } #ifdef CONFIG_MIPS_MT_SMP diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c index 4c35301..80562b8 100644 --- a/arch/mips/mti-malta/malta-platform.c +++ b/arch/mips/mti-malta/malta-platform.c @@ -138,11 +138,6 @@ static int __init malta_add_devices(void) if (err) return err; - /* - * Set RTC to BCD mode to support current alarm code. - */ - CMOS_WRITE(CMOS_READ(RTC_CONTROL) & ~RTC_DM_BINARY, RTC_CONTROL); - return 0; } diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 7dab0cd..e9cceba 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -25,6 +25,7 @@ #include <linux/err.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/io.h> @@ -107,6 +108,7 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ for (;;) { + rcu_idle_enter(); while (!need_resched()) { void (*idle)(void); @@ -121,6 +123,7 @@ void cpu_idle(void) } idle(); } + rcu_idle_exit(); schedule_preempt_disabled(); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 2c05a929..8c6b6b6 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -48,6 +48,7 @@ #include <linux/unistd.h> #include <linux/kallsyms.h> #include <linux/uaccess.h> +#include <linux/rcupdate.h> #include <asm/io.h> #include <asm/asm-offsets.h> @@ -69,8 +70,10 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) barrier(); + rcu_idle_exit(); schedule_preempt_disabled(); check_pgt_cache(); } diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 1c1aadc..c32ae5c 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -1,10 +1,6 @@ addnote empty.c hack-coff -infblock.c -infblock.h -infcodes.c -infcodes.h inffast.c inffast.h inffixed.h diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 53b6dfa..54b73a2 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -386,6 +386,7 @@ extern unsigned long cpuidle_disable; enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ +extern void power7_nap(void); #ifdef CONFIG_PSERIES_IDLE extern void update_smt_snooze_delay(int snooze); diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 3b4b4a8..c1f2676 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -197,12 +197,6 @@ struct cpu_usage { DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array); -#if defined(CONFIG_VIRT_CPU_ACCOUNTING) -#define account_process_vtime(tsk) account_process_tick(tsk, 0) -#else -#define account_process_vtime(tsk) do { } while (0) -#endif - extern void secondary_cpu_time_init(void); DECLARE_PER_CPU(u64, decrementers_next_tb); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 85b05c4..e899572 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -76,6 +76,7 @@ int main(void) DEFINE(SIGSEGV, SIGSEGV); DEFINE(NMI_MASK, NMI_MASK); DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr)); + DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit)); #else DEFINE(THREAD_INFO, offsetof(struct task_struct, stack)); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 5b25c80..a892680 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void) void doorbell_cause_ipi(int cpu, unsigned long data) { + /* Order previous accesses vs. msgsnd, which is treated as a store */ + mb(); ppc_msgsnd(PPC_DBELL, 0, data); } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 4b01a25..b40e0b4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -370,6 +370,12 @@ _GLOBAL(ret_from_fork) li r3,0 b syscall_exit + .section ".toc","aw" +DSCR_DEFAULT: + .tc dscr_default[TC],dscr_default + + .section ".text" + /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -509,9 +515,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) mr r1,r8 /* start using new stack pointer */ std r7,PACAKSAVE(r13) - ld r6,_CCR(r1) - mtcrf 0xFF,r6 - #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION ld r0,THREAD_VRSAVE(r4) @@ -520,14 +523,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_PPC64 BEGIN_FTR_SECTION + lwz r6,THREAD_DSCR_INHERIT(r4) + ld r7,DSCR_DEFAULT@toc(2) ld r0,THREAD_DSCR(r4) - cmpd r0,r25 - beq 1f + cmpwi r6,0 + bne 1f + ld r0,0(r7) +1: cmpd r0,r25 + beq 2f mtspr SPRN_DSCR,r0 -1: +2: END_FTR_SECTION_IFSET(CPU_FTR_DSCR) #endif + ld r6,_CCR(r1) + mtcrf 0xFF,r6 + /* r3-r13 are destroyed -- Cort */ REST_8GPRS(14, r1) REST_10GPRS(22, r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e894515..39aa97d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -186,7 +186,7 @@ hardware_interrupt_hv: KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) - MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer) + STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00) @@ -486,6 +486,7 @@ machine_check_common: STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) + STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception) STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 7140d83..e11863f 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -28,7 +28,9 @@ _GLOBAL(power7_idle) lwz r4,ADDROFF(powersave_nap)(r3) cmpwi 0,r4,0 beqlr + /* fall through */ +_GLOBAL(power7_nap) /* NAP is a state loss, we create a regs frame on the * stack, fill it up with the state we care about and * stick a pointer to it in PACAR1. We really only diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 710f400..e9cb51f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -514,9 +514,6 @@ struct task_struct *__switch_to(struct task_struct *prev, local_irq_save(flags); - account_system_vtime(current); - account_process_vtime(current); - /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out @@ -802,16 +799,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #endif /* CONFIG_PPC_STD_MMU_64 */ #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_DSCR)) { - if (current->thread.dscr_inherit) { - p->thread.dscr_inherit = 1; - p->thread.dscr = current->thread.dscr; - } else if (0 != dscr_default) { - p->thread.dscr_inherit = 1; - p->thread.dscr = dscr_default; - } else { - p->thread.dscr_inherit = 0; - p->thread.dscr = 0; - } + p->thread.dscr_inherit = current->thread.dscr_inherit; + p->thread.dscr = current->thread.dscr; } #endif diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 0321007..8d4214a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -198,8 +198,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) struct cpu_messages *info = &per_cpu(ipi_message, cpu); char *message = (char *)&info->messages; + /* + * Order previous accesses before accesses in the IPI handler. + */ + smp_mb(); message[msg] = 1; - mb(); + /* + * cause_ipi functions are required to include a full barrier + * before doing whatever causes the IPI. + */ smp_ops->cause_ipi(cpu, info->data); } @@ -211,7 +218,7 @@ irqreturn_t smp_ipi_demux(void) mb(); /* order any irq clear */ do { - all = xchg_local(&info->messages, 0); + all = xchg(&info->messages, 0); #ifdef __BIG_ENDIAN if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION))) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 3529446..8302af6 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev, return sprintf(buf, "%lx\n", dscr_default); } +static void update_dscr(void *dummy) +{ + if (!current->thread.dscr_inherit) { + current->thread.dscr = dscr_default; + mtspr(SPRN_DSCR, dscr_default); + } +} + static ssize_t __used store_dscr_default(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev, return -EINVAL; dscr_default = val; + on_each_cpu(update_dscr, NULL, 1); + return count; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index be171ee..eaa9d0e 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -291,13 +291,12 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -void account_system_vtime(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk, + u64 *sys_scaled, u64 *stolen) { - u64 now, nowscaled, delta, deltascaled; - unsigned long flags; - u64 stolen, udelta, sys_scaled, user_scaled; + u64 now, nowscaled, deltascaled; + u64 udelta, delta, user_scaled; - local_irq_save(flags); now = mftb(); nowscaled = read_spurr(now); get_paca()->system_time += now - get_paca()->starttime; @@ -305,7 +304,7 @@ void account_system_vtime(struct task_struct *tsk) deltascaled = nowscaled - get_paca()->startspurr; get_paca()->startspurr = nowscaled; - stolen = calculate_stolen_time(now); + *stolen = calculate_stolen_time(now); delta = get_paca()->system_time; get_paca()->system_time = 0; @@ -322,35 +321,45 @@ void account_system_vtime(struct task_struct *tsk) * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - sys_scaled = delta; + *sys_scaled = delta; user_scaled = udelta; if (deltascaled != delta + udelta) { if (udelta) { - sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - sys_scaled; + *sys_scaled = deltascaled * delta / (delta + udelta); + user_scaled = deltascaled - *sys_scaled; } else { - sys_scaled = deltascaled; + *sys_scaled = deltascaled; } } get_paca()->user_time_scaled += user_scaled; - if (in_interrupt() || idle_task(smp_processor_id()) != tsk) { - account_system_time(tsk, 0, delta, sys_scaled); - if (stolen) - account_steal_time(stolen); - } else { - account_idle_time(delta + stolen); - } - local_irq_restore(flags); + return delta; +} + +void vtime_account_system(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_system_time(tsk, 0, delta, sys_scaled); + if (stolen) + account_steal_time(stolen); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_idle_time(delta + stolen); } -EXPORT_SYMBOL_GPL(account_system_vtime); /* * Transfer the user and system times accumulated in the paca * by the exception entry and exit code to the generic process * user and system time records. * Must be called with interrupts disabled. - * Assumes that account_system_vtime() has been called recently + * Assumes that vtime_account() has been called recently * (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ @@ -366,6 +375,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick) account_user_time(tsk, utime, utimescaled); } +void vtime_task_switch(struct task_struct *prev) +{ + vtime_account(prev); + account_process_tick(prev, 0); +} + #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ #define calc_cputime_factors() #endif @@ -535,6 +550,15 @@ void timer_interrupt(struct pt_regs * regs) trace_timer_interrupt_exit(regs); } +/* + * Hypervisor decrementer interrupts shouldn't occur but are sometimes + * left pending on exit from a KVM guest. We don't need to do anything + * to clear them, as they are edge-triggered. + */ +void hdec_interrupt(struct pt_regs *regs) +{ +} + #ifdef CONFIG_SUSPEND static void generic_suspend_disable_irqs(void) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 1589723..ae0843f 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -972,8 +972,9 @@ static int emulate_instruction(struct pt_regs *regs) cpu_has_feature(CPU_FTR_DSCR)) { PPC_WARN_EMULATED(mtdscr, regs); rd = (instword >> 21) & 0x1f; - mtspr(SPRN_DSCR, regs->gpr[rd]); + current->thread.dscr = regs->gpr[rd]; current->thread.dscr_inherit = 1; + mtspr(SPRN_DSCR, current->thread.dscr); return 0; } #endif diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index dd223b3..17e5b23 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -20,7 +20,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr) { int err; - err = __put_user(instr, addr); + __put_user_size(instr, addr, 4, err); if (err) return err; asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr)); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 39b1597..59213cf 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,11 +1436,11 @@ static long vphn_get_associativity(unsigned long cpu, /* * Update the node maps and sysfs entries for each cpu whose home node - * has changed. + * has changed. Returns 1 when the topology has changed, and 0 otherwise. */ int arch_update_cpu_topology(void) { - int cpu, nid, old_nid; + int cpu, nid, old_nid, changed = 0; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; struct device *dev; @@ -1466,9 +1466,10 @@ int arch_update_cpu_topology(void) dev = get_cpu_device(cpu); if (dev) kobject_uevent(&dev->kobj, KOBJ_CHANGE); + changed = 1; } - return 1; + return changed; } static void topology_work_fn(struct work_struct *work) diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 30fd01d..72afd28 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -1,6 +1,7 @@ config PPC64 bool "64-bit kernel" default n + select HAVE_VIRT_CPU_ACCOUNTING help This option selects whether a 32-bit or a 64-bit kernel will be built. @@ -337,21 +338,6 @@ config PPC_MM_SLICES default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES) default n -config VIRT_CPU_ACCOUNTING - bool "Deterministic task and CPU time accounting" - depends on PPC64 - default y - help - Select this option to enable more accurate task and CPU time - accounting. This is done by reading a CPU counter on each - kernel entry and exit and on transitions within the kernel - between system, softirq and hardirq state, so there is a - small performance impact. This also enables accounting of - stolen time on logically-partitioned systems running on - IBM POWER5-based machines. - - If in doubt, say Y here. - config PPC_HAVE_PMU_SUPPORT bool diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 3ef4625..7698b6e 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -106,14 +106,6 @@ static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; - /* If powersave_nap is enabled, use NAP mode, else just - * spin aimlessly - */ - if (!powersave_nap) { - generic_mach_cpu_die(); - return; - } - /* Standard hot unplug procedure */ local_irq_disable(); idle_task_exit(); @@ -128,7 +120,7 @@ static void pnv_smp_cpu_kill_self(void) */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { - power7_idle(); + power7_nap(); if (!generic_check_cpu_restart(cpu)) { DBG("CPU%d Unexpected exit while offline !\n", cpu); /* We may be getting an IPI, so we re-enable diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index 14469cf..df0fc58 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsigned int value) static inline void icp_hv_set_qirr(int n_cpu , u8 value) { int hw_cpu = get_hard_smp_processor_id(n_cpu); - long rc = plpar_hcall_norets(H_IPI, hw_cpu, value); + long rc; + + /* Make sure all previous accesses are ordered before IPI sending */ + mb(); + rc = plpar_hcall_norets(H_IPI, hw_cpu, value); if (rc != H_SUCCESS) { pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x " "returned %ld\n", __func__, n_cpu, hw_cpu, value, rc); diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild index 9858476..cc45d25 100644 --- a/arch/s390/Kbuild +++ b/arch/s390/Kbuild @@ -5,3 +5,4 @@ obj-$(CONFIG_CRYPTO_HW) += crypto/ obj-$(CONFIG_S390_HYPFS_FS) += hypfs/ obj-$(CONFIG_APPLDATA_BASE) += appldata/ obj-$(CONFIG_MATHEMU) += math-emu/ +obj-y += net/ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 107610e..f9acddd 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -49,10 +49,13 @@ config GENERIC_LOCKBREAK config PGSTE def_bool y if KVM -config VIRT_CPU_ACCOUNTING +config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y -config ARCH_SUPPORTS_DEBUG_PAGEALLOC +config KEXEC + def_bool y + +config AUDIT_ARCH def_bool y config S390 @@ -84,11 +87,15 @@ config S390 select HAVE_KERNEL_XZ select HAVE_ARCH_MUTEX_CPU_RELAX select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 + select HAVE_BPF_JIT if 64BIT && PACK_STACK select ARCH_SAVE_PAGE_KEYS if HIBERNATION select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_CMPXCHG_LOCAL + select HAVE_CMPXCHG_DOUBLE + select HAVE_VIRT_CPU_ACCOUNTING + select VIRT_CPU_ACCOUNTING select ARCH_DISCARD_MEMBLOCK select BUILDTIME_EXTABLE_SORT select ARCH_INLINE_SPIN_TRYLOCK @@ -133,9 +140,79 @@ source "init/Kconfig" source "kernel/Kconfig.freezer" -menu "Base setup" +menu "Processor type and features" + +config HAVE_MARCH_Z900_FEATURES + def_bool n + +config HAVE_MARCH_Z990_FEATURES + def_bool n + select HAVE_MARCH_Z900_FEATURES + +config HAVE_MARCH_Z9_109_FEATURES + def_bool n + select HAVE_MARCH_Z990_FEATURES + +config HAVE_MARCH_Z10_FEATURES + def_bool n + select HAVE_MARCH_Z9_109_FEATURES + +config HAVE_MARCH_Z196_FEATURES + def_bool n + select HAVE_MARCH_Z10_FEATURES + +choice + prompt "Processor type" + default MARCH_G5 + +config MARCH_G5 + bool "System/390 model G5 and G6" + depends on !64BIT + help + Select this to build a 31 bit kernel that works + on all ESA/390 and z/Architecture machines. -comment "Processor type and features" +config MARCH_Z900 + bool "IBM zSeries model z800 and z900" + select HAVE_MARCH_Z900_FEATURES if 64BIT + help + Select this to enable optimizations for model z800/z900 (2064 and + 2066 series). This will enable some optimizations that are not + available on older ESA/390 (31 Bit) only CPUs. + +config MARCH_Z990 + bool "IBM zSeries model z890 and z990" + select HAVE_MARCH_Z990_FEATURES if 64BIT + help + Select this to enable optimizations for model z890/z990 (2084 and + 2086 series). The kernel will be slightly faster but will not work + on older machines. + +config MARCH_Z9_109 + bool "IBM System z9" + select HAVE_MARCH_Z9_109_FEATURES if 64BIT + help + Select this to enable optimizations for IBM System z9 (2094 and + 2096 series). The kernel will be slightly faster but will not work + on older machines. + +config MARCH_Z10 + bool "IBM System z10" + select HAVE_MARCH_Z10_FEATURES if 64BIT + help + Select this to enable optimizations for IBM System z10 (2097 and + 2098 series). The kernel will be slightly faster but will not work + on older machines. + +config MARCH_Z196 + bool "IBM zEnterprise 114 and 196" + select HAVE_MARCH_Z196_FEATURES if 64BIT + help + Select this to enable optimizations for IBM zEnterprise 114 and 196 + (2818 and 2817 series). The kernel will be slightly faster but will + not work on older machines. + +endchoice config 64BIT def_bool y @@ -147,6 +224,24 @@ config 64BIT config 32BIT def_bool y if !64BIT +config COMPAT + def_bool y + prompt "Kernel support for 31 bit emulation" + depends on 64BIT + select COMPAT_BINFMT_ELF if BINFMT_ELF + select ARCH_WANT_OLD_COMPAT_IPC + help + Select this option if you want to enable your system kernel to + handle system-calls from ELF binaries for 31 bit ESA. This option + (and some other stuff like libraries and such) is needed for + executing 31 bit applications. It is safe to say "Y". + +config SYSVIPC_COMPAT + def_bool y if COMPAT && SYSVIPC + +config KEYS_COMPAT + def_bool y if COMPAT && KEYS + config SMP def_bool y prompt "Symmetric multi-processing support" @@ -202,6 +297,8 @@ config SCHED_BOOK Book scheduler support improves the CPU scheduler's decision making when dealing with machines that have several books. +source kernel/Kconfig.preempt + config MATHEMU def_bool y prompt "IEEE FPU emulation" @@ -211,100 +308,35 @@ config MATHEMU on older ESA/390 machines. Say Y unless you know your machine doesn't need this. -config COMPAT - def_bool y - prompt "Kernel support for 31 bit emulation" - depends on 64BIT - select COMPAT_BINFMT_ELF if BINFMT_ELF - select ARCH_WANT_OLD_COMPAT_IPC - help - Select this option if you want to enable your system kernel to - handle system-calls from ELF binaries for 31 bit ESA. This option - (and some other stuff like libraries and such) is needed for - executing 31 bit applications. It is safe to say "Y". +source kernel/Kconfig.hz -config SYSVIPC_COMPAT - def_bool y if COMPAT && SYSVIPC +endmenu -config KEYS_COMPAT - def_bool y if COMPAT && KEYS +menu "Memory setup" -config AUDIT_ARCH +config ARCH_SPARSEMEM_ENABLE def_bool y + select SPARSEMEM_VMEMMAP_ENABLE + select SPARSEMEM_VMEMMAP + select SPARSEMEM_STATIC if !64BIT -config HAVE_MARCH_Z900_FEATURES - def_bool n - -config HAVE_MARCH_Z990_FEATURES - def_bool n - select HAVE_MARCH_Z900_FEATURES - -config HAVE_MARCH_Z9_109_FEATURES - def_bool n - select HAVE_MARCH_Z990_FEATURES - -config HAVE_MARCH_Z10_FEATURES - def_bool n - select HAVE_MARCH_Z9_109_FEATURES - -config HAVE_MARCH_Z196_FEATURES - def_bool n - select HAVE_MARCH_Z10_FEATURES - -comment "Code generation options" - -choice - prompt "Processor type" - default MARCH_G5 - -config MARCH_G5 - bool "System/390 model G5 and G6" - depends on !64BIT - help - Select this to build a 31 bit kernel that works - on all ESA/390 and z/Architecture machines. - -config MARCH_Z900 - bool "IBM zSeries model z800 and z900" - select HAVE_MARCH_Z900_FEATURES if 64BIT - help - Select this to enable optimizations for model z800/z900 (2064 and - 2066 series). This will enable some optimizations that are not - available on older ESA/390 (31 Bit) only CPUs. +config ARCH_SPARSEMEM_DEFAULT + def_bool y -config MARCH_Z990 - bool "IBM zSeries model z890 and z990" - select HAVE_MARCH_Z990_FEATURES if 64BIT - help - Select this to enable optimizations for model z890/z990 (2084 and - 2086 series). The kernel will be slightly faster but will not work - on older machines. +config ARCH_SELECT_MEMORY_MODEL + def_bool y -config MARCH_Z9_109 - bool "IBM System z9" - select HAVE_MARCH_Z9_109_FEATURES if 64BIT - help - Select this to enable optimizations for IBM System z9 (2094 and - 2096 series). The kernel will be slightly faster but will not work - on older machines. +config ARCH_ENABLE_MEMORY_HOTPLUG + def_bool y if SPARSEMEM -config MARCH_Z10 - bool "IBM System z10" - select HAVE_MARCH_Z10_FEATURES if 64BIT - help - Select this to enable optimizations for IBM System z10 (2097 and - 2098 series). The kernel will be slightly faster but will not work - on older machines. +config ARCH_ENABLE_MEMORY_HOTREMOVE + def_bool y -config MARCH_Z196 - bool "IBM zEnterprise 114 and 196" - select HAVE_MARCH_Z196_FEATURES if 64BIT - help - Select this to enable optimizations for IBM zEnterprise 114 and 196 - (2818 and 2817 series). The kernel will be slightly faster but will - not work on older machines. +config FORCE_MAX_ZONEORDER + int + default "9" -endchoice +source "mm/Kconfig" config PACK_STACK def_bool y @@ -368,34 +400,9 @@ config WARN_DYNAMIC_STACK Say N if you are unsure. -comment "Kernel preemption" - -source "kernel/Kconfig.preempt" - -config ARCH_SPARSEMEM_ENABLE - def_bool y - select SPARSEMEM_VMEMMAP_ENABLE - select SPARSEMEM_VMEMMAP - select SPARSEMEM_STATIC if !64BIT - -config ARCH_SPARSEMEM_DEFAULT - def_bool y - -config ARCH_SELECT_MEMORY_MODEL - def_bool y - -config ARCH_ENABLE_MEMORY_HOTPLUG - def_bool y if SPARSEMEM - -config ARCH_ENABLE_MEMORY_HOTREMOVE - def_bool y - -config ARCH_HIBERNATION_POSSIBLE - def_bool y if 64BIT - -source "mm/Kconfig" +endmenu -comment "I/O subsystem configuration" +menu "I/O subsystem" config QDIO def_tristate y @@ -426,13 +433,102 @@ config CHSC_SCH If unsure, say N. -comment "Misc" +config SCM_BUS + def_bool y + depends on 64BIT + prompt "SCM bus driver" + help + Bus driver for Storage Class Memory. + +config EADM_SCH + def_tristate m + prompt "Support for EADM subchannels" + depends on SCM_BUS + help + This driver allows usage of EADM subchannels. EADM subchannels act + as a communication vehicle for SCM increments. + + To compile this driver as a module, choose M here: the + module will be called eadm_sch. + +endmenu + +menu "Dump support" + +config CRASH_DUMP + bool "kernel crash dumps" + depends on 64BIT && SMP + select KEXEC + help + Generate crash dump after being started by kexec. + Crash dump kernels are loaded in the main kernel with kexec-tools + into a specially reserved region and then later executed after + a crash by kdump/kexec. + For more details see Documentation/kdump/kdump.txt + +config ZFCPDUMP + def_bool n + prompt "zfcpdump support" + select SMP + help + Select this option if you want to build an zfcpdump enabled kernel. + Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this. + +endmenu + +menu "Executable file formats / Emulations" source "fs/Kconfig.binfmt" -config FORCE_MAX_ZONEORDER - int - default "9" +config SECCOMP + def_bool y + prompt "Enable seccomp to safely compute untrusted bytecode" + depends on PROC_FS + help + This kernel feature is useful for number crunching applications + that may need to compute untrusted bytecode during their + execution. By using pipes or other transports made available to + the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in + their own address space using seccomp. Once seccomp is + enabled via /proc/<pid>/seccomp, it cannot be disabled + and the task is only allowed to execute a few safe syscalls + defined by each seccomp mode. + + If unsure, say Y. + +endmenu + +menu "Power Management" + +config ARCH_HIBERNATION_POSSIBLE + def_bool y if 64BIT + +source "kernel/power/Kconfig" + +endmenu + +source "net/Kconfig" + +config PCMCIA + def_bool n + +config CCW + def_bool y + +source "drivers/Kconfig" + +source "fs/Kconfig" + +source "arch/s390/Kconfig.debug" + +source "security/Kconfig" + +source "crypto/Kconfig" + +source "lib/Kconfig" + +menu "Virtualization" config PFAULT def_bool y @@ -448,8 +544,8 @@ config PFAULT this option. config SHARED_KERNEL - def_bool y - prompt "VM shared kernel support" + bool "VM shared kernel support" + depends on !JUMP_LABEL help Select this option, if you want to share the text segment of the Linux kernel between different VM guests. This reduces memory @@ -544,8 +640,6 @@ config APPLDATA_NET_SUM This can also be compiled as a module, which will be called appldata_net_sum.o. -source kernel/Kconfig.hz - config S390_HYPFS_FS def_bool y prompt "s390 hypervisor file system support" @@ -554,90 +648,21 @@ config S390_HYPFS_FS This is a virtual file system intended to provide accounting information in an s390 hypervisor environment. -config KEXEC - def_bool n - prompt "kexec system call" - help - kexec is a system call that implements the ability to shutdown your - current kernel, and to start another kernel. It is like a reboot - but is independent of hardware/microcode support. - -config CRASH_DUMP - bool "kernel crash dumps" - depends on 64BIT && SMP - select KEXEC - help - Generate crash dump after being started by kexec. - Crash dump kernels are loaded in the main kernel with kexec-tools - into a specially reserved region and then later executed after - a crash by kdump/kexec. - For more details see Documentation/kdump/kdump.txt - -config ZFCPDUMP - def_bool n - prompt "zfcpdump support" - select SMP - help - Select this option if you want to build an zfcpdump enabled kernel. - Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this. +source "arch/s390/kvm/Kconfig" config S390_GUEST def_bool y - prompt "s390 guest support for KVM (EXPERIMENTAL)" + prompt "s390 support for virtio devices (EXPERIMENTAL)" depends on 64BIT && EXPERIMENTAL select VIRTUALIZATION select VIRTIO select VIRTIO_RING select VIRTIO_CONSOLE help - Select this option if you want to run the kernel as a guest under - the KVM hypervisor. This will add detection for KVM as well as a - virtio transport. If KVM is detected, the virtio console will be - the default console. - -config SECCOMP - def_bool y - prompt "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. - -endmenu + Enabling this option adds support for virtio based paravirtual device + drivers on s390. -menu "Power Management" - -source "kernel/power/Kconfig" + Select this option if you want to run the kernel as a guest under + the KVM hypervisor. endmenu - -source "net/Kconfig" - -config PCMCIA - def_bool n - -config CCW - def_bool y - -source "drivers/Kconfig" - -source "fs/Kconfig" - -source "arch/s390/Kconfig.debug" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - -source "arch/s390/kvm/Kconfig" diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 10e22c4..3ad8f61 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -11,6 +11,7 @@ targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \ sizes.h head$(BITS).o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += $(call cc-option,-mpacked-stack) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 465eca7..c4c6a1c 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -71,34 +71,37 @@ void *memset(void *s, int c, size_t n) { char *xs; - if (c == 0) - return __builtin_memset(s, 0, n); - - xs = (char *) s; - if (n > 0) - do { - *xs++ = c; - } while (--n > 0); + xs = s; + while (n--) + *xs++ = c; return s; } -void *memcpy(void *__dest, __const void *__src, size_t __n) +void *memcpy(void *dest, const void *src, size_t n) { - return __builtin_memcpy(__dest, __src, __n); + const char *s = src; + char *d = dest; + + while (n--) + *d++ = *s++; + return dest; } -void *memmove(void *__dest, __const void *__src, size_t __n) +void *memmove(void *dest, const void *src, size_t n) { - char *d; - const char *s; - - if (__dest <= __src) - return __builtin_memcpy(__dest, __src, __n); - d = __dest + __n; - s = __src + __n; - while (__n--) - *--d = *--s; - return __dest; + const char *s = src; + char *d = dest; + + if (d <= s) { + while (n--) + *d++ = *s++; + } else { + d += n; + s += n; + while (n--) + *--d = *--s; + } + return dest; } static void error(char *x) diff --git a/arch/s390/defconfig b/arch/s390/defconfig index f39cd71..b74400e 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -16,8 +16,8 @@ CONFIG_CGROUPS=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEMCG=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y @@ -32,20 +32,19 @@ CONFIG_EXPERT=y CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_PREEMPT=y +CONFIG_HZ_100=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y -CONFIG_BINFMT_MISC=m -CONFIG_CMM=m -CONFIG_HZ_100=y CONFIG_CRASH_DUMP=y +CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -75,6 +74,7 @@ CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=y +CONFIG_BPF_JIT=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=m @@ -121,7 +121,6 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_TRACE=y CONFIG_KPROBES_SANITY_TEST=y CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -CONFIG_CPU_NOTIFIER_ERROR_INJECT=m CONFIG_LATENCYTOP=y CONFIG_DEBUG_PAGEALLOC=y CONFIG_BLK_DEV_IO_TRACE=y @@ -173,3 +172,4 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRC7=m +CONFIG_CMM=m diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h index f328294..32a7059 100644 --- a/arch/s390/include/asm/appldata.h +++ b/arch/s390/include/asm/appldata.h @@ -70,7 +70,7 @@ static inline int appldata_asm(struct appldata_product_id *id, int ry; if (!MACHINE_IS_VM) - return -ENOSYS; + return -EOPNOTSUPP; parm_list.diag = 0xdc; parm_list.function = fn; parm_list.parlist_length = sizeof(parm_list); diff --git a/arch/s390/include/asm/chsc.h b/arch/s390/include/asm/chsc.h index bf115b4..aea451f 100644 --- a/arch/s390/include/asm/chsc.h +++ b/arch/s390/include/asm/chsc.h @@ -125,32 +125,4 @@ struct chsc_cpd_info { #define CHSC_INFO_CPD _IOWR(CHSC_IOCTL_MAGIC, 0x87, struct chsc_cpd_info) #define CHSC_INFO_DCAL _IOWR(CHSC_IOCTL_MAGIC, 0x88, struct chsc_dcal) -#ifdef __KERNEL__ - -struct css_general_char { - u64 : 12; - u32 dynio : 1; /* bit 12 */ - u32 : 28; - u32 aif : 1; /* bit 41 */ - u32 : 3; - u32 mcss : 1; /* bit 45 */ - u32 fcs : 1; /* bit 46 */ - u32 : 1; - u32 ext_mb : 1; /* bit 48 */ - u32 : 7; - u32 aif_tdd : 1; /* bit 56 */ - u32 : 1; - u32 qebsm : 1; /* bit 58 */ - u32 : 8; - u32 aif_osa : 1; /* bit 67 */ - u32 : 14; - u32 cib : 1; /* bit 82 */ - u32 : 5; - u32 fcx : 1; /* bit 88 */ - u32 : 7; -}__attribute__((packed)); - -extern struct css_general_char css_general_characteristics; - -#endif /* __KERNEL__ */ #endif diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 77043aa..55bde60 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -80,6 +80,18 @@ struct erw { } __attribute__ ((packed)); /** + * struct erw_eadm - EADM Subchannel extended report word + * @b: aob error + * @r: arsb error + */ +struct erw_eadm { + __u32 : 16; + __u32 b : 1; + __u32 r : 1; + __u32 : 14; +} __packed; + +/** * struct sublog - subchannel logout area * @res0: reserved * @esf: extended status flags @@ -170,9 +182,22 @@ struct esw3 { } __attribute__ ((packed)); /** + * struct esw_eadm - EADM Subchannel Extended Status Word (ESW) + * @sublog: subchannel logout + * @erw: extended report word + */ +struct esw_eadm { + __u32 sublog; + struct erw_eadm erw; + __u32 : 32; + __u32 : 32; + __u32 : 32; +} __packed; + +/** * struct irb - interruption response block * @scsw: subchannel status word - * @esw: extened status word, 4 formats + * @esw: extened status word * @ecw: extended control word * * The irb that is handed to the device driver when an interrupt occurs. For @@ -191,6 +216,7 @@ struct irb { struct esw1 esw1; struct esw2 esw2; struct esw3 esw3; + struct esw_eadm eadm; } esw; __u8 ecw[32]; } __attribute__ ((packed,aligned(4))); diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h index 8d798e9..0f636cb 100644 --- a/arch/s390/include/asm/cmpxchg.h +++ b/arch/s390/include/asm/cmpxchg.h @@ -7,7 +7,9 @@ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H +#include <linux/mmdebug.h> #include <linux/types.h> +#include <linux/bug.h> extern void __xchg_called_with_bad_pointer(void); @@ -203,6 +205,65 @@ static inline unsigned long long __cmpxchg64(void *ptr, }) #endif /* CONFIG_64BIT */ +#define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn) \ +({ \ + register __typeof__(*(p1)) __old1 asm("2") = (o1); \ + register __typeof__(*(p2)) __old2 asm("3") = (o2); \ + register __typeof__(*(p1)) __new1 asm("4") = (n1); \ + register __typeof__(*(p2)) __new2 asm("5") = (n2); \ + int cc; \ + asm volatile( \ + insn " %[old],%[new],%[ptr]\n" \ + " ipm %[cc]\n" \ + " srl %[cc],28" \ + : [cc] "=d" (cc), [old] "+d" (__old1), "+d" (__old2) \ + : [new] "d" (__new1), "d" (__new2), \ + [ptr] "Q" (*(p1)), "Q" (*(p2)) \ + : "memory", "cc"); \ + !cc; \ +}) + +#define __cmpxchg_double_4(p1, p2, o1, o2, n1, n2) \ + __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, "cds") + +#define __cmpxchg_double_8(p1, p2, o1, o2, n1, n2) \ + __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, "cdsg") + +extern void __cmpxchg_double_called_with_bad_pointer(void); + +#define __cmpxchg_double(p1, p2, o1, o2, n1, n2) \ +({ \ + int __ret; \ + switch (sizeof(*(p1))) { \ + case 4: \ + __ret = __cmpxchg_double_4(p1, p2, o1, o2, n1, n2); \ + break; \ + case 8: \ + __ret = __cmpxchg_double_8(p1, p2, o1, o2, n1, n2); \ + break; \ + default: \ + __cmpxchg_double_called_with_bad_pointer(); \ + } \ + __ret; \ +}) + +#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ +({ \ + __typeof__(p1) __p1 = (p1); \ + __typeof__(p2) __p2 = (p2); \ + int __ret; \ + BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long)); \ + BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long)); \ + VM_BUG_ON((unsigned long)((__p1) + 1) != (unsigned long)(__p2));\ + if (sizeof(long) == 4) \ + __ret = __cmpxchg_double_4(__p1, __p2, o1, o2, n1, n2); \ + else \ + __ret = __cmpxchg_double_8(__p1, __p2, o1, o2, n1, n2); \ + __ret; \ +}) + +#define system_has_cmpxchg_double() 1 + #include <asm-generic/cmpxchg-local.h> static inline unsigned long __cmpxchg_local(void *ptr, diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index a3afecd..35f0020 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -21,11 +21,15 @@ #define CPU_MF_INT_SF_LSDA (1 << 22) /* loss of sample data alert */ #define CPU_MF_INT_CF_CACA (1 << 7) /* counter auth. change alert */ #define CPU_MF_INT_CF_LCDA (1 << 6) /* loss of counter data alert */ +#define CPU_MF_INT_RI_HALTED (1 << 5) /* run-time instr. halted */ +#define CPU_MF_INT_RI_BUF_FULL (1 << 4) /* run-time instr. program + buffer full */ #define CPU_MF_INT_CF_MASK (CPU_MF_INT_CF_CACA|CPU_MF_INT_CF_LCDA) #define CPU_MF_INT_SF_MASK (CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE| \ CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA| \ CPU_MF_INT_SF_LSDA) +#define CPU_MF_INT_RI_MASK (CPU_MF_INT_RI_HALTED|CPU_MF_INT_RI_BUF_FULL) /* CPU measurement facility support */ static inline int cpum_cf_avail(void) diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 8709bde..023d5ae 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -12,6 +12,9 @@ #include <linux/spinlock.h> #include <asm/div64.h> + +#define __ARCH_HAS_VTIME_ACCOUNT + /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ typedef unsigned long long __nocast cputime_t; diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h new file mode 100644 index 0000000..a06ebc2 --- /dev/null +++ b/arch/s390/include/asm/css_chars.h @@ -0,0 +1,39 @@ +#ifndef _ASM_CSS_CHARS_H +#define _ASM_CSS_CHARS_H + +#include <linux/types.h> + +#ifdef __KERNEL__ + +struct css_general_char { + u64 : 12; + u32 dynio : 1; /* bit 12 */ + u32 : 4; + u32 eadm : 1; /* bit 17 */ + u32 : 23; + u32 aif : 1; /* bit 41 */ + u32 : 3; + u32 mcss : 1; /* bit 45 */ + u32 fcs : 1; /* bit 46 */ + u32 : 1; + u32 ext_mb : 1; /* bit 48 */ + u32 : 7; + u32 aif_tdd : 1; /* bit 56 */ + u32 : 1; + u32 qebsm : 1; /* bit 58 */ + u32 : 8; + u32 aif_osa : 1; /* bit 67 */ + u32 : 12; + u32 eadm_rf : 1; /* bit 80 */ + u32 : 1; + u32 cib : 1; /* bit 82 */ + u32 : 5; + u32 fcx : 1; /* bit 88 */ + u32 : 19; + u32 alt_ssi : 1; /* bit 108 */ +} __packed; + +extern struct css_general_char css_general_characteristics; + +#endif /* __KERNEL__ */ +#endif diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h new file mode 100644 index 0000000..8d48471 --- /dev/null +++ b/arch/s390/include/asm/eadm.h @@ -0,0 +1,124 @@ +#ifndef _ASM_S390_EADM_H +#define _ASM_S390_EADM_H + +#include <linux/types.h> +#include <linux/device.h> + +struct arqb { + u64 data; + u16 fmt:4; + u16:12; + u16 cmd_code; + u16:16; + u16 msb_count; + u32 reserved[12]; +} __packed; + +#define ARQB_CMD_MOVE 1 + +struct arsb { + u16 fmt:4; + u32:28; + u8 ef; + u8:8; + u8 ecbi; + u8:8; + u8 fvf; + u16:16; + u8 eqc; + u32:32; + u64 fail_msb; + u64 fail_aidaw; + u64 fail_ms; + u64 fail_scm; + u32 reserved[4]; +} __packed; + +struct msb { + u8 fmt:4; + u8 oc:4; + u8 flags; + u16:12; + u16 bs:4; + u32 blk_count; + u64 data_addr; + u64 scm_addr; + u64:64; +} __packed; + +struct aidaw { + u8 flags; + u32 :24; + u32 :32; + u64 data_addr; +} __packed; + +#define MSB_OC_CLEAR 0 +#define MSB_OC_READ 1 +#define MSB_OC_WRITE 2 +#define MSB_OC_RELEASE 3 + +#define MSB_FLAG_BNM 0x80 +#define MSB_FLAG_IDA 0x40 + +#define MSB_BS_4K 0 +#define MSB_BS_1M 1 + +#define AOB_NR_MSB 124 + +struct aob { + struct arqb request; + struct arsb response; + struct msb msb[AOB_NR_MSB]; +} __packed __aligned(PAGE_SIZE); + +struct aob_rq_header { + struct scm_device *scmdev; + char data[0]; +}; + +struct scm_device { + u64 address; + u64 size; + unsigned int nr_max_block; + struct device dev; + struct { + unsigned int persistence:4; + unsigned int oper_state:4; + unsigned int data_state:4; + unsigned int rank:4; + unsigned int release:1; + unsigned int res_id:8; + } __packed attrs; +}; + +#define OP_STATE_GOOD 1 +#define OP_STATE_TEMP_ERR 2 +#define OP_STATE_PERM_ERR 3 + +struct scm_driver { + struct device_driver drv; + int (*probe) (struct scm_device *scmdev); + int (*remove) (struct scm_device *scmdev); + void (*notify) (struct scm_device *scmdev); + void (*handler) (struct scm_device *scmdev, void *data, int error); +}; + +int scm_driver_register(struct scm_driver *scmdrv); +void scm_driver_unregister(struct scm_driver *scmdrv); + +int scm_start_aob(struct aob *aob); +void scm_irq_handler(struct aob *aob, int error); + +struct eadm_ops { + int (*eadm_start) (struct aob *aob); + struct module *owner; +}; + +int scm_get_ref(void); +void scm_put_ref(void); + +void register_eadm_ops(struct eadm_ops *ops); +void unregister_eadm_ops(struct eadm_ops *ops); + +#endif /* _ASM_S390_EADM_H */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 9b94a16..178ff96 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -101,6 +101,7 @@ #define HWCAP_S390_HPAGE 128 #define HWCAP_S390_ETF3EH 256 #define HWCAP_S390_HIGH_GPRS 512 +#define HWCAP_S390_TE 1024 /* * These are used to set parameters in the core dumps. @@ -212,4 +213,6 @@ int arch_setup_additional_pages(struct linux_binprm *, int); extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa); + #endif diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h index a24b03b..629b79a 100644 --- a/arch/s390/include/asm/etr.h +++ b/arch/s390/include/asm/etr.h @@ -140,7 +140,7 @@ struct etr_ptff_qto { /* Inline assembly helper functions */ static inline int etr_setr(struct etr_eacr *ctrl) { - int rc = -ENOSYS; + int rc = -EOPNOTSUPP; asm volatile( " .insn s,0xb2160000,%1\n" @@ -154,7 +154,7 @@ static inline int etr_setr(struct etr_eacr *ctrl) /* Stores a format 1 aib with 64 bytes */ static inline int etr_stetr(struct etr_aib *aib) { - int rc = -ENOSYS; + int rc = -EOPNOTSUPP; asm volatile( " .insn s,0xb2170000,%1\n" @@ -169,7 +169,7 @@ static inline int etr_stetr(struct etr_aib *aib) static inline int etr_steai(struct etr_aib *aib, unsigned int func) { register unsigned int reg0 asm("0") = func; - int rc = -ENOSYS; + int rc = -EOPNOTSUPP; asm volatile( " .insn s,0xb2b30000,%1\n" @@ -190,7 +190,7 @@ static inline int etr_ptff(void *ptff_block, unsigned int func) { register unsigned int reg0 asm("0") = func; register unsigned long reg1 asm("1") = (unsigned long) ptff_block; - int rc = -ENOSYS; + int rc = -EOPNOTSUPP; asm volatile( " .word 0x0104\n" diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 799ed0f..2d6e6e3 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -66,16 +66,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return pte; } -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = huge_ptep_get(ptep); - - mm->context.flush_mm = 1; - pmd_clear((pmd_t *) ptep); - return pte; -} - static inline void __pmd_csp(pmd_t *pmdp) { register unsigned long reg2 asm("2") = pmd_val(*pmdp); @@ -117,6 +107,15 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm, __pmd_csp(pmdp); } +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t pte = huge_ptep_get(ptep); + + huge_ptep_invalidate(mm, addr, ptep); + return pte; +} + #define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \ ({ \ int __changed = !pte_same(huge_ptep_get(__ptep), __entry); \ @@ -131,10 +130,7 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm, ({ \ pte_t __pte = huge_ptep_get(__ptep); \ if (pte_write(__pte)) { \ - (__mm)->context.flush_mm = 1; \ - if (atomic_read(&(__mm)->context.attach_count) > 1 || \ - (__mm) != current->active_mm) \ - huge_ptep_invalidate(__mm, __addr, __ptep); \ + huge_ptep_invalidate(__mm, __addr, __ptep); \ set_huge_pte_at(__mm, __addr, __ptep, \ huge_pte_wrprotect(__pte)); \ } \ diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index 2b9d418..6703dd9 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -19,6 +19,7 @@ enum interruption_class { EXTINT_IUC, EXTINT_CMS, EXTINT_CMC, + EXTINT_CMR, IOINT_CIO, IOINT_QAI, IOINT_DAS, @@ -30,6 +31,7 @@ enum interruption_class { IOINT_CLW, IOINT_CTC, IOINT_APB, + IOINT_ADM, IOINT_CSC, NMI_NMI, NR_IRQS, diff --git a/arch/s390/include/asm/isc.h b/arch/s390/include/asm/isc.h index 1420a11..5ae6064 100644 --- a/arch/s390/include/asm/isc.h +++ b/arch/s390/include/asm/isc.h @@ -14,6 +14,7 @@ /* Regular I/O interrupts. */ #define IO_SCH_ISC 3 /* regular I/O subchannels */ #define CONSOLE_ISC 1 /* console I/O subchannel */ +#define EADM_SCH_ISC 4 /* EADM subchannels */ #define CHSC_SCH_ISC 7 /* CHSC subchannels */ /* Adapter interrupts. */ #define QDIO_AIRQ_ISC IO_SCH_ISC /* I/O subchannel in qdio mode */ diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index aab5555..bbf8141 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -329,9 +329,13 @@ struct _lowcore { __u8 pad_0x1338[0x1340-0x1338]; /* 0x1338 */ __u32 access_regs_save_area[16]; /* 0x1340 */ __u64 cregs_save_area[16]; /* 0x1380 */ + __u8 pad_0x1400[0x1800-0x1400]; /* 0x1400 */ + + /* Transaction abort diagnostic block */ + __u8 pgm_tdb[256]; /* 0x1800 */ /* align to the top of the prefix area */ - __u8 pad_0x1400[0x2000-0x1400]; /* 0x1400 */ + __u8 pad_0x1900[0x2000-0x1900]; /* 0x1900 */ } __packed; #endif /* CONFIG_32BIT */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index b749c57..084e775 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -57,7 +57,7 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk) pgd_t *pgd = mm->pgd; S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd); - if (addressing_mode != HOME_SPACE_MODE) { + if (s390_user_mode != HOME_SPACE_MODE) { /* Load primary space page table origin. */ asm volatile(LCTL_OPCODE" 1,1,%0\n" : : "m" (S390_lowcore.user_asce) ); diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 6537e72..86fe0ee 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -20,7 +20,7 @@ #endif #define arch_this_cpu_to_op(pcp, val, op) \ -do { \ +({ \ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ old__, new__, prev__; \ pcp_op_T__ *ptr__; \ @@ -39,13 +39,19 @@ do { \ } \ } while (prev__ != old__); \ preempt_enable(); \ -} while (0) + new__; \ +}) #define this_cpu_add_1(pcp, val) arch_this_cpu_to_op(pcp, val, +) #define this_cpu_add_2(pcp, val) arch_this_cpu_to_op(pcp, val, +) #define this_cpu_add_4(pcp, val) arch_this_cpu_to_op(pcp, val, +) #define this_cpu_add_8(pcp, val) arch_this_cpu_to_op(pcp, val, +) +#define this_cpu_add_return_1(pcp, val) arch_this_cpu_to_op(pcp, val, +) +#define this_cpu_add_return_2(pcp, val) arch_this_cpu_to_op(pcp, val, +) +#define this_cpu_add_return_4(pcp, val) arch_this_cpu_to_op(pcp, val, +) +#define this_cpu_add_return_8(pcp, val) arch_this_cpu_to_op(pcp, val, +) + #define this_cpu_and_1(pcp, val) arch_this_cpu_to_op(pcp, val, &) #define this_cpu_and_2(pcp, val) arch_this_cpu_to_op(pcp, val, &) #define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, &) @@ -61,7 +67,7 @@ do { \ #define this_cpu_xor_4(pcp, val) arch_this_cpu_to_op(pcp, val, ^) #define this_cpu_xor_8(pcp, val) arch_this_cpu_to_op(pcp, val, ^) -#define arch_this_cpu_cmpxchg(pcp, oval, nval) \ +#define arch_this_cpu_cmpxchg(pcp, oval, nval) \ ({ \ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ ret__; \ @@ -84,6 +90,44 @@ do { \ #define this_cpu_cmpxchg_4(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval) #define this_cpu_cmpxchg_8(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval) +#define arch_this_cpu_xchg(pcp, nval) \ +({ \ + typeof(pcp) *ptr__; \ + typeof(pcp) ret__; \ + preempt_disable(); \ + ptr__ = __this_cpu_ptr(&(pcp)); \ + ret__ = xchg(ptr__, nval); \ + preempt_enable(); \ + ret__; \ +}) + +#define this_cpu_xchg_1(pcp, nval) arch_this_cpu_xchg(pcp, nval) +#define this_cpu_xchg_2(pcp, nval) arch_this_cpu_xchg(pcp, nval) +#define this_cpu_xchg_4(pcp, nval) arch_this_cpu_xchg(pcp, nval) +#ifdef CONFIG_64BIT +#define this_cpu_xchg_8(pcp, nval) arch_this_cpu_xchg(pcp, nval) +#endif + +#define arch_this_cpu_cmpxchg_double(pcp1, pcp2, o1, o2, n1, n2) \ +({ \ + typeof(pcp1) o1__ = (o1), n1__ = (n1); \ + typeof(pcp2) o2__ = (o2), n2__ = (n2); \ + typeof(pcp1) *p1__; \ + typeof(pcp2) *p2__; \ + int ret__; \ + preempt_disable(); \ + p1__ = __this_cpu_ptr(&(pcp1)); \ + p2__ = __this_cpu_ptr(&(pcp2)); \ + ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \ + preempt_enable(); \ + ret__; \ +}) + +#define this_cpu_cmpxchg_double_4 arch_this_cpu_cmpxchg_double +#ifdef CONFIG_64BIT +#define this_cpu_cmpxchg_double_8 arch_this_cpu_cmpxchg_double +#endif + #include <asm-generic/percpu.h> #endif /* __ARCH_S390_PERCPU__ */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 11e4e32..f3e0aab 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -11,12 +11,15 @@ #ifndef __ASM_S390_PROCESSOR_H #define __ASM_S390_PROCESSOR_H +#ifndef __ASSEMBLY__ + #include <linux/linkage.h> #include <linux/irqflags.h> #include <asm/cpu.h> #include <asm/page.h> #include <asm/ptrace.h> #include <asm/setup.h> +#include <asm/runtime_instr.h> /* * Default implementation of macro that returns current @@ -75,11 +78,20 @@ struct thread_struct { unsigned long gmap_addr; /* address of last gmap fault. */ struct per_regs per_user; /* User specified PER registers */ struct per_event per_event; /* Cause of the last PER trap */ + unsigned long per_flags; /* Flags to control debug behavior */ /* pfault_wait is used to block the process on a pfault event */ unsigned long pfault_wait; struct list_head list; + /* cpu runtime instrumentation */ + struct runtime_instr_cb *ri_cb; + int ri_signum; +#ifdef CONFIG_64BIT + unsigned char trap_tdb[256]; /* Transaction abort diagnose block */ +#endif }; +#define PER_FLAG_NO_TE 1UL /* Flag to disable transactions. */ + typedef struct thread_struct thread_struct; /* @@ -130,6 +142,12 @@ struct task_struct; struct mm_struct; struct seq_file; +#ifdef CONFIG_64BIT +extern void show_cacheinfo(struct seq_file *m); +#else +static inline void show_cacheinfo(struct seq_file *m) { } +#endif + /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); @@ -140,6 +158,7 @@ extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); extern unsigned long thread_saved_pc(struct task_struct *t); extern void show_code(struct pt_regs *regs); +extern void print_fn_code(unsigned char *code, unsigned long len); unsigned long get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ @@ -331,23 +350,6 @@ extern void (*s390_base_ext_handler_fn)(void); #define ARCH_LOW_ADDRESS_LIMIT 0x7fffffffUL -/* - * Helper macro for exception table entries - */ -#ifndef CONFIG_64BIT -#define EX_TABLE(_fault,_target) \ - ".section __ex_table,\"a\"\n" \ - " .align 4\n" \ - " .long " #_fault "," #_target "\n" \ - ".previous\n" -#else -#define EX_TABLE(_fault,_target) \ - ".section __ex_table,\"a\"\n" \ - " .align 8\n" \ - " .quad " #_fault "," #_target "\n" \ - ".previous\n" -#endif - extern int memcpy_real(void *, void *, size_t); extern void memcpy_absolute(void *, void *, size_t); @@ -358,4 +360,25 @@ extern void memcpy_absolute(void *, void *, size_t); memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ } -#endif /* __ASM_S390_PROCESSOR_H */ +/* + * Helper macro for exception table entries + */ +#define EX_TABLE(_fault, _target) \ + ".section __ex_table,\"a\"\n" \ + ".align 4\n" \ + ".long (" #_fault ") - .\n" \ + ".long (" #_target ") - .\n" \ + ".previous\n" + +#else /* __ASSEMBLY__ */ + +#define EX_TABLE(_fault, _target) \ + .section __ex_table,"a" ; \ + .align 4 ; \ + .long (_fault) - . ; \ + .long (_target) - . ; \ + .previous + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_S390_PROCESSOR_H */ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index d5f08ea..ce20a53 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -235,6 +235,7 @@ typedef struct #define PSW_MASK_ASC 0x0000C000UL #define PSW_MASK_CC 0x00003000UL #define PSW_MASK_PM 0x00000F00UL +#define PSW_MASK_RI 0x00000000UL #define PSW_MASK_EA 0x00000000UL #define PSW_MASK_BA 0x00000000UL @@ -264,10 +265,11 @@ typedef struct #define PSW_MASK_ASC 0x0000C00000000000UL #define PSW_MASK_CC 0x0000300000000000UL #define PSW_MASK_PM 0x00000F0000000000UL +#define PSW_MASK_RI 0x0000008000000000UL #define PSW_MASK_EA 0x0000000100000000UL #define PSW_MASK_BA 0x0000000080000000UL -#define PSW_MASK_USER 0x00003F0180000000UL +#define PSW_MASK_USER 0x00003F8180000000UL #define PSW_ADDR_AMODE 0x0000000000000000UL #define PSW_ADDR_INSN 0xFFFFFFFFFFFFFFFFUL @@ -359,17 +361,19 @@ struct per_struct_kernel { unsigned char access_id; /* PER trap access identification */ }; -#define PER_EVENT_MASK 0xE9000000UL +#define PER_EVENT_MASK 0xEB000000UL #define PER_EVENT_BRANCH 0x80000000UL #define PER_EVENT_IFETCH 0x40000000UL #define PER_EVENT_STORE 0x20000000UL #define PER_EVENT_STORE_REAL 0x08000000UL +#define PER_EVENT_TRANSACTION_END 0x02000000UL #define PER_EVENT_NULLIFICATION 0x01000000UL -#define PER_CONTROL_MASK 0x00a00000UL +#define PER_CONTROL_MASK 0x00e00000UL #define PER_CONTROL_BRANCH_ADDRESS 0x00800000UL +#define PER_CONTROL_SUSPENSION 0x00400000UL #define PER_CONTROL_ALTERATION 0x00200000UL #endif @@ -483,6 +487,8 @@ typedef struct #define PTRACE_GET_LAST_BREAK 0x5006 #define PTRACE_PEEK_SYSTEM_CALL 0x5007 #define PTRACE_POKE_SYSTEM_CALL 0x5008 +#define PTRACE_ENABLE_TE 0x5009 +#define PTRACE_DISABLE_TE 0x5010 /* * PT_PROT definition is loosely based on hppa bsd definition in diff --git a/arch/s390/include/asm/runtime_instr.h b/arch/s390/include/asm/runtime_instr.h new file mode 100644 index 0000000..830da73 --- /dev/null +++ b/arch/s390/include/asm/runtime_instr.h @@ -0,0 +1,98 @@ +#ifndef _RUNTIME_INSTR_H +#define _RUNTIME_INSTR_H + +#define S390_RUNTIME_INSTR_START 0x1 +#define S390_RUNTIME_INSTR_STOP 0x2 + +struct runtime_instr_cb { + __u64 buf_current; + __u64 buf_origin; + __u64 buf_limit; + + __u32 valid : 1; + __u32 pstate : 1; + __u32 pstate_set_buf : 1; + __u32 home_space : 1; + __u32 altered : 1; + __u32 : 3; + __u32 pstate_sample : 1; + __u32 sstate_sample : 1; + __u32 pstate_collect : 1; + __u32 sstate_collect : 1; + __u32 : 1; + __u32 halted_int : 1; + __u32 int_requested : 1; + __u32 buffer_full_int : 1; + __u32 key : 4; + __u32 : 9; + __u32 rgs : 3; + + __u32 mode : 4; + __u32 next : 1; + __u32 mae : 1; + __u32 : 2; + __u32 call_type_br : 1; + __u32 return_type_br : 1; + __u32 other_type_br : 1; + __u32 bc_other_type : 1; + __u32 emit : 1; + __u32 tx_abort : 1; + __u32 : 2; + __u32 bp_xn : 1; + __u32 bp_xt : 1; + __u32 bp_ti : 1; + __u32 bp_ni : 1; + __u32 suppr_y : 1; + __u32 suppr_z : 1; + + __u32 dc_miss_extra : 1; + __u32 lat_lev_ignore : 1; + __u32 ic_lat_lev : 4; + __u32 dc_lat_lev : 4; + + __u64 reserved1; + __u64 scaling_factor; + __u64 rsic; + __u64 reserved2; +} __packed __aligned(8); + +extern struct runtime_instr_cb runtime_instr_empty_cb; + +static inline void load_runtime_instr_cb(struct runtime_instr_cb *cb) +{ + asm volatile(".insn rsy,0xeb0000000060,0,0,%0" /* LRIC */ + : : "Q" (*cb)); +} + +static inline void store_runtime_instr_cb(struct runtime_instr_cb *cb) +{ + asm volatile(".insn rsy,0xeb0000000061,0,0,%0" /* STRIC */ + : "=Q" (*cb) : : "cc"); +} + +static inline void save_ri_cb(struct runtime_instr_cb *cb_prev) +{ +#ifdef CONFIG_64BIT + if (cb_prev) + store_runtime_instr_cb(cb_prev); +#endif +} + +static inline void restore_ri_cb(struct runtime_instr_cb *cb_next, + struct runtime_instr_cb *cb_prev) +{ +#ifdef CONFIG_64BIT + if (cb_next) + load_runtime_instr_cb(cb_next); + else if (cb_prev) + load_runtime_instr_cb(&runtime_instr_empty_cb); +#endif +} + +#ifdef CONFIG_64BIT +extern void exit_thread_runtime_instr(void); +#else +static inline void exit_thread_runtime_instr(void) { } +#endif + +#endif /* _RUNTIME_INSTR_H */ diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h index 4071d00..4af99cd 100644 --- a/arch/s390/include/asm/scsw.h +++ b/arch/s390/include/asm/scsw.h @@ -1,7 +1,7 @@ /* * Helper functions for scsw access. * - * Copyright IBM Corp. 2008, 2009 + * Copyright IBM Corp. 2008, 2012 * Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com> */ @@ -9,7 +9,7 @@ #define _ASM_S390_SCSW_H_ #include <linux/types.h> -#include <asm/chsc.h> +#include <asm/css_chars.h> #include <asm/cio.h> /** @@ -100,14 +100,46 @@ struct tm_scsw { } __attribute__ ((packed)); /** + * struct eadm_scsw - subchannel status word for eadm subchannels + * @key: subchannel key + * @eswf: esw format + * @cc: deferred condition code + * @ectl: extended control + * @fctl: function control + * @actl: activity control + * @stctl: status control + * @aob: AOB address + * @dstat: device status + * @cstat: subchannel status + */ +struct eadm_scsw { + u32 key:4; + u32:1; + u32 eswf:1; + u32 cc:2; + u32:6; + u32 ectl:1; + u32:2; + u32 fctl:3; + u32 actl:7; + u32 stctl:5; + u32 aob; + u32 dstat:8; + u32 cstat:8; + u32:16; +} __packed; + +/** * union scsw - subchannel status word * @cmd: command-mode SCSW * @tm: transport-mode SCSW + * @eadm: eadm SCSW */ union scsw { struct cmd_scsw cmd; struct tm_scsw tm; -} __attribute__ ((packed)); + struct eadm_scsw eadm; +} __packed; #define SCSW_FCTL_CLEAR_FUNC 0x1 #define SCSW_FCTL_HALT_FUNC 0x2 diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index e6859d1..87b47ca 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -60,7 +60,7 @@ void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr, #define SECONDARY_SPACE_MODE 2 #define HOME_SPACE_MODE 3 -extern unsigned int addressing_mode; +extern unsigned int s390_user_mode; /* * Machine features detected in head.S @@ -80,6 +80,7 @@ extern unsigned int addressing_mode; #define MACHINE_FLAG_LPAR (1UL << 12) #define MACHINE_FLAG_SPP (1UL << 13) #define MACHINE_FLAG_TOPOLOGY (1UL << 14) +#define MACHINE_FLAG_TE (1UL << 15) #define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) #define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) @@ -98,6 +99,7 @@ extern unsigned int addressing_mode; #define MACHINE_HAS_PFMF (0) #define MACHINE_HAS_SPP (0) #define MACHINE_HAS_TOPOLOGY (0) +#define MACHINE_HAS_TE (0) #else /* CONFIG_64BIT */ #define MACHINE_HAS_IEEE (1) #define MACHINE_HAS_CSP (1) @@ -109,6 +111,7 @@ extern unsigned int addressing_mode; #define MACHINE_HAS_PFMF (S390_lowcore.machine_flags & MACHINE_FLAG_PFMF) #define MACHINE_HAS_SPP (S390_lowcore.machine_flags & MACHINE_FLAG_SPP) #define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY) +#define MACHINE_HAS_TE (S390_lowcore.machine_flags & MACHINE_FLAG_TE) #endif /* CONFIG_64BIT */ #define ZFCPDUMP_HSA_SIZE (32UL<<20) diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index ce26ac3..b64f15c 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -30,6 +30,8 @@ extern int smp_vcpu_scheduled(int cpu); extern void smp_yield_cpu(int cpu); extern void smp_yield(void); extern void smp_stop_cpu(void); +extern void smp_cpu_set_polarization(int cpu, int val); +extern int smp_cpu_get_polarization(int cpu); #else /* CONFIG_SMP */ @@ -43,7 +45,7 @@ static inline void smp_call_online_cpu(void (*func)(void *), void *data) func(data); } -static inline int smp_find_processor_id(int address) { return 0; } +static inline int smp_find_processor_id(u16 address) { return 0; } static inline int smp_store_status(int cpu) { return 0; } static inline int smp_vcpu_scheduled(int cpu) { return 1; } static inline void smp_yield_cpu(int cpu) { } diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 1bd1352..7e2dcd7 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -96,7 +96,6 @@ static inline char *strcat(char *dst, const char *src) static inline char *strcpy(char *dst, const char *src) { -#if __GNUC__ < 4 register int r0 asm("0") = 0; char *ret = dst; @@ -106,14 +105,10 @@ static inline char *strcpy(char *dst, const char *src) : "+&a" (dst), "+&a" (src) : "d" (r0) : "cc", "memory"); return ret; -#else - return __builtin_strcpy(dst, src); -#endif } static inline size_t strlen(const char *s) { -#if __GNUC__ < 4 register unsigned long r0 asm("0") = 0; const char *tmp = s; @@ -122,9 +117,6 @@ static inline size_t strlen(const char *s) " jo 0b" : "+d" (r0), "+a" (tmp) : : "cc"); return r0 - (unsigned long) s; -#else - return __builtin_strlen(s); -#endif } static inline size_t strnlen(const char * s, size_t n) diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index f223068..f3a9e0f 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -80,21 +80,19 @@ static inline void restore_access_regs(unsigned int *acrs) if (prev->mm) { \ save_fp_regs(&prev->thread.fp_regs); \ save_access_regs(&prev->thread.acrs[0]); \ + save_ri_cb(prev->thread.ri_cb); \ } \ if (next->mm) { \ restore_fp_regs(&next->thread.fp_regs); \ restore_access_regs(&next->thread.acrs[0]); \ + restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ update_per_regs(next); \ } \ prev = __switch_to(prev,next); \ } while (0) -extern void account_vtime(struct task_struct *, struct task_struct *); -extern void account_tick_vtime(struct task_struct *); - #define finish_arch_switch(prev) do { \ set_fs(current->thread.mm_segment); \ - account_vtime(prev, current); \ } while (0) #endif /* __ASM_SWITCH_TO_H */ diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index 282ee36..f92428e 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -17,7 +17,10 @@ #include <asm/bitsperlong.h> struct sysinfo_1_1_1 { - unsigned short :16; + unsigned char p:1; + unsigned char :6; + unsigned char t:1; + unsigned char :8; unsigned char ccr; unsigned char cai; char reserved_0[28]; @@ -30,9 +33,14 @@ struct sysinfo_1_1_1 { char model[16]; char model_perm_cap[16]; char model_temp_cap[16]; - char model_cap_rating[4]; - char model_perm_cap_rating[4]; - char model_temp_cap_rating[4]; + unsigned int model_cap_rating; + unsigned int model_perm_cap_rating; + unsigned int model_temp_cap_rating; + unsigned char typepct[5]; + unsigned char reserved_2[3]; + unsigned int ncr; + unsigned int npr; + unsigned int ntr; }; struct sysinfo_1_2_1 { @@ -47,8 +55,9 @@ struct sysinfo_1_2_2 { char format; char reserved_0[1]; unsigned short acc_offset; - char reserved_1[24]; - unsigned int secondary_capability; + char reserved_1[20]; + unsigned int nominal_cap; + unsigned int secondary_cap; unsigned int capability; unsigned short cpus_total; unsigned short cpus_configured; @@ -109,6 +118,8 @@ struct sysinfo_3_2_2 { char reserved_544[3552]; }; +extern int topology_max_mnest; + #define TOPOLOGY_CPU_BITS 64 #define TOPOLOGY_NR_MAG 6 @@ -142,21 +153,7 @@ struct sysinfo_15_1_x { union topology_entry tle[0]; }; -static inline int stsi(void *sysinfo, int fc, int sel1, int sel2) -{ - register int r0 asm("0") = (fc << 28) | sel1; - register int r1 asm("1") = sel2; - - asm volatile( - " stsi 0(%2)\n" - "0: jz 2f\n" - "1: lhi %0,%3\n" - "2:\n" - EX_TABLE(0b, 1b) - : "+d" (r0) : "d" (r1), "a" (sysinfo), "K" (-ENOSYS) - : "cc", "memory"); - return r0; -} +int stsi(void *sysinfo, int fc, int sel1, int sel2); /* * Service level reporting interface. diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 9fde315..1d8fe2b 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -90,12 +90,10 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) static inline void __tlb_flush_mm_cond(struct mm_struct * mm) { - spin_lock(&mm->page_table_lock); if (mm->context.flush_mm) { __tlb_flush_mm(mm); mm->context.flush_mm = 0; } - spin_unlock(&mm->page_table_lock); } /* diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 0837de8..9ca3053 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -2,8 +2,8 @@ #define _ASM_S390_TOPOLOGY_H #include <linux/cpumask.h> -#include <asm/sysinfo.h> +struct sysinfo_15_1_x; struct cpu; #ifdef CONFIG_SCHED_BOOK @@ -51,24 +51,6 @@ static inline void topology_expect_change(void) { } #define POLARIZATION_VM (2) #define POLARIZATION_VH (3) -extern int cpu_polarization[]; - -static inline void cpu_set_polarization(int cpu, int val) -{ -#ifdef CONFIG_SCHED_BOOK - cpu_polarization[cpu] = val; -#endif -} - -static inline int cpu_read_polarization(int cpu) -{ -#ifdef CONFIG_SCHED_BOOK - return cpu_polarization[cpu]; -#else - return POLARIZATION_HRZ; -#endif -} - #ifdef CONFIG_SCHED_BOOK void s390_init_cpu_topology(void); #else diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index a8ab18b..34268df 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -76,9 +76,22 @@ static inline int __range_ok(unsigned long addr, unsigned long size) struct exception_table_entry { - unsigned long insn, fixup; + int insn, fixup; }; +static inline unsigned long extable_insn(const struct exception_table_entry *x) +{ + return (unsigned long)&x->insn + x->insn; +} + +static inline unsigned long extable_fixup(const struct exception_table_entry *x) +{ + return (unsigned long)&x->fixup + x->fixup; +} + +#define ARCH_HAS_SORT_EXTABLE +#define ARCH_HAS_SEARCH_EXTABLE + struct uaccess_ops { size_t (*copy_from_user)(size_t, const void __user *, void *); size_t (*copy_from_user_small)(size_t, const void __user *, void *); diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 6756e78..4e64b5c 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -277,7 +277,9 @@ #define __NR_setns 339 #define __NR_process_vm_readv 340 #define __NR_process_vm_writev 341 -#define NR_syscalls 342 +#define __NR_s390_runtime_instr 342 +#define __NR_kcmp 343 +#define NR_syscalls 344 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 9733b3f..4da52fe 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -23,10 +23,11 @@ CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w obj-y := bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \ processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \ debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \ - sysinfo.o jump_label.o lgr.o os_info.o + sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o obj-y += $(if $(CONFIG_64BIT),entry64.o,entry.o) obj-y += $(if $(CONFIG_64BIT),reipl64.o,reipl.o) +obj-y += $(if $(CONFIG_64BIT),relocate_kernel64.o,relocate_kernel.o) extra-y += head.o vmlinux.lds extra-y += $(if $(CONFIG_64BIT),head64.o,head31.o) @@ -48,12 +49,11 @@ obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o -# Kexec part -S390_KEXEC_OBJS := machine_kexec.o crash.o -S390_KEXEC_OBJS += $(if $(CONFIG_64BIT),relocate_kernel64.o,relocate_kernel.o) -obj-$(CONFIG_KEXEC) += $(S390_KEXEC_OBJS) +ifdef CONFIG_64BIT +obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o +obj-y += runtime_instr.o cache.o +endif # vdso obj-$(CONFIG_64BIT) += vdso64/ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 45ef1a7..fface87 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -157,6 +157,8 @@ int main(void) DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr)); DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data)); DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap)); + DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb)); + DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb)); DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); #endif /* CONFIG_32BIT */ return 0; diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c new file mode 100644 index 0000000..8df8d8a1 --- /dev/null +++ b/arch/s390/kernel/cache.c @@ -0,0 +1,385 @@ +/* + * Extract CPU cache information and expose them via sysfs. + * + * Copyright IBM Corp. 2012 + * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> + */ + +#include <linux/notifier.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <asm/facility.h> + +struct cache { + unsigned long size; + unsigned int line_size; + unsigned int associativity; + unsigned int nr_sets; + unsigned int level : 3; + unsigned int type : 2; + unsigned int private : 1; + struct list_head list; +}; + +struct cache_dir { + struct kobject *kobj; + struct cache_index_dir *index; +}; + +struct cache_index_dir { + struct kobject kobj; + int cpu; + struct cache *cache; + struct cache_index_dir *next; +}; + +enum { + CACHE_SCOPE_NOTEXISTS, + CACHE_SCOPE_PRIVATE, + CACHE_SCOPE_SHARED, + CACHE_SCOPE_RESERVED, +}; + +enum { + CACHE_TYPE_SEPARATE, + CACHE_TYPE_DATA, + CACHE_TYPE_INSTRUCTION, + CACHE_TYPE_UNIFIED, +}; + +enum { + EXTRACT_TOPOLOGY, + EXTRACT_LINE_SIZE, + EXTRACT_SIZE, + EXTRACT_ASSOCIATIVITY, +}; + +enum { + CACHE_TI_UNIFIED = 0, + CACHE_TI_INSTRUCTION = 0, + CACHE_TI_DATA, +}; + +struct cache_info { + unsigned char : 4; + unsigned char scope : 2; + unsigned char type : 2; +}; + +#define CACHE_MAX_LEVEL 8 + +union cache_topology { + struct cache_info ci[CACHE_MAX_LEVEL]; + unsigned long long raw; +}; + +static const char * const cache_type_string[] = { + "Data", + "Instruction", + "Unified", +}; + +static struct cache_dir *cache_dir_cpu[NR_CPUS]; +static LIST_HEAD(cache_list); + +void show_cacheinfo(struct seq_file *m) +{ + struct cache *cache; + int index = 0; + + list_for_each_entry(cache, &cache_list, list) { + seq_printf(m, "cache%-11d: ", index); + seq_printf(m, "level=%d ", cache->level); + seq_printf(m, "type=%s ", cache_type_string[cache->type]); + seq_printf(m, "scope=%s ", cache->private ? "Private" : "Shared"); + seq_printf(m, "size=%luK ", cache->size >> 10); + seq_printf(m, "line_size=%u ", cache->line_size); + seq_printf(m, "associativity=%d", cache->associativity); + seq_puts(m, "\n"); + index++; + } +} + +static inline unsigned long ecag(int ai, int li, int ti) +{ + unsigned long cmd, val; + + cmd = ai << 4 | li << 1 | ti; + asm volatile(".insn rsy,0xeb000000004c,%0,0,0(%1)" /* ecag */ + : "=d" (val) : "a" (cmd)); + return val; +} + +static int __init cache_add(int level, int private, int type) +{ + struct cache *cache; + int ti; + + cache = kzalloc(sizeof(*cache), GFP_KERNEL); + if (!cache) + return -ENOMEM; + ti = type == CACHE_TYPE_DATA ? CACHE_TI_DATA : CACHE_TI_UNIFIED; + cache->size = ecag(EXTRACT_SIZE, level, ti); + cache->line_size = ecag(EXTRACT_LINE_SIZE, level, ti); + cache->associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti); + cache->nr_sets = cache->size / cache->associativity; + cache->nr_sets /= cache->line_size; + cache->private = private; + cache->level = level + 1; + cache->type = type - 1; + list_add_tail(&cache->list, &cache_list); + return 0; +} + +static void __init cache_build_info(void) +{ + struct cache *cache, *next; + union cache_topology ct; + int level, private, rc; + + ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); + for (level = 0; level < CACHE_MAX_LEVEL; level++) { + switch (ct.ci[level].scope) { + case CACHE_SCOPE_NOTEXISTS: + case CACHE_SCOPE_RESERVED: + return; + case CACHE_SCOPE_SHARED: + private = 0; + break; + case CACHE_SCOPE_PRIVATE: + private = 1; + break; + } + if (ct.ci[level].type == CACHE_TYPE_SEPARATE) { + rc = cache_add(level, private, CACHE_TYPE_DATA); + rc |= cache_add(level, private, CACHE_TYPE_INSTRUCTION); + } else { + rc = cache_add(level, private, ct.ci[level].type); + } + if (rc) + goto error; + } + return; +error: + list_for_each_entry_safe(cache, next, &cache_list, list) { + list_del(&cache->list); + kfree(cache); + } +} + +static struct cache_dir *__cpuinit cache_create_cache_dir(int cpu) +{ + struct cache_dir *cache_dir; + struct kobject *kobj = NULL; + struct device *dev; + + dev = get_cpu_device(cpu); + if (!dev) + goto out; + kobj = kobject_create_and_add("cache", &dev->kobj); + if (!kobj) + goto out; + cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL); + if (!cache_dir) + goto out; + cache_dir->kobj = kobj; + cache_dir_cpu[cpu] = cache_dir; + return cache_dir; +out: + kobject_put(kobj); + return NULL; +} + +static struct cache_index_dir *kobj_to_cache_index_dir(struct kobject *kobj) +{ + return container_of(kobj, struct cache_index_dir, kobj); +} + +static void cache_index_release(struct kobject *kobj) +{ + struct cache_index_dir *index; + + index = kobj_to_cache_index_dir(kobj); + kfree(index); +} + +static ssize_t cache_index_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct kobj_attribute *kobj_attr; + + kobj_attr = container_of(attr, struct kobj_attribute, attr); + return kobj_attr->show(kobj, kobj_attr, buf); +} + +#define DEFINE_CACHE_ATTR(_name, _format, _value) \ +static ssize_t cache_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *buf) \ +{ \ + struct cache_index_dir *index; \ + \ + index = kobj_to_cache_index_dir(kobj); \ + return sprintf(buf, _format, _value); \ +} \ +static struct kobj_attribute cache_##_name##_attr = \ + __ATTR(_name, 0444, cache_##_name##_show, NULL); + +DEFINE_CACHE_ATTR(size, "%luK\n", index->cache->size >> 10); +DEFINE_CACHE_ATTR(coherency_line_size, "%u\n", index->cache->line_size); +DEFINE_CACHE_ATTR(number_of_sets, "%u\n", index->cache->nr_sets); +DEFINE_CACHE_ATTR(ways_of_associativity, "%u\n", index->cache->associativity); +DEFINE_CACHE_ATTR(type, "%s\n", cache_type_string[index->cache->type]); +DEFINE_CACHE_ATTR(level, "%d\n", index->cache->level); + +static ssize_t shared_cpu_map_func(struct kobject *kobj, int type, char *buf) +{ + struct cache_index_dir *index; + int len; + + index = kobj_to_cache_index_dir(kobj); + len = type ? + cpulist_scnprintf(buf, PAGE_SIZE - 2, cpumask_of(index->cpu)) : + cpumask_scnprintf(buf, PAGE_SIZE - 2, cpumask_of(index->cpu)); + len += sprintf(&buf[len], "\n"); + return len; +} + +static ssize_t shared_cpu_map_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return shared_cpu_map_func(kobj, 0, buf); +} +static struct kobj_attribute cache_shared_cpu_map_attr = + __ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL); + +static ssize_t shared_cpu_list_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return shared_cpu_map_func(kobj, 1, buf); +} +static struct kobj_attribute cache_shared_cpu_list_attr = + __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL); + +static struct attribute *cache_index_default_attrs[] = { + &cache_type_attr.attr, + &cache_size_attr.attr, + &cache_number_of_sets_attr.attr, + &cache_ways_of_associativity_attr.attr, + &cache_level_attr.attr, + &cache_coherency_line_size_attr.attr, + &cache_shared_cpu_map_attr.attr, + &cache_shared_cpu_list_attr.attr, + NULL, +}; + +static const struct sysfs_ops cache_index_ops = { + .show = cache_index_show, +}; + +static struct kobj_type cache_index_type = { + .sysfs_ops = &cache_index_ops, + .release = cache_index_release, + .default_attrs = cache_index_default_attrs, +}; + +static int __cpuinit cache_create_index_dir(struct cache_dir *cache_dir, + struct cache *cache, int index, + int cpu) +{ + struct cache_index_dir *index_dir; + int rc; + + index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL); + if (!index_dir) + return -ENOMEM; + index_dir->cache = cache; + index_dir->cpu = cpu; + rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type, + cache_dir->kobj, "index%d", index); + if (rc) + goto out; + index_dir->next = cache_dir->index; + cache_dir->index = index_dir; + return 0; +out: + kfree(index_dir); + return rc; +} + +static int __cpuinit cache_add_cpu(int cpu) +{ + struct cache_dir *cache_dir; + struct cache *cache; + int rc, index = 0; + + if (list_empty(&cache_list)) + return 0; + cache_dir = cache_create_cache_dir(cpu); + if (!cache_dir) + return -ENOMEM; + list_for_each_entry(cache, &cache_list, list) { + if (!cache->private) + break; + rc = cache_create_index_dir(cache_dir, cache, index, cpu); + if (rc) + return rc; + index++; + } + return 0; +} + +static void __cpuinit cache_remove_cpu(int cpu) +{ + struct cache_index_dir *index, *next; + struct cache_dir *cache_dir; + + cache_dir = cache_dir_cpu[cpu]; + if (!cache_dir) + return; + index = cache_dir->index; + while (index) { + next = index->next; + kobject_put(&index->kobj); + index = next; + } + kobject_put(cache_dir->kobj); + kfree(cache_dir); + cache_dir_cpu[cpu] = NULL; +} + +static int __cpuinit cache_hotplug(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + int rc = 0; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + rc = cache_add_cpu(cpu); + if (rc) + cache_remove_cpu(cpu); + break; + case CPU_DEAD: + cache_remove_cpu(cpu); + break; + } + return rc ? NOTIFY_BAD : NOTIFY_OK; +} + +static int __init cache_init(void) +{ + int cpu; + + if (!test_facility(34)) + return 0; + cache_build_info(); + for_each_online_cpu(cpu) + cache_add_cpu(cpu); + hotcpu_notifier(cache_hotplug, 0); + return 0; +} +device_initcall(cache_init); diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 2d82cfc..3afba80 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1646,3 +1646,16 @@ ENTRY(compat_sys_process_vm_writev_wrapper) llgf %r0,164(%r15) # unsigned long stg %r0,160(%r15) jg compat_sys_process_vm_writev + +ENTRY(sys_s390_runtime_instr_wrapper) + lgfr %r2,%r2 # int + lgfr %r3,%r3 # int + jg sys_s390_runtime_instr + +ENTRY(sys_kcmp_wrapper) + lgfr %r2,%r2 # pid_t + lgfr %r3,%r3 # pid_t + lgfr %r4,%r4 # int + llgfr %r5,%r5 # unsigned long + llgfr %r6,%r6 # unsigned long + jg sys_kcmp diff --git a/arch/s390/kernel/crash.c b/arch/s390/kernel/crash.c deleted file mode 100644 index 3819153..0000000 --- a/arch/s390/kernel/crash.c +++ /dev/null @@ -1,14 +0,0 @@ -/* - * Copyright IBM Corp. 2005 - * - * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> - * - */ - -#include <linux/threads.h> -#include <linux/kexec.h> -#include <linux/reboot.h> - -void machine_crash_shutdown(struct pt_regs *regs) -{ -} diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index cc1172b..fb8d878 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -13,8 +13,9 @@ #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/elf.h> -#include <asm/ipl.h> #include <asm/os_info.h> +#include <asm/elf.h> +#include <asm/ipl.h> #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 619c5d3..cc84a24 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -315,6 +315,11 @@ enum { LONG_INSN_POPCNT, LONG_INSN_RISBHG, LONG_INSN_RISBLG, + LONG_INSN_RINEXT, + LONG_INSN_RIEMIT, + LONG_INSN_TABORT, + LONG_INSN_TBEGIN, + LONG_INSN_TBEGINC, }; static char *long_insn_name[] = { @@ -329,7 +334,12 @@ static char *long_insn_name[] = { [LONG_INSN_LLGHRL] = "llghrl", [LONG_INSN_POPCNT] = "popcnt", [LONG_INSN_RISBHG] = "risbhg", - [LONG_INSN_RISBLG] = "risblk", + [LONG_INSN_RISBLG] = "risblg", + [LONG_INSN_RINEXT] = "rinext", + [LONG_INSN_RIEMIT] = "riemit", + [LONG_INSN_TABORT] = "tabort", + [LONG_INSN_TBEGIN] = "tbegin", + [LONG_INSN_TBEGINC] = "tbeginc", }; static struct insn opcode[] = { @@ -582,6 +592,17 @@ static struct insn opcode_a7[] = { { "", 0, INSTR_INVALID } }; +static struct insn opcode_aa[] = { +#ifdef CONFIG_64BIT + { { 0, LONG_INSN_RINEXT }, 0x00, INSTR_RI_RI }, + { "rion", 0x01, INSTR_RI_RI }, + { "tric", 0x02, INSTR_RI_RI }, + { "rioff", 0x03, INSTR_RI_RI }, + { { 0, LONG_INSN_RIEMIT }, 0x04, INSTR_RI_RI }, +#endif + { "", 0, INSTR_INVALID } +}; + static struct insn opcode_b2[] = { #ifdef CONFIG_64BIT { "sske", 0x2b, INSTR_RRF_M0RR }, @@ -594,6 +615,9 @@ static struct insn opcode_b2[] = { { "lpswe", 0xb2, INSTR_S_RD }, { "srnmt", 0xb9, INSTR_S_RD }, { "lfas", 0xbd, INSTR_S_RD }, + { "etndg", 0xec, INSTR_RRE_R0 }, + { { 0, LONG_INSN_TABORT }, 0xfc, INSTR_S_RD }, + { "tend", 0xf8, INSTR_S_RD }, #endif { "stidp", 0x02, INSTR_S_RD }, { "sck", 0x04, INSTR_S_RD }, @@ -1150,6 +1174,7 @@ static struct insn opcode_e3[] = { { "stfh", 0xcb, INSTR_RXY_RRRD }, { "chf", 0xcd, INSTR_RXY_RRRD }, { "clhf", 0xcf, INSTR_RXY_RRRD }, + { "ntstg", 0x25, INSTR_RXY_RRRD }, #endif { "lrv", 0x1e, INSTR_RXY_RRRD }, { "lrvh", 0x1f, INSTR_RXY_RRRD }, @@ -1173,6 +1198,8 @@ static struct insn opcode_e5[] = { { "mvhhi", 0x44, INSTR_SIL_RDI }, { "mvhi", 0x4c, INSTR_SIL_RDI }, { "mvghi", 0x48, INSTR_SIL_RDI }, + { { 0, LONG_INSN_TBEGIN }, 0x60, INSTR_SIL_RDU }, + { { 0, LONG_INSN_TBEGINC }, 0x61, INSTR_SIL_RDU }, #endif { "lasp", 0x00, INSTR_SSE_RDRD }, { "tprot", 0x01, INSTR_SSE_RDRD }, @@ -1210,6 +1237,9 @@ static struct insn opcode_eb[] = { { "cliy", 0x55, INSTR_SIY_URD }, { "oiy", 0x56, INSTR_SIY_URD }, { "xiy", 0x57, INSTR_SIY_URD }, + { "lric", 0x60, INSTR_RSY_RDRM }, + { "stric", 0x61, INSTR_RSY_RDRM }, + { "mric", 0x62, INSTR_RSY_RDRM }, { "icmh", 0x80, INSTR_RSE_RURD }, { "icmh", 0x80, INSTR_RSY_RURD }, { "icmy", 0x81, INSTR_RSY_RURD }, @@ -1408,6 +1438,9 @@ static struct insn *find_insn(unsigned char *code) case 0xa7: table = opcode_a7; break; + case 0xaa: + table = opcode_aa; + break; case 0xb2: table = opcode_b2; break; @@ -1601,3 +1634,26 @@ void show_code(struct pt_regs *regs) } printk("\n"); } + +void print_fn_code(unsigned char *code, unsigned long len) +{ + char buffer[64], *ptr; + int opsize, i; + + while (len) { + ptr = buffer; + opsize = insn_length(*code); + ptr += sprintf(ptr, "%p: ", code); + for (i = 0; i < opsize; i++) + ptr += sprintf(ptr, "%02x", code[i]); + *ptr++ = '\t'; + if (i < 4) + *ptr++ = '\t'; + ptr += print_insn(ptr, code, (unsigned long) code); + *ptr++ = '\n'; + *ptr++ = 0; + printk(buffer); + code += opsize; + len -= opsize; + } +} diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 83c3271..7f47176 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -215,36 +215,54 @@ static noinline __init void init_kernel_storage_key(void) PAGE_DEFAULT_KEY, 0); } -static __initdata struct sysinfo_3_2_2 vmms __aligned(PAGE_SIZE); +static __initdata char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE); static noinline __init void detect_machine_type(void) { + struct sysinfo_3_2_2 *vmms = (struct sysinfo_3_2_2 *)&sysinfo_page; + /* Check current-configuration-level */ - if ((stsi(NULL, 0, 0, 0) >> 28) <= 2) { + if (stsi(NULL, 0, 0, 0) <= 2) { S390_lowcore.machine_flags |= MACHINE_FLAG_LPAR; return; } /* Get virtual-machine cpu information. */ - if (stsi(&vmms, 3, 2, 2) == -ENOSYS || !vmms.count) + if (stsi(vmms, 3, 2, 2) || !vmms->count) return; /* Running under KVM? If not we assume z/VM */ - if (!memcmp(vmms.vm[0].cpi, "\xd2\xe5\xd4", 3)) + if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3)) S390_lowcore.machine_flags |= MACHINE_FLAG_KVM; else S390_lowcore.machine_flags |= MACHINE_FLAG_VM; } +static __init void setup_topology(void) +{ +#ifdef CONFIG_64BIT + int max_mnest; + + if (!test_facility(11)) + return; + S390_lowcore.machine_flags |= MACHINE_FLAG_TOPOLOGY; + for (max_mnest = 6; max_mnest > 1; max_mnest--) { + if (stsi(&sysinfo_page, 15, 1, max_mnest) == 0) + break; + } + topology_max_mnest = max_mnest; +#endif +} + static void early_pgm_check_handler(void) { - unsigned long addr; const struct exception_table_entry *fixup; + unsigned long addr; addr = S390_lowcore.program_old_psw.addr; fixup = search_exception_tables(addr & PSW_ADDR_INSN); if (!fixup) disabled_wait(0); - S390_lowcore.program_old_psw.addr = fixup->fixup | PSW_ADDR_AMODE; + S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE; } static noinline __init void setup_lowcore_early(void) @@ -267,12 +285,10 @@ static noinline __init void setup_facility_list(void) static noinline __init void setup_hpage(void) { -#ifndef CONFIG_DEBUG_PAGEALLOC if (!test_facility(2) || !test_facility(8)) return; S390_lowcore.machine_flags |= MACHINE_FLAG_HPAGE; __ctl_set_bit(0, 23); -#endif } static __init void detect_mvpg(void) @@ -366,12 +382,12 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; if (test_facility(8)) S390_lowcore.machine_flags |= MACHINE_FLAG_PFMF; - if (test_facility(11)) - S390_lowcore.machine_flags |= MACHINE_FLAG_TOPOLOGY; if (test_facility(27)) S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS; if (test_facility(40)) S390_lowcore.machine_flags |= MACHINE_FLAG_SPP; + if (test_facility(50) && test_facility(73)) + S390_lowcore.machine_flags |= MACHINE_FLAG_TE; #endif } @@ -441,7 +457,6 @@ static void __init setup_boot_command_line(void) append_to_cmdline(append_ipl_scpdata); } - /* * Save ipl parameters, clear bss memory, initialize storage keys * and create a kernel NSS at startup if the SAVESYS= parm is defined @@ -468,6 +483,7 @@ void __init startup_init(void) detect_diag44(); detect_machine_facilities(); setup_hpage(); + setup_topology(); sclp_facilities_detect(); detect_memory_layout(memory_chunk); #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 349b7ee..7549985 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <asm/processor.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ptrace.h> @@ -412,6 +413,11 @@ ENTRY(pgm_check_handler) 1: UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER LAST_BREAK %r14 lg %r15,__LC_KERNEL_STACK + lg %r14,__TI_task(%r12) + lghi %r13,__LC_PGM_TDB + tm __LC_PGM_ILC+2,0x02 # check for transaction abort + jz 2f + mvc __THREAD_trap_tdb(256,%r14),0(%r13) 2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) @@ -422,13 +428,12 @@ ENTRY(pgm_check_handler) stg %r10,__PT_ARGS(%r11) tm __LC_PGM_ILC+3,0x80 # check for per exception jz 0f - lg %r1,__TI_task(%r12) tmhh %r8,0x0001 # kernel per event ? jz pgm_kprobe oi __TI_flags+7(%r12),_TIF_PER_TRAP - mvc __THREAD_per_address(8,%r1),__LC_PER_ADDRESS - mvc __THREAD_per_cause(2,%r1),__LC_PER_CAUSE - mvc __THREAD_per_paid(1,%r1),__LC_PER_PAID + mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS + mvc __THREAD_per_cause(2,%r14),__LC_PER_CAUSE + mvc __THREAD_per_paid(1,%r14),__LC_PER_PAID 0: REENABLE_IRQS xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) larl %r1,pgm_check_table @@ -1004,9 +1009,7 @@ sie_fault: .Lhost_id: .quad 0 - .section __ex_table,"a" - .quad sie_loop,sie_fault - .previous + EX_TABLE(sie_loop,sie_fault) #endif .section .rodata, "a" diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index dd7630d..6cdc55b 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -30,33 +30,35 @@ struct irq_class { }; static const struct irq_class intrclass_names[] = { - {.name = "EXT" }, - {.name = "I/O" }, - {.name = "CLK", .desc = "[EXT] Clock Comparator" }, - {.name = "EXC", .desc = "[EXT] External Call" }, - {.name = "EMS", .desc = "[EXT] Emergency Signal" }, - {.name = "TMR", .desc = "[EXT] CPU Timer" }, - {.name = "TAL", .desc = "[EXT] Timing Alert" }, - {.name = "PFL", .desc = "[EXT] Pseudo Page Fault" }, - {.name = "DSD", .desc = "[EXT] DASD Diag" }, - {.name = "VRT", .desc = "[EXT] Virtio" }, - {.name = "SCP", .desc = "[EXT] Service Call" }, - {.name = "IUC", .desc = "[EXT] IUCV" }, - {.name = "CMS", .desc = "[EXT] CPU-Measurement: Sampling" }, - {.name = "CMC", .desc = "[EXT] CPU-Measurement: Counter" }, - {.name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt" }, - {.name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt" }, - {.name = "DAS", .desc = "[I/O] DASD" }, - {.name = "C15", .desc = "[I/O] 3215" }, - {.name = "C70", .desc = "[I/O] 3270" }, - {.name = "TAP", .desc = "[I/O] Tape" }, - {.name = "VMR", .desc = "[I/O] Unit Record Devices" }, - {.name = "LCS", .desc = "[I/O] LCS" }, - {.name = "CLW", .desc = "[I/O] CLAW" }, - {.name = "CTC", .desc = "[I/O] CTC" }, - {.name = "APB", .desc = "[I/O] AP Bus" }, - {.name = "CSC", .desc = "[I/O] CHSC Subchannel" }, - {.name = "NMI", .desc = "[NMI] Machine Check" }, + [EXTERNAL_INTERRUPT] = {.name = "EXT"}, + [IO_INTERRUPT] = {.name = "I/O"}, + [EXTINT_CLK] = {.name = "CLK", .desc = "[EXT] Clock Comparator"}, + [EXTINT_EXC] = {.name = "EXC", .desc = "[EXT] External Call"}, + [EXTINT_EMS] = {.name = "EMS", .desc = "[EXT] Emergency Signal"}, + [EXTINT_TMR] = {.name = "TMR", .desc = "[EXT] CPU Timer"}, + [EXTINT_TLA] = {.name = "TAL", .desc = "[EXT] Timing Alert"}, + [EXTINT_PFL] = {.name = "PFL", .desc = "[EXT] Pseudo Page Fault"}, + [EXTINT_DSD] = {.name = "DSD", .desc = "[EXT] DASD Diag"}, + [EXTINT_VRT] = {.name = "VRT", .desc = "[EXT] Virtio"}, + [EXTINT_SCP] = {.name = "SCP", .desc = "[EXT] Service Call"}, + [EXTINT_IUC] = {.name = "IUC", .desc = "[EXT] IUCV"}, + [EXTINT_CMS] = {.name = "CMS", .desc = "[EXT] CPU-Measurement: Sampling"}, + [EXTINT_CMC] = {.name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"}, + [EXTINT_CMR] = {.name = "CMR", .desc = "[EXT] CPU-Measurement: RI"}, + [IOINT_CIO] = {.name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"}, + [IOINT_QAI] = {.name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"}, + [IOINT_DAS] = {.name = "DAS", .desc = "[I/O] DASD"}, + [IOINT_C15] = {.name = "C15", .desc = "[I/O] 3215"}, + [IOINT_C70] = {.name = "C70", .desc = "[I/O] 3270"}, + [IOINT_TAP] = {.name = "TAP", .desc = "[I/O] Tape"}, + [IOINT_VMR] = {.name = "VMR", .desc = "[I/O] Unit Record Devices"}, + [IOINT_LCS] = {.name = "LCS", .desc = "[I/O] LCS"}, + [IOINT_CLW] = {.name = "CLW", .desc = "[I/O] CLAW"}, + [IOINT_CTC] = {.name = "CTC", .desc = "[I/O] CTC"}, + [IOINT_APB] = {.name = "APB", .desc = "[I/O] AP Bus"}, + [IOINT_ADM] = {.name = "ADM", .desc = "[I/O] EADM Subchannel"}, + [IOINT_CSC] = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"}, + [NMI_NMI] = {.name = "NMI", .desc = "[NMI] Machine Check"}, }; /* diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 8aa634f..d1c7214 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -547,7 +547,7 @@ static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) */ entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); if (entry) { - regs->psw.addr = entry->fixup | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE; return 1; } diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c index eca94e7..6ea6d69 100644 --- a/arch/s390/kernel/lgr.c +++ b/arch/s390/kernel/lgr.c @@ -51,16 +51,6 @@ static struct lgr_info lgr_info_cur; static struct debug_info *lgr_dbf; /* - * Return number of valid stsi levels - */ -static inline int stsi_0(void) -{ - int rc = stsi(NULL, 0, 0, 0); - - return rc == -ENOSYS ? rc : (((unsigned int) rc) >> 28); -} - -/* * Copy buffer and then convert it to ASCII */ static void cpascii(char *dst, char *src, int size) @@ -76,7 +66,7 @@ static void lgr_stsi_1_1_1(struct lgr_info *lgr_info) { struct sysinfo_1_1_1 *si = (void *) lgr_page; - if (stsi(si, 1, 1, 1) == -ENOSYS) + if (stsi(si, 1, 1, 1)) return; cpascii(lgr_info->manufacturer, si->manufacturer, sizeof(si->manufacturer)); @@ -93,7 +83,7 @@ static void lgr_stsi_2_2_2(struct lgr_info *lgr_info) { struct sysinfo_2_2_2 *si = (void *) lgr_page; - if (stsi(si, 2, 2, 2) == -ENOSYS) + if (stsi(si, 2, 2, 2)) return; cpascii(lgr_info->name, si->name, sizeof(si->name)); memcpy(&lgr_info->lpar_number, &si->lpar_number, @@ -108,7 +98,7 @@ static void lgr_stsi_3_2_2(struct lgr_info *lgr_info) struct sysinfo_3_2_2 *si = (void *) lgr_page; int i; - if (stsi(si, 3, 2, 2) == -ENOSYS) + if (stsi(si, 3, 2, 2)) return; for (i = 0; i < min_t(u8, si->count, VM_LEVEL_MAX); i++) { cpascii(lgr_info->vm[i].name, si->vm[i].name, @@ -124,16 +114,17 @@ static void lgr_stsi_3_2_2(struct lgr_info *lgr_info) */ static void lgr_info_get(struct lgr_info *lgr_info) { + int level; + memset(lgr_info, 0, sizeof(*lgr_info)); stfle(lgr_info->stfle_fac_list, ARRAY_SIZE(lgr_info->stfle_fac_list)); - lgr_info->level = stsi_0(); - if (lgr_info->level == -ENOSYS) - return; - if (lgr_info->level >= 1) + level = stsi(NULL, 0, 0, 0); + lgr_info->level = level; + if (level >= 1) lgr_stsi_1_1_1(lgr_info); - if (lgr_info->level >= 2) + if (level >= 2) lgr_stsi_2_2_2(lgr_info); - if (lgr_info->level >= 3) + if (level >= 3) lgr_stsi_3_2_2(lgr_info); } diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 493304b..b3de277 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -21,6 +21,7 @@ #include <asm/reset.h> #include <asm/ipl.h> #include <asm/diag.h> +#include <asm/elf.h> #include <asm/asm-offsets.h> #include <asm/os_info.h> @@ -31,8 +32,6 @@ extern const unsigned long long relocate_kernel_len; #ifdef CONFIG_CRASH_DUMP -void *fill_cpu_elf_notes(void *ptr, struct save_area *sa); - /* * Create ELF notes for one CPU */ @@ -159,7 +158,7 @@ int machine_kexec_prepare(struct kimage *image) /* Can't replace kernel image since it is read-only. */ if (ipl_flags & IPL_NSS_VALID) - return -ENOSYS; + return -EOPNOTSUPP; if (image->type == KEXEC_TYPE_CRASH) return machine_kexec_prepare_kdump(); @@ -191,6 +190,10 @@ void machine_shutdown(void) { } +void machine_crash_shutdown(struct pt_regs *regs) +{ +} + /* * Do normal kexec */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 7331753..5024be2 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -26,10 +26,12 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/vtimer.h> +#include <asm/exec.h> #include <asm/irq.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/switch_to.h> +#include <asm/runtime_instr.h> #include "entry.h" asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); @@ -132,6 +134,7 @@ EXPORT_SYMBOL(kernel_thread); */ void exit_thread(void) { + exit_thread_runtime_instr(); } void flush_thread(void) @@ -170,6 +173,11 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, /* Save access registers to new thread structure. */ save_access_regs(&p->thread.acrs[0]); + /* Don't copy runtime instrumentation info */ + p->thread.ri_cb = NULL; + p->thread.ri_signum = 0; + frame->childregs.psw.mask &= ~PSW_MASK_RI; + #ifndef CONFIG_64BIT /* * save fprs to current->thread.fp_regs to merge them with diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 572d4c9..753c41d 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -39,9 +39,9 @@ void __cpuinit cpu_init(void) */ static int show_cpuinfo(struct seq_file *m, void *v) { - static const char *hwcap_str[10] = { + static const char *hwcap_str[] = { "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", - "edat", "etf3eh", "highgprs" + "edat", "etf3eh", "highgprs", "te" }; unsigned long n = (unsigned long) v - 1; int i; @@ -54,10 +54,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) num_online_cpus(), loops_per_jiffy/(500000/HZ), (loops_per_jiffy/(5000/HZ))%100); seq_puts(m, "features\t: "); - for (i = 0; i < 10; i++) + for (i = 0; i < ARRAY_SIZE(hwcap_str); i++) if (hwcap_str[i] && (elf_hwcap & (1UL << i))) seq_printf(m, "%s ", hwcap_str[i]); seq_puts(m, "\n"); + show_cacheinfo(m); } get_online_cpus(); if (cpu_online(n)) { diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index e4be113..a314c57 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -42,6 +42,7 @@ enum s390_regset { REGSET_GENERAL, REGSET_FP, REGSET_LAST_BREAK, + REGSET_TDB, REGSET_SYSTEM_CALL, REGSET_GENERAL_EXTENDED, }; @@ -52,6 +53,22 @@ void update_per_regs(struct task_struct *task) struct thread_struct *thread = &task->thread; struct per_regs old, new; +#ifdef CONFIG_64BIT + /* Take care of the enable/disable of transactional execution. */ + if (MACHINE_HAS_TE) { + unsigned long cr0, cr0_new; + + __ctl_store(cr0, 0, 0); + /* set or clear transaction execution bits 8 and 9. */ + if (task->thread.per_flags & PER_FLAG_NO_TE) + cr0_new = cr0 & ~(3UL << 54); + else + cr0_new = cr0 | (3UL << 54); + /* Only load control register 0 if necessary. */ + if (cr0 != cr0_new) + __ctl_load(cr0_new, 0, 0); + } +#endif /* Copy user specified PER registers */ new.control = thread->per_user.control; new.start = thread->per_user.start; @@ -60,6 +77,10 @@ void update_per_regs(struct task_struct *task) /* merge TIF_SINGLE_STEP into user specified PER registers. */ if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) { new.control |= PER_EVENT_IFETCH; +#ifdef CONFIG_64BIT + new.control |= PER_CONTROL_SUSPENSION; + new.control |= PER_EVENT_TRANSACTION_END; +#endif new.start = 0; new.end = PSW_ADDR_INSN; } @@ -100,6 +121,7 @@ void ptrace_disable(struct task_struct *task) memset(&task->thread.per_event, 0, sizeof(task->thread.per_event)); clear_tsk_thread_flag(task, TIF_SINGLE_STEP); clear_tsk_thread_flag(task, TIF_PER_TRAP); + task->thread.per_flags = 0; } #ifndef CONFIG_64BIT @@ -416,6 +438,16 @@ long arch_ptrace(struct task_struct *child, long request, put_user(task_thread_info(child)->last_break, (unsigned long __user *) data); return 0; + case PTRACE_ENABLE_TE: + if (!MACHINE_HAS_TE) + return -EIO; + child->thread.per_flags &= ~PER_FLAG_NO_TE; + return 0; + case PTRACE_DISABLE_TE: + if (!MACHINE_HAS_TE) + return -EIO; + child->thread.per_flags |= PER_FLAG_NO_TE; + return 0; default: /* Removing high order bit from addr (only for 31 bit). */ addr &= PSW_ADDR_INSN; @@ -903,6 +935,28 @@ static int s390_last_break_set(struct task_struct *target, return 0; } +static int s390_tdb_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + unsigned char *data; + + if (!(regs->int_code & 0x200)) + return -ENODATA; + data = target->thread.trap_tdb; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, data, 0, 256); +} + +static int s390_tdb_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + return 0; +} + #endif static int s390_system_call_get(struct task_struct *target, @@ -951,6 +1005,14 @@ static const struct user_regset s390_regsets[] = { .get = s390_last_break_get, .set = s390_last_break_set, }, + [REGSET_TDB] = { + .core_note_type = NT_S390_TDB, + .n = 1, + .size = 256, + .align = 1, + .get = s390_tdb_get, + .set = s390_tdb_set, + }, #endif [REGSET_SYSTEM_CALL] = { .core_note_type = NT_S390_SYSTEM_CALL, @@ -1148,6 +1210,14 @@ static const struct user_regset s390_compat_regsets[] = { .get = s390_compat_last_break_get, .set = s390_compat_last_break_set, }, + [REGSET_TDB] = { + .core_note_type = NT_S390_TDB, + .n = 1, + .size = 256, + .align = 1, + .get = s390_tdb_get, + .set = s390_tdb_set, + }, [REGSET_SYSTEM_CALL] = { .core_note_type = NT_S390_SYSTEM_CALL, .n = 1, diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c new file mode 100644 index 0000000..61066f6 --- /dev/null +++ b/arch/s390/kernel/runtime_instr.c @@ -0,0 +1,150 @@ +/* + * Copyright IBM Corp. 2012 + * Author(s): Jan Glauber <jang@linux.vnet.ibm.com> + */ + +#include <linux/kernel.h> +#include <linux/syscalls.h> +#include <linux/signal.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/kernel_stat.h> +#include <asm/runtime_instr.h> +#include <asm/cpu_mf.h> +#include <asm/irq.h> + +/* empty control block to disable RI by loading it */ +struct runtime_instr_cb runtime_instr_empty_cb; + +static int runtime_instr_avail(void) +{ + return test_facility(64); +} + +static void disable_runtime_instr(void) +{ + struct pt_regs *regs = task_pt_regs(current); + + load_runtime_instr_cb(&runtime_instr_empty_cb); + + /* + * Make sure the RI bit is deleted from the PSW. If the user did not + * switch off RI before the system call the process will get a + * specification exception otherwise. + */ + regs->psw.mask &= ~PSW_MASK_RI; +} + +static void init_runtime_instr_cb(struct runtime_instr_cb *cb) +{ + cb->buf_limit = 0xfff; + if (s390_user_mode == HOME_SPACE_MODE) + cb->home_space = 1; + cb->int_requested = 1; + cb->pstate = 1; + cb->pstate_set_buf = 1; + cb->pstate_sample = 1; + cb->pstate_collect = 1; + cb->key = PAGE_DEFAULT_KEY; + cb->valid = 1; +} + +void exit_thread_runtime_instr(void) +{ + struct task_struct *task = current; + + if (!task->thread.ri_cb) + return; + disable_runtime_instr(); + kfree(task->thread.ri_cb); + task->thread.ri_signum = 0; + task->thread.ri_cb = NULL; +} + +static void runtime_instr_int_handler(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + struct siginfo info; + + if (!(param32 & CPU_MF_INT_RI_MASK)) + return; + + kstat_cpu(smp_processor_id()).irqs[EXTINT_CMR]++; + + if (!current->thread.ri_cb) + return; + if (current->thread.ri_signum < SIGRTMIN || + current->thread.ri_signum > SIGRTMAX) { + WARN_ON_ONCE(1); + return; + } + + memset(&info, 0, sizeof(info)); + info.si_signo = current->thread.ri_signum; + info.si_code = SI_QUEUE; + if (param32 & CPU_MF_INT_RI_BUF_FULL) + info.si_int = ENOBUFS; + else if (param32 & CPU_MF_INT_RI_HALTED) + info.si_int = ECANCELED; + else + return; /* unknown reason */ + + send_sig_info(current->thread.ri_signum, &info, current); +} + +SYSCALL_DEFINE2(s390_runtime_instr, int, command, int, signum) +{ + struct runtime_instr_cb *cb; + + if (!runtime_instr_avail()) + return -EOPNOTSUPP; + + if (command == S390_RUNTIME_INSTR_STOP) { + preempt_disable(); + exit_thread_runtime_instr(); + preempt_enable(); + return 0; + } + + if (command != S390_RUNTIME_INSTR_START || + (signum < SIGRTMIN || signum > SIGRTMAX)) + return -EINVAL; + + if (!current->thread.ri_cb) { + cb = kzalloc(sizeof(*cb), GFP_KERNEL); + if (!cb) + return -ENOMEM; + } else { + cb = current->thread.ri_cb; + memset(cb, 0, sizeof(*cb)); + } + + init_runtime_instr_cb(cb); + current->thread.ri_signum = signum; + + /* now load the control block to make it available */ + preempt_disable(); + current->thread.ri_cb = cb; + load_runtime_instr_cb(cb); + preempt_enable(); + return 0; +} + +static int __init runtime_instr_init(void) +{ + int rc; + + if (!runtime_instr_avail()) + return 0; + + measurement_alert_subclass_register(); + rc = register_external_interrupt(0x1407, runtime_instr_int_handler); + if (rc) + measurement_alert_subclass_unregister(); + else + pr_info("Runtime instrumentation facility initialized\n"); + return rc; +} +device_initcall(runtime_instr_init); diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 57b5366..9bdbcef 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -8,3 +8,5 @@ EXPORT_SYMBOL(_mcount); #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) EXPORT_SYMBOL(sie64a); #endif +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memset); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f86c81e..afa9fdb 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -302,10 +302,10 @@ static int __init parse_vmalloc(char *arg) } early_param("vmalloc", parse_vmalloc); -unsigned int addressing_mode = HOME_SPACE_MODE; -EXPORT_SYMBOL_GPL(addressing_mode); +unsigned int s390_user_mode = PRIMARY_SPACE_MODE; +EXPORT_SYMBOL_GPL(s390_user_mode); -static int set_amode_primary(void) +static void __init set_user_mode_primary(void) { psw_kernel_bits = (psw_kernel_bits & ~PSW_MASK_ASC) | PSW_ASC_HOME; psw_user_bits = (psw_user_bits & ~PSW_MASK_ASC) | PSW_ASC_PRIMARY; @@ -313,48 +313,30 @@ static int set_amode_primary(void) psw32_user_bits = (psw32_user_bits & ~PSW32_MASK_ASC) | PSW32_ASC_PRIMARY; #endif - - if (MACHINE_HAS_MVCOS) { - memcpy(&uaccess, &uaccess_mvcos_switch, sizeof(uaccess)); - return 1; - } else { - memcpy(&uaccess, &uaccess_pt, sizeof(uaccess)); - return 0; - } -} - -/* - * Switch kernel/user addressing modes? - */ -static int __init early_parse_switch_amode(char *p) -{ - addressing_mode = PRIMARY_SPACE_MODE; - return 0; + uaccess = MACHINE_HAS_MVCOS ? uaccess_mvcos_switch : uaccess_pt; } -early_param("switch_amode", early_parse_switch_amode); static int __init early_parse_user_mode(char *p) { if (p && strcmp(p, "primary") == 0) - addressing_mode = PRIMARY_SPACE_MODE; + s390_user_mode = PRIMARY_SPACE_MODE; else if (!p || strcmp(p, "home") == 0) - addressing_mode = HOME_SPACE_MODE; + s390_user_mode = HOME_SPACE_MODE; else return 1; return 0; } early_param("user_mode", early_parse_user_mode); -static void setup_addressing_mode(void) +static void __init setup_addressing_mode(void) { - if (addressing_mode == PRIMARY_SPACE_MODE) { - if (set_amode_primary()) - pr_info("Address spaces switched, " - "mvcos available\n"); - else - pr_info("Address spaces switched, " - "mvcos not available\n"); - } + if (s390_user_mode != PRIMARY_SPACE_MODE) + return; + set_user_mode_primary(); + if (MACHINE_HAS_MVCOS) + pr_info("Address spaces switched, mvcos available\n"); + else + pr_info("Address spaces switched, mvcos not available\n"); } void *restart_stack __attribute__((__section__(".data"))); @@ -602,9 +584,7 @@ static void __init setup_memory_end(void) static void __init setup_vmcoreinfo(void) { -#ifdef CONFIG_KEXEC mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); -#endif } #ifdef CONFIG_CRASH_DUMP @@ -974,12 +954,20 @@ static void __init setup_hwcaps(void) if (MACHINE_HAS_HPAGE) elf_hwcap |= HWCAP_S390_HPAGE; +#if defined(CONFIG_64BIT) /* * 64-bit register support for 31-bit processes * HWCAP_S390_HIGH_GPRS is bit 9. */ elf_hwcap |= HWCAP_S390_HIGH_GPRS; + /* + * Transactional execution support HWCAP_S390_TE is bit 10. + */ + if (test_facility(50) && test_facility(73)) + elf_hwcap |= HWCAP_S390_TE; +#endif + get_cpu_id(&cpu_id); switch (cpu_id.machine) { case 0x9672: diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 720fda1..ea431e5 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -66,7 +66,7 @@ struct pcpu { unsigned long panic_stack; /* panic stack for the cpu */ unsigned long ec_mask; /* bit mask for ec_xxx functions */ int state; /* physical cpu state */ - u32 status; /* last status received via sigp */ + int polarization; /* physical polarization */ u16 address; /* physical cpu address */ }; @@ -74,6 +74,10 @@ static u8 boot_cpu_type; static u16 boot_cpu_address; static struct pcpu pcpu_devices[NR_CPUS]; +/* + * The smp_cpu_state_mutex must be held when changing the state or polarization + * member of a pcpu data structure within the pcpu_devices arreay. + */ DEFINE_MUTEX(smp_cpu_state_mutex); /* @@ -99,7 +103,7 @@ static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status) int cc; while (1) { - cc = __pcpu_sigp(addr, order, parm, status); + cc = __pcpu_sigp(addr, order, parm, NULL); if (cc != SIGP_CC_BUSY) return cc; cpu_relax(); @@ -111,7 +115,7 @@ static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) int cc, retry; for (retry = 0; ; retry++) { - cc = __pcpu_sigp(pcpu->address, order, parm, &pcpu->status); + cc = __pcpu_sigp(pcpu->address, order, parm, NULL); if (cc != SIGP_CC_BUSY) break; if (retry >= 3) @@ -122,16 +126,18 @@ static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) static inline int pcpu_stopped(struct pcpu *pcpu) { + u32 uninitialized_var(status); + if (__pcpu_sigp(pcpu->address, SIGP_SENSE, - 0, &pcpu->status) != SIGP_CC_STATUS_STORED) + 0, &status) != SIGP_CC_STATUS_STORED) return 0; - return !!(pcpu->status & (SIGP_STATUS_CHECK_STOP|SIGP_STATUS_STOPPED)); + return !!(status & (SIGP_STATUS_CHECK_STOP|SIGP_STATUS_STOPPED)); } static inline int pcpu_running(struct pcpu *pcpu) { if (__pcpu_sigp(pcpu->address, SIGP_SENSE_RUNNING, - 0, &pcpu->status) != SIGP_CC_STATUS_STORED) + 0, NULL) != SIGP_CC_STATUS_STORED) return 1; /* Status stored condition code is equivalent to cpu not running. */ return 0; @@ -586,6 +592,16 @@ static inline void smp_get_save_area(int cpu, u16 address) { } #endif /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */ +void smp_cpu_set_polarization(int cpu, int val) +{ + pcpu_devices[cpu].polarization = val; +} + +int smp_cpu_get_polarization(int cpu) +{ + return pcpu_devices[cpu].polarization; +} + static struct sclp_cpu_info *smp_get_cpu_info(void) { static int use_sigp_detection; @@ -628,7 +644,7 @@ static int __devinit __smp_rescan_cpus(struct sclp_cpu_info *info, pcpu->address = info->cpu[i].address; pcpu->state = (cpu >= info->configured) ? CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; - cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); set_cpu_present(cpu, true); if (sysfs_add && smp_add_present_cpu(cpu) != 0) set_cpu_present(cpu, false); @@ -796,7 +812,7 @@ void __init smp_prepare_boot_cpu(void) pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE; pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE; S390_lowcore.percpu_offset = __per_cpu_offset[0]; - cpu_set_polarization(0, POLARIZATION_UNKNOWN); + smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN); set_cpu_present(0, true); set_cpu_online(0, true); } @@ -862,7 +878,7 @@ static ssize_t cpu_configure_store(struct device *dev, if (rc) break; pcpu->state = CPU_STATE_STANDBY; - cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); topology_expect_change(); break; case 1: @@ -872,7 +888,7 @@ static ssize_t cpu_configure_store(struct device *dev, if (rc) break; pcpu->state = CPU_STATE_CONFIGURED; - cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); topology_expect_change(); break; default: @@ -959,23 +975,17 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self, struct device *s = &c->dev; int err = 0; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: err = sysfs_create_group(&s->kobj, &cpu_online_attr_group); break; case CPU_DEAD: - case CPU_DEAD_FROZEN: sysfs_remove_group(&s->kobj, &cpu_online_attr_group); break; } return notifier_from_errno(err); } -static struct notifier_block __cpuinitdata smp_cpu_nb = { - .notifier_call = smp_cpu_notify, -}; - static int __devinit smp_add_present_cpu(int cpu) { struct cpu *c = &pcpu_devices[cpu].cpu; @@ -1050,7 +1060,7 @@ static int __init s390_smp_init(void) { int cpu, rc; - register_cpu_notifier(&smp_cpu_nb); + hotcpu_notifier(smp_cpu_notify, 0); #ifdef CONFIG_HOTPLUG_CPU rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan); if (rc) diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index bcab2f0..4817485 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -350,3 +350,5 @@ SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper) SYSCALL(sys_setns,sys_setns,sys_setns_wrapper) SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */ SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper) +SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,sys_s390_runtime_instr_wrapper) +SYSCALL(sys_kcmp,sys_kcmp,sys_kcmp_wrapper) diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index fa0eb23..62f89d9 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -22,17 +22,41 @@ #include <math-emu/soft-fp.h> #include <math-emu/single.h> -static inline int stsi_0(void) +int topology_max_mnest; + +/* + * stsi - store system information + * + * Returns the current configuration level if function code 0 was specified. + * Otherwise returns 0 on success or a negative value on error. + */ +int stsi(void *sysinfo, int fc, int sel1, int sel2) { - int rc = stsi(NULL, 0, 0, 0); - return rc == -ENOSYS ? rc : (((unsigned int) rc) >> 28); + register int r0 asm("0") = (fc << 28) | sel1; + register int r1 asm("1") = sel2; + int rc = 0; + + asm volatile( + " stsi 0(%3)\n" + "0: jz 2f\n" + "1: lhi %1,%4\n" + "2:\n" + EX_TABLE(0b, 1b) + : "+d" (r0), "+d" (rc) + : "d" (r1), "a" (sysinfo), "K" (-EOPNOTSUPP) + : "cc", "memory"); + if (rc) + return rc; + return fc ? 0 : ((unsigned int) r0) >> 28; } +EXPORT_SYMBOL(stsi); -static int stsi_1_1_1(struct sysinfo_1_1_1 *info, char *page, int len) +static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info) { - if (stsi(info, 1, 1, 1) == -ENOSYS) - return len; + int i; + if (stsi(info, 1, 1, 1)) + return; EBCASC(info->manufacturer, sizeof(info->manufacturer)); EBCASC(info->type, sizeof(info->type)); EBCASC(info->model, sizeof(info->model)); @@ -41,242 +65,197 @@ static int stsi_1_1_1(struct sysinfo_1_1_1 *info, char *page, int len) EBCASC(info->model_capacity, sizeof(info->model_capacity)); EBCASC(info->model_perm_cap, sizeof(info->model_perm_cap)); EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap)); - len += sprintf(page + len, "Manufacturer: %-16.16s\n", - info->manufacturer); - len += sprintf(page + len, "Type: %-4.4s\n", - info->type); + seq_printf(m, "Manufacturer: %-16.16s\n", info->manufacturer); + seq_printf(m, "Type: %-4.4s\n", info->type); + /* + * Sigh: the model field has been renamed with System z9 + * to model_capacity and a new model field has been added + * after the plant field. To avoid confusing older programs + * the "Model:" prints "model_capacity model" or just + * "model_capacity" if the model string is empty . + */ + seq_printf(m, "Model: %-16.16s", info->model_capacity); if (info->model[0] != '\0') - /* - * Sigh: the model field has been renamed with System z9 - * to model_capacity and a new model field has been added - * after the plant field. To avoid confusing older programs - * the "Model:" prints "model_capacity model" or just - * "model_capacity" if the model string is empty . - */ - len += sprintf(page + len, - "Model: %-16.16s %-16.16s\n", - info->model_capacity, info->model); - else - len += sprintf(page + len, "Model: %-16.16s\n", - info->model_capacity); - len += sprintf(page + len, "Sequence Code: %-16.16s\n", - info->sequence); - len += sprintf(page + len, "Plant: %-4.4s\n", - info->plant); - len += sprintf(page + len, "Model Capacity: %-16.16s %08u\n", - info->model_capacity, *(u32 *) info->model_cap_rating); - if (info->model_perm_cap[0] != '\0') - len += sprintf(page + len, - "Model Perm. Capacity: %-16.16s %08u\n", - info->model_perm_cap, - *(u32 *) info->model_perm_cap_rating); - if (info->model_temp_cap[0] != '\0') - len += sprintf(page + len, - "Model Temp. Capacity: %-16.16s %08u\n", - info->model_temp_cap, - *(u32 *) info->model_temp_cap_rating); + seq_printf(m, " %-16.16s", info->model); + seq_putc(m, '\n'); + seq_printf(m, "Sequence Code: %-16.16s\n", info->sequence); + seq_printf(m, "Plant: %-4.4s\n", info->plant); + seq_printf(m, "Model Capacity: %-16.16s %08u\n", + info->model_capacity, info->model_cap_rating); + if (info->model_perm_cap_rating) + seq_printf(m, "Model Perm. Capacity: %-16.16s %08u\n", + info->model_perm_cap, + info->model_perm_cap_rating); + if (info->model_temp_cap_rating) + seq_printf(m, "Model Temp. Capacity: %-16.16s %08u\n", + info->model_temp_cap, + info->model_temp_cap_rating); + if (info->ncr) + seq_printf(m, "Nominal Cap. Rating: %08u\n", info->ncr); + if (info->npr) + seq_printf(m, "Nominal Perm. Rating: %08u\n", info->npr); + if (info->ntr) + seq_printf(m, "Nominal Temp. Rating: %08u\n", info->ntr); if (info->cai) { - len += sprintf(page + len, - "Capacity Adj. Ind.: %d\n", - info->cai); - len += sprintf(page + len, "Capacity Ch. Reason: %d\n", - info->ccr); + seq_printf(m, "Capacity Adj. Ind.: %d\n", info->cai); + seq_printf(m, "Capacity Ch. Reason: %d\n", info->ccr); + seq_printf(m, "Capacity Transient: %d\n", info->t); + } + if (info->p) { + for (i = 1; i <= ARRAY_SIZE(info->typepct); i++) { + seq_printf(m, "Type %d Percentage: %d\n", + i, info->typepct[i - 1]); + } } - return len; } -static int stsi_15_1_x(struct sysinfo_15_1_x *info, char *page, int len) +static void stsi_15_1_x(struct seq_file *m, struct sysinfo_15_1_x *info) { static int max_mnest; int i, rc; - len += sprintf(page + len, "\n"); + seq_putc(m, '\n'); if (!MACHINE_HAS_TOPOLOGY) - return len; - if (max_mnest) { - stsi(info, 15, 1, max_mnest); - } else { - for (max_mnest = 6; max_mnest > 1; max_mnest--) { - rc = stsi(info, 15, 1, max_mnest); - if (rc != -ENOSYS) - break; - } - } - len += sprintf(page + len, "CPU Topology HW: "); + return; + if (stsi(info, 15, 1, topology_max_mnest)) + return; + seq_printf(m, "CPU Topology HW: "); for (i = 0; i < TOPOLOGY_NR_MAG; i++) - len += sprintf(page + len, " %d", info->mag[i]); - len += sprintf(page + len, "\n"); + seq_printf(m, " %d", info->mag[i]); + seq_putc(m, '\n'); #ifdef CONFIG_SCHED_MC store_topology(info); - len += sprintf(page + len, "CPU Topology SW: "); + seq_printf(m, "CPU Topology SW: "); for (i = 0; i < TOPOLOGY_NR_MAG; i++) - len += sprintf(page + len, " %d", info->mag[i]); - len += sprintf(page + len, "\n"); + seq_printf(m, " %d", info->mag[i]); + seq_putc(m, '\n'); #endif - return len; } -static int stsi_1_2_2(struct sysinfo_1_2_2 *info, char *page, int len) +static void stsi_1_2_2(struct seq_file *m, struct sysinfo_1_2_2 *info) { struct sysinfo_1_2_2_extension *ext; int i; - if (stsi(info, 1, 2, 2) == -ENOSYS) - return len; + if (stsi(info, 1, 2, 2)) + return; ext = (struct sysinfo_1_2_2_extension *) ((unsigned long) info + info->acc_offset); - - len += sprintf(page + len, "CPUs Total: %d\n", - info->cpus_total); - len += sprintf(page + len, "CPUs Configured: %d\n", - info->cpus_configured); - len += sprintf(page + len, "CPUs Standby: %d\n", - info->cpus_standby); - len += sprintf(page + len, "CPUs Reserved: %d\n", - info->cpus_reserved); - - if (info->format == 1) { - /* - * Sigh 2. According to the specification the alternate - * capability field is a 32 bit floating point number - * if the higher order 8 bits are not zero. Printing - * a floating point number in the kernel is a no-no, - * always print the number as 32 bit unsigned integer. - * The user-space needs to know about the strange - * encoding of the alternate cpu capability. - */ - len += sprintf(page + len, "Capability: %u %u\n", - info->capability, ext->alt_capability); - for (i = 2; i <= info->cpus_total; i++) - len += sprintf(page + len, - "Adjustment %02d-way: %u %u\n", - i, info->adjustment[i-2], - ext->alt_adjustment[i-2]); - - } else { - len += sprintf(page + len, "Capability: %u\n", - info->capability); - for (i = 2; i <= info->cpus_total; i++) - len += sprintf(page + len, - "Adjustment %02d-way: %u\n", - i, info->adjustment[i-2]); + seq_printf(m, "CPUs Total: %d\n", info->cpus_total); + seq_printf(m, "CPUs Configured: %d\n", info->cpus_configured); + seq_printf(m, "CPUs Standby: %d\n", info->cpus_standby); + seq_printf(m, "CPUs Reserved: %d\n", info->cpus_reserved); + /* + * Sigh 2. According to the specification the alternate + * capability field is a 32 bit floating point number + * if the higher order 8 bits are not zero. Printing + * a floating point number in the kernel is a no-no, + * always print the number as 32 bit unsigned integer. + * The user-space needs to know about the strange + * encoding of the alternate cpu capability. + */ + seq_printf(m, "Capability: %u", info->capability); + if (info->format == 1) + seq_printf(m, " %u", ext->alt_capability); + seq_putc(m, '\n'); + if (info->nominal_cap) + seq_printf(m, "Nominal Capability: %d\n", info->nominal_cap); + if (info->secondary_cap) + seq_printf(m, "Secondary Capability: %d\n", info->secondary_cap); + for (i = 2; i <= info->cpus_total; i++) { + seq_printf(m, "Adjustment %02d-way: %u", + i, info->adjustment[i-2]); + if (info->format == 1) + seq_printf(m, " %u", ext->alt_adjustment[i-2]); + seq_putc(m, '\n'); } - - if (info->secondary_capability != 0) - len += sprintf(page + len, "Secondary Capability: %d\n", - info->secondary_capability); - return len; } -static int stsi_2_2_2(struct sysinfo_2_2_2 *info, char *page, int len) +static void stsi_2_2_2(struct seq_file *m, struct sysinfo_2_2_2 *info) { - if (stsi(info, 2, 2, 2) == -ENOSYS) - return len; - + if (stsi(info, 2, 2, 2)) + return; EBCASC(info->name, sizeof(info->name)); - - len += sprintf(page + len, "\n"); - len += sprintf(page + len, "LPAR Number: %d\n", - info->lpar_number); - - len += sprintf(page + len, "LPAR Characteristics: "); + seq_putc(m, '\n'); + seq_printf(m, "LPAR Number: %d\n", info->lpar_number); + seq_printf(m, "LPAR Characteristics: "); if (info->characteristics & LPAR_CHAR_DEDICATED) - len += sprintf(page + len, "Dedicated "); + seq_printf(m, "Dedicated "); if (info->characteristics & LPAR_CHAR_SHARED) - len += sprintf(page + len, "Shared "); + seq_printf(m, "Shared "); if (info->characteristics & LPAR_CHAR_LIMITED) - len += sprintf(page + len, "Limited "); - len += sprintf(page + len, "\n"); - - len += sprintf(page + len, "LPAR Name: %-8.8s\n", - info->name); - - len += sprintf(page + len, "LPAR Adjustment: %d\n", - info->caf); - - len += sprintf(page + len, "LPAR CPUs Total: %d\n", - info->cpus_total); - len += sprintf(page + len, "LPAR CPUs Configured: %d\n", - info->cpus_configured); - len += sprintf(page + len, "LPAR CPUs Standby: %d\n", - info->cpus_standby); - len += sprintf(page + len, "LPAR CPUs Reserved: %d\n", - info->cpus_reserved); - len += sprintf(page + len, "LPAR CPUs Dedicated: %d\n", - info->cpus_dedicated); - len += sprintf(page + len, "LPAR CPUs Shared: %d\n", - info->cpus_shared); - return len; + seq_printf(m, "Limited "); + seq_putc(m, '\n'); + seq_printf(m, "LPAR Name: %-8.8s\n", info->name); + seq_printf(m, "LPAR Adjustment: %d\n", info->caf); + seq_printf(m, "LPAR CPUs Total: %d\n", info->cpus_total); + seq_printf(m, "LPAR CPUs Configured: %d\n", info->cpus_configured); + seq_printf(m, "LPAR CPUs Standby: %d\n", info->cpus_standby); + seq_printf(m, "LPAR CPUs Reserved: %d\n", info->cpus_reserved); + seq_printf(m, "LPAR CPUs Dedicated: %d\n", info->cpus_dedicated); + seq_printf(m, "LPAR CPUs Shared: %d\n", info->cpus_shared); } -static int stsi_3_2_2(struct sysinfo_3_2_2 *info, char *page, int len) +static void stsi_3_2_2(struct seq_file *m, struct sysinfo_3_2_2 *info) { int i; - if (stsi(info, 3, 2, 2) == -ENOSYS) - return len; + if (stsi(info, 3, 2, 2)) + return; for (i = 0; i < info->count; i++) { EBCASC(info->vm[i].name, sizeof(info->vm[i].name)); EBCASC(info->vm[i].cpi, sizeof(info->vm[i].cpi)); - len += sprintf(page + len, "\n"); - len += sprintf(page + len, "VM%02d Name: %-8.8s\n", - i, info->vm[i].name); - len += sprintf(page + len, "VM%02d Control Program: %-16.16s\n", - i, info->vm[i].cpi); - - len += sprintf(page + len, "VM%02d Adjustment: %d\n", - i, info->vm[i].caf); - - len += sprintf(page + len, "VM%02d CPUs Total: %d\n", - i, info->vm[i].cpus_total); - len += sprintf(page + len, "VM%02d CPUs Configured: %d\n", - i, info->vm[i].cpus_configured); - len += sprintf(page + len, "VM%02d CPUs Standby: %d\n", - i, info->vm[i].cpus_standby); - len += sprintf(page + len, "VM%02d CPUs Reserved: %d\n", - i, info->vm[i].cpus_reserved); + seq_putc(m, '\n'); + seq_printf(m, "VM%02d Name: %-8.8s\n", i, info->vm[i].name); + seq_printf(m, "VM%02d Control Program: %-16.16s\n", i, info->vm[i].cpi); + seq_printf(m, "VM%02d Adjustment: %d\n", i, info->vm[i].caf); + seq_printf(m, "VM%02d CPUs Total: %d\n", i, info->vm[i].cpus_total); + seq_printf(m, "VM%02d CPUs Configured: %d\n", i, info->vm[i].cpus_configured); + seq_printf(m, "VM%02d CPUs Standby: %d\n", i, info->vm[i].cpus_standby); + seq_printf(m, "VM%02d CPUs Reserved: %d\n", i, info->vm[i].cpus_reserved); } - return len; } -static int proc_read_sysinfo(char *page, char **start, - off_t off, int count, - int *eof, void *data) +static int sysinfo_show(struct seq_file *m, void *v) { - unsigned long info = get_zeroed_page(GFP_KERNEL); - int level, len; + void *info = (void *)get_zeroed_page(GFP_KERNEL); + int level; if (!info) return 0; - - len = 0; - level = stsi_0(); + level = stsi(NULL, 0, 0, 0); if (level >= 1) - len = stsi_1_1_1((struct sysinfo_1_1_1 *) info, page, len); - + stsi_1_1_1(m, info); if (level >= 1) - len = stsi_15_1_x((struct sysinfo_15_1_x *) info, page, len); - + stsi_15_1_x(m, info); if (level >= 1) - len = stsi_1_2_2((struct sysinfo_1_2_2 *) info, page, len); - + stsi_1_2_2(m, info); if (level >= 2) - len = stsi_2_2_2((struct sysinfo_2_2_2 *) info, page, len); - + stsi_2_2_2(m, info); if (level >= 3) - len = stsi_3_2_2((struct sysinfo_3_2_2 *) info, page, len); + stsi_3_2_2(m, info); + free_page((unsigned long)info); + return 0; +} - free_page(info); - return len; +static int sysinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, sysinfo_show, NULL); } -static __init int create_proc_sysinfo(void) +static const struct file_operations sysinfo_fops = { + .open = sysinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init sysinfo_create_proc(void) { - create_proc_read_entry("sysinfo", 0444, NULL, - proc_read_sysinfo, NULL); + proc_create("sysinfo", 0444, NULL, &sysinfo_fops); return 0; } -device_initcall(create_proc_sysinfo); +device_initcall(sysinfo_create_proc); /* * Service levels interface. @@ -407,7 +386,7 @@ void s390_adjust_jiffies(void) if (!info) return; - if (stsi(info, 1, 2, 2) != -ENOSYS) { + if (stsi(info, 1, 2, 2) == 0) { /* * Major sigh. The cpu capability encoding is "special". * If the first 9 bits of info->capability are 0 then it diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index dcec960..2db1011 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -329,7 +329,7 @@ static unsigned long clock_sync_flags; * The synchronous get_clock function. It will write the current clock * value to the clock pointer and return 0 if the clock is in sync with * the external time source. If the clock mode is local it will return - * -ENOSYS and -EAGAIN if the clock is not in sync with the external + * -EOPNOTSUPP and -EAGAIN if the clock is not in sync with the external * reference. */ int get_sync_clock(unsigned long long *clock) @@ -347,7 +347,7 @@ int get_sync_clock(unsigned long long *clock) return 0; if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags) && !test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) - return -ENOSYS; + return -EOPNOTSUPP; if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags) && !test_bit(CLOCK_SYNC_STP, &clock_sync_flags)) return -EACCES; diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 05151e0..54d93f4 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -17,6 +17,7 @@ #include <linux/cpu.h> #include <linux/smp.h> #include <linux/mm.h> +#include <asm/sysinfo.h> #define PTF_HORIZONTAL (0UL) #define PTF_VERTICAL (1UL) @@ -44,9 +45,6 @@ static struct mask_info book_info; cpumask_t cpu_book_map[NR_CPUS]; unsigned char cpu_book_id[NR_CPUS]; -/* smp_cpu_state_mutex must be held when accessing this array */ -int cpu_polarization[NR_CPUS]; - static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) { cpumask_t mask; @@ -75,10 +73,7 @@ static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu, { unsigned int cpu; - for (cpu = find_first_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS); - cpu < TOPOLOGY_CPU_BITS; - cpu = find_next_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS, cpu + 1)) - { + for_each_set_bit(cpu, &tl_cpu->mask[0], TOPOLOGY_CPU_BITS) { unsigned int rcpu; int lcpu; @@ -94,7 +89,7 @@ static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu, } else { cpu_core_id[lcpu] = core->id; } - cpu_set_polarization(lcpu, tl_cpu->pp); + smp_cpu_set_polarization(lcpu, tl_cpu->pp); } } return core; @@ -201,7 +196,7 @@ static void topology_update_polarization_simple(void) mutex_lock(&smp_cpu_state_mutex); for_each_possible_cpu(cpu) - cpu_set_polarization(cpu, POLARIZATION_HRZ); + smp_cpu_set_polarization(cpu, POLARIZATION_HRZ); mutex_unlock(&smp_cpu_state_mutex); } @@ -231,7 +226,7 @@ int topology_set_cpu_management(int fc) if (rc) return -EBUSY; for_each_possible_cpu(cpu) - cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); return rc; } @@ -250,12 +245,10 @@ static void update_cpu_core_map(void) void store_topology(struct sysinfo_15_1_x *info) { - int rc; - - rc = stsi(info, 15, 1, 3); - if (rc != -ENOSYS) - return; - stsi(info, 15, 1, 2); + if (topology_max_mnest >= 3) + stsi(info, 15, 1, 3); + else + stsi(info, 15, 1, 2); } int arch_update_cpu_topology(void) @@ -415,7 +408,7 @@ static ssize_t cpu_polarization_show(struct device *dev, ssize_t count; mutex_lock(&smp_cpu_state_mutex); - switch (cpu_read_polarization(cpu)) { + switch (smp_cpu_get_polarization(cpu)) { case POLARIZATION_HRZ: count = sprintf(buf, "horizontal\n"); break; diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 01775c0..3d2b0fa3 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -57,6 +57,23 @@ static int kstack_depth_to_print = 12; static int kstack_depth_to_print = 20; #endif /* CONFIG_64BIT */ +static inline void __user *get_trap_ip(struct pt_regs *regs) +{ +#ifdef CONFIG_64BIT + unsigned long address; + + if (regs->int_code & 0x200) + address = *(unsigned long *)(current->thread.trap_tdb + 24); + else + address = regs->psw.addr; + return (void __user *) + ((address - (regs->int_code >> 16)) & PSW_ADDR_INSN); +#else + return (void __user *) + ((regs->psw.addr - (regs->int_code >> 16)) & PSW_ADDR_INSN); +#endif +} + /* * For show_trace we have tree different stack to consider: * - the panic stack which is used if the kernel stack has overflown @@ -214,7 +231,6 @@ void show_registers(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { - print_modules(); printk("CPU: %d %s %s %.*s\n", task_thread_info(current)->cpu, print_tainted(), init_utsname()->release, @@ -254,6 +270,7 @@ void die(struct pt_regs *regs, const char *str) #endif printk("\n"); notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); + print_modules(); show_regs(regs); bust_spinlocks(0); add_taint(TAINT_DIE); @@ -285,12 +302,6 @@ int is_valid_bugaddr(unsigned long addr) return 1; } -static inline void __user *get_psw_address(struct pt_regs *regs) -{ - return (void __user *) - ((regs->psw.addr - (regs->int_code >> 16)) & PSW_ADDR_INSN); -} - static void __kprobes do_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) { @@ -304,14 +315,14 @@ static void __kprobes do_trap(struct pt_regs *regs, info.si_signo = si_signo; info.si_errno = 0; info.si_code = si_code; - info.si_addr = get_psw_address(regs); + info.si_addr = get_trap_ip(regs); force_sig_info(si_signo, &info, current); report_user_fault(regs, si_signo); } else { const struct exception_table_entry *fixup; fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); if (fixup) - regs->psw.addr = fixup->fixup | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE; else { enum bug_trap_type btt; @@ -381,6 +392,11 @@ DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN, DO_ERROR_INFO(translation_exception, SIGILL, ILL_ILLOPN, "translation exception") +#ifdef CONFIG_64BIT +DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN, + "transaction constraint exception") +#endif + static inline void do_fp_trap(struct pt_regs *regs, int fpc) { int si_code = 0; @@ -408,7 +424,7 @@ static void __kprobes illegal_op(struct pt_regs *regs) __u16 __user *location; int signal = 0; - location = get_psw_address(regs); + location = get_trap_ip(regs); if (user_mode(regs)) { if (get_user(*((__u16 *) opcode), (__u16 __user *) location)) @@ -476,7 +492,7 @@ void specification_exception(struct pt_regs *regs) __u16 __user *location = NULL; int signal = 0; - location = (__u16 __user *) get_psw_address(regs); + location = (__u16 __user *) get_trap_ip(regs); if (user_mode(regs)) { get_user(*((__u16 *) opcode), location); @@ -525,7 +541,7 @@ static void data_exception(struct pt_regs *regs) __u16 __user *location; int signal = 0; - location = get_psw_address(regs); + location = get_trap_ip(regs); if (MACHINE_HAS_IEEE) asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc)); @@ -641,6 +657,7 @@ void __init trap_init(void) pgm_check_table[0x12] = &translation_exception; pgm_check_table[0x13] = &special_op_exception; #ifdef CONFIG_64BIT + pgm_check_table[0x18] = &transaction_exception; pgm_check_table[0x38] = &do_asce_exception; pgm_check_table[0x39] = &do_dat_exception; pgm_check_table[0x3A] = &do_dat_exception; diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 9a19ca3..d777628 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -85,7 +85,7 @@ struct vdso_data *vdso_data = &vdso_data_store.data; static void vdso_init_data(struct vdso_data *vd) { vd->ectg_available = - addressing_mode != HOME_SPACE_MODE && test_facility(31); + s390_user_mode != HOME_SPACE_MODE && test_facility(31); } #ifdef CONFIG_64BIT @@ -102,7 +102,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) lowcore->vdso_per_cpu_data = __LC_PASTE; - if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled) + if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) return 0; segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); @@ -147,7 +147,7 @@ void vdso_free_per_cpu(struct _lowcore *lowcore) unsigned long segment_table, page_table, page_frame; u32 *psal, *aste; - if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled) + if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) return; psal = (u32 *)(addr_t) lowcore->paste[4]; @@ -165,7 +165,7 @@ static void vdso_init_cr5(void) { unsigned long cr5; - if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled) + if (s390_user_mode == HOME_SPACE_MODE || !vdso_enabled) return; cr5 = offsetof(struct _lowcore, paste); __ctl_load(cr5, 5, 5); diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 4fc97b4..7903344 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -99,7 +99,7 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) return virt_timer_forward(user + system); } -void account_vtime(struct task_struct *prev, struct task_struct *next) +void vtime_task_switch(struct task_struct *prev) { struct thread_info *ti; @@ -107,7 +107,7 @@ void account_vtime(struct task_struct *prev, struct task_struct *next) ti = task_thread_info(prev); ti->user_timer = S390_lowcore.user_timer; ti->system_timer = S390_lowcore.system_timer; - ti = task_thread_info(next); + ti = task_thread_info(current); S390_lowcore.user_timer = ti->user_timer; S390_lowcore.system_timer = ti->system_timer; } @@ -122,7 +122,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick) * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -void account_system_vtime(struct task_struct *tsk) +void vtime_account(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); u64 timer, system; @@ -138,7 +138,7 @@ void account_system_vtime(struct task_struct *tsk) virt_timer_forward(system); } -EXPORT_SYMBOL_GPL(account_system_vtime); +EXPORT_SYMBOL_GPL(vtime_account); void __kprobes vtime_stop_cpu(void) { @@ -378,9 +378,8 @@ static int __cpuinit s390_nohz_notify(struct notifier_block *self, long cpu = (long) hcpu; idle = &per_cpu(s390_idle, cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DYING: - case CPU_DYING_FROZEN: idle->nohz_delay = 0; default: break; diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 78eb984..9b04a32 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -5,7 +5,7 @@ source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION def_bool y - prompt "Virtualization" + prompt "KVM" ---help--- Say Y here to get to see options for using your Linux host to run other operating systems inside virtual machines (guests). diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 60da903..310be61 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -211,7 +211,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) spin_unlock(&fi->lock); /* deal with other level 3 hypervisors */ - if (stsi(mem, 3, 2, 2) == -ENOSYS) + if (stsi(mem, 3, 2, 2)) mem->count = 0; if (mem->count < 8) mem->count++; @@ -259,7 +259,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) mem = get_zeroed_page(GFP_KERNEL); if (!mem) goto out_fail; - if (stsi((void *) mem, fc, sel1, sel2) == -ENOSYS) + if (stsi((void *) mem, fc, sel1, sel2)) goto out_mem; break; case 3: diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 761ab8b..6ab0d0b 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -4,6 +4,7 @@ lib-y += delay.o string.o uaccess_std.o uaccess_pt.o obj-y += usercopy.o -obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o +obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o +obj-$(CONFIG_64BIT) += mem64.o lib-$(CONFIG_64BIT) += uaccess_mvcos.o lib-$(CONFIG_SMP) += spinlock.o diff --git a/arch/s390/lib/mem32.S b/arch/s390/lib/mem32.S new file mode 100644 index 0000000..14ca924 --- /dev/null +++ b/arch/s390/lib/mem32.S @@ -0,0 +1,92 @@ +/* + * String handling functions. + * + * Copyright IBM Corp. 2012 + */ + +#include <linux/linkage.h> + +/* + * memset implementation + * + * This code corresponds to the C construct below. We do distinguish + * between clearing (c == 0) and setting a memory array (c != 0) simply + * because nearly all memset invocations in the kernel clear memory and + * the xc instruction is preferred in such cases. + * + * void *memset(void *s, int c, size_t n) + * { + * if (likely(c == 0)) + * return __builtin_memset(s, 0, n); + * return __builtin_memset(s, c, n); + * } + */ +ENTRY(memset) + basr %r5,%r0 +.Lmemset_base: + ltr %r4,%r4 + bzr %r14 + ltr %r3,%r3 + jnz .Lmemset_fill + ahi %r4,-1 + lr %r3,%r4 + srl %r3,8 + ltr %r3,%r3 + lr %r1,%r2 + je .Lmemset_clear_rest +.Lmemset_clear_loop: + xc 0(256,%r1),0(%r1) + la %r1,256(%r1) + brct %r3,.Lmemset_clear_loop +.Lmemset_clear_rest: + ex %r4,.Lmemset_xc-.Lmemset_base(%r5) + br %r14 +.Lmemset_fill: + stc %r3,0(%r2) + chi %r4,1 + lr %r1,%r2 + ber %r14 + ahi %r4,-2 + lr %r3,%r4 + srl %r3,8 + ltr %r3,%r3 + je .Lmemset_fill_rest +.Lmemset_fill_loop: + mvc 1(256,%r1),0(%r1) + la %r1,256(%r1) + brct %r3,.Lmemset_fill_loop +.Lmemset_fill_rest: + ex %r4,.Lmemset_mvc-.Lmemset_base(%r5) + br %r14 +.Lmemset_xc: + xc 0(1,%r1),0(%r1) +.Lmemset_mvc: + mvc 1(1,%r1),0(%r1) + +/* + * memcpy implementation + * + * void *memcpy(void *dest, const void *src, size_t n) + */ +ENTRY(memcpy) + basr %r5,%r0 +.Lmemcpy_base: + ltr %r4,%r4 + bzr %r14 + ahi %r4,-1 + lr %r0,%r4 + srl %r0,8 + ltr %r0,%r0 + lr %r1,%r2 + jnz .Lmemcpy_loop +.Lmemcpy_rest: + ex %r4,.Lmemcpy_mvc-.Lmemcpy_base(%r5) + br %r14 +.Lmemcpy_loop: + mvc 0(256,%r1),0(%r3) + la %r1,256(%r1) + la %r3,256(%r3) + brct %r0,.Lmemcpy_loop + j .Lmemcpy_rest +.Lmemcpy_mvc: + mvc 0(1,%r1),0(%r3) diff --git a/arch/s390/lib/mem64.S b/arch/s390/lib/mem64.S new file mode 100644 index 0000000..c6d553e --- /dev/null +++ b/arch/s390/lib/mem64.S @@ -0,0 +1,88 @@ +/* + * String handling functions. + * + * Copyright IBM Corp. 2012 + */ + +#include <linux/linkage.h> + +/* + * memset implementation + * + * This code corresponds to the C construct below. We do distinguish + * between clearing (c == 0) and setting a memory array (c != 0) simply + * because nearly all memset invocations in the kernel clear memory and + * the xc instruction is preferred in such cases. + * + * void *memset(void *s, int c, size_t n) + * { + * if (likely(c == 0)) + * return __builtin_memset(s, 0, n); + * return __builtin_memset(s, c, n); + * } + */ +ENTRY(memset) + ltgr %r4,%r4 + bzr %r14 + ltgr %r3,%r3 + jnz .Lmemset_fill + aghi %r4,-1 + srlg %r3,%r4,8 + ltgr %r3,%r3 + lgr %r1,%r2 + jz .Lmemset_clear_rest +.Lmemset_clear_loop: + xc 0(256,%r1),0(%r1) + la %r1,256(%r1) + brctg %r3,.Lmemset_clear_loop +.Lmemset_clear_rest: + larl %r3,.Lmemset_xc + ex %r4,0(%r3) + br %r14 +.Lmemset_fill: + stc %r3,0(%r2) + cghi %r4,1 + lgr %r1,%r2 + ber %r14 + aghi %r4,-2 + srlg %r3,%r4,8 + ltgr %r3,%r3 + jz .Lmemset_fill_rest +.Lmemset_fill_loop: + mvc 1(256,%r1),0(%r1) + la %r1,256(%r1) + brctg %r3,.Lmemset_fill_loop +.Lmemset_fill_rest: + larl %r3,.Lmemset_mvc + ex %r4,0(%r3) + br %r14 +.Lmemset_xc: + xc 0(1,%r1),0(%r1) +.Lmemset_mvc: + mvc 1(1,%r1),0(%r1) + +/* + * memcpy implementation + * + * void *memcpy(void *dest, const void *src, size_t n) + */ +ENTRY(memcpy) + ltgr %r4,%r4 + bzr %r14 + aghi %r4,-1 + srlg %r5,%r4,8 + ltgr %r5,%r5 + lgr %r1,%r2 + jnz .Lmemcpy_loop +.Lmemcpy_rest: + larl %r5,.Lmemcpy_mvc + ex %r4,0(%r5) + br %r14 +.Lmemcpy_loop: + mvc 0(256,%r1),0(%r3) + la %r1,256(%r1) + la %r3,256(%r3) + brctg %r5,.Lmemcpy_loop + j .Lmemcpy_rest +.Lmemcpy_mvc: + mvc 0(1,%r1),0(%r3) diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index 846ec64..b647d5f 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -43,11 +43,7 @@ static inline char *__strnend(const char *s, size_t n) */ size_t strlen(const char *s) { -#if __GNUC__ < 4 return __strend(s) - s; -#else - return __builtin_strlen(s); -#endif } EXPORT_SYMBOL(strlen); @@ -73,7 +69,6 @@ EXPORT_SYMBOL(strnlen); */ char *strcpy(char *dest, const char *src) { -#if __GNUC__ < 4 register int r0 asm("0") = 0; char *ret = dest; @@ -82,9 +77,6 @@ char *strcpy(char *dest, const char *src) : "+&a" (dest), "+&a" (src) : "d" (r0) : "cc", "memory" ); return ret; -#else - return __builtin_strcpy(dest, src); -#endif } EXPORT_SYMBOL(strcpy); @@ -106,7 +98,7 @@ size_t strlcpy(char *dest, const char *src, size_t size) if (size) { size_t len = (ret >= size) ? size-1 : ret; dest[len] = '\0'; - __builtin_memcpy(dest, src, len); + memcpy(dest, src, len); } return ret; } @@ -124,8 +116,8 @@ EXPORT_SYMBOL(strlcpy); char *strncpy(char *dest, const char *src, size_t n) { size_t len = __strnend(src, n) - src; - __builtin_memset(dest + len, 0, n - len); - __builtin_memcpy(dest, src, len); + memset(dest + len, 0, n - len); + memcpy(dest, src, len); return dest; } EXPORT_SYMBOL(strncpy); @@ -171,7 +163,7 @@ size_t strlcat(char *dest, const char *src, size_t n) if (len >= n) len = n - 1; dest[len] = '\0'; - __builtin_memcpy(dest, src, len); + memcpy(dest, src, len); } return res; } @@ -194,7 +186,7 @@ char *strncat(char *dest, const char *src, size_t n) char *p = __strend(dest); p[len] = '\0'; - __builtin_memcpy(p, src, len); + memcpy(p, src, len); return dest; } EXPORT_SYMBOL(strncat); @@ -348,41 +340,3 @@ void *memscan(void *s, int c, size_t n) return (void *) ret; } EXPORT_SYMBOL(memscan); - -/** - * memcpy - Copy one area of memory to another - * @dest: Where to copy to - * @src: Where to copy from - * @n: The size of the area. - * - * returns a pointer to @dest - */ -void *memcpy(void *dest, const void *src, size_t n) -{ - return __builtin_memcpy(dest, src, n); -} -EXPORT_SYMBOL(memcpy); - -/** - * memset - Fill a region of memory with the given value - * @s: Pointer to the start of the area. - * @c: The byte to fill the area with - * @n: The size of the area. - * - * returns a pointer to @s - */ -void *memset(void *s, int c, size_t n) -{ - char *xs; - - if (c == 0) - return __builtin_memset(s, 0, n); - - xs = (char *) s; - if (n > 0) - do { - *xs++ = c; - } while (--n > 0); - return s; -} -EXPORT_SYMBOL(memset); diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 60ee2b8..2d37bb8 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -2,69 +2,82 @@ * User access functions based on page table walks for enhanced * system layout without hardware support. * - * Copyright IBM Corp. 2006 + * Copyright IBM Corp. 2006, 2012 * Author(s): Gerald Schaefer (gerald.schaefer@de.ibm.com) */ #include <linux/errno.h> #include <linux/hardirq.h> #include <linux/mm.h> +#include <linux/hugetlb.h> #include <asm/uaccess.h> #include <asm/futex.h> #include "uaccess.h" -static inline pte_t *follow_table(struct mm_struct *mm, unsigned long addr) + +/* + * Returns kernel address for user virtual address. If the returned address is + * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address + * contains the (negative) exception code. + */ +static __always_inline unsigned long follow_table(struct mm_struct *mm, + unsigned long addr, int write) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; + pte_t *ptep; pgd = pgd_offset(mm, addr); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return (pte_t *) 0x3a; + return -0x3aUL; pud = pud_offset(pgd, addr); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return (pte_t *) 0x3b; + return -0x3bUL; pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - return (pte_t *) 0x10; + if (pmd_none(*pmd)) + return -0x10UL; + if (pmd_huge(*pmd)) { + if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO)) + return -0x04UL; + return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK); + } + if (unlikely(pmd_bad(*pmd))) + return -0x10UL; + + ptep = pte_offset_map(pmd, addr); + if (!pte_present(*ptep)) + return -0x11UL; + if (write && !pte_write(*ptep)) + return -0x04UL; - return pte_offset_map(pmd, addr); + return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK); } static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr, size_t n, int write_user) { struct mm_struct *mm = current->mm; - unsigned long offset, pfn, done, size; - pte_t *pte; + unsigned long offset, done, size, kaddr; void *from, *to; done = 0; retry: spin_lock(&mm->page_table_lock); do { - pte = follow_table(mm, uaddr); - if ((unsigned long) pte < 0x1000) + kaddr = follow_table(mm, uaddr, write_user); + if (IS_ERR_VALUE(kaddr)) goto fault; - if (!pte_present(*pte)) { - pte = (pte_t *) 0x11; - goto fault; - } else if (write_user && !pte_write(*pte)) { - pte = (pte_t *) 0x04; - goto fault; - } - pfn = pte_pfn(*pte); - offset = uaddr & (PAGE_SIZE - 1); + offset = uaddr & ~PAGE_MASK; size = min(n - done, PAGE_SIZE - offset); if (write_user) { - to = (void *)((pfn << PAGE_SHIFT) + offset); + to = (void *) kaddr; from = kptr + done; } else { - from = (void *)((pfn << PAGE_SHIFT) + offset); + from = (void *) kaddr; to = kptr + done; } memcpy(to, from, size); @@ -75,7 +88,7 @@ retry: return n - done; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(uaddr, (unsigned long) pte, write_user)) + if (__handle_fault(uaddr, -kaddr, write_user)) return n - done; goto retry; } @@ -84,27 +97,22 @@ fault: * Do DAT for user address by page table walk, return kernel address. * This function needs to be called with current->mm->page_table_lock held. */ -static __always_inline unsigned long __dat_user_addr(unsigned long uaddr) +static __always_inline unsigned long __dat_user_addr(unsigned long uaddr, + int write) { struct mm_struct *mm = current->mm; - unsigned long pfn; - pte_t *pte; + unsigned long kaddr; int rc; retry: - pte = follow_table(mm, uaddr); - if ((unsigned long) pte < 0x1000) - goto fault; - if (!pte_present(*pte)) { - pte = (pte_t *) 0x11; + kaddr = follow_table(mm, uaddr, write); + if (IS_ERR_VALUE(kaddr)) goto fault; - } - pfn = pte_pfn(*pte); - return (pfn << PAGE_SHIFT) + (uaddr & (PAGE_SIZE - 1)); + return kaddr; fault: spin_unlock(&mm->page_table_lock); - rc = __handle_fault(uaddr, (unsigned long) pte, 0); + rc = __handle_fault(uaddr, -kaddr, write); spin_lock(&mm->page_table_lock); if (!rc) goto retry; @@ -159,11 +167,9 @@ static size_t clear_user_pt(size_t n, void __user *to) static size_t strnlen_user_pt(size_t count, const char __user *src) { - char *addr; unsigned long uaddr = (unsigned long) src; struct mm_struct *mm = current->mm; - unsigned long offset, pfn, done, len; - pte_t *pte; + unsigned long offset, done, len, kaddr; size_t len_str; if (segment_eq(get_fs(), KERNEL_DS)) @@ -172,19 +178,13 @@ static size_t strnlen_user_pt(size_t count, const char __user *src) retry: spin_lock(&mm->page_table_lock); do { - pte = follow_table(mm, uaddr); - if ((unsigned long) pte < 0x1000) - goto fault; - if (!pte_present(*pte)) { - pte = (pte_t *) 0x11; + kaddr = follow_table(mm, uaddr, 0); + if (IS_ERR_VALUE(kaddr)) goto fault; - } - pfn = pte_pfn(*pte); - offset = uaddr & (PAGE_SIZE-1); - addr = (char *)(pfn << PAGE_SHIFT) + offset; + offset = uaddr & ~PAGE_MASK; len = min(count - done, PAGE_SIZE - offset); - len_str = strnlen(addr, len); + len_str = strnlen((char *) kaddr, len); done += len_str; uaddr += len_str; } while ((len_str == len) && (done < count)); @@ -192,7 +192,7 @@ retry: return done + 1; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(uaddr, (unsigned long) pte, 0)) + if (__handle_fault(uaddr, -kaddr, 0)) return 0; goto retry; } @@ -225,11 +225,10 @@ static size_t copy_in_user_pt(size_t n, void __user *to, const void __user *from) { struct mm_struct *mm = current->mm; - unsigned long offset_from, offset_to, offset_max, pfn_from, pfn_to, - uaddr, done, size, error_code; + unsigned long offset_max, uaddr, done, size, error_code; unsigned long uaddr_from = (unsigned long) from; unsigned long uaddr_to = (unsigned long) to; - pte_t *pte_from, *pte_to; + unsigned long kaddr_to, kaddr_from; int write_user; if (segment_eq(get_fs(), KERNEL_DS)) { @@ -242,38 +241,23 @@ retry: do { write_user = 0; uaddr = uaddr_from; - pte_from = follow_table(mm, uaddr_from); - error_code = (unsigned long) pte_from; - if (error_code < 0x1000) - goto fault; - if (!pte_present(*pte_from)) { - error_code = 0x11; + kaddr_from = follow_table(mm, uaddr_from, 0); + error_code = kaddr_from; + if (IS_ERR_VALUE(error_code)) goto fault; - } write_user = 1; uaddr = uaddr_to; - pte_to = follow_table(mm, uaddr_to); - error_code = (unsigned long) pte_to; - if (error_code < 0x1000) - goto fault; - if (!pte_present(*pte_to)) { - error_code = 0x11; + kaddr_to = follow_table(mm, uaddr_to, 1); + error_code = (unsigned long) kaddr_to; + if (IS_ERR_VALUE(error_code)) goto fault; - } else if (!pte_write(*pte_to)) { - error_code = 0x04; - goto fault; - } - pfn_from = pte_pfn(*pte_from); - pfn_to = pte_pfn(*pte_to); - offset_from = uaddr_from & (PAGE_SIZE-1); - offset_to = uaddr_from & (PAGE_SIZE-1); - offset_max = max(offset_from, offset_to); + offset_max = max(uaddr_from & ~PAGE_MASK, + uaddr_to & ~PAGE_MASK); size = min(n - done, PAGE_SIZE - offset_max); - memcpy((void *)(pfn_to << PAGE_SHIFT) + offset_to, - (void *)(pfn_from << PAGE_SHIFT) + offset_from, size); + memcpy((void *) kaddr_to, (void *) kaddr_from, size); done += size; uaddr_from += size; uaddr_to += size; @@ -282,7 +266,7 @@ retry: return n - done; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(uaddr, error_code, write_user)) + if (__handle_fault(uaddr, -error_code, write_user)) return n - done; goto retry; } @@ -341,7 +325,7 @@ int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) return __futex_atomic_op_pt(op, uaddr, oparg, old); spin_lock(¤t->mm->page_table_lock); uaddr = (u32 __force __user *) - __dat_user_addr((__force unsigned long) uaddr); + __dat_user_addr((__force unsigned long) uaddr, 1); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; @@ -378,7 +362,7 @@ int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval); spin_lock(¤t->mm->page_table_lock); uaddr = (u32 __force __user *) - __dat_user_addr((__force unsigned long) uaddr); + __dat_user_addr((__force unsigned long) uaddr, 1); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index d98fe90..0f5536b 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -3,7 +3,7 @@ # obj-y := init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o \ - page-states.o gup.o + page-states.o gup.o extable.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_DEBUG_SET_MODULE_RONX) += pageattr.o diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c new file mode 100644 index 0000000..4d1ee88 --- /dev/null +++ b/arch/s390/mm/extable.c @@ -0,0 +1,81 @@ +#include <linux/module.h> +#include <linux/sort.h> +#include <asm/uaccess.h> + +/* + * Search one exception table for an entry corresponding to the + * given instruction address, and return the address of the entry, + * or NULL if none is found. + * We use a binary search, and thus we assume that the table is + * already sorted. + */ +const struct exception_table_entry * +search_extable(const struct exception_table_entry *first, + const struct exception_table_entry *last, + unsigned long value) +{ + const struct exception_table_entry *mid; + unsigned long addr; + + while (first <= last) { + mid = ((last - first) >> 1) + first; + addr = extable_insn(mid); + if (addr < value) + first = mid + 1; + else if (addr > value) + last = mid - 1; + else + return mid; + } + return NULL; +} + +/* + * The exception table needs to be sorted so that the binary + * search that we use to find entries in it works properly. + * This is used both for the kernel exception table and for + * the exception tables of modules that get loaded. + * + */ +static int cmp_ex(const void *a, const void *b) +{ + const struct exception_table_entry *x = a, *y = b; + + /* This compare is only valid after normalization. */ + return x->insn - y->insn; +} + +void sort_extable(struct exception_table_entry *start, + struct exception_table_entry *finish) +{ + struct exception_table_entry *p; + int i; + + /* Normalize entries to being relative to the start of the section */ + for (p = start, i = 0; p < finish; p++, i += 8) + p->insn += i; + sort(start, finish - start, sizeof(*start), cmp_ex, NULL); + /* Denormalize all entries */ + for (p = start, i = 0; p < finish; p++, i += 8) + p->insn -= i; +} + +#ifdef CONFIG_MODULES +/* + * If the exception table is sorted, any referring to the module init + * will be at the beginning or the end. + */ +void trim_init_extable(struct module *m) +{ + /* Trim the beginning */ + while (m->num_exentries && + within_module_init(extable_insn(&m->extable[0]), m)) { + m->extable++; + m->num_exentries--; + } + /* Trim the end */ + while (m->num_exentries && + within_module_init(extable_insn(&m->extable[m->num_exentries-1]), m)) + m->num_exentries--; +} +#endif /* CONFIG_MODULES */ diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 6c013f5..ac9122c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -111,7 +111,7 @@ static inline int user_space_fault(unsigned long trans_exc_code) if (trans_exc_code == 2) /* Access via secondary space, set_fs setting decides */ return current->thread.mm_segment.ar4; - if (addressing_mode == HOME_SPACE_MODE) + if (s390_user_mode == HOME_SPACE_MODE) /* User space if the access has been done via home space. */ return trans_exc_code == 3; /* @@ -163,7 +163,7 @@ static noinline void do_no_context(struct pt_regs *regs) /* Are we prepared to handle this kernel fault? */ fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); if (fixup) { - regs->psw.addr = fixup->fixup | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE; return; } @@ -628,9 +628,8 @@ static int __cpuinit pfault_cpu_notify(struct notifier_block *self, struct thread_struct *thread, *next; struct task_struct *tsk; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DEAD: - case CPU_DEAD_FROZEN: spin_lock_irq(&pfault_lock); list_for_each_entry_safe(thread, next, &pfault_list, list) { thread->pfault_wait = 0; diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 65cb06e..eeaf802 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -154,6 +154,43 @@ static inline int gup_pud_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, return 1; } +/* + * Like get_user_pages_fast() except its IRQ-safe in that it won't fall + * back to the regular GUP. + */ +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next, flags; + pgd_t *pgdp, pgd; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, + (void __user *)start, len))) + return 0; + + local_irq_save(flags); + pgdp = pgd_offset(mm, addr); + do { + pgd = *pgdp; + barrier(); + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + break; + if (!gup_pud_range(pgdp, pgd, addr, next, write, pages, &nr)) + break; + } while (pgdp++, addr = next, addr != end); + local_irq_restore(flags); + + return nr; +} + /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 6adbc08..81e596c 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -42,7 +42,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE))); unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); -static unsigned long setup_zero_pages(void) +static unsigned long __init setup_zero_pages(void) { struct cpuid cpu_id; unsigned int order; @@ -212,7 +212,7 @@ void free_initmem(void) } #ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) +void __init free_initrd_mem(unsigned long start, unsigned long end) { free_init_pages("initrd memory", start, end); } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 18df31d..b402991 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -609,8 +609,8 @@ static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits) */ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr) { - struct page *page; - unsigned long *table; + unsigned long *uninitialized_var(table); + struct page *uninitialized_var(page); unsigned int mask, bit; if (mm_has_pgste(mm)) @@ -796,7 +796,7 @@ int s390_enable_sie(void) struct mm_struct *mm, *old_mm; /* Do we have switched amode? If no, we cannot do sie */ - if (addressing_mode == HOME_SPACE_MODE) + if (s390_user_mode == HOME_SPACE_MODE) return -EINVAL; /* Do we have pgstes? if yes, we are done */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6f896e7..c22abf9 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -107,7 +107,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0)); pm_dir = pmd_offset(pu_dir, address); -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC) if (MACHINE_HAS_HPAGE && !(address & ~HPAGE_MASK) && (address + HPAGE_SIZE <= start + size) && (address >= HPAGE_SIZE)) { diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile new file mode 100644 index 0000000..90568c3 --- /dev/null +++ b/arch/s390/net/Makefile @@ -0,0 +1,4 @@ +# +# Arch-specific network modules +# +obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S new file mode 100644 index 0000000..7e45d13 --- /dev/null +++ b/arch/s390/net/bpf_jit.S @@ -0,0 +1,130 @@ +/* + * BPF Jit compiler for s390, help functions. + * + * Copyright IBM Corp. 2012 + * + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + */ +#include <linux/linkage.h> + +/* + * Calling convention: + * registers %r2, %r6-%r8, %r10-%r11, %r13, %r15 are call saved + * %r2: skb pointer + * %r3: offset parameter + * %r5: BPF A accumulator + * %r8: return address + * %r9: save register for skb pointer + * %r10: skb->data + * %r11: skb->len - skb->data_len (headlen) + * %r12: BPF X accumulator + * + * skb_copy_bits takes 4 parameters: + * %r2 = skb pointer + * %r3 = offset into skb data + * %r4 = length to copy + * %r5 = pointer to temp buffer + */ +#define SKBDATA %r8 + + /* A = *(u32 *) (skb->data+K+X) */ +ENTRY(sk_load_word_ind) + ar %r3,%r12 # offset += X + bmr %r8 # < 0 -> return with cc + + /* A = *(u32 *) (skb->data+K) */ +ENTRY(sk_load_word) + llgfr %r1,%r3 # extend offset + ahi %r3,4 # offset + 4 + clr %r11,%r3 # hlen <= offset + 4 ? + jl sk_load_word_slow + l %r5,0(%r1,%r10) # get word from skb + xr %r1,%r1 # set cc to zero + br %r8 + +sk_load_word_slow: + lgr %r9,%r2 # save %r2 + lhi %r4,4 # 4 bytes + la %r5,160(%r15) # pointer to temp buffer + brasl %r14,skb_copy_bits # get data from skb + l %r5,160(%r15) # load result from temp buffer + ltgr %r2,%r2 # set cc to (%r2 != 0) + lgr %r2,%r9 # restore %r2 + br %r8 + + /* A = *(u16 *) (skb->data+K+X) */ +ENTRY(sk_load_half_ind) + ar %r3,%r12 # offset += X + bmr %r8 # < 0 -> return with cc + + /* A = *(u16 *) (skb->data+K) */ +ENTRY(sk_load_half) + llgfr %r1,%r3 # extend offset + ahi %r3,2 # offset + 2 + clr %r11,%r3 # hlen <= offset + 2 ? + jl sk_load_half_slow + llgh %r5,0(%r1,%r10) # get half from skb + xr %r1,%r1 # set cc to zero + br %r8 + +sk_load_half_slow: + lgr %r9,%r2 # save %r2 + lhi %r4,2 # 2 bytes + la %r5,162(%r15) # pointer to temp buffer + brasl %r14,skb_copy_bits # get data from skb + xc 160(2,%r15),160(%r15) + l %r5,160(%r15) # load result from temp buffer + ltgr %r2,%r2 # set cc to (%r2 != 0) + lgr %r2,%r9 # restore %r2 + br %r8 + + /* A = *(u8 *) (skb->data+K+X) */ +ENTRY(sk_load_byte_ind) + ar %r3,%r12 # offset += X + bmr %r8 # < 0 -> return with cc + + /* A = *(u8 *) (skb->data+K) */ +ENTRY(sk_load_byte) + llgfr %r1,%r3 # extend offset + clr %r11,%r3 # hlen < offset ? + jle sk_load_byte_slow + lhi %r5,0 + ic %r5,0(%r1,%r10) # get byte from skb + xr %r1,%r1 # set cc to zero + br %r8 + +sk_load_byte_slow: + lgr %r9,%r2 # save %r2 + lhi %r4,1 # 1 bytes + la %r5,163(%r15) # pointer to temp buffer + brasl %r14,skb_copy_bits # get data from skb + xc 160(3,%r15),160(%r15) + l %r5,160(%r15) # load result from temp buffer + ltgr %r2,%r2 # set cc to (%r2 != 0) + lgr %r2,%r9 # restore %r2 + br %r8 + + /* A = (*(u8 *)(skb->data+K) & 0xf) << 2 */ +ENTRY(sk_load_byte_msh) + llgfr %r1,%r3 # extend offset + clr %r11,%r3 # hlen < offset ? + jle sk_load_byte_slow + lhi %r12,0 + ic %r12,0(%r1,%r10) # get byte from skb + nill %r12,0x0f + sll %r12,2 + xr %r1,%r1 # set cc to zero + br %r8 + +sk_load_byte_msh_slow: + lgr %r9,%r2 # save %r2 + lhi %r4,2 # 2 bytes + la %r5,162(%r15) # pointer to temp buffer + brasl %r14,skb_copy_bits # get data from skb + xc 160(3,%r15),160(%r15) + l %r12,160(%r15) # load result from temp buffer + nill %r12,0x0f + sll %r12,2 + ltgr %r2,%r2 # set cc to (%r2 != 0) + lgr %r2,%r9 # restore %r2 + br %r8 diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c new file mode 100644 index 0000000..9b355b4 --- /dev/null +++ b/arch/s390/net/bpf_jit_comp.c @@ -0,0 +1,776 @@ +/* + * BPF Jit compiler for s390. + * + * Copyright IBM Corp. 2012 + * + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + */ +#include <linux/moduleloader.h> +#include <linux/netdevice.h> +#include <linux/filter.h> +#include <asm/cacheflush.h> +#include <asm/processor.h> +#include <asm/facility.h> + +/* + * Conventions: + * %r2 = skb pointer + * %r3 = offset parameter + * %r4 = scratch register / length parameter + * %r5 = BPF A accumulator + * %r8 = return address + * %r9 = save register for skb pointer + * %r10 = skb->data + * %r11 = skb->len - skb->data_len (headlen) + * %r12 = BPF X accumulator + * %r13 = literal pool pointer + * 0(%r15) - 63(%r15) scratch memory array with BPF_MEMWORDS + */ +int bpf_jit_enable __read_mostly; + +/* + * assembly code in arch/x86/net/bpf_jit.S + */ +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; +extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[]; + +struct bpf_jit { + unsigned int seen; + u8 *start; + u8 *prg; + u8 *mid; + u8 *lit; + u8 *end; + u8 *base_ip; + u8 *ret0_ip; + u8 *exit_ip; + unsigned int off_load_word; + unsigned int off_load_half; + unsigned int off_load_byte; + unsigned int off_load_bmsh; + unsigned int off_load_iword; + unsigned int off_load_ihalf; + unsigned int off_load_ibyte; +}; + +#define BPF_SIZE_MAX 4096 /* Max size for program */ + +#define SEEN_DATAREF 1 /* might call external helpers */ +#define SEEN_XREG 2 /* ebx is used */ +#define SEEN_MEM 4 /* use mem[] for temporary storage */ +#define SEEN_RET0 8 /* pc_ret0 points to a valid return 0 */ +#define SEEN_LITERAL 16 /* code uses literals */ +#define SEEN_LOAD_WORD 32 /* code uses sk_load_word */ +#define SEEN_LOAD_HALF 64 /* code uses sk_load_half */ +#define SEEN_LOAD_BYTE 128 /* code uses sk_load_byte */ +#define SEEN_LOAD_BMSH 256 /* code uses sk_load_byte_msh */ +#define SEEN_LOAD_IWORD 512 /* code uses sk_load_word_ind */ +#define SEEN_LOAD_IHALF 1024 /* code uses sk_load_half_ind */ +#define SEEN_LOAD_IBYTE 2048 /* code uses sk_load_byte_ind */ + +#define EMIT2(op) \ +({ \ + if (jit->prg + 2 <= jit->mid) \ + *(u16 *) jit->prg = op; \ + jit->prg += 2; \ +}) + +#define EMIT4(op) \ +({ \ + if (jit->prg + 4 <= jit->mid) \ + *(u32 *) jit->prg = op; \ + jit->prg += 4; \ +}) + +#define EMIT4_DISP(op, disp) \ +({ \ + unsigned int __disp = (disp) & 0xfff; \ + EMIT4(op | __disp); \ +}) + +#define EMIT4_IMM(op, imm) \ +({ \ + unsigned int __imm = (imm) & 0xffff; \ + EMIT4(op | __imm); \ +}) + +#define EMIT4_PCREL(op, pcrel) \ +({ \ + long __pcrel = ((pcrel) >> 1) & 0xffff; \ + EMIT4(op | __pcrel); \ +}) + +#define EMIT6(op1, op2) \ +({ \ + if (jit->prg + 6 <= jit->mid) { \ + *(u32 *) jit->prg = op1; \ + *(u16 *) (jit->prg + 4) = op2; \ + } \ + jit->prg += 6; \ +}) + +#define EMIT6_DISP(op1, op2, disp) \ +({ \ + unsigned int __disp = (disp) & 0xfff; \ + EMIT6(op1 | __disp, op2); \ +}) + +#define EMIT6_IMM(op, imm) \ +({ \ + unsigned int __imm = (imm); \ + EMIT6(op | (__imm >> 16), __imm & 0xffff); \ +}) + +#define EMIT_CONST(val) \ +({ \ + unsigned int ret; \ + ret = (unsigned int) (jit->lit - jit->base_ip); \ + jit->seen |= SEEN_LITERAL; \ + if (jit->lit + 4 <= jit->end) \ + *(u32 *) jit->lit = val; \ + jit->lit += 4; \ + ret; \ +}) + +#define EMIT_FN_CONST(bit, fn) \ +({ \ + unsigned int ret; \ + ret = (unsigned int) (jit->lit - jit->base_ip); \ + if (jit->seen & bit) { \ + jit->seen |= SEEN_LITERAL; \ + if (jit->lit + 8 <= jit->end) \ + *(void **) jit->lit = fn; \ + jit->lit += 8; \ + } \ + ret; \ +}) + +static void bpf_jit_prologue(struct bpf_jit *jit) +{ + /* Save registers and create stack frame if necessary */ + if (jit->seen & SEEN_DATAREF) { + /* stmg %r8,%r15,88(%r15) */ + EMIT6(0xeb8ff058, 0x0024); + /* lgr %r14,%r15 */ + EMIT4(0xb90400ef); + /* ahi %r15,<offset> */ + EMIT4_IMM(0xa7fa0000, (jit->seen & SEEN_MEM) ? -112 : -80); + /* stg %r14,152(%r15) */ + EMIT6(0xe3e0f098, 0x0024); + } else if ((jit->seen & SEEN_XREG) && (jit->seen & SEEN_LITERAL)) + /* stmg %r12,%r13,120(%r15) */ + EMIT6(0xebcdf078, 0x0024); + else if (jit->seen & SEEN_XREG) + /* stg %r12,120(%r15) */ + EMIT6(0xe3c0f078, 0x0024); + else if (jit->seen & SEEN_LITERAL) + /* stg %r13,128(%r15) */ + EMIT6(0xe3d0f080, 0x0024); + + /* Setup literal pool */ + if (jit->seen & SEEN_LITERAL) { + /* basr %r13,0 */ + EMIT2(0x0dd0); + jit->base_ip = jit->prg; + } + jit->off_load_word = EMIT_FN_CONST(SEEN_LOAD_WORD, sk_load_word); + jit->off_load_half = EMIT_FN_CONST(SEEN_LOAD_HALF, sk_load_half); + jit->off_load_byte = EMIT_FN_CONST(SEEN_LOAD_BYTE, sk_load_byte); + jit->off_load_bmsh = EMIT_FN_CONST(SEEN_LOAD_BMSH, sk_load_byte_msh); + jit->off_load_iword = EMIT_FN_CONST(SEEN_LOAD_IWORD, sk_load_word_ind); + jit->off_load_ihalf = EMIT_FN_CONST(SEEN_LOAD_IHALF, sk_load_half_ind); + jit->off_load_ibyte = EMIT_FN_CONST(SEEN_LOAD_IBYTE, sk_load_byte_ind); + + /* Filter needs to access skb data */ + if (jit->seen & SEEN_DATAREF) { + /* l %r11,<len>(%r2) */ + EMIT4_DISP(0x58b02000, offsetof(struct sk_buff, len)); + /* s %r11,<data_len>(%r2) */ + EMIT4_DISP(0x5bb02000, offsetof(struct sk_buff, data_len)); + /* lg %r10,<data>(%r2) */ + EMIT6_DISP(0xe3a02000, 0x0004, + offsetof(struct sk_buff, data)); + } +} + +static void bpf_jit_epilogue(struct bpf_jit *jit) +{ + /* Return 0 */ + if (jit->seen & SEEN_RET0) { + jit->ret0_ip = jit->prg; + /* lghi %r2,0 */ + EMIT4(0xa7290000); + } + jit->exit_ip = jit->prg; + /* Restore registers */ + if (jit->seen & SEEN_DATAREF) + /* lmg %r8,%r15,<offset>(%r15) */ + EMIT6_DISP(0xeb8ff000, 0x0004, + (jit->seen & SEEN_MEM) ? 200 : 168); + else if ((jit->seen & SEEN_XREG) && (jit->seen & SEEN_LITERAL)) + /* lmg %r12,%r13,120(%r15) */ + EMIT6(0xebcdf078, 0x0004); + else if (jit->seen & SEEN_XREG) + /* lg %r12,120(%r15) */ + EMIT6(0xe3c0f078, 0x0004); + else if (jit->seen & SEEN_LITERAL) + /* lg %r13,128(%r15) */ + EMIT6(0xe3d0f080, 0x0004); + /* br %r14 */ + EMIT2(0x07fe); +} + +/* + * make sure we dont leak kernel information to user + */ +static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter) +{ + /* Clear temporary memory if (seen & SEEN_MEM) */ + if (jit->seen & SEEN_MEM) + /* xc 0(64,%r15),0(%r15) */ + EMIT6(0xd73ff000, 0xf000); + /* Clear X if (seen & SEEN_XREG) */ + if (jit->seen & SEEN_XREG) + /* lhi %r12,0 */ + EMIT4(0xa7c80000); + /* Clear A if the first register does not set it. */ + switch (filter[0].code) { + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: + case BPF_S_LD_W_LEN: + case BPF_S_LD_W_IND: + case BPF_S_LD_H_IND: + case BPF_S_LD_B_IND: + case BPF_S_LDX_B_MSH: + case BPF_S_LD_IMM: + case BPF_S_LD_MEM: + case BPF_S_MISC_TXA: + case BPF_S_ANC_PROTOCOL: + case BPF_S_ANC_PKTTYPE: + case BPF_S_ANC_IFINDEX: + case BPF_S_ANC_MARK: + case BPF_S_ANC_QUEUE: + case BPF_S_ANC_HATYPE: + case BPF_S_ANC_RXHASH: + case BPF_S_ANC_CPU: + case BPF_S_RET_K: + /* first instruction sets A register */ + break; + default: /* A = 0 */ + /* lhi %r5,0 */ + EMIT4(0xa7580000); + } +} + +static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, + unsigned int *addrs, int i, int last) +{ + unsigned int K; + int offset; + unsigned int mask; + + K = filter->k; + switch (filter->code) { + case BPF_S_ALU_ADD_X: /* A += X */ + jit->seen |= SEEN_XREG; + /* ar %r5,%r12 */ + EMIT2(0x1a5c); + break; + case BPF_S_ALU_ADD_K: /* A += K */ + if (!K) + break; + if (K <= 16383) + /* ahi %r5,<K> */ + EMIT4_IMM(0xa75a0000, K); + else if (test_facility(21)) + /* alfi %r5,<K> */ + EMIT6_IMM(0xc25b0000, K); + else + /* a %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5a50d000, EMIT_CONST(K)); + break; + case BPF_S_ALU_SUB_X: /* A -= X */ + jit->seen |= SEEN_XREG; + /* sr %r5,%r12 */ + EMIT2(0x1b5c); + break; + case BPF_S_ALU_SUB_K: /* A -= K */ + if (!K) + break; + if (K <= 16384) + /* ahi %r5,-K */ + EMIT4_IMM(0xa75a0000, -K); + else if (test_facility(21)) + /* alfi %r5,-K */ + EMIT6_IMM(0xc25b0000, -K); + else + /* s %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5b50d000, EMIT_CONST(K)); + break; + case BPF_S_ALU_MUL_X: /* A *= X */ + jit->seen |= SEEN_XREG; + /* msr %r5,%r12 */ + EMIT4(0xb252005c); + break; + case BPF_S_ALU_MUL_K: /* A *= K */ + if (K <= 16383) + /* mhi %r5,K */ + EMIT4_IMM(0xa75c0000, K); + else if (test_facility(34)) + /* msfi %r5,<K> */ + EMIT6_IMM(0xc2510000, K); + else + /* ms %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x7150d000, EMIT_CONST(K)); + break; + case BPF_S_ALU_DIV_X: /* A /= X */ + jit->seen |= SEEN_XREG | SEEN_RET0; + /* ltr %r12,%r12 */ + EMIT2(0x12cc); + /* jz <ret0> */ + EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg)); + /* lhi %r4,0 */ + EMIT4(0xa7480000); + /* dr %r4,%r12 */ + EMIT2(0x1d4c); + break; + case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */ + /* m %r4,<d(K)>(%r13) */ + EMIT4_DISP(0x5c40d000, EMIT_CONST(K)); + /* lr %r5,%r4 */ + EMIT2(0x1854); + break; + case BPF_S_ALU_AND_X: /* A &= X */ + jit->seen |= SEEN_XREG; + /* nr %r5,%r12 */ + EMIT2(0x145c); + break; + case BPF_S_ALU_AND_K: /* A &= K */ + if (test_facility(21)) + /* nilf %r5,<K> */ + EMIT6_IMM(0xc05b0000, K); + else + /* n %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5450d000, EMIT_CONST(K)); + break; + case BPF_S_ALU_OR_X: /* A |= X */ + jit->seen |= SEEN_XREG; + /* or %r5,%r12 */ + EMIT2(0x165c); + break; + case BPF_S_ALU_OR_K: /* A |= K */ + if (test_facility(21)) + /* oilf %r5,<K> */ + EMIT6_IMM(0xc05d0000, K); + else + /* o %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5650d000, EMIT_CONST(K)); + break; + case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ + jit->seen |= SEEN_XREG; + /* xr %r5,%r12 */ + EMIT2(0x175c); + break; + case BPF_S_ALU_LSH_X: /* A <<= X; */ + jit->seen |= SEEN_XREG; + /* sll %r5,0(%r12) */ + EMIT4(0x8950c000); + break; + case BPF_S_ALU_LSH_K: /* A <<= K */ + if (K == 0) + break; + /* sll %r5,K */ + EMIT4_DISP(0x89500000, K); + break; + case BPF_S_ALU_RSH_X: /* A >>= X; */ + jit->seen |= SEEN_XREG; + /* srl %r5,0(%r12) */ + EMIT4(0x8850c000); + break; + case BPF_S_ALU_RSH_K: /* A >>= K; */ + if (K == 0) + break; + /* srl %r5,K */ + EMIT4_DISP(0x88500000, K); + break; + case BPF_S_ALU_NEG: /* A = -A */ + /* lnr %r5,%r5 */ + EMIT2(0x1155); + break; + case BPF_S_JMP_JA: /* ip += K */ + offset = addrs[i + K] + jit->start - jit->prg; + EMIT4_PCREL(0xa7f40000, offset); + break; + case BPF_S_JMP_JGT_K: /* ip += (A > K) ? jt : jf */ + mask = 0x200000; /* jh */ + goto kbranch; + case BPF_S_JMP_JGE_K: /* ip += (A >= K) ? jt : jf */ + mask = 0xa00000; /* jhe */ + goto kbranch; + case BPF_S_JMP_JEQ_K: /* ip += (A == K) ? jt : jf */ + mask = 0x800000; /* je */ +kbranch: /* Emit compare if the branch targets are different */ + if (filter->jt != filter->jf) { + if (K <= 16383) + /* chi %r5,<K> */ + EMIT4_IMM(0xa75e0000, K); + else if (test_facility(21)) + /* clfi %r5,<K> */ + EMIT6_IMM(0xc25f0000, K); + else + /* c %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5950d000, EMIT_CONST(K)); + } +branch: if (filter->jt == filter->jf) { + if (filter->jt == 0) + break; + /* j <jt> */ + offset = addrs[i + filter->jt] + jit->start - jit->prg; + EMIT4_PCREL(0xa7f40000, offset); + break; + } + if (filter->jt != 0) { + /* brc <mask>,<jt> */ + offset = addrs[i + filter->jt] + jit->start - jit->prg; + EMIT4_PCREL(0xa7040000 | mask, offset); + } + if (filter->jf != 0) { + /* brc <mask^15>,<jf> */ + offset = addrs[i + filter->jf] + jit->start - jit->prg; + EMIT4_PCREL(0xa7040000 | (mask ^ 0xf00000), offset); + } + break; + case BPF_S_JMP_JSET_K: /* ip += (A & K) ? jt : jf */ + mask = 0x700000; /* jnz */ + /* Emit test if the branch targets are different */ + if (filter->jt != filter->jf) { + if (K > 65535) { + /* lr %r4,%r5 */ + EMIT2(0x1845); + /* n %r4,<d(K)>(%r13) */ + EMIT4_DISP(0x5440d000, EMIT_CONST(K)); + } else + /* tmll %r5,K */ + EMIT4_IMM(0xa7510000, K); + } + goto branch; + case BPF_S_JMP_JGT_X: /* ip += (A > X) ? jt : jf */ + mask = 0x200000; /* jh */ + goto xbranch; + case BPF_S_JMP_JGE_X: /* ip += (A >= X) ? jt : jf */ + mask = 0xa00000; /* jhe */ + goto xbranch; + case BPF_S_JMP_JEQ_X: /* ip += (A == X) ? jt : jf */ + mask = 0x800000; /* je */ +xbranch: /* Emit compare if the branch targets are different */ + if (filter->jt != filter->jf) { + jit->seen |= SEEN_XREG; + /* cr %r5,%r12 */ + EMIT2(0x195c); + } + goto branch; + case BPF_S_JMP_JSET_X: /* ip += (A & X) ? jt : jf */ + mask = 0x700000; /* jnz */ + /* Emit test if the branch targets are different */ + if (filter->jt != filter->jf) { + jit->seen |= SEEN_XREG; + /* lr %r4,%r5 */ + EMIT2(0x1845); + /* nr %r4,%r12 */ + EMIT2(0x144c); + } + goto branch; + case BPF_S_LD_W_ABS: /* A = *(u32 *) (skb->data+K) */ + jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_WORD; + offset = jit->off_load_word; + goto load_abs; + case BPF_S_LD_H_ABS: /* A = *(u16 *) (skb->data+K) */ + jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_HALF; + offset = jit->off_load_half; + goto load_abs; + case BPF_S_LD_B_ABS: /* A = *(u8 *) (skb->data+K) */ + jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_BYTE; + offset = jit->off_load_byte; +load_abs: if ((int) K < 0) + goto out; +call_fn: /* lg %r1,<d(function)>(%r13) */ + EMIT6_DISP(0xe310d000, 0x0004, offset); + /* l %r3,<d(K)>(%r13) */ + EMIT4_DISP(0x5830d000, EMIT_CONST(K)); + /* basr %r8,%r1 */ + EMIT2(0x0d81); + /* jnz <ret0> */ + EMIT4_PCREL(0xa7740000, (jit->ret0_ip - jit->prg)); + break; + case BPF_S_LD_W_IND: /* A = *(u32 *) (skb->data+K+X) */ + jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IWORD; + offset = jit->off_load_iword; + goto call_fn; + case BPF_S_LD_H_IND: /* A = *(u16 *) (skb->data+K+X) */ + jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IHALF; + offset = jit->off_load_ihalf; + goto call_fn; + case BPF_S_LD_B_IND: /* A = *(u8 *) (skb->data+K+X) */ + jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IBYTE; + offset = jit->off_load_ibyte; + goto call_fn; + case BPF_S_LDX_B_MSH: + /* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */ + jit->seen |= SEEN_RET0; + if ((int) K < 0) { + /* j <ret0> */ + EMIT4_PCREL(0xa7f40000, (jit->ret0_ip - jit->prg)); + break; + } + jit->seen |= SEEN_DATAREF | SEEN_LOAD_BMSH; + offset = jit->off_load_bmsh; + goto call_fn; + case BPF_S_LD_W_LEN: /* A = skb->len; */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + /* l %r5,<d(len)>(%r2) */ + EMIT4_DISP(0x58502000, offsetof(struct sk_buff, len)); + break; + case BPF_S_LDX_W_LEN: /* X = skb->len; */ + jit->seen |= SEEN_XREG; + /* l %r12,<d(len)>(%r2) */ + EMIT4_DISP(0x58c02000, offsetof(struct sk_buff, len)); + break; + case BPF_S_LD_IMM: /* A = K */ + if (K <= 16383) + /* lhi %r5,K */ + EMIT4_IMM(0xa7580000, K); + else if (test_facility(21)) + /* llilf %r5,<K> */ + EMIT6_IMM(0xc05f0000, K); + else + /* l %r5,<d(K)>(%r13) */ + EMIT4_DISP(0x5850d000, EMIT_CONST(K)); + break; + case BPF_S_LDX_IMM: /* X = K */ + jit->seen |= SEEN_XREG; + if (K <= 16383) + /* lhi %r12,<K> */ + EMIT4_IMM(0xa7c80000, K); + else if (test_facility(21)) + /* llilf %r12,<K> */ + EMIT6_IMM(0xc0cf0000, K); + else + /* l %r12,<d(K)>(%r13) */ + EMIT4_DISP(0x58c0d000, EMIT_CONST(K)); + break; + case BPF_S_LD_MEM: /* A = mem[K] */ + jit->seen |= SEEN_MEM; + /* l %r5,<K>(%r15) */ + EMIT4_DISP(0x5850f000, + (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); + break; + case BPF_S_LDX_MEM: /* X = mem[K] */ + jit->seen |= SEEN_XREG | SEEN_MEM; + /* l %r12,<K>(%r15) */ + EMIT4_DISP(0x58c0f000, + (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); + break; + case BPF_S_MISC_TAX: /* X = A */ + jit->seen |= SEEN_XREG; + /* lr %r12,%r5 */ + EMIT2(0x18c5); + break; + case BPF_S_MISC_TXA: /* A = X */ + jit->seen |= SEEN_XREG; + /* lr %r5,%r12 */ + EMIT2(0x185c); + break; + case BPF_S_RET_K: + if (K == 0) { + jit->seen |= SEEN_RET0; + if (last) + break; + /* j <ret0> */ + EMIT4_PCREL(0xa7f40000, jit->ret0_ip - jit->prg); + } else { + if (K <= 16383) + /* lghi %r2,K */ + EMIT4_IMM(0xa7290000, K); + else + /* llgf %r2,<K>(%r13) */ + EMIT6_DISP(0xe320d000, 0x0016, EMIT_CONST(K)); + /* j <exit> */ + if (last && !(jit->seen & SEEN_RET0)) + break; + EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); + } + break; + case BPF_S_RET_A: + /* llgfr %r2,%r5 */ + EMIT4(0xb9160025); + /* j <exit> */ + EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); + break; + case BPF_S_ST: /* mem[K] = A */ + jit->seen |= SEEN_MEM; + /* st %r5,<K>(%r15) */ + EMIT4_DISP(0x5050f000, + (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); + break; + case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ + jit->seen |= SEEN_XREG | SEEN_MEM; + /* st %r12,<K>(%r15) */ + EMIT4_DISP(0x50c0f000, + (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); + break; + case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + /* lhi %r5,0 */ + EMIT4(0xa7580000); + /* icm %r5,3,<d(protocol)>(%r2) */ + EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, protocol)); + break; + case BPF_S_ANC_IFINDEX: /* if (!skb->dev) return 0; + * A = skb->dev->ifindex */ + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + jit->seen |= SEEN_RET0; + /* lg %r1,<d(dev)>(%r2) */ + EMIT6_DISP(0xe3102000, 0x0004, offsetof(struct sk_buff, dev)); + /* ltgr %r1,%r1 */ + EMIT4(0xb9020011); + /* jz <ret0> */ + EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg); + /* l %r5,<d(ifindex)>(%r1) */ + EMIT4_DISP(0x58501000, offsetof(struct net_device, ifindex)); + break; + case BPF_S_ANC_MARK: /* A = skb->mark */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + /* l %r5,<d(mark)>(%r2) */ + EMIT4_DISP(0x58502000, offsetof(struct sk_buff, mark)); + break; + case BPF_S_ANC_QUEUE: /* A = skb->queue_mapping */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + /* lhi %r5,0 */ + EMIT4(0xa7580000); + /* icm %r5,3,<d(queue_mapping)>(%r2) */ + EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, queue_mapping)); + break; + case BPF_S_ANC_HATYPE: /* if (!skb->dev) return 0; + * A = skb->dev->type */ + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + jit->seen |= SEEN_RET0; + /* lg %r1,<d(dev)>(%r2) */ + EMIT6_DISP(0xe3102000, 0x0004, offsetof(struct sk_buff, dev)); + /* ltgr %r1,%r1 */ + EMIT4(0xb9020011); + /* jz <ret0> */ + EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg); + /* lhi %r5,0 */ + EMIT4(0xa7580000); + /* icm %r5,3,<d(type)>(%r1) */ + EMIT4_DISP(0xbf531000, offsetof(struct net_device, type)); + break; + case BPF_S_ANC_RXHASH: /* A = skb->rxhash */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4); + /* l %r5,<d(rxhash)>(%r2) */ + EMIT4_DISP(0x58502000, offsetof(struct sk_buff, rxhash)); + break; + case BPF_S_ANC_CPU: /* A = smp_processor_id() */ +#ifdef CONFIG_SMP + /* l %r5,<d(cpu_nr)> */ + EMIT4_DISP(0x58500000, offsetof(struct _lowcore, cpu_nr)); +#else + /* lhi %r5,0 */ + EMIT4(0xa7580000); +#endif + break; + default: /* too complex, give up */ + goto out; + } + addrs[i] = jit->prg - jit->start; + return 0; +out: + return -1; +} + +void bpf_jit_compile(struct sk_filter *fp) +{ + unsigned long size, prg_len, lit_len; + struct bpf_jit jit, cjit; + unsigned int *addrs; + int pass, i; + + if (!bpf_jit_enable) + return; + addrs = kmalloc(fp->len * sizeof(*addrs), GFP_KERNEL); + if (addrs == NULL) + return; + memset(addrs, 0, fp->len * sizeof(*addrs)); + memset(&jit, 0, sizeof(cjit)); + memset(&cjit, 0, sizeof(cjit)); + + for (pass = 0; pass < 10; pass++) { + jit.prg = jit.start; + jit.lit = jit.mid; + + bpf_jit_prologue(&jit); + bpf_jit_noleaks(&jit, fp->insns); + for (i = 0; i < fp->len; i++) { + if (bpf_jit_insn(&jit, fp->insns + i, addrs, i, + i == fp->len - 1)) + goto out; + } + bpf_jit_epilogue(&jit); + if (jit.start) { + WARN_ON(jit.prg > cjit.prg || jit.lit > cjit.lit); + if (memcmp(&jit, &cjit, sizeof(jit)) == 0) + break; + } else if (jit.prg == cjit.prg && jit.lit == cjit.lit) { + prg_len = jit.prg - jit.start; + lit_len = jit.lit - jit.mid; + size = max_t(unsigned long, prg_len + lit_len, + sizeof(struct work_struct)); + if (size >= BPF_SIZE_MAX) + goto out; + jit.start = module_alloc(size); + if (!jit.start) + goto out; + jit.prg = jit.mid = jit.start + prg_len; + jit.lit = jit.end = jit.start + prg_len + lit_len; + jit.base_ip += (unsigned long) jit.start; + jit.exit_ip += (unsigned long) jit.start; + jit.ret0_ip += (unsigned long) jit.start; + } + cjit = jit; + } + if (bpf_jit_enable > 1) { + pr_err("flen=%d proglen=%lu pass=%d image=%p\n", + fp->len, jit.end - jit.start, pass, jit.start); + if (jit.start) { + printk(KERN_ERR "JIT code:\n"); + print_fn_code(jit.start, jit.mid - jit.start); + print_hex_dump(KERN_ERR, "JIT literals:\n", + DUMP_PREFIX_ADDRESS, 16, 1, + jit.mid, jit.end - jit.mid, false); + } + } + if (jit.start) + fp->bpf_func = (void *) jit.start; +out: + kfree(addrs); +} + +static void jit_free_defer(struct work_struct *arg) +{ + module_free(NULL, arg); +} + +/* run from softirq, we must use a work_struct to call + * module_free() from process context + */ +void bpf_jit_free(struct sk_filter *fp) +{ + struct work_struct *work; + + if (fp->bpf_func == sk_run_filter) + return; + work = (struct work_struct *)fp->bpf_func; + INIT_WORK(work, jit_free_defer); + schedule_work(work); +} diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index a1e9d69..584b936 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -169,7 +169,7 @@ static ssize_t hw_interval_write(struct file *file, char const __user *buf, if (*offset) return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (val < oprofile_min_interval) oprofile_hw_interval = oprofile_min_interval; @@ -212,7 +212,7 @@ static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (val != 0) return -EINVAL; @@ -243,7 +243,7 @@ static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (val != 0 && val != 1) @@ -278,7 +278,7 @@ static ssize_t hwsampler_user_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (val != 0 && val != 1) @@ -317,7 +317,7 @@ static ssize_t timer_enabled_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (val != 0 && val != 1) diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index 2707023..637970c 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -27,6 +27,7 @@ #include <linux/reboot.h> #include <linux/elfcore.h> #include <linux/pm.h> +#include <linux/rcupdate.h> void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); @@ -50,9 +51,10 @@ void __noreturn cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) barrier(); - + rcu_idle_exit(); schedule_preempt_disabled(); } } diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S index b7cf6a5..7e605b9 100644 --- a/arch/sh/kernel/cpu/sh5/entry.S +++ b/arch/sh/kernel/cpu/sh5/entry.S @@ -933,7 +933,7 @@ ret_with_reschedule: pta restore_all, tr1 - movi _TIF_SIGPENDING, r8 + movi (_TIF_SIGPENDING|_TIF_NOTIFY_RESUME), r8 and r8, r7, r8 pta work_notifysig, tr0 bne r8, ZERO, tr0 diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index f67601c..b96489d 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -139,7 +139,7 @@ work_pending: ! r8: current_thread_info ! t: result of "tst #_TIF_NEED_RESCHED, r0" bf/s work_resched - tst #_TIF_SIGPENDING, r0 + tst #(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME), r0 work_notifysig: bt/s __restore_all mov r15, r4 diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index 15e0a16..f1ddc0d 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -48,9 +48,7 @@ void *module_alloc(unsigned long size) return NULL; ret = module_map(size); - if (!ret) - ret = ERR_PTR(-ENOMEM); - else + if (ret) memset(ret, 0, size); return ret; @@ -116,6 +114,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, v = sym->st_value + rel[i].r_addend; switch (ELF_R_TYPE(rel[i].r_info) & 0xff) { + case R_SPARC_DISP32: + v -= (Elf_Addr) location; + *loc32 = v; + break; #ifdef CONFIG_SPARC64 case R_SPARC_64: location[0] = v >> 56; @@ -128,11 +130,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, location[7] = v >> 0; break; - case R_SPARC_DISP32: - v -= (Elf_Addr) location; - *loc32 = v; - break; - case R_SPARC_WDISP19: v -= (Elf_Addr) location; *loc32 = (*loc32 & ~0x7ffff) | diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index 7a7ce390..d5e86c9 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -69,7 +69,6 @@ static inline const struct cpumask *cpumask_of_node(int node) | 1*SD_BALANCE_FORK \ | 0*SD_BALANCE_WAKE \ | 0*SD_WAKE_AFFINE \ - | 0*SD_PREFER_LOCAL \ | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ diff --git a/arch/tile/include/gxio/iorpc_trio.h b/arch/tile/include/gxio/iorpc_trio.h index 15fb779..58105c3 100644 --- a/arch/tile/include/gxio/iorpc_trio.h +++ b/arch/tile/include/gxio/iorpc_trio.h @@ -25,21 +25,23 @@ #include <linux/module.h> #include <asm/pgtable.h> -#define GXIO_TRIO_OP_ALLOC_ASIDS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1400) +#define GXIO_TRIO_OP_DEALLOC_ASID IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1400) +#define GXIO_TRIO_OP_ALLOC_ASIDS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1401) -#define GXIO_TRIO_OP_ALLOC_MEMORY_MAPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1402) +#define GXIO_TRIO_OP_ALLOC_MEMORY_MAPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1404) -#define GXIO_TRIO_OP_ALLOC_PIO_REGIONS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140e) -#define GXIO_TRIO_OP_INIT_PIO_REGION_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140f) +#define GXIO_TRIO_OP_ALLOC_PIO_REGIONS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1412) -#define GXIO_TRIO_OP_INIT_MEMORY_MAP_MMU_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1417) -#define GXIO_TRIO_OP_GET_PORT_PROPERTY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1418) -#define GXIO_TRIO_OP_CONFIG_LEGACY_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1419) -#define GXIO_TRIO_OP_CONFIG_MSI_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x141a) +#define GXIO_TRIO_OP_INIT_PIO_REGION_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1414) -#define GXIO_TRIO_OP_SET_MPS_MRS IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141c) -#define GXIO_TRIO_OP_FORCE_RC_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141d) -#define GXIO_TRIO_OP_FORCE_EP_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141e) +#define GXIO_TRIO_OP_INIT_MEMORY_MAP_MMU_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141e) +#define GXIO_TRIO_OP_GET_PORT_PROPERTY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141f) +#define GXIO_TRIO_OP_CONFIG_LEGACY_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1420) +#define GXIO_TRIO_OP_CONFIG_MSI_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1421) + +#define GXIO_TRIO_OP_SET_MPS_MRS IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1423) +#define GXIO_TRIO_OP_FORCE_RC_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1424) +#define GXIO_TRIO_OP_FORCE_EP_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1425) #define GXIO_TRIO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) #define GXIO_TRIO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 664a60e..c17de0d 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -705,6 +705,7 @@ static void stack_proc(void *arg) struct task_struct *from = current, *to = arg; to->thread.saved_task = from; + rcu_switch(from, to); switch_to(from, to, from); } diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 69f1c57..33a6a24 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -20,14 +20,6 @@ struct mm_struct; struct thread_struct { struct task_struct *saved_task; - /* - * This flag is set to 1 before calling do_fork (and analyzed in - * copy_thread) to mark that we are begin called from userspace (fork / - * vfork / clone), and reset to 0 after. It is left to 0 when called - * from kernelspace (i.e. kernel_thread() or fork_idle(), - * as of 2.6.11). - */ - int forking; struct pt_regs regs; int singlestep_syscall; void *fault_addr; @@ -58,7 +50,6 @@ struct thread_struct { #define INIT_THREAD \ { \ - .forking = 0, \ .regs = EMPTY_REGS, \ .fault_addr = NULL, \ .prev_sched = NULL, \ diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h index 40db8f7..2df313b 100644 --- a/arch/um/include/shared/common-offsets.h +++ b/arch/um/include/shared/common-offsets.h @@ -7,16 +7,6 @@ DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK); DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT); DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC); -DEFINE_STR(UM_KERN_EMERG, KERN_EMERG); -DEFINE_STR(UM_KERN_ALERT, KERN_ALERT); -DEFINE_STR(UM_KERN_CRIT, KERN_CRIT); -DEFINE_STR(UM_KERN_ERR, KERN_ERR); -DEFINE_STR(UM_KERN_WARNING, KERN_WARNING); -DEFINE_STR(UM_KERN_NOTICE, KERN_NOTICE); -DEFINE_STR(UM_KERN_INFO, KERN_INFO); -DEFINE_STR(UM_KERN_DEBUG, KERN_DEBUG); -DEFINE_STR(UM_KERN_CONT, KERN_CONT); - DEFINE(UM_ELF_CLASS, ELF_CLASS); DEFINE(UM_ELFCLASS32, ELFCLASS32); DEFINE(UM_ELFCLASS64, ELFCLASS64); diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index 4fa82c0..cef0685 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -26,6 +26,17 @@ extern void panic(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); +/* Requires preincluding include/linux/kern_levels.h */ +#define UM_KERN_EMERG KERN_EMERG +#define UM_KERN_ALERT KERN_ALERT +#define UM_KERN_CRIT KERN_CRIT +#define UM_KERN_ERR KERN_ERR +#define UM_KERN_WARNING KERN_WARNING +#define UM_KERN_NOTICE KERN_NOTICE +#define UM_KERN_INFO KERN_INFO +#define UM_KERN_DEBUG KERN_DEBUG +#define UM_KERN_CONT KERN_CONT + #ifdef UML_CONFIG_PRINTK extern int printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 6cade93..8c82786 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -39,34 +39,21 @@ void flush_thread(void) void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) { + get_safe_registers(regs->regs.gp, regs->regs.fp); PT_REGS_IP(regs) = eip; PT_REGS_SP(regs) = esp; -} -EXPORT_SYMBOL(start_thread); - -static long execve1(const char *file, - const char __user *const __user *argv, - const char __user *const __user *env) -{ - long error; - - error = do_execve(file, argv, env, ¤t->thread.regs); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; + current->ptrace &= ~PT_DTRACE; #ifdef SUBARCH_EXECVE1 - SUBARCH_EXECVE1(¤t->thread.regs.regs); + SUBARCH_EXECVE1(regs->regs); #endif - task_unlock(current); - } - return error; } +EXPORT_SYMBOL(start_thread); long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env) { long err; - err = execve1(file, argv, env); + err = do_execve(file, argv, env, ¤t->thread.regs); if (!err) UML_LONGJMP(current->thread.exec_buf, 1); return err; @@ -81,7 +68,7 @@ long sys_execve(const char __user *file, const char __user *const __user *argv, filename = getname(file); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = execve1(filename, argv, env); + error = do_execve(filename, argv, env, ¤t->thread.regs); putname(filename); out: return error; diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 57fc702..c5f5afa 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -181,11 +181,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, struct pt_regs *regs) { void (*handler)(void); + int kthread = current->flags & PF_KTHREAD; int ret = 0; p->thread = (struct thread_struct) INIT_THREAD; - if (current->thread.forking) { + if (!kthread) { memcpy(&p->thread.regs.regs, ®s->regs, sizeof(p->thread.regs.regs)); PT_REGS_SET_SYSCALL_RETURN(&p->thread.regs, 0); @@ -195,8 +196,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, handler = fork_handler; arch_copy_thread(¤t->thread.arch, &p->thread.arch); - } - else { + } else { get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); p->thread.request.u.thread = current->thread.request.u.thread; handler = new_thread_handler; @@ -204,7 +204,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, new_thread(task_stack_page(p), &p->thread.switch_buf, handler); - if (current->thread.forking) { + if (!kthread) { clear_flushed_tls(p); /* diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 7362d58..cc9c235 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -22,9 +22,13 @@ static void handle_signal(struct pt_regs *regs, unsigned long signr, struct k_sigaction *ka, siginfo_t *info) { sigset_t *oldset = sigmask_to_save(); + int singlestep = 0; unsigned long sp; int err; + if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) + singlestep = 1; + /* Did we come from a system call? */ if (PT_REGS_SYSCALL_NR(regs) >= 0) { /* If so, check system call restarting.. */ @@ -61,7 +65,7 @@ static void handle_signal(struct pt_regs *regs, unsigned long signr, if (err) force_sigsegv(signr, current); else - signal_delivered(signr, info, ka, regs, 0); + signal_delivered(signr, info, ka, regs, singlestep); } static int kern_do_signal(struct pt_regs *regs) diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index f958cb8..a4c6d8e 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -17,25 +17,25 @@ long sys_fork(void) { - long ret; - - current->thread.forking = 1; - ret = do_fork(SIGCHLD, UPT_SP(¤t->thread.regs.regs), + return do_fork(SIGCHLD, UPT_SP(¤t->thread.regs.regs), ¤t->thread.regs, 0, NULL, NULL); - current->thread.forking = 0; - return ret; } long sys_vfork(void) { - long ret; - - current->thread.forking = 1; - ret = do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, UPT_SP(¤t->thread.regs.regs), ¤t->thread.regs, 0, NULL, NULL); - current->thread.forking = 0; - return ret; +} + +long sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid) +{ + if (!newsp) + newsp = UPT_SP(¤t->thread.regs.regs); + + return do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, + child_tid); } long old_mmap(unsigned long addr, unsigned long len, diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index f602385..0748fe0 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -114,7 +114,7 @@ static void deliver_alarm(void) skew += this_tick - last_tick; while (skew >= one_tick) { - alarm_handler(SIGVTALRM, NULL); + alarm_handler(SIGVTALRM, NULL, NULL); skew -= one_tick; } diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules index d50270d..15889df 100644 --- a/arch/um/scripts/Makefile.rules +++ b/arch/um/scripts/Makefile.rules @@ -8,7 +8,7 @@ USER_OBJS += $(filter %_user.o,$(obj-y) $(obj-m) $(USER_SINGLE_OBJS)) USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file)) $(USER_OBJS:.o=.%): \ - c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include user.h $(CFLAGS_$(basetarget).o) + c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include $(srctree)/include/linux/kern_levels.h -include user.h $(CFLAGS_$(basetarget).o) # These are like USER_OBJS but filter USER_CFLAGS through unprofile instead of # using it directly. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8ec3a1a..9436670 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -7,11 +7,13 @@ config 64BIT Say no to build a 32-bit kernel - formerly known as i386 config X86_32 - def_bool !64BIT + def_bool y + depends on !64BIT select CLKSRC_I8253 config X86_64 - def_bool 64BIT + def_bool y + depends on 64BIT select X86_DEV_DMA_OPS ### Arch settings @@ -36,6 +38,7 @@ config X86 select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FENTRY if X86_64 select HAVE_C_RECORDMCOUNT select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER @@ -60,6 +63,8 @@ config X86 select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS select HAVE_PERF_EVENTS_NMI + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP select ANON_INODES select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386 select HAVE_CMPXCHG_LOCAL if !M386 @@ -97,9 +102,12 @@ config X86 select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER + select HAVE_RCU_USER_QS if X86_64 + select HAVE_IRQ_TIME_ACCOUNTING config INSTRUCTION_DECODER - def_bool (KPROBES || PERF_EVENTS || UPROBES) + def_bool y + depends on KPROBES || PERF_EVENTS || UPROBES config OUTPUT_FORMAT string @@ -127,13 +135,15 @@ config SBUS bool config NEED_DMA_MAP_STATE - def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG) + def_bool y + depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG config NEED_SG_DMA_LENGTH def_bool y config GENERIC_ISA_DMA - def_bool ISA_DMA_API + def_bool y + depends on ISA_DMA_API config GENERIC_BUG def_bool y @@ -150,13 +160,16 @@ config GENERIC_GPIO bool config ARCH_MAY_HAVE_PC_FDC - def_bool ISA_DMA_API + def_bool y + depends on ISA_DMA_API config RWSEM_GENERIC_SPINLOCK - def_bool !X86_XADD + def_bool y + depends on !X86_XADD config RWSEM_XCHGADD_ALGORITHM - def_bool X86_XADD + def_bool y + depends on X86_XADD config GENERIC_CALIBRATE_DELAY def_bool y @@ -746,13 +759,14 @@ config SWIOTLB def_bool y if X86_64 ---help--- Support for software bounce buffers used on x86-64 systems - which don't have a hardware IOMMU (e.g. the current generation - of Intel's x86-64 CPUs). Using this PCI devices which can only - access 32-bits of memory can be used on systems with more than - 3 GB of memory. If unsure, say Y. + which don't have a hardware IOMMU. Using this PCI devices + which can only access 32-bits of memory can be used on systems + with more than 3 GB of memory. + If unsure, say Y. config IOMMU_HELPER - def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU) + def_bool y + depends on CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" @@ -796,17 +810,6 @@ config SCHED_MC making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. -config IRQ_TIME_ACCOUNTING - bool "Fine granularity task level IRQ time accounting" - default n - ---help--- - Select this option to enable fine granularity task irq time - accounting. This is done by reading a timestamp on each - transitions between softirq and hardirq state, so there can be a - small performance impact. - - If in doubt, say N here. - source "kernel/Kconfig.preempt" config X86_UP_APIC @@ -871,6 +874,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS config X86_MCE bool "Machine Check / overheating reporting" + default y ---help--- Machine Check support allows the processor to notify the kernel if it detects a problem (e.g. overheating, data corruption). @@ -982,25 +986,25 @@ config X86_REBOOTFIXUPS Say N otherwise. config MICROCODE - tristate "/dev/cpu/microcode - microcode support" + tristate "CPU microcode loading support" select FW_LOADER ---help--- + If you say Y here, you will be able to update the microcode on certain Intel and AMD processors. The Intel support is for the - IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, - Pentium 4, Xeon etc. The AMD support is for family 0x10 and - 0x11 processors, e.g. Opteron, Phenom and Turion 64 Ultra. - You will obviously need the actual microcode binary data itself - which is not shipped with the Linux kernel. + IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, + Xeon etc. The AMD support is for families 0x10 and later. You will + obviously need the actual microcode binary data itself which is not + shipped with the Linux kernel. This option selects the general module only, you need to select at least one vendor specific module as well. - To compile this driver as a module, choose M here: the - module will be called microcode. + To compile this driver as a module, choose M here: the module + will be called microcode. config MICROCODE_INTEL - bool "Intel microcode patch loading support" + bool "Intel microcode loading support" depends on MICROCODE default MICROCODE select FW_LOADER @@ -1013,7 +1017,7 @@ config MICROCODE_INTEL <http://www.urbanmyth.org/microcode/>. config MICROCODE_AMD - bool "AMD microcode patch loading support" + bool "AMD microcode loading support" depends on MICROCODE select FW_LOADER ---help--- @@ -1159,10 +1163,12 @@ config X86_PAE consumes more pagetable space per process. config ARCH_PHYS_ADDR_T_64BIT - def_bool X86_64 || X86_PAE + def_bool y + depends on X86_64 || X86_PAE config ARCH_DMA_ADDR_T_64BIT - def_bool X86_64 || HIGHMEM64G + def_bool y + depends on X86_64 || HIGHMEM64G config DIRECT_GBPAGES bool "Enable 1GB pages for kernel pagetables" if EXPERT @@ -1285,8 +1291,8 @@ config ARCH_SELECT_MEMORY_MODEL depends on ARCH_SPARSEMEM_ENABLE config ARCH_MEMORY_PROBE - def_bool X86_64 - depends on MEMORY_HOTPLUG + def_bool y + depends on X86_64 && MEMORY_HOTPLUG config ARCH_PROC_KCORE_TEXT def_bool y @@ -1975,7 +1981,6 @@ config PCI_MMCONFIG config PCI_CNB20LE_QUIRK bool "Read CNB20LE Host Bridge Windows" if EXPERT - default n depends on PCI && EXPERIMENTAL help Read the PCI windows out of the CNB20LE host bridge. This allows @@ -2186,18 +2191,18 @@ config COMPAT depends on IA32_EMULATION || X86_X32 select ARCH_WANT_OLD_COMPAT_IPC +if COMPAT config COMPAT_FOR_U64_ALIGNMENT - def_bool COMPAT - depends on X86_64 + def_bool y config SYSVIPC_COMPAT def_bool y - depends on COMPAT && SYSVIPC + depends on SYSVIPC config KEYS_COMPAT - bool - depends on COMPAT && KEYS - default y + def_bool y + depends on KEYS +endif endmenu diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 706e12e..f3b86d0 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -306,7 +306,8 @@ config X86_INTERNODE_CACHE_SHIFT default X86_L1_CACHE_SHIFT config X86_CMPXCHG - def_bool X86_64 || (X86_32 && !M386) + def_bool y + depends on X86_64 || (X86_32 && !M386) config X86_L1_CACHE_SHIFT int @@ -317,7 +318,7 @@ config X86_L1_CACHE_SHIFT config X86_XADD def_bool y - depends on X86_64 || !M386 + depends on !M386 config X86_PPRO_FENCE bool "PentiumPro memory ordering errata workaround" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 682e9c2..474ca35 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -142,7 +142,7 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) -archscripts: +archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs ### diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e398bb5..8a84501 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -28,6 +28,9 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \ $(obj)/piggy.o +$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone +$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone + ifeq ($(CONFIG_EFI_STUB), y) VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o endif diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index b3e0227..c760e07 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -276,8 +276,9 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, nr_gops = size / sizeof(void *); for (i = 0; i < nr_gops; i++) { struct efi_graphics_output_mode_info *info; - efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; - void *pciio; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy; void *h = gop_handle[i]; status = efi_call_phys3(sys_table->boottime->handle_protocol, @@ -285,19 +286,21 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, if (status != EFI_SUCCESS) continue; - efi_call_phys3(sys_table->boottime->handle_protocol, - h, &pciio_proto, &pciio); + status = efi_call_phys3(sys_table->boottime->handle_protocol, + h, &conout_proto, &dummy); + + if (status == EFI_SUCCESS) + conout_found = true; status = efi_call_phys4(gop->query_mode, gop, gop->mode->mode, &size, &info); - if (status == EFI_SUCCESS && (!first_gop || pciio)) { + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* - * Apple provide GOPs that are not backed by - * real hardware (they're used to handle - * multiple displays). The workaround is to - * search for a GOP implementing the PCIIO - * protocol, and if one isn't found, to just - * fallback to the first GOP. + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. */ width = info->horizontal_resolution; height = info->vertical_resolution; @@ -308,10 +311,10 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, pixels_per_scan_line = info->pixels_per_scan_line; /* - * Once we've found a GOP supporting PCIIO, + * Once we've found a GOP supporting ConOut, * don't bother looking any further. */ - if (pciio) + if (conout_found) break; first_gop = gop; @@ -328,7 +331,6 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; - si->lfb_size = fb_size; si->pages = 1; if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { @@ -376,6 +378,10 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, si->rsvd_pos = 0; } + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; + free_handle: efi_call_phys1(sys_table->boottime->free_pool, gop_handle); return status; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 3b6e156..e5b0a8f 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -14,6 +14,10 @@ #define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT) #define EFI_READ_CHUNK_SIZE (1024 * 1024) +#define EFI_CONSOLE_OUT_DEVICE_GUID \ + EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ + 0x3f, 0xc1, 0x4d) + #define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 #define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1 #define PIXEL_BIT_MASK 2 diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b4e15dd..2a01744 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -32,10 +32,6 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define SVGA_MODE ASK_VGA #endif -#ifndef RAMDISK -#define RAMDISK 0 -#endif - #ifndef ROOT_RDONLY #define ROOT_RDONLY 1 #endif diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 119db67..5598547 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -8,6 +8,8 @@ CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y @@ -34,8 +36,6 @@ CONFIG_SGI_PARTITION=y CONFIG_SUN_PARTITION=y CONFIG_KARMA_PARTITION=y CONFIG_EFI_PARTITION=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y @@ -144,8 +144,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y @@ -231,8 +229,6 @@ CONFIG_SND_HRTIMER=y CONFIG_SND_HDA_INTEL=y CONFIG_SND_HDA_HWDEP=y CONFIG_HIDRAW=y -CONFIG_HID_PID=y -CONFIG_USB_HIDDEV=y CONFIG_HID_GYRATION=y CONFIG_LOGITECH_FF=y CONFIG_HID_NTRIG=y @@ -243,11 +239,11 @@ CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y CONFIG_HID_TOPSEED=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set @@ -262,10 +258,9 @@ CONFIG_RTC_CLASS=y CONFIG_DMADEVICES=y CONFIG_EEEPC_LAPTOP=y CONFIG_EFI_VARS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set @@ -280,7 +275,6 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y @@ -299,13 +293,11 @@ CONFIG_DEBUG_KERNEL=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_STACK_USAGE=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set -CONFIG_DEBUG_NX_TEST=m CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y CONFIG_KEYS_DEBUG_PROC_KEYS=y @@ -316,4 +308,3 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_CRYPTO_AES_586=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC_T10DIF=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 76eb290..671524d 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -8,6 +8,8 @@ CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y CONFIG_CGROUP_FREEZER=y @@ -34,8 +36,6 @@ CONFIG_SGI_PARTITION=y CONFIG_SUN_PARTITION=y CONFIG_KARMA_PARTITION=y CONFIG_EFI_PARTITION=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_CALGARY_IOMMU=y CONFIG_NR_CPUS=64 @@ -144,8 +144,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_BLK_DEV_SR_VENDOR=y @@ -227,8 +225,6 @@ CONFIG_SND_HRTIMER=y CONFIG_SND_HDA_INTEL=y CONFIG_SND_HDA_HWDEP=y CONFIG_HIDRAW=y -CONFIG_HID_PID=y -CONFIG_USB_HIDDEV=y CONFIG_HID_GYRATION=y CONFIG_LOGITECH_FF=y CONFIG_HID_NTRIG=y @@ -239,11 +235,11 @@ CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y CONFIG_HID_TOPSEED=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set @@ -262,10 +258,9 @@ CONFIG_AMD_IOMMU_STATS=y CONFIG_INTEL_IOMMU=y # CONFIG_INTEL_IOMMU_DEFAULT_ON is not set CONFIG_EFI_VARS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set @@ -280,7 +275,6 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y @@ -298,13 +292,11 @@ CONFIG_DEBUG_KERNEL=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_STACK_USAGE=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set -CONFIG_DEBUG_NX_TEST=m CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y CONFIG_KEYS_DEBUG_PROC_KEYS=y @@ -314,4 +306,3 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC_T10DIF=y diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 673ac9b..8c77c64 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -162,7 +162,8 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, } seg = get_fs(); set_fs(KERNEL_DS); - ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp); + ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss, regs->sp); set_fs(seg); if (ret >= 0 && uoss_ptr) { if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t))) @@ -250,7 +251,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, get_user_ex(tmp, &sc->fpstate); buf = compat_ptr(tmp); - err |= restore_i387_xstate_ia32(buf); + err |= restore_xstate_sig(buf, 1); get_user_ex(*pax, &sc->ax); } get_user_catch(err); @@ -361,7 +362,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, */ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, - void **fpstate) + void __user **fpstate) { unsigned long sp; @@ -381,9 +382,12 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, sp = (unsigned long) ka->sa.sa_restorer; if (used_math()) { - sp = sp - sig_xstate_ia32_size; - *fpstate = (struct _fpstate_ia32 *) sp; - if (save_i387_xstate_ia32(*fpstate) < 0) + unsigned long fx_aligned, math_size; + + sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size); + *fpstate = (struct _fpstate_ia32 __user *) sp; + if (save_xstate_sig(*fpstate, (void __user *)fx_aligned, + math_size) < 0) return (void __user *) -1L; } @@ -448,7 +452,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, * These are actually not used anymore, but left because some * gdb versions depend on them as a marker. */ - put_user_ex(*((u64 *)&code), (u64 *)frame->retcode); + put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); } put_user_catch(err); if (err) @@ -529,7 +533,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * Not actually used anymore, but left because some gdb * versions need it. */ - put_user_ex(*((u64 *)&code), (u64 *)frame->retcode); + put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); } put_user_catch(err); if (err) diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 4540bec..c5b938d 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -287,7 +287,7 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act, return ret; } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, +asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, int options) { return compat_sys_wait4(pid, stat_addr, options, NULL); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 7078068..444704c 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -60,7 +60,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, void *text, void *text_end); extern void alternatives_smp_module_del(struct module *mod); -extern void alternatives_smp_switch(int smp); +extern void alternatives_enable_smp(void); extern int alternatives_text_reserved(void *start, void *end); extern bool skip_smp_alternatives; #else @@ -68,7 +68,7 @@ static inline void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, void *text, void *text_end) {} static inline void alternatives_smp_module_del(struct module *mod) {} -static inline void alternatives_smp_switch(int smp) {} +static inline void alternatives_enable_smp(void) {} static inline int alternatives_text_reserved(void *start, void *end) { return 0; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 72f5009..6dfd019 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -355,7 +355,7 @@ static int test_bit(int nr, const volatile unsigned long *addr); */ static inline unsigned long __ffs(unsigned long word) { - asm("bsf %1,%0" + asm("rep; bsf %1,%0" : "=r" (word) : "rm" (word)); return word; @@ -369,7 +369,7 @@ static inline unsigned long __ffs(unsigned long word) */ static inline unsigned long ffz(unsigned long word) { - asm("bsf %1,%0" + asm("rep; bsf %1,%0" : "=r" (word) : "r" (~word)); return word; @@ -417,10 +417,9 @@ static inline int ffs(int x) * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ - long tmp = -1; asm("bsfl %1,%0" : "=r" (r) - : "rm" (x), "0" (tmp)); + : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" @@ -459,10 +458,9 @@ static inline int fls(int x) * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ - long tmp = -1; asm("bsrl %1,%0" : "=r" (r) - : "rm" (x), "0" (tmp)); + : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" @@ -490,13 +488,13 @@ static inline int fls(int x) #ifdef CONFIG_X86_64 static __always_inline int fls64(__u64 x) { - long bitpos = -1; + int bitpos = -1; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ - asm("bsrq %1,%0" + asm("bsrq %1,%q0" : "+r" (bitpos) : "rm" (x)); return bitpos + 1; diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index a9e3a74..7f8422a 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -49,38 +49,36 @@ For 32-bit we have the following conventions - kernel is built with #include "dwarf2.h" /* - * 64-bit system call stack frame layout defines and helpers, for - * assembly code (note that the seemingly unnecessary parentheses - * are to prevent cpp from inserting spaces in expressions that get - * passed to macros): + * 64-bit system call stack frame layout defines and helpers, + * for assembly code: */ -#define R15 (0) -#define R14 (8) -#define R13 (16) -#define R12 (24) -#define RBP (32) -#define RBX (40) +#define R15 0 +#define R14 8 +#define R13 16 +#define R12 24 +#define RBP 32 +#define RBX 40 /* arguments: interrupts/non tracing syscalls only save up to here: */ -#define R11 (48) -#define R10 (56) -#define R9 (64) -#define R8 (72) -#define RAX (80) -#define RCX (88) -#define RDX (96) -#define RSI (104) -#define RDI (112) -#define ORIG_RAX (120) /* + error_code */ +#define R11 48 +#define R10 56 +#define R9 64 +#define R8 72 +#define RAX 80 +#define RCX 88 +#define RDX 96 +#define RSI 104 +#define RDI 112 +#define ORIG_RAX 120 /* + error_code */ /* end of arguments */ /* cpu exception frame or undefined in case of fast syscall: */ -#define RIP (128) -#define CS (136) -#define EFLAGS (144) -#define RSP (152) -#define SS (160) +#define RIP 128 +#define CS 136 +#define EFLAGS 144 +#define RSP 152 +#define SS 160 #define ARGOFFSET R11 #define SWFRAME ORIG_RAX diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 6b7ee5f..16cae42 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -97,6 +97,7 @@ #define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF (3*32+28) /* APERFMPERF */ +#define X86_FEATURE_EAGER_FPU (3*32+29) /* "eagerfpu" Non lazy FPU restore */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ @@ -209,6 +210,7 @@ #define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -299,12 +301,14 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) +#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) #define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) +#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 75f4c6d..92f3c6e 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -12,6 +12,7 @@ #include <linux/kernel_stat.h> #include <linux/regset.h> +#include <linux/compat.h> #include <linux/slab.h> #include <asm/asm.h> #include <asm/cpufeature.h> @@ -21,42 +22,74 @@ #include <asm/uaccess.h> #include <asm/xsave.h> -extern unsigned int sig_xstate_size; +#ifdef CONFIG_X86_64 +# include <asm/sigcontext32.h> +# include <asm/user32.h> +int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + compat_sigset_t *set, struct pt_regs *regs); +int ia32_setup_frame(int sig, struct k_sigaction *ka, + compat_sigset_t *set, struct pt_regs *regs); +#else +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct +# define ia32_setup_frame __setup_frame +# define ia32_setup_rt_frame __setup_rt_frame +#endif + +extern unsigned int mxcsr_feature_mask; extern void fpu_init(void); +extern void eager_fpu_init(void); DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); +extern void convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk); +extern void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env); + extern user_regset_active_fn fpregs_active, xfpregs_active; extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, xstateregs_get; extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, xstateregs_set; - /* * xstateregs_active == fpregs_active. Please refer to the comment * at the definition of fpregs_active. */ #define xstateregs_active fpregs_active -extern struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -extern unsigned int sig_xstate_ia32_size; -extern struct _fpx_sw_bytes fx_sw_reserved_ia32; -struct _fpstate_ia32; -struct _xstate_ia32; -extern int save_i387_xstate_ia32(void __user *buf); -extern int restore_i387_xstate_ia32(void __user *buf); -#endif - #ifdef CONFIG_MATH_EMULATION +# define HAVE_HWFP (boot_cpu_data.hard_math) extern void finit_soft_fpu(struct i387_soft_struct *soft); #else +# define HAVE_HWFP 1 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} #endif +static inline int is_ia32_compat_frame(void) +{ + return config_enabled(CONFIG_IA32_EMULATION) && + test_thread_flag(TIF_IA32); +} + +static inline int is_ia32_frame(void) +{ + return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); +} + +static inline int is_x32_frame(void) +{ + return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); +} + #define X87_FSW_ES (1 << 7) /* Exception Summary */ +static __always_inline __pure bool use_eager_fpu(void) +{ + return static_cpu_has(X86_FEATURE_EAGER_FPU); +} + static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); @@ -72,6 +105,13 @@ static __always_inline __pure bool use_fxsr(void) return static_cpu_has(X86_FEATURE_FXSR); } +static inline void fx_finit(struct i387_fxsave_struct *fx) +{ + memset(fx, 0, xstate_size); + fx->cwd = 0x37f; + fx->mxcsr = MXCSR_DEFAULT; +} + extern void __sanitize_i387_state(struct task_struct *); static inline void sanitize_i387_state(struct task_struct *tsk) @@ -81,131 +121,88 @@ static inline void sanitize_i387_state(struct task_struct *tsk) __sanitize_i387_state(tsk); } -#ifdef CONFIG_X86_64 -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) +#define check_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +static inline int fsave_user(struct i387_fsave_struct __user *fx) { - int err; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxrstorq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "m" (*fx), "0" (0)); -#else - asm volatile("1: rex64/fxrstor (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err) - : [fx] "R" (fx), "m" (*fx), "0" (0)); -#endif - return err; + return check_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int fxsave_user(struct i387_fxsave_struct __user *fx) { - int err; + if (config_enabled(CONFIG_X86_32)) + return check_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return check_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - /* - * Clear the bytes not touched by the fxsave and reserved - * for the SW usage. - */ - err = __clear_user(&fx->sw_reserved, - sizeof(struct _fpx_sw_bytes)); - if (unlikely(err)) - return -EFAULT; - - /* See comment in fxsave() below. */ -#ifdef CONFIG_AS_FXSAVEQ - asm volatile("1: fxsaveq %[fx]\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), [fx] "=m" (*fx) - : "0" (0)); -#else - asm volatile("1: rex64/fxsave (%[fx])\n\t" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl $-1,%[err]\n" - " jmp 2b\n" - ".previous\n" - _ASM_EXTABLE(1b, 3b) - : [err] "=r" (err), "=m" (*fx) - : [fx] "R" (fx), "0" (0)); -#endif - if (unlikely(err) && - __clear_user(fx, sizeof(struct i387_fxsave_struct))) - err = -EFAULT; - /* No need to clear here because the caller clears USED_MATH */ - return err; + /* See comment in fpu_fxsave() below. */ + return check_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); } -static inline void fpu_fxsave(struct fpu *fpu) +static inline int fxrstor_checking(struct i387_fxsave_struct *fx) { - /* Using "rex64; fxsave %0" is broken because, if the memory operand - uses any extended registers for addressing, a second REX prefix - will be generated (to the assembler, rex64 followed by semicolon - is a separate instruction), and hence the 64-bitness is lost. */ + if (config_enabled(CONFIG_X86_32)) + return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); -#ifdef CONFIG_AS_FXSAVEQ - /* Using "fxsaveq %0" would be the ideal choice, but is only supported - starting with gas 2.16. */ - __asm__ __volatile__("fxsaveq %0" - : "=m" (fpu->state->fxsave)); -#else - /* Using, as a workaround, the properly prefixed form below isn't - accepted by any binutils version so far released, complaining that - the same type of prefix is used twice if an extended register is - needed for addressing (fix submitted to mainline 2005-11-21). - asm volatile("rex64/fxsave %0" - : "=m" (fpu->state->fxsave)); - This, however, we can work around by forcing the compiler to select - an addressing mode that doesn't require extended registers. */ - asm volatile("rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); -#endif + /* See comment in fpu_fxsave() below. */ + return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), + "m" (*fx)); } -#else /* CONFIG_X86_32 */ - -/* perform fxrstor iff the processor has extended states, otherwise frstor */ -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) +static inline int frstor_checking(struct i387_fsave_struct *fx) { - /* - * The "nop" is needed to make the instructions the same - * length. - */ - alternative_input( - "nop ; frstor %1", - "fxrstor %1", - X86_FEATURE_FXSR, - "m" (*fx)); - - return 0; + return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void fpu_fxsave(struct fpu *fpu) { - asm volatile("fxsave %[fx]" - : [fx] "=m" (fpu->state->fxsave)); + if (config_enabled(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave)); + else { + /* Using "rex64; fxsave %0" is broken because, if the memory + * operand uses any extended registers for addressing, a second + * REX prefix will be generated (to the assembler, rex64 + * followed by semicolon is a separate instruction), and hence + * the 64-bitness is lost. + * + * Using "fxsaveq %0" would be the ideal choice, but is only + * supported starting with gas 2.16. + * + * Using, as a workaround, the properly prefixed form below + * isn't accepted by any binutils version so far released, + * complaining that the same type of prefix is used twice if + * an extended register is needed for addressing (fix submitted + * to mainline 2005-11-21). + * + * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave)); + * + * This, however, we can work around by forcing the compiler to + * select an addressing mode that doesn't require extended + * registers. + */ + asm volatile( "rex64/fxsave (%[fx])" + : "=m" (fpu->state->fxsave) + : [fx] "R" (&fpu->state->fxsave)); + } } -#endif /* CONFIG_X86_64 */ - /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact. @@ -248,17 +245,14 @@ static inline int __save_init_fpu(struct task_struct *tsk) return fpu_save_init(&tsk->thread.fpu); } -static inline int fpu_fxrstor_checking(struct fpu *fpu) -{ - return fxrstor_checking(&fpu->state->fxsave); -} - static inline int fpu_restore_checking(struct fpu *fpu) { if (use_xsave()) - return fpu_xrstor_checking(fpu); + return fpu_xrstor_checking(&fpu->state->xsave); + else if (use_fxsr()) + return fxrstor_checking(&fpu->state->fxsave); else - return fpu_fxrstor_checking(fpu); + return frstor_checking(&fpu->state->fsave); } static inline int restore_fpu_checking(struct task_struct *tsk) @@ -310,15 +304,52 @@ static inline void __thread_set_has_fpu(struct task_struct *tsk) static inline void __thread_fpu_end(struct task_struct *tsk) { __thread_clear_has_fpu(tsk); - stts(); + if (!use_eager_fpu()) + stts(); } static inline void __thread_fpu_begin(struct task_struct *tsk) { - clts(); + if (!use_eager_fpu()) + clts(); __thread_set_has_fpu(tsk); } +static inline void __drop_fpu(struct task_struct *tsk) +{ + if (__thread_has_fpu(tsk)) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + __thread_fpu_end(tsk); + } +} + +static inline void drop_fpu(struct task_struct *tsk) +{ + /* + * Forget coprocessor state.. + */ + preempt_disable(); + tsk->fpu_counter = 0; + __drop_fpu(tsk); + clear_used_math(); + preempt_enable(); +} + +static inline void drop_init_fpu(struct task_struct *tsk) +{ + if (!use_eager_fpu()) + drop_fpu(tsk); + else { + if (use_xsave()) + xrstor_state(init_xstate_buf, -1); + else + fxrstor_checking(&init_xstate_buf->i387); + } +} + /* * FPU state switching for scheduling. * @@ -352,7 +383,12 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta { fpu_switch_t fpu; - fpu.preload = tsk_used_math(new) && new->fpu_counter > 5; + /* + * If the task has used the math, pre-load the FPU on xsave processors + * or if the past 5 consecutive context-switches used math. + */ + fpu.preload = tsk_used_math(new) && (use_eager_fpu() || + new->fpu_counter > 5); if (__thread_has_fpu(old)) { if (!__save_init_fpu(old)) cpu = ~0; @@ -364,14 +400,14 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta new->fpu_counter++; __thread_set_has_fpu(new); prefetch(new->thread.fpu.state); - } else + } else if (!use_eager_fpu()) stts(); } else { old->fpu_counter = 0; old->thread.fpu.last_cpu = ~0; if (fpu.preload) { new->fpu_counter++; - if (fpu_lazy_restore(new, cpu)) + if (!use_eager_fpu() && fpu_lazy_restore(new, cpu)) fpu.preload = 0; else prefetch(new->thread.fpu.state); @@ -391,44 +427,40 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) { if (fpu.preload) { if (unlikely(restore_fpu_checking(new))) - __thread_fpu_end(new); + drop_init_fpu(new); } } /* * Signal frame handlers... */ -extern int save_i387_xstate(void __user *buf); -extern int restore_i387_xstate(void __user *buf); +extern int save_xstate_sig(void __user *buf, void __user *fx, int size); +extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size); -static inline void __clear_fpu(struct task_struct *tsk) +static inline int xstate_sigframe_size(void) { - if (__thread_has_fpu(tsk)) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - __thread_fpu_end(tsk); + return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; +} + +static inline int restore_xstate_sig(void __user *buf, int ia32_frame) +{ + void __user *buf_fx = buf; + int size = xstate_sigframe_size(); + + if (ia32_frame && use_fxsr()) { + buf_fx = buf + sizeof(struct i387_fsave_struct); + size += sizeof(struct i387_fsave_struct); } + + return __restore_xstate_sig(buf, buf_fx, size); } /* - * The actual user_fpu_begin/end() functions - * need to be preemption-safe. + * Need to be preemption-safe. * - * NOTE! user_fpu_end() must be used only after you - * have saved the FP state, and user_fpu_begin() must - * be used only immediately before restoring it. - * These functions do not do any save/restore on - * their own. + * NOTE! user_fpu_begin() must be used only immediately before restoring + * it. This function does not do any save/restore on their own. */ -static inline void user_fpu_end(void) -{ - preempt_disable(); - __thread_fpu_end(current); - preempt_enable(); -} - static inline void user_fpu_begin(void) { preempt_disable(); @@ -437,25 +469,32 @@ static inline void user_fpu_begin(void) preempt_enable(); } +static inline void __save_fpu(struct task_struct *tsk) +{ + if (use_xsave()) + xsave_state(&tsk->thread.fpu.state->xsave, -1); + else + fpu_fxsave(&tsk->thread.fpu); +} + /* * These disable preemption on their own and are safe */ static inline void save_init_fpu(struct task_struct *tsk) { WARN_ON_ONCE(!__thread_has_fpu(tsk)); + + if (use_eager_fpu()) { + __save_fpu(tsk); + return; + } + preempt_disable(); __save_init_fpu(tsk); __thread_fpu_end(tsk); preempt_enable(); } -static inline void clear_fpu(struct task_struct *tsk) -{ - preempt_disable(); - __clear_fpu(tsk); - preempt_enable(); -} - /* * i387 state interaction */ @@ -510,11 +549,34 @@ static inline void fpu_free(struct fpu *fpu) } } -static inline void fpu_copy(struct fpu *dst, struct fpu *src) +static inline void fpu_copy(struct task_struct *dst, struct task_struct *src) { - memcpy(dst->state, src->state, xstate_size); + if (use_eager_fpu()) { + memset(&dst->thread.fpu.state->xsave, 0, xstate_size); + __save_fpu(dst); + } else { + struct fpu *dfpu = &dst->thread.fpu; + struct fpu *sfpu = &src->thread.fpu; + + unlazy_fpu(src); + memcpy(dfpu->state, sfpu->state, xstate_size); + } } -extern void fpu_finit(struct fpu *fpu); +static inline unsigned long +alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, + unsigned long *size) +{ + unsigned long frame_size = xstate_sigframe_size(); + + *buf_fx = sp = round_down(sp - frame_size, 64); + if (ia32_frame && use_fxsr()) { + frame_size += sizeof(struct i387_fsave_struct); + sp -= sizeof(struct i387_fsave_struct); + } + + *size = frame_size; + return sp; +} #endif diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b0767bc..9a25b52 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -3,38 +3,54 @@ #ifdef __ASSEMBLY__ - .macro MCOUNT_SAVE_FRAME - /* taken from glibc */ - subq $0x38, %rsp - movq %rax, (%rsp) - movq %rcx, 8(%rsp) - movq %rdx, 16(%rsp) - movq %rsi, 24(%rsp) - movq %rdi, 32(%rsp) - movq %r8, 40(%rsp) - movq %r9, 48(%rsp) + /* skip is set if the stack was already partially adjusted */ + .macro MCOUNT_SAVE_FRAME skip=0 + /* + * We add enough stack to save all regs. + */ + subq $(SS+8-\skip), %rsp + movq %rax, RAX(%rsp) + movq %rcx, RCX(%rsp) + movq %rdx, RDX(%rsp) + movq %rsi, RSI(%rsp) + movq %rdi, RDI(%rsp) + movq %r8, R8(%rsp) + movq %r9, R9(%rsp) + /* Move RIP to its proper location */ + movq SS+8(%rsp), %rdx + movq %rdx, RIP(%rsp) .endm - .macro MCOUNT_RESTORE_FRAME - movq 48(%rsp), %r9 - movq 40(%rsp), %r8 - movq 32(%rsp), %rdi - movq 24(%rsp), %rsi - movq 16(%rsp), %rdx - movq 8(%rsp), %rcx - movq (%rsp), %rax - addq $0x38, %rsp + .macro MCOUNT_RESTORE_FRAME skip=0 + movq R9(%rsp), %r9 + movq R8(%rsp), %r8 + movq RDI(%rsp), %rdi + movq RSI(%rsp), %rsi + movq RDX(%rsp), %rdx + movq RCX(%rsp), %rcx + movq RAX(%rsp), %rax + addq $(SS+8-\skip), %rsp .endm #endif #ifdef CONFIG_FUNCTION_TRACER -#define MCOUNT_ADDR ((long)(mcount)) +#ifdef CC_USING_FENTRY +# define MCOUNT_ADDR ((long)(__fentry__)) +#else +# define MCOUNT_ADDR ((long)(mcount)) +#endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ +#ifdef CONFIG_DYNAMIC_FTRACE +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#define ARCH_SUPPORTS_FTRACE_SAVE_REGS +#endif + #ifndef __ASSEMBLY__ extern void mcount(void); extern atomic_t modifying_ftrace_code; +extern void __fentry__(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index d3895db..81f04ce 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -18,6 +18,10 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; + /* + * irq_tlb_count is double-counted in irq_call_count, so it must be + * subtracted from irq_call_count when displaying irq_call_count + */ unsigned int irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 2c392d6..434e210 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -35,8 +35,6 @@ #define HPET_ID_NUMBER_SHIFT 8 #define HPET_ID_VENDOR_SHIFT 16 -#define HPET_ID_VENDOR_8086 0x8086 - #define HPET_CFG_ENABLE 0x001 #define HPET_CFG_LEGACY 0x002 #define HPET_LEGACY_8254 2 diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 257d9cc..ed8089d6 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -19,12 +19,37 @@ struct pt_regs; struct user_i387_struct; extern int init_fpu(struct task_struct *child); +extern void fpu_finit(struct fpu *fpu); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern void math_state_restore(void); extern bool irq_fpu_usable(void); -extern void kernel_fpu_begin(void); -extern void kernel_fpu_end(void); + +/* + * Careful: __kernel_fpu_begin/end() must be called with preempt disabled + * and they don't touch the preempt state on their own. + * If you enable preemption after __kernel_fpu_begin(), preempt notifier + * should call the __kernel_fpu_end() to prevent the kernel/user FPU + * state from getting corrupted. KVM for example uses this model. + * + * All other cases use kernel_fpu_begin/end() which disable preemption + * during kernel FPU usage. + */ +extern void __kernel_fpu_begin(void); +extern void __kernel_fpu_end(void); + +static inline void kernel_fpu_begin(void) +{ + WARN_ON_ONCE(!irq_fpu_usable()); + preempt_disable(); + __kernel_fpu_begin(); +} + +static inline void kernel_fpu_end(void) +{ + __kernel_fpu_end(); + preempt_enable(); +} /* * Some instructions like VIA's padlock instructions generate a spurious diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h index f229b13..f42a047 100644 --- a/arch/x86/include/asm/iommu_table.h +++ b/arch/x86/include/asm/iommu_table.h @@ -48,7 +48,7 @@ struct iommu_table_entry { #define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\ - static const struct iommu_table_entry const \ + static const struct iommu_table_entry \ __iommu_entry_##_detect __used \ __attribute__ ((unused, __section__(".iommu_table"), \ aligned((sizeof(void *))))) \ @@ -63,10 +63,10 @@ struct iommu_table_entry { * to stop detecting the other IOMMUs after yours has been detected. */ #define IOMMU_INIT_POST(_detect) \ - __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, 0, 0, 0) + __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, NULL, NULL, 0) #define IOMMU_INIT_POST_FINISH(detect) \ - __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, 0, 0, 1) + __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, NULL, NULL, 1) /* * A more sophisticated version of IOMMU_INIT. This variant requires: diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 5478825..d3ddd17 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -27,6 +27,7 @@ #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT +#define ARCH_SUPPORTS_KPROBES_ON_FTRACE struct pt_regs; struct kprobe; diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 246617e..41e08cb 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -9,6 +9,22 @@ #include <linux/types.h> #include <linux/ioctl.h> +#define DE_VECTOR 0 +#define DB_VECTOR 1 +#define BP_VECTOR 3 +#define OF_VECTOR 4 +#define BR_VECTOR 5 +#define UD_VECTOR 6 +#define NM_VECTOR 7 +#define DF_VECTOR 8 +#define TS_VECTOR 10 +#define NP_VECTOR 11 +#define SS_VECTOR 12 +#define GP_VECTOR 13 +#define PF_VECTOR 14 +#define MF_VECTOR 16 +#define MC_VECTOR 18 + /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT #define __KVM_HAVE_IOAPIC diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 09155d6..1eaa6b0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -75,22 +75,6 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define DE_VECTOR 0 -#define DB_VECTOR 1 -#define BP_VECTOR 3 -#define OF_VECTOR 4 -#define BR_VECTOR 5 -#define UD_VECTOR 6 -#define NM_VECTOR 7 -#define DF_VECTOR 8 -#define TS_VECTOR 10 -#define NP_VECTOR 11 -#define SS_VECTOR 12 -#define GP_VECTOR 13 -#define PF_VECTOR 14 -#define MF_VECTOR 16 -#define MC_VECTOR 18 - #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index a3ac52b..54d73b1 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -116,19 +116,9 @@ struct mce_log { /* Software defined banks */ #define MCE_EXTENDED_BANK 128 #define MCE_THERMAL_BANK MCE_EXTENDED_BANK + 0 - -#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) /* MCE_AMD */ -#define K8_MCE_THRESHOLD_BANK_0 (MCE_THRESHOLD_BASE + 0 * 9) -#define K8_MCE_THRESHOLD_BANK_1 (MCE_THRESHOLD_BASE + 1 * 9) -#define K8_MCE_THRESHOLD_BANK_2 (MCE_THRESHOLD_BASE + 2 * 9) -#define K8_MCE_THRESHOLD_BANK_3 (MCE_THRESHOLD_BASE + 3 * 9) -#define K8_MCE_THRESHOLD_BANK_4 (MCE_THRESHOLD_BASE + 4 * 9) -#define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9) -#define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0) - +#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) #ifdef __KERNEL__ - extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -171,6 +161,7 @@ DECLARE_PER_CPU(struct device *, mce_device); #ifdef CONFIG_X86_MCE_INTEL extern int mce_cmci_disabled; extern int mce_ignore_ce; +extern int mce_bios_cmci_threshold; void mce_intel_feature_init(struct cpuinfo_x86 *c); void cmci_clear(void); void cmci_reenable(void); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 4ebe157..43d921b 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -15,8 +15,8 @@ struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, const void __user *buf, size_t size); - enum ucode_state (*request_microcode_fw) (int cpu, - struct device *device); + enum ucode_state (*request_microcode_fw) (int cpu, struct device *, + bool refresh_fw); void (*microcode_fini_cpu) (int cpu); @@ -49,12 +49,6 @@ static inline struct microcode_ops * __init init_intel_microcode(void) #ifdef CONFIG_MICROCODE_AMD extern struct microcode_ops * __init init_amd_microcode(void); extern void __exit exit_amd_microcode(void); - -static inline void get_ucode_data(void *to, const u8 *from, size_t n) -{ - memcpy(to, from, n); -} - #else static inline struct microcode_ops * __init init_amd_microcode(void) { diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index cb4e43b..4fabcdf 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -262,4 +262,6 @@ static inline void perf_check_microcode(void) { } static inline void amd_pmu_disable_virt(void) { } #endif +#define arch_perf_out_copy_user copy_from_user_nmi + #endif /* _ASM_X86_PERF_EVENT_H */ diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h new file mode 100644 index 0000000..3f2207b --- /dev/null +++ b/arch/x86/include/asm/perf_regs.h @@ -0,0 +1,33 @@ +#ifndef _ASM_X86_PERF_REGS_H +#define _ASM_X86_PERF_REGS_H + +enum perf_event_x86_regs { + PERF_REG_X86_AX, + PERF_REG_X86_BX, + PERF_REG_X86_CX, + PERF_REG_X86_DX, + PERF_REG_X86_SI, + PERF_REG_X86_DI, + PERF_REG_X86_BP, + PERF_REG_X86_SP, + PERF_REG_X86_IP, + PERF_REG_X86_FLAGS, + PERF_REG_X86_CS, + PERF_REG_X86_SS, + PERF_REG_X86_DS, + PERF_REG_X86_ES, + PERF_REG_X86_FS, + PERF_REG_X86_GS, + PERF_REG_X86_R8, + PERF_REG_X86_R9, + PERF_REG_X86_R10, + PERF_REG_X86_R11, + PERF_REG_X86_R12, + PERF_REG_X86_R13, + PERF_REG_X86_R14, + PERF_REG_X86_R15, + + PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, + PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, +}; +#endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 013286a1..db8fec6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -303,11 +303,9 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte); extern void native_pagetable_reserve(u64 start, u64 end); #ifdef CONFIG_X86_32 -extern void native_pagetable_setup_start(pgd_t *base); -extern void native_pagetable_setup_done(pgd_t *base); +extern void native_pagetable_init(void); #else -#define native_pagetable_setup_start x86_init_pgd_noop -#define native_pagetable_setup_done x86_init_pgd_noop +#define native_pagetable_init paging_init #endif struct seq_file; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d048cad..b98c0d9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -423,7 +423,6 @@ DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); -extern unsigned long kernel_eflags; extern asmlinkage void ignore_sysret(void); #else /* X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR @@ -759,6 +758,8 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } +extern void set_task_blockstep(struct task_struct *task, bool on); + /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h new file mode 100644 index 0000000..d1ac07a --- /dev/null +++ b/arch/x86/include/asm/rcu.h @@ -0,0 +1,32 @@ +#ifndef _ASM_X86_RCU_H +#define _ASM_X86_RCU_H + +#ifndef __ASSEMBLY__ + +#include <linux/rcupdate.h> +#include <asm/ptrace.h> + +static inline void exception_enter(struct pt_regs *regs) +{ + rcu_user_exit(); +} + +static inline void exception_exit(struct pt_regs *regs) +{ +#ifdef CONFIG_RCU_USER_QS + if (user_mode(regs)) + rcu_user_enter(); +#endif +} + +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_RCU_USER_QS +# define SCHEDULE_USER call schedule_user +#else +# define SCHEDULE_USER call schedule +#endif + +#endif /* !__ASSEMBLY__ */ + +#endif diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 598457c..323973f 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -31,6 +31,10 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; +#ifndef CONFIG_COMPAT +typedef sigset_t compat_sigset_t; +#endif + #else /* Here we must cater to libcs that poke about in kernel headers. */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f2b83bc..cdf5674 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -1,6 +1,135 @@ #ifndef __SVM_H #define __SVM_H +#define SVM_EXIT_READ_CR0 0x000 +#define SVM_EXIT_READ_CR3 0x003 +#define SVM_EXIT_READ_CR4 0x004 +#define SVM_EXIT_READ_CR8 0x008 +#define SVM_EXIT_WRITE_CR0 0x010 +#define SVM_EXIT_WRITE_CR3 0x013 +#define SVM_EXIT_WRITE_CR4 0x014 +#define SVM_EXIT_WRITE_CR8 0x018 +#define SVM_EXIT_READ_DR0 0x020 +#define SVM_EXIT_READ_DR1 0x021 +#define SVM_EXIT_READ_DR2 0x022 +#define SVM_EXIT_READ_DR3 0x023 +#define SVM_EXIT_READ_DR4 0x024 +#define SVM_EXIT_READ_DR5 0x025 +#define SVM_EXIT_READ_DR6 0x026 +#define SVM_EXIT_READ_DR7 0x027 +#define SVM_EXIT_WRITE_DR0 0x030 +#define SVM_EXIT_WRITE_DR1 0x031 +#define SVM_EXIT_WRITE_DR2 0x032 +#define SVM_EXIT_WRITE_DR3 0x033 +#define SVM_EXIT_WRITE_DR4 0x034 +#define SVM_EXIT_WRITE_DR5 0x035 +#define SVM_EXIT_WRITE_DR6 0x036 +#define SVM_EXIT_WRITE_DR7 0x037 +#define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_INTR 0x060 +#define SVM_EXIT_NMI 0x061 +#define SVM_EXIT_SMI 0x062 +#define SVM_EXIT_INIT 0x063 +#define SVM_EXIT_VINTR 0x064 +#define SVM_EXIT_CR0_SEL_WRITE 0x065 +#define SVM_EXIT_IDTR_READ 0x066 +#define SVM_EXIT_GDTR_READ 0x067 +#define SVM_EXIT_LDTR_READ 0x068 +#define SVM_EXIT_TR_READ 0x069 +#define SVM_EXIT_IDTR_WRITE 0x06a +#define SVM_EXIT_GDTR_WRITE 0x06b +#define SVM_EXIT_LDTR_WRITE 0x06c +#define SVM_EXIT_TR_WRITE 0x06d +#define SVM_EXIT_RDTSC 0x06e +#define SVM_EXIT_RDPMC 0x06f +#define SVM_EXIT_PUSHF 0x070 +#define SVM_EXIT_POPF 0x071 +#define SVM_EXIT_CPUID 0x072 +#define SVM_EXIT_RSM 0x073 +#define SVM_EXIT_IRET 0x074 +#define SVM_EXIT_SWINT 0x075 +#define SVM_EXIT_INVD 0x076 +#define SVM_EXIT_PAUSE 0x077 +#define SVM_EXIT_HLT 0x078 +#define SVM_EXIT_INVLPG 0x079 +#define SVM_EXIT_INVLPGA 0x07a +#define SVM_EXIT_IOIO 0x07b +#define SVM_EXIT_MSR 0x07c +#define SVM_EXIT_TASK_SWITCH 0x07d +#define SVM_EXIT_FERR_FREEZE 0x07e +#define SVM_EXIT_SHUTDOWN 0x07f +#define SVM_EXIT_VMRUN 0x080 +#define SVM_EXIT_VMMCALL 0x081 +#define SVM_EXIT_VMLOAD 0x082 +#define SVM_EXIT_VMSAVE 0x083 +#define SVM_EXIT_STGI 0x084 +#define SVM_EXIT_CLGI 0x085 +#define SVM_EXIT_SKINIT 0x086 +#define SVM_EXIT_RDTSCP 0x087 +#define SVM_EXIT_ICEBP 0x088 +#define SVM_EXIT_WBINVD 0x089 +#define SVM_EXIT_MONITOR 0x08a +#define SVM_EXIT_MWAIT 0x08b +#define SVM_EXIT_MWAIT_COND 0x08c +#define SVM_EXIT_XSETBV 0x08d +#define SVM_EXIT_NPF 0x400 + +#define SVM_EXIT_ERR -1 + +#define SVM_EXIT_REASONS \ + { SVM_EXIT_READ_CR0, "read_cr0" }, \ + { SVM_EXIT_READ_CR3, "read_cr3" }, \ + { SVM_EXIT_READ_CR4, "read_cr4" }, \ + { SVM_EXIT_READ_CR8, "read_cr8" }, \ + { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ + { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ + { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ + { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ + { SVM_EXIT_READ_DR0, "read_dr0" }, \ + { SVM_EXIT_READ_DR1, "read_dr1" }, \ + { SVM_EXIT_READ_DR2, "read_dr2" }, \ + { SVM_EXIT_READ_DR3, "read_dr3" }, \ + { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ + { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ + { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ + { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ + { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ + { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ + { SVM_EXIT_INTR, "interrupt" }, \ + { SVM_EXIT_NMI, "nmi" }, \ + { SVM_EXIT_SMI, "smi" }, \ + { SVM_EXIT_INIT, "init" }, \ + { SVM_EXIT_VINTR, "vintr" }, \ + { SVM_EXIT_CPUID, "cpuid" }, \ + { SVM_EXIT_INVD, "invd" }, \ + { SVM_EXIT_HLT, "hlt" }, \ + { SVM_EXIT_INVLPG, "invlpg" }, \ + { SVM_EXIT_INVLPGA, "invlpga" }, \ + { SVM_EXIT_IOIO, "io" }, \ + { SVM_EXIT_MSR, "msr" }, \ + { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ + { SVM_EXIT_SHUTDOWN, "shutdown" }, \ + { SVM_EXIT_VMRUN, "vmrun" }, \ + { SVM_EXIT_VMMCALL, "hypercall" }, \ + { SVM_EXIT_VMLOAD, "vmload" }, \ + { SVM_EXIT_VMSAVE, "vmsave" }, \ + { SVM_EXIT_STGI, "stgi" }, \ + { SVM_EXIT_CLGI, "clgi" }, \ + { SVM_EXIT_SKINIT, "skinit" }, \ + { SVM_EXIT_WBINVD, "wbinvd" }, \ + { SVM_EXIT_MONITOR, "monitor" }, \ + { SVM_EXIT_MWAIT, "mwait" }, \ + { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_NPF, "npf" } + +#ifdef __KERNEL__ + enum { INTERCEPT_INTR, INTERCEPT_NMI, @@ -264,81 +393,6 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXITINFO_REG_MASK 0x0F -#define SVM_EXIT_READ_CR0 0x000 -#define SVM_EXIT_READ_CR3 0x003 -#define SVM_EXIT_READ_CR4 0x004 -#define SVM_EXIT_READ_CR8 0x008 -#define SVM_EXIT_WRITE_CR0 0x010 -#define SVM_EXIT_WRITE_CR3 0x013 -#define SVM_EXIT_WRITE_CR4 0x014 -#define SVM_EXIT_WRITE_CR8 0x018 -#define SVM_EXIT_READ_DR0 0x020 -#define SVM_EXIT_READ_DR1 0x021 -#define SVM_EXIT_READ_DR2 0x022 -#define SVM_EXIT_READ_DR3 0x023 -#define SVM_EXIT_READ_DR4 0x024 -#define SVM_EXIT_READ_DR5 0x025 -#define SVM_EXIT_READ_DR6 0x026 -#define SVM_EXIT_READ_DR7 0x027 -#define SVM_EXIT_WRITE_DR0 0x030 -#define SVM_EXIT_WRITE_DR1 0x031 -#define SVM_EXIT_WRITE_DR2 0x032 -#define SVM_EXIT_WRITE_DR3 0x033 -#define SVM_EXIT_WRITE_DR4 0x034 -#define SVM_EXIT_WRITE_DR5 0x035 -#define SVM_EXIT_WRITE_DR6 0x036 -#define SVM_EXIT_WRITE_DR7 0x037 -#define SVM_EXIT_EXCP_BASE 0x040 -#define SVM_EXIT_INTR 0x060 -#define SVM_EXIT_NMI 0x061 -#define SVM_EXIT_SMI 0x062 -#define SVM_EXIT_INIT 0x063 -#define SVM_EXIT_VINTR 0x064 -#define SVM_EXIT_CR0_SEL_WRITE 0x065 -#define SVM_EXIT_IDTR_READ 0x066 -#define SVM_EXIT_GDTR_READ 0x067 -#define SVM_EXIT_LDTR_READ 0x068 -#define SVM_EXIT_TR_READ 0x069 -#define SVM_EXIT_IDTR_WRITE 0x06a -#define SVM_EXIT_GDTR_WRITE 0x06b -#define SVM_EXIT_LDTR_WRITE 0x06c -#define SVM_EXIT_TR_WRITE 0x06d -#define SVM_EXIT_RDTSC 0x06e -#define SVM_EXIT_RDPMC 0x06f -#define SVM_EXIT_PUSHF 0x070 -#define SVM_EXIT_POPF 0x071 -#define SVM_EXIT_CPUID 0x072 -#define SVM_EXIT_RSM 0x073 -#define SVM_EXIT_IRET 0x074 -#define SVM_EXIT_SWINT 0x075 -#define SVM_EXIT_INVD 0x076 -#define SVM_EXIT_PAUSE 0x077 -#define SVM_EXIT_HLT 0x078 -#define SVM_EXIT_INVLPG 0x079 -#define SVM_EXIT_INVLPGA 0x07a -#define SVM_EXIT_IOIO 0x07b -#define SVM_EXIT_MSR 0x07c -#define SVM_EXIT_TASK_SWITCH 0x07d -#define SVM_EXIT_FERR_FREEZE 0x07e -#define SVM_EXIT_SHUTDOWN 0x07f -#define SVM_EXIT_VMRUN 0x080 -#define SVM_EXIT_VMMCALL 0x081 -#define SVM_EXIT_VMLOAD 0x082 -#define SVM_EXIT_VMSAVE 0x083 -#define SVM_EXIT_STGI 0x084 -#define SVM_EXIT_CLGI 0x085 -#define SVM_EXIT_SKINIT 0x086 -#define SVM_EXIT_RDTSCP 0x087 -#define SVM_EXIT_ICEBP 0x088 -#define SVM_EXIT_WBINVD 0x089 -#define SVM_EXIT_MONITOR 0x08a -#define SVM_EXIT_MWAIT 0x08b -#define SVM_EXIT_MWAIT_COND 0x08c -#define SVM_EXIT_XSETBV 0x08d -#define SVM_EXIT_NPF 0x400 - -#define SVM_EXIT_ERR -1 - #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" @@ -350,3 +404,4 @@ struct __attribute__ ((__packed__)) vmcb { #endif +#endif diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 3fda9db4..4ca1c61 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -40,7 +40,7 @@ asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *, struct old_sigaction32 __user *); asmlinkage long sys32_alarm(unsigned int); -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int); +asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); asmlinkage long sys32_sysfs(int, u32, u32); asmlinkage long sys32_sched_rr_get_interval(compat_pid_t, diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 89f794f..c535d847 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -89,6 +89,7 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_FORK 18 /* ret_from_fork */ +#define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_DEBUG 21 /* uses debug registers */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -114,6 +115,7 @@ struct thread_info { #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) +#define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_DEBUG (1 << TIF_DEBUG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) @@ -126,12 +128,13 @@ struct thread_info { /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) + _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -141,7 +144,8 @@ struct thread_info { /* work to do on any return to user space */ #define _TIF_ALLWORK_MASK \ - ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT) + ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_NOHZ) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index f3971bb..8ff8be7 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -42,10 +42,11 @@ struct arch_uprobe { }; struct arch_uprobe_task { - unsigned long saved_trap_nr; #ifdef CONFIG_X86_64 unsigned long saved_scratch_register; #endif + unsigned int saved_trap_nr; + unsigned int saved_tf; }; extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index bb05228..fddb53d 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -11,7 +11,8 @@ extern const char VDSO32_PRELINK[]; #define VDSO32_SYMBOL(base, name) \ ({ \ extern const char VDSO32_##name[]; \ - (void *)(VDSO32_##name - VDSO32_PRELINK + (unsigned long)(base)); \ + (void __user *)(VDSO32_##name - VDSO32_PRELINK + \ + (unsigned long)(base)); \ }) #endif diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 74fcb96..36ec21c 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -25,6 +25,88 @@ * */ +#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 + +#define EXIT_REASON_EXCEPTION_NMI 0 +#define EXIT_REASON_EXTERNAL_INTERRUPT 1 +#define EXIT_REASON_TRIPLE_FAULT 2 + +#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_NMI_WINDOW 8 +#define EXIT_REASON_TASK_SWITCH 9 +#define EXIT_REASON_CPUID 10 +#define EXIT_REASON_HLT 12 +#define EXIT_REASON_INVD 13 +#define EXIT_REASON_INVLPG 14 +#define EXIT_REASON_RDPMC 15 +#define EXIT_REASON_RDTSC 16 +#define EXIT_REASON_VMCALL 18 +#define EXIT_REASON_VMCLEAR 19 +#define EXIT_REASON_VMLAUNCH 20 +#define EXIT_REASON_VMPTRLD 21 +#define EXIT_REASON_VMPTRST 22 +#define EXIT_REASON_VMREAD 23 +#define EXIT_REASON_VMRESUME 24 +#define EXIT_REASON_VMWRITE 25 +#define EXIT_REASON_VMOFF 26 +#define EXIT_REASON_VMON 27 +#define EXIT_REASON_CR_ACCESS 28 +#define EXIT_REASON_DR_ACCESS 29 +#define EXIT_REASON_IO_INSTRUCTION 30 +#define EXIT_REASON_MSR_READ 31 +#define EXIT_REASON_MSR_WRITE 32 +#define EXIT_REASON_INVALID_STATE 33 +#define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_MONITOR_INSTRUCTION 39 +#define EXIT_REASON_PAUSE_INSTRUCTION 40 +#define EXIT_REASON_MCE_DURING_VMENTRY 41 +#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 +#define EXIT_REASON_APIC_ACCESS 44 +#define EXIT_REASON_EPT_VIOLATION 48 +#define EXIT_REASON_EPT_MISCONFIG 49 +#define EXIT_REASON_WBINVD 54 +#define EXIT_REASON_XSETBV 55 +#define EXIT_REASON_INVPCID 58 + +#define VMX_EXIT_REASONS \ + { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ + { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ + { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ + { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ + { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ + { EXIT_REASON_CPUID, "CPUID" }, \ + { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVLPG, "INVLPG" }, \ + { EXIT_REASON_RDPMC, "RDPMC" }, \ + { EXIT_REASON_RDTSC, "RDTSC" }, \ + { EXIT_REASON_VMCALL, "VMCALL" }, \ + { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ + { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ + { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ + { EXIT_REASON_VMPTRST, "VMPTRST" }, \ + { EXIT_REASON_VMREAD, "VMREAD" }, \ + { EXIT_REASON_VMRESUME, "VMRESUME" }, \ + { EXIT_REASON_VMWRITE, "VMWRITE" }, \ + { EXIT_REASON_VMOFF, "VMOFF" }, \ + { EXIT_REASON_VMON, "VMON" }, \ + { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ + { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ + { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ + { EXIT_REASON_MSR_READ, "MSR_READ" }, \ + { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ + { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ + { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ + { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ + { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ + { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_WBINVD, "WBINVD" } + +#ifdef __KERNEL__ + #include <linux/types.h> /* @@ -241,49 +323,6 @@ enum vmcs_field { HOST_RIP = 0x00006c16, }; -#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 - -#define EXIT_REASON_EXCEPTION_NMI 0 -#define EXIT_REASON_EXTERNAL_INTERRUPT 1 -#define EXIT_REASON_TRIPLE_FAULT 2 - -#define EXIT_REASON_PENDING_INTERRUPT 7 -#define EXIT_REASON_NMI_WINDOW 8 -#define EXIT_REASON_TASK_SWITCH 9 -#define EXIT_REASON_CPUID 10 -#define EXIT_REASON_HLT 12 -#define EXIT_REASON_INVD 13 -#define EXIT_REASON_INVLPG 14 -#define EXIT_REASON_RDPMC 15 -#define EXIT_REASON_RDTSC 16 -#define EXIT_REASON_VMCALL 18 -#define EXIT_REASON_VMCLEAR 19 -#define EXIT_REASON_VMLAUNCH 20 -#define EXIT_REASON_VMPTRLD 21 -#define EXIT_REASON_VMPTRST 22 -#define EXIT_REASON_VMREAD 23 -#define EXIT_REASON_VMRESUME 24 -#define EXIT_REASON_VMWRITE 25 -#define EXIT_REASON_VMOFF 26 -#define EXIT_REASON_VMON 27 -#define EXIT_REASON_CR_ACCESS 28 -#define EXIT_REASON_DR_ACCESS 29 -#define EXIT_REASON_IO_INSTRUCTION 30 -#define EXIT_REASON_MSR_READ 31 -#define EXIT_REASON_MSR_WRITE 32 -#define EXIT_REASON_INVALID_STATE 33 -#define EXIT_REASON_MWAIT_INSTRUCTION 36 -#define EXIT_REASON_MONITOR_INSTRUCTION 39 -#define EXIT_REASON_PAUSE_INSTRUCTION 40 -#define EXIT_REASON_MCE_DURING_VMENTRY 41 -#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 -#define EXIT_REASON_APIC_ACCESS 44 -#define EXIT_REASON_EPT_VIOLATION 48 -#define EXIT_REASON_EPT_MISCONFIG 49 -#define EXIT_REASON_WBINVD 54 -#define EXIT_REASON_XSETBV 55 -#define EXIT_REASON_INVPCID 58 - /* * Interruption-information format */ @@ -488,3 +527,5 @@ enum vm_instruction_error_number { }; #endif + +#endif diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 38155f6..5769349 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -81,12 +81,13 @@ struct x86_init_mapping { /** * struct x86_init_paging - platform specific paging functions - * @pagetable_setup_start: platform specific pre paging_init() call - * @pagetable_setup_done: platform specific post paging_init() call + * @pagetable_init: platform specific paging initialization call to setup + * the kernel pagetables and prepare accessors functions. + * Callback must call paging_init(). Called once after the + * direct mapping for phys memory is available. */ struct x86_init_paging { - void (*pagetable_setup_start)(pgd_t *base); - void (*pagetable_setup_done)(pgd_t *base); + void (*pagetable_init)(void); }; /** diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 93971e8..472b9b7 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -51,7 +51,8 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, extern int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op); -extern int m2p_remove_override(struct page *page, bool clear_pte); +extern int m2p_remove_override(struct page *page, + struct gnttab_map_grant_ref *kmap_op); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 4545708..aabd585 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -534,38 +534,6 @@ static struct xor_block_template xor_block_p5_mmx = { * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) */ -#define XMMS_SAVE \ -do { \ - preempt_disable(); \ - cr0 = read_cr0(); \ - clts(); \ - asm volatile( \ - "movups %%xmm0,(%0) ;\n\t" \ - "movups %%xmm1,0x10(%0) ;\n\t" \ - "movups %%xmm2,0x20(%0) ;\n\t" \ - "movups %%xmm3,0x30(%0) ;\n\t" \ - : \ - : "r" (xmm_save) \ - : "memory"); \ -} while (0) - -#define XMMS_RESTORE \ -do { \ - asm volatile( \ - "sfence ;\n\t" \ - "movups (%0),%%xmm0 ;\n\t" \ - "movups 0x10(%0),%%xmm1 ;\n\t" \ - "movups 0x20(%0),%%xmm2 ;\n\t" \ - "movups 0x30(%0),%%xmm3 ;\n\t" \ - : \ - : "r" (xmm_save) \ - : "memory"); \ - write_cr0(cr0); \ - preempt_enable(); \ -} while (0) - -#define ALIGN16 __attribute__((aligned(16))) - #define OFFS(x) "16*("#x")" #define PF_OFFS(x) "256+16*("#x")" #define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n" @@ -587,10 +555,8 @@ static void xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -633,7 +599,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) : : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -641,10 +607,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -694,7 +658,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -702,10 +666,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -762,7 +724,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -770,10 +732,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4, unsigned long *p5) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); /* Make sure GCC forgets anything it knows about p4 or p5, such that it won't pass to the asm volatile below a @@ -850,7 +810,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, like assuming they have some legal value. */ asm("" : "=r" (p4), "=r" (p5)); - XMMS_RESTORE; + kernel_fpu_end(); } static struct xor_block_template xor_block_pIII_sse = { diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h index b9b2323..5fc06d0 100644 --- a/arch/x86/include/asm/xor_64.h +++ b/arch/x86/include/asm/xor_64.h @@ -34,41 +34,7 @@ * no advantages to be gotten from x86-64 here anyways. */ -typedef struct { - unsigned long a, b; -} __attribute__((aligned(16))) xmm_store_t; - -/* Doesn't use gcc to save the XMM registers, because there is no easy way to - tell it to do a clts before the register saving. */ -#define XMMS_SAVE \ -do { \ - preempt_disable(); \ - asm volatile( \ - "movq %%cr0,%0 ;\n\t" \ - "clts ;\n\t" \ - "movups %%xmm0,(%1) ;\n\t" \ - "movups %%xmm1,0x10(%1) ;\n\t" \ - "movups %%xmm2,0x20(%1) ;\n\t" \ - "movups %%xmm3,0x30(%1) ;\n\t" \ - : "=&r" (cr0) \ - : "r" (xmm_save) \ - : "memory"); \ -} while (0) - -#define XMMS_RESTORE \ -do { \ - asm volatile( \ - "sfence ;\n\t" \ - "movups (%1),%%xmm0 ;\n\t" \ - "movups 0x10(%1),%%xmm1 ;\n\t" \ - "movups 0x20(%1),%%xmm2 ;\n\t" \ - "movups 0x30(%1),%%xmm3 ;\n\t" \ - "movq %0,%%cr0 ;\n\t" \ - : \ - : "r" (cr0), "r" (xmm_save) \ - : "memory"); \ - preempt_enable(); \ -} while (0) +#include <asm/i387.h> #define OFFS(x) "16*("#x")" #define PF_OFFS(x) "256+16*("#x")" @@ -91,10 +57,8 @@ static void xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { unsigned int lines = bytes >> 8; - unsigned long cr0; - xmm_store_t xmm_save[4]; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -135,7 +99,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) : [inc] "r" (256UL) : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -143,11 +107,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3) { unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK #define BLOCK(i) \ @@ -194,7 +155,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) : [inc] "r" (256UL) : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -202,10 +163,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -261,7 +220,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, : [inc] "r" (256UL) : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -269,10 +228,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4, unsigned long *p5) { unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -336,7 +293,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, : [inc] "r" (256UL) : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static struct xor_block_template xor_block_sse = { diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 2510d35..7ea79c5 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -20,32 +20,6 @@ #include <linux/compiler.h> #include <asm/i387.h> -#define ALIGN32 __aligned(32) - -#define YMM_SAVED_REGS 4 - -#define YMMS_SAVE \ -do { \ - preempt_disable(); \ - cr0 = read_cr0(); \ - clts(); \ - asm volatile("vmovaps %%ymm0, %0" : "=m" (ymm_save[0]) : : "memory"); \ - asm volatile("vmovaps %%ymm1, %0" : "=m" (ymm_save[32]) : : "memory"); \ - asm volatile("vmovaps %%ymm2, %0" : "=m" (ymm_save[64]) : : "memory"); \ - asm volatile("vmovaps %%ymm3, %0" : "=m" (ymm_save[96]) : : "memory"); \ -} while (0); - -#define YMMS_RESTORE \ -do { \ - asm volatile("sfence" : : : "memory"); \ - asm volatile("vmovaps %0, %%ymm3" : : "m" (ymm_save[96])); \ - asm volatile("vmovaps %0, %%ymm2" : : "m" (ymm_save[64])); \ - asm volatile("vmovaps %0, %%ymm1" : : "m" (ymm_save[32])); \ - asm volatile("vmovaps %0, %%ymm0" : : "m" (ymm_save[0])); \ - write_cr0(cr0); \ - preempt_enable(); \ -} while (0); - #define BLOCK4(i) \ BLOCK(32 * i, 0) \ BLOCK(32 * (i + 1), 1) \ @@ -60,10 +34,9 @@ do { \ static void xor_avx_2(unsigned long bytes, unsigned long *p0, unsigned long *p1) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -82,16 +55,15 @@ do { \ p1 = (unsigned long *)((uintptr_t)p1 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static void xor_avx_3(unsigned long bytes, unsigned long *p0, unsigned long *p1, unsigned long *p2) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -113,16 +85,15 @@ do { \ p2 = (unsigned long *)((uintptr_t)p2 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static void xor_avx_4(unsigned long bytes, unsigned long *p0, unsigned long *p1, unsigned long *p2, unsigned long *p3) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -147,16 +118,15 @@ do { \ p3 = (unsigned long *)((uintptr_t)p3 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static void xor_avx_5(unsigned long bytes, unsigned long *p0, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { - unsigned long cr0, lines = bytes >> 9; - char ymm_save[32 * YMM_SAVED_REGS] ALIGN32; + unsigned long lines = bytes >> 9; - YMMS_SAVE + kernel_fpu_begin(); while (lines--) { #undef BLOCK @@ -184,7 +154,7 @@ do { \ p4 = (unsigned long *)((uintptr_t)p4 + 512); } - YMMS_RESTORE + kernel_fpu_end(); } static struct xor_block_template xor_block_avx = { diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 8a1b6f9..2ddee1b8 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -34,17 +34,14 @@ extern unsigned int xstate_size; extern u64 pcntxt_mask; extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; +extern struct xsave_struct *init_xstate_buf; extern void xsave_init(void); extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); extern int init_fpu(struct task_struct *child); -extern int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *sw); -static inline int fpu_xrstor_checking(struct fpu *fpu) +static inline int fpu_xrstor_checking(struct xsave_struct *fx) { - struct xsave_struct *fx = &fpu->state->xsave; int err; asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t" @@ -69,8 +66,7 @@ static inline int xsave_user(struct xsave_struct __user *buf) * Clear the xsave header first, so that reserved fields are * initialized to zero. */ - err = __clear_user(&buf->xsave_hdr, - sizeof(struct xsave_hdr_struct)); + err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr)); if (unlikely(err)) return -EFAULT; @@ -84,9 +80,6 @@ static inline int xsave_user(struct xsave_struct __user *buf) : [err] "=r" (err) : "D" (buf), "a" (-1), "d" (-1), "0" (0) : "memory"); - if (unlikely(err) && __clear_user(buf, xstate_size)) - err = -EFAULT; - /* No need to clear here because the caller clears USED_MATH */ return err; } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e56..8d7a619 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b2297e5..e651f7a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -656,7 +656,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) acpi_register_lapic(physid, ACPI_MADT_ENABLED); /* - * If mp_register_lapic successfully generates a new logical cpu + * If acpi_register_lapic successfully generates a new logical cpu * number, then the following will get us exactly what was mapped */ cpumask_andnot(new_map, cpu_present_mask, tmp_map); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ced4534..ef5ccca 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -23,19 +23,6 @@ #define MAX_PATCH_LEN (255-1) -#ifdef CONFIG_HOTPLUG_CPU -static int smp_alt_once; - -static int __init bootonly(char *str) -{ - smp_alt_once = 1; - return 1; -} -__setup("smp-alt-boot", bootonly); -#else -#define smp_alt_once 1 -#endif - static int __initdata_or_module debug_alternative; static int __init debug_alt(char *str) @@ -317,7 +304,7 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, /* turn DS segment override prefix into lock prefix */ if (*ptr == 0x3e) text_poke(ptr, ((unsigned char []){0xf0}), 1); - }; + } mutex_unlock(&text_mutex); } @@ -326,9 +313,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, { const s32 *poff; - if (noreplace_smp) - return; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -338,7 +322,7 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, /* turn lock prefix into DS segment override prefix */ if (*ptr == 0xf0) text_poke(ptr, ((unsigned char []){0x3E}), 1); - }; + } mutex_unlock(&text_mutex); } @@ -359,7 +343,7 @@ struct smp_alt_module { }; static LIST_HEAD(smp_alt_modules); static DEFINE_MUTEX(smp_alt); -static int smp_mode = 1; /* protected by smp_alt */ +static bool uniproc_patched = false; /* protected by smp_alt */ void __init_or_module alternatives_smp_module_add(struct module *mod, char *name, @@ -368,19 +352,18 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, { struct smp_alt_module *smp; - if (noreplace_smp) - return; + mutex_lock(&smp_alt); + if (!uniproc_patched) + goto unlock; - if (smp_alt_once) { - if (boot_cpu_has(X86_FEATURE_UP)) - alternatives_smp_unlock(locks, locks_end, - text, text_end); - return; - } + if (num_possible_cpus() == 1) + /* Don't bother remembering, we'll never have to undo it. */ + goto smp_unlock; smp = kzalloc(sizeof(*smp), GFP_KERNEL); if (NULL == smp) - return; /* we'll run the (safe but slow) SMP code then ... */ + /* we'll run the (safe but slow) SMP code then ... */ + goto unlock; smp->mod = mod; smp->name = name; @@ -392,11 +375,10 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, __func__, smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); - mutex_lock(&smp_alt); list_add_tail(&smp->next, &smp_alt_modules); - if (boot_cpu_has(X86_FEATURE_UP)) - alternatives_smp_unlock(smp->locks, smp->locks_end, - smp->text, smp->text_end); +smp_unlock: + alternatives_smp_unlock(locks, locks_end, text, text_end); +unlock: mutex_unlock(&smp_alt); } @@ -404,24 +386,18 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) { struct smp_alt_module *item; - if (smp_alt_once || noreplace_smp) - return; - mutex_lock(&smp_alt); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; list_del(&item->next); - mutex_unlock(&smp_alt); - DPRINTK("%s: %s\n", __func__, item->name); kfree(item); - return; + break; } mutex_unlock(&smp_alt); } -bool skip_smp_alternatives; -void alternatives_smp_switch(int smp) +void alternatives_enable_smp(void) { struct smp_alt_module *mod; @@ -436,34 +412,21 @@ void alternatives_smp_switch(int smp) pr_info("lockdep: fixing up alternatives\n"); #endif - if (noreplace_smp || smp_alt_once || skip_smp_alternatives) - return; - BUG_ON(!smp && (num_online_cpus() > 1)); + /* Why bother if there are no other CPUs? */ + BUG_ON(num_possible_cpus() == 1); mutex_lock(&smp_alt); - /* - * Avoid unnecessary switches because it forces JIT based VMs to - * throw away all cached translations, which can be quite costly. - */ - if (smp == smp_mode) { - /* nothing */ - } else if (smp) { + if (uniproc_patched) { pr_info("switching to SMP code\n"); + BUG_ON(num_online_cpus() != 1); clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_lock(mod->locks, mod->locks_end, mod->text, mod->text_end); - } else { - pr_info("switching to UP code\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); - set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); - list_for_each_entry(mod, &smp_alt_modules, next) - alternatives_smp_unlock(mod->locks, mod->locks_end, - mod->text, mod->text_end); + uniproc_patched = false; } - smp_mode = smp; mutex_unlock(&smp_alt); } @@ -540,40 +503,22 @@ void __init alternative_instructions(void) apply_alternatives(__alt_instructions, __alt_instructions_end); - /* switch to patch-once-at-boottime-only mode and free the - * tables in case we know the number of CPUs will never ever - * change */ -#ifdef CONFIG_HOTPLUG_CPU - if (num_possible_cpus() < 2) - smp_alt_once = 1; -#endif - #ifdef CONFIG_SMP - if (smp_alt_once) { - if (1 == num_possible_cpus()) { - pr_info("switching to UP code\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); - set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); - - alternatives_smp_unlock(__smp_locks, __smp_locks_end, - _text, _etext); - } - } else { + /* Patch to UP if other cpus not imminent. */ + if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { + uniproc_patched = true; alternatives_smp_module_add(NULL, "core kernel", __smp_locks, __smp_locks_end, _text, _etext); - - /* Only switch to UP mode if we don't immediately boot others */ - if (num_present_cpus() == 1 || setup_max_cpus <= 1) - alternatives_smp_switch(0); } -#endif - apply_paravirt(__parainstructions, __parainstructions_end); - if (smp_alt_once) + if (!uniproc_patched || num_possible_cpus() == 1) free_init_pages("SMP alternatives", (unsigned long)__smp_locks, (unsigned long)__smp_locks_end); +#endif + + apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 24deb30..b17416e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1934,7 +1934,7 @@ void smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]); i++; v1 >>= 1; - }; + } apic_printk(APIC_DEBUG, KERN_CONT "\n"); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9d92e19..f7e98a2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -737,6 +737,72 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, } #endif +static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) +{ + if (!cpu_has_invlpg) + return; + + tlb_flushall_shift = 5; + + if (c->x86 <= 0x11) + tlb_flushall_shift = 4; +} + +static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c) +{ + u32 ebx, eax, ecx, edx; + u16 mask = 0xfff; + + if (c->x86 < 0xf) + return; + + if (c->extended_cpuid_level < 0x80000006) + return; + + cpuid(0x80000006, &eax, &ebx, &ecx, &edx); + + tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask; + tlb_lli_4k[ENTRIES] = ebx & mask; + + /* + * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB + * characteristics from the CPUID function 0x80000005 instead. + */ + if (c->x86 == 0xf) { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + mask = 0xff; + } + + /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!((eax >> 16) & mask)) { + u32 a, b, c, d; + + cpuid(0x80000005, &a, &b, &c, &d); + tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff; + } else { + tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; + } + + /* a 4M entry uses two 2M entries */ + tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; + + /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!(eax & mask)) { + /* Erratum 658 */ + if (c->x86 == 0x15 && c->x86_model <= 0x1f) { + tlb_lli_2m[ENTRIES] = 1024; + } else { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + tlb_lli_2m[ENTRIES] = eax & 0xff; + } + } else + tlb_lli_2m[ENTRIES] = eax & mask; + + tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; + + cpu_set_tlb_flushall_shift(c); +} + static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, @@ -756,6 +822,7 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_size_cache = amd_size_cache, #endif .c_early_init = early_init_amd, + .c_detect_tlb = cpu_detect_tlb_amd, .c_bsp_init = bsp_init_amd, .c_init = init_amd, .c_x86_vendor = X86_VENDOR_AMD, diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c97bb7b..d0e910d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -165,10 +165,15 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); #endif check_config(); - check_fpu(); check_hlt(); check_popad(); init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); + + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + check_fpu(); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5fbc3c..532691b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -476,7 +476,7 @@ void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c) printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \ - "tlb_flushall_shift is 0x%x\n", + "tlb_flushall_shift: %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], @@ -942,8 +942,7 @@ void __init identify_boot_cpu(void) #else vgetcpu_set_mode(); #endif - if (boot_cpu_data.cpuid_level >= 2) - cpu_detect_tlb(&boot_cpu_data); + cpu_detect_tlb(&boot_cpu_data); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) @@ -1023,14 +1022,16 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", c->x86_model_id); + printk(KERN_CONT "%s", strim(c->x86_model_id)); else printk(KERN_CONT "%d86", c->x86); + printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model); + if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT " stepping %02x\n", c->x86_mask); + printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask); else - printk(KERN_CONT "\n"); + printk(KERN_CONT ")\n"); print_cpu_msr(c); } @@ -1116,8 +1117,6 @@ void syscall_init(void) X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL); } -unsigned long kernel_eflags; - /* * Copies of the original ist values from the tss are only accessed during * debugging, no special alignment required. @@ -1297,9 +1296,6 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); - xsave_init(); - - raw_local_save_flags(kernel_eflags); if (is_uv_system()) uv_cpu_init(); @@ -1352,6 +1348,5 @@ void __cpuinit cpu_init(void) dbg_restore_debug_regs(); fpu_init(); - xsave_init(); } #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0a4ce29..198e019 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -648,6 +648,10 @@ static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c) int i, j, n; unsigned int regs[4]; unsigned char *desc = (unsigned char *)regs; + + if (c->cpuid_level < 2) + return; + /* Number of times to iterate */ n = cpuid_eax(2) & 0xFF; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index fc4beb3..ddc72f8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -78,6 +78,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) } static cpumask_var_t mce_inject_cpumask; +static DEFINE_MUTEX(mce_inject_mutex); static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { @@ -194,7 +195,11 @@ static void raise_mce(struct mce *m) put_online_cpus(); } else #endif + { + preempt_disable(); raise_local(); + preempt_enable(); + } } /* Error injection interface */ @@ -225,7 +230,10 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, * so do it a jiffie or two later everywhere. */ schedule_timeout(2); + + mutex_lock(&mce_inject_mutex); raise_mce(&m); + mutex_unlock(&mce_inject_mutex); return usize; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index ed44c8a..6a05c1d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -28,6 +28,18 @@ extern int mce_ser; extern struct mce_bank *mce_banks; +#ifdef CONFIG_X86_MCE_INTEL +unsigned long mce_intel_adjust_timer(unsigned long interval); +void mce_intel_cmci_poll(void); +void mce_intel_hcpu_update(unsigned long cpu); +#else +# define mce_intel_adjust_timer mce_adjust_timer_default +static inline void mce_intel_cmci_poll(void) { } +static inline void mce_intel_hcpu_update(unsigned long cpu) { } +#endif + +void mce_timer_kick(unsigned long interval); + #ifdef CONFIG_ACPI_APEI int apei_write_mce(struct mce *m); ssize_t apei_read_mce(struct mce *m, u64 *record_id); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 292d025..29e87d3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -83,6 +83,7 @@ static int mce_dont_log_ce __read_mostly; int mce_cmci_disabled __read_mostly; int mce_ignore_ce __read_mostly; int mce_ser __read_mostly; +int mce_bios_cmci_threshold __read_mostly; struct mce_bank *mce_banks __read_mostly; @@ -1266,6 +1267,14 @@ static unsigned long check_interval = 5 * 60; /* 5 minutes */ static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); +static unsigned long mce_adjust_timer_default(unsigned long interval) +{ + return interval; +} + +static unsigned long (*mce_adjust_timer)(unsigned long interval) = + mce_adjust_timer_default; + static void mce_timer_fn(unsigned long data) { struct timer_list *t = &__get_cpu_var(mce_timer); @@ -1276,6 +1285,7 @@ static void mce_timer_fn(unsigned long data) if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_poll_banks)); + mce_intel_cmci_poll(); } /* @@ -1283,14 +1293,38 @@ static void mce_timer_fn(unsigned long data) * polling interval, otherwise increase the polling interval. */ iv = __this_cpu_read(mce_next_interval); - if (mce_notify_irq()) + if (mce_notify_irq()) { iv = max(iv / 2, (unsigned long) HZ/100); - else + } else { iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); + iv = mce_adjust_timer(iv); + } __this_cpu_write(mce_next_interval, iv); + /* Might have become 0 after CMCI storm subsided */ + if (iv) { + t->expires = jiffies + iv; + add_timer_on(t, smp_processor_id()); + } +} - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); +/* + * Ensure that the timer is firing in @interval from now. + */ +void mce_timer_kick(unsigned long interval) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned long when = jiffies + interval; + unsigned long iv = __this_cpu_read(mce_next_interval); + + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); + } else { + t->expires = round_jiffies(when); + add_timer_on(t, smp_processor_id()); + } + if (interval < iv) + __this_cpu_write(mce_next_interval, interval); } /* Must not be called in IRQ context where del_timer_sync() can deadlock */ @@ -1585,6 +1619,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); + mce_adjust_timer = mce_intel_adjust_timer; break; case X86_VENDOR_AMD: mce_amd_feature_init(c); @@ -1594,23 +1629,28 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } -static void __mcheck_cpu_init_timer(void) +static void mce_start_timer(unsigned int cpu, struct timer_list *t) { - struct timer_list *t = &__get_cpu_var(mce_timer); - unsigned long iv = check_interval * HZ; + unsigned long iv = mce_adjust_timer(check_interval * HZ); - setup_timer(t, mce_timer_fn, smp_processor_id()); + __this_cpu_write(mce_next_interval, iv); - if (mce_ignore_ce) + if (mce_ignore_ce || !iv) return; - __this_cpu_write(mce_next_interval, iv); - if (!iv) - return; t->expires = round_jiffies(jiffies + iv); add_timer_on(t, smp_processor_id()); } +static void __mcheck_cpu_init_timer(void) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + unsigned int cpu = smp_processor_id(); + + setup_timer(t, mce_timer_fn, cpu); + mce_start_timer(cpu, t); +} + /* Handle unconfigured int18 (should never happen) */ static void unexpected_machine_check(struct pt_regs *regs, long error_code) { @@ -1907,6 +1947,7 @@ static struct miscdevice mce_chrdev_device = { * check, or 0 to not wait * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. * mce=nobootlog Don't log MCEs from before booting. + * mce=bios_cmci_threshold Don't program the CMCI threshold */ static int __init mcheck_enable(char *str) { @@ -1926,6 +1967,8 @@ static int __init mcheck_enable(char *str) mce_ignore_ce = 1; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) mce_bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + mce_bios_cmci_threshold = 1; else if (isdigit(str[0])) { get_option(&str, &tolerant); if (*str == ',') { @@ -2166,6 +2209,11 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { &mce_cmci_disabled }; +static struct dev_ext_attribute dev_attr_bios_cmci_threshold = { + __ATTR(bios_cmci_threshold, 0444, device_show_int, NULL), + &mce_bios_cmci_threshold +}; + static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, @@ -2174,6 +2222,7 @@ static struct device_attribute *mce_device_attrs[] = { &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, &dev_attr_cmci_disabled.attr, + &dev_attr_bios_cmci_threshold.attr, NULL }; @@ -2294,38 +2343,33 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) unsigned int cpu = (unsigned long)hcpu; struct timer_list *t = &per_cpu(mce_timer, cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: mce_device_create(cpu); if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); break; case CPU_DEAD: - case CPU_DEAD_FROZEN: if (threshold_cpu_callback) threshold_cpu_callback(action, cpu); mce_device_remove(cpu); + mce_intel_hcpu_update(cpu); break; case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - del_timer_sync(t); smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + del_timer_sync(t); break; case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - if (!mce_ignore_ce && check_interval) { - t->expires = round_jiffies(jiffies + - per_cpu(mce_next_interval, cpu)); - add_timer_on(t, cpu); - } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + mce_start_timer(cpu, t); break; - case CPU_POST_DEAD: + } + + if (action == CPU_POST_DEAD) { /* intentionally ignoring frozen here */ cmci_rediscover(cpu); - break; } + return NOTIFY_OK; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 38e49bc9..5f88abf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -15,6 +15,8 @@ #include <asm/msr.h> #include <asm/mce.h> +#include "mce-internal.h" + /* * Support for Intel Correct Machine Check Interrupts. This allows * the CPU to raise an interrupt when a corrected machine check happened. @@ -30,7 +32,22 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); */ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); -#define CMCI_THRESHOLD 1 +#define CMCI_THRESHOLD 1 +#define CMCI_POLL_INTERVAL (30 * HZ) +#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_THRESHOLD 15 + +static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); +static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); +static DEFINE_PER_CPU(unsigned int, cmci_storm_state); + +enum { + CMCI_STORM_NONE, + CMCI_STORM_ACTIVE, + CMCI_STORM_SUBSIDED, +}; + +static atomic_t cmci_storm_on_cpus; static int cmci_supported(int *banks) { @@ -53,6 +70,93 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +void mce_intel_cmci_poll(void) +{ + if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) + return; + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); +} + +void mce_intel_hcpu_update(unsigned long cpu) +{ + if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) + atomic_dec(&cmci_storm_on_cpus); + + per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +} + +unsigned long mce_intel_adjust_timer(unsigned long interval) +{ + int r; + + if (interval < CMCI_POLL_INTERVAL) + return interval; + + switch (__this_cpu_read(cmci_storm_state)) { + case CMCI_STORM_ACTIVE: + /* + * We switch back to interrupt mode once the poll timer has + * silenced itself. That means no events recorded and the + * timer interval is back to our poll interval. + */ + __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); + r = atomic_sub_return(1, &cmci_storm_on_cpus); + if (r == 0) + pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ + + case CMCI_STORM_SUBSIDED: + /* + * We wait for all cpus to go back to SUBSIDED + * state. When that happens we switch back to + * interrupt mode. + */ + if (!atomic_read(&cmci_storm_on_cpus)) { + __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); + cmci_reenable(); + cmci_recheck(); + } + return CMCI_POLL_INTERVAL; + default: + /* + * We have shiny weather. Let the poll do whatever it + * thinks. + */ + return interval; + } +} + +static bool cmci_storm_detect(void) +{ + unsigned int cnt = __this_cpu_read(cmci_storm_cnt); + unsigned long ts = __this_cpu_read(cmci_time_stamp); + unsigned long now = jiffies; + int r; + + if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) + return true; + + if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { + cnt++; + } else { + cnt = 1; + __this_cpu_write(cmci_time_stamp, now); + } + __this_cpu_write(cmci_storm_cnt, cnt); + + if (cnt <= CMCI_STORM_THRESHOLD) + return false; + + cmci_clear(); + __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); + r = atomic_add_return(1, &cmci_storm_on_cpus); + mce_timer_kick(CMCI_POLL_INTERVAL); + + if (r == 1) + pr_notice("CMCI storm detected: switching to poll mode\n"); + return true; +} + /* * The interrupt handler. This is called on every event. * Just call the poller directly to log any events. @@ -61,33 +165,28 @@ static int cmci_supported(int *banks) */ static void intel_threshold_interrupt(void) { + if (cmci_storm_detect()) + return; machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); mce_notify_irq(); } -static void print_update(char *type, int *hdr, int num) -{ - if (*hdr == 0) - printk(KERN_INFO "CPU %d MCA banks", smp_processor_id()); - *hdr = 1; - printk(KERN_CONT " %s:%d", type, num); -} - /* * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks * on this CPU. Use the algorithm recommended in the SDM to discover shared * banks. */ -static void cmci_discover(int banks, int boot) +static void cmci_discover(int banks) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); unsigned long flags; - int hdr = 0; int i; + int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; + int bios_zero_thresh = 0; if (test_bit(i, owned)) continue; @@ -96,29 +195,52 @@ static void cmci_discover(int banks, int boot) /* Already owned by someone else? */ if (val & MCI_CTL2_CMCI_EN) { - if (test_and_clear_bit(i, owned) && !boot) - print_update("SHD", &hdr, i); + clear_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); continue; } - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD; + if (!mce_bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { + /* + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. + */ + bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; + } + + val |= MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Did the enable bit stick? -- the bank supports CMCI */ if (val & MCI_CTL2_CMCI_EN) { - if (!test_and_set_bit(i, owned) && !boot) - print_update("CMCI", &hdr, i); + set_bit(i, owned); __clear_bit(i, __get_cpu_var(mce_poll_banks)); + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mce_bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + bios_wrong_thresh = 1; } else { WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); - if (hdr) - printk(KERN_CONT "\n"); + if (mce_bios_cmci_threshold && bios_wrong_thresh) { + pr_info_once( + "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); + pr_info_once( + "bios_cmci_threshold: Make sure your BIOS supports this boot option\n"); + } } /* @@ -156,7 +278,7 @@ void cmci_clear(void) continue; /* Disable CMCI */ rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK); + val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } @@ -186,7 +308,7 @@ void cmci_rediscover(int dying) continue; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } set_cpus_allowed_ptr(current, old); @@ -200,7 +322,7 @@ void cmci_reenable(void) { int banks; if (cmci_supported(&banks)) - cmci_discover(banks, 0); + cmci_discover(banks); } static void intel_init_cmci(void) @@ -211,7 +333,7 @@ static void intel_init_cmci(void) return; mce_threshold_vector = intel_threshold_interrupt; - cmci_discover(banks, 1); + cmci_discover(banks); /* * For CPU #0 this runs with still disabled APIC, but that's * ok because only the vector is set up. We still do another diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 6605a81..8b6defe 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[]; extern struct event_constraint intel_snb_pebs_event_constraints[]; +extern struct event_constraint intel_ivb_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 7bfb5be..eebd5ff 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -209,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config) return -EOPNOTSUPP; } +static const struct perf_event_attr ibs_notsupp = { + .exclude_user = 1, + .exclude_kernel = 1, + .exclude_hv = 1, + .exclude_idle = 1, + .exclude_host = 1, + .exclude_guest = 1, +}; + static int perf_ibs_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -229,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event) if (event->pmu != &perf_ibs->pmu) return -ENOENT; + if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp)) + return -EINVAL; + if (config & ~perf_ibs->config_mask) return -EINVAL; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 7f2739e..6bca492 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void) break; case 28: /* Atom */ + case 54: /* Cedariew */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2047,7 +2048,6 @@ __init int intel_pmu_init(void) case 42: /* SandyBridge */ case 45: /* SandyBridge, "Romely-EP" */ x86_add_quirk(intel_sandybridge_quirk); - case 58: /* IvyBridge */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, @@ -2072,6 +2072,29 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; + case 58: /* IvyBridge */ + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.extra_regs = intel_snb_extra_regs; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); + + pr_cont("IvyBridge events, "); + break; + default: switch (x86_pmu.version) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index e38d97b..826054a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_ivb_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 520b426..da02e9c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void) * to have an operational LBR which can freeze * on PMU interrupt */ - if (boot_cpu_data.x86_mask < 10) { + if (boot_cpu_data.x86_model == 28 + && boot_cpu_data.x86_mask < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 0a55710..99d96a4 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + static struct attribute *snb_uncore_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = { .constraints = snb_uncore_cbox_constraints, .ops = &snb_uncore_msr_ops, .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, }; static struct intel_uncore_type *snb_msr_uncores[] = { @@ -1944,7 +1950,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp static struct intel_uncore_box * uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - static struct intel_uncore_box *box; + struct intel_uncore_box *box; box = *per_cpu_ptr(pmu->box, cpu); if (box) @@ -2341,6 +2347,27 @@ int uncore_pmu_event_init(struct perf_event *event) return ret; } +static ssize_t uncore_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); + +static struct attribute *uncore_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group uncore_pmu_attr_group = { + .attrs = uncore_pmu_attrs, +}; + static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -2378,8 +2405,8 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) free_percpu(type->pmus[i].box); kfree(type->pmus); type->pmus = NULL; - kfree(type->attr_groups[1]); - type->attr_groups[1] = NULL; + kfree(type->events_group); + type->events_group = NULL; } static void __init uncore_types_exit(struct intel_uncore_type **types) @@ -2431,9 +2458,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type) for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->attr_groups[1] = events_group; + type->events_group = events_group; } + type->pmu_group = &uncore_pmu_attr_group; type->pmus = pmus; return 0; fail: diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 5b81c18..e68a455 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -369,10 +369,12 @@ struct intel_uncore_type { struct intel_uncore_pmu *pmus; struct intel_uncore_ops *ops; struct uncore_event_desc *event_descs; - const struct attribute_group *attr_groups[3]; + const struct attribute_group *attr_groups[4]; }; -#define format_group attr_groups[0] +#define pmu_group attr_groups[0] +#define format_group attr_groups[1] +#define events_group attr_groups[2] struct intel_uncore_ops { void (*init_box)(struct intel_uncore_box *); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 8022c66..fbd8955 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -140,10 +140,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = cpumask_first(cpu_online_mask); - else - *pos = cpumask_next(*pos - 1, cpu_online_mask); + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return &cpu_data(*pos); return NULL; diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 39472dd..60c7891 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -199,12 +199,14 @@ static int __init cpuid_init(void) goto out_chrdev; } cpuid_class->devnode = cpuid_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = cpuid_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -214,6 +216,7 @@ out_class: for_each_online_cpu(i) { cpuid_device_destroy(i); } + put_online_cpus(); class_destroy(cpuid_class); out_chrdev: __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); @@ -225,11 +228,13 @@ static void __exit cpuid_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); + put_online_cpus(); } module_init(cpuid_init); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 3ae2ced..b158152 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -342,6 +342,47 @@ const struct irq_domain_ops ioapic_irq_domain_ops = { .xlate = ioapic_xlate, }; +static void dt_add_ioapic_domain(unsigned int ioapic_num, + struct device_node *np) +{ + struct irq_domain *id; + struct mp_ioapic_gsi *gsi_cfg; + int ret; + int num; + + gsi_cfg = mp_ioapic_gsi_routing(ioapic_num); + num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; + + id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops, + (void *)ioapic_num); + BUG_ON(!id); + if (gsi_cfg->gsi_base == 0) { + /* + * The first NR_IRQS_LEGACY irq descs are allocated in + * early_irq_init() and need just a mapping. The + * remaining irqs need both. All of them are preallocated + * and assigned so we can keep the 1:1 mapping which the ioapic + * is having. + */ + ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY); + if (ret) + pr_err("Error mapping legacy IRQs: %d\n", ret); + + if (num > NR_IRQS_LEGACY) { + ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY, + NR_IRQS_LEGACY, num - NR_IRQS_LEGACY); + if (ret) + pr_err("Error creating mapping for the " + "remaining IRQs: %d\n", ret); + } + irq_set_default_host(id); + } else { + ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num); + if (ret) + pr_err("Error creating IRQ mapping: %d\n", ret); + } +} + static void __init ioapic_add_ofnode(struct device_node *np) { struct resource r; @@ -356,15 +397,7 @@ static void __init ioapic_add_ofnode(struct device_node *np) for (i = 0; i < nr_ioapics; i++) { if (r.start == mpc_ioapic_addr(i)) { - struct irq_domain *id; - struct mp_ioapic_gsi *gsi_cfg; - - gsi_cfg = mp_ioapic_gsi_routing(i); - - id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0, - &ioapic_irq_domain_ops, - (void*)i); - BUG_ON(!id); + dt_add_ioapic_domain(i, np); return; } } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 623f288..f438a44 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1109,17 +1109,21 @@ ENTRY(ftrace_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %eax + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax movl 0x4(%ebp), %edx + leal function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call ftrace_call: call ftrace_stub + addl $4,%esp /* skip NULL pointer */ popl %edx popl %ecx popl %eax +ftrace_ret: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -1131,6 +1135,71 @@ ftrace_stub: ret END(ftrace_caller) +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS,13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + +ftrace_restore_flags: + popf + jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) @@ -1171,9 +1240,6 @@ END(mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 69babd8..066334b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -56,6 +56,7 @@ #include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> +#include <asm/rcu.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -68,25 +69,51 @@ .section .entry.text, "ax" #ifdef CONFIG_FUNCTION_TRACER + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +#else +# define function_hook mcount +#endif + #ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(mcount) + +ENTRY(function_hook) retq -END(mcount) +END(function_hook) + +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + leaq function_trace_op, %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif +.endm ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ cmpl $0, function_trace_stop jne ftrace_stub - MCOUNT_SAVE_FRAME - - movq 0x38(%rsp), %rdi - movq 8(%rbp), %rsi - subq $MCOUNT_INSN_SIZE, %rdi + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx GLOBAL(ftrace_call) call ftrace_stub MCOUNT_RESTORE_FRAME +ftrace_return: #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -97,8 +124,78 @@ GLOBAL(ftrace_stub) retq END(ftrace_caller) +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, SS+8(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + #else /* ! CONFIG_DYNAMIC_FTRACE */ -ENTRY(mcount) + +ENTRY(function_hook) cmpl $0, function_trace_stop jne ftrace_stub @@ -119,8 +216,12 @@ GLOBAL(ftrace_stub) trace: MCOUNT_SAVE_FRAME - movq 0x38(%rsp), %rdi + movq RIP(%rsp), %rdi +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else movq 8(%rbp), %rsi +#endif subq $MCOUNT_INSN_SIZE, %rdi call *ftrace_trace_function @@ -128,20 +229,22 @@ trace: MCOUNT_RESTORE_FRAME jmp ftrace_stub -END(mcount) +END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - MCOUNT_SAVE_FRAME +#ifdef CC_USING_FENTRY + leaq SS+16(%rsp), %rdi + movq $0, %rdx /* No framepointers needed */ +#else leaq 8(%rbp), %rdi - movq 0x38(%rsp), %rsi movq (%rbp), %rdx +#endif + movq RIP(%rsp), %rsi subq $MCOUNT_INSN_SIZE, %rsi call prepare_ftrace_return @@ -342,15 +445,15 @@ ENDPROC(native_usergs_sysret64) .macro SAVE_ARGS_IRQ cld /* start from rbp in pt_regs and jump over */ - movq_cfi rdi, RDI-RBP - movq_cfi rsi, RSI-RBP - movq_cfi rdx, RDX-RBP - movq_cfi rcx, RCX-RBP - movq_cfi rax, RAX-RBP - movq_cfi r8, R8-RBP - movq_cfi r9, R9-RBP - movq_cfi r10, R10-RBP - movq_cfi r11, R11-RBP + movq_cfi rdi, (RDI-RBP) + movq_cfi rsi, (RSI-RBP) + movq_cfi rdx, (RDX-RBP) + movq_cfi rcx, (RCX-RBP) + movq_cfi rax, (RAX-RBP) + movq_cfi r8, (R8-RBP) + movq_cfi r9, (R9-RBP) + movq_cfi r10, (R10-RBP) + movq_cfi r11, (R11-RBP) /* Save rbp so that we can unwind from get_irq_regs() */ movq_cfi rbp, 0 @@ -384,7 +487,7 @@ ENDPROC(native_usergs_sysret64) .endm ENTRY(save_rest) - PARTIAL_FRAME 1 REST_SKIP+8 + PARTIAL_FRAME 1 (REST_SKIP+8) movq 5*8+16(%rsp), %r11 /* save return address */ movq_cfi rbx, RBX+16 movq_cfi rbp, RBP+16 @@ -440,7 +543,7 @@ ENTRY(ret_from_fork) LOCK ; btr $TIF_FORK,TI_flags(%r8) - pushq_cfi kernel_eflags(%rip) + pushq_cfi $0x0002 popfq_cfi # reset kernel eflags call schedule_tail # rdi: 'prev' task parameter @@ -565,7 +668,7 @@ sysret_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi jmp sysret_check @@ -678,7 +781,7 @@ int_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -974,7 +1077,7 @@ retint_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi - call schedule + SCHEDULE_USER popq_cfi %rdi GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) @@ -1449,7 +1552,7 @@ paranoid_userspace: paranoid_schedule: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) - call schedule + SCHEDULE_USER DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF jmp paranoid_userspace diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c3a7cb4..1d41402 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -206,6 +206,21 @@ static int ftrace_modify_code(unsigned long ip, unsigned const char *old_code, unsigned const char *new_code); +/* + * Should never be called: + * As it is only called by __ftrace_replace_code() which is called by + * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() + * which is called to turn mcount into nops or nops into function calls + * but not to convert a function from not using regs to one that uses + * regs, which ftrace_modify_call() is for. + */ +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + WARN_ON(1); + return -EINVAL; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); @@ -220,6 +235,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func) ret = ftrace_modify_code(ip, old, new); + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + } + atomic_dec(&modifying_ftrace_code); return ret; @@ -299,6 +322,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } +/* + * If the record has the FTRACE_FL_REGS set, that means that it + * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS + * is not not set, then it wants to convert to the normal callback. + */ +static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +/* + * The FTRACE_FL_REGS_EN is set when the record already points to + * a function that saves all the regs. Basically the '_EN' version + * represents the current state of the function. + */ +static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS_EN) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; @@ -306,7 +355,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -316,6 +365,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + ftrace_addr = get_ftrace_old_addr(rec); + /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -360,13 +413,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); + nop = ftrace_call_replace(ip, ftrace_addr); + + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) + goto update; + + /* Check both ftrace_addr and ftrace_old_addr */ + ftrace_addr = get_ftrace_old_addr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } + update: return probe_kernel_write((void *)ip, &nop[0], 1); } @@ -405,12 +466,14 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return add_update_call(rec, ftrace_addr); @@ -455,12 +518,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return finish_update_call(rec, ftrace_addr); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index f250431..675a050 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -19,24 +19,17 @@ #include <asm/fpu-internal.h> #include <asm/user.h> -#ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> -# include <asm/user32.h> -#else -# define save_i387_xstate_ia32 save_i387_xstate -# define restore_i387_xstate_ia32 restore_i387_xstate -# define _fpstate_ia32 _fpstate -# define _xstate_ia32 _xstate -# define sig_xstate_ia32_size sig_xstate_size -# define fx_sw_reserved_ia32 fx_sw_reserved -# define user_i387_ia32_struct user_i387_struct -# define user32_fxsr_struct user_fxsr_struct -#endif - /* * Were we in an interrupt that interrupted kernel mode? * - * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * For now, with eagerfpu we will return interrupted kernel FPU + * state as not-idle. TBD: Ideally we can change the return value + * to something like __thread_has_fpu(current). But we need to + * be careful of doing __thread_clear_has_fpu() before saving + * the FPU etc for supporting nested uses etc. For now, take + * the simple route! + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that * pair does nothing at all: the thread must not have fpu (so * that we don't try to save the FPU state), and TS must * be set (so that the clts/stts pair does nothing that is @@ -44,6 +37,9 @@ */ static inline bool interrupted_kernel_fpu_idle(void) { + if (use_eager_fpu()) + return 0; + return !__thread_has_fpu(current) && (read_cr0() & X86_CR0_TS); } @@ -77,29 +73,29 @@ bool irq_fpu_usable(void) } EXPORT_SYMBOL(irq_fpu_usable); -void kernel_fpu_begin(void) +void __kernel_fpu_begin(void) { struct task_struct *me = current; - WARN_ON_ONCE(!irq_fpu_usable()); - preempt_disable(); if (__thread_has_fpu(me)) { __save_init_fpu(me); __thread_clear_has_fpu(me); - /* We do 'stts()' in kernel_fpu_end() */ - } else { + /* We do 'stts()' in __kernel_fpu_end() */ + } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task, NULL); clts(); } } -EXPORT_SYMBOL(kernel_fpu_begin); +EXPORT_SYMBOL(__kernel_fpu_begin); -void kernel_fpu_end(void) +void __kernel_fpu_end(void) { - stts(); - preempt_enable(); + if (use_eager_fpu()) + math_state_restore(); + else + stts(); } -EXPORT_SYMBOL(kernel_fpu_end); +EXPORT_SYMBOL(__kernel_fpu_end); void unlazy_fpu(struct task_struct *tsk) { @@ -113,23 +109,15 @@ void unlazy_fpu(struct task_struct *tsk) } EXPORT_SYMBOL(unlazy_fpu); -#ifdef CONFIG_MATH_EMULATION -# define HAVE_HWFP (boot_cpu_data.hard_math) -#else -# define HAVE_HWFP 1 -#endif - -static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; - clts(); if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); asm volatile("fxsave %0" : : "m" (fx_scratch)); @@ -138,7 +126,6 @@ static void __cpuinit mxcsr_feature_mask_init(void) mask = 0x0000ffbf; } mxcsr_feature_mask &= mask; - stts(); } static void __cpuinit init_thread_xstate(void) @@ -192,9 +179,8 @@ void __cpuinit fpu_init(void) init_thread_xstate(); mxcsr_feature_mask_init(); - /* clean state in init */ - current_thread_info()->status = 0; - clear_used_math(); + xsave_init(); + eager_fpu_init(); } void fpu_finit(struct fpu *fpu) @@ -205,12 +191,7 @@ void fpu_finit(struct fpu *fpu) } if (cpu_has_fxsr) { - struct i387_fxsave_struct *fx = &fpu->state->fxsave; - - memset(fx, 0, xstate_size); - fx->cwd = 0x37f; - if (cpu_has_xmm) - fx->mxcsr = MXCSR_DEFAULT; + fx_finit(&fpu->state->fxsave); } else { struct i387_fsave_struct *fp = &fpu->state->fsave; memset(fp, 0, xstate_size); @@ -454,7 +435,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) * FXSR floating point environment conversions. */ -static void +void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; @@ -491,8 +472,8 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) memcpy(&to[i], &from[i], sizeof(to[0])); } -static void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) { struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; @@ -589,223 +570,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, } /* - * Signal frame handlers. - */ - -static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave; - - fp->status = fp->swd; - if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct))) - return -1; - return 1; -} - -static int save_i387_fxsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - struct user_i387_ia32_struct env; - int err = 0; - - convert_from_fxsr(&env, tsk); - if (__copy_to_user(buf, &env, sizeof(env))) - return -1; - - err |= __put_user(fx->swd, &buf->status); - err |= __put_user(X86_FXSR_MAGIC, &buf->magic); - if (err) - return -1; - - if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size)) - return -1; - return 1; -} - -static int save_i387_xsave(void __user *buf) -{ - struct task_struct *tsk = current; - struct _fpstate_ia32 __user *fx = buf; - int err = 0; - - - sanitize_i387_state(tsk); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. - * This will enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware applications can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - if (save_i387_fxsave(fx) < 0) - return -1; - - err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32, - sizeof(struct _fpx_sw_bytes)); - err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *) (buf + sig_xstate_ia32_size - - FP_XSTATE_MAGIC2_SIZE)); - if (err) - return -1; - - return 1; -} - -int save_i387_xstate_ia32(void __user *buf) -{ - struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf; - struct task_struct *tsk = current; - - if (!used_math()) - return 0; - - if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size)) - return -EACCES; - /* - * This will cause a "finit" to be triggered by the next - * attempted FPU operation by the 'current' process. - */ - clear_used_math(); - - if (!HAVE_HWFP) { - return fpregs_soft_get(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, fp) ? -1 : 1; - } - - unlazy_fpu(tsk); - - if (cpu_has_xsave) - return save_i387_xsave(fp); - if (cpu_has_fxsr) - return save_i387_fxsave(fp); - else - return save_i387_fsave(fp); -} - -static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf) -{ - struct task_struct *tsk = current; - - return __copy_from_user(&tsk->thread.fpu.state->fsave, buf, - sizeof(struct i387_fsave_struct)); -} - -static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf, - unsigned int size) -{ - struct task_struct *tsk = current; - struct user_i387_ia32_struct env; - int err; - - err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0], - size); - /* mxcsr reserved bits must be masked to zero for security reasons */ - tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - if (err || __copy_from_user(&env, buf, sizeof(env))) - return 1; - convert_to_fxsr(tsk, &env); - - return 0; -} - -static int restore_i387_xsave(void __user *buf) -{ - struct _fpx_sw_bytes fx_sw_user; - struct _fpstate_ia32 __user *fx_user = - ((struct _fpstate_ia32 __user *) buf); - struct i387_fxsave_struct __user *fx = - (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0]; - struct xsave_hdr_struct *xsave_hdr = - ¤t->thread.fpu.state->xsave.xsave_hdr; - u64 mask; - int err; - - if (check_for_xstate(fx, buf, &fx_sw_user)) - goto fx_only; - - mask = fx_sw_user.xstate_bv; - - err = restore_i387_fxsave(buf, fx_sw_user.xstate_size); - - xsave_hdr->xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; - - /* - * Init the state that is not present in the memory layout - * and enabled by the OS. - */ - mask = ~(pcntxt_mask & ~mask); - xsave_hdr->xstate_bv &= mask; - - return err; -fx_only: - /* - * Couldn't find the extended state information in the memory - * layout. Restore the FP/SSE and init the other extended state - * enabled by the OS. - */ - xsave_hdr->xstate_bv = XSTATE_FPSSE; - return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct)); -} - -int restore_i387_xstate_ia32(void __user *buf) -{ - int err; - struct task_struct *tsk = current; - struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf; - - if (HAVE_HWFP) - clear_fpu(tsk); - - if (!buf) { - if (used_math()) { - clear_fpu(tsk); - clear_used_math(); - } - - return 0; - } else - if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size)) - return -EACCES; - - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } - - if (HAVE_HWFP) { - if (cpu_has_xsave) - err = restore_i387_xsave(buf); - else if (cpu_has_fxsr) - err = restore_i387_fxsave(fp, sizeof(struct - i387_fxsave_struct)); - else - err = restore_i387_fsave(fp); - } else { - err = fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, fp) != 0; - } - set_used_math(); - - return err; -} - -/* * FPU state for core dumps. * This is only used for a.out dumps now. * It is declared generically using elf_fpregset_t (which is diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 36d1853..9a5c460 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -263,7 +263,7 @@ static void i8259A_shutdown(void) * out of. */ outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ - outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ + outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ } static struct syscore_ops i8259_syscore_ops = { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index d44f782..e4595f1 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -92,7 +92,8 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - + irq_stats(j)->irq_tlb_count); seq_printf(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) @@ -147,7 +148,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; - sum += irq_stats(cpu)->irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR sum += irq_stats(cpu)->irq_thermal_count; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e2f751e..57916c0 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -541,6 +541,23 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } +#ifdef KPROBES_CAN_USE_FTRACE +static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); +} +#endif + /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. @@ -599,6 +616,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } else if (kprobe_running()) { p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { +#ifdef KPROBES_CAN_USE_FTRACE + if (kprobe_ftrace(p)) { + skip_singlestep(p, regs, kcb); + return 1; + } +#endif setup_singlestep(p, regs, kcb, 0); return 1; } @@ -1052,6 +1075,50 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } +#ifdef KPROBES_CAN_USE_FTRACE +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} +#endif + int __init arch_init_kprobes(void) { return arch_init_optprobes(); diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 82746f9..7720ff5 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -75,20 +75,113 @@ struct microcode_amd { static struct equiv_cpu_entry *equiv_cpu_table; -/* page-sized ucode patch buffer */ -void *patch; +struct ucode_patch { + struct list_head plist; + void *data; + u32 patch_id; + u16 equiv_cpu; +}; + +static LIST_HEAD(pcache); + +static u16 find_equiv_id(unsigned int cpu) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + int i = 0; + + if (!equiv_cpu_table) + return 0; + + while (equiv_cpu_table[i].installed_cpu != 0) { + if (uci->cpu_sig.sig == equiv_cpu_table[i].installed_cpu) + return equiv_cpu_table[i].equiv_cpu; + + i++; + } + return 0; +} + +static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu) +{ + int i = 0; + + BUG_ON(!equiv_cpu_table); + + while (equiv_cpu_table[i].equiv_cpu != 0) { + if (equiv_cpu == equiv_cpu_table[i].equiv_cpu) + return equiv_cpu_table[i].installed_cpu; + i++; + } + return 0; +} + +/* + * a small, trivial cache of per-family ucode patches + */ +static struct ucode_patch *cache_find_patch(u16 equiv_cpu) +{ + struct ucode_patch *p; + + list_for_each_entry(p, &pcache, plist) + if (p->equiv_cpu == equiv_cpu) + return p; + return NULL; +} + +static void update_cache(struct ucode_patch *new_patch) +{ + struct ucode_patch *p; + + list_for_each_entry(p, &pcache, plist) { + if (p->equiv_cpu == new_patch->equiv_cpu) { + if (p->patch_id >= new_patch->patch_id) + /* we already have the latest patch */ + return; + + list_replace(&p->plist, &new_patch->plist); + kfree(p->data); + kfree(p); + return; + } + } + /* no patch found, add it */ + list_add_tail(&new_patch->plist, &pcache); +} + +static void free_cache(void) +{ + struct ucode_patch *p, *tmp; + + list_for_each_entry_safe(p, tmp, &pcache, plist) { + __list_del(p->plist.prev, p->plist.next); + kfree(p->data); + kfree(p); + } +} + +static struct ucode_patch *find_patch(unsigned int cpu) +{ + u16 equiv_id; + + equiv_id = find_equiv_id(cpu); + if (!equiv_id) + return NULL; + + return cache_find_patch(equiv_id); +} static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); + csig->sig = cpuid_eax(0x00000001); csig->rev = c->microcode; pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); return 0; } -static unsigned int verify_ucode_size(int cpu, u32 patch_size, +static unsigned int verify_patch_size(int cpu, u32 patch_size, unsigned int size) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -118,95 +211,37 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size, return patch_size; } -static u16 find_equiv_id(void) +static int apply_microcode_amd(int cpu) { - unsigned int current_cpu_id, i = 0; - - BUG_ON(equiv_cpu_table == NULL); - - current_cpu_id = cpuid_eax(0x00000001); - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (current_cpu_id == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } - return 0; -} + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_amd *mc_amd; + struct ucode_cpu_info *uci; + struct ucode_patch *p; + u32 rev, dummy; -/* - * we signal a good patch is found by returning its size > 0 - */ -static int get_matching_microcode(int cpu, const u8 *ucode_ptr, - unsigned int leftover_size, int rev, - unsigned int *current_size) -{ - struct microcode_header_amd *mc_hdr; - unsigned int actual_size, patch_size; - u16 equiv_cpu_id; + BUG_ON(raw_smp_processor_id() != cpu); - /* size of the current patch we're staring at */ - patch_size = *(u32 *)(ucode_ptr + 4); - *current_size = patch_size + SECTION_HDR_SIZE; + uci = ucode_cpu_info + cpu; - equiv_cpu_id = find_equiv_id(); - if (!equiv_cpu_id) + p = find_patch(cpu); + if (!p) return 0; - /* - * let's look at the patch header itself now - */ - mc_hdr = (struct microcode_header_amd *)(ucode_ptr + SECTION_HDR_SIZE); + mc_amd = p->data; + uci->mc = p->data; - if (mc_hdr->processor_rev_id != equiv_cpu_id) - return 0; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* ucode might be chipset specific -- currently we don't support this */ - if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { - pr_err("CPU%d: chipset specific code not yet supported\n", - cpu); + /* need to apply patch? */ + if (rev >= mc_amd->hdr.patch_id) { + c->microcode = rev; return 0; } - if (mc_hdr->patch_id <= rev) - return 0; - - /* - * now that the header looks sane, verify its size - */ - actual_size = verify_ucode_size(cpu, patch_size, leftover_size); - if (!actual_size) - return 0; - - /* clear the patch buffer */ - memset(patch, 0, PAGE_SIZE); - - /* all looks ok, get the binary patch */ - get_ucode_data(patch, ucode_ptr + SECTION_HDR_SIZE, actual_size); - - return actual_size; -} - -static int apply_microcode_amd(int cpu) -{ - u32 rev, dummy; - int cpu_num = raw_smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - struct microcode_amd *mc_amd = uci->mc; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - /* We should bind the task to the CPU */ - BUG_ON(cpu_num != cpu); - - if (mc_amd == NULL) - return 0; - wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); - /* get patch id after patching */ - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* check current patch id and patch's id for match */ + /* verify patch application was successful */ + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev != mc_amd->hdr.patch_id) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -238,7 +273,7 @@ static int install_equiv_cpu_table(const u8 *buf) return -ENOMEM; } - get_ucode_data(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); + memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size); /* add header length */ return size + CONTAINER_HDR_SZ; @@ -250,61 +285,113 @@ static void free_equiv_cpu_table(void) equiv_cpu_table = NULL; } -static enum ucode_state -generic_load_microcode(int cpu, const u8 *data, size_t size) +static void cleanup(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct microcode_header_amd *mc_hdr = NULL; - unsigned int mc_size, leftover, current_size = 0; + free_equiv_cpu_table(); + free_cache(); +} + +/* + * We return the current size even if some of the checks failed so that + * we can skip over the next patch. If we return a negative value, we + * signal a grave error like a memory allocation has failed and the + * driver cannot continue functioning normally. In such cases, we tear + * down everything we've used up so far and exit. + */ +static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct microcode_header_amd *mc_hdr; + struct ucode_patch *patch; + unsigned int patch_size, crnt_size, ret; + u32 proc_fam; + u16 proc_id; + + patch_size = *(u32 *)(fw + 4); + crnt_size = patch_size + SECTION_HDR_SIZE; + mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE); + proc_id = mc_hdr->processor_rev_id; + + proc_fam = find_cpu_family_by_equiv_cpu(proc_id); + if (!proc_fam) { + pr_err("No patch family for equiv ID: 0x%04x\n", proc_id); + return crnt_size; + } + + /* check if patch is for the current family */ + proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff); + if (proc_fam != c->x86) + return crnt_size; + + if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { + pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", + mc_hdr->patch_id); + return crnt_size; + } + + ret = verify_patch_size(cpu, patch_size, leftover); + if (!ret) { + pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id); + return crnt_size; + } + + patch = kzalloc(sizeof(*patch), GFP_KERNEL); + if (!patch) { + pr_err("Patch allocation failure.\n"); + return -EINVAL; + } + + patch->data = kzalloc(patch_size, GFP_KERNEL); + if (!patch->data) { + pr_err("Patch data allocation failure.\n"); + kfree(patch); + return -EINVAL; + } + + /* All looks ok, copy patch... */ + memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size); + INIT_LIST_HEAD(&patch->plist); + patch->patch_id = mc_hdr->patch_id; + patch->equiv_cpu = proc_id; + + /* ... and add to cache. */ + update_cache(patch); + + return crnt_size; +} + +static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) +{ + enum ucode_state ret = UCODE_ERROR; + unsigned int leftover; + u8 *fw = (u8 *)data; + int crnt_size = 0; int offset; - const u8 *ucode_ptr = data; - void *new_mc = NULL; - unsigned int new_rev = uci->cpu_sig.rev; - enum ucode_state state = UCODE_ERROR; - offset = install_equiv_cpu_table(ucode_ptr); + offset = install_equiv_cpu_table(data); if (offset < 0) { pr_err("failed to create equivalent cpu table\n"); - goto out; + return ret; } - ucode_ptr += offset; + fw += offset; leftover = size - offset; - if (*(u32 *)ucode_ptr != UCODE_UCODE_TYPE) { + if (*(u32 *)fw != UCODE_UCODE_TYPE) { pr_err("invalid type field in container file section header\n"); - goto free_table; + free_equiv_cpu_table(); + return ret; } while (leftover) { - mc_size = get_matching_microcode(cpu, ucode_ptr, leftover, - new_rev, ¤t_size); - if (mc_size) { - mc_hdr = patch; - new_mc = patch; - new_rev = mc_hdr->patch_id; - goto out_ok; - } - - ucode_ptr += current_size; - leftover -= current_size; - } + crnt_size = verify_and_add_patch(cpu, fw, leftover); + if (crnt_size < 0) + return ret; - if (!new_mc) { - state = UCODE_NFOUND; - goto free_table; + fw += crnt_size; + leftover -= crnt_size; } -out_ok: - uci->mc = new_mc; - state = UCODE_OK; - pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n", - cpu, uci->cpu_sig.rev, new_rev); - -free_table: - free_equiv_cpu_table(); - -out: - return state; + return UCODE_OK; } /* @@ -315,7 +402,7 @@ out: * * This legacy file is always smaller than 2K in size. * - * Starting at family 15h they are in family specific firmware files: + * Beginning with family 15h, they are in family-specific firmware files: * * amd-ucode/microcode_amd_fam15h.bin * amd-ucode/microcode_amd_fam16h.bin @@ -323,12 +410,17 @@ out: * * These might be larger than 2K. */ -static enum ucode_state request_microcode_amd(int cpu, struct device *device) +static enum ucode_state request_microcode_amd(int cpu, struct device *device, + bool refresh_fw) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; - const struct firmware *fw; - enum ucode_state ret = UCODE_NFOUND; struct cpuinfo_x86 *c = &cpu_data(cpu); + enum ucode_state ret = UCODE_NFOUND; + const struct firmware *fw; + + /* reload ucode container only on the boot cpu */ + if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + return UCODE_OK; if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); @@ -344,12 +436,17 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) goto fw_release; } - ret = generic_load_microcode(cpu, fw->data, fw->size); + /* free old equiv table */ + free_equiv_cpu_table(); + + ret = load_microcode_amd(cpu, fw->data, fw->size); + if (ret != UCODE_OK) + cleanup(); -fw_release: + fw_release: release_firmware(fw); -out: + out: return ret; } @@ -383,14 +480,10 @@ struct microcode_ops * __init init_amd_microcode(void) return NULL; } - patch = (void *)get_zeroed_page(GFP_KERNEL); - if (!patch) - return NULL; - return µcode_amd_ops; } void __exit exit_amd_microcode(void) { - free_page((unsigned long)patch); + cleanup(); } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 4873e62..3a04b22 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, if (do_microcode_update(buf, len) == 0) ret = (ssize_t)len; + if (ret > 0) + perf_check_microcode(); + mutex_unlock(µcode_mutex); put_online_cpus(); @@ -276,19 +279,18 @@ static struct platform_device *microcode_pdev; static int reload_for_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + enum ucode_state ustate; int err = 0; - if (uci->valid) { - enum ucode_state ustate; - - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - } + if (!uci->valid) + return err; + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); + if (ustate == UCODE_OK) + apply_microcode_on_target(cpu); + else + if (ustate == UCODE_ERROR) + err = -EINVAL; return err; } @@ -370,18 +372,15 @@ static void microcode_fini_cpu(int cpu) static enum ucode_state microcode_resume_cpu(int cpu) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - if (!uci->mc) - return UCODE_NFOUND; - pr_debug("CPU%d updated upon resume\n", cpu); - apply_microcode_on_target(cpu); + + if (apply_microcode_on_target(cpu)) + return UCODE_ERROR; return UCODE_OK; } -static enum ucode_state microcode_init_cpu(int cpu) +static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) { enum ucode_state ustate; @@ -392,7 +391,8 @@ static enum ucode_state microcode_init_cpu(int cpu) if (system_state != SYSTEM_RUNNING) return UCODE_NFOUND; - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev); + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, + refresh_fw); if (ustate == UCODE_OK) { pr_debug("CPU%d updated upon init\n", cpu); @@ -405,14 +405,11 @@ static enum ucode_state microcode_init_cpu(int cpu) static enum ucode_state microcode_update_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; if (uci->valid) - ustate = microcode_resume_cpu(cpu); - else - ustate = microcode_init_cpu(cpu); + return microcode_resume_cpu(cpu); - return ustate; + return microcode_init_cpu(cpu, false); } static int mc_device_add(struct device *dev, struct subsys_interface *sif) @@ -428,7 +425,7 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif) if (err) return err; - if (microcode_init_cpu(cpu) == UCODE_ERROR) + if (microcode_init_cpu(cpu, true) == UCODE_ERROR) return -EINVAL; return err; @@ -477,34 +474,41 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) struct device *dev; dev = get_cpu_device(cpu); - switch (action) { + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: microcode_update_cpu(cpu); - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: pr_debug("CPU%d added\n", cpu); + /* + * "break" is missing on purpose here because we want to fall + * through in order to create the sysfs group. + */ + + case CPU_DOWN_FAILED: if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); break; + case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&dev->kobj, &mc_attr_group); pr_debug("CPU%d removed\n", cpu); break; /* + * case CPU_DEAD: + * * When a CPU goes offline, don't free up or invalidate the copy of * the microcode in kernel memory, so that we can reuse it when the * CPU comes back online without unnecessarily requesting the userspace * for it again. */ - case CPU_UP_CANCELED_FROZEN: - /* The CPU refused to come up during a system resume */ - microcode_fini_cpu(cpu); - break; } + + /* The CPU refused to come up during a system resume */ + if (action == CPU_UP_CANCELED_FROZEN) + microcode_fini_cpu(cpu); + return NOTIFY_OK; } diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 0327e2b..3544aed 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -405,7 +405,8 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } -static enum ucode_state request_microcode_fw(int cpu, struct device *device) +static enum ucode_state request_microcode_fw(int cpu, struct device *device, + bool refresh_fw) { char name[30]; struct cpuinfo_x86 *c = &cpu_data(cpu); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index eb11369..a7c5661 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -257,12 +257,14 @@ static int __init msr_init(void) goto out_chrdev; } msr_class->devnode = msr_devnode; + get_online_cpus(); for_each_online_cpu(i) { err = msr_device_create(i); if (err != 0) goto out_class; } register_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); err = 0; goto out; @@ -271,6 +273,7 @@ out_class: i = 0; for_each_online_cpu(i) msr_device_destroy(i); + put_online_cpus(); class_destroy(msr_class); out_chrdev: __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); @@ -281,11 +284,13 @@ out: static void __exit msr_exit(void) { int cpu = 0; + get_online_cpus(); for_each_online_cpu(cpu) msr_device_destroy(cpu); class_destroy(msr_class); __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); + put_online_cpus(); } module_init(msr_init); diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c new file mode 100644 index 0000000..e309cc5 --- /dev/null +++ b/arch/x86/kernel/perf_regs.c @@ -0,0 +1,105 @@ +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/perf_event.h> +#include <linux/bug.h> +#include <linux/stddef.h> +#include <asm/perf_regs.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_X86_32 +#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX +#else +#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX +#endif + +#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) + +static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { + PT_REGS_OFFSET(PERF_REG_X86_AX, ax), + PT_REGS_OFFSET(PERF_REG_X86_BX, bx), + PT_REGS_OFFSET(PERF_REG_X86_CX, cx), + PT_REGS_OFFSET(PERF_REG_X86_DX, dx), + PT_REGS_OFFSET(PERF_REG_X86_SI, si), + PT_REGS_OFFSET(PERF_REG_X86_DI, di), + PT_REGS_OFFSET(PERF_REG_X86_BP, bp), + PT_REGS_OFFSET(PERF_REG_X86_SP, sp), + PT_REGS_OFFSET(PERF_REG_X86_IP, ip), + PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags), + PT_REGS_OFFSET(PERF_REG_X86_CS, cs), + PT_REGS_OFFSET(PERF_REG_X86_SS, ss), +#ifdef CONFIG_X86_32 + PT_REGS_OFFSET(PERF_REG_X86_DS, ds), + PT_REGS_OFFSET(PERF_REG_X86_ES, es), + PT_REGS_OFFSET(PERF_REG_X86_FS, fs), + PT_REGS_OFFSET(PERF_REG_X86_GS, gs), +#else + /* + * The pt_regs struct does not store + * ds, es, fs, gs in 64 bit mode. + */ + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, +#endif +#ifdef CONFIG_X86_64 + PT_REGS_OFFSET(PERF_REG_X86_R8, r8), + PT_REGS_OFFSET(PERF_REG_X86_R9, r9), + PT_REGS_OFFSET(PERF_REG_X86_R10, r10), + PT_REGS_OFFSET(PERF_REG_X86_R11, r11), + PT_REGS_OFFSET(PERF_REG_X86_R12, r12), + PT_REGS_OFFSET(PERF_REG_X86_R13, r13), + PT_REGS_OFFSET(PERF_REG_X86_R14, r14), + PT_REGS_OFFSET(PERF_REG_X86_R15, r15), +#endif +}; + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) + return 0; + + return regs_get_register(regs, pt_regs_offset[idx]); +} + +#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) + +#ifdef CONFIG_X86_32 +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} +#else /* CONFIG_X86_64 */ +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ + (1ULL << PERF_REG_X86_ES) | \ + (1ULL << PERF_REG_X86_FS) | \ + (1ULL << PERF_REG_X86_GS)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + if (mask & REG_NOSUPPORT) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_IA32)) + return PERF_SAMPLE_REGS_ABI_32; + else + return PERF_SAMPLE_REGS_ABI_64; +} +#endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 0bc72e2..d5f15c3 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -150,7 +150,7 @@ static struct resource *find_oprom(struct pci_dev *pdev) return oprom; } -void *pci_map_biosrom(struct pci_dev *pdev) +void __iomem *pci_map_biosrom(struct pci_dev *pdev) { struct resource *oprom = find_oprom(pdev); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ef6a845..dc3567e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -66,15 +66,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { int ret; - unlazy_fpu(src); - *dst = *src; if (fpu_allocated(&src->thread.fpu)) { memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); ret = fpu_alloc(&dst->thread.fpu); if (ret) return ret; - fpu_copy(&dst->thread.fpu, &src->thread.fpu); + fpu_copy(dst, src); } return 0; } @@ -97,16 +95,6 @@ void arch_task_cache_init(void) SLAB_PANIC | SLAB_NOTRACK, NULL); } -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - /* * Free current thread data structures etc.. */ @@ -163,7 +151,13 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - drop_fpu(tsk); + drop_init_fpu(tsk); + /* + * Free the FPU state for non xsave platforms. They get reallocated + * lazily at the first use. + */ + if (!use_eager_fpu()) + free_thread_xstate(tsk); } static void hard_disable_TSC(void) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 516fa18..b9ff83c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -190,10 +190,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->cs = __USER_CS; regs->ip = new_ip; regs->sp = new_sp; - /* - * Free the old FP and other extended state - */ - free_thread_xstate(current); } EXPORT_SYMBOL_GPL(start_thread); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0a980c9..8a6d20c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -232,10 +232,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - /* - * Free the old FP and other extended state - */ - free_thread_xstate(current); } void diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index c4c6a5c..b00b33a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include <linux/signal.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -1332,9 +1333,6 @@ static const struct user_regset_view user_x86_64_view = { #define genregs32_get genregs_get #define genregs32_set genregs_set -#define user_i387_ia32_struct user_i387_struct -#define user32_fxsr_struct user_fxsr_struct - #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION @@ -1463,6 +1461,8 @@ long syscall_trace_enter(struct pt_regs *regs) { long ret = 0; + rcu_user_exit(); + /* * If we stepped into a sysenter/syscall insn, it trapped in * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. @@ -1526,4 +1526,6 @@ void syscall_trace_leave(struct pt_regs *regs) !test_thread_flag(TIF_SYSCALL_EMU); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, step); + + rcu_user_enter(); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f4b9b80..4f16547 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -961,9 +961,7 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif - x86_init.paging.pagetable_setup_start(swapper_pg_dir); - paging_init(); - x86_init.paging.pagetable_setup_done(swapper_pg_dir); + x86_init.paging.pagetable_init(); if (boot_cpu_data.cpuid_level >= 0) { /* A CPU has %cr4 if and only if it has CPUID */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b280908..3160c26 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -114,7 +114,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, regs->orig_ax = -1; /* disable syscall checks */ get_user_ex(buf, &sc->fpstate); - err |= restore_i387_xstate(buf); + err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); get_user_ex(*pax, &sc->ax); } get_user_catch(err); @@ -206,35 +206,32 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { /* Default to using normal stack */ + unsigned long math_size = 0; unsigned long sp = regs->sp; + unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); -#ifdef CONFIG_X86_64 /* redzone */ - sp -= 128; -#endif /* CONFIG_X86_64 */ + if (config_enabled(CONFIG_X86_64)) + sp -= 128; if (!onsigstack) { /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { if (current->sas_ss_size) sp = current->sas_ss_sp + current->sas_ss_size; - } else { -#ifdef CONFIG_X86_32 - /* This is the legacy signal stack switching. */ - if ((regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) + } else if (config_enabled(CONFIG_X86_32) && + (regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; -#endif /* CONFIG_X86_32 */ } } if (used_math()) { - sp -= sig_xstate_size; -#ifdef CONFIG_X86_64 - sp = round_down(sp, 64); -#endif /* CONFIG_X86_64 */ + sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -247,8 +244,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (onsigstack && !likely(on_sig_stack(sp))) return (void __user *)-1L; - /* save i387 state */ - if (used_math() && save_i387_xstate(*fpstate) < 0) + /* save i387 and extended state */ + if (used_math() && + save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -474,6 +472,74 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } #endif /* CONFIG_X86_32 */ +static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, + siginfo_t *info, compat_sigset_t *set, + struct pt_regs *regs) +{ +#ifdef CONFIG_X86_X32_ABI + struct rt_sigframe_x32 __user *frame; + void __user *restorer; + int err = 0; + void __user *fpstate = NULL; + + frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + return -EFAULT; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user32(&frame->info, info)) + return -EFAULT; + } + + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + put_user_ex(0, &frame->uc.uc__pad0); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (ka->sa.sa_flags & SA_RESTORER) { + restorer = ka->sa.sa_restorer; + } else { + /* could use a vstub here */ + restorer = NULL; + err |= -EFAULT; + } + put_user_ex(restorer, &frame->pretcode); + } put_user_catch(err); + + if (err) + return -EFAULT; + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ka->sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; +#endif /* CONFIG_X86_X32_ABI */ + + return 0; +} + #ifdef CONFIG_X86_32 /* * Atomically swap in the new signal mask, and wait for a signal. @@ -612,55 +678,22 @@ static int signr_convert(int sig) return sig; } -#ifdef CONFIG_X86_32 - -#define is_ia32 1 -#define ia32_setup_frame __setup_frame -#define ia32_setup_rt_frame __setup_rt_frame - -#else /* !CONFIG_X86_32 */ - -#ifdef CONFIG_IA32_EMULATION -#define is_ia32 test_thread_flag(TIF_IA32) -#else /* !CONFIG_IA32_EMULATION */ -#define is_ia32 0 -#endif /* CONFIG_IA32_EMULATION */ - -#ifdef CONFIG_X86_X32_ABI -#define is_x32 test_thread_flag(TIF_X32) - -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, - struct pt_regs *regs); -#else /* !CONFIG_X86_X32_ABI */ -#define is_x32 0 -#endif /* CONFIG_X86_X32_ABI */ - -int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs *regs); - -#endif /* CONFIG_X86_32 */ - static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, struct pt_regs *regs) { int usig = signr_convert(sig); sigset_t *set = sigmask_to_save(); + compat_sigset_t *cset = (compat_sigset_t *) set; /* Set up the stack frame */ - if (is_ia32) { + if (is_ia32_frame()) { if (ka->sa.sa_flags & SA_SIGINFO) - return ia32_setup_rt_frame(usig, ka, info, set, regs); + return ia32_setup_rt_frame(usig, ka, info, cset, regs); else - return ia32_setup_frame(usig, ka, set, regs); -#ifdef CONFIG_X86_X32_ABI - } else if (is_x32) { - return x32_setup_rt_frame(usig, ka, info, - (compat_sigset_t *)set, regs); -#endif + return ia32_setup_frame(usig, ka, cset, regs); + } else if (is_x32_frame()) { + return x32_setup_rt_frame(usig, ka, info, cset, regs); } else { return __setup_rt_frame(sig, ka, info, set, regs); } @@ -779,6 +812,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { + rcu_user_exit(); + #ifdef CONFIG_X86_MCE /* notify userspace of pending MCEs */ if (thread_info_flags & _TIF_MCE_NOTIFY) @@ -804,6 +839,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); #endif /* CONFIG_X86_32 */ + + rcu_user_enter(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) @@ -824,72 +861,6 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) } #ifdef CONFIG_X86_X32_ABI -static int x32_setup_rt_frame(int sig, struct k_sigaction *ka, - siginfo_t *info, compat_sigset_t *set, - struct pt_regs *regs) -{ - struct rt_sigframe_x32 __user *frame; - void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate); - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - return -EFAULT; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user32(&frame->info, info)) - return -EFAULT; - } - - put_user_try { - /* Create the ucontext. */ - if (cpu_has_xsave) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - put_user_ex(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - put_user_ex(0, &frame->uc.uc__pad0); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (ka->sa.sa_flags & SA_RESTORER) { - restorer = ka->sa.sa_restorer; - } else { - /* could use a vstub here */ - restorer = NULL; - err |= -EFAULT; - } - put_user_ex(restorer, &frame->pretcode); - } put_user_catch(err); - - if (err) - return -EFAULT; - - /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; - - /* We use the x32 calling convention here... */ - regs->di = sig; - regs->si = (unsigned long) &frame->info; - regs->dx = (unsigned long) &frame->uc; - - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); - - regs->cs = __USER_CS; - regs->ss = __USER_DS; - - return 0; -} - asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs) { struct rt_sigframe_x32 __user *frame; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c5a8c3..c80a33b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -665,7 +665,8 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long boot_error = 0; int timeout; - alternatives_smp_switch(1); + /* Just in case we booted with a single CPU. */ + alternatives_enable_smp(); idle->thread.sp = (unsigned long) (((struct pt_regs *) (THREAD_SIZE + task_stack_page(idle))) - 1); @@ -1053,20 +1054,6 @@ out: preempt_enable(); } -void arch_disable_nonboot_cpus_begin(void) -{ - /* - * Avoid the smp alternatives switch during the disable_nonboot_cpus(). - * In the suspend path, we will be back in the SMP mode shortly anyways. - */ - skip_smp_alternatives = true; -} - -void arch_disable_nonboot_cpus_end(void) -{ - skip_smp_alternatives = false; -} - void arch_enable_nonboot_cpus_begin(void) { set_mtrr_aps_delayed_init(); @@ -1256,9 +1243,6 @@ void native_cpu_die(unsigned int cpu) if (per_cpu(cpu_state, cpu) == CPU_DEAD) { if (system_state == SYSTEM_RUNNING) pr_info("CPU %u is now offline\n", cpu); - - if (1 == num_online_cpus()) - alternatives_smp_switch(0); return; } msleep(100); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index c346d11..cd3b243 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child) return 1; } +void set_task_blockstep(struct task_struct *task, bool on) +{ + unsigned long debugctl; + + /* + * Ensure irq/preemption can't change debugctl in between. + * Note also that both TIF_BLOCKSTEP and debugctl should + * be changed atomically wrt preemption. + * FIXME: this means that set/clear TIF_BLOCKSTEP is simply + * wrong if task != current, SIGKILL can wakeup the stopped + * tracee and set/clear can play with the running task, this + * can confuse the next __switch_to_xtra(). + */ + local_irq_disable(); + debugctl = get_debugctlmsr(); + if (on) { + debugctl |= DEBUGCTLMSR_BTF; + set_tsk_thread_flag(task, TIF_BLOCKSTEP); + } else { + debugctl &= ~DEBUGCTLMSR_BTF; + clear_tsk_thread_flag(task, TIF_BLOCKSTEP); + } + if (task == current) + update_debugctlmsr(debugctl); + local_irq_enable(); +} + /* * Enable single or block step. */ @@ -169,19 +196,10 @@ static void enable_step(struct task_struct *child, bool block) * So no one should try to use debugger block stepping in a program * that uses user-mode single stepping itself. */ - if (enable_single_step(child) && block) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - set_tsk_thread_flag(child, TIF_BLOCKSTEP); - } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (enable_single_step(child) && block) + set_task_blockstep(child, true); + else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); } void user_enable_single_step(struct task_struct *child) @@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b481341..8276dc6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -55,6 +55,7 @@ #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/mce.h> +#include <asm/rcu.h> #include <asm/mach_traps.h> @@ -107,30 +108,45 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) dec_preempt_count(); } -static void __kprobes -do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, - long error_code, siginfo_t *info) +static int __kprobes +do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, + struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - #ifdef CONFIG_X86_32 if (regs->flags & X86_VM_MASK) { /* - * traps 0, 1, 3, 4, and 5 should be forwarded to vm86. + * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86. * On nmi (interrupt 2), do_trap should not be called. */ - if (trapnr < X86_TRAP_UD) - goto vm86_trap; - goto trap_signal; + if (trapnr < X86_TRAP_UD) { + if (!handle_vm86_trap((struct kernel_vm86_regs *) regs, + error_code, trapnr)) + return 0; + } + return -1; } #endif + if (!user_mode(regs)) { + if (!fixup_exception(regs)) { + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = trapnr; + die(str, regs, error_code); + } + return 0; + } - if (!user_mode(regs)) - goto kernel_trap; + return -1; +} -#ifdef CONFIG_X86_32 -trap_signal: -#endif +static void __kprobes +do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, + long error_code, siginfo_t *info) +{ + struct task_struct *tsk = current; + + + if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) + return; /* * We want error_code and trap_nr set for userspace faults and * kernelspace faults which result in die(), but not @@ -158,33 +174,20 @@ trap_signal: force_sig_info(signr, info, tsk); else force_sig(signr, tsk); - return; - -kernel_trap: - if (!fixup_exception(regs)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = trapnr; - die(str, regs, error_code); - } - return; - -#ifdef CONFIG_X86_32 -vm86_trap: - if (handle_vm86_trap((struct kernel_vm86_regs *) regs, - error_code, trapnr)) - goto trap_signal; - return; -#endif } #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ + exception_exit(regs); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ @@ -195,11 +198,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ + exception_enter(regs); \ + if (notify_die(DIE_TRAP, str, regs, error_code, \ + trapnr, signr) == NOTIFY_STOP) { \ + exception_exit(regs); \ return; \ + } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ + exception_exit(regs); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -222,12 +229,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { + exception_enter(regs); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) == NOTIFY_STOP) - return; - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); + X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { + preempt_conditional_sti(regs); + do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); + preempt_conditional_cli(regs); + } + exception_exit(regs); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -235,6 +244,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; + exception_enter(regs); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -255,16 +265,29 @@ do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + exception_enter(regs); conditional_sti(regs); #ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) - goto gp_in_vm86; + if (regs->flags & X86_VM_MASK) { + local_irq_enable(); + handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + goto exit; + } #endif tsk = current; - if (!user_mode(regs)) - goto gp_in_kernel; + if (!user_mode(regs)) { + if (fixup_exception(regs)) + goto exit; + + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = X86_TRAP_GP; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) + die("general protection fault", regs, error_code); + goto exit; + } tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -279,25 +302,8 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig(SIGSEGV, tsk); - return; - -#ifdef CONFIG_X86_32 -gp_in_vm86: - local_irq_enable(); - handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - return; -#endif - -gp_in_kernel: - if (fixup_exception(regs)) - return; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (notify_die(DIE_GPF, "general protection fault", regs, error_code, - X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); +exit: + exception_exit(regs); } /* May run on IST stack. */ @@ -312,15 +318,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + exception_enter(regs); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -331,6 +338,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); debug_stack_usage_dec(); +exit: + exception_exit(regs); } #ifdef CONFIG_X86_64 @@ -391,6 +400,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; + exception_enter(regs); + get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -406,7 +417,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Catch kmemcheck conditions first of all! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) - return; + goto exit; /* DR6 may or may not be cleared by the CPU */ set_debugreg(0, 6); @@ -421,7 +432,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, SIGTRAP) == NOTIFY_STOP) - return; + goto exit; /* * Let others (NMI) know that the debug stack is in use @@ -437,7 +448,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) X86_TRAP_DB); preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; + goto exit; } /* @@ -458,7 +469,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); - return; +exit: + exception_exit(regs); } /* @@ -555,14 +567,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 ignore_fpu_irq = 1; #endif - + exception_enter(regs); math_error(regs, error_code, X86_TRAP_MF); + exception_exit(regs); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { + exception_enter(regs); math_error(regs, error_code, X86_TRAP_XF); + exception_exit(regs); } dotraplinkage void @@ -613,11 +628,12 @@ void math_state_restore(void) } __thread_fpu_begin(tsk); + /* * Paranoid restore. send a SIGSEGV if we fail to restore the state. */ if (unlikely(restore_fpu_checking(tsk))) { - __thread_fpu_end(tsk); + drop_init_fpu(tsk); force_sig(SIGSEGV, tsk); return; } @@ -629,6 +645,9 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { + exception_enter(regs); + BUG_ON(use_eager_fpu()); + #ifdef CONFIG_MATH_EMULATION if (read_cr0() & X86_CR0_EM) { struct math_emu_info info = { }; @@ -637,6 +656,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + exception_exit(regs); return; } #endif @@ -644,12 +664,15 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif + exception_exit(regs); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + + exception_enter(regs); local_irq_enable(); info.si_signo = SIGILL; @@ -657,10 +680,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) info.si_code = ILL_BADSTK; info.si_addr = NULL; if (notify_die(DIE_TRAP, "iret exception", regs, error_code, - X86_TRAP_IRET, SIGILL) == NOTIFY_STOP) - return; - do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, - &info); + X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + &info); + } + exception_exit(regs); } #endif diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 36fd420..9538f00 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -41,6 +41,9 @@ /* Adjust the return address of a call insn */ #define UPROBE_FIX_CALL 0x2 +/* Instruction will modify TF, don't change it */ +#define UPROBE_FIX_SETF 0x4 + #define UPROBE_FIX_RIP_AX 0x8000 #define UPROBE_FIX_RIP_CX 0x4000 @@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) insn_get_opcode(insn); /* should be a nop */ switch (OPCODE1(insn)) { + case 0x9d: + /* popf */ + auprobe->fixups |= UPROBE_FIX_SETF; + break; case 0xc3: /* ret/lret */ case 0xcb: case 0xc2: @@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) * Skip these instructions as per the currently known x86 ISA. * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 } */ -bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { int i; @@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) } return false; } + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + bool ret = __skip_sstep(auprobe, regs); + if (ret && (regs->flags & X86_EFLAGS_TF)) + send_sig(SIGTRAP, current, 0); + return ret; +} + +void arch_uprobe_enable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + struct pt_regs *regs = task_pt_regs(task); + + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) + set_task_blockstep(task, false); +} + +void arch_uprobe_disable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED); + struct pt_regs *regs = task_pt_regs(task); + /* + * The state of TIF_BLOCKSTEP was not saved so we can get an extra + * SIGTRAP if we do not clear TF. We need to examine the opcode to + * make it right. + */ + if (unlikely(trapped)) { + if (!autask->saved_tf) + regs->flags &= ~X86_EFLAGS_TF; + } else { + if (autask->saved_tf) + send_sig(SIGTRAP, task, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + } +} diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 6020f6f..1330dd1 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -13,9 +13,13 @@ #include <asm/ftrace.h> #ifdef CONFIG_FUNCTION_TRACER -/* mcount is defined in assembly */ +/* mcount and __fentry__ are defined in assembly */ +#ifdef CC_USING_FENTRY +EXPORT_SYMBOL(__fentry__); +#else EXPORT_SYMBOL(mcount); #endif +#endif EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 9f3167e..7a3d075 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -26,7 +26,6 @@ void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } -void __init x86_init_pgd_noop(pgd_t *unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } @@ -68,8 +67,7 @@ struct x86_init_ops x86_init __initdata = { }, .paging = { - .pagetable_setup_start = native_pagetable_setup_start, - .pagetable_setup_done = native_pagetable_setup_done, + .pagetable_init = native_pagetable_init, }, .timers = { diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 3d3e207..4e89b3d 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -10,9 +10,7 @@ #include <linux/compat.h> #include <asm/i387.h> #include <asm/fpu-internal.h> -#ifdef CONFIG_IA32_EMULATION -#include <asm/sigcontext32.h> -#endif +#include <asm/sigframe.h> #include <asm/xcr.h> /* @@ -23,13 +21,9 @@ u64 pcntxt_mask; /* * Represents init state for the supported extended state. */ -static struct xsave_struct *init_xstate_buf; - -struct _fpx_sw_bytes fx_sw_reserved; -#ifdef CONFIG_IA32_EMULATION -struct _fpx_sw_bytes fx_sw_reserved_ia32; -#endif +struct xsave_struct *init_xstate_buf; +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; /* @@ -44,9 +38,9 @@ static unsigned int *xstate_offsets, *xstate_sizes, xstate_features; */ void __sanitize_i387_state(struct task_struct *tsk) { - u64 xstate_bv; - int feature_bit = 0x2; struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; + int feature_bit = 0x2; + u64 xstate_bv; if (!fx) return; @@ -104,213 +98,326 @@ void __sanitize_i387_state(struct task_struct *tsk) * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. */ -int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw_user) +static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) { int min_xstate_size = sizeof(struct i387_fxsave_struct) + sizeof(struct xsave_hdr_struct); unsigned int magic2; - int err; - err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0], - sizeof(struct _fpx_sw_bytes)); - if (err) - return -EFAULT; + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; - /* - * First Magic check failed. - */ - if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1) - return -EINVAL; + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; /* - * Check for error scenarios. - */ - if (fx_sw_user->xstate_size < min_xstate_size || - fx_sw_user->xstate_size > xstate_size || - fx_sw_user->xstate_size > fx_sw_user->extended_size) - return -EINVAL; - - err = __get_user(magic2, (__u32 *) (((void *)fpstate) + - fx_sw_user->extended_size - - FP_XSTATE_MAGIC2_SIZE)); - if (err) - return err; - /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ - if (magic2 != FP_XSTATE_MAGIC2) - return -EFAULT; + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; return 0; } -#ifdef CONFIG_X86_64 /* * Signal frame handlers. */ - -int save_i387_xstate(void __user *buf) +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) { - struct task_struct *tsk = current; - int err = 0; - - if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size)) - return -EACCES; + if (use_fxsr()) { + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct user_i387_ia32_struct env; + struct _fpstate_ia32 __user *fp = buf; - BUG_ON(sig_xstate_size < xstate_size); + convert_from_fxsr(&env, tsk); - if ((unsigned long)buf % 64) - pr_err("%s: bad fpstate %p\n", __func__, buf); - - if (!used_math()) - return 0; - - if (user_has_fpu()) { - if (use_xsave()) - err = xsave_user(buf); - else - err = fxsave_user(buf); - - if (err) - return err; - user_fpu_end(); + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, - xstate_size)) + struct i387_fsave_struct __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) return -1; } - clear_used_math(); /* trigger finit */ + return 0; +} - if (use_xsave()) { - struct _fpstate __user *fx = buf; - struct _xstate __user *x = buf; - u64 xstate_bv; +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xsave_struct __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xstate_bv; + int err; - err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved, - sizeof(struct _fpx_sw_bytes)); + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *) (buf + sig_xstate_size - - FP_XSTATE_MAGIC2_SIZE)); + if (!use_xsave()) + return err; - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers and - * set the FP/SSE bits. - */ - err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv); + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; + /* + * Read the xstate_bv which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv); + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xstate_bv in the xsave header. + * + * xsave aware apps can change the xstate_bv in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xstate_bv |= XSTATE_FPSSE; - if (err) - return err; - } + err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - return 1; + return err; +} + +static inline int save_user_xstate(struct xsave_struct __user *buf) +{ + int err; + + if (use_xsave()) + err = xsave_user(buf); + else if (use_fxsr()) + err = fxsave_user((struct i387_fxsave_struct __user *) buf); + else + err = fsave_user((struct i387_fsave_struct __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; } /* - * Restore the extended state if present. Otherwise, restore the FP/SSE - * state. + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. */ -static int restore_user_xstate(void __user *buf) +int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) { - struct _fpx_sw_bytes fx_sw_user; - u64 mask; - int err; + struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); - if (((unsigned long)buf % 64) || - check_for_xstate(buf, buf, &fx_sw_user)) - goto fx_only; + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); - mask = fx_sw_user.xstate_bv; + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; - /* - * restore the state passed by the user. - */ - err = xrestore_user(buf, mask); - if (err) - return err; + if (!HAVE_HWFP) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - /* - * init the state skipped by the user. - */ - mask = pcntxt_mask & ~mask; - if (unlikely(mask)) - xrstor_state(init_xstate_buf, mask); + if (user_has_fpu()) { + /* Save the live register state to the user directly. */ + if (save_user_xstate(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + fpu_fxsave(&tsk->thread.fpu); + } else { + sanitize_i387_state(tsk); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + drop_init_fpu(tsk); /* trigger finit */ return 0; +} -fx_only: - /* - * couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE); - return fxrstor_checking((__force struct i387_fxsave_struct *)buf); +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xstate_bv, int fx_only) +{ + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; + + if (use_xsave()) { + /* These bits must be zero. */ + xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + xsave_hdr->xstate_bv = XSTATE_FPSSE; + else + xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } } /* - * This restores directly out of user space. Exceptions are handled. + * Restore the extended state if present. Otherwise, restore the FP/SSE state. */ -int restore_i387_xstate(void __user *buf) +static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) { + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; + xrstor_state(init_xstate_buf, init_bv); + return fxrstor_checking((__force void *) buf); + } else { + u64 init_bv = pcntxt_mask & ~xbv; + if (unlikely(init_bv)) + xrstor_state(init_xstate_buf, init_bv); + return xrestore_user(buf, xbv); + } + } else if (use_fxsr()) { + return fxrstor_checking((__force void *) buf); + } else + return frstor_checking((__force void *) buf); +} + +int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); struct task_struct *tsk = current; - int err = 0; + int state_size = xstate_size; + u64 xstate_bv = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); if (!buf) { - if (used_math()) - goto clear; + drop_init_fpu(tsk); return 0; - } else - if (!access_ok(VERIFY_READ, buf, sig_xstate_size)) - return -EACCES; + } - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + if (!used_math() && init_fpu(tsk)) + return -1; + + if (!HAVE_HWFP) { + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; } - user_fpu_begin(); - if (use_xsave()) - err = restore_user_xstate(buf); - else - err = fxrstor_checking((__force struct i387_fxsave_struct *) - buf); - if (unlikely(err)) { + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct i387_fxsave_struct); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xstate_bv = fx_sw_user.xstate_bv; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears used_math(). This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * set_used_math() is again set. + */ + drop_fpu(tsk); + + if (__copy_from_user(xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); + set_used_math(); + } + + if (use_eager_fpu()) + math_state_restore(); + + return err; + } else { /* - * Encountered an error while doing the restore from the - * user buffer, clear the fpu state. + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). */ -clear: - clear_fpu(tsk); - clear_used_math(); + user_fpu_begin(); + if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { + drop_init_fpu(tsk); + return -1; + } } - return err; + + return 0; } -#endif /* * Prepare the SW reserved portion of the fxsave memory layout, indicating @@ -321,31 +428,22 @@ clear: */ static void prepare_fx_sw_frame(void) { - int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) + - FP_XSTATE_MAGIC2_SIZE; + int fsave_header_size = sizeof(struct i387_fsave_struct); + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - sig_xstate_size = sizeof(struct _fpstate) + size_extended; - -#ifdef CONFIG_IA32_EMULATION - sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended; -#endif - - memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved)); + if (config_enabled(CONFIG_X86_32)) + size += fsave_header_size; fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = sig_xstate_size; + fx_sw_reserved.extended_size = size; fx_sw_reserved.xstate_bv = pcntxt_mask; fx_sw_reserved.xstate_size = xstate_size; -#ifdef CONFIG_IA32_EMULATION - memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved, - sizeof(struct _fpx_sw_bytes)); - fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size; -#endif -} -#ifdef CONFIG_X86_64 -unsigned int sig_xstate_size = sizeof(struct _fpstate); -#endif + if (config_enabled(CONFIG_IA32_EMULATION)) { + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size += fsave_header_size; + } +} /* * Enable the extended processor state save/restore feature @@ -384,19 +482,21 @@ static void __init setup_xstate_features(void) /* * setup the xstate image representing the init state */ -static void __init setup_xstate_init(void) +static void __init setup_init_fpu_buf(void) { - setup_xstate_features(); - /* * Setup init_xstate_buf to represent the init state of * all the features managed by the xsave */ init_xstate_buf = alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); - init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; + fx_finit(&init_xstate_buf->i387); + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); - clts(); /* * Init all the features state with header_bv being 0x0 */ @@ -406,9 +506,21 @@ static void __init setup_xstate_init(void) * of any feature which is not represented by all zero's. */ xsave_state(init_xstate_buf, -1); - stts(); } +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + /* * Enable and initialize the xsave feature. */ @@ -445,8 +557,11 @@ static void __init xstate_enable_boot_cpu(void) update_regset_xstate_info(xstate_size, pcntxt_mask); prepare_fx_sw_frame(); + setup_init_fpu_buf(); - setup_xstate_init(); + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", pcntxt_mask, xstate_size); @@ -471,3 +586,43 @@ void __cpuinit xsave_init(void) next_func = xstate_enable; this_func(); } + +static inline void __init eager_fpu_init_bp(void) +{ + current->thread.fpu.state = + alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); + if (!init_xstate_buf) + setup_init_fpu_buf(); +} + +void __cpuinit eager_fpu_init(void) +{ + static __refdata void (*boot_func)(void) = eager_fpu_init_bp; + + clear_used_math(); + current_thread_info()->status = 0; + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + if (!cpu_has_eager_fpu) { + stts(); + return; + } + + if (boot_func) { + boot_func(); + boot_func = NULL; + } + + /* + * This is same as math_state_restore(). But use_xsave() is + * not yet patched to use math_state_restore(). + */ + init_fpu(current); + __thread_fpu_begin(current); + if (cpu_has_xsave) + xrstor_state(init_xstate_buf, -1); + else + fxrstor_checking(&init_xstate_buf->i387); +} diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index e498b18..9fc9aa7 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -318,7 +318,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x10) { u8 edge_irr = s->irr & ~s->elcr; int i; - bool found; + bool found = false; struct kvm_vcpu *vcpu; s->init4 = val & 1; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a71faf7..bca63f0 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -183,95 +183,6 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 -#define VMX_EXIT_REASONS \ - { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ - { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ - { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ - { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ - { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ - { EXIT_REASON_CPUID, "CPUID" }, \ - { EXIT_REASON_HLT, "HLT" }, \ - { EXIT_REASON_INVLPG, "INVLPG" }, \ - { EXIT_REASON_RDPMC, "RDPMC" }, \ - { EXIT_REASON_RDTSC, "RDTSC" }, \ - { EXIT_REASON_VMCALL, "VMCALL" }, \ - { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ - { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ - { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ - { EXIT_REASON_VMPTRST, "VMPTRST" }, \ - { EXIT_REASON_VMREAD, "VMREAD" }, \ - { EXIT_REASON_VMRESUME, "VMRESUME" }, \ - { EXIT_REASON_VMWRITE, "VMWRITE" }, \ - { EXIT_REASON_VMOFF, "VMOFF" }, \ - { EXIT_REASON_VMON, "VMON" }, \ - { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ - { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ - { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ - { EXIT_REASON_MSR_READ, "MSR_READ" }, \ - { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ - { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ - { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ - { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ - { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ - { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ - { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ - { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ - { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ - { EXIT_REASON_WBINVD, "WBINVD" } - -#define SVM_EXIT_REASONS \ - { SVM_EXIT_READ_CR0, "read_cr0" }, \ - { SVM_EXIT_READ_CR3, "read_cr3" }, \ - { SVM_EXIT_READ_CR4, "read_cr4" }, \ - { SVM_EXIT_READ_CR8, "read_cr8" }, \ - { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ - { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ - { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ - { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ - { SVM_EXIT_READ_DR0, "read_dr0" }, \ - { SVM_EXIT_READ_DR1, "read_dr1" }, \ - { SVM_EXIT_READ_DR2, "read_dr2" }, \ - { SVM_EXIT_READ_DR3, "read_dr3" }, \ - { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ - { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ - { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ - { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ - { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ - { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ - { SVM_EXIT_INTR, "interrupt" }, \ - { SVM_EXIT_NMI, "nmi" }, \ - { SVM_EXIT_SMI, "smi" }, \ - { SVM_EXIT_INIT, "init" }, \ - { SVM_EXIT_VINTR, "vintr" }, \ - { SVM_EXIT_CPUID, "cpuid" }, \ - { SVM_EXIT_INVD, "invd" }, \ - { SVM_EXIT_HLT, "hlt" }, \ - { SVM_EXIT_INVLPG, "invlpg" }, \ - { SVM_EXIT_INVLPGA, "invlpga" }, \ - { SVM_EXIT_IOIO, "io" }, \ - { SVM_EXIT_MSR, "msr" }, \ - { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ - { SVM_EXIT_SHUTDOWN, "shutdown" }, \ - { SVM_EXIT_VMRUN, "vmrun" }, \ - { SVM_EXIT_VMMCALL, "hypercall" }, \ - { SVM_EXIT_VMLOAD, "vmload" }, \ - { SVM_EXIT_VMSAVE, "vmsave" }, \ - { SVM_EXIT_STGI, "stgi" }, \ - { SVM_EXIT_CLGI, "clgi" }, \ - { SVM_EXIT_SKINIT, "skinit" }, \ - { SVM_EXIT_WBINVD, "wbinvd" }, \ - { SVM_EXIT_MONITOR, "monitor" }, \ - { SVM_EXIT_MWAIT, "mwait" }, \ - { SVM_EXIT_XSETBV, "xsetbv" }, \ - { SVM_EXIT_NPF, "npf" } - /* * Tracepoint for kvm guest exit: */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c00f03d..851aa7c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1493,8 +1493,12 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif - if (user_has_fpu()) - clts(); + /* + * If the FPU is not active (through the host task or + * the guest vcpu), then restore the cr0.TS bit. + */ + if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) + stts(); load_gdt(&__get_cpu_var(host_gdt)); } @@ -3619,6 +3623,7 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { + struct page *page; struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; @@ -3633,7 +3638,13 @@ static int alloc_apic_access_page(struct kvm *kvm) if (r) goto out; - kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); + page = gfn_to_page(kvm, 0xfee00); + if (is_error_page(page)) { + r = -EFAULT; + goto out; + } + + kvm->arch.apic_access_page = page; out: mutex_unlock(&kvm->slots_lock); return r; @@ -3641,6 +3652,7 @@ out: static int alloc_identity_pagetable(struct kvm *kvm) { + struct page *page; struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; @@ -3656,8 +3668,13 @@ static int alloc_identity_pagetable(struct kvm *kvm) if (r) goto out; - kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, - kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); + page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); + if (is_error_page(page)) { + r = -EFAULT; + goto out; + } + + kvm->arch.ept_identity_pagetable = page; out: mutex_unlock(&kvm->slots_lock); return r; @@ -3730,7 +3747,7 @@ static void vmx_set_constant_host_state(void) unsigned long tmpl; struct desc_ptr dt; - vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */ + vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */ vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ @@ -4530,7 +4547,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } - }; + } break; case 2: /* clts */ handle_clts(vcpu); @@ -6575,7 +6592,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) /* Exposing INVPCID only when PCID is exposed */ best = kvm_find_cpuid_entry(vcpu, 0x7, 0); if (vmx_invpcid_supported() && - best && (best->ecx & bit(X86_FEATURE_INVPCID)) && + best && (best->ebx & bit(X86_FEATURE_INVPCID)) && guest_cpuid_has_pcid(vcpu)) { exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, @@ -6585,7 +6602,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); if (best) - best->ecx &= ~bit(X86_FEATURE_INVPCID); + best->ebx &= ~bit(X86_FEATURE_INVPCID); } } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 148ed66..1f09552 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5113,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) !kvm_event_needs_reinjection(vcpu); } -static void vapic_enter(struct kvm_vcpu *vcpu) +static int vapic_enter(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct page *page; if (!apic || !apic->vapic_addr) - return; + return 0; page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); + if (is_error_page(page)) + return -EFAULT; vcpu->arch.apic->vapic_page = page; + return 0; } static void vapic_exit(struct kvm_vcpu *vcpu) @@ -5430,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - vapic_enter(vcpu); + r = vapic_enter(vcpu); + if (r) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + return r; + } r = 1; while (r > 0) { @@ -5972,7 +5979,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; - unlazy_fpu(current); + __kernel_fpu_begin(); fpu_restore_checking(&vcpu->arch.guest_fpu); trace_kvm_fpu(1); } @@ -5986,6 +5993,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) vcpu->guest_fpu_loaded = 0; fpu_save_init(&vcpu->arch.guest_fpu); + __kernel_fpu_end(); ++vcpu->stat.fpu_reload; kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); trace_kvm_fpu(0); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 76dcd9d..7dde46d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -18,6 +18,7 @@ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_START */ +#include <asm/rcu.h> /* exception_enter(), ... */ /* * Page fault error code bits: @@ -1000,8 +1001,8 @@ static int fault_in_kernel_space(unsigned long address) * and the problem, and then passes it off to one of the appropriate * routines. */ -dotraplinkage void __kprobes -do_page_fault(struct pt_regs *regs, unsigned long error_code) +static void __kprobes +__do_page_fault(struct pt_regs *regs, unsigned long error_code) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -1209,3 +1210,11 @@ good_area: up_read(&mm->mmap_sem); } + +dotraplinkage void __kprobes +do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + exception_enter(regs); + __do_page_fault(regs, error_code); + exception_exit(regs); +} diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index e0e6990..ab1f6a9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -319,7 +319,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr <= 256) + if (pagenr < 256) return 1; if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) return 0; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 575d86f..4f04db1 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -445,10 +445,10 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base) } #endif /* CONFIG_HIGHMEM */ -void __init native_pagetable_setup_start(pgd_t *base) +void __init native_pagetable_init(void) { unsigned long pfn, va; - pgd_t *pgd; + pgd_t *pgd, *base = swapper_pg_dir; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -475,10 +475,7 @@ void __init native_pagetable_setup_start(pgd_t *base) pte_clear(NULL, va, pte); } paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT); -} - -void __init native_pagetable_setup_done(pgd_t *base) -{ + paging_init(); } /* @@ -493,7 +490,7 @@ void __init native_pagetable_setup_done(pgd_t *base) * If we're booting paravirtualized under a hypervisor, then there are * more options: we may already be running PAE, and the pagetable may * or may not be based in swapper_pg_dir. In any case, - * paravirt_pagetable_setup_start() will set up swapper_pg_dir + * paravirt_pagetable_init() will set up swapper_pg_dir * appropriately for the rest of the initialization to work. * * In general, pagetable_init() assumes that the pagetable may already diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 613cd83..0777f04 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -98,6 +98,8 @@ static void flush_tlb_func(void *info) { struct flush_tlb_info *f = info; + inc_irq_stat(irq_tlb_count); + if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; @@ -320,7 +322,7 @@ static ssize_t tlbflush_write_file(struct file *file, if (kstrtos8(buf, 0, &shift)) return -EINVAL; - if (shift > 64) + if (shift < -1 || shift >= BITS_PER_LONG) return -EINVAL; tlb_flushall_shift = shift; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 937bcec..704b9ec 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -585,7 +585,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) while (i >= sizeof(struct acpi_mcfg_allocation)) { entries++; i -= sizeof(struct acpi_mcfg_allocation); - }; + } if (entries == 0) { pr_err(PREFIX "MMCONFIG has no entries\n"); return -ENODEV; diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index 73b8be0..6db1cc4 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1 +1,2 @@ obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o +obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c new file mode 100644 index 0000000..f6a0c1b --- /dev/null +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -0,0 +1,76 @@ +/* + * Copyright 2012 Intel Corporation + * Author: Josh Triplett <josh@joshtriplett.org> + * + * Based on the bgrt driver: + * Copyright 2012 Red Hat, Inc <mjg@redhat.com> + * Author: Matthew Garrett + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/kernel.h> +#include <linux/acpi.h> +#include <linux/efi.h> +#include <linux/efi-bgrt.h> + +struct acpi_table_bgrt *bgrt_tab; +void *bgrt_image; +size_t bgrt_image_size; + +struct bmp_header { + u16 id; + u32 size; +} __packed; + +void efi_bgrt_init(void) +{ + acpi_status status; + void __iomem *image; + bool ioremapped = false; + struct bmp_header bmp_header; + + if (acpi_disabled) + return; + + status = acpi_get_table("BGRT", 0, + (struct acpi_table_header **)&bgrt_tab); + if (ACPI_FAILURE(status)) + return; + + if (bgrt_tab->version != 1) + return; + if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address) + return; + + image = efi_lookup_mapped_addr(bgrt_tab->image_address); + if (!image) { + image = ioremap(bgrt_tab->image_address, sizeof(bmp_header)); + ioremapped = true; + if (!image) + return; + } + + memcpy_fromio(&bmp_header, image, sizeof(bmp_header)); + if (ioremapped) + iounmap(image); + bgrt_image_size = bmp_header.size; + + bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL); + if (!bgrt_image) + return; + + if (ioremapped) { + image = ioremap(bgrt_tab->image_address, bmp_header.size); + if (!image) { + kfree(bgrt_image); + bgrt_image = NULL; + return; + } + } + + memcpy_fromio(bgrt_image, image, bgrt_image_size); + if (ioremapped) + iounmap(image); +} diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 92660eda..aded2a9 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -31,6 +31,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/efi.h> +#include <linux/efi-bgrt.h> #include <linux/export.h> #include <linux/bootmem.h> #include <linux/memblock.h> @@ -419,10 +420,21 @@ void __init efi_reserve_boot_services(void) } } -static void __init efi_free_boot_services(void) +static void __init efi_unmap_memmap(void) +{ + if (memmap.map) { + early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); + memmap.map = NULL; + } +} + +void __init efi_free_boot_services(void) { void *p; + if (!efi_native) + return; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; unsigned long long start = md->phys_addr; @@ -438,6 +450,8 @@ static void __init efi_free_boot_services(void) free_bootmem_late(start, size); } + + efi_unmap_memmap(); } static int __init efi_systab_init(void *phys) @@ -732,6 +746,11 @@ void __init efi_init(void) #endif } +void __init efi_late_init(void) +{ + efi_bgrt_init(); +} + void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -764,6 +783,34 @@ static void __init runtime_code_page_mkexec(void) } /* + * We can't ioremap data in EFI boot services RAM, because we've already mapped + * it as RAM. So, look it up in the existing EFI memory map instead. Only + * callable after efi_enter_virtual_mode and before efi_free_boot_services. + */ +void __iomem *efi_lookup_mapped_addr(u64 phys_addr) +{ + void *p; + if (WARN_ON(!memmap.map)) + return NULL; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + u64 size = md->num_pages << EFI_PAGE_SHIFT; + u64 end = md->phys_addr + size; + if (!(md->attribute & EFI_MEMORY_RUNTIME) && + md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) + continue; + if (!md->virt_addr) + continue; + if (phys_addr >= md->phys_addr && phys_addr < end) { + phys_addr += md->virt_addr - md->phys_addr; + return (__force void __iomem *)(unsigned long)phys_addr; + } + } + return NULL; +} + +/* * This function will switch the EFI runtime services to virtual mode. * Essentially, look through the EFI memmap and map every region that * has the runtime attribute bit set in its memory descriptor and update @@ -787,8 +834,10 @@ void __init efi_enter_virtual_mode(void) * non-native EFI */ - if (!efi_native) - goto out; + if (!efi_native) { + efi_unmap_memmap(); + return; + } /* Merge contiguous regions of the same type and attribute */ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { @@ -878,18 +927,12 @@ void __init efi_enter_virtual_mode(void) } /* - * Thankfully, it does seem that no runtime services other than - * SetVirtualAddressMap() will touch boot services code, so we can - * get rid of it all at this point - */ - efi_free_boot_services(); - - /* * Now that EFI is in virtual mode, update the function * pointers in the runtime service table to the new virtual addresses. * * Call EFI services through wrapper functions. */ + efi.runtime_version = efi_systab.fw_revision; efi.get_time = virt_efi_get_time; efi.set_time = virt_efi_set_time; efi.get_wakeup_time = virt_efi_get_wakeup_time; @@ -906,9 +949,6 @@ void __init efi_enter_virtual_mode(void) if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); -out: - early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); - memmap.map = NULL; kfree(new_memmap); } diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 9926e11..aeaff8b 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -21,6 +21,7 @@ config 64BIT config X86_32 def_bool !64BIT select HAVE_AOUT + select ARCH_WANT_IPC_PARSE_VERSION config X86_64 def_bool 64BIT diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index 5868526..46a9df9 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -7,9 +7,6 @@ #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) -#define STR(x) #x -#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " STR(val) " " #val: : ) - #define BLANK() asm volatile("\n->" : : ) #define OFFSET(sym, str, mem) \ diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h index bd9a89b..ca255a8 100644 --- a/arch/x86/um/shared/sysdep/syscalls.h +++ b/arch/x86/um/shared/sysdep/syscalls.h @@ -1,3 +1,5 @@ +extern long sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid); #ifdef __i386__ #include "syscalls_32.h" #else diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index a508cea1..ba7363e 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -416,9 +416,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, PT_REGS_AX(regs) = (unsigned long) sig; PT_REGS_DX(regs) = (unsigned long) 0; PT_REGS_CX(regs) = (unsigned long) 0; - - if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) - ptrace_notify(SIGTRAP); return 0; } @@ -466,9 +463,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, PT_REGS_AX(regs) = (unsigned long) sig; PT_REGS_DX(regs) = (unsigned long) &frame->info; PT_REGS_CX(regs) = (unsigned long) &frame->uc; - - if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) - ptrace_notify(SIGTRAP); return 0; } diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 68d1dc9..b5408ce 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -28,7 +28,7 @@ #define ptregs_execve sys_execve #define ptregs_iopl sys_iopl #define ptregs_vm86old sys_vm86old -#define ptregs_clone sys_clone +#define ptregs_clone i386_clone #define ptregs_vm86 sys_vm86 #define ptregs_sigaltstack sys_sigaltstack #define ptregs_vfork sys_vfork diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c index b853e86..db444c7 100644 --- a/arch/x86/um/syscalls_32.c +++ b/arch/x86/um/syscalls_32.c @@ -3,37 +3,24 @@ * Licensed under the GPL */ -#include "linux/sched.h" -#include "linux/shm.h" -#include "linux/ipc.h" -#include "linux/syscalls.h" -#include "asm/mman.h" -#include "asm/uaccess.h" -#include "asm/unistd.h" +#include <linux/syscalls.h> +#include <sysdep/syscalls.h> /* * The prototype on i386 is: * - * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls, int * child_tidptr) + * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls * * and the "newtls" arg. on i386 is read by copy_thread directly from the * register saved on the stack. */ -long sys_clone(unsigned long clone_flags, unsigned long newsp, - int __user *parent_tid, void *newtls, int __user *child_tid) +long i386_clone(unsigned long clone_flags, unsigned long newsp, + int __user *parent_tid, void *newtls, int __user *child_tid) { - long ret; - - if (!newsp) - newsp = UPT_SP(¤t->thread.regs.regs); - - current->thread.forking = 1; - ret = do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); - current->thread.forking = 0; - return ret; + return sys_clone(clone_flags, newsp, parent_tid, child_tid); } + long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index f3d82bb..adb08eb 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -5,12 +5,9 @@ * Licensed under the GPL */ -#include "linux/linkage.h" -#include "linux/personality.h" -#include "linux/utsname.h" -#include "asm/prctl.h" /* XXX This should get the constants from libc */ -#include "asm/uaccess.h" -#include "os.h" +#include <linux/sched.h> +#include <asm/prctl.h> /* XXX This should get the constants from libc */ +#include <os.h> long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) { @@ -79,20 +76,6 @@ long sys_arch_prctl(int code, unsigned long addr) return arch_prctl(current, code, (unsigned long __user *) addr); } -long sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid) -{ - long ret; - - if (!newsp) - newsp = UPT_SP(¤t->thread.regs.regs); - current->thread.forking = 1; - ret = do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); - current->thread.forking = 0; - return ret; -} - void arch_switch_to(struct task_struct *to) { if ((to->thread.arch.fs == 0) || (to->mm == NULL)) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 9642d4a..1fbe75a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1452,6 +1452,10 @@ asmlinkage void __init xen_start_kernel(void) pci_request_acs(); xen_acpi_sleep_register(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = x86_init_uint_noop; } #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b65a761..7a769b7 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1174,8 +1174,13 @@ static void xen_exit_mmap(struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } -static void __init xen_pagetable_setup_start(pgd_t *base) +static void xen_post_allocator_init(void); + +static void __init xen_pagetable_init(void) { + paging_init(); + xen_setup_shared_info(); + xen_post_allocator_init(); } static __init void xen_mapping_pagetable_reserve(u64 start, u64 end) @@ -1192,14 +1197,6 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end) } } -static void xen_post_allocator_init(void); - -static void __init xen_pagetable_setup_done(pgd_t *base) -{ - xen_setup_shared_info(); - xen_post_allocator_init(); -} - static void xen_write_cr2(unsigned long cr2) { this_cpu_read(xen_vcpu)->arch.cr2 = cr2; @@ -1283,7 +1280,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { + if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { args->op.cmd = MMUEXT_INVLPG_MULTI; args->op.arg1.linear_addr = start; } @@ -2068,8 +2065,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { void __init xen_init_mmu_ops(void) { x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve; - x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start; - x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done; + x86_init.paging.pagetable_init = xen_pagetable_init; pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index d4b2554..72213da 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -599,7 +599,7 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_ if (p2m_index(set_pfn)) return false; - for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { topidx = p2m_top_index(pfn); if (!p2m_top[topidx]) @@ -828,9 +828,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, xen_mc_issue(PARAVIRT_LAZY_MMU); } - /* let's use dev_bus_addr to record the old mfn instead */ - kmap_op->dev_bus_addr = page->index; - page->index = (unsigned long) kmap_op; } spin_lock_irqsave(&m2p_override_lock, flags); list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); @@ -857,7 +854,8 @@ int m2p_add_override(unsigned long mfn, struct page *page, return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); -int m2p_remove_override(struct page *page, bool clear_pte) +int m2p_remove_override(struct page *page, + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; unsigned long mfn; @@ -887,10 +885,8 @@ int m2p_remove_override(struct page *page, bool clear_pte) WARN_ON(!PagePrivate(page)); ClearPagePrivate(page); - if (clear_pte) { - struct gnttab_map_grant_ref *map_op = - (struct gnttab_map_grant_ref *) page->index; - set_phys_to_machine(pfn, map_op->dev_bus_addr); + set_phys_to_machine(pfn, page->index); + if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; struct gnttab_unmap_grant_ref *unmap_op; @@ -902,13 +898,13 @@ int m2p_remove_override(struct page *page, bool clear_pte) * issued. In this case handle is going to -1 because * it hasn't been modified yet. */ - if (map_op->handle == -1) + if (kmap_op->handle == -1) xen_mc_flush(); /* - * Now if map_op->handle is negative it means that the + * Now if kmap_op->handle is negative it means that the * hypercall actually returned an error. */ - if (map_op->handle == GNTST_general_error) { + if (kmap_op->handle == GNTST_general_error) { printk(KERN_WARNING "m2p_remove_override: " "pfn %lx mfn %lx, failed to modify kernel mappings", pfn, mfn); @@ -918,8 +914,8 @@ int m2p_remove_override(struct page *page, bool clear_pte) mcs = xen_mc_entry( sizeof(struct gnttab_unmap_grant_ref)); unmap_op = mcs.args; - unmap_op->host_addr = map_op->host_addr; - unmap_op->handle = map_op->handle; + unmap_op->host_addr = kmap_op->host_addr; + unmap_op->handle = kmap_op->handle; unmap_op->dev_bus_addr = 0; MULTI_grant_table_op(mcs.mc, @@ -930,10 +926,9 @@ int m2p_remove_override(struct page *page, bool clear_pte) set_pte_at(&init_mm, address, ptep, pfn_pte(pfn, PAGE_KERNEL)); __flush_tlb_single(address); - map_op->host_addr = 0; + kmap_op->host_addr = 0; } - } else - set_phys_to_machine(pfn, page->index); + } /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present * somewhere in this domain, even before being added to the diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index d11ca11..e2d62d6 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -17,6 +17,7 @@ #include <asm/e820.h> #include <asm/setup.h> #include <asm/acpi.h> +#include <asm/numa.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -544,4 +545,7 @@ void __init xen_arch_setup(void) disable_cpufreq(); WARN_ON(set_pm_idle_to_default()); fiddle_vdso(); +#ifdef CONFIG_NUMA + numa_off = 1; +#endif } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index f58dca7..353c50f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -377,7 +377,8 @@ static int __cpuinit xen_cpu_up(unsigned int cpu, struct task_struct *idle) return rc; if (num_online_cpus() == 1) - alternatives_smp_switch(1); + /* Just in case we booted with a single CPU. */ + alternatives_enable_smp(); rc = xen_smp_intr_init(cpu); if (rc) @@ -424,9 +425,6 @@ static void xen_cpu_die(unsigned int cpu) unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); - - if (num_online_cpus() == 1) - alternatives_smp_switch(0); } static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 2c8d6a3..bc44311 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -31,6 +31,7 @@ #include <linux/mqueue.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <asm/pgtable.h> #include <asm/uaccess.h> @@ -110,8 +111,10 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { + rcu_idle_enter(); while (!need_resched()) platform_idle(); + rcu_idle_exit(); schedule_preempt_disabled(); } } |