diff options
author | Ziyan <jaraidaniel@gmail.com> | 2015-10-24 18:19:09 +0200 |
---|---|---|
committer | Ziyan <jaraidaniel@gmail.com> | 2015-10-25 16:24:52 +0100 |
commit | 101878938737bd16a5f7fb932b51041f7dbbb733 (patch) | |
tree | 235732d29c6741f22f2020218b2fad41c40b57b8 /arch | |
parent | 540bea4ab32149f8bc71fe34b73340c8d9abc053 (diff) | |
parent | 5dba9ddd98cbc7ad319d687887981a0ea0062c75 (diff) | |
download | kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.zip kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.tar.gz kernel_samsung_espresso10-101878938737bd16a5f7fb932b51041f7dbbb733.tar.bz2 |
Merge remote-tracking branch 'linux-stable/linux-3.0.y' into p-android-omap-3.0-dev-espresso
Conflicts:
Makefile
arch/arm/include/asm/hardware/cache-l2x0.h
arch/arm/kernel/smp.c
arch/arm/mach-omap2/board-4430sdp.c
arch/arm/mach-omap2/board-omap4panda.c
arch/arm/mach-omap2/opp.c
arch/ia64/include/asm/futex.h
drivers/bluetooth/ath3k.c
drivers/bluetooth/btusb.c
drivers/firmware/efivars.c
drivers/gpu/drm/i915/intel_lvds.c
drivers/gpu/drm/radeon/radeon_atombios.c
drivers/gpu/drm/radeon/radeon_irq_kms.c
drivers/hwmon/fam15h_power.c
drivers/mfd/twl6030-irq.c
drivers/mmc/core/sdio.c
drivers/net/tun.c
drivers/net/usb/ipheth.c
drivers/net/usb/usbnet.c
drivers/usb/core/hub.c
drivers/usb/host/xhci-mem.c
drivers/usb/host/xhci.h
drivers/usb/musb/omap2430.c
drivers/usb/serial/ftdi_sio.c
drivers/usb/serial/ftdi_sio_ids.h
drivers/usb/serial/option.c
drivers/usb/serial/qcserial.c
drivers/usb/serial/ti_usb_3410_5052.c
drivers/usb/serial/ti_usb_3410_5052.h
drivers/video/omap2/dss/hdmi.c
fs/splice.c
include/asm-generic/pgtable.h
include/net/sch_generic.h
kernel/cgroup.c
kernel/futex.c
kernel/time/timekeeping.c
net/ipv4/route.c
net/ipv4/syncookies.c
net/ipv4/tcp_ipv4.c
net/wireless/util.c
security/commoncap.c
sound/soc/soc-dapm.c
Diffstat (limited to 'arch')
238 files changed, 2045 insertions, 1075 deletions
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index e756d04..b15162f 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -14,8 +14,8 @@ */ -#define ATOMIC_INIT(i) ( (atomic_t) { (i) } ) -#define ATOMIC64_INIT(i) ( (atomic64_t) { (i) } ) +#define ATOMIC_INIT(i) { (i) } +#define ATOMIC64_INIT(i) { (i) } #define atomic_read(v) (*(volatile int *)&(v)->counter) #define atomic64_read(v) (*(volatile long *)&(v)->counter) diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h index 06edfef..3eeb47c 100644 --- a/arch/alpha/include/asm/socket.h +++ b/arch/alpha/include/asm/socket.h @@ -69,9 +69,11 @@ #define SO_RXQ_OVFL 40 +#ifdef __KERNEL__ /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. */ #define SOCK_NONBLOCK 0x40000000 +#endif /* __KERNEL__ */ #endif /* _ASM_SOCKET_H */ diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 99c0f46..dc616b3 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -189,6 +189,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr) extern void free_reserved_mem(void *, void *); extern void pcibios_claim_one_bus(struct pci_bus *); +static struct resource irongate_io = { + .name = "Irongate PCI IO", + .flags = IORESOURCE_IO, +}; static struct resource irongate_mem = { .name = "Irongate PCI MEM", .flags = IORESOURCE_MEM, @@ -210,6 +214,7 @@ nautilus_init_pci(void) irongate = pci_get_bus_and_slot(0, 0); bus->self = irongate; + bus->resource[0] = &irongate_io; bus->resource[1] = &irongate_mem; pci_bus_size_bridges(bus); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index dc73e61..45e2bee 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1235,6 +1235,42 @@ config ARM_ERRATA_754327 This workaround defines cpu_relax() as smp_mb(), preventing correctly written polling loops from denying visibility of updates to memory. +config ARM_ERRATA_764369 + bool "ARM errata: Data cache line maintenance operation by MVA may not succeed" + depends on CPU_V7 && SMP + help + This option enables the workaround for erratum 764369 + affecting Cortex-A9 MPCore with two or more processors (all + current revisions). Under certain timing circumstances, a data + cache line maintenance operation by MVA targeting an Inner + Shareable memory region may fail to proceed up to either the + Point of Coherency or to the Point of Unification of the + system. This workaround adds a DSB instruction before the + relevant cache maintenance functions and sets a specific bit + in the diagnostic control register of the SCU. + +config PL310_ERRATA_769419 + bool "PL310 errata: no automatic Store Buffer drain" + depends on CACHE_L2X0 + help + On revisions of the PL310 prior to r3p2, the Store Buffer does + not automatically drain. This can cause normal, non-cacheable + writes to be retained when the memory system is idle, leading + to suboptimal I/O performance for drivers using coherent DMA. + This option adds a write barrier to the cpu_idle loop so that, + on systems with an outer cache, the store buffer is drained + explicitly. + +config ARM_ERRATA_775420 + bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock" + depends on CPU_V7 + help + This option enables the workaround for the 775420 Cortex-A9 (r2p2, + r2p6,r2p8,r2p10,r3p0) erratum. In case a date cache maintenance + operation aborts with MMU exception, it might cause the processor + to deadlock. This workaround puts DSB before executing ISB if + an abort may occur on cache maintenance. + endmenu source "arch/arm/common/Kconfig" @@ -1299,32 +1335,6 @@ source "drivers/pci/Kconfig" source "drivers/pcmcia/Kconfig" -config ARM_ERRATA_764369 - bool "ARM errata: Data cache line maintenance operation by MVA may not succeed" - depends on CPU_V7 && SMP - help - This option enables the workaround for erratum 764369 - affecting Cortex-A9 MPCore with two or more processors (all - current revisions). Under certain timing circumstances, a data - cache line maintenance operation by MVA targeting an Inner - Shareable memory region may fail to proceed up to either the - Point of Coherency or to the Point of Unification of the - system. This workaround adds a DSB instruction before the - relevant cache maintenance functions and sets a specific bit - in the diagnostic control register of the SCU. - -config PL310_ERRATA_769419 - bool "PL310 errata: no automatic Store Buffer drain" - depends on CACHE_L2X0 - help - On revisions of the PL310 prior to r3p2, the Store Buffer does - not automatically drain. This can cause normal, non-cacheable - writes to be retained when the memory system is idle, leading - to suboptimal I/O performance for drivers using coherent DMA. - This option adds a write barrier to the cpu_idle loop so that, - on systems with an outer cache, the store buffer is drained - explicitly. - endmenu menu "Kernel Features" @@ -1885,6 +1895,7 @@ source "drivers/cpufreq/Kconfig" config CPU_FREQ_IMX tristate "CPUfreq driver for i.MX CPUs" depends on ARCH_MXC && CPU_FREQ + select CPU_FREQ_TABLE help This enables the CPUfreq driver for i.MX CPUs. diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index e58603b..caddb9d 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -539,6 +539,7 @@ __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 diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 2bf2243..166d6aa 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -29,7 +29,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_AEABI=y -CONFIG_DEFAULT_MMAP_MIN_ADDR=65536 CONFIG_AUTO_ZRELADDR=y CONFIG_FPE_NWFPE=y CONFIG_NET=y diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 1252a26..42dec04 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -215,7 +215,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm) static inline void vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) __cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end), vma->vm_flags); } @@ -223,7 +225,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned static inline void vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { unsigned long addr = user_addr & PAGE_MASK; __cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags); } diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 5dc6db1..2871580 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -45,10 +45,19 @@ #define L2X0_CLEAN_INV_LINE_PA 0x7F0 #define L2X0_CLEAN_INV_LINE_IDX 0x7F8 #define L2X0_CLEAN_INV_WAY 0x7FC + #define L2X0_LOCKDOWN_WAY_D0 0x900 #define L2X0_LOCKDOWN_WAY_D1 0x908 #define L2X0_LOCKDOWN_WAY_I0 0x904 #define L2X0_LOCKDOWN_WAY_I1 0x90C +/* + * The lockdown registers repeat 8 times for L310, the L210 has only one + * D and one I lockdown register at 0x0900 and 0x0904. + */ +#define L2X0_LOCKDOWN_WAY_D_BASE 0x900 +#define L2X0_LOCKDOWN_WAY_I_BASE 0x904 +#define L2X0_LOCKDOWN_STRIDE 0x08 + #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h index c1062c3..1e3f30f 100644 --- a/arch/arm/include/asm/hwcap.h +++ b/arch/arm/include/asm/hwcap.h @@ -18,8 +18,9 @@ #define HWCAP_THUMBEE 2048 #define HWCAP_NEON 4096 #define HWCAP_VFPv3 8192 -#define HWCAP_VFPv3D16 16384 +#define HWCAP_VFPv3D16 (1 << 14) /* also set for VFPv4-D16 */ #define HWCAP_TLS 32768 +#define HWCAP_VFPD32 (1 << 19) /* set if VFP has 32 regs (not 16) */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) /* diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h index 93226cf..b1479fd 100644 --- a/arch/arm/include/asm/mutex.h +++ b/arch/arm/include/asm/mutex.h @@ -7,121 +7,10 @@ */ #ifndef _ASM_MUTEX_H #define _ASM_MUTEX_H - -#if __LINUX_ARM_ARCH__ < 6 -/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */ -# include <asm-generic/mutex-xchg.h> -#else - /* - * Attempting to lock a mutex on ARMv6+ can be done with a bastardized - * atomic decrement (it is not a reliable atomic decrement but it satisfies - * the defined semantics for our purpose, while being smaller and faster - * than a real atomic decrement or atomic swap. The idea is to attempt - * decrementing the lock value only once. If once decremented it isn't zero, - * or if its store-back fails due to a dispute on the exclusive store, we - * simply bail out immediately through the slow path where the lock will be - * reattempted until it succeeds. + * On pre-ARMv6 hardware this results in a swp-based implementation, + * which is the most efficient. For ARMv6+, we emit a pair of exclusive + * accesses instead. */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res; - - __asm__ ( - - "ldrex %0, [%2] \n\t" - "sub %0, %0, #1 \n\t" - "strex %1, %0, [%2] " - - : "=&r" (__res), "=&r" (__ex_flag) - : "r" (&(count)->counter) - : "cc","memory" ); - - __res |= __ex_flag; - if (unlikely(__res != 0)) - fail_fn(count); -} - -static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res; - - __asm__ ( - - "ldrex %0, [%2] \n\t" - "sub %0, %0, #1 \n\t" - "strex %1, %0, [%2] " - - : "=&r" (__res), "=&r" (__ex_flag) - : "r" (&(count)->counter) - : "cc","memory" ); - - __res |= __ex_flag; - if (unlikely(__res != 0)) - __res = fail_fn(count); - return __res; -} - -/* - * Same trick is used for the unlock fast path. However the original value, - * rather than the result, is used to test for success in order to have - * better generated assembly. - */ -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res, __orig; - - __asm__ ( - - "ldrex %0, [%3] \n\t" - "add %1, %0, #1 \n\t" - "strex %2, %1, [%3] " - - : "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag) - : "r" (&(count)->counter) - : "cc","memory" ); - - __orig |= __ex_flag; - if (unlikely(__orig != 0)) - fail_fn(count); -} - -/* - * If the unlock was done on a contended lock, or if the unlock simply fails - * then the mutex remains locked. - */ -#define __mutex_slowpath_needs_to_unlock() 1 - -/* - * For __mutex_fastpath_trylock we use another construct which could be - * described as a "single value cmpxchg". - * - * This provides the needed trylock semantics like cmpxchg would, but it is - * lighter and less generic than a true cmpxchg implementation. - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res, __orig; - - __asm__ ( - - "1: ldrex %0, [%3] \n\t" - "subs %1, %0, #1 \n\t" - "strexeq %2, %1, [%3] \n\t" - "movlt %0, #0 \n\t" - "cmpeq %2, #0 \n\t" - "bgt 1b " - - : "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag) - : "r" (&count->counter) - : "cc", "memory" ); - - return __orig; -} - -#endif +#include <asm-generic/mutex-xchg.h> #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index f1956b2..a558978 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -363,6 +363,18 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext) #define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0) +#define pte_none(pte) (!pte_val(pte)) +#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT) +#define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY)) +#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY) +#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG) +#define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN)) +#define pte_special(pte) (0) + +#define pte_present_user(pte) \ + ((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \ + (L_PTE_PRESENT | L_PTE_USER)) + #if __LINUX_ARM_ARCH__ < 6 static inline void __sync_icache_dcache(pte_t pteval) { @@ -374,25 +386,15 @@ extern void __sync_icache_dcache(pte_t pteval); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { - if (addr >= TASK_SIZE) - set_pte_ext(ptep, pteval, 0); - else { + unsigned long ext = 0; + + if (addr < TASK_SIZE && pte_present_user(pteval)) { __sync_icache_dcache(pteval); - set_pte_ext(ptep, pteval, PTE_EXT_NG); + ext |= PTE_EXT_NG; } -} -#define pte_none(pte) (!pte_val(pte)) -#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT) -#define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY)) -#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY) -#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG) -#define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN)) -#define pte_special(pte) (0) - -#define pte_present_user(pte) \ - ((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \ - (L_PTE_PRESENT | L_PTE_USER)) + set_pte_ext(ptep, pteval, ext); +} #define PTE_BIT_FUNC(fn,op) \ static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; } @@ -419,13 +421,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 - * <--------------- offset --------------------> <- type --> 0 0 0 + * <--------------- offset ----------------------> < type -> 0 0 0 * - * This gives us up to 63 swap files and 32GB per swap file. Note that + * This gives us up to 31 swap files and 64GB per swap file. Note that * the offset field is always non-zero. */ #define __SWP_TYPE_SHIFT 3 -#define __SWP_TYPE_BITS 6 +#define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h index 43ba0fb..559ee24 100644 --- a/arch/arm/include/asm/signal.h +++ b/arch/arm/include/asm/signal.h @@ -127,6 +127,7 @@ struct sigaction { __sigrestore_t sa_restorer; sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h index 3d5fc41..c49c8f7 100644 --- a/arch/arm/include/asm/vfpmacros.h +++ b/arch/arm/include/asm/vfpmacros.h @@ -27,9 +27,9 @@ #if __LINUX_ARM_ARCH__ <= 6 ldr \tmp, =elf_hwcap @ may not have MVFR regs ldr \tmp, [\tmp, #0] - tst \tmp, #HWCAP_VFPv3D16 - ldceq p11, cr0, [\base],#32*4 @ FLDMIAD \base!, {d16-d31} - addne \base, \base, #32*4 @ step over unused register space + tst \tmp, #HWCAP_VFPD32 + ldcnel p11, cr0, [\base],#32*4 @ FLDMIAD \base!, {d16-d31} + addeq \base, \base, #32*4 @ step over unused register space #else VFPFMRX \tmp, MVFR0 @ Media and VFP Feature Register 0 and \tmp, \tmp, #MVFR0_A_SIMD_MASK @ A_SIMD field @@ -51,9 +51,9 @@ #if __LINUX_ARM_ARCH__ <= 6 ldr \tmp, =elf_hwcap @ may not have MVFR regs ldr \tmp, [\tmp, #0] - tst \tmp, #HWCAP_VFPv3D16 - stceq p11, cr0, [\base],#32*4 @ FSTMIAD \base!, {d16-d31} - addne \base, \base, #32*4 @ step over unused register space + tst \tmp, #HWCAP_VFPD32 + stcnel p11, cr0, [\base],#32*4 @ FSTMIAD \base!, {d16-d31} + addeq \base, \base, #32*4 @ step over unused register space #else VFPFMRX \tmp, MVFR0 @ Media and VFP Feature Register 0 and \tmp, \tmp, #MVFR0_A_SIMD_MASK @ A_SIMD field diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 2b5b142..75373a9 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -741,6 +741,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) struct frame_tail __user *tail; + perf_callchain_store(entry, regs->ARM_pc); tail = (struct frame_tail __user *)regs->ARM_fp - 1; while ((entry->nr < PERF_MAX_STACK_DEPTH) && diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 8e9461b..6127ac3 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -278,21 +278,27 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid) asmlinkage void __cpuinit secondary_start_kernel(void) { struct mm_struct *mm = &init_mm; - unsigned int cpu = smp_processor_id(); + unsigned int cpu; static bool booted; - printk("CPU%u: Booted secondary processor\n", cpu); + /* + * The identity mapping is uncached (strongly ordered), so + * switch away from it before attempting any exclusive accesses. + */ + cpu_switch_mm(mm->pgd, mm); + enter_lazy_tlb(mm, current); + local_flush_tlb_all(); /* * All kernel threads share the same mm context; grab a * reference and switch to it. */ + cpu = smp_processor_id(); atomic_inc(&mm->mm_count); current->active_mm = mm; cpumask_set_cpu(cpu, mm_cpumask(mm)); - cpu_switch_mm(mm->pgd, mm); - enter_lazy_tlb(mm, current); - local_flush_tlb_all(); + + printk("CPU%u: Booted secondary processor\n", cpu); cpu_init(); preempt_disable(); @@ -444,9 +450,7 @@ static DEFINE_PER_CPU(struct clock_event_device, percpu_clockevent); static void ipi_timer(void) { struct clock_event_device *evt = &__get_cpu_var(percpu_clockevent); - irq_enter(); evt->event_handler(evt); - irq_exit(); } #ifdef CONFIG_LOCAL_TIMERS @@ -457,7 +461,9 @@ asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs) if (local_timer_ack()) { __inc_irq_stat(cpu, local_timer_irqs); + irq_enter(); ipi_timer(); + irq_exit(); } set_irq_regs(old_regs); @@ -619,7 +625,9 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) switch (ipinr) { case IPI_TIMER: + irq_enter(); ipi_timer(); + irq_exit(); break; case IPI_RESCHEDULE: @@ -627,15 +635,21 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) break; case IPI_CALL_FUNC: + irq_enter(); generic_smp_call_function_interrupt(); + irq_exit(); break; case IPI_CALL_FUNC_SINGLE: + irq_enter(); generic_smp_call_function_single_interrupt(); + irq_exit(); break; case IPI_CPU_STOP: + irq_enter(); ipi_cpu_stop(cpu); + irq_exit(); break; case IPI_CPU_BACKTRACE: diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index 40ee7e5..0951a32 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -108,10 +108,12 @@ static void set_segfault(struct pt_regs *regs, unsigned long addr) { siginfo_t info; + down_read(¤t->mm->mmap_sem); if (find_vma(current->mm, addr) == NULL) info.si_code = SEGV_MAPERR; else info.si_code = SEGV_ACCERR; + up_read(¤t->mm->mmap_sem); info.si_signo = SIGSEGV; info.si_errno = 0; diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index 62e7c61..0264ab4 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -115,7 +115,7 @@ int kernel_execve(const char *filename, "Ir" (THREAD_START_SP - sizeof(regs)), "r" (®s), "Ir" (sizeof(regs)) - : "r0", "r1", "r2", "r3", "ip", "lr", "memory"); + : "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory"); out: return ret; diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c index 7227755..871a818 100644 --- a/arch/arm/mach-at91/at91rm9200_devices.c +++ b/arch/arm/mach-at91/at91rm9200_devices.c @@ -454,7 +454,7 @@ static struct i2c_gpio_platform_data pdata = { static struct platform_device at91rm9200_twi_device = { .name = "i2c-gpio", - .id = -1, + .id = 0, .dev.platform_data = &pdata, }; diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c index 39f81f4..89a8414 100644 --- a/arch/arm/mach-at91/at91sam9260_devices.c +++ b/arch/arm/mach-at91/at91sam9260_devices.c @@ -459,7 +459,7 @@ static struct i2c_gpio_platform_data pdata = { static struct platform_device at91sam9260_twi_device = { .name = "i2c-gpio", - .id = -1, + .id = 0, .dev.platform_data = &pdata, }; diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c index 5004bf0..5d43cf4 100644 --- a/arch/arm/mach-at91/at91sam9261_devices.c +++ b/arch/arm/mach-at91/at91sam9261_devices.c @@ -276,7 +276,7 @@ static struct i2c_gpio_platform_data pdata = { static struct platform_device at91sam9261_twi_device = { .name = "i2c-gpio", - .id = -1, + .id = 0, .dev.platform_data = &pdata, }; diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c index a050f41..2bbd163 100644 --- a/arch/arm/mach-at91/at91sam9263_devices.c +++ b/arch/arm/mach-at91/at91sam9263_devices.c @@ -534,7 +534,7 @@ static struct i2c_gpio_platform_data pdata = { static struct platform_device at91sam9263_twi_device = { .name = "i2c-gpio", - .id = -1, + .id = 0, .dev.platform_data = &pdata, }; diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c index aacb19d..659870e 100644 --- a/arch/arm/mach-at91/at91sam9rl_devices.c +++ b/arch/arm/mach-at91/at91sam9rl_devices.c @@ -319,7 +319,7 @@ static struct i2c_gpio_platform_data pdata = { static struct platform_device at91sam9rl_twi_device = { .name = "i2c-gpio", - .id = -1, + .id = 0, .dev.platform_data = &pdata, }; diff --git a/arch/arm/mach-dove/include/mach/pm.h b/arch/arm/mach-dove/include/mach/pm.h index 3ad9f94..11799c3 100644 --- a/arch/arm/mach-dove/include/mach/pm.h +++ b/arch/arm/mach-dove/include/mach/pm.h @@ -45,7 +45,7 @@ static inline int pmu_to_irq(int pin) static inline int irq_to_pmu(int irq) { - if (IRQ_DOVE_PMU_START < irq && irq < NR_IRQS) + if (IRQ_DOVE_PMU_START <= irq && irq < NR_IRQS) return irq - IRQ_DOVE_PMU_START; return -EINVAL; diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c index f07fd16..9f2fd10 100644 --- a/arch/arm/mach-dove/irq.c +++ b/arch/arm/mach-dove/irq.c @@ -61,8 +61,20 @@ static void pmu_irq_ack(struct irq_data *d) int pin = irq_to_pmu(d->irq); u32 u; + /* + * The PMU mask register is not RW0C: it is RW. This means that + * the bits take whatever value is written to them; if you write + * a '1', you will set the interrupt. + * + * Unfortunately this means there is NO race free way to clear + * these interrupts. + * + * So, let's structure the code so that the window is as small as + * possible. + */ u = ~(1 << (pin & 31)); - writel(u, PMU_INTERRUPT_CAUSE); + u &= readl_relaxed(PMU_INTERRUPT_CAUSE); + writel_relaxed(u, PMU_INTERRUPT_CAUSE); } static struct irq_chip pmu_irq_chip = { diff --git a/arch/arm/mach-imx/mach-mx21ads.c b/arch/arm/mach-imx/mach-mx21ads.c index 74ac889..a37fe02 100644 --- a/arch/arm/mach-imx/mach-mx21ads.c +++ b/arch/arm/mach-imx/mach-mx21ads.c @@ -32,7 +32,7 @@ * Memory-mapped I/O on MX21ADS base board */ #define MX21ADS_MMIO_BASE_ADDR 0xf5000000 -#define MX21ADS_MMIO_SIZE SZ_16M +#define MX21ADS_MMIO_SIZE 0xc00000 #define MX21ADS_REG_ADDR(offset) (void __force __iomem *) \ (MX21ADS_MMIO_BASE_ADDR + (offset)) diff --git a/arch/arm/mach-kirkwood/ts219-setup.c b/arch/arm/mach-kirkwood/ts219-setup.c index 68f32f2..eb1a7ba 100644 --- a/arch/arm/mach-kirkwood/ts219-setup.c +++ b/arch/arm/mach-kirkwood/ts219-setup.c @@ -124,7 +124,7 @@ static void __init qnap_ts219_init(void) static int __init ts219_pci_init(void) { if (machine_is_ts219()) - kirkwood_pcie_init(KW_PCIE0); + kirkwood_pcie_init(KW_PCIE1 | KW_PCIE0); return 0; } diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index c565971..9a1e1f7 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -56,11 +56,11 @@ #define RX51_USB_TRANSCEIVER_RST_GPIO 67 -/* list all spi devices here */ +/* List all SPI devices here. Note that the list/probe order seems to matter! */ enum { RX51_SPI_WL1251, - RX51_SPI_MIPID, /* LCD panel */ RX51_SPI_TSC2005, /* Touch Controller */ + RX51_SPI_MIPID, /* LCD panel */ }; static struct wl12xx_platform_data wl1251_pdata; diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c index c313be8..e899c00 100644 --- a/arch/arm/mach-omap2/opp.c +++ b/arch/arm/mach-omap2/opp.c @@ -58,21 +58,21 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def, omap_table_init = 1; /* Lets now register with OPP library */ - for (i = 0; i < opp_def_size; i++) { + for (i = 0; i < opp_def_size; i++, opp_def++) { struct omap_hwmod *oh; struct device *dev; if (!opp_def->hwmod_name) { WARN(1, "%s: NULL name of omap_hwmod, failing" " [%d].\n", __func__, i); - goto next; + continue; } oh = omap_hwmod_lookup(opp_def->hwmod_name); if (!oh || !oh->od) { pr_warn("%s: no hwmod or odev for %s, [%d] " "cannot add OPPs.\n", __func__, opp_def->hwmod_name, i); - goto next; + continue; } dev = &oh->od->pdev.dev; @@ -84,12 +84,12 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def, } else { WARN(1, "%s: round_rate for clock %s failed\n", __func__, opp_def->clk_name); - goto next; /* skip Bad OPP */ + continue; /* skip Bad OPP */ } } else { WARN(1, "%s: No clock by name %s found\n", __func__, opp_def->clk_name); - goto next; /* skip Bad OPP */ + continue; /* skip Bad OPP */ } r = opp_add(dev, opp_def->freq, opp_def->u_volt); if (r) { @@ -112,8 +112,6 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def, dev_err(dev, "%s:%s:err dvfs register %d %d\n", __func__, opp_def->hwmod_name, r, i); } -next: - opp_def++; } return 0; diff --git a/arch/arm/mach-orion5x/mpp.h b/arch/arm/mach-orion5x/mpp.h index eac6897..db70e79 100644 --- a/arch/arm/mach-orion5x/mpp.h +++ b/arch/arm/mach-orion5x/mpp.h @@ -65,8 +65,8 @@ #define MPP8_GIGE MPP(8, 0x1, 0, 0, 1, 1, 1) #define MPP9_UNUSED MPP(9, 0x0, 0, 0, 1, 1, 1) -#define MPP9_GPIO MPP(9, 0x0, 0, 0, 1, 1, 1) -#define MPP9_GIGE MPP(9, 0x1, 1, 1, 1, 1, 1) +#define MPP9_GPIO MPP(9, 0x0, 1, 1, 1, 1, 1) +#define MPP9_GIGE MPP(9, 0x1, 0, 0, 1, 1, 1) #define MPP10_UNUSED MPP(10, 0x0, 0, 0, 1, 1, 1) #define MPP10_GPIO MPP(10, 0x0, 1, 1, 1, 1, 1) diff --git a/arch/arm/mach-pxa/include/mach/smemc.h b/arch/arm/mach-pxa/include/mach/smemc.h index 654adc9..301bf0e 100644 --- a/arch/arm/mach-pxa/include/mach/smemc.h +++ b/arch/arm/mach-pxa/include/mach/smemc.h @@ -37,6 +37,7 @@ #define CSADRCFG1 (SMEMC_VIRT + 0x84) /* Address Configuration Register for CS1 */ #define CSADRCFG2 (SMEMC_VIRT + 0x88) /* Address Configuration Register for CS2 */ #define CSADRCFG3 (SMEMC_VIRT + 0x8C) /* Address Configuration Register for CS3 */ +#define CSMSADRCFG (SMEMC_VIRT + 0xA0) /* Chip Select Configuration Register */ /* * More handy macros for PCMCIA diff --git a/arch/arm/mach-pxa/smemc.c b/arch/arm/mach-pxa/smemc.c index 7992305..f38aa89 100644 --- a/arch/arm/mach-pxa/smemc.c +++ b/arch/arm/mach-pxa/smemc.c @@ -40,6 +40,8 @@ static void pxa3xx_smemc_resume(void) __raw_writel(csadrcfg[1], CSADRCFG1); __raw_writel(csadrcfg[2], CSADRCFG2); __raw_writel(csadrcfg[3], CSADRCFG3); + /* CSMSADRCFG wakes up in its default state (0), so we need to set it */ + __raw_writel(0x2, CSMSADRCFG); } static struct syscore_ops smemc_syscore_ops = { @@ -49,8 +51,19 @@ static struct syscore_ops smemc_syscore_ops = { static int __init smemc_init(void) { - if (cpu_is_pxa3xx()) + if (cpu_is_pxa3xx()) { + /* + * The only documentation we have on the + * Chip Select Configuration Register (CSMSADRCFG) is that + * it must be programmed to 0x2. + * Moreover, in the bit definitions, the second bit + * (CSMSADRCFG[1]) is called "SETALWAYS". + * Other bits are reserved in this register. + */ + __raw_writel(0x2, CSMSADRCFG); + register_syscore_ops(&smemc_syscore_ops); + } return 0; } diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c index 13c7e5f..3f47259 100644 --- a/arch/arm/mach-versatile/pci.c +++ b/arch/arm/mach-versatile/pci.c @@ -43,9 +43,9 @@ #define PCI_IMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0) #define PCI_IMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4) #define PCI_IMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8) -#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10) -#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14) -#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18) +#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14) +#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18) +#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x1c) #define PCI_SELFID __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc) #define DEVICE_ID_OFFSET 0x00 diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 724ba3b..1aa3a70 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -721,7 +721,6 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) unsigned long instr = 0, instrptr; int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs); unsigned int type; - mm_segment_t fs; unsigned int fault; u16 tinstr = 0; int isize = 4; @@ -729,16 +728,15 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) instrptr = instruction_pointer(regs); - fs = get_fs(); - set_fs(KERNEL_DS); if (thumb_mode(regs)) { - fault = __get_user(tinstr, (u16 *)(instrptr & ~1)); + u16 *ptr = (u16 *)(instrptr & ~1); + fault = probe_kernel_address(ptr, tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ u16 tinst2 = 0; - fault = __get_user(tinst2, (u16 *)(instrptr+2)); + fault = probe_kernel_address(ptr + 1, tinst2); instr = (tinstr << 16) | tinst2; thumb2_32b = 1; } else { @@ -747,8 +745,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } } } else - fault = __get_user(instr, (u32 *)instrptr); - set_fs(fs); + fault = probe_kernel_address(instrptr, instr); if (fault) { type = TYPE_FAULT; diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index e0b0e7a..09f8851 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -342,6 +342,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 6f6c1a6..19c764f 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -320,6 +320,25 @@ static void l2x0_disable(void) spin_unlock_irqrestore(&l2x0_lock, flags); } +static void __init l2x0_unlock(__u32 cache_id) +{ + int lockregs; + int i; + + if (cache_id == L2X0_CACHE_ID_PART_L310) + lockregs = 8; + else + /* L210 and unknown types */ + lockregs = 1; + + for (i = 0; i < lockregs; i++) { + writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + + i * L2X0_LOCKDOWN_STRIDE); + writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + + i * L2X0_LOCKDOWN_STRIDE); + } +} + void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) { __u32 aux; @@ -370,6 +389,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) * accessing the below registers will fault. */ if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* Make sure that I&D is not locked down when starting */ + l2x0_unlock(l2x0_cache_id); /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 1ed1fd3..428b243 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -211,6 +211,9 @@ ENTRY(v7_coherent_user_range) * isn't mapped, just try the next page. */ 9001: +#ifdef CONFIG_ARM_ERRATA_775420 + dsb +#endif mov r12, r12, lsr #12 mov r12, r12, lsl #12 add r12, r12, #4096 diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1a765c8..f00076c 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -479,25 +479,27 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, void (*op)(const void *, size_t, int)) { + unsigned long pfn; + size_t left = size; + + pfn = page_to_pfn(page) + offset / PAGE_SIZE; + offset %= PAGE_SIZE; + /* * A single sg entry may refer to multiple physically contiguous * pages. But we still need to process highmem pages individually. * If highmem is not configured then the bulk of this loop gets * optimized out. */ - size_t left = size; do { size_t len = left; void *vaddr; + page = pfn_to_page(pfn); + if (PageHighMem(page)) { - if (len + offset > PAGE_SIZE) { - if (offset >= PAGE_SIZE) { - page += offset / PAGE_SIZE; - offset %= PAGE_SIZE; - } + if (len + offset > PAGE_SIZE) len = PAGE_SIZE - offset; - } vaddr = kmap_high_get(page); if (vaddr) { vaddr += offset; @@ -514,7 +516,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, op(vaddr, len, dir); } offset = 0; - page++; + pfn++; left -= len; } while (left); } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index bc0e1d8..8799eae 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -266,7 +266,9 @@ good_area: return fault; check_stack: - if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr)) + /* Don't allow expansion below FIRST_USER_ADDRESS */ + if (vma->vm_flags & VM_GROWSDOWN && + addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr)) goto good_area; out: return fault; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 1a8d4aa..8fda9f7 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -236,8 +236,6 @@ void __sync_icache_dcache(pte_t pteval) struct page *page; struct address_space *mapping; - if (!pte_present_user(pteval)) - return; if (cache_is_vipt_nonaliasing() && !pte_exec(pteval)) /* only flush non-aliasing VIPT caches for exec mappings */ return; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index ea9c9f3..f23e315 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -475,7 +475,7 @@ static void __init build_mem_type_table(void) } for (i = 0; i < 16; i++) { - unsigned long v = pgprot_val(protection_map[i]); + pteval_t v = pgprot_val(protection_map[i]); protection_map[i] = __pgprot(v | user_pgprot); } diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index 53cd5b4..d7d0f7f 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -39,10 +39,18 @@ ENTRY(v7wbi_flush_user_tlb_range) mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT asid r3, r3 @ mask ASID +#ifdef CONFIG_ARM_ERRATA_720789 + ALT_SMP(W(mov) r3, #0 ) + ALT_UP(W(nop) ) +#endif orr r0, r3, r0, lsl #PAGE_SHIFT @ Create initial MVA mov r1, r1, lsl #PAGE_SHIFT 1: +#ifdef CONFIG_ARM_ERRATA_720789 + ALT_SMP(mcr p15, 0, r0, c8, c3, 3) @ TLB invalidate U MVA all ASID (shareable) +#else ALT_SMP(mcr p15, 0, r0, c8, c3, 1) @ TLB invalidate U MVA (shareable) +#endif ALT_UP(mcr p15, 0, r0, c8, c7, 1) @ TLB invalidate U MVA add r0, r0, #PAGE_SZ @@ -70,7 +78,11 @@ ENTRY(v7wbi_flush_kern_tlb_range) mov r0, r0, lsl #PAGE_SHIFT mov r1, r1, lsl #PAGE_SHIFT 1: +#ifdef CONFIG_ARM_ERRATA_720789 + ALT_SMP(mcr p15, 0, r0, c8, c3, 3) @ TLB invalidate U MVA all ASID (shareable) +#else ALT_SMP(mcr p15, 0, r0, c8, c3, 1) @ TLB invalidate U MVA (shareable) +#endif ALT_UP(mcr p15, 0, r0, c8, c7, 1) @ TLB invalidate U MVA add r0, r0, #PAGE_SZ cmp r0, r1 diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index 11dce87..214b002 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -343,7 +343,7 @@ static struct resource orion_ge10_shared_resources[] = { static struct platform_device orion_ge10_shared = { .name = MV643XX_ETH_SHARED_NAME, - .id = 1, + .id = 2, .dev = { .platform_data = &orion_ge10_shared_data, }, @@ -358,8 +358,8 @@ static struct resource orion_ge10_resources[] = { static struct platform_device orion_ge10 = { .name = MV643XX_ETH_NAME, - .id = 1, - .num_resources = 2, + .id = 2, + .num_resources = 1, .resource = orion_ge10_resources, .dev = { .coherent_dma_mask = DMA_BIT_MASK(32), @@ -397,7 +397,7 @@ static struct resource orion_ge11_shared_resources[] = { static struct platform_device orion_ge11_shared = { .name = MV643XX_ETH_SHARED_NAME, - .id = 1, + .id = 3, .dev = { .platform_data = &orion_ge11_shared_data, }, @@ -412,8 +412,8 @@ static struct resource orion_ge11_resources[] = { static struct platform_device orion_ge11 = { .name = MV643XX_ETH_NAME, - .id = 1, - .num_resources = 2, + .id = 3, + .num_resources = 1, .resource = orion_ge11_resources, .dev = { .coherent_dma_mask = DMA_BIT_MASK(32), diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c index 0719f49..9f422ba 100644 --- a/arch/arm/plat-s3c24xx/dma.c +++ b/arch/arm/plat-s3c24xx/dma.c @@ -431,7 +431,7 @@ s3c2410_dma_canload(struct s3c2410_dma_chan *chan) * when necessary. */ -int s3c2410_dma_enqueue(unsigned int channel, void *id, +int s3c2410_dma_enqueue(enum dma_ch channel, void *id, dma_addr_t data, int size) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c index e8f2be2..df14954 100644 --- a/arch/arm/plat-samsung/adc.c +++ b/arch/arm/plat-samsung/adc.c @@ -143,11 +143,13 @@ int s3c_adc_start(struct s3c_adc_client *client, return -EINVAL; } - if (client->is_ts && adc->ts_pend) - return -EAGAIN; - spin_lock_irqsave(&adc->lock, flags); + if (client->is_ts && adc->ts_pend) { + spin_unlock_irqrestore(&adc->lock, flags); + return -EAGAIN; + } + client->channel = channel; client->nr_samples = nr_samples; diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index e37c5fd..6a1f90a 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -376,7 +376,7 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs) * If there isn't a second FP instruction, exit now. Note that * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1. */ - if (fpexc ^ (FPEXC_EX | FPEXC_FP2V)) + if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V)) goto exit; /* @@ -600,11 +600,14 @@ static int __init vfp_init(void) elf_hwcap |= HWCAP_VFPv3; /* - * Check for VFPv3 D16. CPUs in this configuration - * only have 16 x 64bit registers. + * Check for VFPv3 D16 and VFPv4 D16. CPUs in + * this configuration only have 16 x 64bit + * registers. */ if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK)) == 1) - elf_hwcap |= HWCAP_VFPv3D16; + elf_hwcap |= HWCAP_VFPv3D16; /* also v4-D16 */ + else + elf_hwcap |= HWCAP_VFPD32; } #endif #ifdef CONFIG_NEON diff --git a/arch/avr32/include/asm/signal.h b/arch/avr32/include/asm/signal.h index 8790dfc..e6952a0 100644 --- a/arch/avr32/include/asm/signal.h +++ b/arch/avr32/include/asm/signal.h @@ -128,6 +128,7 @@ struct sigaction { __sigrestore_t sa_restorer; sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index a727f54..9c266ab 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -271,7 +271,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, break; case R_AVR32_GOT18SW: if ((relocation & 0xfffe0003) != 0 - && (relocation & 0xfffc0003) != 0xffff0000) + && (relocation & 0xfffc0000) != 0xfffc0000) return reloc_overflow(module, "R_AVR32_GOT18SW", relocation); relocation >>= 2; diff --git a/arch/cris/include/asm/io.h b/arch/cris/include/asm/io.h index 32567bc..ac12ae2 100644 --- a/arch/cris/include/asm/io.h +++ b/arch/cris/include/asm/io.h @@ -133,12 +133,39 @@ static inline void writel(unsigned int b, volatile void __iomem *addr) #define insb(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,1,count) : 0) #define insw(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,2,count) : 0) #define insl(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,4,count) : 0) -#define outb(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,1,1) -#define outw(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,2,1) -#define outl(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,4,1) -#define outsb(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,1,count) -#define outsw(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,2,count) -#define outsl(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,3,count) +static inline void outb(unsigned char data, unsigned int port) +{ + if (cris_iops) + cris_iops->write_io(port, (void *) &data, 1, 1); +} +static inline void outw(unsigned short data, unsigned int port) +{ + if (cris_iops) + cris_iops->write_io(port, (void *) &data, 2, 1); +} +static inline void outl(unsigned int data, unsigned int port) +{ + if (cris_iops) + cris_iops->write_io(port, (void *) &data, 4, 1); +} +static inline void outsb(unsigned int port, const void *addr, + unsigned long count) +{ + if (cris_iops) + cris_iops->write_io(port, (void *)addr, 1, count); +} +static inline void outsw(unsigned int port, const void *addr, + unsigned long count) +{ + if (cris_iops) + cris_iops->write_io(port, (void *)addr, 2, count); +} +static inline void outsl(unsigned int port, const void *addr, + unsigned long count) +{ + if (cris_iops) + cris_iops->write_io(port, (void *)addr, 4, count); +} /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem diff --git a/arch/cris/include/asm/signal.h b/arch/cris/include/asm/signal.h index ea6af9a..057fea2 100644 --- a/arch/cris/include/asm/signal.h +++ b/arch/cris/include/asm/signal.h @@ -122,6 +122,7 @@ struct sigaction { void (*sa_restorer)(void); sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index a6990cb..a68b983 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS EXCEPTION_TABLE(4) + _sdata = .; RODATA . = ALIGN (4); diff --git a/arch/h8300/include/asm/signal.h b/arch/h8300/include/asm/signal.h index fd8b66e..8695707 100644 --- a/arch/h8300/include/asm/signal.h +++ b/arch/h8300/include/asm/signal.h @@ -121,6 +121,7 @@ struct sigaction { void (*sa_restorer)(void); sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 4468814..6fcc9a0 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -18,8 +18,8 @@ #include <asm/system.h> -#define ATOMIC_INIT(i) ((atomic_t) { (i) }) -#define ATOMIC64_INIT(i) ((atomic64_t) { (i) }) +#define ATOMIC_INIT(i) { (i) } +#define ATOMIC64_INIT(i) { (i) } #define atomic_read(v) (*(volatile int *)&(v)->counter) #define atomic64_read(v) (*(volatile long *)&(v)->counter) diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h index 21ab376..1bd14d5 100644 --- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -107,16 +107,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; { - register unsigned long r8 __asm ("r8"); + register unsigned long r8 __asm ("r8") = 0; unsigned long prev; __asm__ __volatile__( " mf;; \n" - " mov %0=r0 \n" " mov ar.ccv=%4;; \n" "[1:] cmpxchg4.acq %1=[%2],%3,ar.ccv \n" " .xdata4 \"__ex_table\", 1b-., 2f-. \n" "[2:]" - : "=r" (r8), "=r" (prev) + : "+r" (r8), "=&r" (prev) : "r" (uaddr), "r" (newval), "rO" ((long) (unsigned) oldval) : "memory"); diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h index 43f96ab..8c70961 100644 --- a/arch/ia64/include/asm/mca.h +++ b/arch/ia64/include/asm/mca.h @@ -143,6 +143,7 @@ extern unsigned long __per_cpu_mca[NR_CPUS]; extern int cpe_vector; extern int ia64_cpe_irq; extern void ia64_mca_init(void); +extern void ia64_mca_irq_init(void); extern void ia64_mca_cpu_init(void *); extern void ia64_os_mca_dispatch(void); extern void ia64_os_mca_dispatch_end(void); diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index 7c928da..d8de182 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -321,11 +321,12 @@ #define __NR_syncfs 1329 #define __NR_setns 1330 #define __NR_sendmmsg 1331 +#define __NR_accept4 1334 #ifdef __KERNEL__ -#define NR_syscalls 308 /* length of syscall table */ +#define NR_syscalls 311 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 97dd2ab..df477f8 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1777,6 +1777,9 @@ sys_call_table: data8 sys_syncfs data8 sys_setns // 1330 data8 sys_sendmmsg + data8 sys_ni_syscall /* process_vm_readv */ + data8 sys_ni_syscall /* process_vm_writev */ + data8 sys_accept4 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */ diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index ad69606..f2c41828 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -23,6 +23,8 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <asm/mca.h> + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -83,6 +85,12 @@ bool is_affinity_mask_valid(const struct cpumask *cpumask) #endif /* CONFIG_SMP */ +int __init arch_early_irq_init(void) +{ + ia64_mca_irq_init(); + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU unsigned int vectors_in_migration[NR_IRQS]; diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 782c3a35..3540c5e 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -23,7 +23,6 @@ #include <linux/ioport.h> #include <linux/kernel_stat.h> #include <linux/ptrace.h> -#include <linux/random.h> /* for rand_initialize_irq() */ #include <linux/signal.h> #include <linux/smp.h> #include <linux/threads.h> diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 84fb405..9b97303 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -2071,22 +2071,16 @@ ia64_mca_init(void) printk(KERN_INFO "MCA related initialization done\n"); } + /* - * ia64_mca_late_init - * - * Opportunity to setup things that require initialization later - * than ia64_mca_init. Setup a timer to poll for CPEs if the - * platform doesn't support an interrupt driven mechanism. - * - * Inputs : None - * Outputs : Status + * These pieces cannot be done in ia64_mca_init() because it is called before + * early_irq_init() which would wipe out our percpu irq registrations. But we + * cannot leave them until ia64_mca_late_init() because by then all the other + * processors have been brought online and have set their own CMC vectors to + * point at a non-existant action. Called from arch_early_irq_init(). */ -static int __init -ia64_mca_late_init(void) +void __init ia64_mca_irq_init(void) { - if (!mca_init) - return 0; - /* * Configure the CMCI/P vector and handler. Interrupts for CMC are * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). @@ -2105,6 +2099,23 @@ ia64_mca_late_init(void) /* Setup the CPEI/P handler */ register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); #endif +} + +/* + * ia64_mca_late_init + * + * Opportunity to setup things that require initialization later + * than ia64_mca_init. Setup a timer to poll for CPEs if the + * platform doesn't support an interrupt driven mechanism. + * + * Inputs : None + * Outputs : Status + */ +static int __init +ia64_mca_late_init(void) +{ + if (!mca_init) + return 0; register_hotcpu_notifier(&mca_cpu_notifier); diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 8213efe..a874213 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1168,6 +1168,11 @@ out: #define PALE_RESET_ENTRY 0x80000000ffffffb0UL +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kcm) == (vcpu->arch.apic != NULL); +} + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct kvm_vcpu *v; diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c index 4332f7e..a7869f8 100644 --- a/arch/ia64/kvm/vtlb.c +++ b/arch/ia64/kvm/vtlb.c @@ -256,7 +256,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte) "srlz.d;;" "ssm psr.i;;" "srlz.d;;" - : "=r"(ret) : "r"(iha), "r"(pte):"memory"); + : "=&r"(ret) : "r"(iha), "r"(pte) : "memory"); return ret; } diff --git a/arch/m32r/boot/compressed/Makefile b/arch/m32r/boot/compressed/Makefile index 177716b..01729c2 100644 --- a/arch/m32r/boot/compressed/Makefile +++ b/arch/m32r/boot/compressed/Makefile @@ -43,9 +43,9 @@ endif OBJCOPYFLAGS += -R .empty_zero_page -suffix_$(CONFIG_KERNEL_GZIP) = gz -suffix_$(CONFIG_KERNEL_BZIP2) = bz2 -suffix_$(CONFIG_KERNEL_LZMA) = lzma +suffix-$(CONFIG_KERNEL_GZIP) = gz +suffix-$(CONFIG_KERNEL_BZIP2) = bz2 +suffix-$(CONFIG_KERNEL_LZMA) = lzma $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE $(call if_changed,ld) diff --git a/arch/m32r/boot/compressed/misc.c b/arch/m32r/boot/compressed/misc.c index 370d608..28a0952 100644 --- a/arch/m32r/boot/compressed/misc.c +++ b/arch/m32r/boot/compressed/misc.c @@ -28,7 +28,7 @@ static unsigned long free_mem_ptr; static unsigned long free_mem_end_ptr; #ifdef CONFIG_KERNEL_BZIP2 -static void *memset(void *s, int c, size_t n) +void *memset(void *s, int c, size_t n) { char *ss = s; @@ -39,6 +39,16 @@ static void *memset(void *s, int c, size_t n) #endif #ifdef CONFIG_KERNEL_GZIP +void *memcpy(void *dest, const void *src, size_t n) +{ + char *d = dest; + const char *s = src; + while (n--) + *d++ = *s++; + + return dest; +} + #define BOOT_HEAP_SIZE 0x10000 #include "../../../../lib/decompress_inflate.c" #endif diff --git a/arch/m32r/include/asm/signal.h b/arch/m32r/include/asm/signal.h index b2eeb0d..802d561 100644 --- a/arch/m32r/include/asm/signal.h +++ b/arch/m32r/include/asm/signal.h @@ -123,6 +123,7 @@ struct sigaction { __sigrestore_t sa_restorer; sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c index 2291a7d..fa277ae 100644 --- a/arch/m68k/emu/natfeat.c +++ b/arch/m68k/emu/natfeat.c @@ -18,9 +18,11 @@ #include <asm/machdep.h> #include <asm/natfeat.h> +extern long nf_get_id2(const char *feature_name); + asm("\n" -" .global nf_get_id,nf_call\n" -"nf_get_id:\n" +" .global nf_get_id2,nf_call\n" +"nf_get_id2:\n" " .short 0x7300\n" " rts\n" "nf_call:\n" @@ -29,12 +31,25 @@ asm("\n" "1: moveq.l #0,%d0\n" " rts\n" " .section __ex_table,\"a\"\n" -" .long nf_get_id,1b\n" +" .long nf_get_id2,1b\n" " .long nf_call,1b\n" " .previous"); -EXPORT_SYMBOL_GPL(nf_get_id); EXPORT_SYMBOL_GPL(nf_call); +long nf_get_id(const char *feature_name) +{ + /* feature_name may be in vmalloc()ed memory, so make a copy */ + char name_copy[32]; + size_t n; + + n = strlcpy(name_copy, feature_name, sizeof(name_copy)); + if (n >= sizeof(name_copy)) + return 0; + + return nf_get_id2(name_copy); +} +EXPORT_SYMBOL_GPL(nf_get_id); + void nfprint(const char *fmt, ...) { static char buf[256]; diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h index edb6614..7558032 100644 --- a/arch/m68k/include/asm/div64.h +++ b/arch/m68k/include/asm/div64.h @@ -13,16 +13,17 @@ unsigned long long n64; \ } __n; \ unsigned long __rem, __upper; \ + unsigned long __base = (base); \ \ __n.n64 = (n); \ if ((__upper = __n.n32[0])) { \ asm ("divul.l %2,%1:%0" \ - : "=d" (__n.n32[0]), "=d" (__upper) \ - : "d" (base), "0" (__n.n32[0])); \ + : "=d" (__n.n32[0]), "=d" (__upper) \ + : "d" (__base), "0" (__n.n32[0])); \ } \ asm ("divu.l %2,%1:%0" \ - : "=d" (__n.n32[1]), "=d" (__rem) \ - : "d" (base), "1" (__upper), "0" (__n.n32[1])); \ + : "=d" (__n.n32[1]), "=d" (__rem) \ + : "d" (__base), "1" (__upper), "0" (__n.n32[1])); \ (n) = __n.n64; \ __rem; \ }) diff --git a/arch/m68k/include/asm/entry_mm.h b/arch/m68k/include/asm/entry_mm.h index 73b8c8f..bdace4b 100644 --- a/arch/m68k/include/asm/entry_mm.h +++ b/arch/m68k/include/asm/entry_mm.h @@ -35,8 +35,8 @@ /* the following macro is used when enabling interrupts */ #if defined(MACH_ATARI_ONLY) - /* block out HSYNC on the atari */ -#define ALLOWINT (~0x400) + /* block out HSYNC = ipl 2 on the atari */ +#define ALLOWINT (~0x500) #define MAX_NOINT_IPL 3 #else /* portable version */ diff --git a/arch/m68k/include/asm/signal.h b/arch/m68k/include/asm/signal.h index 5bc09c7..ee80858 100644 --- a/arch/m68k/include/asm/signal.h +++ b/arch/m68k/include/asm/signal.h @@ -119,6 +119,7 @@ struct sigaction { __sigrestore_t sa_restorer; sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; @@ -156,7 +157,7 @@ typedef struct sigaltstack { static inline void sigaddset(sigset_t *set, int _sig) { asm ("bfset %0{%1,#1}" - : "+od" (*set) + : "+o" (*set) : "id" ((_sig - 1) ^ 31) : "cc"); } @@ -164,7 +165,7 @@ static inline void sigaddset(sigset_t *set, int _sig) static inline void sigdelset(sigset_t *set, int _sig) { asm ("bfclr %0{%1,#1}" - : "+od" (*set) + : "+o" (*set) : "id" ((_sig - 1) ^ 31) : "cc"); } @@ -180,7 +181,7 @@ static inline int __gen_sigismember(sigset_t *set, int _sig) int ret; asm ("bfextu %1{%2,#1},%0" : "=d" (ret) - : "od" (*set), "id" ((_sig-1) ^ 31) + : "o" (*set), "id" ((_sig-1) ^ 31) : "cc"); return ret; } diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 8623f8d..9a5932e 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -479,9 +479,13 @@ sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5, goto bad_access; } - mem_value = *mem; + /* + * No need to check for EFAULT; we know that the page is + * present and writable. + */ + __get_user(mem_value, mem); if (mem_value == oldval) - *mem = newval; + __put_user(newval, mem); pte_unmap_unlock(pte, ptl); up_read(&mm->mmap_sem); diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 884819c..9aa60f6 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -236,7 +236,7 @@ KBUILD_CPPFLAGS += -D"DATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0)" LDFLAGS += -m $(ld-emul) ifdef CONFIG_MIPS -CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -xc /dev/null | \ +CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \ egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \ sed -e 's/^\#define /-D/' -e "s/ /='/" -e "s/$$/'/") ifdef CONFIG_64BIT diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 97f8bf6..adda036 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -60,6 +60,8 @@ struct thread_info { register struct thread_info *__current_thread_info __asm__("$28"); #define current_thread_info() __current_thread_info +#endif /* !__ASSEMBLY__ */ + /* thread information allocation */ #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT) #define THREAD_SIZE_ORDER (1) @@ -97,8 +99,6 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define free_thread_info(info) kfree(info) -#endif /* !__ASSEMBLY__ */ - #define PREEMPT_ACTIVE 0x10000000 /* diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 83bba33..8b3c62c 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -100,7 +100,7 @@ obj-$(CONFIG_MIPS_MACHINE) += mips_machine.o obj-$(CONFIG_OF) += prom.o -CFLAGS_cpu-bugs64.o = $(shell if $(CC) $(KBUILD_CFLAGS) -Wa,-mdaddi -c -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-DHAVE_AS_SET_DADDI"; fi) +CFLAGS_cpu-bugs64.o = $(shell if $(CC) $(KBUILD_CFLAGS) -Wa,-mdaddi -c -o /dev/null -x c /dev/null >/dev/null 2>&1; then echo "-DHAVE_AS_SET_DADDI"; fi) obj-$(CONFIG_HAVE_STD_PC_SERIAL_PORT) += 8250-platform.o diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index f4546e9..23817a6 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -283,6 +283,15 @@ static int kgdb_mips_notify(struct notifier_block *self, unsigned long cmd, struct pt_regs *regs = args->regs; int trap = (regs->cp0_cause & 0x7c) >> 2; +#ifdef CONFIG_KPROBES + /* + * Return immediately if the kprobes fault notifier has set + * DIE_PAGE_FAULT. + */ + if (cmd == DIE_PAGE_FAULT) + return NOTIFY_DONE; +#endif /* CONFIG_KPROBES */ + /* Userspace events, ignore. */ if (user_mode(regs)) return NOTIFY_DONE; diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index a81176f..be281c6 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -1,5 +1,6 @@ #include <asm/asm-offsets.h> #include <asm/page.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> #undef mips @@ -73,7 +74,7 @@ SECTIONS .data : { /* Data */ . = . + DATAOFFSET; /* for CONFIG_MAPPED_KERNEL */ - INIT_TASK_DATA(PAGE_SIZE) + INIT_TASK_DATA(THREAD_SIZE) NOSAVE_DATA CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) diff --git a/arch/mn10300/Makefile b/arch/mn10300/Makefile index 7120282..3eb4a52 100644 --- a/arch/mn10300/Makefile +++ b/arch/mn10300/Makefile @@ -26,7 +26,7 @@ CHECKFLAGS += PROCESSOR := unset UNIT := unset -KBUILD_CFLAGS += -mam33 -mmem-funcs -DCPU=AM33 +KBUILD_CFLAGS += -mam33 -DCPU=AM33 $(call cc-option,-mmem-funcs,) KBUILD_AFLAGS += -mam33 -DCPU=AM33 ifeq ($(CONFIG_MN10300_CURRENT_IN_E2),y) diff --git a/arch/mn10300/include/asm/signal.h b/arch/mn10300/include/asm/signal.h index 1865d72..eecaa76 100644 --- a/arch/mn10300/include/asm/signal.h +++ b/arch/mn10300/include/asm/signal.h @@ -131,6 +131,7 @@ struct sigaction { __sigrestore_t sa_restorer; sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 26fd114..3706cf0 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -248,7 +248,7 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u) #define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) -#define ATOMIC_INIT(i) ((atomic_t) { (i) }) +#define ATOMIC_INIT(i) { (i) } #define smp_mb__before_atomic_dec() smp_mb() #define smp_mb__after_atomic_dec() smp_mb() @@ -257,7 +257,7 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u) #ifdef CONFIG_64BIT -#define ATOMIC64_INIT(i) ((atomic64_t) { (i) }) +#define ATOMIC64_INIT(i) { (i) } static __inline__ s64 __atomic64_add_return(s64 i, atomic64_t *v) diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 22dadeb..9d35a3e 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -12,11 +12,10 @@ #include <linux/bitops.h> #include <linux/spinlock.h> +#include <linux/mm_types.h> #include <asm/processor.h> #include <asm/cache.h> -struct vm_area_struct; - /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel * memory. For the return value to be meaningful, ADDR must be >= @@ -40,7 +39,14 @@ struct vm_area_struct; do{ \ *(pteptr) = (pteval); \ } while(0) -#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) + +extern void purge_tlb_entries(struct mm_struct *, unsigned long); + +#define set_pte_at(mm, addr, ptep, pteval) \ + do { \ + set_pte(ptep, pteval); \ + purge_tlb_entries(mm, addr); \ + } while (0) #endif /* !__ASSEMBLY__ */ @@ -464,6 +470,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, old = pte_val(*ptep); new = pte_val(pte_wrprotect(__pte (old))); } while (cmpxchg((unsigned long *) ptep, old, new) != old); + purge_tlb_entries(mm, addr); #else pte_t old_pte = *ptep; set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); diff --git a/arch/parisc/include/asm/prefetch.h b/arch/parisc/include/asm/prefetch.h index c5edc60..1ee7c82 100644 --- a/arch/parisc/include/asm/prefetch.h +++ b/arch/parisc/include/asm/prefetch.h @@ -21,7 +21,12 @@ #define ARCH_HAS_PREFETCH static inline void prefetch(const void *addr) { - __asm__("ldw 0(%0), %%r0" : : "r" (addr)); + __asm__( +#ifndef CONFIG_PA20 + /* Need to avoid prefetch of NULL on PA7300LC */ + " extrw,u,= %0,31,32,%%r0\n" +#endif + " ldw 0(%0), %%r0" : : "r" (addr)); } /* LDD is a PA2.0 addition. */ diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 83335f3..5241698 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -421,6 +421,24 @@ void kunmap_parisc(void *addr) EXPORT_SYMBOL(kunmap_parisc); #endif +void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags; + + /* Note: purge_tlb_entries can be called at startup with + no context. */ + + /* Disable preemption while we play with %sr1. */ + preempt_disable(); + mtsp(mm->context, 1); + purge_tlb_start(flags); + pdtlb(addr); + pitlb(addr); + purge_tlb_end(flags); + preempt_enable(); +} +EXPORT_SYMBOL(purge_tlb_entries); + void __flush_tlb_range(unsigned long sid, unsigned long start, unsigned long end) { diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 6f05944..07ef351 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -552,7 +552,7 @@ * entry (identifying the physical page) and %r23 up with * the from tlb entry (or nothing if only a to entry---for * clear_user_page_asm) */ - .macro do_alias spc,tmp,tmp1,va,pte,prot,fault + .macro do_alias spc,tmp,tmp1,va,pte,prot,fault,patype cmpib,COND(<>),n 0,\spc,\fault ldil L%(TMPALIAS_MAP_START),\tmp #if defined(CONFIG_64BIT) && (TMPALIAS_MAP_START >= 0x80000000) @@ -581,7 +581,15 @@ */ cmpiclr,= 0x01,\tmp,%r0 ldi (_PAGE_DIRTY|_PAGE_READ|_PAGE_WRITE),\prot +.ifc \patype,20 depd,z \prot,8,7,\prot +.else +.ifc \patype,11 + depw,z \prot,8,7,\prot +.else + .error "undefined PA type to do_alias" +.endif +.endif /* * OK, it is in the temp alias region, check whether "from" or "to". * Check "subtle" note in pacache.S re: r23/r26. @@ -1185,7 +1193,7 @@ dtlb_miss_20w: nop dtlb_check_alias_20w: - do_alias spc,t0,t1,va,pte,prot,dtlb_fault + do_alias spc,t0,t1,va,pte,prot,dtlb_fault,20 idtlbt pte,prot @@ -1209,7 +1217,7 @@ nadtlb_miss_20w: nop nadtlb_check_alias_20w: - do_alias spc,t0,t1,va,pte,prot,nadtlb_emulate + do_alias spc,t0,t1,va,pte,prot,nadtlb_emulate,20 idtlbt pte,prot @@ -1241,7 +1249,7 @@ dtlb_miss_11: nop dtlb_check_alias_11: - do_alias spc,t0,t1,va,pte,prot,dtlb_fault + do_alias spc,t0,t1,va,pte,prot,dtlb_fault,11 idtlba pte,(va) idtlbp prot,(va) @@ -1273,7 +1281,7 @@ nadtlb_miss_11: nop nadtlb_check_alias_11: - do_alias spc,t0,t1,va,pte,prot,nadtlb_emulate + do_alias spc,t0,t1,va,pte,prot,nadtlb_emulate,11 idtlba pte,(va) idtlbp prot,(va) @@ -1300,7 +1308,7 @@ dtlb_miss_20: nop dtlb_check_alias_20: - do_alias spc,t0,t1,va,pte,prot,dtlb_fault + do_alias spc,t0,t1,va,pte,prot,dtlb_fault,20 idtlbt pte,prot @@ -1326,7 +1334,7 @@ nadtlb_miss_20: nop nadtlb_check_alias_20: - do_alias spc,t0,t1,va,pte,prot,nadtlb_emulate + do_alias spc,t0,t1,va,pte,prot,nadtlb_emulate,20 idtlbt pte,prot @@ -1453,7 +1461,7 @@ naitlb_miss_20w: nop naitlb_check_alias_20w: - do_alias spc,t0,t1,va,pte,prot,naitlb_fault + do_alias spc,t0,t1,va,pte,prot,naitlb_fault,20 iitlbt pte,prot @@ -1507,7 +1515,7 @@ naitlb_miss_11: nop naitlb_check_alias_11: - do_alias spc,t0,t1,va,pte,prot,itlb_fault + do_alias spc,t0,t1,va,pte,prot,itlb_fault,11 iitlba pte,(%sr0, va) iitlbp prot,(%sr0, va) @@ -1553,7 +1561,7 @@ naitlb_miss_20: nop naitlb_check_alias_20: - do_alias spc,t0,t1,va,pte,prot,naitlb_fault + do_alias spc,t0,t1,va,pte,prot,naitlb_fault,20 iitlbt pte,prot diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 93ff3d9..5d7218a 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -692,7 +692,7 @@ ENTRY(flush_icache_page_asm) /* Purge any old translation */ - pitlb (%sr0,%r28) + pitlb (%sr4,%r28) ldil L%icache_stride, %r1 ldw R%icache_stride(%r1), %r1 @@ -706,27 +706,29 @@ ENTRY(flush_icache_page_asm) sub %r25, %r1, %r25 -1: fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) - fic,m %r1(%r28) + /* fic only has the type 26 form on PA1.1, requiring an + * explicit space specification, so use %sr4 */ +1: fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) + fic,m %r1(%sr4,%r28) cmpb,COND(<<) %r28, %r25,1b - fic,m %r1(%r28) + fic,m %r1(%sr4,%r28) sync bv %r0(%r2) - pitlb (%sr0,%r25) + pitlb (%sr4,%r25) .exit .procend diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c index e141324..d0ea054 100644 --- a/arch/parisc/kernel/signal32.c +++ b/arch/parisc/kernel/signal32.c @@ -67,7 +67,8 @@ put_sigset32(compat_sigset_t __user *up, sigset_t *set, size_t sz) { compat_sigset_t s; - if (sz != sizeof *set) panic("put_sigset32()"); + if (sz != sizeof *set) + return -EINVAL; sigset_64to32(&s, set); return copy_to_user(up, &s, sizeof s); @@ -79,7 +80,8 @@ get_sigset32(compat_sigset_t __user *up, sigset_t *set, size_t sz) compat_sigset_t s; int r; - if (sz != sizeof *set) panic("put_sigset32()"); + if (sz != sizeof *set) + return -EINVAL; if ((r = copy_from_user(&s, up, sz)) == 0) { sigset_32to64(set, &s); diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index c9b9322..7ea75d1 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -73,6 +73,8 @@ static unsigned long get_shared_area(struct address_space *mapping, struct vm_area_struct *vma; int offset = mapping ? get_offset(mapping) : 0; + offset = (offset + (pgoff << PAGE_SHIFT)) & 0x3FF000; + addr = DCACHE_ALIGN(addr - offset) + offset; for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) { diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 8b58bf0..0acc27b 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -811,14 +811,14 @@ void notrace handle_interruption(int code, struct pt_regs *regs) else { /* - * The kernel should never fault on its own address space. + * The kernel should never fault on its own address space, + * unless pagefault_disable() was called before. */ - if (fault_space == 0) + if (fault_space == 0 && !in_atomic()) { pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); - } } diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index fa6f2b8..64a9998 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -50,8 +50,10 @@ SECTIONS . = KERNEL_BINARY_TEXT_START; _text = .; /* Text and read-only data */ - .text ALIGN(16) : { + .head ALIGN(16) : { HEAD_TEXT + } = 0 + .text ALIGN(16) : { TEXT_TEXT SCHED_TEXT LOCK_TEXT @@ -65,7 +67,7 @@ SECTIONS *(.fixup) *(.lock.text) /* out-of-line lock text */ *(.gnu.warning) - } = 0 + } /* End of text section */ _etext = .; diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index b7212b6..f1b5251 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -67,7 +67,7 @@ LDFLAGS_vmlinux-yy := -Bstatic LDFLAGS_vmlinux-$(CONFIG_PPC64)$(CONFIG_RELOCATABLE) := -pie LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-yy) -CFLAGS-$(CONFIG_PPC64) := -mminimal-toc -mtraceback=none -mcall-aixdesc +CFLAGS-$(CONFIG_PPC64) := -mminimal-toc -mtraceback=no -mcall-aixdesc CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 -mmultiple KBUILD_CPPFLAGS += -Iarch/$(ARCH) KBUILD_AFLAGS += -Iarch/$(ARCH) diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 1cf20bd..33a3580 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -126,11 +126,11 @@ static inline u64 cputime64_to_jiffies64(const cputime_t ct) /* * Convert cputime <-> microseconds */ -extern u64 __cputime_msec_factor; +extern u64 __cputime_usec_factor; static inline unsigned long cputime_to_usecs(const cputime_t ct) { - return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC; + return mulhdu(ct, __cputime_usec_factor); } static inline cputime_t usecs_to_cputime(const unsigned long us) @@ -143,7 +143,7 @@ static inline cputime_t usecs_to_cputime(const unsigned long us) sec = us / 1000000; if (ct) { ct *= tb_ticks_per_sec; - do_div(ct, 1000); + do_div(ct, 1000000); } if (sec) ct += (cputime_t) sec * tb_ticks_per_sec; diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 0192a4e..80de64b 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -87,10 +87,9 @@ struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, struct exception_table_entry *finish); -#ifdef CONFIG_MODVERSIONS +#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64) #define ARCH_RELOCATES_KCRCTAB - -extern const unsigned long reloc_start[]; +#define reloc_start PHYSICAL_START #endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MODULE_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c5cae0d..764e99c 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1000,7 +1000,8 @@ /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ #define mfmsr() ({unsigned long rval; \ - asm volatile("mfmsr %0" : "=r" (rval)); rval;}) + asm volatile("mfmsr %0" : "=r" (rval) : \ + : "memory"); rval;}) #ifdef CONFIG_PPC_BOOK3S_64 #define __mtmsrd(v, l) asm volatile("mtmsrd %0," __stringify(l) \ : : "r" (v) : "memory") diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h index 3eb13be..ec63a0a 100644 --- a/arch/powerpc/include/asm/signal.h +++ b/arch/powerpc/include/asm/signal.h @@ -109,6 +109,7 @@ struct sigaction { __sigrestore_t sa_restorer; sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 8184ee9..3fcbae0 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -764,6 +764,16 @@ int fix_alignment(struct pt_regs *regs) nb = aligninfo[instr].len; flags = aligninfo[instr].flags; + /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */ + if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) { + nb = 8; + flags = LD+SW; + } else if (IS_XFORM(instruction) && + ((instruction >> 1) & 0x3ff) == 660) { + nb = 8; + flags = ST+SW; + } + /* Byteswap little endian loads and stores */ swiz = 0; if (regs->msr & MSR_LE) { diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 36e1c8a..4c12a751 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -75,6 +75,7 @@ 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/cputable.c b/arch/powerpc/kernel/cputable.c index 9fb9332..421c9a0 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -268,7 +268,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, - .mmu_features = MMU_FTR_HPTE_TABLE, + .mmu_features = MMU_FTRS_PPC970, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d834425..654fc53 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -380,6 +380,12 @@ _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 @@ -519,9 +525,6 @@ 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) @@ -530,14 +533,22 @@ 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/ftrace.c b/arch/powerpc/kernel/ftrace.c index bf99cfa..6324008 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -245,9 +245,9 @@ __ftrace_make_nop(struct module *mod, /* * On PPC32 the trampoline looks like: - * 0x3d, 0x60, 0x00, 0x00 lis r11,sym@ha - * 0x39, 0x6b, 0x00, 0x00 addi r11,r11,sym@l - * 0x7d, 0x69, 0x03, 0xa6 mtctr r11 + * 0x3d, 0x80, 0x00, 0x00 lis r12,sym@ha + * 0x39, 0x8c, 0x00, 0x00 addi r12,r12,sym@l + * 0x7d, 0x89, 0x03, 0xa6 mtctr r12 * 0x4e, 0x80, 0x04, 0x20 bctr */ @@ -262,9 +262,9 @@ __ftrace_make_nop(struct module *mod, pr_devel(" %08x %08x ", jmp[0], jmp[1]); /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d600000) || - ((jmp[1] & 0xffff0000) != 0x396b0000) || - (jmp[2] != 0x7d6903a6) || + if (((jmp[0] & 0xffff0000) != 0x3d800000) || + ((jmp[1] & 0xffff0000) != 0x398c0000) || + (jmp[2] != 0x7d8903a6) || (jmp[3] != 0x4e800420)) { printk(KERN_ERR "Not a trampoline\n"); return -EINVAL; diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index ba50409..a5031c3 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -425,7 +425,7 @@ _STATIC(__after_prom_start) tovirt(r6,r6) /* on booke, we already run at PAGE_OFFSET */ #endif -#ifdef CONFIG_CRASH_DUMP +#ifdef CONFIG_RELOCATABLE /* * Check if the kernel has to be running as relocatable kernel based on the * variable __run_at_load, if it is set the kernel is treated as relocatable @@ -492,6 +492,7 @@ _GLOBAL(copy_and_flush) sync addi r5,r5,8 addi r6,r6,8 + isync blr .align 8 diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 961bb03..795e807 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -495,7 +495,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) /* number of bytes needed for the bitmap */ sz = (tbl->it_size + 7) >> 3; - page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz)); + page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz)); if (!page) panic("iommu_init_table: Can't allocate %ld bytes\n", sz); tbl->it_map = page_address(page); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 583af70..cac9d2c 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -163,6 +163,8 @@ static int kexec_all_irq_disabled = 0; static void kexec_smp_down(void *arg) { local_irq_disable(); + hard_irq_disable(); + mb(); /* make sure our irqs are disabled before we say they are */ get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF; while(kexec_all_irq_disabled == 0) @@ -245,6 +247,8 @@ static void kexec_prepare_cpus(void) wake_offline_cpus(); smp_call_function(kexec_smp_down, NULL, /* wait */0); local_irq_disable(); + hard_irq_disable(); + mb(); /* make sure IRQs are disabled before we say they are */ get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF; @@ -282,6 +286,7 @@ static void kexec_prepare_cpus(void) if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(0, 0); local_irq_disable(); + hard_irq_disable(); } #endif /* SMP */ diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index f832773..449a7e0 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -187,8 +187,8 @@ int apply_relocate(Elf32_Shdr *sechdrs, static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { - if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16) - && entry->jump[1] == 0x396b0000 + (val & 0xffff)) + if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16) + && entry->jump[1] == 0x398c0000 + (val & 0xffff)) return 1; return 0; } @@ -215,10 +215,9 @@ static uint32_t do_plt_call(void *location, entry++; } - /* Stolen from Paul Mackerras as well... */ - entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */ - entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/ - entry->jump[2] = 0x7d6903a6; /* mtctr r11 */ + entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */ + entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/ + entry->jump[2] = 0x7d8903a6; /* mtctr r12 */ entry->jump[3] = 0x4e800420; /* bctr */ DEBUGP("Initialized plt for 0x%x at %p\n", val, entry); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 91e52df..5596397 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -794,16 +794,8 @@ 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/ptrace.c b/arch/powerpc/kernel/ptrace.c index cb22024..9321d0f 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1497,9 +1497,14 @@ long arch_ptrace(struct task_struct *child, long request, if (index < PT_FPR0) { tmp = ptrace_get_reg(child, (int) index); } else { + unsigned int fpidx = index - PT_FPR0; + flush_fp_to_thread(child); - tmp = ((unsigned long *)child->thread.fpr) - [TS_FPRWIDTH * (index - PT_FPR0)]; + if (fpidx < (PT_FPSCR - PT_FPR0)) + tmp = ((unsigned long *)child->thread.fpr) + [fpidx * TS_FPRWIDTH]; + else + tmp = child->thread.fpscr.val; } ret = put_user(tmp, datalp); break; @@ -1525,9 +1530,14 @@ long arch_ptrace(struct task_struct *child, long request, if (index < PT_FPR0) { ret = ptrace_put_reg(child, index, data); } else { + unsigned int fpidx = index - PT_FPR0; + flush_fp_to_thread(child); - ((unsigned long *)child->thread.fpr) - [TS_FPRWIDTH * (index - PT_FPR0)] = data; + if (fpidx < (PT_FPSCR - PT_FPR0)) + ((unsigned long *)child->thread.fpr) + [fpidx * TS_FPRWIDTH] = data; + else + child->thread.fpscr.val = data; ret = 0; } break; diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index f0f2199..cd51a5c 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -192,6 +192,14 @@ static ssize_t show_dscr_default(struct sysdev_class *class, 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 sysdev_class *class, struct sysdev_class_attribute *attr, const char *buf, size_t count) @@ -204,6 +212,8 @@ static ssize_t __used store_dscr_default(struct sysdev_class *class, 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 2de304a..818d809 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -168,13 +168,13 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Factors for converting from cputime_t (timebase ticks) to - * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds). + * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). * These are all stored as 0.64 fixed-point binary fractions. */ u64 __cputime_jiffies_factor; EXPORT_SYMBOL(__cputime_jiffies_factor); -u64 __cputime_msec_factor; -EXPORT_SYMBOL(__cputime_msec_factor); +u64 __cputime_usec_factor; +EXPORT_SYMBOL(__cputime_usec_factor); u64 __cputime_sec_factor; EXPORT_SYMBOL(__cputime_sec_factor); u64 __cputime_clockt_factor; @@ -192,8 +192,8 @@ static void calc_cputime_factors(void) div128_by_32(HZ, 0, tb_ticks_per_sec, &res); __cputime_jiffies_factor = res.result_low; - div128_by_32(1000, 0, tb_ticks_per_sec, &res); - __cputime_msec_factor = res.result_low; + div128_by_32(1000000, 0, tb_ticks_per_sec, &res); + __cputime_usec_factor = res.result_low; div128_by_32(1, 0, tb_ticks_per_sec, &res); __cputime_sec_factor = res.result_low; div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); @@ -859,13 +859,8 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, void update_vsyscall_tz(void) { - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_mb(); vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; vdso_data->tz_dsttime = sys_tz.tz_dsttime; - smp_mb(); - ++vdso_data->tb_update_count; } static void __init clocksource_init(void) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 1a01414..6889f26 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -935,8 +935,9 @@ 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/kernel/vio.c b/arch/powerpc/kernel/vio.c index 1b695fd..c9f2ac8 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1345,11 +1345,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, const char *cp; dn = dev->of_node; - if (!dn) - return -ENODEV; + if (!dn) { + strcat(buf, "\n"); + return strlen(buf); + } cp = of_get_property(dn, "compatible", NULL); - if (!cp) - return -ENODEV; + if (!cp) { + strcat(buf, "\n"); + return strlen(buf); + } return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp); } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 920276c..3e8fe4b 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -38,9 +38,6 @@ jiffies = jiffies_64 + 4; #endif SECTIONS { - . = 0; - reloc_start = .; - . = KERNELBASE; /* diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c index 549bb2c..ded8a1a 100644 --- a/arch/powerpc/kvm/44x_emulate.c +++ b/arch/powerpc/kvm/44x_emulate.c @@ -79,6 +79,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, run->dcr.dcrn = dcrn; run->dcr.data = 0; run->dcr.is_write = 0; + vcpu->arch.dcr_is_write = 0; vcpu->arch.io_gpr = rt; vcpu->arch.dcr_needed = 1; kvmppc_account_exit(vcpu, DCR_EXITS); @@ -100,6 +101,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, run->dcr.dcrn = dcrn; run->dcr.data = kvmppc_get_gpr(vcpu, rs); run->dcr.is_write = 1; + vcpu->arch.dcr_is_write = 1; vcpu->arch.dcr_needed = 1; kvmppc_account_exit(vcpu, DCR_EXITS); emulated = EMULATE_DO_DCR; diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 18245af..afa2eba 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -272,8 +272,8 @@ _GLOBAL(csum_partial_copy_generic) rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */ beq .Lcopy_aligned - li r7,4 - sub r6,r7,r6 + li r9,4 + sub r6,r9,r6 mtctr r6 1: diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 2c1ae7a..97042c6 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -221,7 +221,7 @@ int __node_distance(int a, int b) int distance = LOCAL_DISTANCE; if (!form1_affinity) - return distance; + return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE); for (i = 0; i < distance_ref_points_depth; i++) { if (distance_lookup_table[a][i] == distance_lookup_table[b][i]) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 856e9c3..6786f9d 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -100,6 +100,7 @@ spufs_new_inode(struct super_block *sb, int mode) if (!inode) goto out; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 1b5dc1a..daf793b 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -85,9 +85,11 @@ void __init wii_memory_fixups(void) wii_hole_start = p[0].base + p[0].size; wii_hole_size = p[1].base - wii_hole_start; - pr_info("MEM1: <%08llx %08llx>\n", p[0].base, p[0].size); + pr_info("MEM1: <%08llx %08llx>\n", + (unsigned long long) p[0].base, (unsigned long long) p[0].size); pr_info("HOLE: <%08lx %08lx>\n", wii_hole_start, wii_hole_size); - pr_info("MEM2: <%08llx %08llx>\n", p[1].base, p[1].size); + pr_info("MEM2: <%08llx %08llx>\n", + (unsigned long long) p[1].base, (unsigned long long) p[1].size); p[0].size += wii_hole_size + p[1].size; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 81e30d9..2e0b2a7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -377,7 +377,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) (0x1UL << 4), &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; - BUG_ON(lpar_rc != H_NOT_FOUND); + + /* + * The test for adjunct partition is performed before the + * ANDCOND test. H_RESOURCE may be returned, so we need to + * check for that as well. + */ + BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE); slot_offset++; slot_offset &= 0x7; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 42541bb..ace1784 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -975,7 +975,7 @@ static int cpu_cmd(void) /* print cpus waiting or in xmon */ printf("cpus stopped:"); count = 0; - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_cpu(cpu) { if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 801fbe1..4e15253 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -67,6 +67,10 @@ static inline int is_zero_pfn(unsigned long pfn) #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) +/* TODO: s390 cannot support io_remap_pfn_range... */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h index cdf5cb2..c872626 100644 --- a/arch/s390/include/asm/signal.h +++ b/arch/s390/include/asm/signal.h @@ -131,6 +131,7 @@ struct sigaction { void (*sa_restorer)(void); sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 88829a4..a4b8f60 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -126,4 +126,32 @@ static inline unsigned long long get_clock_monotonic(void) return get_clock_xt() - sched_clock_base_cc; } +/** + * tod_to_ns - convert a TOD format value to nanoseconds + * @todval: to be converted TOD format value + * Returns: number of nanoseconds that correspond to the TOD format value + * + * Converting a 64 Bit TOD format value to nanoseconds means that the value + * must be divided by 4.096. In order to achieve that we multiply with 125 + * and divide by 512: + * + * ns = (todval * 125) >> 9; + * + * In order to avoid an overflow with the multiplication we can rewrite this. + * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits) + * we end up with + * + * ns = ((2^32 * th + tl) * 125 ) >> 9; + * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9); + * + */ +static inline unsigned long long tod_to_ns(unsigned long long todval) +{ + unsigned long long ns; + + ns = ((todval >> 32) << 23) * 125; + ns += ((todval & 0xffffffff) * 125) >> 9; + return ns; +} + #endif diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index b7a4f2e..d7862ad 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -73,8 +73,6 @@ static inline void __tlb_flush_idte(unsigned long asce) static inline void __tlb_flush_mm(struct mm_struct * mm) { - if (unlikely(cpumask_empty(mm_cpumask(mm)))) - return; /* * If the machine has IDTE we prefer to do a per mm flush * on all cpus instead of doing a local flush if the mm diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 53acaa8..f98af03 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -631,7 +631,6 @@ asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg) return -EFAULT; if (a.offset & ~PAGE_MASK) return -EINVAL; - a.addr = (unsigned long) compat_ptr(a.addr); return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } @@ -642,7 +641,6 @@ asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg) if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; - a.addr = (unsigned long) compat_ptr(a.addr); return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); } diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index dff9330..943ea0e 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators); */ unsigned long long notrace __kprobes sched_clock(void) { - return (get_clock_monotonic() * 125) >> 9; + return tod_to_ns(get_clock_monotonic()); } /* diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 35c21bf..a3db4c8 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -358,7 +358,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return 0; } - sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9; + sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 2ada634..1e88eef 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -445,6 +445,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, static void __vcpu_run(struct kvm_vcpu *vcpu) { + int rc; + memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16); if (need_resched()) @@ -455,21 +457,24 @@ static void __vcpu_run(struct kvm_vcpu *vcpu) kvm_s390_deliver_pending_interrupts(vcpu); + VCPU_EVENT(vcpu, 6, "entering sie flags %x", + atomic_read(&vcpu->arch.sie_block->cpuflags)); + vcpu->arch.sie_block->icptcode = 0; local_irq_disable(); kvm_guest_enter(); local_irq_enable(); - VCPU_EVENT(vcpu, 6, "entering sie flags %x", - atomic_read(&vcpu->arch.sie_block->cpuflags)); - if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) { + rc = sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs); + local_irq_disable(); + kvm_guest_exit(); + local_irq_enable(); + + if (rc) { VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); } VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); - local_irq_disable(); - kvm_guest_exit(); - local_irq_enable(); memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16); } @@ -584,6 +589,14 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) } else prefix = 0; + /* + * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy + * copying in vcpu load/put. Lets update our copies before we save + * it into the save area + */ + save_fp_regs(&vcpu->arch.guest_fpregs); + save_access_regs(vcpu->arch.guest_acrs); + if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs), vcpu->arch.guest_fpregs.fprs, 128, prefix)) return -EFAULT; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index d814f79..6903d44 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -567,6 +567,7 @@ static void pfault_interrupt(unsigned int ext_int_code, tsk->thread.pfault_wait = 0; list_del(&tsk->thread.list); wake_up_process(tsk); + put_task_struct(tsk); } else { /* Completion interrupt was faster than initial * interrupt. Set pfault_wait to -1 so the initial @@ -576,14 +577,22 @@ static void pfault_interrupt(unsigned int ext_int_code, put_task_struct(tsk); } else { /* signal bit not set -> a real page is missing. */ - if (tsk->thread.pfault_wait == -1) { + if (tsk->thread.pfault_wait == 1) { + /* Already on the list with a reference: put to sleep */ + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + set_tsk_need_resched(tsk); + } else if (tsk->thread.pfault_wait == -1) { /* Completion interrupt was faster than the initial * interrupt (pfault_wait == -1). Set pfault_wait * back to zero and exit. */ tsk->thread.pfault_wait = 0; } else { /* Initial interrupt arrived before completion - * interrupt. Let the task sleep. */ + * interrupt. Let the task sleep. + * An extra task reference is needed since a different + * cpu may set the task state to TASK_RUNNING again + * before the scheduler is reached. */ + get_task_struct(tsk); tsk->thread.pfault_wait = 1; list_add(&tsk->thread.list, &pfault_list); set_task_state(tsk, TASK_UNINTERRUPTIBLE); @@ -608,6 +617,7 @@ static int __cpuinit pfault_cpu_notify(struct notifier_block *self, list_del(&thread->list); tsk = container_of(thread, struct task_struct, thread); wake_up_process(tsk); + put_task_struct(tsk); } spin_unlock_irq(&pfault_lock); break; diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 65cb06e..4ccf9f5 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -183,7 +183,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, addr = start; len = (unsigned long) nr_pages << PAGE_SHIFT; end = start + len; - if (end < start) + if ((end < start) || (end > TASK_SIZE)) goto slow_irqon; /* diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index f38112b..978b7fd 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -202,9 +202,9 @@ extern void __kernel_vsyscall; if (vdso_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE); \ else \ - NEW_AUX_ENT(AT_IGNORE, 0); + NEW_AUX_ENT(AT_IGNORE, 0) #else -#define VSYSCALL_AUX_ENT +#define VSYSCALL_AUX_ENT NEW_AUX_ENT(AT_IGNORE, 0) #endif /* CONFIG_VSYSCALL */ #ifdef CONFIG_SH_FPU diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 2e79419..bc31e5e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -31,6 +31,7 @@ config SPARC config SPARC32 def_bool !64BIT + select GENERIC_ATOMIC64 config SPARC64 def_bool 64BIT @@ -590,6 +591,9 @@ config SYSVIPC_COMPAT depends on COMPAT && SYSVIPC default y +config KEYS_COMPAT + def_bool y if COMPAT && KEYS + endmenu source "net/Kconfig" diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 7ae128b..98f223a 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -15,6 +15,8 @@ #ifdef __KERNEL__ +#include <asm-generic/atomic64.h> + #include <asm/system.h> #define ATOMIC_INIT(i) { (i) } diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 1770610..f368cef 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -58,14 +58,20 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - ptep_set_wrprotect(mm, addr, ptep); + pte_t old_pte = *ptep; + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); } static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { - return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + int changed = !pte_same(*ptep, pte); + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_page(vma, addr); + } + return changed; } static inline pte_t huge_ptep_get(pte_t *ptep) diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 9822628..ba63d08 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -774,6 +774,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); } +#include <asm/tlbflush.h> #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/signal.h b/arch/sparc/include/asm/signal.h index e49b828..4929431 100644 --- a/arch/sparc/include/asm/signal.h +++ b/arch/sparc/include/asm/signal.h @@ -191,6 +191,7 @@ struct __old_sigaction { unsigned long sa_flags; void (*sa_restorer)(void); /* not used by Linux/SPARC yet */ }; +#define __ARCH_HAS_SA_RESTORER typedef struct sigaltstack { void __user *ss_sp; diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h index 10bcabc..f856c7f 100644 --- a/arch/sparc/include/asm/system_64.h +++ b/arch/sparc/include/asm/system_64.h @@ -140,8 +140,7 @@ do { \ * and 2 stores in this critical code path. -DaveM */ #define switch_to(prev, next, last) \ -do { flush_tlb_pending(); \ - save_and_clear_fpu(); \ +do { save_and_clear_fpu(); \ /* If you are tempted to conditionalize the following */ \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 2ef4634..f0d6a97 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -11,24 +11,40 @@ struct tlb_batch { struct mm_struct *mm; unsigned long tlb_nr; + unsigned long active; unsigned long vaddrs[TLB_BATCH_NR]; }; extern void flush_tsb_kernel_range(unsigned long start, unsigned long end); extern void flush_tsb_user(struct tlb_batch *tb); +extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); /* TLB flush operations. */ -extern void flush_tlb_pending(void); +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define flush_tlb_range(vma,start,end) \ - do { (void)(start); flush_tlb_pending(); } while (0) -#define flush_tlb_page(vma,addr) flush_tlb_pending() -#define flush_tlb_mm(mm) flush_tlb_pending() +extern void flush_tlb_pending(void); +extern void arch_enter_lazy_mmu_mode(void); +extern void arch_leave_lazy_mmu_mode(void); +#define arch_flush_lazy_mmu_mode() do {} while (0) /* Local cpu only. */ extern void __flush_tlb_all(void); - +extern void __flush_tlb_page(unsigned long context, unsigned long vaddr); extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP @@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end); \ __flush_tlb_kernel_range(start,end); \ } while (0) +static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +} + #else /* CONFIG_SMP */ extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); #define flush_tlb_kernel_range(start, end) \ do { flush_tsb_kernel_range(start,end); \ smp_flush_tlb_kernel_range(start, end); \ } while (0) +#define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + #endif /* ! CONFIG_SMP */ #endif /* _SPARC64_TLBFLUSH_H */ diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c index 68f7e11..ce48203 100644 --- a/arch/sparc/kernel/asm-offsets.c +++ b/arch/sparc/kernel/asm-offsets.c @@ -34,6 +34,8 @@ int foo(void) DEFINE(AOFF_task_thread, offsetof(struct task_struct, thread)); BLANK(); DEFINE(AOFF_mm_context, offsetof(struct mm_struct, context)); + BLANK(); + DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm)); /* DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); */ return 0; diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index 7eef3f7..f5ddc0b 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -268,4 +268,4 @@ static int __init sunfire_init(void) return 0; } -subsys_initcall(sunfire_init); +fs_initcall(sunfire_init); diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index f445e98..cfabc3d 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -1177,7 +1177,7 @@ sys_sigreturn: nop call syscall_trace - nop + mov 1, %o1 1: /* We don't want to muck with user registers like a diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index 79f3103..7c00735 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -25,11 +25,10 @@ kvmap_itlb: */ kvmap_itlb_4v: -kvmap_itlb_nonlinear: /* Catch kernel NULL pointer calls. */ sethi %hi(PAGE_SIZE), %g5 cmp %g4, %g5 - bleu,pn %xcc, kvmap_dtlb_longpath + blu,pn %xcc, kvmap_itlb_longpath nop KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load) diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 6860d40..904ed63 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -513,11 +513,13 @@ static u64 nop_for_index(int idx) static inline void sparc_pmu_enable_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc, int idx) { - u64 val, mask = mask_for_index(idx); + u64 enc, val, mask = mask_for_index(idx); + + enc = perf_event_get_enc(cpuc->events[idx]); val = cpuc->pcr; val &= ~mask; - val |= hwc->config; + val |= event_encoding(enc, idx); cpuc->pcr = val; pcr_ops->write(cpuc->pcr); @@ -1380,8 +1382,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, { unsigned long ufp; - perf_callchain_store(entry, regs->tpc); - ufp = regs->u_regs[UREG_I6] + STACK_BIAS; do { struct sparc_stackf *usf, sf; @@ -1402,8 +1402,6 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, { unsigned long ufp; - perf_callchain_store(entry, regs->tpc); - ufp = regs->u_regs[UREG_I6] & 0xffffffffUL; do { struct sparc_stackf32 *usf, sf; @@ -1422,6 +1420,11 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { + perf_callchain_store(entry, regs->tpc); + + if (!current->mm) + return; + flushw_user(); if (test_thread_flag(TIF_32BIT)) perf_callchain_user_32(entry, regs); diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index d58260b..77d4761 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -309,9 +309,7 @@ void do_rt_sigreturn(struct pt_regs *regs) err |= restore_fpu_state(regs, fpu_save); err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t)); - err |= do_sigaltstack(&sf->stack, NULL, (unsigned long)sf); - - if (err) + if (err || do_sigaltstack(&sf->stack, NULL, (unsigned long)sf) == -EFAULT) goto segv; err |= __get_user(rwin_save, &sf->rwin_save); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 99cb172..e82c18e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -856,7 +856,7 @@ void smp_tsb_sync(struct mm_struct *mm) } extern unsigned long xcall_flush_tlb_mm; -extern unsigned long xcall_flush_tlb_pending; +extern unsigned long xcall_flush_tlb_page; extern unsigned long xcall_flush_tlb_kernel_range; extern unsigned long xcall_fetch_glob_regs; extern unsigned long xcall_receive_signal; @@ -1070,23 +1070,56 @@ local_flush_and_out: put_cpu(); } +struct tlb_pending_info { + unsigned long ctx; + unsigned long nr; + unsigned long *vaddrs; +}; + +static void tlb_pending_func(void *info) +{ + struct tlb_pending_info *t = info; + + __flush_tlb_pending(t->ctx, t->nr, t->vaddrs); +} + void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) { u32 ctx = CTX_HWBITS(mm->context); + struct tlb_pending_info info; int cpu = get_cpu(); + info.ctx = ctx; + info.nr = nr; + info.vaddrs = vaddrs; + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); else - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, - mm_cpumask(mm)); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); put_cpu(); } +void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long context = CTX_HWBITS(mm->context); + int cpu = get_cpu(); + + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) + cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); + else + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); + + put_cpu(); +} + void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end) { start &= PAGE_MASK; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 908b47a..10c9b36 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -519,12 +519,12 @@ SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality) { int ret; - if (current->personality == PER_LINUX32 && - personality == PER_LINUX) - personality = PER_LINUX32; + if (personality(current->personality) == PER_LINUX32 && + personality(personality) == PER_LINUX) + personality |= PER_LINUX32; ret = sys_personality(personality); - if (ret == PER_LINUX32) - ret = PER_LINUX; + if (personality(ret) == PER_LINUX32) + ret &= ~PER_LINUX32; return ret; } diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index 1d7e274..817187d 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -147,7 +147,7 @@ linux_syscall_trace32: srl %i4, 0, %o4 srl %i1, 0, %o1 srl %i2, 0, %o2 - ba,pt %xcc, 2f + ba,pt %xcc, 5f srl %i3, 0, %o3 linux_syscall_trace: @@ -177,13 +177,13 @@ linux_sparc_syscall32: srl %i1, 0, %o1 ! IEU0 Group ldx [%g6 + TI_FLAGS], %l0 ! Load - srl %i5, 0, %o5 ! IEU1 + srl %i3, 0, %o3 ! IEU0 srl %i2, 0, %o2 ! IEU0 Group andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0 bne,pn %icc, linux_syscall_trace32 ! CTI mov %i0, %l5 ! IEU1 - call %l7 ! CTI Group brk forced - srl %i3, 0, %o3 ! IEU0 +5: call %l7 ! CTI Group brk forced + srl %i5, 0, %o5 ! IEU1 ba,a,pt %xcc, 3f /* Linux native system calls enter here... */ @@ -212,24 +212,20 @@ linux_sparc_syscall: 3: stx %o0, [%sp + PTREGS_OFF + PT_V9_I0] ret_sys_call: ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %g3 - ldx [%sp + PTREGS_OFF + PT_V9_TNPC], %l1 ! pc = npc sra %o0, 0, %o0 mov %ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2 sllx %g2, 32, %g2 - /* Check if force_successful_syscall_return() - * was invoked. - */ - ldub [%g6 + TI_SYS_NOERROR], %l2 - brnz,a,pn %l2, 80f - stb %g0, [%g6 + TI_SYS_NOERROR] - cmp %o0, -ERESTART_RESTARTBLOCK bgeu,pn %xcc, 1f - andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %l6 -80: + andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0 + ldx [%sp + PTREGS_OFF + PT_V9_TNPC], %l1 ! pc = npc + +2: + stb %g0, [%g6 + TI_SYS_NOERROR] /* System call success, clear Carry condition code. */ andn %g3, %g2, %g3 +3: stx %g3, [%sp + PTREGS_OFF + PT_V9_TSTATE] bne,pn %icc, linux_syscall_trace2 add %l1, 0x4, %l2 ! npc = npc+4 @@ -238,20 +234,20 @@ ret_sys_call: stx %l2, [%sp + PTREGS_OFF + PT_V9_TNPC] 1: + /* Check if force_successful_syscall_return() + * was invoked. + */ + ldub [%g6 + TI_SYS_NOERROR], %l2 + brnz,pn %l2, 2b + ldx [%sp + PTREGS_OFF + PT_V9_TNPC], %l1 ! pc = npc /* System call failure, set Carry condition code. * Also, get abs(errno) to return to the process. */ - andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %l6 sub %g0, %o0, %o0 - or %g3, %g2, %g3 stx %o0, [%sp + PTREGS_OFF + PT_V9_I0] - stx %g3, [%sp + PTREGS_OFF + PT_V9_TSTATE] - bne,pn %icc, linux_syscall_trace2 - add %l1, 0x4, %l2 ! npc = npc+4 - stx %l1, [%sp + PTREGS_OFF + PT_V9_TPC] + ba,pt %xcc, 3b + or %g3, %g2, %g3 - b,pt %xcc, rtrap - stx %l2, [%sp + PTREGS_OFF + PT_V9_TNPC] linux_syscall_trace2: call syscall_trace_leave add %sp, PTREGS_OFF, %o0 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f566518..248fb67 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -74,7 +74,7 @@ sys_call_table32: .word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy /*270*/ .word sys32_io_submit, sys_io_cancel, compat_sys_io_getevents, sys32_mq_open, sys_mq_unlink .word compat_sys_mq_timedsend, compat_sys_mq_timedreceive, compat_sys_mq_notify, compat_sys_mq_getsetattr, compat_sys_waitid -/*280*/ .word sys32_tee, sys_add_key, sys_request_key, sys_keyctl, compat_sys_openat +/*280*/ .word sys32_tee, sys_add_key, sys_request_key, compat_sys_keyctl, compat_sys_openat .word sys_mkdirat, sys_mknodat, sys_fchownat, compat_sys_futimesat, compat_sys_fstatat64 /*290*/ .word sys_unlinkat, sys_renameat, sys_linkat, sys_symlinkat, sys_readlinkat .word sys_fchmodat, sys_faccessat, compat_sys_pselect6, compat_sys_ppoll, sys_unshare diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S index da1b781..8fa84a3 100644 --- a/arch/sparc/kernel/trampoline_64.S +++ b/arch/sparc/kernel/trampoline_64.S @@ -131,7 +131,6 @@ startup_continue: clr %l5 sethi %hi(num_kernel_image_mappings), %l6 lduw [%l6 + %lo(num_kernel_image_mappings)], %l6 - add %l6, 1, %l6 mov 15, %l7 BRANCH_IF_ANY_CHEETAH(g1,g5,2f) @@ -224,7 +223,6 @@ niagara_lock_tlb: clr %l5 sethi %hi(num_kernel_image_mappings), %l6 lduw [%l6 + %lo(num_kernel_image_mappings)], %l6 - add %l6, 1, %l6 1: mov HV_FAST_MMU_MAP_PERM_ADDR, %o5 diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index a3fc437..4961516 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -40,7 +40,7 @@ lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-y += iomap.o -obj-$(CONFIG_SPARC32) += atomic32.o +obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o obj-y += ksyms.o obj-$(CONFIG_SPARC64) += PeeCeeI.o obj-y += usercopy.o diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c index 1b30bb3..fbb8005 100644 --- a/arch/sparc/lib/ksyms.c +++ b/arch/sparc/lib/ksyms.c @@ -131,15 +131,6 @@ EXPORT_SYMBOL(___copy_from_user); EXPORT_SYMBOL(___copy_in_user); EXPORT_SYMBOL(__clear_user); -/* RW semaphores */ -EXPORT_SYMBOL(__down_read); -EXPORT_SYMBOL(__down_read_trylock); -EXPORT_SYMBOL(__down_write); -EXPORT_SYMBOL(__down_write_trylock); -EXPORT_SYMBOL(__up_read); -EXPORT_SYMBOL(__up_write); -EXPORT_SYMBOL(__downgrade_write); - /* Atomic counter implementation. */ EXPORT_SYMBOL(atomic_add); EXPORT_SYMBOL(atomic_add_ret); diff --git a/arch/sparc/lib/ucmpdi2.c b/arch/sparc/lib/ucmpdi2.c new file mode 100644 index 0000000..1e06ed5 --- /dev/null +++ b/arch/sparc/lib/ucmpdi2.c @@ -0,0 +1,19 @@ +#include <linux/module.h> +#include "libgcc.h" + +word_type __ucmpdi2(unsigned long long a, unsigned long long b) +{ + const DWunion au = {.ll = a}; + const DWunion bu = {.ll = b}; + + if ((unsigned int) au.s.high < (unsigned int) bu.s.high) + return 0; + else if ((unsigned int) au.s.high > (unsigned int) bu.s.high) + return 2; + if ((unsigned int) au.s.low < (unsigned int) bu.s.low) + return 0; + else if ((unsigned int) au.s.low > (unsigned int) bu.s.low) + return 2; + return 1; +} +EXPORT_SYMBOL(__ucmpdi2); diff --git a/arch/sparc/mm/hypersparc.S b/arch/sparc/mm/hypersparc.S index 44aad32..969f964 100644 --- a/arch/sparc/mm/hypersparc.S +++ b/arch/sparc/mm/hypersparc.S @@ -74,7 +74,7 @@ hypersparc_flush_cache_mm_out: /* The things we do for performance... */ hypersparc_flush_cache_range: - ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 #ifndef CONFIG_SMP ld [%o0 + AOFF_mm_context], %g1 cmp %g1, -1 @@ -163,7 +163,7 @@ hypersparc_flush_cache_range_out: */ /* Verified, my ass... */ hypersparc_flush_cache_page: - ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 ld [%o0 + AOFF_mm_context], %g2 #ifndef CONFIG_SMP cmp %g2, -1 @@ -284,7 +284,7 @@ hypersparc_flush_tlb_mm_out: sta %g5, [%g1] ASI_M_MMUREGS hypersparc_flush_tlb_range: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 mov SRMMU_CTX_REG, %g1 ld [%o0 + AOFF_mm_context], %o3 lda [%g1] ASI_M_MMUREGS, %g5 @@ -307,7 +307,7 @@ hypersparc_flush_tlb_range_out: sta %g5, [%g1] ASI_M_MMUREGS hypersparc_flush_tlb_page: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 mov SRMMU_CTX_REG, %g1 ld [%o0 + AOFF_mm_context], %o3 andn %o1, (PAGE_SIZE - 1), %o1 diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 8e073d8..b4989f9 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1071,7 +1071,14 @@ static int __init grab_mblocks(struct mdesc_handle *md) m->size = *val; val = mdesc_get_property(md, node, "address-congruence-offset", NULL); - m->offset = *val; + + /* The address-congruence-offset property is optional. + * Explicity zero it be identifty this. + */ + if (val) + m->offset = *val; + else + m->offset = 0UL; numadbg("MBLOCK[%d]: base[%llx] size[%llx] offset[%llx]\n", count - 1, m->base, m->size, m->offset); @@ -2118,6 +2125,9 @@ EXPORT_SYMBOL(_PAGE_CACHE); #ifdef CONFIG_SPARSEMEM_VMEMMAP unsigned long vmemmap_table[VMEMMAP_SIZE]; +static long __meminitdata addr_start, addr_end; +static int __meminitdata node_start; + int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) { unsigned long vstart = (unsigned long) start; @@ -2148,15 +2158,30 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) *vmem_pp = pte_base | __pa(block); - printk(KERN_INFO "[%p-%p] page_structs=%lu " - "node=%d entry=%lu/%lu\n", start, block, nr, - node, - addr >> VMEMMAP_CHUNK_SHIFT, - VMEMMAP_SIZE); + /* check to see if we have contiguous blocks */ + if (addr_end != addr || node_start != node) { + if (addr_start) + printk(KERN_DEBUG " [%lx-%lx] on node %d\n", + addr_start, addr_end-1, node_start); + addr_start = addr; + node_start = node; + } + addr_end = addr + VMEMMAP_CHUNK; } } return 0; } + +void __meminit vmemmap_populate_print_last(void) +{ + if (addr_start) { + printk(KERN_DEBUG " [%lx-%lx] on node %d\n", + addr_start, addr_end-1, node_start); + addr_start = 0; + addr_end = 0; + node_start = 0; + } +} #endif /* CONFIG_SPARSEMEM_VMEMMAP */ static void prot_init_common(unsigned long page_none, diff --git a/arch/sparc/mm/swift.S b/arch/sparc/mm/swift.S index c801c39..5d2b88d 100644 --- a/arch/sparc/mm/swift.S +++ b/arch/sparc/mm/swift.S @@ -105,7 +105,7 @@ swift_flush_cache_mm_out: .globl swift_flush_cache_range swift_flush_cache_range: - ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 sub %o2, %o1, %o2 sethi %hi(4096), %o3 cmp %o2, %o3 @@ -116,7 +116,7 @@ swift_flush_cache_range: .globl swift_flush_cache_page swift_flush_cache_page: - ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 70: ld [%o0 + AOFF_mm_context], %g2 cmp %g2, -1 @@ -219,7 +219,7 @@ swift_flush_sig_insns: .globl swift_flush_tlb_range .globl swift_flush_tlb_all swift_flush_tlb_range: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 swift_flush_tlb_mm: ld [%o0 + AOFF_mm_context], %g2 cmp %g2, -1 @@ -233,7 +233,7 @@ swift_flush_tlb_all_out: .globl swift_flush_tlb_page swift_flush_tlb_page: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 mov SRMMU_CTX_REG, %g1 ld [%o0 + AOFF_mm_context], %o3 andn %o1, (PAGE_SIZE - 1), %o1 diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b1f279c..072f553 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch); void flush_tlb_pending(void) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); + struct mm_struct *mm = tb->mm; - if (tb->tlb_nr) { - flush_tsb_user(tb); + if (!tb->tlb_nr) + goto out; - if (CTX_VALID(tb->mm->context)) { + flush_tsb_user(tb); + + if (CTX_VALID(mm->context)) { + if (tb->tlb_nr == 1) { + global_flush_tlb_page(mm, tb->vaddrs[0]); + } else { #ifdef CONFIG_SMP smp_flush_tlb_pending(tb->mm, tb->tlb_nr, &tb->vaddrs[0]); @@ -37,12 +43,30 @@ void flush_tlb_pending(void) tb->tlb_nr, &tb->vaddrs[0]); #endif } - tb->tlb_nr = 0; } + tb->tlb_nr = 0; + +out: put_cpu_var(tlb_batch); } +void arch_enter_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + tb->active = 1; +} + +void arch_leave_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + if (tb->tlb_nr) + flush_tlb_pending(); + tb->active = 0; +} + void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig, int fullmm) { @@ -90,6 +114,12 @@ no_cache_flush: nr = 0; } + if (!tb->active) { + flush_tsb_user_page(mm, vaddr); + global_flush_tlb_page(mm, vaddr); + goto out; + } + if (nr == 0) tb->mm = mm; @@ -98,5 +128,6 @@ no_cache_flush: if (nr >= TLB_BATCH_NR) flush_tlb_pending(); +out: put_cpu_var(tlb_batch); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index a5f51b2..cb16ff3 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -8,11 +8,10 @@ #include <linux/slab.h> #include <asm/system.h> #include <asm/page.h> -#include <asm/tlbflush.h> -#include <asm/tlb.h> -#include <asm/mmu_context.h> #include <asm/pgtable.h> +#include <asm/mmu_context.h> #include <asm/tsb.h> +#include <asm/tlb.h> #include <asm/oplib.h> extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; @@ -47,23 +46,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) } } -static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, - unsigned long tsb, unsigned long nentries) +static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries) { - unsigned long i; + unsigned long tag, ent, hash; - for (i = 0; i < tb->tlb_nr; i++) { - unsigned long v = tb->vaddrs[i]; - unsigned long tag, ent, hash; + v &= ~0x1UL; + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); - v &= ~0x1UL; + tsb_flush(ent, tag); +} - hash = tsb_hash(v, hash_shift, nentries); - ent = tsb + (hash * sizeof(struct tsb)); - tag = (v >> 22UL); +static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, + unsigned long tsb, unsigned long nentries) +{ + unsigned long i; - tsb_flush(ent, tag); - } + for (i = 0; i < tb->tlb_nr; i++) + __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } void flush_tsb_user(struct tlb_batch *tb) @@ -91,6 +94,30 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + #if defined(CONFIG_SPARC64_PAGE_SIZE_8KB) #define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K #define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K diff --git a/arch/sparc/mm/tsunami.S b/arch/sparc/mm/tsunami.S index 4e55e8f..bf10a34 100644 --- a/arch/sparc/mm/tsunami.S +++ b/arch/sparc/mm/tsunami.S @@ -24,7 +24,7 @@ /* Sliiick... */ tsunami_flush_cache_page: tsunami_flush_cache_range: - ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 tsunami_flush_cache_mm: ld [%o0 + AOFF_mm_context], %g2 cmp %g2, -1 @@ -46,7 +46,7 @@ tsunami_flush_sig_insns: /* More slick stuff... */ tsunami_flush_tlb_range: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 tsunami_flush_tlb_mm: ld [%o0 + AOFF_mm_context], %g2 cmp %g2, -1 @@ -65,7 +65,7 @@ tsunami_flush_tlb_out: /* This one can be done in a fine grained manner... */ tsunami_flush_tlb_page: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 mov SRMMU_CTX_REG, %g1 ld [%o0 + AOFF_mm_context], %o3 andn %o1, (PAGE_SIZE - 1), %o1 diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index b57a594..dd10caa 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -53,6 +53,33 @@ __flush_tlb_mm: /* 18 insns */ nop .align 32 + .globl __flush_tlb_page +__flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + andn %o1, 1, %o3 + be,pn %icc, 1f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + + .align 32 .globl __flush_tlb_pending __flush_tlb_pending: /* 26 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ @@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + be,pn %icc, 1f + andn %o1, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + __cheetah_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 @@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */ retl nop +__hypervisor_flush_tlb_page: /* 11 insns */ + /* %o0 = context, %o1 = vaddr */ + mov %o0, %g2 + mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g2, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + retl + nop + __hypervisor_flush_tlb_pending: /* 16 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 @@ -339,6 +405,13 @@ cheetah_patch_cachetlbops: call tlb_patch_one mov 19, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__cheetah_flush_tlb_pending), %o1 @@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop - .globl xcall_flush_tlb_pending -xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=context, %g1=nr, %g7=vaddrs[] */ - sllx %g1, 3, %g1 + .globl xcall_flush_tlb_page +xcall_flush_tlb_page: /* 17 insns */ + /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */ or %g5, %g4, %g5 mov PRIMARY_CONTEXT, %g4 stxa %g5, [%g4] ASI_DMMU -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %g5 - andcc %g5, 0x1, %g0 + andcc %g1, 0x1, %g0 be,pn %icc, 2f - - andn %g5, 0x1, %g5 + andn %g1, 0x1, %g5 stxa %g0, [%g5] ASI_IMMU_DEMAP 2: stxa %g0, [%g5] ASI_DMMU_DEMAP membar #Sync - brnz,pt %g1, 1b - nop stxa %g2, [%g4] ASI_DMMU retry nop + nop .globl xcall_flush_tlb_kernel_range xcall_flush_tlb_kernel_range: /* 25 insns */ @@ -495,11 +563,11 @@ xcall_fetch_glob_regs: stx %o7, [%g1 + GR_SNAP_O7] stx %i7, [%g1 + GR_SNAP_I7] /* Don't try this at home kids... */ - rdpr %cwp, %g2 - sub %g2, 1, %g7 + rdpr %cwp, %g3 + sub %g3, 1, %g7 wrpr %g7, %cwp mov %i7, %g7 - wrpr %g2, %cwp + wrpr %g3, %cwp stx %g7, [%g1 + GR_SNAP_RPC] sethi %hi(trap_block), %g7 or %g7, %lo(trap_block), %g7 @@ -596,15 +664,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ membar #Sync retry - .globl __hypervisor_xcall_flush_tlb_pending -__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ - sllx %g1, 3, %g1 + .globl __hypervisor_xcall_flush_tlb_page +__hypervisor_xcall_flush_tlb_page: /* 17 insns */ + /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 mov %o2, %g4 -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g1, %o0 /* ARG0: virtual address */ mov %g5, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ srlx %o0, PAGE_SHIFT, %o0 @@ -613,8 +679,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */ mov HV_MMU_UNMAP_ADDR_TRAP, %g6 brnz,a,pn %o0, __hypervisor_tlb_xcall_error mov %o0, %g5 - brnz,pt %g1, 1b - nop mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 @@ -697,6 +761,13 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 10, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__hypervisor_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_flush_tlb_page), %o1 + call tlb_patch_one + mov 11, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 @@ -728,12 +799,12 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 21, %o2 - sethi %hi(xcall_flush_tlb_pending), %o0 - or %o0, %lo(xcall_flush_tlb_pending), %o0 - sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 - or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + sethi %hi(xcall_flush_tlb_page), %o0 + or %o0, %lo(xcall_flush_tlb_page), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 21, %o2 + mov 17, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 diff --git a/arch/sparc/mm/viking.S b/arch/sparc/mm/viking.S index 6dfcc13..a516372 100644 --- a/arch/sparc/mm/viking.S +++ b/arch/sparc/mm/viking.S @@ -109,7 +109,7 @@ viking_mxcc_flush_page: viking_flush_cache_page: viking_flush_cache_range: #ifndef CONFIG_SMP - ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 #endif viking_flush_cache_mm: #ifndef CONFIG_SMP @@ -149,7 +149,7 @@ viking_flush_tlb_mm: #endif viking_flush_tlb_range: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 mov SRMMU_CTX_REG, %g1 ld [%o0 + AOFF_mm_context], %o3 lda [%g1] ASI_M_MMUREGS, %g5 @@ -174,7 +174,7 @@ viking_flush_tlb_range: #endif viking_flush_tlb_page: - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 mov SRMMU_CTX_REG, %g1 ld [%o0 + AOFF_mm_context], %o3 lda [%g1] ASI_M_MMUREGS, %g5 @@ -240,7 +240,7 @@ sun4dsmp_flush_tlb_range: tst %g5 bne 3f mov SRMMU_CTX_REG, %g1 - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 ld [%o0 + AOFF_mm_context], %o3 lda [%g1] ASI_M_MMUREGS, %g5 sethi %hi(~((1 << SRMMU_PGDIR_SHIFT) - 1)), %o4 @@ -266,7 +266,7 @@ sun4dsmp_flush_tlb_page: tst %g5 bne 2f mov SRMMU_CTX_REG, %g1 - ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */ + ld [%o0 + VMA_VM_MM], %o0 ld [%o0 + AOFF_mm_context], %o3 lda [%g1] ASI_M_MMUREGS, %g5 and %o1, PAGE_MASK, %o1 diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 0249b8b..532a2a4 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -11,6 +11,7 @@ config TILE select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select GENERIC_IRQ_SHOW + select HAVE_SYSCALL_WRAPPERS if TILEGX select SYS_HYPERVISOR # FIXME: investigate whether we need/want these options. diff --git a/arch/tile/Makefile b/arch/tile/Makefile index 17acce7..04c637c 100644 --- a/arch/tile/Makefile +++ b/arch/tile/Makefile @@ -26,6 +26,10 @@ $(error Set TILERA_ROOT or CROSS_COMPILE when building $(ARCH) on $(HOST_ARCH)) endif endif +# The tile compiler may emit .eh_frame information for backtracing. +# In kernel modules, this causes load failures due to unsupported relocations. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables + ifneq ($(CONFIG_DEBUG_EXTRA_FLAGS),"") KBUILD_CFLAGS += $(CONFIG_DEBUG_EXTRA_FLAGS) endif diff --git a/arch/tile/include/asm/bitops.h b/arch/tile/include/asm/bitops.h index 16f1fa5..bd186c4 100644 --- a/arch/tile/include/asm/bitops.h +++ b/arch/tile/include/asm/bitops.h @@ -77,6 +77,11 @@ static inline int ffs(int x) return __builtin_ffs(x); } +static inline int fls64(__u64 w) +{ + return (sizeof(__u64) * 8) - __builtin_clzll(w); +} + /** * fls - find last set bit in word * @x: the word to search @@ -90,12 +95,7 @@ static inline int ffs(int x) */ static inline int fls(int x) { - return (sizeof(int) * 8) - __builtin_clz(x); -} - -static inline int fls64(__u64 w) -{ - return (sizeof(__u64) * 8) - __builtin_clzll(w); + return fls64((unsigned int) x); } static inline unsigned int __arch_hweight32(unsigned int w) diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h index 63294f5..4f7ae39 100644 --- a/arch/tile/include/asm/percpu.h +++ b/arch/tile/include/asm/percpu.h @@ -15,9 +15,37 @@ #ifndef _ASM_TILE_PERCPU_H #define _ASM_TILE_PERCPU_H -register unsigned long __my_cpu_offset __asm__("tp"); -#define __my_cpu_offset __my_cpu_offset -#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp)) +register unsigned long my_cpu_offset_reg asm("tp"); + +#ifdef CONFIG_PREEMPT +/* + * For full preemption, we can't just use the register variable + * directly, since we need barrier() to hazard against it, causing the + * compiler to reload anything computed from a previous "tp" value. + * But we also don't want to use volatile asm, since we'd like the + * compiler to be able to cache the value across multiple percpu reads. + * So we use a fake stack read as a hazard against barrier(). + * The 'U' constraint is like 'm' but disallows postincrement. + */ +static inline unsigned long __my_cpu_offset(void) +{ + unsigned long tp; + register unsigned long *sp asm("sp"); + asm("move %0, tp" : "=r" (tp) : "U" (*sp)); + return tp; +} +#define __my_cpu_offset __my_cpu_offset() +#else +/* + * We don't need to hazard against barrier() since "tp" doesn't ever + * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only + * changes at function call points, at which we are already re-reading + * the value of "tp" due to "my_cpu_offset_reg" being a global variable. + */ +#define __my_cpu_offset my_cpu_offset_reg +#endif + +#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp)) #include <asm-generic/percpu.h> diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c index a7869ad..41459d8 100644 --- a/arch/tile/kernel/compat_signal.c +++ b/arch/tile/kernel/compat_signal.c @@ -406,19 +406,17 @@ int compat_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * Set up registers for signal handler. * Registers that we don't modify keep the value they had from * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). */ regs->pc = ptr_to_compat_reg(ka->sa.sa_handler); regs->ex1 = PL_ICS_EX1(USER_PL, 1); /* set crit sec in handler */ regs->sp = ptr_to_compat_reg(frame); regs->lr = restorer; regs->regs[0] = (unsigned long) usig; - - if (ka->sa.sa_flags & SA_SIGINFO) { - /* Need extra arguments, so mark to restore caller-saves. */ - regs->regs[1] = ptr_to_compat_reg(&frame->info); - regs->regs[2] = ptr_to_compat_reg(&frame->uc); - regs->flags |= PT_FLAGS_CALLER_SAVES; - } + regs->regs[1] = ptr_to_compat_reg(&frame->info); + regs->regs[2] = ptr_to_compat_reg(&frame->uc); + regs->flags |= PT_FLAGS_CALLER_SAVES; /* * Notify any tracer that was single-stepping it. diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c index 49284fa..0996ef7 100644 --- a/arch/tile/lib/exports.c +++ b/arch/tile/lib/exports.c @@ -89,4 +89,6 @@ uint64_t __ashrdi3(uint64_t, unsigned int); EXPORT_SYMBOL(__ashrdi3); uint64_t __ashldi3(uint64_t, unsigned int); EXPORT_SYMBOL(__ashldi3); +int __ffsdi2(uint64_t); +EXPORT_SYMBOL(__ffsdi2); #endif diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 41474fb..5888f1b 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -69,6 +69,8 @@ extern unsigned long end_iomem; #define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) #define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) +#define io_remap_pfn_range remap_pfn_range + /* * The i386 can't do page protection for execute, and considers that the same * are read. @@ -271,6 +273,12 @@ static inline void set_pte(pte_t *pteptr, pte_t pteval) } #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval) +#define __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return !((pte_val(pte_a) ^ pte_val(pte_b)) & ~_PAGE_NEWPAGE); +} + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. @@ -346,11 +354,11 @@ extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr); #define update_mmu_cache(vma,address,ptep) do ; while (0) /* Encode and de-code a swap entry */ -#define __swp_type(x) (((x).val >> 4) & 0x3f) +#define __swp_type(x) (((x).val >> 5) & 0x1f) #define __swp_offset(x) ((x).val >> 11) #define __swp_entry(type, offset) \ - ((swp_entry_t) { ((type) << 4) | ((offset) << 11) }) + ((swp_entry_t) { ((type) << 5) | ((offset) << 11) }) #define __pte_to_swp_entry(pte) \ ((swp_entry_t) { pte_val(pte_mkuptodate(pte)) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 37357a5..90bf314 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1219,10 +1219,6 @@ config HAVE_ARCH_BOOTMEM def_bool y depends on X86_32 && NUMA -config HAVE_ARCH_ALLOC_REMAP - def_bool y - depends on X86_32 && NUMA - config ARCH_HAVE_MEMORY_PRESENT def_bool y depends on X86_32 && DISCONTIGMEM @@ -1451,6 +1447,15 @@ config ARCH_USES_PG_UNCACHED def_bool y depends on X86_PAT +config ARCH_RANDOM + def_bool y + prompt "x86 architectural random number generator" if EXPERT + ---help--- + Enable the x86 architectural RDRAND instruction + (Intel Bull Mountain technology) to generate random numbers. + If supported, this is a high bandwidth, cryptographically + secure hardware random number generator. + config EFI bool "EFI runtime service support" depends on ACPI diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index be6d9e3..3470624 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -2460,10 +2460,12 @@ ENTRY(aesni_cbc_dec) pxor IN3, STATE4 movaps IN4, IV #else - pxor (INP), STATE2 - pxor 0x10(INP), STATE3 pxor IN1, STATE4 movaps IN2, IV + movups (INP), IN1 + pxor IN1, STATE2 + movups 0x10(INP), IN2 + pxor IN2, STATE3 #endif movups STATE1, (OUTP) movups STATE2, 0x10(OUTP) diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index c1870dd..26af1e3 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -208,7 +208,7 @@ sysexit_from_sys_call: testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) jnz ia32_ret_from_sys_call TRACE_IRQS_ON - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %eax,%esi /* second arg, syscall return value */ cmpl $0,%eax /* is it < 0? */ setl %al /* 1 if so, 0 if not */ @@ -218,7 +218,7 @@ sysexit_from_sys_call: GET_THREAD_INFO(%r10) movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi - cli + DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl %edi,TI_flags(%r10) jz \exit diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h new file mode 100644 index 0000000..0d9ec77 --- /dev/null +++ b/arch/x86/include/asm/archrandom.h @@ -0,0 +1,75 @@ +/* + * This file is part of the Linux kernel. + * + * Copyright (c) 2011, Intel Corporation + * Authors: Fenghua Yu <fenghua.yu@intel.com>, + * H. Peter Anvin <hpa@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * + */ + +#ifndef ASM_X86_ARCHRANDOM_H +#define ASM_X86_ARCHRANDOM_H + +#include <asm/processor.h> +#include <asm/cpufeature.h> +#include <asm/alternative.h> +#include <asm/nops.h> + +#define RDRAND_RETRY_LOOPS 10 + +#define RDRAND_INT ".byte 0x0f,0xc7,0xf0" +#ifdef CONFIG_X86_64 +# define RDRAND_LONG ".byte 0x48,0x0f,0xc7,0xf0" +#else +# define RDRAND_LONG RDRAND_INT +#endif + +#ifdef CONFIG_ARCH_RANDOM + +#define GET_RANDOM(name, type, rdrand, nop) \ +static inline int name(type *v) \ +{ \ + int ok; \ + alternative_io("movl $0, %0\n\t" \ + nop, \ + "\n1: " rdrand "\n\t" \ + "jc 2f\n\t" \ + "decl %0\n\t" \ + "jnz 1b\n\t" \ + "2:", \ + X86_FEATURE_RDRAND, \ + ASM_OUTPUT2("=r" (ok), "=a" (*v)), \ + "0" (RDRAND_RETRY_LOOPS)); \ + return ok; \ +} + +#ifdef CONFIG_X86_64 + +GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5); +GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4); + +#else + +GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3); +GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3); + +#endif /* CONFIG_X86_64 */ + +#endif /* CONFIG_ARCH_RANDOM */ + +extern void x86_init_rdrand(struct cpuinfo_x86 *c); + +#endif /* ASM_X86_ARCHRANDOM_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 71cc380..c5d941f 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -173,7 +173,7 @@ #define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ #define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ #define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */ +#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d2ac8e2..1eb45de 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -391,8 +391,8 @@ struct kvm_vcpu_arch { gpa_t time; struct pvclock_vcpu_time_info hv_clock; unsigned int hw_tsc_khz; - unsigned int time_offset; - struct page *time_page; + struct gfn_to_hva_cache pv_time; + bool pv_time_enabled; u64 last_guest_tsc; u64 last_kernel_ns; u64 last_tsc_nsec; diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index ffa037f..a6a6414 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -14,12 +14,6 @@ extern struct pglist_data *node_data[]; #include <asm/numaq.h> -extern void resume_map_numa_kva(pgd_t *pgd); - -#else /* !CONFIG_NUMA */ - -static inline void resume_map_numa_kva(pgd_t *pgd) {} - #endif /* CONFIG_NUMA */ #ifdef CONFIG_DISCONTIGMEM diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index ebbc4d8..2fdfe31 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -731,7 +731,10 @@ static inline void arch_leave_lazy_mmu_mode(void) PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } -void arch_flush_lazy_mmu_mode(void); +static inline void arch_flush_lazy_mmu_mode(void) +{ + PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush); +} static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8288509..4b67ec9 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -85,6 +85,7 @@ struct pv_lazy_ops { /* Set deferred update mode, used for batching operations. */ void (*enter)(void); void (*leave)(void); + void (*flush)(void); }; struct pv_time_ops { @@ -673,6 +674,7 @@ void paravirt_end_context_switch(struct task_struct *next); void paravirt_enter_lazy_mmu(void); void paravirt_leave_lazy_mmu(void); +void paravirt_flush_lazy_mmu(void); void _paravirt_nop(void); u32 _paravirt_ident_32(u32); diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index effff47..43876f1 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -31,6 +31,56 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte) ptep->pte_low = pte.pte_low; } +#define pmd_read_atomic pmd_read_atomic +/* + * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with + * a "*pmdp" dereference done by gcc. Problem is, in certain places + * where pte_offset_map_lock is called, concurrent page faults are + * allowed, if the mmap_sem is hold for reading. An example is mincore + * vs page faults vs MADV_DONTNEED. On the page fault side + * pmd_populate rightfully does a set_64bit, but if we're reading the + * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen + * because gcc will not read the 64bit of the pmd atomically. To fix + * this all places running pmd_offset_map_lock() while holding the + * mmap_sem in read mode, shall read the pmdp pointer using this + * function to know if the pmd is null nor not, and in turn to know if + * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd + * operations. + * + * Without THP if the mmap_sem is hold for reading, the + * pmd can only transition from null to not null while pmd_read_atomic runs. + * So there's no need of literally reading it atomically. + * + * With THP if the mmap_sem is hold for reading, the pmd can become + * THP or null or point to a pte (and in turn become "stable") at any + * time under pmd_read_atomic, so it's mandatory to read it atomically + * with cmpxchg8b. + */ +#ifndef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pmd_read_atomic(pmd_t *pmdp) +{ + pmdval_t ret; + u32 *tmp = (u32 *)pmdp; + + ret = (pmdval_t) (*tmp); + if (ret) { + /* + * If the low part is null, we must not read the high part + * or we can end up with a partial pmd. + */ + smp_rmb(); + ret |= ((pmdval_t)*(tmp + 1)) << 32; + } + + return (pmd_t) { ret }; +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline pmd_t pmd_read_atomic(pmd_t *pmdp) +{ + return (pmd_t) { atomic64_read((atomic64_t *)pmdp) }; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { set_64bit((unsigned long long *)(ptep), native_pte_val(pte)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 18601c8..6be9909 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -142,12 +142,16 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT; } +static inline unsigned long pud_pfn(pud_t pud) +{ + return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT; +} + #define pte_page(pte) pfn_to_page(pte_pfn(pte)) static inline int pmd_large(pmd_t pte) { - return (pmd_flags(pte) & (_PAGE_PSE | _PAGE_PRESENT)) == - (_PAGE_PSE | _PAGE_PRESENT); + return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -415,7 +419,13 @@ static inline int pte_hidden(pte_t pte) static inline int pmd_present(pmd_t pmd) { - return pmd_flags(pmd) & _PAGE_PRESENT; + /* + * Checking for _PAGE_PSE is needed too because + * split_huge_page will temporarily clear the present bit (but + * the _PAGE_PSE flag will remain set at all times while the + * _PAGE_PRESENT bit is clear). + */ + return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } static inline int pmd_none(pmd_t pmd) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 5d9c61d..e5f7248 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -99,7 +99,6 @@ struct cpuinfo_x86 { u16 apicid; u16 initial_apicid; u16 x86_clflush_size; -#ifdef CONFIG_SMP /* number of cores as seen by the OS: */ u16 booted_cores; /* Physical processor id: */ @@ -110,7 +109,6 @@ struct cpuinfo_x86 { u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; -#endif } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define X86_VENDOR_INTEL 0 diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 94e7618..f332d64 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -187,21 +187,14 @@ static inline int v8086_mode(struct pt_regs *regs) #endif } -/* - * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode - * when it traps. The previous stack will be directly underneath the saved - * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. - * - * This is valid only for kernel mode traps. - */ -static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) -{ #ifdef CONFIG_X86_32 - return (unsigned long)(®s->sp); +extern unsigned long kernel_stack_pointer(struct pt_regs *regs); #else +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ return regs->sp; -#endif } +#endif #define GET_IP(regs) ((regs)->ip) #define GET_FP(regs) ((regs)->bp) diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 598457c..6cbc795 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -125,6 +125,8 @@ typedef unsigned long sigset_t; extern void do_notify_resume(struct pt_regs *, void *, __u32); # endif /* __KERNEL__ */ +#define __ARCH_HAS_SA_RESTORER + #ifdef __i386__ # ifdef __KERNEL__ struct old_sigaction { diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index c2ff2a1..f0d89d9 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -93,10 +93,6 @@ do { \ "memory"); \ } while (0) -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT #else /* frame pointer must be last for get_wchan */ @@ -392,9 +388,6 @@ static inline void clflush(volatile void *__p) #define nop() asm volatile ("nop") -void disable_hlt(void); -void enable_hlt(void); - void cpu_idle_wait(void); extern unsigned long arch_align_stack(unsigned long sp); diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 0310da6..1d44903 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_TRAPS_H #define _ASM_X86_TRAPS_H +#include <linux/kprobes.h> #include <asm/debugreg.h> #include <asm/siginfo.h> /* TRAP_TRACE, ... */ @@ -87,4 +88,29 @@ asmlinkage void smp_thermal_interrupt(void); asmlinkage void mce_threshold_interrupt(void); #endif +/* Interrupts/Exceptions */ +enum { + X86_TRAP_DE = 0, /* 0, Divide-by-zero */ + X86_TRAP_DB, /* 1, Debug */ + X86_TRAP_NMI, /* 2, Non-maskable Interrupt */ + X86_TRAP_BP, /* 3, Breakpoint */ + X86_TRAP_OF, /* 4, Overflow */ + X86_TRAP_BR, /* 5, Bound Range Exceeded */ + X86_TRAP_UD, /* 6, Invalid Opcode */ + X86_TRAP_NM, /* 7, Device Not Available */ + X86_TRAP_DF, /* 8, Double Fault */ + X86_TRAP_OLD_MF, /* 9, Coprocessor Segment Overrun */ + X86_TRAP_TS, /* 10, Invalid TSS */ + X86_TRAP_NP, /* 11, Segment Not Present */ + X86_TRAP_SS, /* 12, Stack Segment Fault */ + X86_TRAP_GP, /* 13, General Protection Fault */ + X86_TRAP_PF, /* 14, Page Fault */ + X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */ + X86_TRAP_MF, /* 16, x87 Floating-Point Exception */ + X86_TRAP_AC, /* 17, Alignment Check */ + X86_TRAP_MC, /* 18, Machine Check */ + X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */ + X86_TRAP_IRET = 32, /* 32, IRET Exception */ +}; + #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4558f0d..479d03c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -416,12 +416,14 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, return 0; } - if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (intsrc->source_irq == 0) { if (acpi_skip_timer_override) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + printk(PREFIX "BIOS IRQ0 override ignored.\n"); return 0; } - if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + + if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity + && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); } @@ -1327,17 +1329,12 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d) } /* - * Force ignoring BIOS IRQ0 pin2 override + * Force ignoring BIOS IRQ0 override */ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) { - /* - * The ati_ixp4x0_rev() early PCI quirk should have set - * the acpi_skip_timer_override flag already: - */ if (!acpi_skip_timer_override) { - WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n"); - pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", + pr_notice("%s detected: Ignoring BIOS IRQ0 override\n", d->ident); acpi_skip_timer_override = 1; } @@ -1431,7 +1428,7 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { * is enabled. This input is incorrectly designated the * ISA IRQ 0 via an interrupt source override even though * it is wired to the output of the master 8259A and INTIN0 - * is not connected at all. Force ignoring BIOS IRQ0 pin2 + * is not connected at all. Force ignoring BIOS IRQ0 * override in that cases. */ { @@ -1466,6 +1463,14 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq 6715b"), }, }, + { + .callback = dmi_ignore_irq0_timer_override, + .ident = "FUJITSU SIEMENS", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), + }, + }, {} }; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a81f2d5..4c734e6 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -161,7 +161,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] = #endif #ifdef P6_NOP1 -static const unsigned char __initconst_or_module p6nops[] = +static const unsigned char p6nops[] = { P6_NOP1, P6_NOP2, @@ -220,7 +220,7 @@ void __init arch_init_ideal_nops(void) ideal_nops = intel_nops; #endif } - + break; default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index bfd75ff..d9302b7 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -53,6 +53,8 @@ static struct protection_domain *pt_domain; static struct iommu_ops amd_iommu_ops; +static struct dma_map_ops amd_iommu_dma_ops; + /* * general struct to manage commands send to an IOMMU */ @@ -1778,18 +1780,20 @@ static int device_change_notifier(struct notifier_block *nb, domain = domain_for_device(dev); - /* allocate a protection domain if a device is added */ dma_domain = find_protection_domain(devid); - if (dma_domain) - goto out; - dma_domain = dma_ops_domain_alloc(); - if (!dma_domain) - goto out; - dma_domain->target_dev = devid; + if (!dma_domain) { + /* allocate a protection domain if a device is added */ + dma_domain = dma_ops_domain_alloc(); + if (!dma_domain) + goto out; + dma_domain->target_dev = devid; + + spin_lock_irqsave(&iommu_pd_list_lock, flags); + list_add_tail(&dma_domain->list, &iommu_pd_list); + spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + } - spin_lock_irqsave(&iommu_pd_list_lock, flags); - list_add_tail(&dma_domain->list, &iommu_pd_list); - spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + dev->archdata.dma_ops = &amd_iommu_dma_ops; break; case BUS_NOTIFY_DEL_DEVICE: diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 33df6e8..d86aa3f 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -1363,6 +1363,7 @@ static struct syscore_ops amd_iommu_syscore_ops = { */ static int __init amd_iommu_init(void) { + struct amd_iommu *iommu; int i, ret = 0; /* @@ -1411,9 +1412,6 @@ static int __init amd_iommu_init(void) if (amd_iommu_pd_alloc_bitmap == NULL) goto free; - /* init the device table */ - init_device_table(); - /* * let all alias entries point to itself */ @@ -1463,6 +1461,12 @@ static int __init amd_iommu_init(void) if (ret) goto free_disable; + /* init the device table */ + init_device_table(); + + for_each_iommu(iommu) + iommu_flush_all_caches(iommu); + amd_iommu_init_api(); amd_iommu_init_notifier(); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index bae1efe..be16854 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -154,16 +154,14 @@ int amd_get_subcaches(int cpu) { struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; unsigned int mask; - int cuid = 0; + int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return 0; pci_read_config_dword(link, 0x1d4, &mask); -#ifdef CONFIG_SMP cuid = cpu_data(cpu).compute_unit_id; -#endif return (mask >> (4 * cuid)) & 0xf; } @@ -172,7 +170,7 @@ int amd_set_subcaches(int cpu, int mask) static unsigned int reset, ban; struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); unsigned int reg; - int cuid = 0; + int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf) return -EINVAL; @@ -190,9 +188,7 @@ int amd_set_subcaches(int cpu, int mask) pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000); } -#ifdef CONFIG_SMP cuid = cpu_data(cpu).compute_unit_id; -#endif mask <<= 4 * cuid; mask |= (0xf ^ (1 << cuid)) << 26; diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index f5373df..db4f704 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -20,12 +20,19 @@ static int set_x2apic_phys_mode(char *arg) } early_param("x2apic_phys", set_x2apic_phys_mode); +static bool x2apic_fadt_phys(void) +{ + if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && + (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { + printk(KERN_DEBUG "System requires x2apic physical mode\n"); + return true; + } + return false; +} + static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - if (x2apic_phys) - return x2apic_enabled(); - else - return 0; + return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } static void @@ -108,7 +115,7 @@ static void init_x2apic_ldr(void) static int x2apic_phys_probe(void) { - if (x2apic_mode && x2apic_phys) + if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys())) return 1; return apic == &apic_x2apic_phys; diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 6042981..0e3a82a 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -15,6 +15,7 @@ CFLAGS_common.o := $(nostackp) obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o +obj-y += rdrand.o obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b13ed39..3f4b6da 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -146,7 +146,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -190,7 +189,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) valid_k7: ; -#endif } static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) @@ -556,6 +554,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } + /* + * The way access filter has a performance penalty on some workloads. + * Disable it on the affected CPUs. + */ + if ((c->x86 == 0x15) && + (c->x86_model >= 0x02) && (c->x86_model < 0x20)) { + u64 val; + + if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) { + val |= 0x1E; + checking_wrmsrl(0xc0011021, val); + } + } + cpu_detect_cache_sizes(c); /* Multi core CPU? */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 22a073d..1579ab9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -15,6 +15,7 @@ #include <asm/stackprotector.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> +#include <asm/archrandom.h> #include <asm/hypervisor.h> #include <asm/processor.h> #include <asm/sections.h> @@ -675,9 +676,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_early_init) this_cpu->c_early_init(c); -#ifdef CONFIG_SMP c->cpu_index = 0; -#endif filter_cpuid_features(c, false); setup_smep(c); @@ -760,10 +759,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) c->apicid = c->initial_apicid; # endif #endif - -#ifdef CONFIG_X86_HT c->phys_proc_id = c->initial_apicid; -#endif } setup_smep(c); @@ -857,6 +853,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) #endif init_hypervisor(c); + x86_init_rdrand(c); /* * Clear/Set all flags overriden by options, need do it diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ed6086e..e0dc000 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -179,7 +179,6 @@ static void __cpuinit trap_init_f00f_bug(void) static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -196,7 +195,6 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: SMP operation may be unreliable" "with B stepping processors.\n"); } -#endif } static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 1e8d66c..362190b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -101,15 +101,19 @@ static struct severity { }; /* - * If the EIPV bit is set, it means the saved IP is the - * instruction which caused the MCE. + * If mcgstatus indicated that ip/cs on the stack were + * no good, then "m->cs" will be zero and we will have + * to assume the worst case (IN_KERNEL) as we actually + * have no idea what we were executing when the machine + * check hit. + * If we do have a good "m->cs" (or a faked one in the + * case we were executing in VM86 mode) we can use it to + * distinguish an exception taken in user from from one + * taken in the kernel. */ static int error_context(struct mce *m) { - if (m->mcgstatus & MCG_STATUS_EIPV) - return (m->ip && (m->cs & 3) == 3) ? IN_USER : IN_KERNEL; - /* Unknown, assume kernel */ - return IN_KERNEL; + return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; } int mce_severity(struct mce *a, int tolerant, char **msg) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index ff1ae9b..1396edf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -122,9 +122,7 @@ void mce_setup(struct mce *m) m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); -#ifdef CONFIG_SMP m->socketid = cpu_data(m->extcpu).phys_proc_id; -#endif m->apicid = cpu_data(m->extcpu).initial_apicid; rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); } @@ -453,6 +451,13 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) if (regs && (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV))) { m->ip = regs->ip; m->cs = regs->cs; + /* + * When in VM86 mode make the cs look like ring 3 + * always. This is a lie, but it's better than passing + * the additional vm86 bit around everywhere. + */ + if (v8086_mode(regs)) + m->cs |= 3; } else { m->ip = 0; m->cs = 0; @@ -990,6 +995,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK); + mce_get_rip(&m, regs); severity = mce_severity(&m, tolerant, NULL); /* @@ -1028,7 +1034,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) mce_ring_add(m.addr >> PAGE_SHIFT); - mce_get_rip(&m, regs); mce_log(&m); if (severity > worst) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index bb0adad..b97aa72 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -52,6 +52,7 @@ struct threshold_block { unsigned int cpu; u32 address; u16 interrupt_enable; + bool interrupt_capable; u16 threshold_limit; struct kobject kobj; struct list_head miscj; @@ -64,11 +65,9 @@ struct threshold_bank { }; static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks); -#ifdef CONFIG_SMP static unsigned char shared_bank[NR_BANKS] = { 0, 0, 0, 0, 1 }; -#endif static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ @@ -86,6 +85,21 @@ struct thresh_restart { u16 old_limit; }; +static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits) +{ + /* + * bank 4 supports APIC LVT interrupts implicitly since forever. + */ + if (bank == 4) + return true; + + /* + * IntP: interrupt present; if this bit is set, the thresholding + * bank can generate APIC LVT interrupts + */ + return msr_high_bits & BIT(28); +} + static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) { int msr = (hi & MASK_LVTOFF_HI) >> 20; @@ -107,8 +121,10 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) return 1; }; -/* must be called with correct cpu affinity */ -/* Called via smp_call_function_single() */ +/* + * Called via smp_call_function_single(), must be called with correct + * cpu affinity. + */ static void threshold_restart_bank(void *_tr) { struct thresh_restart *tr = _tr; @@ -131,6 +147,12 @@ static void threshold_restart_bank(void *_tr) (new_count & THRESHOLD_MAX); } + /* clear IntType */ + hi &= ~MASK_INT_TYPE_HI; + + if (!tr->b->interrupt_capable) + goto done; + if (tr->set_lvt_off) { if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) { /* set new lvt offset */ @@ -139,9 +161,10 @@ static void threshold_restart_bank(void *_tr) } } - tr->b->interrupt_enable ? - (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) : - (hi &= ~MASK_INT_TYPE_HI); + if (tr->b->interrupt_enable) + hi |= INT_TYPE_APIC; + + done: hi |= MASK_COUNT_EN_HI; wrmsr(tr->b->address, lo, hi); @@ -202,18 +225,21 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (!block) per_cpu(bank_map, cpu) |= (1 << bank); -#ifdef CONFIG_SMP + if (shared_bank[bank] && c->cpu_core_id) break; -#endif - offset = setup_APIC_mce(offset, - (high & MASK_LVTOFF_HI) >> 20); memset(&b, 0, sizeof(b)); - b.cpu = cpu; - b.bank = bank; - b.block = block; - b.address = address; + b.cpu = cpu; + b.bank = bank; + b.block = block; + b.address = address; + b.interrupt_capable = lvt_interrupt_supported(bank, high); + + if (b.interrupt_capable) { + int new = (high & MASK_LVTOFF_HI) >> 20; + offset = setup_APIC_mce(offset, new); + } mce_threshold_block_init(&b, offset); mce_threshold_vector = amd_threshold_interrupt; @@ -313,6 +339,9 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size) struct thresh_restart tr; unsigned long new; + if (!b->interrupt_capable) + return -EINVAL; + if (strict_strtoul(buf, 0, &new) < 0) return -EINVAL; @@ -471,6 +500,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu, b->cpu = cpu; b->address = address; b->interrupt_enable = 0; + b->interrupt_capable = lvt_interrupt_supported(bank, high); b->threshold_limit = THRESHOLD_MAX; INIT_LIST_HEAD(&b->miscj); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 27c6251..99cd9d2 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -322,17 +322,6 @@ device_initcall(thermal_throttle_init_device); #endif /* CONFIG_SYSFS */ -/* - * Set up the most two significant bit to notify mce log that this thermal - * event type. - * This is a temp solution. May be changed in the future with mce log - * infrasture. - */ -#define CORE_THROTTLED (0) -#define CORE_POWER_LIMIT ((__u64)1 << 62) -#define PACKAGE_THROTTLED ((__u64)2 << 62) -#define PACKAGE_POWER_LIMIT ((__u64)3 << 62) - static void notify_thresholds(__u64 msr_val) { /* check whether the interrupt handler is defined; @@ -362,27 +351,23 @@ static void intel_thermal_interrupt(void) if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, CORE_LEVEL) != 0) - mce_log_therm_throt_event(CORE_THROTTLED | msr_val); + mce_log_therm_throt_event(msr_val); if (this_cpu_has(X86_FEATURE_PLN)) - if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, + therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, - CORE_LEVEL) != 0) - mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val); + CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PTS)) { rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); - if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, + therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, - PACKAGE_LEVEL) != 0) - mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val); + PACKAGE_LEVEL); if (this_cpu_has(X86_FEATURE_PLN)) - if (therm_throt_process(msr_val & + therm_throt_process(msr_val & PACKAGE_THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, - PACKAGE_LEVEL) != 0) - mce_log_therm_throt_event(PACKAGE_POWER_LIMIT - | msr_val); + PACKAGE_LEVEL); } } diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index fe29c1d..4b50c96 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -437,6 +437,7 @@ static __initconst const struct x86_pmu amd_pmu = { * 0x023 DE PERF_CTL[2:0] * 0x02D LS PERF_CTL[3] * 0x02E LS PERF_CTL[3,0] + * 0x031 LS PERF_CTL[2:0] (**) * 0x043 CU PERF_CTL[2:0] * 0x045 CU PERF_CTL[2:0] * 0x046 CU PERF_CTL[2:0] @@ -450,10 +451,12 @@ static __initconst const struct x86_pmu amd_pmu = { * 0x0DD LS PERF_CTL[5:0] * 0x0DE LS PERF_CTL[5:0] * 0x0DF LS PERF_CTL[5:0] + * 0x1C0 EX PERF_CTL[5:3] * 0x1D6 EX PERF_CTL[5:0] * 0x1D8 EX PERF_CTL[5:0] * - * (*) depending on the umask all FPU counters may be used + * (*) depending on the umask all FPU counters may be used + * (**) only one unitmask enabled at a time */ static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0); @@ -503,6 +506,12 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev return &amd_f15_PMC3; case 0x02E: return &amd_f15_PMC30; + case 0x031: + if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1) + return &amd_f15_PMC20; + return &emptyconstraint; + case 0x1C0: + return &amd_f15_PMC53; default: return &amd_f15_PMC50; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index d812fe2..c81d1f8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -754,6 +754,16 @@ static void intel_ds_init(void) } } +void perf_restore_debug_store(void) +{ + struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds); + + if (!x86_pmu.bts && !x86_pmu.pebs) + return; + + wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds); +} + #else /* CONFIG_CPU_SUP_INTEL */ static void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 62ac8cb..72c365a 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -64,12 +64,10 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) static int show_cpuinfo(struct seq_file *m, void *v) { struct cpuinfo_x86 *c = v; - unsigned int cpu = 0; + unsigned int cpu; int i; -#ifdef CONFIG_SMP cpu = c->cpu_index; -#endif seq_printf(m, "processor\t: %u\n" "vendor_id\t: %s\n" "cpu family\t: %d\n" diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c new file mode 100644 index 0000000..feca286 --- /dev/null +++ b/arch/x86/kernel/cpu/rdrand.c @@ -0,0 +1,73 @@ +/* + * This file is part of the Linux kernel. + * + * Copyright (c) 2011, Intel Corporation + * Authors: Fenghua Yu <fenghua.yu@intel.com>, + * H. Peter Anvin <hpa@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * + */ + +#include <asm/processor.h> +#include <asm/archrandom.h> +#include <asm/sections.h> + +static int __init x86_rdrand_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_RDRAND); + return 1; +} +__setup("nordrand", x86_rdrand_setup); + +/* We can't use arch_get_random_long() here since alternatives haven't run */ +static inline int rdrand_long(unsigned long *v) +{ + int ok; + asm volatile("1: " RDRAND_LONG "\n\t" + "jc 2f\n\t" + "decl %0\n\t" + "jnz 1b\n\t" + "2:" + : "=r" (ok), "=a" (*v) + : "0" (RDRAND_RETRY_LOOPS)); + return ok; +} + +/* + * Force a reseed cycle; we are architecturally guaranteed a reseed + * after no more than 512 128-bit chunks of random data. This also + * acts as a test of the CPU capability. + */ +#define RESEED_LOOP ((512*128)/sizeof(unsigned long)) + +void __cpuinit x86_init_rdrand(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_ARCH_RANDOM + unsigned long tmp; + int i, count, ok; + + if (!cpu_has(c, X86_FEATURE_RDRAND)) + return; /* Nothing to do */ + + for (count = i = 0; i < RESEED_LOOP; i++) { + ok = rdrand_long(&tmp); + if (ok) + count++; + } + + if (count != RESEED_LOOP) + clear_cpu_cap(c, X86_FEATURE_RDRAND); +#endif +} diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index c7f64e6..ea6106c 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,7 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { - { X86_FEATURE_DTS, CR_EAX, 0, 0x00000006, 0 }, + { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index edb3d46..2df1252 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1029,7 +1029,7 @@ ENTRY(xen_sysenter_target) ENTRY(xen_hypervisor_callback) CFI_STARTPROC - pushl_cfi $0 + pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL TRACE_IRQS_OFF @@ -1071,14 +1071,15 @@ ENTRY(xen_failsafe_callback) 2: mov 8(%esp),%es 3: mov 12(%esp),%fs 4: mov 16(%esp),%gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ testl %eax,%eax popl_cfi %eax lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f - addl $16,%esp - jmp iret_exc # EAX != 0 => Category 2 (Bad IRET) -5: pushl_cfi $0 # EAX == 0 => Category 1 (Bad segment) + jmp iret_exc +5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp ret_from_exception CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 8a445a0..dd4dba4 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1308,7 +1308,7 @@ ENTRY(xen_failsafe_callback) CFI_RESTORE r11 addq $0x30,%rsp CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $0 + pushq_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp error_exit CFI_ENDPROC diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index af0699b..f6c4674 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -5,8 +5,6 @@ #include <asm/setup.h> #include <asm/bios_ebda.h> -#define BIOS_LOWMEM_KILOBYTES 0x413 - /* * The BIOS places the EBDA/XBDA at the top of conventional * memory, and usually decreases the reported amount of @@ -16,17 +14,30 @@ * chipset: reserve a page before VGA to prevent PCI prefetch * into it (errata #56). Usually the page is reserved anyways, * unless you have no PS/2 mouse plugged in. + * + * This functions is deliberately very conservative. Losing + * memory in the bottom megabyte is rarely a problem, as long + * as we have enough memory to install the trampoline. Using + * memory that is in use by the BIOS or by some DMA device + * the BIOS didn't shut down *is* a big problem. */ + +#define BIOS_LOWMEM_KILOBYTES 0x413 +#define LOWMEM_CAP 0x9f000U /* Absolute maximum */ +#define INSANE_CUTOFF 0x20000U /* Less than this = insane */ + void __init reserve_ebda_region(void) { unsigned int lowmem, ebda_addr; - /* To determine the position of the EBDA and the */ - /* end of conventional memory, we need to look at */ - /* the BIOS data area. In a paravirtual environment */ - /* that area is absent. We'll just have to assume */ - /* that the paravirt case can handle memory setup */ - /* correctly, without our help. */ + /* + * To determine the position of the EBDA and the + * end of conventional memory, we need to look at + * the BIOS data area. In a paravirtual environment + * that area is absent. We'll just have to assume + * that the paravirt case can handle memory setup + * correctly, without our help. + */ if (paravirt_enabled()) return; @@ -37,19 +48,23 @@ void __init reserve_ebda_region(void) /* start of EBDA area */ ebda_addr = get_bios_ebda(); - /* Fixup: bios puts an EBDA in the top 64K segment */ - /* of conventional memory, but does not adjust lowmem. */ - if ((lowmem - ebda_addr) <= 0x10000) - lowmem = ebda_addr; + /* + * Note: some old Dells seem to need 4k EBDA without + * reporting so, so just consider the memory above 0x9f000 + * to be off limits (bugzilla 2990). + */ + + /* If the EBDA address is below 128K, assume it is bogus */ + if (ebda_addr < INSANE_CUTOFF) + ebda_addr = LOWMEM_CAP; - /* Fixup: bios does not report an EBDA at all. */ - /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */ - if ((ebda_addr == 0) && (lowmem >= 0x9f000)) - lowmem = 0x9f000; + /* If lowmem is less than 128K, assume it is bogus */ + if (lowmem < INSANE_CUTOFF) + lowmem = LOWMEM_CAP; - /* Paranoia: should never happen, but... */ - if ((lowmem == 0) || (lowmem >= 0x100000)) - lowmem = 0x9f000; + /* Use the lower of the lowmem and EBDA markers as the cutoff */ + lowmem = min(lowmem, ebda_addr); + lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */ /* reserve all memory between lowmem and the 1MB mark */ memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved"); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index aa083d3..0aa649e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -427,7 +427,7 @@ void hpet_msi_unmask(struct irq_data *data) /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg |= HPET_TN_FSB; + cfg |= HPET_TN_ENABLE | HPET_TN_FSB; hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } @@ -438,7 +438,7 @@ void hpet_msi_mask(struct irq_data *data) /* mask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); - cfg &= ~HPET_TN_FSB; + cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB); hpet_writel(cfg, HPET_Tn_CFG(hdev->num)); } diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 12aff25..f7183ec 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -51,7 +51,7 @@ void __cpuinit mxcsr_feature_mask_init(void) clts(); if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : : "m" (fx_scratch)); + asm volatile("fxsave %0" : "+m" (fx_scratch)); mask = fx_scratch.mxcsr_mask; if (mask == 0) mask = 0x0000ffbf; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 6c0802e..a669961 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -159,10 +159,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) u64 arch_irq_stat(void) { u64 sum = atomic_read(&irq_err_count); - -#ifdef CONFIG_X86_IO_APIC - sum += atomic_read(&irq_mis_count); -#endif return sum; } diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index b727450..53ab9ff 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -162,6 +162,7 @@ static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size) #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 #define F15H_MPB_MAX_SIZE 4096 +#define F16H_MPB_MAX_SIZE 3458 switch (c->x86) { case 0x14: @@ -170,6 +171,9 @@ static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size) case 0x15: max_size = F15H_MPB_MAX_SIZE; break; + case 0x16: + max_size = F16H_MPB_MAX_SIZE; + break; default: max_size = F1XH_MPB_MAX_SIZE; break; diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index f924280..c4e2465 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -297,20 +297,31 @@ static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t size) { unsigned long val; - int cpu = dev->id; - int ret = 0; - char *end; + int cpu; + ssize_t ret = 0, tmp_ret; - val = simple_strtoul(buf, &end, 0); - if (end == buf) + /* allow reload only from the BSP */ + if (boot_cpu_data.cpu_index != dev->id) return -EINVAL; - if (val == 1) { - get_online_cpus(); - if (cpu_online(cpu)) - ret = reload_for_cpu(cpu); - put_online_cpus(); + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val != 1) + return size; + + get_online_cpus(); + for_each_online_cpu(cpu) { + tmp_ret = reload_for_cpu(cpu); + if (tmp_ret != 0) + pr_warn("Error reloading microcode on CPU %d\n", cpu); + + /* save retval of the first encountered reload error */ + if (!ret) + ret = tmp_ret; } + put_online_cpus(); if (!ret) ret = size; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 12fcbe2..f7d1a64 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -175,6 +175,9 @@ static int msr_open(struct inode *inode, struct file *file) unsigned int cpu; struct cpuinfo_x86 *c; + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + cpu = iminor(file->f_path.dentry->d_inode); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 869e1ae..704faba 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -253,6 +253,18 @@ void paravirt_leave_lazy_mmu(void) leave_lazy(PARAVIRT_LAZY_MMU); } +void paravirt_flush_lazy_mmu(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + void paravirt_start_context_switch(struct task_struct *prev) { BUG_ON(preemptible()); @@ -282,18 +294,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return percpu_read(paravirt_lazy_mode); } -void arch_flush_lazy_mmu_mode(void) -{ - preempt_disable(); - - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } - - preempt_enable(); -} - struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, @@ -462,6 +462,7 @@ struct pv_mmu_ops pv_mmu_ops = { .lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, + .flush = paravirt_nop, }, .set_fixmap = native_set_fixmap, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e1ba8cb..4272502 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -341,34 +341,10 @@ void (*pm_idle)(void); EXPORT_SYMBOL(pm_idle); #endif -#ifdef CONFIG_X86_32 -/* - * This halt magic was a workaround for ancient floppy DMA - * wreckage. It should be safe to remove. - */ -static int hlt_counter; -void disable_hlt(void) -{ - hlt_counter++; -} -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - hlt_counter--; -} -EXPORT_SYMBOL(enable_hlt); - -static inline int hlt_use_halt(void) -{ - return (!hlt_counter && boot_cpu_data.hlt_works_ok); -} -#else static inline int hlt_use_halt(void) { return 1; } -#endif /* * We use this if we don't have any better diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 807c2a2..911e16d 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/module.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -164,6 +165,35 @@ static inline bool invalid_selector(u16 value) #define FLAG_MASK FLAG_MASK_32 +/* + * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode + * when it traps. The previous stack will be directly underneath the saved + * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. + * + * Now, if the stack is empty, '®s->sp' is out of range. In this + * case we try to take the previous stack. To always return a non-null + * stack pointer we fall back to regs as stack if no previous stack + * exists. + * + * This is valid only for kernel mode traps. + */ +unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1); + unsigned long sp = (unsigned long)®s->sp; + struct thread_info *tinfo; + + if (context == (sp & ~(THREAD_SIZE - 1))) + return sp; + + tinfo = (struct thread_info *)context; + if (tinfo->previous_esp) + return tinfo->previous_esp; + + return (unsigned long)regs; +} +EXPORT_SYMBOL_GPL(kernel_stack_pointer); + static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index d4a705f..282c98f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -452,6 +452,30 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"), }, }, + { /* Handle problems with rebooting on the Precision M6600. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), + }, + }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Some C6100 machines were shipped with vendor being 'Dell'. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, { } }; diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 7a6f3b3..f2bb9c9 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -160,7 +160,7 @@ identity_mapped: xorq %rbp, %rbp xorq %r8, %r8 xorq %r9, %r9 - xorq %r10, %r9 + xorq %r10, %r10 xorq %r11, %r11 xorq %r12, %r12 xorq %r13, %r13 diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index afaf384..6c4e9ff 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -631,6 +631,83 @@ static __init void reserve_ibft_region(void) static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; +static bool __init snb_gfx_workaround_needed(void) +{ +#ifdef CONFIG_PCI + int i; + u16 vendor, devid; + static const u16 snb_ids[] = { + 0x0102, + 0x0112, + 0x0122, + 0x0106, + 0x0116, + 0x0126, + 0x010a, + }; + + /* Assume no if something weird is going on with PCI */ + if (!early_pci_allowed()) + return false; + + vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID); + if (vendor != 0x8086) + return false; + + devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID); + for (i = 0; i < ARRAY_SIZE(snb_ids); i++) + if (devid == snb_ids[i]) + return true; +#endif + + return false; +} + +/* + * Sandy Bridge graphics has trouble with certain ranges, exclude + * them from allocation. + */ +static void __init trim_snb_memory(void) +{ + static const unsigned long bad_pages[] = { + 0x20050000, + 0x20110000, + 0x20130000, + 0x20138000, + 0x40004000, + }; + int i; + + if (!snb_gfx_workaround_needed()) + return; + + printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n"); + + /* + * Reserve all memory below the 1 MB mark that has not + * already been reserved. + */ + memblock_reserve(0, 1<<20); + + for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { + if (memblock_reserve(bad_pages[i], PAGE_SIZE)) + printk(KERN_WARNING "failed to reserve 0x%08lx\n", + bad_pages[i]); + } +} + +/* + * Here we put platform-specific memory range workarounds, i.e. + * memory known to be corrupt or otherwise in need to be reserved on + * specific platforms. + * + * If this gets used more widely it could use a real dispatch mechanism. + */ +static void __init trim_platform_memory_ranges(void) +{ + trim_snb_memory(); +} + static void __init trim_bios_range(void) { /* @@ -651,6 +728,7 @@ static void __init trim_bios_range(void) * take them out. */ e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -929,6 +1007,8 @@ void __init setup_arch(char **cmdline_p) setup_trampolines(); + trim_platform_memory_ranges(); + init_gbpages(); /* max_pfn_mapped is updated here */ @@ -937,8 +1017,21 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { - max_pfn_mapped = init_memory_mapping(1UL<<32, - max_pfn<<PAGE_SHIFT); + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (ei->addr + ei->size <= 1UL << 32) + continue; + + if (ei->type == E820_RESERVED) + continue; + + max_pfn_mapped = init_memory_mapping( + ei->addr < 1UL << 32 ? 1UL << 32 : ei->addr, + ei->addr + ei->size); + } + /* can we preseve max_low_pfn ?*/ max_low_pfn = max_pfn; } diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 71f4727..5a98aa2 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void) #endif rc = -EINVAL; if (pcpu_chosen_fc != PCPU_FC_PAGE) { - const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE; const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE; + size_t atom_size; + /* + * On 64bit, use PMD_SIZE for atom_size so that embedded + * percpu areas are aligned to PMD. This, in the future, + * can also allow using PMD mappings in vmalloc area. Use + * PAGE_SIZE on 32bit as vmalloc space is highly contended + * and large vmalloc area allocs can easily fail. + */ +#ifdef CONFIG_X86_64 + atom_size = PMD_SIZE; +#else + atom_size = PAGE_SIZE; +#endif rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, dyn_size, atom_size, pcpu_cpu_distance, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index efad723..43e04d1 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -338,11 +338,15 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) +static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) { + struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; struct kvm_timer *pt = &ps->pit_timer; s64 interval; + if (!irqchip_in_kernel(kvm)) + return; + interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); pr_debug("create pit timer, interval is %llu nsec\n", interval); @@ -394,13 +398,13 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) /* FIXME: enhance mode 4 precision */ case 4: if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) { - create_pit_timer(ps, val, 0); + create_pit_timer(kvm, val, 0); } break; case 2: case 3: if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){ - create_pit_timer(ps, val, 1); + create_pit_timer(kvm, val, 1); } break; default: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2ad060a..be1d830 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3836,6 +3836,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (err != EMULATE_DONE) return 0; + if (vcpu->arch.halt_request) { + vcpu->arch.halt_request = 0; + ret = kvm_emulate_halt(vcpu); + goto out; + } + if (signal_pending(current)) goto out; if (need_resched()) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fbb0936..34afae8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -548,8 +548,6 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if (index != XCR_XFEATURE_ENABLED_MASK) return 1; xcr0 = xcr; - if (kvm_x86_ops->get_cpl(vcpu) != 0) - return 1; if (!(xcr0 & XSTATE_FP)) return 1; if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) @@ -563,7 +561,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (__kvm_set_xcr(vcpu, index, xcr)) { + if (kvm_x86_ops->get_cpl(vcpu) != 0 || + __kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); return 1; } @@ -575,6 +574,9 @@ static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + if (!cpu_has_xsave) + return 0; + best = kvm_find_cpuid_entry(vcpu, 1, 0); return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } @@ -1070,7 +1072,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) { unsigned long flags; struct kvm_vcpu_arch *vcpu = &v->arch; - void *shared_kaddr; unsigned long this_tsc_khz; s64 kernel_ns, max_kernel_ns; u64 tsc_timestamp; @@ -1106,7 +1107,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) local_irq_restore(flags); - if (!vcpu->time_page) + if (!vcpu->pv_time_enabled) return 0; /* @@ -1164,14 +1165,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) */ vcpu->hv_clock.version += 2; - shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0); - - memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); - - kunmap_atomic(shared_kaddr, KM_USER0); - - mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); return 0; } @@ -1451,7 +1447,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa)) + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + sizeof(u32))) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); @@ -1461,10 +1458,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - if (vcpu->arch.time_page) { - kvm_release_page_dirty(vcpu->arch.time_page); - vcpu->arch.time_page = NULL; - } + vcpu->arch.pv_time_enabled = false; } int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) @@ -1524,6 +1518,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { + u64 gpa_offset; kvmclock_reset(vcpu); vcpu->arch.time = data; @@ -1533,16 +1528,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!(data & 1)) break; - /* ...but clean it before doing the actual write */ - vcpu->arch.time_offset = data & ~(PAGE_MASK | 1); - - vcpu->arch.time_page = - gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT); + gpa_offset = data & ~(PAGE_MASK | 1); - if (is_error_page(vcpu->arch.time_page)) { - kvm_release_page_clean(vcpu->arch.time_page); - vcpu->arch.time_page = NULL; - } + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.pv_time, data & ~1ULL, + sizeof(struct pvclock_vcpu_time_info))) + vcpu->arch.pv_time_enabled = false; + else + vcpu->arch.pv_time_enabled = true; break; } case MSR_KVM_ASYNC_PF_EN: @@ -3410,6 +3403,9 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EEXIST; if (kvm->arch.vpic) goto create_irqchip_unlock; + r = -EINVAL; + if (atomic_read(&kvm->online_vcpus)) + goto create_irqchip_unlock; r = -ENOMEM; vpic = kvm_create_pic(kvm); if (vpic) { @@ -5851,6 +5847,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int pending_vec, max_bits, idx; struct desc_ptr dt; + if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE)) + return -EINVAL; + dt.size = sregs->idt.limit; dt.address = sregs->idt.base; kvm_x86_ops->set_idt(vcpu, &dt); @@ -6116,12 +6115,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) if (r == 0) r = kvm_mmu_setup(vcpu); vcpu_put(vcpu); - if (r < 0) - goto free_vcpu; - return 0; -free_vcpu: - kvm_x86_ops->vcpu_free(vcpu); return r; } @@ -6194,6 +6188,11 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); +} + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct page *page; @@ -6243,6 +6242,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) goto fail_free_mce_banks; + vcpu->arch.pv_time_enabled = false; kvm_async_pf_hash_reset(vcpu); return 0; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index db832fd..2d45247 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1309,6 +1309,7 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; + pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; pv_mmu_ops.pte_update_defer = lguest_pte_update; diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b7c2849..554b7b5 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -169,10 +169,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) char c; unsigned zero_len; - for (; len; --len) { + for (; len; --len, to++) { if (__get_user_nocheck(c, from++, sizeof(char))) break; - if (__put_user_nocheck(c, to++, sizeof(char))) + if (__put_user_nocheck(c, to, sizeof(char))) break; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2dbf6bf..7653f14 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -376,10 +376,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) + if (pgd_none(*pgd)) { set_pgd(pgd, *pgd_ref); - else + arch_flush_lazy_mmu_mode(); + } else { BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } /* * Below here mismatches are bugs because these lower tables @@ -720,12 +722,15 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, if (is_errata100(regs, address)) return; - if (unlikely(show_unhandled_signals)) + /* Kernel addresses are always protection faults: */ + if (address >= TASK_SIZE) + error_code |= PF_PROT; + + if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); - /* Kernel addresses are always protection faults: */ tsk->thread.cr2 = address; - tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.error_code = error_code; tsk->thread.trap_no = 14; force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index f581a18..df7d12c 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) } /* - * search for a shareable pmd page for hugetlb. + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. */ -static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +static pte_t * +huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; @@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; + pte_t *pte; if (!vma_shareable(vma, addr)) - return; + return (pte_t *)pmd_alloc(mm, pud, addr); mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) { @@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) put_page(virt_to_page(spte)); spin_unlock(&mm->page_table_lock); out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); mutex_unlock(&mapping->i_mmap_mutex); + return pte; } /* @@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, } else { BUG_ON(sz != PMD_SIZE); if (pud_none(*pud)) - huge_pmd_share(mm, addr, pud); - pte = (pte_t *) pmd_alloc(mm, pud, addr); + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); } } BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 87488b9..96c4577 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -28,37 +28,56 @@ int direct_gbpages #endif ; -static void __init find_early_table_space(unsigned long end, int use_pse, - int use_gbpages) +struct map_range { + unsigned long start; + unsigned long end; + unsigned page_size_mask; +}; + +/* + * First calculate space needed for kernel direct mapping page tables to cover + * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB + * pages. Then find enough contiguous space for those page tables. + */ +static void __init find_early_table_space(struct map_range *mr, int nr_range) { - unsigned long puds, pmds, ptes, tables, start = 0, good_end = end; + int i; + unsigned long puds = 0, pmds = 0, ptes = 0, tables; + unsigned long start = 0, good_end; + unsigned long pgd_extra = 0; phys_addr_t base; - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); - - if (use_gbpages) { - unsigned long extra; + for (i = 0; i < nr_range; i++) { + unsigned long range, extra; - extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT); - pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT; - } else - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; + if ((mr[i].end >> PGDIR_SHIFT) - (mr[i].start >> PGDIR_SHIFT)) + pgd_extra++; - tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); + range = mr[i].end - mr[i].start; + puds += (range + PUD_SIZE - 1) >> PUD_SHIFT; - if (use_pse) { - unsigned long extra; + if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) { + extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT); + pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT; + } else { + pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT; + } - extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); + if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) { + extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT); #ifdef CONFIG_X86_32 - extra += PMD_SIZE; + extra += PMD_SIZE; #endif - ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; - } else - ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; + } else { + ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT; + } + } + tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); + tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); + tables += (pgd_extra * PAGE_SIZE); #ifdef CONFIG_X86_32 /* for fixmap */ @@ -74,8 +93,9 @@ static void __init find_early_table_space(unsigned long end, int use_pse, pgt_buf_end = pgt_buf_start; pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); - printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT); + printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n", + mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT, + (pgt_buf_top << PAGE_SHIFT) - 1); } void __init native_pagetable_reserve(u64 start, u64 end) @@ -83,12 +103,6 @@ void __init native_pagetable_reserve(u64 start, u64 end) memblock_x86_reserve_range(start, end, "PGTABLE"); } -struct map_range { - unsigned long start; - unsigned long end; - unsigned page_size_mask; -}; - #ifdef CONFIG_X86_32 #define NR_RANGE_MR 3 #else /* CONFIG_X86_64 */ @@ -260,7 +274,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * nodes are discovered. */ if (!after_bootmem) - find_early_table_space(end, use_pse, use_gbpages); + find_early_table_space(mr, nr_range); for (i = 0; i < nr_range; i++) ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bbaaa00..44b93da 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -831,6 +831,9 @@ int kern_addr_valid(unsigned long addr) if (pud_none(*pud)) return 0; + if (pud_large(*pud)) + return pfn_valid(pud_pfn(*pud)); + pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return 0; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index f5510d8..469ccae 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -207,9 +207,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end) if (end && (end - start) < NODE_MIN_SIZE) return; - /* initialize remap allocator before aligning to ZONE_ALIGN */ - init_alloc_remap(nid, start, end); - start = roundup(start, ZONE_ALIGN); printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n", diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 849a975..025d469 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -73,167 +73,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, extern unsigned long highend_pfn, highstart_pfn; -#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE) - -static void *node_remap_start_vaddr[MAX_NUMNODES]; -void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); - -/* - * Remap memory allocator - */ -static unsigned long node_remap_start_pfn[MAX_NUMNODES]; -static void *node_remap_end_vaddr[MAX_NUMNODES]; -static void *node_remap_alloc_vaddr[MAX_NUMNODES]; - -/** - * alloc_remap - Allocate remapped memory - * @nid: NUMA node to allocate memory from - * @size: The size of allocation - * - * Allocate @size bytes from the remap area of NUMA node @nid. The - * size of the remap area is predetermined by init_alloc_remap() and - * only the callers considered there should call this function. For - * more info, please read the comment on top of init_alloc_remap(). - * - * The caller must be ready to handle allocation failure from this - * function and fall back to regular memory allocator in such cases. - * - * CONTEXT: - * Single CPU early boot context. - * - * RETURNS: - * Pointer to the allocated memory on success, %NULL on failure. - */ -void *alloc_remap(int nid, unsigned long size) -{ - void *allocation = node_remap_alloc_vaddr[nid]; - - size = ALIGN(size, L1_CACHE_BYTES); - - if (!allocation || (allocation + size) > node_remap_end_vaddr[nid]) - return NULL; - - node_remap_alloc_vaddr[nid] += size; - memset(allocation, 0, size); - - return allocation; -} - -#ifdef CONFIG_HIBERNATION -/** - * resume_map_numa_kva - add KVA mapping to the temporary page tables created - * during resume from hibernation - * @pgd_base - temporary resume page directory - */ -void resume_map_numa_kva(pgd_t *pgd_base) -{ - int node; - - for_each_online_node(node) { - unsigned long start_va, start_pfn, nr_pages, pfn; - - start_va = (unsigned long)node_remap_start_vaddr[node]; - start_pfn = node_remap_start_pfn[node]; - nr_pages = (node_remap_end_vaddr[node] - - node_remap_start_vaddr[node]) >> PAGE_SHIFT; - - printk(KERN_DEBUG "%s: node %d\n", __func__, node); - - for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) { - unsigned long vaddr = start_va + (pfn << PAGE_SHIFT); - pgd_t *pgd = pgd_base + pgd_index(vaddr); - pud_t *pud = pud_offset(pgd, vaddr); - pmd_t *pmd = pmd_offset(pud, vaddr); - - set_pmd(pmd, pfn_pmd(start_pfn + pfn, - PAGE_KERNEL_LARGE_EXEC)); - - printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n", - __func__, vaddr, start_pfn + pfn); - } - } -} -#endif - -/** - * init_alloc_remap - Initialize remap allocator for a NUMA node - * @nid: NUMA node to initizlie remap allocator for - * - * NUMA nodes may end up without any lowmem. As allocating pgdat and - * memmap on a different node with lowmem is inefficient, a special - * remap allocator is implemented which can be used by alloc_remap(). - * - * For each node, the amount of memory which will be necessary for - * pgdat and memmap is calculated and two memory areas of the size are - * allocated - one in the node and the other in lowmem; then, the area - * in the node is remapped to the lowmem area. - * - * As pgdat and memmap must be allocated in lowmem anyway, this - * doesn't waste lowmem address space; however, the actual lowmem - * which gets remapped over is wasted. The amount shouldn't be - * problematic on machines this feature will be used. - * - * Initialization failure isn't fatal. alloc_remap() is used - * opportunistically and the callers will fall back to other memory - * allocation mechanisms on failure. - */ -void __init init_alloc_remap(int nid, u64 start, u64 end) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long end_pfn = end >> PAGE_SHIFT; - unsigned long size, pfn; - u64 node_pa, remap_pa; - void *remap_va; - - /* - * The acpi/srat node info can show hot-add memroy zones where - * memory could be added but not currently present. - */ - printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n", - nid, start_pfn, end_pfn); - - /* calculate the necessary space aligned to large page size */ - size = node_memmap_size_bytes(nid, start_pfn, end_pfn); - size += ALIGN(sizeof(pg_data_t), PAGE_SIZE); - size = ALIGN(size, LARGE_PAGE_BYTES); - - /* allocate node memory and the lowmem remap area */ - node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES); - if (node_pa == MEMBLOCK_ERROR) { - pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n", - size, nid); - return; - } - memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM"); - - remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT, - max_low_pfn << PAGE_SHIFT, - size, LARGE_PAGE_BYTES); - if (remap_pa == MEMBLOCK_ERROR) { - pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n", - size, nid); - memblock_x86_free_range(node_pa, node_pa + size); - return; - } - memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG"); - remap_va = phys_to_virt(remap_pa); - - /* perform actual remap */ - for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE) - set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT), - (node_pa >> PAGE_SHIFT) + pfn, - PAGE_KERNEL_LARGE); - - /* initialize remap allocator parameters */ - node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT; - node_remap_start_vaddr[nid] = remap_va; - node_remap_end_vaddr[nid] = remap_va + size; - node_remap_alloc_vaddr[nid] = remap_va; - - printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n", - nid, node_pa, node_pa + size, remap_va, remap_va + size); -} - void __init initmem_init(void) { x86_numa_init(); diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index 7178c3a..ad86ec9 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -21,12 +21,6 @@ void __init numa_reset_distance(void); void __init x86_numa_init(void); -#ifdef CONFIG_X86_64 -static inline void init_alloc_remap(int nid, u64 start, u64 end) { } -#else -void __init init_alloc_remap(int nid, u64 start, u64 end); -#endif - #ifdef CONFIG_NUMA_EMU void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt); diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 68894fd..a00c588 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -55,7 +55,7 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, val |= counter_config->extra; event &= model->event_mask ? model->event_mask : 0xFF; val |= event & 0xFF; - val |= (event & 0x0F00) << 24; + val |= (u64)(event & 0x0F00) << 24; return val; } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 6dd8955..0951b81 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -521,3 +521,20 @@ static void sb600_disable_hpet_bar(struct pci_dev *dev) } } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar); + +/* + * Twinhead H12Y needs us to block out a region otherwise we map devices + * there and any access kills the box. + * + * See: https://bugzilla.kernel.org/show_bug.cgi?id=10231 + * + * Match off the LPC and svid/sdid (older kernels lose the bridge subvendor) + */ +static void __devinit twinhead_reserve_killing_zone(struct pci_dev *dev) +{ + if (dev->subsystem_vendor == 0x14FF && dev->subsystem_device == 0xA003) { + pr_info("Reserving memory on Twinhead H12Y\n"); + request_mem_region(0xFFB00000, 0x100000, "twinhead"); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 899e393..86272f0 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -588,10 +588,13 @@ void __init efi_enter_virtual_mode(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; + if (!(md->attribute & EFI_MEMORY_RUNTIME)) { +#ifdef CONFIG_X86_64 + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) +#endif + continue; + } size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index ac3aa54..0fba86d 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -38,7 +38,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> -static pgd_t save_pgd __initdata; +static pgd_t *save_pgd __initdata; static unsigned long efi_flags __initdata; static void __init early_code_mapping_set_exec(int executable) @@ -61,12 +61,20 @@ static void __init early_code_mapping_set_exec(int executable) void __init efi_call_phys_prelog(void) { unsigned long vaddress; + int pgd; + int n_pgds; early_code_mapping_set_exec(1); local_irq_save(efi_flags); - vaddress = (unsigned long)__va(0x0UL); - save_pgd = *pgd_offset_k(0x0UL); - set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress)); + + n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); + save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL); + + for (pgd = 0; pgd < n_pgds; pgd++) { + save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE); + vaddress = (unsigned long)__va(pgd * PGDIR_SIZE); + set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress)); + } __flush_tlb_all(); } @@ -75,7 +83,11 @@ void __init efi_call_phys_epilog(void) /* * After the lock is released, the original page table is restored. */ - set_pgd(pgd_offset_k(0x0UL), save_pgd); + int pgd; + int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + for (pgd = 0; pgd < n_pgds; pgd++) + set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]); + kfree(save_pgd); __flush_tlb_all(); local_irq_restore(efi_flags); early_code_mapping_set_exec(0); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 87bb35e..0ea8bd2 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -10,6 +10,7 @@ #include <linux/suspend.h> #include <linux/smp.h> +#include <linux/perf_event.h> #include <asm/pgtable.h> #include <asm/proto.h> @@ -224,6 +225,7 @@ static void __restore_processor_state(struct saved_context *ctxt) do_fpu_end(); mtrr_bp_restore(); + perf_restore_debug_store(); } /* Needed by apm.c */ diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 3769079..a09ecb9 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -130,8 +130,6 @@ static int resume_physical_mapping_init(pgd_t *pgd_base) } } - resume_map_numa_kva(pgd_base); - return 0; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0fb662a..e11efbd 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -62,6 +62,7 @@ #include <asm/reboot.h> #include <asm/stackprotector.h> #include <asm/hypervisor.h> +#include <asm/pci_x86.h> #include "xen-ops.h" #include "mmu.h" @@ -128,6 +129,21 @@ static void xen_vcpu_setup(int cpu) BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); + /* + * This path is called twice on PVHVM - first during bootup via + * smp_init -> xen_hvm_cpu_notify, and then if the VCPU is being + * hotplugged: cpu_up -> xen_hvm_cpu_notify. + * As we can only do the VCPUOP_register_vcpu_info once lets + * not over-write its result. + * + * For PV it is called during restore (xen_vcpu_restore) and bootup + * (xen_setup_vcpu_info_placement). The hotplug mechanism does not + * use this function. + */ + if (xen_hvm_domain()) { + if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu)) + return; + } if (cpu < MAX_VIRT_CPUS) per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; @@ -197,6 +213,9 @@ static void __init xen_banner(void) xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +#define CPUID_THERM_POWER_LEAF 6 +#define APERFMPERF_PRESENT 0 + static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; @@ -217,6 +236,11 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, maskedx = cpuid_leaf1_edx_mask; break; + case CPUID_THERM_POWER_LEAF: + /* Disabling APERFMPERF for kernel usage */ + maskecx = ~(1 << APERFMPERF_PRESENT); + break; + case 0xb: /* Suppress extended topology stuff */ maskebx = 0; @@ -794,7 +818,16 @@ static void xen_write_cr4(unsigned long cr4) native_write_cr4(cr4); } - +#ifdef CONFIG_X86_64 +static inline unsigned long xen_read_cr8(void) +{ + return 0; +} +static inline void xen_write_cr8(unsigned long val) +{ + BUG_ON(val); +} +#endif static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; @@ -959,6 +992,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_cr4_safe = native_read_cr4_safe, .write_cr4 = xen_write_cr4, +#ifdef CONFIG_X86_64 + .read_cr8 = xen_read_cr8, + .write_cr8 = xen_write_cr8, +#endif + .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, @@ -966,6 +1004,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, + .read_tscp = native_read_tscp, + .iret = xen_iret, .irq_enable_sysexit = xen_sysexit, #ifdef CONFIG_X86_64 @@ -1259,8 +1299,10 @@ asmlinkage void __init xen_start_kernel(void) /* Make sure ACS will be enabled */ pci_request_acs(); } - - +#ifdef CONFIG_PCI + /* PCI BIOS service won't work from a PV guest. */ + pci_probe &= ~PCI_PROBE_BIOS; +#endif xen_raw_console_write("about to get started...\n"); xen_setup_runstate_info(0); @@ -1338,8 +1380,11 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: xen_vcpu_setup(cpu); - if (xen_have_vector_callback) + if (xen_have_vector_callback) { xen_init_lock_cpu(cpu); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_timer(cpu); + } break; default: break; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5f76c0a..a0aed70 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -320,8 +320,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) { if (val & _PAGE_PRESENT) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + unsigned long pfn = mfn_to_pfn(mfn); + pteval_t flags = val & PTE_FLAGS_MASK; - val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; + if (unlikely(pfn == ~0)) + val = flags & ~_PAGE_PRESENT; + else + val = ((pteval_t)pfn << PAGE_SHIFT) | flags; } return val; @@ -2006,6 +2011,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .lazy_mode = { .enter = paravirt_enter_lazy_mmu, .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, }, .set_fixmap = xen_set_fixmap, diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58efeb9..2f7847d 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -683,6 +683,7 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; + int ret = 0; pfn = page_to_pfn(page); if (!PageHighMem(page)) { @@ -706,6 +707,24 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); spin_unlock_irqrestore(&m2p_override_lock, flags); + /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in + * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other + * pfn so that the following mfn_to_pfn(mfn) calls will return the + * pfn from the m2p_override (the backend pfn) instead. + * We need to do this because the pages shared by the frontend + * (xen-blkfront) can be already locked (lock_page, called by + * do_read_cache_page); when the userspace backend tries to use them + * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so + * do_blockdev_direct_IO is going to try to lock the same pages + * again resulting in a deadlock. + * As a side effect get_user_pages_fast might not be safe on the + * frontend pages while they are being shared with the backend, + * because mfn_to_pfn (that ends up being called by GUPF) will + * return the backend pfn rather than the frontend pfn. */ + ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); + if (ret == 0 && get_phys_to_machine(pfn) == mfn) + set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); + return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); @@ -717,6 +736,7 @@ int m2p_remove_override(struct page *page, bool clear_pte) unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; + int ret = 0; pfn = page_to_pfn(page); mfn = get_phys_to_machine(pfn); @@ -743,6 +763,22 @@ int m2p_remove_override(struct page *page, bool clear_pte) /* No tlb flush necessary because the caller already * left the pte unmapped. */ + /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present + * somewhere in this domain, even before being added to the + * m2p_override (see comment above in m2p_add_override). + * If there are no other entries in the m2p_override corresponding + * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for + * the original pfn (the one shared by the frontend): the backend + * cannot do any IO on this page anymore because it has been + * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of + * the original pfn causes mfn_to_pfn(mfn) to return the frontend + * pfn again. */ + mfn &= ~FOREIGN_FRAME_BIT; + ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); + if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && + m2p_find_override(mfn) == NULL) + set_phys_to_machine(pfn, mfn); + return 0; } EXPORT_SYMBOL_GPL(m2p_remove_override); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index f8dcda4..5669564 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -15,6 +15,7 @@ #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> @@ -463,4 +464,7 @@ void __init xen_arch_setup(void) boot_option_idle_override = IDLE_HALT; fiddle_vdso(); +#ifdef CONFIG_NUMA + numa_off = 1; +#endif } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index cc9b1e1..d99537f 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -313,7 +313,6 @@ static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl) if (per_cpu(lock_spinners, cpu) == xl) { ADD_STATS(released_slow_kicked, 1); xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); - break; } } } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 5158c50..19568a0 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -36,9 +36,8 @@ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); -/* unused ns of stolen and blocked time */ +/* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -static DEFINE_PER_CPU(u64, xen_residual_blocked); /* return an consistent snapshot of 64-bit time/counter value */ static u64 get64(const u64 *p) @@ -115,7 +114,7 @@ static void do_stolen_accounting(void) { struct vcpu_runstate_info state; struct vcpu_runstate_info *snap; - s64 blocked, runnable, offline, stolen; + s64 runnable, offline, stolen; cputime_t ticks; get_runstate_snapshot(&state); @@ -125,7 +124,6 @@ static void do_stolen_accounting(void) snap = &__get_cpu_var(xen_runstate_snapshot); /* work out how much time the VCPU has not been runn*ing* */ - blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked]; runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; @@ -141,17 +139,6 @@ static void do_stolen_accounting(void) ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __this_cpu_write(xen_residual_stolen, stolen); account_steal_ticks(ticks); - - /* Add the appropriate number of ticks of blocked time, - including any left-overs from last time. */ - blocked += __this_cpu_read(xen_residual_blocked); - - if (blocked < 0) - blocked = 0; - - ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); - __this_cpu_write(xen_residual_blocked, blocked); - account_idle_ticks(ticks); } /* Get the TSC speed from Xen */ @@ -482,7 +469,11 @@ static void xen_hvm_setup_cpu_clockevents(void) { int cpu = smp_processor_id(); xen_setup_runstate_info(cpu); - xen_setup_timer(cpu); + /* + * xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence + * doing it xen_hvm_cpu_notify (which gets called by smp_init during + * early bootup and also during CPU hotplug events). + */ xen_setup_cpu_clockevents(); } diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index b040b0e..7328f71 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -88,11 +88,11 @@ ENTRY(xen_iret) */ #ifdef CONFIG_SMP GET_THREAD_INFO(%eax) - movl TI_cpu(%eax), %eax - movl __per_cpu_offset(,%eax,4), %eax - mov xen_vcpu(%eax), %eax + movl %ss:TI_cpu(%eax), %eax + movl %ss:__per_cpu_offset(,%eax,4), %eax + mov %ss:xen_vcpu(%eax), %eax #else - movl xen_vcpu, %eax + movl %ss:xen_vcpu, %eax #endif /* check IF state we're restoring */ @@ -105,11 +105,11 @@ ENTRY(xen_iret) * resuming the code, so we don't have to be worried about * being preempted to another CPU. */ - setz XEN_vcpu_info_mask(%eax) + setz %ss:XEN_vcpu_info_mask(%eax) xen_iret_start_crit: /* check for unmasked and pending */ - cmpw $0x0001, XEN_vcpu_info_pending(%eax) + cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax) /* * If there's something pending, mask events again so we can @@ -117,7 +117,7 @@ xen_iret_start_crit: * touch XEN_vcpu_info_mask. */ jne 1f - movb $1, XEN_vcpu_info_mask(%eax) + movb $1, %ss:XEN_vcpu_info_mask(%eax) 1: popl %eax diff --git a/arch/xtensa/include/asm/signal.h b/arch/xtensa/include/asm/signal.h index 633ba73..75edf8a 100644 --- a/arch/xtensa/include/asm/signal.h +++ b/arch/xtensa/include/asm/signal.h @@ -133,6 +133,7 @@ struct sigaction { void (*sa_restorer)(void); sigset_t sa_mask; /* mask last for extensibility */ }; +#define __ARCH_HAS_SA_RESTORER struct k_sigaction { struct sigaction sa; |