diff options
281 files changed, 3891 insertions, 2398 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-dock b/Documentation/ABI/testing/sysfs-devices-platform-dock new file mode 100644 index 000000000000..1d8c18f905c7 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-platform-dock @@ -0,0 +1,39 @@ +What: /sys/devices/platform/dock.N/docked +Date: Dec, 2006 +KernelVersion: 2.6.19 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Value 1 or 0 indicates whether the software believes the + laptop is docked in a docking station. + +What: /sys/devices/platform/dock.N/undock +Date: Dec, 2006 +KernelVersion: 2.6.19 +Contact: linux-acpi@vger.kernel.org +Description: + (WO) Writing to this file causes the software to initiate an + undock request to the firmware. + +What: /sys/devices/platform/dock.N/uid +Date: Feb, 2007 +KernelVersion: v2.6.21 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Displays the docking station the laptop is docked to. + +What: /sys/devices/platform/dock.N/flags +Date: May, 2007 +KernelVersion: v2.6.21 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Show dock station flags, useful for checking if undock + request has been made by the user (from the immediate_undock + option). + +What: /sys/devices/platform/dock.N/type +Date: Aug, 2008 +KernelVersion: v2.6.27 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Display the dock station type- dock_station, ata_bay or + battery_bay. diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index bfd29bc8d37a..4ed63b6cfb15 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -108,6 +108,8 @@ Description: CPU topology files that describe a logical CPU's relationship What: /sys/devices/system/cpu/cpuidle/current_driver /sys/devices/system/cpu/cpuidle/current_governer_ro + /sys/devices/system/cpu/cpuidle/available_governors + /sys/devices/system/cpu/cpuidle/current_governor Date: September 2007 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Discover cpuidle policy and mechanism @@ -119,13 +121,84 @@ Description: Discover cpuidle policy and mechanism Idle policy (governor) is differentiated from idle mechanism (driver) - current_driver: displays current idle mechanism + current_driver: (RO) displays current idle mechanism - current_governor_ro: displays current idle policy + current_governor_ro: (RO) displays current idle policy + + With the cpuidle_sysfs_switch boot option enabled (meant for + developer testing), the following three attributes are visible + instead: + + current_driver: same as described above + + available_governors: (RO) displays a space separated list of + available governors + + current_governor: (RW) displays current idle policy. Users can + switch the governor at runtime by writing to this file. See files in Documentation/cpuidle/ for more information. +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/name + /sys/devices/system/cpu/cpuX/cpuidle/stateN/latency + /sys/devices/system/cpu/cpuX/cpuidle/stateN/power + /sys/devices/system/cpu/cpuX/cpuidle/stateN/time + /sys/devices/system/cpu/cpuX/cpuidle/stateN/usage +Date: September 2007 +KernelVersion: v2.6.24 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + The directory /sys/devices/system/cpu/cpuX/cpuidle contains per + logical CPU specific cpuidle information for each online cpu X. + The processor idle states which are available for use have the + following attributes: + + name: (RO) Name of the idle state (string). + + latency: (RO) The latency to exit out of this idle state (in + microseconds). + + power: (RO) The power consumed while in this idle state (in + milliwatts). + + time: (RO) The total time spent in this idle state (in microseconds). + + usage: (RO) Number of times this state was entered (a count). + + +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc +Date: February 2008 +KernelVersion: v2.6.25 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + (RO) A small description about the idle state (string). + + +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/disable +Date: March 2012 +KernelVersion: v3.10 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + (RW) Option to disable this idle state (bool). The behavior and + the effect of the disable variable depends on the implementation + of a particular governor. In the ladder governor, for example, + it is not coherent, i.e. if one is disabling a light state, then + all deeper states are disabled as well, but the disable variable + does not reflect it. Likewise, if one enables a deep state but a + lighter state still is disabled, then this has no effect. + + +What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/residency +Date: March 2014 +KernelVersion: v3.15 +Contact: Linux power management list <linux-pm@vger.kernel.org> +Description: + (RO) Display the target residency i.e. the minimum amount of + time (in microseconds) this cpu should spend in this idle state + to make the transition worth the effort. + + What: /sys/devices/system/cpu/cpu#/cpufreq/* Date: pre-git history Contact: linux-pm@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-platform-dptf b/Documentation/ABI/testing/sysfs-platform-dptf new file mode 100644 index 000000000000..325dc0667dbb --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-dptf @@ -0,0 +1,40 @@ +What: /sys/bus/platform/devices/INT3407:00/dptf_power/charger_type +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) The charger type - Traditional, Hybrid or NVDC. + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/adapter_rating_mw +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Adapter rating in milliwatts (the maximum Adapter power). + Must be 0 if no AC Adaptor is plugged in. + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/max_platform_power_mw +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Maximum platform power that can be supported by the battery + in milliwatts. + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/platform_power_source +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) Display the platform power source + 0x00 = DC + 0x01 = AC + 0x02 = USB + 0x03 = Wireless Charger + +What: /sys/bus/platform/devices/INT3407:00/dptf_power/battery_steady_power +Date: Jul, 2016 +KernelVersion: v4.10 +Contact: linux-acpi@vger.kernel.org +Description: + (RO) The maximum sustained power for battery in milliwatts. diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt index 5550bfdcce5f..be70b32c95d9 100644 --- a/Documentation/atomic_bitops.txt +++ b/Documentation/atomic_bitops.txt @@ -58,7 +58,12 @@ Like with atomic_t, the rule of thumb is: - RMW operations that have a return value are fully ordered. -Except for test_and_set_bit_lock() which has ACQUIRE semantics and + - RMW operations that are conditional are unordered on FAILURE, + otherwise the above rules apply. In the case of test_and_{}_bit() operations, + if the bit in memory is unchanged by the operation then it is deemed to have + failed. + +Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and clear_bit_unlock() which has RELEASE semantics. Since a platform only has a single means of achieving atomic operations diff --git a/Documentation/devicetree/bindings/power/mti,mips-cpc.txt b/Documentation/devicetree/bindings/power/mti,mips-cpc.txt new file mode 100644 index 000000000000..c6b82511ae8a --- /dev/null +++ b/Documentation/devicetree/bindings/power/mti,mips-cpc.txt @@ -0,0 +1,8 @@ +Binding for MIPS Cluster Power Controller (CPC). + +This binding allows a system to specify where the CPC registers are +located. + +Required properties: +compatible : Should be "mti,mips-cpc". +regs: Should describe the address & size of the CPC register region. diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt new file mode 100644 index 000000000000..2c815a7f1ba7 --- /dev/null +++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt @@ -0,0 +1,62 @@ +# +# Feature name: membarrier-sync-core +# Kconfig: ARCH_HAS_MEMBARRIER_SYNC_CORE +# description: arch supports core serializing membarrier +# +# Architecture requirements +# +# * arm64 +# +# Rely on eret context synchronization when returning from IPI handler, and +# when returning to user-space. +# +# * x86 +# +# x86-32 uses IRET as return from interrupt, which takes care of the IPI. +# However, it uses both IRET and SYSEXIT to go back to user-space. The IRET +# instruction is core serializing, but not SYSEXIT. +# +# x86-64 uses IRET as return from interrupt, which takes care of the IPI. +# However, it can return to user-space through either SYSRETL (compat code), +# SYSRETQ, or IRET. +# +# Given that neither SYSRET{L,Q}, nor SYSEXIT, are core serializing, we rely +# instead on write_cr3() performed by switch_mm() to provide core serialization +# after changing the current mm, and deal with the special case of kthread -> +# uthread (temporarily keeping current mm into active_mm) by issuing a +# sync_core_before_usermode() in that specific case. +# + ----------------------- + | arch |status| + ----------------------- + | alpha: | TODO | + | arc: | TODO | + | arm: | TODO | + | arm64: | ok | + | blackfin: | TODO | + | c6x: | TODO | + | cris: | TODO | + | frv: | TODO | + | h8300: | TODO | + | hexagon: | TODO | + | ia64: | TODO | + | m32r: | TODO | + | m68k: | TODO | + | metag: | TODO | + | microblaze: | TODO | + | mips: | TODO | + | mn10300: | TODO | + | nios2: | TODO | + | openrisc: | TODO | + | parisc: | TODO | + | powerpc: | TODO | + | s390: | TODO | + | score: | TODO | + | sh: | TODO | + | sparc: | TODO | + | tile: | TODO | + | um: | TODO | + | unicore32: | TODO | + | x86: | ok | + | xtensa: | TODO | + ----------------------- diff --git a/Documentation/locking/mutex-design.txt b/Documentation/locking/mutex-design.txt index 60c482df1a38..818aca19612f 100644 --- a/Documentation/locking/mutex-design.txt +++ b/Documentation/locking/mutex-design.txt @@ -21,37 +21,23 @@ Implementation -------------- Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h -and implemented in kernel/locking/mutex.c. These locks use a three -state atomic counter (->count) to represent the different possible -transitions that can occur during the lifetime of a lock: - - 1: unlocked - 0: locked, no waiters - negative: locked, with potential waiters - -In its most basic form it also includes a wait-queue and a spinlock -that serializes access to it. CONFIG_SMP systems can also include -a pointer to the lock task owner (->owner) as well as a spinner MCS -lock (->osq), both described below in (ii). +and implemented in kernel/locking/mutex.c. These locks use an atomic variable +(->owner) to keep track of the lock state during its lifetime. Field owner +actually contains 'struct task_struct *' to the current lock owner and it is +therefore NULL if not currently owned. Since task_struct pointers are aligned +at at least L1_CACHE_BYTES, low bits (3) are used to store extra state (e.g., +if waiter list is non-empty). In its most basic form it also includes a +wait-queue and a spinlock that serializes access to it. Furthermore, +CONFIG_MUTEX_SPIN_ON_OWNER=y systems use a spinner MCS lock (->osq), described +below in (ii). When acquiring a mutex, there are three possible paths that can be taken, depending on the state of the lock: -(i) fastpath: tries to atomically acquire the lock by decrementing the - counter. If it was already taken by another task it goes to the next - possible path. This logic is architecture specific. On x86-64, the - locking fastpath is 2 instructions: - - 0000000000000e10 <mutex_lock>: - e21: f0 ff 0b lock decl (%rbx) - e24: 79 08 jns e2e <mutex_lock+0x1e> - - the unlocking fastpath is equally tight: - - 0000000000000bc0 <mutex_unlock>: - bc8: f0 ff 07 lock incl (%rdi) - bcb: 7f 0a jg bd7 <mutex_unlock+0x17> - +(i) fastpath: tries to atomically acquire the lock by cmpxchg()ing the owner with + the current task. This only works in the uncontended case (cmpxchg() checks + against 0UL, so all 3 state bits above have to be 0). If the lock is + contended it goes to the next possible path. (ii) midpath: aka optimistic spinning, tries to spin for acquisition while the lock owner is running and there are no other tasks ready @@ -143,11 +129,10 @@ Test if the mutex is taken: Disadvantages ------------- -Unlike its original design and purpose, 'struct mutex' is larger than -most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice -as large as 'struct semaphore' (24 bytes) and tied, along with rwsems, -for the largest lock in the kernel. Larger structure sizes mean more -CPU cache and memory footprint. +Unlike its original design and purpose, 'struct mutex' is among the largest +locks in the kernel. E.g: on x86-64 it is 32 bytes, where 'struct semaphore' +is 24 bytes and rw_semaphore is 40 bytes. Larger structure sizes mean more CPU +cache and memory footprint. When to use mutexes ------------------- diff --git a/MAINTAINERS b/MAINTAINERS index fc3427d11d75..ce3519e1c18c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9205,6 +9205,7 @@ MIPS GENERIC PLATFORM M: Paul Burton <paul.burton@mips.com> L: linux-mips@linux-mips.org S: Supported +F: Documentation/devicetree/bindings/power/mti,mips-cpc.txt F: arch/mips/generic/ F: arch/mips/tools/generic-board-config.sh @@ -9944,6 +9945,7 @@ F: drivers/nfc/nxp-nci OBJTOOL M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Peter Zijlstra <peterz@infradead.org> S: Supported F: tools/objtool/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index be7bd19c87ec..eda8c5f629fc 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -20,7 +20,7 @@ #define MPIDR_UP_BITMASK (0x1 << 30) #define MPIDR_MT_BITMASK (0x1 << 24) -#define MPIDR_HWID_BITMASK 0xff00ffffff +#define MPIDR_HWID_BITMASK 0xff00ffffffUL #define MPIDR_LEVEL_BITS_SHIFT 3 #define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1dca41bea16a..e73f68569624 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -22,7 +22,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) { - return *ptep; + return READ_ONCE(*ptep); } diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 9679067a1574..7faed6e48b46 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -185,42 +185,42 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) return pmd; } -static inline void kvm_set_s2pte_readonly(pte_t *pte) +static inline void kvm_set_s2pte_readonly(pte_t *ptep) { pteval_t old_pteval, pteval; - pteval = READ_ONCE(pte_val(*pte)); + pteval = READ_ONCE(pte_val(*ptep)); do { old_pteval = pteval; pteval &= ~PTE_S2_RDWR; pteval |= PTE_S2_RDONLY; - pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval); + pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); } -static inline bool kvm_s2pte_readonly(pte_t *pte) +static inline bool kvm_s2pte_readonly(pte_t *ptep) { - return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY; + return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY; } -static inline bool kvm_s2pte_exec(pte_t *pte) +static inline bool kvm_s2pte_exec(pte_t *ptep) { - return !(pte_val(*pte) & PTE_S2_XN); + return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN); } -static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) +static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp) { - kvm_set_s2pte_readonly((pte_t *)pmd); + kvm_set_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_readonly(pmd_t *pmd) +static inline bool kvm_s2pmd_readonly(pmd_t *pmdp) { - return kvm_s2pte_readonly((pte_t *)pmd); + return kvm_s2pte_readonly((pte_t *)pmdp); } -static inline bool kvm_s2pmd_exec(pmd_t *pmd) +static inline bool kvm_s2pmd_exec(pmd_t *pmdp) { - return !(pmd_val(*pmd) & PMD_S2_XN); + return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN); } static inline bool kvm_page_empty(void *ptr) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 8d3331985d2e..39ec0b8a689e 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -141,13 +141,13 @@ static inline void cpu_install_idmap(void) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void cpu_replace_ttbr1(pgd_t *pgd) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; ttbr_replace_func *replace_phys; - phys_addr_t pgd_phys = virt_to_phys(pgd); + phys_addr_t pgd_phys = virt_to_phys(pgdp); replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index e9d9f1b006ef..2e05bcd944c8 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -36,23 +36,23 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) return (pmd_t *)__get_free_page(PGALLOC_GFP); } -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp) { - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); + BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1)); + free_page((unsigned long)pmdp); } -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { - set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot)); + set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot)); } -static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp) { - __pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE); + __pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE); } #else -static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot) +static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { BUILD_BUG(); } @@ -65,30 +65,30 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) return (pud_t *)__get_free_page(PGALLOC_GFP); } -static inline void pud_free(struct mm_struct *mm, pud_t *pud) +static inline void pud_free(struct mm_struct *mm, pud_t *pudp) { - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + BUG_ON((unsigned long)pudp & (PAGE_SIZE-1)); + free_page((unsigned long)pudp); } -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { - set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot)); + set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot)); } -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp) { - __pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE); + __pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE); } #else -static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot) +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ extern pgd_t *pgd_alloc(struct mm_struct *mm); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr) @@ -114,10 +114,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) /* * Free a PTE table. */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) { - if (pte) - free_page((unsigned long)pte); + if (ptep) + free_page((unsigned long)ptep); } static inline void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -126,10 +126,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) __free_page(pte); } -static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, +static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { - set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot)); + set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot)); } /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 094374c82db0..7e2c27e63cd8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -218,7 +218,7 @@ static inline pmd_t pmd_mkcont(pmd_t pmd) static inline void set_pte(pte_t *ptep, pte_t pte) { - *ptep = pte; + WRITE_ONCE(*ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance @@ -250,6 +250,8 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { + pte_t old_pte; + if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); @@ -258,14 +260,15 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) && + old_pte = READ_ONCE(*ptep); + if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) && (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) { VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + __func__, pte_val(old_pte), pte_val(pte)); + VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", - __func__, pte_val(*ptep), pte_val(pte)); + __func__, pte_val(old_pte), pte_val(pte)); } set_pte(ptep, pte); @@ -431,7 +434,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); dsb(ishst); isb(); } @@ -482,7 +485,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) static inline void set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); dsb(ishst); isb(); } @@ -500,7 +503,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) /* Find an entry in the second-level page table. */ #define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) -#define pmd_offset_phys(dir, addr) (pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t)) +#define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_offset(dir, addr) ((pmd_t *)__va(pmd_offset_phys((dir), (addr)))) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) @@ -535,7 +538,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pgd; + WRITE_ONCE(*pgdp, pgd); dsb(ishst); } @@ -552,7 +555,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd) /* Find an entry in the frst-level page table. */ #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) -#define pud_offset_phys(dir, addr) (pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t)) +#define pud_offset_phys(dir, addr) (pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) #define pud_offset(dir, addr) ((pud_t *)__va(pud_offset_phys((dir), (addr)))) #define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 07823595b7f0..52f15cd896e1 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -408,6 +408,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + .enable = qcom_enable_link_stack_sanitization, + }, + { + .capability = ARM64_HARDEN_BP_POST_GUEST_EXIT, + MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + }, + { + .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), .enable = enable_smccc_arch_workaround_1, }, diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index f85ac58d08a3..a8bf1c892b90 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -90,7 +90,7 @@ static int __init set_permissions(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { efi_memory_desc_t *md = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); if (md->attribute & EFI_MEMORY_RO) pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f20cf7e99249..1ec5f28c39fc 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -202,10 +202,10 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; unsigned long dst = (unsigned long)allocator(mask); if (!dst) { @@ -216,38 +216,38 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); flush_icache_range(dst, dst + length); - pgd = pgd_offset_raw(allocator(mask), dst_addr); - if (pgd_none(*pgd)) { - pud = allocator(mask); - if (!pud) { + pgdp = pgd_offset_raw(allocator(mask), dst_addr); + if (pgd_none(READ_ONCE(*pgdp))) { + pudp = allocator(mask); + if (!pudp) { rc = -ENOMEM; goto out; } - pgd_populate(&init_mm, pgd, pud); + pgd_populate(&init_mm, pgdp, pudp); } - pud = pud_offset(pgd, dst_addr); - if (pud_none(*pud)) { - pmd = allocator(mask); - if (!pmd) { + pudp = pud_offset(pgdp, dst_addr); + if (pud_none(READ_ONCE(*pudp))) { + pmdp = allocator(mask); + if (!pmdp) { rc = -ENOMEM; goto out; } - pud_populate(&init_mm, pud, pmd); + pud_populate(&init_mm, pudp, pmdp); } - pmd = pmd_offset(pud, dst_addr); - if (pmd_none(*pmd)) { - pte = allocator(mask); - if (!pte) { + pmdp = pmd_offset(pudp, dst_addr); + if (pmd_none(READ_ONCE(*pmdp))) { + ptep = allocator(mask); + if (!ptep) { rc = -ENOMEM; goto out; } - pmd_populate_kernel(&init_mm, pmd, pte); + pmd_populate_kernel(&init_mm, pmdp, ptep); } - pte = pte_offset_kernel(pmd, dst_addr); - set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); + ptep = pte_offset_kernel(pmdp, dst_addr); + set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); /* * Load our new page tables. A strict BBM approach requires that we @@ -263,7 +263,7 @@ static int create_safe_exec_page(void *src_start, size_t length, */ cpu_set_reserved_ttbr0(); local_flush_tlb_all(); - write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1); + write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1); isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -320,9 +320,9 @@ int swsusp_arch_suspend(void) return ret; } -static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) +static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) { - pte_t pte = *src_pte; + pte_t pte = READ_ONCE(*src_ptep); if (pte_valid(pte)) { /* @@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) * read only (code, rodata). Clear the RDONLY bit from * the temporary mappings we use during restore. */ - set_pte(dst_pte, pte_mkwrite(pte)); + set_pte(dst_ptep, pte_mkwrite(pte)); } else if (debug_pagealloc_enabled() && !pte_none(pte)) { /* * debug_pagealloc will removed the PTE_VALID bit if @@ -343,112 +343,116 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr) */ BUG_ON(!pfn_valid(pte_pfn(pte))); - set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte))); + set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte))); } } -static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start, +static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, unsigned long end) { - pte_t *src_pte; - pte_t *dst_pte; + pte_t *src_ptep; + pte_t *dst_ptep; unsigned long addr = start; - dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pte) + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) return -ENOMEM; - pmd_populate_kernel(&init_mm, dst_pmd, dst_pte); - dst_pte = pte_offset_kernel(dst_pmd, start); + pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep); + dst_ptep = pte_offset_kernel(dst_pmdp, start); - src_pte = pte_offset_kernel(src_pmd, start); + src_ptep = pte_offset_kernel(src_pmdp, start); do { - _copy_pte(dst_pte, src_pte, addr); - } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + _copy_pte(dst_ptep, src_ptep, addr); + } while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end); return 0; } -static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start, +static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, unsigned long end) { - pmd_t *src_pmd; - pmd_t *dst_pmd; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; unsigned long next; unsigned long addr = start; - if (pud_none(*dst_pud)) { - dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pmd) + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) return -ENOMEM; - pud_populate(&init_mm, dst_pud, dst_pmd); + pud_populate(&init_mm, dst_pudp, dst_pmdp); } - dst_pmd = pmd_offset(dst_pud, start); + dst_pmdp = pmd_offset(dst_pudp, start); - src_pmd = pmd_offset(src_pud, start); + src_pmdp = pmd_offset(src_pudp, start); do { + pmd_t pmd = READ_ONCE(*src_pmdp); + next = pmd_addr_end(addr, end); - if (pmd_none(*src_pmd)) + if (pmd_none(pmd)) continue; - if (pmd_table(*src_pmd)) { - if (copy_pte(dst_pmd, src_pmd, addr, next)) + if (pmd_table(pmd)) { + if (copy_pte(dst_pmdp, src_pmdp, addr, next)) return -ENOMEM; } else { - set_pmd(dst_pmd, - __pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY)); + set_pmd(dst_pmdp, + __pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY)); } - } while (dst_pmd++, src_pmd++, addr = next, addr != end); + } while (dst_pmdp++, src_pmdp++, addr = next, addr != end); return 0; } -static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start, +static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, unsigned long end) { - pud_t *dst_pud; - pud_t *src_pud; + pud_t *dst_pudp; + pud_t *src_pudp; unsigned long next; unsigned long addr = start; - if (pgd_none(*dst_pgd)) { - dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC); - if (!dst_pud) + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) return -ENOMEM; - pgd_populate(&init_mm, dst_pgd, dst_pud); + pgd_populate(&init_mm, dst_pgdp, dst_pudp); } - dst_pud = pud_offset(dst_pgd, start); + dst_pudp = pud_offset(dst_pgdp, start); - src_pud = pud_offset(src_pgd, start); + src_pudp = pud_offset(src_pgdp, start); do { + pud_t pud = READ_ONCE(*src_pudp); + next = pud_addr_end(addr, end); - if (pud_none(*src_pud)) + if (pud_none(pud)) continue; - if (pud_table(*(src_pud))) { - if (copy_pmd(dst_pud, src_pud, addr, next)) + if (pud_table(pud)) { + if (copy_pmd(dst_pudp, src_pudp, addr, next)) return -ENOMEM; } else { - set_pud(dst_pud, - __pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY)); + set_pud(dst_pudp, + __pud(pud_val(pud) & ~PMD_SECT_RDONLY)); } - } while (dst_pud++, src_pud++, addr = next, addr != end); + } while (dst_pudp++, src_pudp++, addr = next, addr != end); return 0; } -static int copy_page_tables(pgd_t *dst_pgd, unsigned long start, +static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, unsigned long end) { unsigned long next; unsigned long addr = start; - pgd_t *src_pgd = pgd_offset_k(start); + pgd_t *src_pgdp = pgd_offset_k(start); - dst_pgd = pgd_offset_raw(dst_pgd, start); + dst_pgdp = pgd_offset_raw(dst_pgdp, start); do { next = pgd_addr_end(addr, end); - if (pgd_none(*src_pgd)) + if (pgd_none(READ_ONCE(*src_pgdp))) continue; - if (copy_pud(dst_pgd, src_pgd, addr, next)) + if (copy_pud(dst_pgdp, src_pgdp, addr, next)) return -ENOMEM; - } while (dst_pgd++, src_pgd++, addr = next, addr != end); + } while (dst_pgdp++, src_pgdp++, addr = next, addr != end); return 0; } diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 116252a8d3a5..870f4b1587f9 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -407,8 +407,10 @@ again: u32 midr = read_cpuid_id(); /* Apply BTAC predictors mitigation to all Falkor chips */ - if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1) + if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) || + ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) { __qcom_hyp_sanitize_btac_predictors(); + } } fp_enabled = __fpsimd_enabled(); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 7b60d62ac593..65dfc8571bf8 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,48 +286,52 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) { - pte_t *pte = pte_offset_kernel(pmd, 0UL); + pte_t *ptep = pte_offset_kernel(pmdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { addr = start + i * PAGE_SIZE; - note_page(st, addr, 4, pte_val(*pte)); + note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); } } -static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) { - pmd_t *pmd = pmd_offset(pud, 0UL); + pmd_t *pmdp = pmd_offset(pudp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + pmd_t pmd = READ_ONCE(*pmdp); + addr = start + i * PMD_SIZE; - if (pmd_none(*pmd) || pmd_sect(*pmd)) { - note_page(st, addr, 3, pmd_val(*pmd)); + if (pmd_none(pmd) || pmd_sect(pmd)) { + note_page(st, addr, 3, pmd_val(pmd)); } else { - BUG_ON(pmd_bad(*pmd)); - walk_pte(st, pmd, addr); + BUG_ON(pmd_bad(pmd)); + walk_pte(st, pmdp, addr); } } } -static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) { - pud_t *pud = pud_offset(pgd, 0UL); + pud_t *pudp = pud_offset(pgdp, 0UL); unsigned long addr; unsigned i; - for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + pud_t pud = READ_ONCE(*pudp); + addr = start + i * PUD_SIZE; - if (pud_none(*pud) || pud_sect(*pud)) { - note_page(st, addr, 2, pud_val(*pud)); + if (pud_none(pud) || pud_sect(pud)) { + note_page(st, addr, 2, pud_val(pud)); } else { - BUG_ON(pud_bad(*pud)); - walk_pmd(st, pud, addr); + BUG_ON(pud_bad(pud)); + walk_pmd(st, pudp, addr); } } } @@ -335,17 +339,19 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgd = pgd_offset(mm, 0UL); + pgd_t *pgdp = pgd_offset(mm, 0UL); unsigned i; unsigned long addr; - for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { + for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + pgd_t pgd = READ_ONCE(*pgdp); + addr = start + i * PGDIR_SIZE; - if (pgd_none(*pgd)) { - note_page(st, addr, 1, pgd_val(*pgd)); + if (pgd_none(pgd)) { + note_page(st, addr, 1, pgd_val(pgd)); } else { - BUG_ON(pgd_bad(*pgd)); - walk_pud(st, pgd, addr); + BUG_ON(pgd_bad(pgd)); + walk_pud(st, pgdp, addr); } } } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index f76bb2c3c943..bff11553eb05 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -130,7 +130,8 @@ static void mem_abort_decode(unsigned int esr) void show_pte(unsigned long addr) { struct mm_struct *mm; - pgd_t *pgd; + pgd_t *pgdp; + pgd_t pgd; if (addr < TASK_SIZE) { /* TTBR0 */ @@ -149,33 +150,37 @@ void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n", + pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, VA_BITS, mm->pgd); - pgd = pgd_offset(mm, addr); - pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd)); + pgdp = pgd_offset(mm, addr); + pgd = READ_ONCE(*pgdp); + pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; - if (pgd_none(*pgd) || pgd_bad(*pgd)) + if (pgd_none(pgd) || pgd_bad(pgd)) break; - pud = pud_offset(pgd, addr); - pr_cont(", *pud=%016llx", pud_val(*pud)); - if (pud_none(*pud) || pud_bad(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + pr_cont(", pud=%016llx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud)) break; - pmd = pmd_offset(pud, addr); - pr_cont(", *pmd=%016llx", pmd_val(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + pr_cont(", pmd=%016llx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd)) break; - pte = pte_offset_map(pmd, addr); - pr_cont(", *pte=%016llx", pte_val(*pte)); - pte_unmap(pte); + ptep = pte_offset_map(pmdp, addr); + pte = READ_ONCE(*ptep); + pr_cont(", pte=%016llx", pte_val(pte)); + pte_unmap(ptep); } while(0); pr_cont("\n"); @@ -196,8 +201,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, pte_t entry, int dirty) { pteval_t old_pteval, pteval; + pte_t pte = READ_ONCE(*ptep); - if (pte_same(*ptep, entry)) + if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ @@ -210,7 +216,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; - pteval = READ_ONCE(pte_val(*ptep)); + pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 6cb0fa92a651..ecc6818191df 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -54,14 +54,14 @@ static inline pgprot_t pte_pgprot(pte_t pte) static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp = pgd_offset(mm, addr); + pud_t *pudp; + pmd_t *pmdp; *pgsize = PAGE_SIZE; - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - if ((pte_t *)pmd == ptep) { + pudp = pud_offset(pgdp, addr); + pmdp = pmd_offset(pudp, addr); + if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } @@ -181,11 +181,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, clear_flush(mm, addr, ptep, pgsize, ncontig); - for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) { - pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, - pte_val(pfn_pte(pfn, hugeprot))); + for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); - } } void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, @@ -203,20 +200,20 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (!pud) + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep = NULL; + + pgdp = pgd_offset(mm, addr); + pudp = pud_alloc(mm, pgdp, addr); + if (!pudp) return NULL; if (sz == PUD_SIZE) { - pte = (pte_t *)pud; + ptep = (pte_t *)pudp; } else if (sz == (PAGE_SIZE * CONT_PTES)) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); /* @@ -226,60 +223,55 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, * will be no pte_unmap() to correspond with this * pte_alloc_map(). */ - pte = pte_alloc_map(mm, pmd, addr); + ptep = pte_alloc_map(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && - pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); + pud_none(READ_ONCE(*pudp))) + ptep = huge_pmd_share(mm, addr, pudp); else - pte = (pte_t *)pmd_alloc(mm, pud, addr); + ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (PMD_SIZE * CONT_PMDS)) { - pmd_t *pmd; - - pmd = pmd_alloc(mm, pud, addr); + pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); - return (pte_t *)pmd; + return (pte_t *)pmdp; } - pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, - sz, pte, pte_val(*pte)); - return pte; + return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; - pgd = pgd_offset(mm, addr); - pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); - if (!pgd_present(*pgd)) + pgdp = pgd_offset(mm, addr); + if (!pgd_present(READ_ONCE(*pgdp))) return NULL; - pud = pud_offset(pgd, addr); - if (sz != PUD_SIZE && pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ - if (pud_huge(*pud) || !pud_present(*pud)) - return (pte_t *)pud; + if (pud_huge(pud) || !pud_present(pud)) + return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; - pmd = pmd_offset(pud, addr); + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && - pmd_none(*pmd)) + pmd_none(pmd)) return NULL; - if (pmd_huge(*pmd) || !pmd_present(*pmd)) - return (pte_t *)pmd; + if (pmd_huge(pmd) || !pmd_present(pmd)) + return (pte_t *)pmdp; - if (sz == CONT_PTE_SIZE) { - pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK)); - return pte; - } + if (sz == CONT_PTE_SIZE) + return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK)); return NULL; } @@ -367,7 +359,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, size_t pgsize; pte_t pte; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_set_wrprotect(mm, addr, ptep); return; } @@ -391,7 +383,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, size_t pgsize; int ncontig; - if (!pte_cont(*ptep)) { + if (!pte_cont(READ_ONCE(*ptep))) { ptep_clear_flush(vma, addr, ptep); return; } diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6e02e6fb4c7b..dabfc1ecda3d 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -44,92 +44,92 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) return __pa(p); } -static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node, +static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (pmd_none(*pmd)) { + if (pmd_none(READ_ONCE(*pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) : kasan_alloc_zeroed_page(node); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); } - return early ? pte_offset_kimg(pmd, addr) - : pte_offset_kernel(pmd, addr); + return early ? pte_offset_kimg(pmdp, addr) + : pte_offset_kernel(pmdp, addr); } -static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node, +static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (pud_none(*pud)) { + if (pud_none(READ_ONCE(*pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) : kasan_alloc_zeroed_page(node); - __pud_populate(pud, pmd_phys, PMD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE); } - return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr); + return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr); } -static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node, +static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { - if (pgd_none(*pgd)) { + if (pgd_none(READ_ONCE(*pgdp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) : kasan_alloc_zeroed_page(node); - __pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE); } - return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr); + return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr); } -static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr, +static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pte_t *pte = kasan_pte_offset(pmd, addr, node, early); + pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early); do { phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) : kasan_alloc_zeroed_page(node); next = addr + PAGE_SIZE; - set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); - } while (pte++, addr = next, addr != end && pte_none(*pte)); + set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); + } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep))); } -static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr, +static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early); + pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early); do { next = pmd_addr_end(addr, end); - kasan_pte_populate(pmd, addr, next, node, early); - } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); + kasan_pte_populate(pmdp, addr, next, node, early); + } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp))); } -static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pud_t *pud = kasan_pud_offset(pgd, addr, node, early); + pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early); do { next = pud_addr_end(addr, end); - kasan_pmd_populate(pud, addr, next, node, early); - } while (pud++, addr = next, addr != end && pud_none(*pud)); + kasan_pmd_populate(pudp, addr, next, node, early); + } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - pgd_t *pgd; + pgd_t *pgdp; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - kasan_pud_populate(pgd, addr, next, node, early); - } while (pgd++, addr = next, addr != end); + kasan_pud_populate(pgdp, addr, next, node, early); + } while (pgdp++, addr = next, addr != end); } /* The early shadow maps everything to a single page of zeroes */ @@ -155,14 +155,14 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, */ void __init kasan_copy_shadow(pgd_t *pgdir) { - pgd_t *pgd, *pgd_new, *pgd_end; + pgd_t *pgdp, *pgdp_new, *pgdp_end; - pgd = pgd_offset_k(KASAN_SHADOW_START); - pgd_end = pgd_offset_k(KASAN_SHADOW_END); - pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); + pgdp = pgd_offset_k(KASAN_SHADOW_START); + pgdp_end = pgd_offset_k(KASAN_SHADOW_END); + pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START); do { - set_pgd(pgd_new, *pgd); - } while (pgd++, pgd_new++, pgd != pgd_end); + set_pgd(pgdp_new, READ_ONCE(*pgdp)); + } while (pgdp++, pgdp_new++, pgdp != pgdp_end); } static void __init clear_pgds(unsigned long start, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4694cda823c9..3161b853f29e 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -125,45 +125,48 @@ static bool pgattr_change_is_safe(u64 old, u64 new) return ((old ^ new) & ~mask) == 0; } -static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, +static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot) { - pte_t *pte; + pte_t *ptep; - pte = pte_set_fixmap_offset(pmd, addr); + ptep = pte_set_fixmap_offset(pmdp, addr); do { - pte_t old_pte = *pte; + pte_t old_pte = READ_ONCE(*ptep); - set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot)); + set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot)); /* * After the PTE entry has been populated once, we * only allow updates to the permission attributes. */ - BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte))); + BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), + READ_ONCE(pte_val(*ptep)))); phys += PAGE_SIZE; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (ptep++, addr += PAGE_SIZE, addr != end); pte_clear_fixmap(); } -static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, +static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pmd_t pmd = READ_ONCE(*pmdp); - BUG_ON(pmd_sect(*pmd)); - if (pmd_none(*pmd)) { + BUG_ON(pmd_sect(pmd)); + if (pmd_none(pmd)) { phys_addr_t pte_phys; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(); - __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); + __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); + pmd = READ_ONCE(*pmdp); } - BUG_ON(pmd_bad(*pmd)); + BUG_ON(pmd_bad(pmd)); do { pgprot_t __prot = prot; @@ -175,67 +178,69 @@ static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pte(pmd, addr, next, phys, __prot); + init_pte(pmdp, addr, next, phys, __prot); phys += next - addr; } while (addr = next, addr != end); } -static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end, +static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; - pmd_t *pmd; + pmd_t *pmdp; - pmd = pmd_set_fixmap_offset(pud, addr); + pmdp = pmd_set_fixmap_offset(pudp, addr); do { - pmd_t old_pmd = *pmd; + pmd_t old_pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && (flags & NO_BLOCK_MAPPINGS) == 0) { - pmd_set_huge(pmd, phys, prot); + pmd_set_huge(pmdp, phys, prot); /* * After the PMD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), - pmd_val(*pmd))); + READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmd, addr, next, phys, prot, + alloc_init_cont_pte(pmdp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pmd_val(old_pmd) != 0 && - pmd_val(old_pmd) != pmd_val(*pmd)); + pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; - } while (pmd++, addr = next, addr != end); + } while (pmdp++, addr = next, addr != end); pmd_clear_fixmap(); } -static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, +static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), int flags) { unsigned long next; + pud_t pud = READ_ONCE(*pudp); /* * Check for initial section mappings in the pgd/pud. */ - BUG_ON(pud_sect(*pud)); - if (pud_none(*pud)) { + BUG_ON(pud_sect(pud)); + if (pud_none(pud)) { phys_addr_t pmd_phys; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(); - __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); + __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE); + pud = READ_ONCE(*pudp); } - BUG_ON(pud_bad(*pud)); + BUG_ON(pud_bad(pud)); do { pgprot_t __prot = prot; @@ -247,7 +252,7 @@ static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags); + init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags); phys += next - addr; } while (addr = next, addr != end); @@ -265,25 +270,27 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, return true; } -static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void), - int flags) +static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(void), + int flags) { - pud_t *pud; unsigned long next; + pud_t *pudp; + pgd_t pgd = READ_ONCE(*pgdp); - if (pgd_none(*pgd)) { + if (pgd_none(pgd)) { phys_addr_t pud_phys; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(); - __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); + __pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE); + pgd = READ_ONCE(*pgdp); } - BUG_ON(pgd_bad(*pgd)); + BUG_ON(pgd_bad(pgd)); - pud = pud_set_fixmap_offset(pgd, addr); + pudp = pud_set_fixmap_offset(pgdp, addr); do { - pud_t old_pud = *pud; + pud_t old_pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); @@ -292,23 +299,23 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, */ if (use_1G_block(addr, next, phys) && (flags & NO_BLOCK_MAPPINGS) == 0) { - pud_set_huge(pud, phys, prot); + pud_set_huge(pudp, phys, prot); /* * After the PUD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), - pud_val(*pud))); + READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pud, addr, next, phys, prot, + alloc_init_cont_pmd(pudp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pud_val(old_pud) != 0 && - pud_val(old_pud) != pud_val(*pud)); + pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); } phys += next - addr; - } while (pud++, addr = next, addr != end); + } while (pudp++, addr = next, addr != end); pud_clear_fixmap(); } @@ -320,7 +327,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, int flags) { unsigned long addr, length, end, next; - pgd_t *pgd = pgd_offset_raw(pgdir, virt); + pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* * If the virtual and physical address don't have the same offset @@ -336,10 +343,10 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; - } while (pgd++, addr = next, addr != end); + } while (pgdp++, addr = next, addr != end); } static phys_addr_t pgd_pgtable_alloc(void) @@ -401,10 +408,10 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, flush_tlb_kernel_range(virt, virt + size); } -static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, +static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, + __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, prot, early_pgtable_alloc, flags); } @@ -418,7 +425,7 @@ void __init mark_linear_text_alias_ro(void) PAGE_KERNEL_RO); } -static void __init map_mem(pgd_t *pgd) +static void __init map_mem(pgd_t *pgdp) { phys_addr_t kernel_start = __pa_symbol(_text); phys_addr_t kernel_end = __pa_symbol(__init_begin); @@ -451,7 +458,7 @@ static void __init map_mem(pgd_t *pgd) if (memblock_is_nomap(reg)) continue; - __map_memblock(pgd, start, end, PAGE_KERNEL, flags); + __map_memblock(pgdp, start, end, PAGE_KERNEL, flags); } /* @@ -464,7 +471,7 @@ static void __init map_mem(pgd_t *pgd) * Note that contiguous mappings cannot be remapped in this way, * so we should avoid them here. */ - __map_memblock(pgd, kernel_start, kernel_end, + __map_memblock(pgdp, kernel_start, kernel_end, PAGE_KERNEL, NO_CONT_MAPPINGS); memblock_clear_nomap(kernel_start, kernel_end - kernel_start); @@ -475,7 +482,7 @@ static void __init map_mem(pgd_t *pgd) * through /sys/kernel/kexec_crash_size interface. */ if (crashk_res.end) { - __map_memblock(pgd, crashk_res.start, crashk_res.end + 1, + __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1, PAGE_KERNEL, NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS); memblock_clear_nomap(crashk_res.start, @@ -499,7 +506,7 @@ void mark_rodata_ro(void) debug_checkwx(); } -static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, +static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma, int flags, unsigned long vm_flags) { @@ -509,7 +516,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); - __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, + __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot, early_pgtable_alloc, flags); if (!(vm_flags & VM_NO_GUARD)) @@ -562,7 +569,7 @@ core_initcall(map_entry_trampoline); /* * Create fine-grained mappings for the kernel. */ -static void __init map_kernel(pgd_t *pgd) +static void __init map_kernel(pgd_t *pgdp) { static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext, vmlinux_initdata, vmlinux_data; @@ -578,24 +585,24 @@ static void __init map_kernel(pgd_t *pgd) * Only rodata will be remapped with different permissions later on, * all other segments are allowed to use contiguous mappings. */ - map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0, + map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL, + map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); - map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot, + map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot, &vmlinux_inittext, 0, VM_NO_GUARD); - map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL, + map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL, &vmlinux_initdata, 0, VM_NO_GUARD); - map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); + map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); - if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { + if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) { /* * The fixmap falls in a separate pgd to the kernel, and doesn't * live in the carveout for the swapper_pg_dir. We can simply * re-use the existing dir for the fixmap. */ - set_pgd(pgd_offset_raw(pgd, FIXADDR_START), - *pgd_offset_k(FIXADDR_START)); + set_pgd(pgd_offset_raw(pgdp, FIXADDR_START), + READ_ONCE(*pgd_offset_k(FIXADDR_START))); } else if (CONFIG_PGTABLE_LEVELS > 3) { /* * The fixmap shares its top level pgd entry with the kernel @@ -604,14 +611,15 @@ static void __init map_kernel(pgd_t *pgd) * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START), + pud_populate(&init_mm, + pud_set_fixmap_offset(pgdp, FIXADDR_START), lm_alias(bm_pmd)); pud_clear_fixmap(); } else { BUG(); } - kasan_copy_shadow(pgd); + kasan_copy_shadow(pgdp); } /* @@ -621,10 +629,10 @@ static void __init map_kernel(pgd_t *pgd) void __init paging_init(void) { phys_addr_t pgd_phys = early_pgtable_alloc(); - pgd_t *pgd = pgd_set_fixmap(pgd_phys); + pgd_t *pgdp = pgd_set_fixmap(pgd_phys); - map_kernel(pgd); - map_mem(pgd); + map_kernel(pgdp); + map_mem(pgdp); /* * We want to reuse the original swapper_pg_dir so we don't have to @@ -635,7 +643,7 @@ void __init paging_init(void) * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); - memcpy(swapper_pg_dir, pgd, PGD_SIZE); + memcpy(swapper_pg_dir, pgdp, PGD_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); pgd_clear_fixmap(); @@ -655,37 +663,40 @@ void __init paging_init(void) */ int kern_addr_valid(unsigned long addr) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; if ((((long)addr) >> VA_BITS) != -1UL) return 0; - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return 0; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return 0; - if (pud_sect(*pud)) - return pfn_valid(pud_pfn(*pud)); + if (pud_sect(pud)) + return pfn_valid(pud_pfn(pud)); - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return 0; - if (pmd_sect(*pmd)) - return pfn_valid(pmd_pfn(*pmd)); + if (pmd_sect(pmd)) + return pfn_valid(pmd_pfn(pmd)); - pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) + ptep = pte_offset_kernel(pmdp, addr); + pte = READ_ONCE(*ptep); + if (pte_none(pte)) return 0; - return pfn_valid(pte_pfn(*pte)); + return pfn_valid(pte_pfn(pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS @@ -700,32 +711,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { unsigned long addr = start; unsigned long next; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; do { next = pmd_addr_end(addr, end); - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) + pgdp = vmemmap_pgd_populate(addr, node); + if (!pgdp) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); - if (!pud) + pudp = vmemmap_pud_populate(pgdp, addr, node); + if (!pudp) return -ENOMEM; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { + pmdp = pmd_offset(pudp, addr); + if (pmd_none(READ_ONCE(*pmdp))) { void *p = NULL; p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (!p) return -ENOMEM; - pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL)); + pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); } else - vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_verify((pte_t *)pmdp, node, addr, next); } while (addr = next, addr != end); return 0; @@ -739,20 +750,22 @@ void vmemmap_free(unsigned long start, unsigned long end, static inline pud_t * fixmap_pud(unsigned long addr) { - pgd_t *pgd = pgd_offset_k(addr); + pgd_t *pgdp = pgd_offset_k(addr); + pgd_t pgd = READ_ONCE(*pgdp); - BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); + BUG_ON(pgd_none(pgd) || pgd_bad(pgd)); - return pud_offset_kimg(pgd, addr); + return pud_offset_kimg(pgdp, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) { - pud_t *pud = fixmap_pud(addr); + pud_t *pudp = fixmap_pud(addr); + pud_t pud = READ_ONCE(*pudp); - BUG_ON(pud_none(*pud) || pud_bad(*pud)); + BUG_ON(pud_none(pud) || pud_bad(pud)); - return pmd_offset_kimg(pud, addr); + return pmd_offset_kimg(pudp, addr); } static inline pte_t * fixmap_pte(unsigned long addr) @@ -768,30 +781,31 @@ static inline pte_t * fixmap_pte(unsigned long addr) */ void __init early_fixmap_init(void) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; + pgd_t *pgdp, pgd; + pud_t *pudp; + pmd_t *pmdp; unsigned long addr = FIXADDR_START; - pgd = pgd_offset_k(addr); + pgdp = pgd_offset_k(addr); + pgd = READ_ONCE(*pgdp); if (CONFIG_PGTABLE_LEVELS > 3 && - !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) { + !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud = pud_offset_kimg(pgd, addr); + pudp = pud_offset_kimg(pgdp, addr); } else { - if (pgd_none(*pgd)) - __pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE); - pud = fixmap_pud(addr); + if (pgd_none(pgd)) + __pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE); + pudp = fixmap_pud(addr); } - if (pud_none(*pud)) - __pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); - pmd = fixmap_pmd(addr); - __pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE); + if (pud_none(READ_ONCE(*pudp))) + __pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); + pmdp = fixmap_pmd(addr); + __pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE); /* * The boot-ioremap range spans multiple pmds, for which @@ -800,11 +814,11 @@ void __init early_fixmap_init(void) BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); - if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) - || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { + if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) + || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { WARN_ON(1); - pr_warn("pmd %p != %p, %p\n", - pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), + pr_warn("pmdp %p != %p, %p\n", + pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), fixmap_pmd(fix_to_virt(FIX_BTMAP_END))); pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", fix_to_virt(FIX_BTMAP_BEGIN)); @@ -824,16 +838,16 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); - pte_t *pte; + pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); - pte = fixmap_pte(addr); + ptep = fixmap_pte(addr); if (pgprot_val(flags)) { - set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); + set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { - pte_clear(&init_mm, addr, pte); + pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } @@ -915,36 +929,36 @@ int __init arch_ioremap_pmd_supported(void) return 1; } -int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); BUG_ON(phys & ~PUD_MASK); - set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot)); + set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot)); return 1; } -int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))); BUG_ON(phys & ~PMD_MASK); - set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot)); + set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot)); return 1; } -int pud_clear_huge(pud_t *pud) +int pud_clear_huge(pud_t *pudp) { - if (!pud_sect(*pud)) + if (!pud_sect(READ_ONCE(*pudp))) return 0; - pud_clear(pud); + pud_clear(pudp); return 1; } -int pmd_clear_huge(pmd_t *pmd) +int pmd_clear_huge(pmd_t *pmdp) { - if (!pmd_sect(*pmd)) + if (!pmd_sect(READ_ONCE(*pmdp))) return 0; - pmd_clear(pmd); + pmd_clear(pmdp); return 1; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a682a0a2a0fa..a56359373d8b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -29,7 +29,7 @@ static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct page_change_data *cdata = data; - pte_t pte = *ptep; + pte_t pte = READ_ONCE(*ptep); pte = clear_pte_bit(pte, cdata->clear_mask); pte = set_pte_bit(pte, cdata->set_mask); @@ -156,30 +156,32 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) */ bool kernel_page_present(struct page *page) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgdp; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) + pgdp = pgd_offset_k(addr); + if (pgd_none(READ_ONCE(*pgdp))) return false; - pud = pud_offset(pgd, addr); - if (pud_none(*pud)) + pudp = pud_offset(pgdp, addr); + pud = READ_ONCE(*pudp); + if (pud_none(pud)) return false; - if (pud_sect(*pud)) + if (pud_sect(pud)) return true; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + pmdp = pmd_offset(pudp, addr); + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return false; - if (pmd_sect(*pmd)) + if (pmd_sect(pmd)) return true; - pte = pte_offset_kernel(pmd, addr); - return pte_valid(*pte); + ptep = pte_offset_kernel(pmdp, addr); + return pte_valid(READ_ONCE(*ptep)); } #endif /* CONFIG_HIBERNATION */ #endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 71baed7e592a..c0af47617299 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -205,7 +205,8 @@ ENDPROC(idmap_cpu_replace_ttbr1) dc cvac, cur_\()\type\()p // Ensure any existing dirty dmb sy // lines are written back before ldr \type, [cur_\()\type\()p] // loading the entry - tbz \type, #0, next_\()\type // Skip invalid entries + tbz \type, #0, skip_\()\type // Skip invalid and + tbnz \type, #11, skip_\()\type // non-global entries .endm .macro __idmap_kpti_put_pgtable_ent_ng, type @@ -265,8 +266,9 @@ ENTRY(idmap_kpti_install_ng_mappings) add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) do_pgd: __idmap_kpti_get_pgtable_ent pgd tbnz pgd, #1, walk_puds - __idmap_kpti_put_pgtable_ent_ng pgd next_pgd: + __idmap_kpti_put_pgtable_ent_ng pgd +skip_pgd: add cur_pgdp, cur_pgdp, #8 cmp cur_pgdp, end_pgdp b.ne do_pgd @@ -294,8 +296,9 @@ walk_puds: add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) do_pud: __idmap_kpti_get_pgtable_ent pud tbnz pud, #1, walk_pmds - __idmap_kpti_put_pgtable_ent_ng pud next_pud: + __idmap_kpti_put_pgtable_ent_ng pud +skip_pud: add cur_pudp, cur_pudp, 8 cmp cur_pudp, end_pudp b.ne do_pud @@ -314,8 +317,9 @@ walk_pmds: add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) do_pmd: __idmap_kpti_get_pgtable_ent pmd tbnz pmd, #1, walk_ptes - __idmap_kpti_put_pgtable_ent_ng pmd next_pmd: + __idmap_kpti_put_pgtable_ent_ng pmd +skip_pmd: add cur_pmdp, cur_pmdp, #8 cmp cur_pmdp, end_pmdp b.ne do_pmd @@ -333,7 +337,7 @@ walk_ptes: add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) do_pte: __idmap_kpti_get_pgtable_ent pte __idmap_kpti_put_pgtable_ent_ng pte -next_pte: +skip_pte: add cur_ptep, cur_ptep, #8 cmp cur_ptep, end_ptep b.ne do_pte diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 0b4c65a1af25..498f3da3f225 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -41,7 +41,6 @@ ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index 19c88d770054..fcf9af492d60 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -10,6 +10,8 @@ #include <linux/errno.h> #include <linux/percpu.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/spinlock.h> #include <asm/mips-cps.h> @@ -22,6 +24,17 @@ static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); phys_addr_t __weak mips_cpc_default_phys_base(void) { + struct device_node *cpc_node; + struct resource res; + int err; + + cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc"); + if (cpc_node) { + err = of_address_to_resource(cpc_node, 0, &res); + if (!err) + return res.start; + } + return 0; } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 85bc601e9a0d..5f8b0a9e30b3 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -375,6 +375,7 @@ static void __init bootmem_init(void) unsigned long reserved_end; unsigned long mapstart = ~0UL; unsigned long bootmap_size; + phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX; bool bootmap_valid = false; int i; @@ -395,7 +396,8 @@ static void __init bootmem_init(void) max_low_pfn = 0; /* - * Find the highest page frame number we have available. + * Find the highest page frame number we have available + * and the lowest used RAM address */ for (i = 0; i < boot_mem_map.nr_map; i++) { unsigned long start, end; @@ -407,6 +409,8 @@ static void __init bootmem_init(void) end = PFN_DOWN(boot_mem_map.map[i].addr + boot_mem_map.map[i].size); + ramstart = min(ramstart, boot_mem_map.map[i].addr); + #ifndef CONFIG_HIGHMEM /* * Skip highmem here so we get an accurate max_low_pfn if low @@ -436,6 +440,13 @@ static void __init bootmem_init(void) mapstart = max(reserved_end, start); } + /* + * Reserve any memory between the start of RAM and PHYS_OFFSET + */ + if (ramstart > PHYS_OFFSET) + add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, + BOOT_MEM_RESERVED); + if (min_low_pfn >= max_low_pfn) panic("Incorrect memory mapping !!!"); if (min_low_pfn > ARCH_PFN_OFFSET) { @@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p) add_memory_region(start, size, BOOT_MEM_RAM); - if (start && start > PHYS_OFFSET) - add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET, - BOOT_MEM_RESERVED); return 0; } early_param("mem", early_parse_mem); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 87dcac2447c8..9d41732a9146 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -572,7 +572,7 @@ asmlinkage void __weak plat_wired_tlb_setup(void) */ } -void __init bmips_cpu_setup(void) +void bmips_cpu_setup(void) { void __iomem __maybe_unused *cbr = BMIPS_GET_CBR(); u32 __maybe_unused cfg; diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 30a155c0a6b0..c615abdce119 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -16,6 +16,7 @@ #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 949d691094a4..67c5475311ee 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -63,7 +63,8 @@ static inline int hash__hugepd_ok(hugepd_t hpd) * keeping the prototype consistent across the two formats. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, unsigned long hidx, + int offset) { return (hidx << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX); diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 338b7da468ce..3bcf269f8f55 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -45,7 +45,7 @@ * generic accessors and iterators here */ #define __real_pte __real_pte -static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) { real_pte_t rpte; unsigned long *hidxp; @@ -59,7 +59,7 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) */ smp_rmb(); - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + hidxp = (unsigned long *)(ptep + offset); rpte.hidx = *hidxp; return rpte; } @@ -86,9 +86,10 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) * expected to modify the PTE bits accordingly and commit the PTE to memory. */ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, - unsigned int subpg_index, unsigned long hidx) + unsigned int subpg_index, + unsigned long hidx, int offset) { - unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); + unsigned long *hidxp = (unsigned long *)(ptep + offset); rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index); *hidxp = rpte.hidx | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index); @@ -140,13 +141,18 @@ static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long a } #define H_PTE_TABLE_SIZE PTE_FRAG_SIZE -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE) #define H_PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + \ (sizeof(unsigned long) << PMD_INDEX_SIZE)) #else #define H_PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #endif +#ifdef CONFIG_HUGETLB_PAGE +#define H_PUD_TABLE_SIZE ((sizeof(pud_t) << PUD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PUD_INDEX_SIZE)) +#else #define H_PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#endif #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 0920eff731b3..935adcd92a81 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -23,7 +23,8 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_PPC_64K_PAGES) +#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \ + defined(CONFIG_PPC_64K_PAGES) /* * only with hash 64k we need to use the second half of pmd page table * to store pointer to deposited pgtable_t @@ -33,6 +34,16 @@ #define H_PMD_CACHE_INDEX H_PMD_INDEX_SIZE #endif /* + * We store the slot details in the second half of page table. + * Increase the pud level table so that hugetlb ptes can be stored + * at pud level. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE + 1) +#else +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE) +#endif +/* * Define the address range of the kernel non-linear virtual area */ #define H_KERN_VIRT_START ASM_CONST(0xD000000000000000) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 1fcfa425cefa..4746bc68d446 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -73,10 +73,16 @@ static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { + pgd_t *pgd; + if (radix_enabled()) return radix__pgd_alloc(mm); - return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), - pgtable_gfp_flags(mm, GFP_KERNEL)); + + pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), + pgtable_gfp_flags(mm, GFP_KERNEL)); + memset(pgd, 0, PGD_TABLE_SIZE); + + return pgd; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -93,13 +99,13 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), + return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), pgtable_gfp_flags(mm, GFP_KERNEL)); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud); + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) @@ -115,7 +121,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE); + pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 51017726d495..a6b9f1d74600 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -232,11 +232,13 @@ extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; extern unsigned long __pmd_cache_index; +extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size #define PMD_CACHE_INDEX __pmd_cache_index +#define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table * are not always derived out of index size above. @@ -348,7 +350,7 @@ extern unsigned long pci_io_base; */ #ifndef __real_pte -#define __real_pte(e,p) ((real_pte_t){(e)}) +#define __real_pte(e, p, o) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 176dfb73d42c..471b2274fbeb 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -645,7 +645,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXC_HV, SOFTEN_TEST_HV, bitmask) #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec, bitmask);\ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 88e5e8f17e98..855e17d158b1 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -30,6 +30,16 @@ #define PACA_IRQ_PMI 0x40 /* + * Some soft-masked interrupts must be hard masked until they are replayed + * (e.g., because the soft-masked handler does not clear the exception). + */ +#ifdef CONFIG_PPC_BOOK3S +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI) +#else +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE) +#endif + +/* * flags for paca->irq_soft_mask */ #define IRQS_ENABLED 0 @@ -244,7 +254,7 @@ static inline bool lazy_irq_pending(void) static inline void may_hard_irq_enable(void) { get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - if (!(get_paca()->irq_happened & PACA_IRQ_EE)) + if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) __hard_irq_enable(); } diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 9dcbfa6bbb91..d8b1e8e7e035 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -140,6 +140,12 @@ static inline bool kdump_in_progress(void) return false; } +static inline void crash_ipi_callback(struct pt_regs *regs) { } + +static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) +{ +} + #endif /* CONFIG_KEXEC_CORE */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 504a3c36ce5c..03bbd1149530 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -24,6 +24,7 @@ extern int icache_44x_need_flush; #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index abddf5830ad5..5c5f75d005ad 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -27,6 +27,7 @@ #else #define PMD_CACHE_INDEX PMD_INDEX_SIZE #endif +#define PUD_CACHE_INDEX PUD_INDEX_SIZE /* * Define the address range of the kernel non-linear virtual area diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 88187c285c70..9f421641a35c 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,6 +44,11 @@ extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); extern int numa_update_cpu_topology(bool cpus_locked); +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) +{ + numa_cpu_lookup_table[cpu] = node; +} + static inline int early_cpu_to_node(int cpu) { int nid; @@ -76,12 +81,16 @@ static inline int numa_update_cpu_topology(bool cpus_locked) { return 0; } + +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int start_topology_update(void); extern int stop_topology_update(void); extern int prrn_is_enabled(void); +extern int find_and_online_cpu_nid(int cpu); #else static inline int start_topology_update(void) { @@ -95,6 +104,10 @@ static inline int prrn_is_enabled(void) { return 0; } +static inline int find_and_online_cpu_nid(int cpu) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index ee832d344a5a..9b6e653e501a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -943,6 +943,8 @@ kernel_dbg_exc: /* * An interrupt came in while soft-disabled; We mark paca->irq_happened * accordingly and if the interrupt is level sensitive, we hard disable + * hard disable (full_mask) corresponds to PACA_IRQ_MUST_HARD_MASK, so + * keep these in synch. */ .macro masked_interrupt_book3e paca_irq full_mask diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 243d072a225a..3ac87e53b3da 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1426,7 +1426,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) * triggered and won't automatically refire. * - If it was a HMI we return immediately since we handled it in realmode * and it won't refire. - * - else we hard disable and return. + * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ #define MASKED_INTERRUPT(_H) \ @@ -1441,8 +1441,8 @@ masked_##_H##interrupt: \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ b MASKED_DEC_HANDLER_LABEL; \ -1: andi. r10,r10,(PACA_IRQ_DBELL|PACA_IRQ_HMI); \ - bne 2f; \ +1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK; \ + beq 2f; \ mfspr r10,SPRN_##_H##SRR1; \ xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5a8bfee6e187..04d0bbd7a1dd 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -788,7 +788,8 @@ static int register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_create_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ @@ -873,7 +874,8 @@ static int unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_remove_file(s, &dev_attr_pir); - if (cpu_has_feature(CPU_FTR_ARCH_206)) + if (cpu_has_feature(CPU_FTR_ARCH_206) && + !firmware_has_feature(FW_FEATURE_LPAR)) device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 1604110c4238..916844f99c64 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -216,6 +216,8 @@ static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, u32 i, n_lmbs; n_lmbs = of_read_number(prop++, 1); + if (n_lmbs == 0) + return; for (i = 0; i < n_lmbs; i++) { read_drconf_v1_cell(&lmb, &prop); @@ -245,6 +247,8 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, u32 i, j, lmb_sets; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; for (i = 0; i < lmb_sets; i++) { read_drconf_v2_cell(&dr_cell, &prop); @@ -354,6 +358,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) struct drmem_lmb *lmb; drmem_info->n_lmbs = of_read_number(prop++, 1); + if (drmem_info->n_lmbs == 0) + return; drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb), GFP_KERNEL); @@ -373,6 +379,8 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) int lmb_index; lmb_sets = of_read_number(prop++, 1); + if (lmb_sets == 0) + return; /* first pass, calculate the number of LMBs */ p = prop; diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index 5a69b51d08a3..d573d7d07f25 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, * need to add in 0x1 if it's a read-only user page */ rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -117,7 +117,7 @@ repeat: return -1; } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 2253bbc6a599..e601d95c3b20 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -86,7 +86,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, subpg_index = (ea & (PAGE_SIZE - 1)) >> shift; vpn = hpt_vpn(ea, vsid, ssize); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); /* *None of the sub 4k page is hashed */ @@ -214,7 +214,7 @@ repeat: return -1; } - new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot); + new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE); new_pte |= H_PAGE_HASHPTE; *ptep = __pte(new_pte & ~H_PAGE_BUSY); @@ -262,7 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, } while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE); if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -327,7 +327,7 @@ repeat: } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 7d07c7e17db6..cf290d415dcd 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1008,6 +1008,7 @@ void __init hash__early_init_mmu(void) __pmd_index_size = H_PMD_INDEX_SIZE; __pud_index_size = H_PUD_INDEX_SIZE; __pgd_index_size = H_PGD_INDEX_SIZE; + __pud_cache_index = H_PUD_CACHE_INDEX; __pmd_cache_index = H_PMD_CACHE_INDEX; __pte_table_size = H_PTE_TABLE_SIZE; __pmd_table_size = H_PMD_TABLE_SIZE; diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 12511f5a015f..b320f5097a06 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -27,7 +27,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, unsigned long vpn; unsigned long old_pte, new_pte; unsigned long rflags, pa, sz; - long slot; + long slot, offset; BUG_ON(shift != mmu_psize_defs[mmu_psize].shift); @@ -63,7 +63,11 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, } while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte))); rflags = htab_convert_pte_flags(new_pte); - rpte = __real_pte(__pte(old_pte), ptep); + if (unlikely(mmu_psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; + rpte = __real_pte(__pte(old_pte), ptep, offset); sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) @@ -104,7 +108,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, return -1; } - new_pte |= pte_set_hidx(ptep, rpte, 0, slot); + new_pte |= pte_set_hidx(ptep, rpte, 0, slot, offset); } /* diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index eb8c6c8c4851..2b656e67f2ea 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -100,6 +100,6 @@ void pgtable_cache_init(void) * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE)) - pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor); + if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) + pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 314d19ab9385..edd8d0bc9364 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -143,11 +143,6 @@ static void reset_numa_cpu_lookup_table(void) numa_cpu_lookup_table[cpu] = -1; } -static void update_numa_cpu_lookup_table(unsigned int cpu, int node) -{ - numa_cpu_lookup_table[cpu] = node; -} - static void map_cpu_to_node(int cpu, int node) { update_numa_cpu_lookup_table(cpu, node); diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 573a9a2ee455..2e10a964e290 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -17,9 +17,11 @@ #include <linux/of_fdt.h> #include <linux/mm.h> #include <linux/string_helpers.h> +#include <linux/stop_machine.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> +#include <asm/mmu_context.h> #include <asm/dma.h> #include <asm/machdep.h> #include <asm/mmu.h> @@ -333,6 +335,22 @@ static void __init radix_init_pgtable(void) "r" (TLBIEL_INVAL_SET_LPID), "r" (0)); asm volatile("eieio; tlbsync; ptesync" : : : "memory"); trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1); + + /* + * The init_mm context is given the first available (non-zero) PID, + * which is the "guard PID" and contains no page table. PIDR should + * never be set to zero because that duplicates the kernel address + * space at the 0x0... offset (quadrant 0)! + * + * An arbitrary PID that may later be allocated by the PID allocator + * for userspace processes must not be used either, because that + * would cause stale user mappings for that PID on CPUs outside of + * the TLB invalidation scheme (because it won't be in mm_cpumask). + * + * So permanently carve out one PID for the purpose of a guard PID. + */ + init_mm.context.id = mmu_base_pid; + mmu_base_pid++; } static void __init radix_init_partition_table(void) @@ -535,6 +553,7 @@ void __init radix__early_init_mmu(void) __pmd_index_size = RADIX_PMD_INDEX_SIZE; __pud_index_size = RADIX_PUD_INDEX_SIZE; __pgd_index_size = RADIX_PGD_INDEX_SIZE; + __pud_cache_index = RADIX_PUD_INDEX_SIZE; __pmd_cache_index = RADIX_PMD_INDEX_SIZE; __pte_table_size = RADIX_PTE_TABLE_SIZE; __pmd_table_size = RADIX_PMD_TABLE_SIZE; @@ -579,7 +598,8 @@ void __init radix__early_init_mmu(void) radix_init_iamr(); radix_init_pgtable(); - + /* Switch to the guard PID before turning on MMU */ + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -604,6 +624,7 @@ void radix__early_init_mmu_secondary(void) } radix_init_iamr(); + radix__switch_mmu_context(NULL, &init_mm); if (cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); } @@ -666,6 +687,30 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) pud_clear(pud); } +struct change_mapping_params { + pte_t *pte; + unsigned long start; + unsigned long end; + unsigned long aligned_start; + unsigned long aligned_end; +}; + +static int stop_machine_change_mapping(void *data) +{ + struct change_mapping_params *params = + (struct change_mapping_params *)data; + + if (!data) + return -1; + + spin_unlock(&init_mm.page_table_lock); + pte_clear(&init_mm, params->aligned_start, params->pte); + create_physical_mapping(params->aligned_start, params->start); + create_physical_mapping(params->end, params->aligned_end); + spin_lock(&init_mm.page_table_lock); + return 0; +} + static void remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end) { @@ -694,6 +739,52 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, } } +/* + * clear the pte and potentially split the mapping helper + */ +static void split_kernel_mapping(unsigned long addr, unsigned long end, + unsigned long size, pte_t *pte) +{ + unsigned long mask = ~(size - 1); + unsigned long aligned_start = addr & mask; + unsigned long aligned_end = addr + size; + struct change_mapping_params params; + bool split_region = false; + + if ((end - addr) < size) { + /* + * We're going to clear the PTE, but not flushed + * the mapping, time to remap and flush. The + * effects if visible outside the processor or + * if we are running in code close to the + * mapping we cleared, we are in trouble. + */ + if (overlaps_kernel_text(aligned_start, addr) || + overlaps_kernel_text(end, aligned_end)) { + /* + * Hack, just return, don't pte_clear + */ + WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel " + "text, not splitting\n", addr, end); + return; + } + split_region = true; + } + + if (split_region) { + params.pte = pte; + params.start = addr; + params.end = end; + params.aligned_start = addr & ~(size - 1); + params.aligned_end = min_t(unsigned long, aligned_end, + (unsigned long)__va(memblock_end_of_DRAM())); + stop_machine(stop_machine_change_mapping, ¶ms, NULL); + return; + } + + pte_clear(&init_mm, addr, pte); +} + static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end) { @@ -709,13 +800,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_huge(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pmd); + split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd); continue; } @@ -740,13 +825,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, continue; if (pud_huge(*pud)) { - if (!IS_ALIGNED(addr, PUD_SIZE) || - !IS_ALIGNED(next, PUD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pud); + split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud); continue; } @@ -772,13 +851,7 @@ static void remove_pagetable(unsigned long start, unsigned long end) continue; if (pgd_huge(*pgd)) { - if (!IS_ALIGNED(addr, PGDIR_SIZE) || - !IS_ALIGNED(next, PGDIR_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; - } - - pte_clear(&init_mm, addr, (pte_t *)pgd); + split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd); continue; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index c9a623c2d8a2..28c980eb4422 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -82,6 +82,8 @@ unsigned long __pgd_index_size; EXPORT_SYMBOL(__pgd_index_size); unsigned long __pmd_cache_index; EXPORT_SYMBOL(__pmd_cache_index); +unsigned long __pud_cache_index; +EXPORT_SYMBOL(__pud_cache_index); unsigned long __pte_table_size; EXPORT_SYMBOL(__pte_table_size); unsigned long __pmd_table_size; @@ -471,6 +473,8 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, if (old & PATB_HR) { asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); } else { asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 881ebd53ffc2..9b23f12e863c 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -51,7 +51,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, unsigned int psize; int ssize; real_pte_t rpte; - int i; + int i, offset; i = batch->index; @@ -67,6 +67,10 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, psize = get_slice_psize(mm, addr); /* Mask the address for the correct page size */ addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1); + if (unlikely(psize == MMU_PAGE_16G)) + offset = PTRS_PER_PUD; + else + offset = PTRS_PER_PMD; #else BUG(); psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */ @@ -78,6 +82,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, * support 64k pages, this might be different from the * hardware page size encoded in the slice table. */ addr &= PAGE_MASK; + offset = PTRS_PER_PTE; } @@ -91,7 +96,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, } WARN_ON(vsid == 0); vpn = hpt_vpn(addr, vsid, ssize); - rpte = __real_pte(__pte(pte), ptep); + rpte = __real_pte(__pte(pte), ptep, offset); /* * Check if we have an active batch on this CPU. If not, just diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index dd4c9b8b8a81..f6f55ab4980e 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -199,9 +199,11 @@ static void disable_nest_pmu_counters(void) const struct cpumask *l_cpumask; get_online_cpus(); - for_each_online_node(nid) { + for_each_node_with_cpus(nid) { l_cpumask = cpumask_of_node(nid); - cpu = cpumask_first(l_cpumask); + cpu = cpumask_first_and(l_cpumask, cpu_online_mask); + if (cpu >= nr_cpu_ids) + continue; opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(cpu)); } diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index 2b3eb01ab110..b7c53a51c31b 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -1063,16 +1063,16 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, rc = PTR_ERR(txwin->paste_kaddr); goto free_window; } + } else { + /* + * A user mapping must ensure that context switch issues + * CP_ABORT for this thread. + */ + rc = set_thread_uses_vas(); + if (rc) + goto free_window; } - /* - * Now that we have a send window, ensure context switch issues - * CP_ABORT for this thread. - */ - rc = -EINVAL; - if (set_thread_uses_vas() < 0) - goto free_window; - set_vinst_win(vinst, txwin); return txwin; diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index dceb51454d8d..652d3e96b812 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -36,6 +36,7 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/plpar_wrappers.h> +#include <asm/topology.h> #include "pseries.h" #include "offline_states.h" @@ -331,6 +332,7 @@ static void pseries_remove_processor(struct device_node *np) BUG_ON(cpu_online(cpu)); set_cpu_present(cpu, false); set_hard_smp_processor_id(cpu, -1); + update_numa_cpu_lookup_table(cpu, -1); break; } if (cpu >= nr_cpu_ids) @@ -340,8 +342,6 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } -extern int find_and_online_cpu_nid(int cpu); - static int dlpar_online_cpu(struct device_node *dn) { int rc = 0; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 81d8614e7379..5e1ef9150182 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -49,6 +49,28 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id); /* + * Enable the hotplug interrupt late because processing them may touch other + * devices or systems (e.g. hugepages) that have not been initialized at the + * subsys stage. + */ +int __init init_ras_hotplug_IRQ(void) +{ + struct device_node *np; + + /* Hotplug Events */ + np = of_find_node_by_path("/event-sources/hot-plug-events"); + if (np != NULL) { + if (dlpar_workqueue_init() == 0) + request_event_sources_irqs(np, ras_hotplug_interrupt, + "RAS_HOTPLUG"); + of_node_put(np); + } + + return 0; +} +machine_late_initcall(pseries, init_ras_hotplug_IRQ); + +/* * Initialize handlers for the set of interrupts caused by hardware errors * and power system events. */ @@ -66,15 +88,6 @@ static int __init init_ras_IRQ(void) of_node_put(np); } - /* Hotplug Events */ - np = of_find_node_by_path("/event-sources/hot-plug-events"); - if (np != NULL) { - if (dlpar_workqueue_init() == 0) - request_event_sources_irqs(np, ras_hotplug_interrupt, - "RAS_HOTPLUG"); - of_node_put(np); - } - /* EPOW Events */ np = of_find_node_by_path("/event-sources/epow-events"); if (np != NULL) { diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index d9c4c9366049..091f1d0d0af1 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -356,7 +356,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size); if (rc) { - pr_err("Error %lld getting queue info prio %d\n", rc, prio); + pr_err("Error %lld getting queue info CPU %d prio %d\n", rc, + target, prio); rc = -EIO; goto fail; } @@ -370,7 +371,8 @@ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, /* Configure and enable the queue in HW */ rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order); if (rc) { - pr_err("Error %lld setting queue for prio %d\n", rc, prio); + pr_err("Error %lld setting queue for CPU %d prio %d\n", rc, + target, prio); rc = -EIO; } else { q->qpage = qpage; @@ -389,8 +391,8 @@ static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc, if (IS_ERR(qpage)) return PTR_ERR(qpage); - return xive_spapr_configure_queue(cpu, q, prio, qpage, - xive_queue_shift); + return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu), + q, prio, qpage, xive_queue_shift); } static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, @@ -399,10 +401,12 @@ static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, struct xive_q *q = &xc->queue[prio]; unsigned int alloc_order; long rc; + int hw_cpu = get_hard_smp_processor_id(cpu); - rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0); + rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0); if (rc) - pr_err("Error %ld setting queue for prio %d\n", rc, prio); + pr_err("Error %ld setting queue for CPU %d prio %d\n", rc, + hw_cpu, prio); alloc_order = xive_alloc_order(xive_queue_shift); free_pages((unsigned long)q->qpage, alloc_order); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6bf594ace663..8767e45f1b2b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -430,6 +430,8 @@ config SPARC_LEON depends on SPARC32 select USB_EHCI_BIG_ENDIAN_MMIO select USB_EHCI_BIG_ENDIAN_DESC + select USB_UHCI_BIG_ENDIAN_MMIO + select USB_UHCI_BIG_ENDIAN_DESC ---help--- If you say Y here if you are running on a SPARC-LEON processor. The LEON processor is a synthesizable VHDL model of the diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index aff152c87cf4..5a82bac5e0bc 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,6 +1,7 @@ boot/compressed/vmlinux tools/test_get_len tools/insn_sanity +tools/insn_decoder_test purgatory/kexec-purgatory.c purgatory/purgatory.ro diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 63bf349b2b24..c1236b187824 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -423,12 +423,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config X86_BIGSMP - bool "Support for big SMP systems with more than 8 CPUs" - depends on X86_32 && SMP - ---help--- - This option is needed for the systems that have more than 8 CPUs - config GOLDFISH def_bool y depends on X86_GOLDFISH @@ -460,6 +454,12 @@ config INTEL_RDT Say N if unsure. if X86_32 +config X86_BIGSMP + bool "Support for big SMP systems with more than 8 CPUs" + depends on SMP + ---help--- + This option is needed for the systems that have more than 8 CPUs + config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" default y @@ -949,25 +949,66 @@ config MAXSMP Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. +# +# The maximum number of CPUs supported: +# +# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT, +# and which can be configured interactively in the +# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range. +# +# The ranges are different on 32-bit and 64-bit kernels, depending on +# hardware capabilities and scalability features of the kernel. +# +# ( If MAXSMP is enabled we just use the highest possible value and disable +# interactive configuration. ) +# + +config NR_CPUS_RANGE_BEGIN + int + default NR_CPUS_RANGE_END if MAXSMP + default 1 if !SMP + default 2 + +config NR_CPUS_RANGE_END + int + depends on X86_32 + default 64 if SMP && X86_BIGSMP + default 8 if SMP && !X86_BIGSMP + default 1 if !SMP + +config NR_CPUS_RANGE_END + int + depends on X86_64 + default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) + default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_32 + default 32 if X86_BIGSMP + default 8 if SMP + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_64 + default 8192 if MAXSMP + default 64 if SMP + default 1 if !SMP + config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP - range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 64 if SMP && X86_32 && X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 - range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 - default "1" if !SMP - default "8192" if MAXSMP - default "32" if SMP && X86_BIGSMP - default "8" if SMP && X86_32 - default "64" if SMP + range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END + default NR_CPUS_DEFAULT ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. - This is purely to save memory - each supported CPU adds - approximately eight kilobytes to the kernel image. + This is purely to save memory: each supported CPU adds about 8KB + to the kernel image. config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" @@ -1363,7 +1404,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486 + depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 select X86_PAE ---help--- Select this if you have a 32-bit processor and more than 4 diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 65a9a4716e34..8b8d2297d486 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -374,7 +374,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 # this should be set for all -march=.. options where the compiler # generates cmov. @@ -385,7 +385,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && X86_P6_NOP + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3f48f695d5e6..dce7092ab24a 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,80 +97,69 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 - .macro ALLOC_PT_GPREGS_ON_STACK - addq $-(15*8), %rsp - .endm +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax + /* + * Push registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq \rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq \rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ + pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ + pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ + pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ + pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ + pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ + pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ + pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ + pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ + pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ + UNWIND_HINT_REGS +.endm - .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 - .if \r11 - movq %r11, 6*8+\offset(%rsp) - .endif - .if \r8910 - movq %r10, 7*8+\offset(%rsp) - movq %r9, 8*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - .endif - .if \rax - movq %rax, 10*8+\offset(%rsp) - .endif - .if \rcx - movq %rcx, 11*8+\offset(%rsp) - .endif - movq %rdx, 12*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) - movq %rdi, 14*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - .macro SAVE_C_REGS offset=0 - SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 - SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_R891011 - SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RCX_R891011 - SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 - SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 - .endm - - .macro SAVE_EXTRA_REGS offset=0 - movq %r15, 0*8+\offset(%rsp) - movq %r14, 1*8+\offset(%rsp) - movq %r13, 2*8+\offset(%rsp) - movq %r12, 3*8+\offset(%rsp) - movq %rbp, 4*8+\offset(%rsp) - movq %rbx, 5*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset - .endm - - .macro POP_EXTRA_REGS +.macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .endm - - .macro POP_C_REGS + .if \skip_r11rcx + popq %rsi + .else popq %r11 + .endif popq %r10 popq %r9 popq %r8 popq %rax + .if \skip_r11rcx + popq %rsi + .else popq %rcx + .endif popq %rdx popq %rsi + .if \pop_rdi popq %rdi - .endm - - .macro icebp - .byte 0xf1 - .endm + .endif +.endm /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The @@ -178,7 +167,7 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 30c8c5344c4a..8971bd64d515 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64) swapgs /* - * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it * is not required to switch CR3. */ movq %rsp, PER_CPU_VAR(rsp_scratch) @@ -227,22 +227,8 @@ ENTRY(entry_SYSCALL_64) pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + + PUSH_AND_CLEAR_REGS rax=$-ENOSYS TRACE_IRQS_OFF @@ -321,15 +307,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY - POP_EXTRA_REGS - popq %rsi /* skip r11 */ - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rsi /* skip rcx */ - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 skip_r11rcx=1 /* * Now all regs are restored except RSP and RDI. @@ -559,9 +537,7 @@ END(irq_entries_start) call switch_to_thread_stack 1: - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -622,15 +598,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - POP_EXTRA_REGS - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 /* * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. @@ -688,8 +656,7 @@ GLOBAL(restore_regs_and_return_to_kernel) ud2 1: #endif - POP_EXTRA_REGS - POP_C_REGS + POP_REGS addq $8, %rsp /* skip regs->orig_ax */ /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -908,7 +875,9 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - ALLOC_PT_GPREGS_ON_STACK + /* Save all registers in pt_regs */ + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ @@ -1121,9 +1090,7 @@ ENTRY(xen_failsafe_callback) addq $0x30, %rsp UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1163,16 +1130,13 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1211,21 +1175,18 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_REGS offset=8 cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - ENCODE_FRAME_POINTER 8 - xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1406,22 +1367,7 @@ ENTRY(nmi) pushq 1*8(%rdx) /* pt_regs->rip */ UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER /* @@ -1631,7 +1577,8 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit @@ -1655,8 +1602,7 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - POP_EXTRA_REGS - POP_C_REGS + POP_REGS /* * Skip orig_ax and the "outermost" frame to point RSP at the "iret" diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 98d5358e4041..fd65e016e413 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ cld /* @@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorq %r12, %r12 /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorq %r13, %r13 /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorq %r14, %r14 /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorq %r15, %r15 /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -338,15 +358,25 @@ ENTRY(entry_INT80_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorq %r8, %r8 /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorq %r9, %r9 /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorq %r10, %r10 /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ cld /* diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 731153a4681e..56457cb73448 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,7 +3559,7 @@ static int intel_snb_pebs_broken(int cpu) break; case INTEL_FAM6_SANDYBRIDGE_X: - switch (cpu_data(cpu).x86_mask) { + switch (cpu_data(cpu).x86_stepping) { case 6: rev = 0x618; break; case 7: rev = 0x70c; break; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index ae64d0b69729..cf372b90557e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1186,7 +1186,7 @@ void __init intel_pmu_lbr_init_atom(void) * on PMU interrupt */ if (boot_cpu_data.x86_model == 28 - && boot_cpu_data.x86_mask < 10) { + && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index a5604c352930..408879b0c0d4 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -234,7 +234,7 @@ static __initconst const struct x86_pmu p6_pmu = { static __init void p6_pmu_rdpmc_quirk(void) { - if (boot_cpu_data.x86_mask < 9) { + if (boot_cpu_data.x86_stepping < 9) { /* * PPro erratum 26; fixed in stepping 9 and above. */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 44f5d79d5105..11881726ed37 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) if (boot_cpu_data.x86 == 0x0F && boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86_model <= 0x05 && - boot_cpu_data.x86_mask < 0x0A) + boot_cpu_data.x86_stepping < 0x0A) return 1; else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E)) return 1; diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 30d406146016..e1259f043ae9 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, asm ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) - :"r"(size),"r" (index) + :"g"(size),"r" (index) :"cc"); return mask; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 34d99af43994..6804d6642767 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -5,23 +5,20 @@ #include <linux/stringify.h> /* - * Since some emulators terminate on UD2, we cannot use it for WARN. - * Since various instruction decoders disagree on the length of UD1, - * we cannot use it either. So use UD0 for WARN. + * Despite that some emulators terminate on UD2, we use it for WARN(). * - * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas - * our kernel decoder thinks it takes a ModRM byte, which seems consistent - * with various things like the Intel SDM instruction encoding rules) + * Since various instruction decoders/specs disagree on the encoding of + * UD0/UD1. */ -#define ASM_UD0 ".byte 0x0f, 0xff" +#define ASM_UD0 ".byte 0x0f, 0xff" /* + ModRM (for Intel) */ #define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ #define ASM_UD2 ".byte 0x0f, 0x0b" #define INSN_UD0 0xff0f #define INSN_UD2 0x0b0f -#define LEN_UD0 2 +#define LEN_UD2 2 #ifdef CONFIG_GENERIC_BUG @@ -77,7 +74,11 @@ do { \ unreachable(); \ } while (0) -#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)) +#define __WARN_FLAGS(flags) \ +do { \ + _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ + annotate_reachable(); \ +} while (0) #include <asm-generic/bug.h> diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 70eddb3922ff..736771c9822e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -148,45 +148,46 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline __pure bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" - "2:\n" - ".skip -(((5f-4f) - (2b-1b)) > 0) * " - "((5f-4f) - (2b-1b)),0x90\n" - "3:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 4f - .\n" /* repl offset */ - " .word %P1\n" /* always replace */ - " .byte 3b - 1b\n" /* src len */ - " .byte 5f - 4f\n" /* repl len */ - " .byte 3b - 2b\n" /* pad len */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "4: jmp %l[t_no]\n" - "5:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ - " .byte 3b - 1b\n" /* src len */ - " .byte 0\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .altinstr_aux,\"ax\"\n" - "6:\n" - " testb %[bitnum],%[cap_byte]\n" - " jnz %l[t_yes]\n" - " jmp %l[t_no]\n" - ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS), - [bitnum] "i" (1 << (bit & 7)), - [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) - : : t_yes, t_no); - t_yes: - return true; - t_no: - return false; + asm_volatile_goto("1: jmp 6f\n" + "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 4f - .\n" /* repl offset */ + " .word %P[always]\n" /* always replace */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "4: jmp %l[t_no]\n" + "5:\n" + ".previous\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 0\n" /* no replacement */ + " .word %P[feature]\n" /* feature bit */ + " .byte 3b - 1b\n" /* src len */ + " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ + ".previous\n" + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" + : : [feature] "i" (bit), + [always] "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); +t_yes: + return true; +t_no: + return false; } #define static_cpu_has(bit) \ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4d57894635f2..76b058533e47 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -6,6 +6,7 @@ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> +#include <asm/msr-index.h> #ifdef __ASSEMBLY__ @@ -164,10 +165,15 @@ static inline void vmexit_fill_RSB(void) static inline void indirect_branch_prediction_barrier(void) { - alternative_input("", - "call __ibp_barrier", - X86_FEATURE_USE_IBPB, - ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_USE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 4baa6bceb232..d652a3808065 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -52,10 +52,6 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); -#ifdef CONFIG_X86_MCE -#define arch_unmap_kpfn arch_unmap_kpfn -#endif - #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 892df375b615..554841fab717 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -297,9 +297,9 @@ static inline void __flush_tlb_global(void) { PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); } -static inline void __flush_tlb_single(unsigned long addr) +static inline void __flush_tlb_one_user(unsigned long addr) { - PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); + PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 6ec54d01972d..f624f1f10316 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -217,7 +217,7 @@ struct pv_mmu_ops { /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_one_user)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e67c0620aec2..e55466760ff8 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -61,7 +61,7 @@ void paging_init(void); #define kpte_clear_flush(ptep, vaddr) \ do { \ pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ + __flush_tlb_one_kernel((vaddr)); \ } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 793bae7e7ce3..1bd9ed87606f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -91,7 +91,7 @@ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; - __u8 x86_mask; + __u8 x86_stepping; #ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; @@ -109,7 +109,7 @@ struct cpuinfo_x86 { char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ - int x86_cache_size; + unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values: */ int x86_cache_max_rmid; /* max index */ @@ -977,7 +977,4 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); - -void __ibp_barrier(void); - #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 461f53d27708..a4189762b266 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); +void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); void common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 2b8f18ca5874..84137c22fdfa 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -140,7 +140,7 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #else #define __flush_tlb() __native_flush_tlb() #define __flush_tlb_global() __native_flush_tlb_global() -#define __flush_tlb_single(addr) __native_flush_tlb_single(addr) +#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif static inline bool tlb_defer_switch_to_init_mm(void) @@ -400,7 +400,7 @@ static inline void __native_flush_tlb_global(void) /* * flush one page in the user mapping */ -static inline void __native_flush_tlb_single(unsigned long addr) +static inline void __native_flush_tlb_one_user(unsigned long addr) { u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); @@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void) /* * flush one page in the kernel mapping */ -static inline void __flush_tlb_one(unsigned long addr) +static inline void __flush_tlb_one_kernel(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); + + /* + * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its + * paravirt equivalent. Even with PCID, this is sufficient: we only + * use PCID if we also use global PTEs for the kernel mapping, and + * INVLPG flushes global translations across all address spaces. + * + * If PTI is on, then the kernel is mapped with non-global PTEs, and + * __flush_tlb_one_user() will flush the given address for the current + * kernel address space and for its usermode counterpart, but it does + * not flush it for other address spaces. + */ + __flush_tlb_one_user(addr); if (!static_cpu_has(X86_FEATURE_PTI)) return; /* - * __flush_tlb_single() will have cleared the TLB entry for this ASID, - * but since kernel space is replicated across all, we must also - * invalidate all others. + * See above. We need to propagate the flush to all other address + * spaces. In principle, we only need to propagate it to kernelmode + * address spaces, but the extra bookkeeping we would need is not + * worth it. */ invalidate_other_asid(); } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 6db28f17ff28..c88e0b127810 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -235,7 +235,7 @@ int amd_cache_northbridges(void) if (boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model >= 0x8 && (boot_cpu_data.x86_model > 0x9 || - boot_cpu_data.x86_mask >= 0x1)) + boot_cpu_data.x86_stepping >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; if (boot_cpu_data.x86 == 0x15) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 25ddf02598d2..b203af0855b5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,7 +546,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static u32 hsx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ case 0x04: return 0x0f; /* EX */ } @@ -556,7 +556,7 @@ static u32 hsx_deadline_rev(void) static u32 bdx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; case 0x03: return 0x0700000e; case 0x04: return 0x0f00000c; @@ -568,7 +568,7 @@ static u32 bdx_deadline_rev(void) static u32 skx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; case 0x04: return 0x02000014; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 46b675aaf20b..f11910b44638 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) uv_gre_table = gre; for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { + unsigned long size = ((unsigned long)(gre->limit - lgre) + << UV_GAM_RANGE_SHFT); + int order = 0; + char suffix[] = " KMGTPE"; + + while (size > 9999 && order < sizeof(suffix)) { + size /= 1024; + order++; + } + if (!index) { pr_info("UV: GAM Range Table...\n"); pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - ((unsigned long)(gre->limit - lgre)) >> - (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ + size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fa1261eefa16..f91ba53e06c8 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,7 +18,7 @@ void foo(void) OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); - OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); + OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5bddbdcbc4a3..f0e6456ca7d3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -119,7 +119,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if (c->x86_model == 6 && c->x86_mask == 1) { + if (c->x86_model == 6 && c->x86_stepping == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); @@ -149,7 +149,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model == 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_stepping < 8)) { /* We can only write allocate on the low 508Mb */ if (mbytes > 508) mbytes = 508; @@ -168,7 +168,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if ((c->x86_model == 8 && c->x86_mask > 7) || + if ((c->x86_model == 8 && c->x86_stepping > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ @@ -221,7 +221,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", @@ -241,12 +241,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * but they are not certified as MP capable. */ /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) + if ((c->x86_model == 6) && ((c->x86_stepping == 0) || + (c->x86_stepping == 1))) return; /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) + if ((c->x86_model == 7) && (c->x86_stepping == 0)) return; /* @@ -256,8 +256,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for * more. */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || + if (((c->x86_model == 6) && (c->x86_stepping >= 2)) || + ((c->x86_model == 7) && (c->x86_stepping >= 1)) || (c->x86_model > 7)) if (cpu_has(c, X86_FEATURE_MP)) return; @@ -628,7 +628,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86 == 5) if (c->x86_model == 13 || c->x86_model == 9 || - (c->x86_model == 8 && c->x86_mask >= 8)) + (c->x86_model == 8 && c->x86_stepping >= 8)) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) @@ -795,7 +795,7 @@ static void init_amd_zn(struct cpuinfo_x86 *c) * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. */ - if (c->x86_model <= 1 && c->x86_mask <= 1) + if (c->x86_model <= 1 && c->x86_stepping <= 1) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -906,11 +906,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { /* Duron Rev A0 */ - if (c->x86_model == 3 && c->x86_mask == 0) + if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; /* Tbird rev A1/A2 */ if (c->x86_model == 4 && - (c->x86_mask == 0 || c->x86_mask == 1)) + (c->x86_stepping == 0 || c->x86_stepping == 1)) size = 256; } return size; @@ -1047,7 +1047,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) } /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_mask; + ms = (cpu->x86_model << 4) | cpu->x86_stepping; while ((range = *erratum++)) if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && (ms >= AMD_MODEL_RANGE_START(range)) && diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 71949bf2de5a..d71c8b54b696 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; @@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_CMD_AUTO; } } @@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -256,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void) goto retpoline_auto; break; } - pr_err("kernel not compiled with retpoline; no mitigation available!"); + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); return; retpoline_auto: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : @@ -281,7 +278,7 @@ retpoline_auto: pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP or KPTI are available, there is a risk of + * If neither SMEP nor PTI are available, there is a risk of * hitting userspace addresses in the RSB after a context switch * from a shallow call stack to a deeper one. To prevent this fill * the entire RSB, even when using IBRS. @@ -295,21 +292,20 @@ retpoline_auto: if ((!boot_cpu_has(X86_FEATURE_PTI) && !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Filling RSB on context switch\n"); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); } /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Enabling Indirect Branch Prediction Barrier\n"); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } } #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return sprintf(buf, "Not affected\n"); @@ -318,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device *dev, return sprintf(buf, "Vulnerable\n"); } -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); @@ -337,9 +331,3 @@ ssize_t cpu_show_spectre_v2(struct device *dev, spectre_v2_module_string()); } #endif - -void __ibp_barrier(void) -{ - __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); -} -EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index c578cd29c2d2..e5ec0f11c0de 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -140,7 +140,7 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: - switch (c->x86_mask) { + switch (c->x86_stepping) { default: name = "2"; break; @@ -215,7 +215,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) * - Note, it seems this may only be in engineering samples. */ if ((c->x86 == 6) && (c->x86_model == 9) && - (c->x86_mask == 1) && (size == 65)) + (c->x86_stepping == 1) && (size == 65)) size -= 1; return size; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d63f4b5706e4..824aee0117bb 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -731,7 +731,7 @@ void cpu_detect(struct cpuinfo_x86 *c) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = x86_family(tfms); c->x86_model = x86_model(tfms); - c->x86_mask = x86_stepping(tfms); + c->x86_stepping = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -1184,9 +1184,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; @@ -1378,8 +1378,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); - if (c->x86_mask || c->cpuid_level >= 0) - pr_cont(", stepping: 0x%x)\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + pr_cont(", stepping: 0x%x)\n", c->x86_stepping); else pr_cont(")\n"); } diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6b4bb335641f..8949b7ae6d92 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -215,7 +215,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* common case step number/rev -- exceptions handled below */ c->x86_model = (dir1 >> 4) + 1; - c->x86_mask = dir1 & 0xf; + c->x86_stepping = dir1 & 0xf; /* Now cook; the original recipe is by Channing Corn, from Cyrix. * We do the same thing for each generation: we work out diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 319bf989fad1..d19e903214b4 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -116,14 +116,13 @@ struct sku_microcode { u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, @@ -136,8 +135,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, - /* Updated in the 20180108 release; blacklist until we know otherwise */ - { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, /* Observed in the wild */ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, @@ -149,7 +146,7 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && - c->x86_mask == spectre_bad_microcodes[i].stepping) + c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } return false; @@ -196,7 +193,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -212,7 +209,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* CPUID workaround for 0F33/0F34 CPU */ if (c->x86 == 0xF && c->x86_model == 0x3 - && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4)) c->x86_phys_bits = 36; /* @@ -310,7 +307,7 @@ int ppro_with_ram_bug(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask < 8) { + boot_cpu_data.x86_stepping < 8) { pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } @@ -327,7 +324,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c) * Mask B, Pentium, but not Pentium MMX */ if (c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_stepping >= 1 && c->x86_stepping <= 4 && c->x86_model <= 3) { /* * Remember we have B step Pentia with bugs @@ -370,7 +367,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until * model 3 mask 3 */ - if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) + if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633) clear_cpu_cap(c, X86_FEATURE_SEP); /* @@ -388,7 +385,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * P4 Xeon erratum 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ - if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { + if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) { if (msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) { pr_info("CPU: C0 stepping P4 Xeon detected.\n"); @@ -403,7 +400,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Specification Update"). */ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && - (c->x86_mask < 0x6 || c->x86_mask == 0xb)) + (c->x86_stepping < 0x6 || c->x86_stepping == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -650,7 +647,7 @@ static void init_intel(struct cpuinfo_x86 *c) case 6: if (l2 == 128) p = "Celeron (Mendocino)"; - else if (c->x86_mask == 0 || c->x86_mask == 5) + else if (c->x86_stepping == 0 || c->x86_stepping == 5) p = "Celeron-A"; break; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 410629f10ad3..589b948e6e01 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -819,7 +819,7 @@ static __init void rdt_quirks(void) cache_alloc_hsw_probe(); break; case INTEL_FAM6_SKYLAKE_X: - if (boot_cpu_data.x86_mask <= 4) + if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index aa0d5df9dc60..e956eb267061 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -115,4 +115,19 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } extern struct mca_config mca_cfg; +#ifndef CONFIG_X86_64 +/* + * On 32-bit systems it would be difficult to safely unmap a poison page + * from the kernel 1:1 map because there are no non-canonical addresses that + * we can use to refer to the address without risking a speculative access. + * However, this isn't much of an issue because: + * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which + * are only mapped into the kernel as needed + * 2) Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +static inline void mce_unmap_kpfn(unsigned long pfn) {} +#define mce_unmap_kpfn mce_unmap_kpfn +#endif + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3a8e88a611eb..8ff94d1e2dce 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -105,6 +105,10 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn); +#endif + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -234,7 +238,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - pr_cont("{%pS}", (void *)m->ip); + pr_cont("{%pS}", (void *)(unsigned long)m->ip); pr_cont("\n"); } @@ -590,7 +594,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, 0); + if (!memory_failure(pfn, 0)) + mce_unmap_kpfn(pfn); } return NOTIFY_OK; @@ -1057,12 +1062,13 @@ static int do_memory_failure(struct mce *m) ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); + else + mce_unmap_kpfn(m->addr >> PAGE_SHIFT); return ret; } -#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) - -void arch_unmap_kpfn(unsigned long pfn) +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn) { unsigned long decoy_addr; @@ -1073,7 +1079,7 @@ void arch_unmap_kpfn(unsigned long pfn) * We would like to just call: * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a - * speculative access to the posion page because we'd have + * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address @@ -1098,7 +1104,6 @@ void arch_unmap_kpfn(unsigned long pfn) if (set_memory_np(decoy_addr, 1)) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - } #endif diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index f7c55b0e753a..a15db2b4e0d6 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -921,7 +921,7 @@ static bool is_blacklisted(unsigned int cpu) */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && - c->x86_mask == 0x01 && + c->x86_stepping == 0x01 && llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); @@ -944,7 +944,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return UCODE_NFOUND; sprintf(name, "intel-ucode/%02x-%02x-%02x", - c->x86, c->x86_model, c->x86_mask); + c->x86, c->x86_model, c->x86_stepping); if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); @@ -982,7 +982,7 @@ static struct microcode_ops microcode_intel_ops = { static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) { - u64 llc_size = c->x86_cache_size * 1024; + u64 llc_size = c->x86_cache_size * 1024ULL; do_div(llc_size, c->x86_max_cores); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fdc55215d44d..e12ee86906c6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, */ if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask <= 7) { + boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 40d5a8a75212..7468de429087 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -711,8 +711,8 @@ void __init mtrr_bp_init(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_mask == 0x3 || - boot_cpu_data.x86_mask == 0x4)) + (boot_cpu_data.x86_stepping == 0x3 || + boot_cpu_data.x86_stepping == 0x4)) phys_addr = 36; size_or_mask = SIZE_OR_MASK_BITS(phys_addr); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7ecedafa1c8..2c8522a39ed5 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,8 +72,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) c->x86_model, c->x86_model_id[0] ? c->x86_model_id : "unknown"); - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_stepping); else seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) @@ -91,8 +91,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c29020907886..b59e4fb40fd9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -37,7 +37,7 @@ #define X86 new_cpu_data+CPUINFO_x86 #define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor #define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping #define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math #define X86_CPUID new_cpu_data+CPUINFO_cpuid_level #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability @@ -332,7 +332,7 @@ ENTRY(startup_32_smp) shrb $4,%al movb %al,X86_MODEL andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK + movb %cl,X86_STEPPING movl %edx,X86_CAPABILITY .Lis486: diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 27d0a1712663..f1c5eb99d445 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -410,7 +410,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01; processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping; processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 041096bdef86..99dc79e76bdc 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -200,9 +200,9 @@ static void native_flush_tlb_global(void) __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static void native_flush_tlb_one_user(unsigned long addr) { - __native_flush_tlb_single(addr); + __native_flush_tlb_one_user(addr); } struct static_key paravirt_steal_enabled; @@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_single = native_flush_tlb_single, + .flush_tlb_one_user = native_flush_tlb_one_user, .flush_tlb_others = native_flush_tlb_others, .pgd_alloc = __paravirt_pgd_alloc, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27facbaa9b..9eee25d07586 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void) cpu_set_state_online(me); } -void __init native_smp_cpus_done(unsigned int max_cpus) +void __init calculate_max_logical_packages(void) { int ncpus; - pr_debug("Boot done\n"); /* * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. @@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus) ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); +} + +void __init native_smp_cpus_done(unsigned int max_cpus) +{ + pr_debug("Boot done\n"); + + calculate_max_logical_packages(); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); @@ -1430,7 +1436,6 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 446c9ef8cfc3..3d9b2308e7fa 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -181,7 +181,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr) break; case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD0; + regs->ip += LEN_UD2; return 1; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eca1d04aeb8..46ff304140c7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5080,7 +5080,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -5110,7 +5110,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -5121,7 +5121,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5129,7 +5129,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5137,7 +5137,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f427723dc7db..3dec126aa302 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10136,7 +10136,10 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); } - if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); + else vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); } @@ -10224,8 +10227,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * updated to reflect this when L1 (or its L2s) actually write to * the MSR. */ - bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); - bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index d6f848d1211d..2dd1fe13a37b 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -18,7 +18,7 @@ unsigned int x86_model(unsigned int sig) { unsigned int fam, model; - fam = x86_family(sig); + fam = x86_family(sig); model = (sig >> 4) & 0xf; diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 7b881d03d0dd..3cdf06128d13 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -7,6 +7,7 @@ asmlinkage void just_return_func(void); asm( ".type just_return_func, @function\n" + ".globl just_return_func\n" "just_return_func:\n" " ret\n" ".size just_return_func, .-just_return_func\n" diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 1ab42c852069..8b72923f1d35 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -256,7 +256,7 @@ static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) @@ -1193,8 +1193,8 @@ void __init mem_init(void) register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, - PAGE_SIZE, KCORE_OTHER); + if (get_gate_vma(&init_mm)) + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); mem_init_print_info(NULL); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index c45b6ec5357b..e2db83bebc3b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -820,5 +820,5 @@ void __init __early_set_fixmap(enum fixed_addresses idx, set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else pte_clear(&init_mm, addr, pte); - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 58477ec3d66d..7c8686709636 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -168,7 +168,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->addr); + __flush_tlb_one_kernel(f->addr); return 0; } diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index c3c5274410a9..9bb7f0ab9fe6 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -63,7 +63,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } unsigned long __FIXADDR_TOP = 0xfffff000; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8dcc0607f805..7f1a51399674 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -498,7 +498,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * flush that changes context.tlb_gen from 2 to 3. If they get * processed on this CPU in reverse order, we'll see * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. - * If we were to use __flush_tlb_single() and set local_tlb_gen to + * If we were to use __flush_tlb_one_user() and set local_tlb_gen to * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * @@ -519,7 +519,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, addr = f->start; while (addr < f->end) { - __flush_tlb_single(addr); + __flush_tlb_one_user(addr); addr += PAGE_SIZE; } if (local) @@ -666,7 +666,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index c2e9285d1bf1..db77e087adaf 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_single(msg->address); + __flush_tlb_one_user(msg->address); stat->d_onetlb++; } stat->d_requestee++; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index d85076223a69..aae88fec9941 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1300,12 +1300,12 @@ static void xen_flush_tlb(void) preempt_enable(); } -static void xen_flush_tlb_single(unsigned long addr) +static void xen_flush_tlb_one_user(unsigned long addr) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_single(addr); + trace_xen_mmu_flush_tlb_one_user(addr); preempt_disable(); @@ -2370,7 +2370,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_one_user = xen_flush_tlb_one_user, .flush_tlb_others = xen_flush_tlb_others, .pgd_alloc = xen_pgd_alloc, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 77c959cf81e7..7a43b2ae19f1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); + else + calculate_max_logical_packages(); if (xen_have_vcpu_info_placement) return; diff --git a/block/blk-mq.c b/block/blk-mq.c index df93102e2149..357492712b0e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3164,6 +3164,7 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) cpu_relax(); } + __set_current_state(TASK_RUNNING); return false; } diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index a965b9d80559..ded148783303 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -20,6 +20,20 @@ #include <crypto/sha3.h> #include <asm/unaligned.h> +/* + * On some 32-bit architectures (mn10300 and h8300), GCC ends up using + * over 1 KB of stack if we inline the round calculation into the loop + * in keccakf(). On the other hand, on 64-bit architectures with plenty + * of [64-bit wide] general purpose registers, not inlining it severely + * hurts performance. So let's use 64-bitness as a heuristic to decide + * whether to inline or not. + */ +#ifdef CONFIG_64BIT +#define SHA3_INLINE inline +#else +#define SHA3_INLINE noinline +#endif + #define KECCAK_ROUNDS 24 static const u64 keccakf_rndc[24] = { @@ -35,111 +49,115 @@ static const u64 keccakf_rndc[24] = { /* update the state with given number of rounds */ -static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25]) +static SHA3_INLINE void keccakf_round(u64 st[25]) { u64 t[5], tt, bc[5]; - int round; - for (round = 0; round < KECCAK_ROUNDS; round++) { + /* Theta */ + bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20]; + bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21]; + bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22]; + bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23]; + bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24]; + + t[0] = bc[4] ^ rol64(bc[1], 1); + t[1] = bc[0] ^ rol64(bc[2], 1); + t[2] = bc[1] ^ rol64(bc[3], 1); + t[3] = bc[2] ^ rol64(bc[4], 1); + t[4] = bc[3] ^ rol64(bc[0], 1); + + st[0] ^= t[0]; + + /* Rho Pi */ + tt = st[1]; + st[ 1] = rol64(st[ 6] ^ t[1], 44); + st[ 6] = rol64(st[ 9] ^ t[4], 20); + st[ 9] = rol64(st[22] ^ t[2], 61); + st[22] = rol64(st[14] ^ t[4], 39); + st[14] = rol64(st[20] ^ t[0], 18); + st[20] = rol64(st[ 2] ^ t[2], 62); + st[ 2] = rol64(st[12] ^ t[2], 43); + st[12] = rol64(st[13] ^ t[3], 25); + st[13] = rol64(st[19] ^ t[4], 8); + st[19] = rol64(st[23] ^ t[3], 56); + st[23] = rol64(st[15] ^ t[0], 41); + st[15] = rol64(st[ 4] ^ t[4], 27); + st[ 4] = rol64(st[24] ^ t[4], 14); + st[24] = rol64(st[21] ^ t[1], 2); + st[21] = rol64(st[ 8] ^ t[3], 55); + st[ 8] = rol64(st[16] ^ t[1], 45); + st[16] = rol64(st[ 5] ^ t[0], 36); + st[ 5] = rol64(st[ 3] ^ t[3], 28); + st[ 3] = rol64(st[18] ^ t[3], 21); + st[18] = rol64(st[17] ^ t[2], 15); + st[17] = rol64(st[11] ^ t[1], 10); + st[11] = rol64(st[ 7] ^ t[2], 6); + st[ 7] = rol64(st[10] ^ t[0], 3); + st[10] = rol64( tt ^ t[1], 1); + + /* Chi */ + bc[ 0] = ~st[ 1] & st[ 2]; + bc[ 1] = ~st[ 2] & st[ 3]; + bc[ 2] = ~st[ 3] & st[ 4]; + bc[ 3] = ~st[ 4] & st[ 0]; + bc[ 4] = ~st[ 0] & st[ 1]; + st[ 0] ^= bc[ 0]; + st[ 1] ^= bc[ 1]; + st[ 2] ^= bc[ 2]; + st[ 3] ^= bc[ 3]; + st[ 4] ^= bc[ 4]; + + bc[ 0] = ~st[ 6] & st[ 7]; + bc[ 1] = ~st[ 7] & st[ 8]; + bc[ 2] = ~st[ 8] & st[ 9]; + bc[ 3] = ~st[ 9] & st[ 5]; + bc[ 4] = ~st[ 5] & st[ 6]; + st[ 5] ^= bc[ 0]; + st[ 6] ^= bc[ 1]; + st[ 7] ^= bc[ 2]; + st[ 8] ^= bc[ 3]; + st[ 9] ^= bc[ 4]; + + bc[ 0] = ~st[11] & st[12]; + bc[ 1] = ~st[12] & st[13]; + bc[ 2] = ~st[13] & st[14]; + bc[ 3] = ~st[14] & st[10]; + bc[ 4] = ~st[10] & st[11]; + st[10] ^= bc[ 0]; + st[11] ^= bc[ 1]; + st[12] ^= bc[ 2]; + st[13] ^= bc[ 3]; + st[14] ^= bc[ 4]; + + bc[ 0] = ~st[16] & st[17]; + bc[ 1] = ~st[17] & st[18]; + bc[ 2] = ~st[18] & st[19]; + bc[ 3] = ~st[19] & st[15]; + bc[ 4] = ~st[15] & st[16]; + st[15] ^= bc[ 0]; + st[16] ^= bc[ 1]; + st[17] ^= bc[ 2]; + st[18] ^= bc[ 3]; + st[19] ^= bc[ 4]; + + bc[ 0] = ~st[21] & st[22]; + bc[ 1] = ~st[22] & st[23]; + bc[ 2] = ~st[23] & st[24]; + bc[ 3] = ~st[24] & st[20]; + bc[ 4] = ~st[20] & st[21]; + st[20] ^= bc[ 0]; + st[21] ^= bc[ 1]; + st[22] ^= bc[ 2]; + st[23] ^= bc[ 3]; + st[24] ^= bc[ 4]; +} - /* Theta */ - bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20]; - bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21]; - bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22]; - bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23]; - bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24]; - - t[0] = bc[4] ^ rol64(bc[1], 1); - t[1] = bc[0] ^ rol64(bc[2], 1); - t[2] = bc[1] ^ rol64(bc[3], 1); - t[3] = bc[2] ^ rol64(bc[4], 1); - t[4] = bc[3] ^ rol64(bc[0], 1); - - st[0] ^= t[0]; - - /* Rho Pi */ - tt = st[1]; - st[ 1] = rol64(st[ 6] ^ t[1], 44); - st[ 6] = rol64(st[ 9] ^ t[4], 20); - st[ 9] = rol64(st[22] ^ t[2], 61); - st[22] = rol64(st[14] ^ t[4], 39); - st[14] = rol64(st[20] ^ t[0], 18); - st[20] = rol64(st[ 2] ^ t[2], 62); - st[ 2] = rol64(st[12] ^ t[2], 43); - st[12] = rol64(st[13] ^ t[3], 25); - st[13] = rol64(st[19] ^ t[4], 8); - st[19] = rol64(st[23] ^ t[3], 56); - st[23] = rol64(st[15] ^ t[0], 41); - st[15] = rol64(st[ 4] ^ t[4], 27); - st[ 4] = rol64(st[24] ^ t[4], 14); - st[24] = rol64(st[21] ^ t[1], 2); - st[21] = rol64(st[ 8] ^ t[3], 55); - st[ 8] = rol64(st[16] ^ t[1], 45); - st[16] = rol64(st[ 5] ^ t[0], 36); - st[ 5] = rol64(st[ 3] ^ t[3], 28); - st[ 3] = rol64(st[18] ^ t[3], 21); - st[18] = rol64(st[17] ^ t[2], 15); - st[17] = rol64(st[11] ^ t[1], 10); - st[11] = rol64(st[ 7] ^ t[2], 6); - st[ 7] = rol64(st[10] ^ t[0], 3); - st[10] = rol64( tt ^ t[1], 1); - - /* Chi */ - bc[ 0] = ~st[ 1] & st[ 2]; - bc[ 1] = ~st[ 2] & st[ 3]; - bc[ 2] = ~st[ 3] & st[ 4]; - bc[ 3] = ~st[ 4] & st[ 0]; - bc[ 4] = ~st[ 0] & st[ 1]; - st[ 0] ^= bc[ 0]; - st[ 1] ^= bc[ 1]; - st[ 2] ^= bc[ 2]; - st[ 3] ^= bc[ 3]; - st[ 4] ^= bc[ 4]; - - bc[ 0] = ~st[ 6] & st[ 7]; - bc[ 1] = ~st[ 7] & st[ 8]; - bc[ 2] = ~st[ 8] & st[ 9]; - bc[ 3] = ~st[ 9] & st[ 5]; - bc[ 4] = ~st[ 5] & st[ 6]; - st[ 5] ^= bc[ 0]; - st[ 6] ^= bc[ 1]; - st[ 7] ^= bc[ 2]; - st[ 8] ^= bc[ 3]; - st[ 9] ^= bc[ 4]; - - bc[ 0] = ~st[11] & st[12]; - bc[ 1] = ~st[12] & st[13]; - bc[ 2] = ~st[13] & st[14]; - bc[ 3] = ~st[14] & st[10]; - bc[ 4] = ~st[10] & st[11]; - st[10] ^= bc[ 0]; - st[11] ^= bc[ 1]; - st[12] ^= bc[ 2]; - st[13] ^= bc[ 3]; - st[14] ^= bc[ 4]; - - bc[ 0] = ~st[16] & st[17]; - bc[ 1] = ~st[17] & st[18]; - bc[ 2] = ~st[18] & st[19]; - bc[ 3] = ~st[19] & st[15]; - bc[ 4] = ~st[15] & st[16]; - st[15] ^= bc[ 0]; - st[16] ^= bc[ 1]; - st[17] ^= bc[ 2]; - st[18] ^= bc[ 3]; - st[19] ^= bc[ 4]; - - bc[ 0] = ~st[21] & st[22]; - bc[ 1] = ~st[22] & st[23]; - bc[ 2] = ~st[23] & st[24]; - bc[ 3] = ~st[24] & st[20]; - bc[ 4] = ~st[20] & st[21]; - st[20] ^= bc[ 0]; - st[21] ^= bc[ 1]; - st[22] ^= bc[ 2]; - st[23] ^= bc[ 3]; - st[24] ^= bc[ 4]; +static void __optimize("O3") keccakf(u64 st[25]) +{ + int round; + for (round = 0; round < KECCAK_ROUNDS; round++) { + keccakf_round(st); /* Iota */ st[0] ^= keccakf_rndc[round]; } diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 676c9788e1c8..0dad0bd9327b 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -660,13 +660,15 @@ struct acpi_device *acpi_companion_match(const struct device *dev) * acpi_of_match_device - Match device object using the "compatible" property. * @adev: ACPI device object to match. * @of_match_table: List of device IDs to match against. + * @of_id: OF ID if matched * * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of * identifiers and a _DSD object with the "compatible" property, use that * property to match against the given list of identifiers. */ static bool acpi_of_match_device(struct acpi_device *adev, - const struct of_device_id *of_match_table) + const struct of_device_id *of_match_table, + const struct of_device_id **of_id) { const union acpi_object *of_compatible, *obj; int i, nval; @@ -690,8 +692,11 @@ static bool acpi_of_match_device(struct acpi_device *adev, const struct of_device_id *id; for (id = of_match_table; id->compatible[0]; id++) - if (!strcasecmp(obj->string.pointer, id->compatible)) + if (!strcasecmp(obj->string.pointer, id->compatible)) { + if (of_id) + *of_id = id; return true; + } } return false; @@ -762,10 +767,11 @@ static bool __acpi_match_device_cls(const struct acpi_device_id *id, return true; } -static const struct acpi_device_id *__acpi_match_device( - struct acpi_device *device, - const struct acpi_device_id *ids, - const struct of_device_id *of_ids) +static bool __acpi_match_device(struct acpi_device *device, + const struct acpi_device_id *acpi_ids, + const struct of_device_id *of_ids, + const struct acpi_device_id **acpi_id, + const struct of_device_id **of_id) { const struct acpi_device_id *id; struct acpi_hardware_id *hwid; @@ -775,30 +781,32 @@ static const struct acpi_device_id *__acpi_match_device( * driver for it. */ if (!device || !device->status.present) - return NULL; + return false; list_for_each_entry(hwid, &device->pnp.ids, list) { /* First, check the ACPI/PNP IDs provided by the caller. */ - for (id = ids; id->id[0] || id->cls; id++) { - if (id->id[0] && !strcmp((char *) id->id, hwid->id)) - return id; - else if (id->cls && __acpi_match_device_cls(id, hwid)) - return id; + if (acpi_ids) { + for (id = acpi_ids; id->id[0] || id->cls; id++) { + if (id->id[0] && !strcmp((char *)id->id, hwid->id)) + goto out_acpi_match; + if (id->cls && __acpi_match_device_cls(id, hwid)) + goto out_acpi_match; + } } /* * Next, check ACPI_DT_NAMESPACE_HID and try to match the * "compatible" property if found. - * - * The id returned by the below is not valid, but the only - * caller passing non-NULL of_ids here is only interested in - * whether or not the return value is NULL. */ - if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id) - && acpi_of_match_device(device, of_ids)) - return id; + if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)) + return acpi_of_match_device(device, of_ids, of_id); } - return NULL; + return false; + +out_acpi_match: + if (acpi_id) + *acpi_id = id; + return true; } /** @@ -815,32 +823,29 @@ static const struct acpi_device_id *__acpi_match_device( const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev) { - return __acpi_match_device(acpi_companion_match(dev), ids, NULL); + const struct acpi_device_id *id = NULL; + + __acpi_match_device(acpi_companion_match(dev), ids, NULL, &id, NULL); + return id; } EXPORT_SYMBOL_GPL(acpi_match_device); -void *acpi_get_match_data(const struct device *dev) +const void *acpi_device_get_match_data(const struct device *dev) { const struct acpi_device_id *match; - if (!dev->driver) - return NULL; - - if (!dev->driver->acpi_match_table) - return NULL; - match = acpi_match_device(dev->driver->acpi_match_table, dev); if (!match) return NULL; - return (void *)match->driver_data; + return (const void *)match->driver_data; } -EXPORT_SYMBOL_GPL(acpi_get_match_data); +EXPORT_SYMBOL_GPL(acpi_device_get_match_data); int acpi_match_device_ids(struct acpi_device *device, const struct acpi_device_id *ids) { - return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT; + return __acpi_match_device(device, ids, NULL, NULL, NULL) ? 0 : -ENOENT; } EXPORT_SYMBOL(acpi_match_device_ids); @@ -849,10 +854,12 @@ bool acpi_driver_match_device(struct device *dev, { if (!drv->acpi_match_table) return acpi_of_match_device(ACPI_COMPANION(dev), - drv->of_match_table); + drv->of_match_table, + NULL); - return !!__acpi_match_device(acpi_companion_match(dev), - drv->acpi_match_table, drv->of_match_table); + return __acpi_match_device(acpi_companion_match(dev), + drv->acpi_match_table, drv->of_match_table, + NULL, NULL); } EXPORT_SYMBOL_GPL(acpi_driver_match_device); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d9f38c645e4a..30a572956557 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1927,6 +1927,9 @@ static int acpi_ec_suspend_noirq(struct device *dev) ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); + if (acpi_sleep_no_ec_events()) + acpi_ec_enter_noirq(ec); + return 0; } @@ -1934,6 +1937,9 @@ static int acpi_ec_resume_noirq(struct device *dev) { struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev)); + if (acpi_sleep_no_ec_events()) + acpi_ec_leave_noirq(ec); + if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 466d1503aba0..5815356ea6ad 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1271,11 +1271,11 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, return 0; } -static void * +static const void * acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { - return acpi_get_match_data(dev); + return acpi_device_get_match_data(dev); } #define DECLARE_ACPI_FWNODE_OPS(ops) \ diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index 89e97d21a89c..9d52743080a4 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -115,6 +115,7 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console) table->serial_port.access_width))) { default: pr_err("Unexpected SPCR Access Width. Defaulting to byte size\n"); + /* fall through */ case 8: iotype = "mmio"; break; diff --git a/drivers/base/core.c b/drivers/base/core.c index b2261f92f2f1..5847364f25d9 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -310,6 +310,9 @@ static void __device_link_del(struct device_link *link) dev_info(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); + if (link->flags & DL_FLAG_PM_RUNTIME) + pm_runtime_drop_link(link->consumer); + list_del(&link->s_node); list_del(&link->c_node); device_link_free(link); diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index a8ac86e4d79e..6637fc319269 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -321,7 +321,8 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq) return; if (device_may_wakeup(wirq->dev)) { - if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED && + !pm_runtime_status_suspended(wirq->dev)) enable_irq(wirq->irq); enable_irq_wake(wirq->irq); @@ -343,7 +344,8 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq) if (device_may_wakeup(wirq->dev)) { disable_irq_wake(wirq->irq); - if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED && + !pm_runtime_status_suspended(wirq->dev)) disable_irq_nosync(wirq->irq); } } diff --git a/drivers/base/property.c b/drivers/base/property.c index 302236281d83..8f205f6461ed 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -1410,9 +1410,8 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, } EXPORT_SYMBOL(fwnode_graph_parse_endpoint); -void *device_get_match_data(struct device *dev) +const void *device_get_match_data(struct device *dev) { - return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, - dev); + return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev); } EXPORT_SYMBOL_GPL(device_get_match_data); diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c index d1f5bb534e0e..6e9df558325b 100644 --- a/drivers/char/hw_random/via-rng.c +++ b/drivers/char/hw_random/via-rng.c @@ -162,7 +162,7 @@ static int via_rng_init(struct hwrng *rng) /* Enable secondary noise source on CPUs where it is present. */ /* Nehemiah stepping 8 and higher */ - if ((c->x86_model == 9) && (c->x86_mask > 7)) + if ((c->x86_model == 9) && (c->x86_stepping > 7)) lo |= VIA_NOISESRC2; /* Esther */ diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 3a2ca0f79daf..d0c34df0529c 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -629,7 +629,7 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c) if (c->x86_vendor == X86_VENDOR_INTEL) { if ((c->x86 == 15) && (c->x86_model == 6) && - (c->x86_mask == 8)) { + (c->x86_stepping == 8)) { pr_info("Intel(R) Xeon(R) 7100 Errata AL30, processors may lock up on frequency changes: disabling acpi-cpufreq\n"); return -ENODEV; } diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 942632a27b50..f730b6528c18 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -775,7 +775,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) break; case 7: - switch (c->x86_mask) { + switch (c->x86_stepping) { case 0: longhaul_version = TYPE_LONGHAUL_V1; cpu_model = CPU_SAMUEL2; @@ -787,7 +787,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) break; case 1 ... 15: longhaul_version = TYPE_LONGHAUL_V2; - if (c->x86_mask < 8) { + if (c->x86_stepping < 8) { cpu_model = CPU_SAMUEL2; cpuname = "C3 'Samuel 2' [C5B]"; } else { @@ -814,7 +814,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) numscales = 32; memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults)); memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr)); - switch (c->x86_mask) { + switch (c->x86_stepping) { case 0 ... 1: cpu_model = CPU_NEHEMIAH; cpuname = "C3 'Nehemiah A' [C5XLOE]"; diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c index fd77812313f3..a25741b1281b 100644 --- a/drivers/cpufreq/p4-clockmod.c +++ b/drivers/cpufreq/p4-clockmod.c @@ -168,7 +168,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) #endif /* Errata workaround */ - cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_mask; + cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_stepping; switch (cpuid) { case 0x0f07: case 0x0f0a: diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index 80ac313e6c59..302e9ce793a0 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -131,7 +131,7 @@ static int check_powernow(void) return 0; } - if ((c->x86_model == 6) && (c->x86_mask == 0)) { + if ((c->x86_model == 6) && (c->x86_stepping == 0)) { pr_info("K7 660[A0] core detected, enabling errata workarounds\n"); have_a0 = 1; } diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c index 41bc5397f4bb..4fa5adf16c70 100644 --- a/drivers/cpufreq/speedstep-centrino.c +++ b/drivers/cpufreq/speedstep-centrino.c @@ -37,7 +37,7 @@ struct cpu_id { __u8 x86; /* CPU family */ __u8 x86_model; /* model */ - __u8 x86_mask; /* stepping */ + __u8 x86_stepping; /* stepping */ }; enum { @@ -277,7 +277,7 @@ static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c, { if ((c->x86 == x->x86) && (c->x86_model == x->x86_model) && - (c->x86_mask == x->x86_mask)) + (c->x86_stepping == x->x86_stepping)) return 1; return 0; } diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c index 8085ec9000d1..e3a9962ee410 100644 --- a/drivers/cpufreq/speedstep-lib.c +++ b/drivers/cpufreq/speedstep-lib.c @@ -272,9 +272,9 @@ unsigned int speedstep_detect_processor(void) ebx = cpuid_ebx(0x00000001); ebx &= 0x000000FF; - pr_debug("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask); + pr_debug("ebx value is %x, x86_stepping is %x\n", ebx, c->x86_stepping); - switch (c->x86_mask) { + switch (c->x86_stepping) { case 4: /* * B-stepping [M-P4-M] @@ -361,7 +361,7 @@ unsigned int speedstep_detect_processor(void) msr_lo, msr_hi); if ((msr_hi & (1<<18)) && (relaxed_check ? 1 : (msr_hi & (3<<24)))) { - if (c->x86_mask == 0x01) { + if (c->x86_stepping == 0x01) { pr_debug("early PIII version\n"); return SPEEDSTEP_CPU_PIII_C_EARLY; } else diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 75d280cb2dc0..e843cf410373 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -228,12 +228,16 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask, * without any error (HW optimizations for later * CAAM eras), then try again. */ + if (ret) + break; + rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK; if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) || - !(rdsta_val & (1 << sh_idx))) + !(rdsta_val & (1 << sh_idx))) { ret = -EAGAIN; - if (ret) break; + } + dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx); /* Clear the contents before recreating the descriptor */ memset(desc, 0x00, CAAM_CMD_SZ * 7); diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 4b6642a25df5..1c6cbda56afe 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -512,7 +512,7 @@ static int __init padlock_init(void) printk(KERN_NOTICE PFX "Using VIA PadLock ACE for AES algorithm.\n"); - if (c->x86 == 6 && c->x86_model == 15 && c->x86_mask == 2) { + if (c->x86 == 6 && c->x86_model == 15 && c->x86_stepping == 2) { ecb_fetch_blocks = MAX_ECB_FETCH_BLOCKS; cbc_fetch_blocks = MAX_CBC_FETCH_BLOCKS; printk(KERN_NOTICE PFX "VIA Nano stepping 2 detected: enabling workaround.\n"); diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c index 0d01d1624252..63d636424161 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c @@ -28,7 +28,7 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng); ss = algt->ss; - spin_lock(&ss->slock); + spin_lock_bh(&ss->slock); writel(mode, ss->base + SS_CTL); @@ -51,6 +51,6 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, } writel(0, ss->base + SS_CTL); - spin_unlock(&ss->slock); - return dlen; + spin_unlock_bh(&ss->slock); + return 0; } diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 9c80e0cb1664..6882fa2f8bad 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1138,6 +1138,10 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src, struct talitos_private *priv = dev_get_drvdata(dev); bool is_sec1 = has_ftr_sec1(priv); + if (!src) { + to_talitos_ptr(ptr, 0, 0, is_sec1); + return 1; + } if (sg_count == 1) { to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1); return sg_count; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 8b16ec595fa7..329cb96f886f 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3147,7 +3147,7 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) struct amd64_family_type *fam_type = NULL; pvt->ext_model = boot_cpu_data.x86_model >> 4; - pvt->stepping = boot_cpu_data.x86_mask; + pvt->stepping = boot_cpu_data.x86_stepping; pvt->model = boot_cpu_data.x86_model; pvt->fam = boot_cpu_data.x86; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index e2c3c5ec42d1..c53095b3b0fb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -568,6 +568,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = { /* HG _PR3 doesn't seem to work on this A+A weston board */ { 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 909499b73d03..021f722e2481 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -733,6 +733,25 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf, return ret == 0 ? count : ret; } +static bool gtt_entry(struct mdev_device *mdev, loff_t *ppos) +{ + struct intel_vgpu *vgpu = mdev_get_drvdata(mdev); + unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + struct intel_gvt *gvt = vgpu->gvt; + int offset; + + /* Only allow MMIO GGTT entry access */ + if (index != PCI_BASE_ADDRESS_0) + return false; + + offset = (u64)(*ppos & VFIO_PCI_OFFSET_MASK) - + intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_0); + + return (offset >= gvt->device_info.gtt_start_offset && + offset < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt)) ? + true : false; +} + static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf, size_t count, loff_t *ppos) { @@ -742,7 +761,21 @@ static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf, while (count) { size_t filled; - if (count >= 4 && !(*ppos % 4)) { + /* Only support GGTT entry 8 bytes read */ + if (count >= 8 && !(*ppos % 8) && + gtt_entry(mdev, ppos)) { + u64 val; + + ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val), + ppos, false); + if (ret <= 0) + goto read_err; + + if (copy_to_user(buf, &val, sizeof(val))) + goto read_err; + + filled = 8; + } else if (count >= 4 && !(*ppos % 4)) { u32 val; ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val), @@ -802,7 +835,21 @@ static ssize_t intel_vgpu_write(struct mdev_device *mdev, while (count) { size_t filled; - if (count >= 4 && !(*ppos % 4)) { + /* Only support GGTT entry 8 bytes write */ + if (count >= 8 && !(*ppos % 8) && + gtt_entry(mdev, ppos)) { + u64 val; + + if (copy_from_user(&val, buf, sizeof(val))) + goto write_err; + + ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val), + ppos, true); + if (ret <= 0) + goto write_err; + + filled = 8; + } else if (count >= 4 && !(*ppos % 4)) { u32 val; if (copy_from_user(&val, buf, sizeof(val))) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 73ad6e90e49d..256f1bb522b7 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -118,6 +118,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */ {RCS, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */ {RCS, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */ + {RCS, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */ {RCS, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */ {RCS, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */ {RCS, TRNULLDETCT, 0, false}, /* 0x4de8 */ diff --git a/drivers/gpu/drm/i915/gvt/trace.h b/drivers/gpu/drm/i915/gvt/trace.h index 7a2511538f34..736bd2bc5127 100644 --- a/drivers/gpu/drm/i915/gvt/trace.h +++ b/drivers/gpu/drm/i915/gvt/trace.h @@ -333,7 +333,7 @@ TRACE_EVENT(render_mmio, TP_PROTO(int old_id, int new_id, char *action, unsigned int reg, unsigned int old_val, unsigned int new_val), - TP_ARGS(old_id, new_id, action, reg, new_val, old_val), + TP_ARGS(old_id, new_id, action, reg, old_val, new_val), TP_STRUCT__entry( __field(int, old_id) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 173d0095e3b2..2f5209de0391 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1433,19 +1433,7 @@ void i915_driver_unload(struct drm_device *dev) intel_modeset_cleanup(dev); - /* - * free the memory space allocated for the child device - * config parsed from VBT - */ - if (dev_priv->vbt.child_dev && dev_priv->vbt.child_dev_num) { - kfree(dev_priv->vbt.child_dev); - dev_priv->vbt.child_dev = NULL; - dev_priv->vbt.child_dev_num = 0; - } - kfree(dev_priv->vbt.sdvo_lvds_vbt_mode); - dev_priv->vbt.sdvo_lvds_vbt_mode = NULL; - kfree(dev_priv->vbt.lfp_lvds_vbt_mode); - dev_priv->vbt.lfp_lvds_vbt_mode = NULL; + intel_bios_cleanup(dev_priv); vga_switcheroo_unregister_client(pdev); vga_client_register(pdev, NULL, NULL, NULL); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index a42deebedb0f..d307429a5ae0 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1349,6 +1349,7 @@ struct intel_vbt_data { u32 size; u8 *data; const u8 *sequence[MIPI_SEQ_MAX]; + u8 *deassert_seq; /* Used by fixup_mipi_sequences() */ } dsi; int crt_ddc_pin; @@ -3657,6 +3658,7 @@ extern void intel_i2c_reset(struct drm_i915_private *dev_priv); /* intel_bios.c */ void intel_bios_init(struct drm_i915_private *dev_priv); +void intel_bios_cleanup(struct drm_i915_private *dev_priv); bool intel_bios_is_valid_vbt(const void *buf, size_t size); bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv); bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 648e7536ff51..0c963fcf31ff 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -803,7 +803,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data, case I915_CONTEXT_PARAM_PRIORITY: { - int priority = args->value; + s64 priority = args->value; if (args->size) ret = -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_oa_cflgt3.c b/drivers/gpu/drm/i915/i915_oa_cflgt3.c index 42ff06fe54a3..792facdb6702 100644 --- a/drivers/gpu/drm/i915/i915_oa_cflgt3.c +++ b/drivers/gpu/drm/i915/i915_oa_cflgt3.c @@ -84,9 +84,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) void i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv) { - strncpy(dev_priv->perf.oa.test_config.uuid, + strlcpy(dev_priv->perf.oa.test_config.uuid, "577e8e2c-3fa0-4875-8743-3538d585e3b0", - UUID_STRING_LEN); + sizeof(dev_priv->perf.oa.test_config.uuid)); dev_priv->perf.oa.test_config.id = 1; dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa; diff --git a/drivers/gpu/drm/i915/i915_oa_cnl.c b/drivers/gpu/drm/i915/i915_oa_cnl.c index ff0ac3627cc4..ba9140c87cc0 100644 --- a/drivers/gpu/drm/i915/i915_oa_cnl.c +++ b/drivers/gpu/drm/i915/i915_oa_cnl.c @@ -96,9 +96,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf) void i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv) { - strncpy(dev_priv->perf.oa.test_config.uuid, + strlcpy(dev_priv->perf.oa.test_config.uuid, "db41edd4-d8e7-4730-ad11-b9a2d6833503", - UUID_STRING_LEN); + sizeof(dev_priv->perf.oa.test_config.uuid)); dev_priv->perf.oa.test_config.id = 1; dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa; diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 55a8a1e29424..0e9b98c32b62 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -285,26 +285,41 @@ static u64 count_interrupts(struct drm_i915_private *i915) return sum; } -static void i915_pmu_event_destroy(struct perf_event *event) +static void engine_event_destroy(struct perf_event *event) { - WARN_ON(event->parent); + struct drm_i915_private *i915 = + container_of(event->pmu, typeof(*i915), pmu.base); + struct intel_engine_cs *engine; + + engine = intel_engine_lookup_user(i915, + engine_event_class(event), + engine_event_instance(event)); + if (WARN_ON_ONCE(!engine)) + return; + + if (engine_event_sample(event) == I915_SAMPLE_BUSY && + intel_engine_supports_stats(engine)) + intel_disable_engine_stats(engine); } -static int engine_event_init(struct perf_event *event) +static void i915_pmu_event_destroy(struct perf_event *event) { - struct drm_i915_private *i915 = - container_of(event->pmu, typeof(*i915), pmu.base); + WARN_ON(event->parent); - if (!intel_engine_lookup_user(i915, engine_event_class(event), - engine_event_instance(event))) - return -ENODEV; + if (is_engine_event(event)) + engine_event_destroy(event); +} - switch (engine_event_sample(event)) { +static int +engine_event_status(struct intel_engine_cs *engine, + enum drm_i915_pmu_engine_sample sample) +{ + switch (sample) { case I915_SAMPLE_BUSY: case I915_SAMPLE_WAIT: break; case I915_SAMPLE_SEMA: - if (INTEL_GEN(i915) < 6) + if (INTEL_GEN(engine->i915) < 6) return -ENODEV; break; default: @@ -314,6 +329,30 @@ static int engine_event_init(struct perf_event *event) return 0; } +static int engine_event_init(struct perf_event *event) +{ + struct drm_i915_private *i915 = + container_of(event->pmu, typeof(*i915), pmu.base); + struct intel_engine_cs *engine; + u8 sample; + int ret; + + engine = intel_engine_lookup_user(i915, engine_event_class(event), + engine_event_instance(event)); + if (!engine) + return -ENODEV; + + sample = engine_event_sample(event); + ret = engine_event_status(engine, sample); + if (ret) + return ret; + + if (sample == I915_SAMPLE_BUSY && intel_engine_supports_stats(engine)) + ret = intel_enable_engine_stats(engine); + + return ret; +} + static int i915_pmu_event_init(struct perf_event *event) { struct drm_i915_private *i915 = @@ -370,7 +409,94 @@ static int i915_pmu_event_init(struct perf_event *event) return 0; } -static u64 __i915_pmu_event_read(struct perf_event *event) +static u64 __get_rc6(struct drm_i915_private *i915) +{ + u64 val; + + val = intel_rc6_residency_ns(i915, + IS_VALLEYVIEW(i915) ? + VLV_GT_RENDER_RC6 : + GEN6_GT_GFX_RC6); + + if (HAS_RC6p(i915)) + val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p); + + if (HAS_RC6pp(i915)) + val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp); + + return val; +} + +static u64 get_rc6(struct drm_i915_private *i915, bool locked) +{ +#if IS_ENABLED(CONFIG_PM) + unsigned long flags; + u64 val; + + if (intel_runtime_pm_get_if_in_use(i915)) { + val = __get_rc6(i915); + intel_runtime_pm_put(i915); + + /* + * If we are coming back from being runtime suspended we must + * be careful not to report a larger value than returned + * previously. + */ + + if (!locked) + spin_lock_irqsave(&i915->pmu.lock, flags); + + if (val >= i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) { + i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0; + i915->pmu.sample[__I915_SAMPLE_RC6].cur = val; + } else { + val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur; + } + + if (!locked) + spin_unlock_irqrestore(&i915->pmu.lock, flags); + } else { + struct pci_dev *pdev = i915->drm.pdev; + struct device *kdev = &pdev->dev; + unsigned long flags2; + + /* + * We are runtime suspended. + * + * Report the delta from when the device was suspended to now, + * on top of the last known real value, as the approximated RC6 + * counter value. + */ + if (!locked) + spin_lock_irqsave(&i915->pmu.lock, flags); + + spin_lock_irqsave(&kdev->power.lock, flags2); + + if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) + i915->pmu.suspended_jiffies_last = + kdev->power.suspended_jiffies; + + val = kdev->power.suspended_jiffies - + i915->pmu.suspended_jiffies_last; + val += jiffies - kdev->power.accounting_timestamp; + + spin_unlock_irqrestore(&kdev->power.lock, flags2); + + val = jiffies_to_nsecs(val); + val += i915->pmu.sample[__I915_SAMPLE_RC6].cur; + i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val; + + if (!locked) + spin_unlock_irqrestore(&i915->pmu.lock, flags); + } + + return val; +#else + return __get_rc6(i915); +#endif +} + +static u64 __i915_pmu_event_read(struct perf_event *event, bool locked) { struct drm_i915_private *i915 = container_of(event->pmu, typeof(*i915), pmu.base); @@ -387,7 +513,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event) if (WARN_ON_ONCE(!engine)) { /* Do nothing */ } else if (sample == I915_SAMPLE_BUSY && - engine->pmu.busy_stats) { + intel_engine_supports_stats(engine)) { val = ktime_to_ns(intel_engine_get_busy_time(engine)); } else { val = engine->pmu.sample[sample].cur; @@ -408,18 +534,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event) val = count_interrupts(i915); break; case I915_PMU_RC6_RESIDENCY: - intel_runtime_pm_get(i915); - val = intel_rc6_residency_ns(i915, - IS_VALLEYVIEW(i915) ? - VLV_GT_RENDER_RC6 : - GEN6_GT_GFX_RC6); - if (HAS_RC6p(i915)) - val += intel_rc6_residency_ns(i915, - GEN6_GT_GFX_RC6p); - if (HAS_RC6pp(i915)) - val += intel_rc6_residency_ns(i915, - GEN6_GT_GFX_RC6pp); - intel_runtime_pm_put(i915); + val = get_rc6(i915, locked); break; } } @@ -434,7 +549,7 @@ static void i915_pmu_event_read(struct perf_event *event) again: prev = local64_read(&hwc->prev_count); - new = __i915_pmu_event_read(event); + new = __i915_pmu_event_read(event, false); if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev) goto again; @@ -442,12 +557,6 @@ again: local64_add(new - prev, &event->count); } -static bool engine_needs_busy_stats(struct intel_engine_cs *engine) -{ - return intel_engine_supports_stats(engine) && - (engine->pmu.enable & BIT(I915_SAMPLE_BUSY)); -} - static void i915_pmu_enable(struct perf_event *event) { struct drm_i915_private *i915 = @@ -487,21 +596,7 @@ static void i915_pmu_enable(struct perf_event *event) GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0); - if (engine->pmu.enable_count[sample]++ == 0) { - /* - * Enable engine busy stats tracking if needed or - * alternatively cancel the scheduled disable. - * - * If the delayed disable was pending, cancel it and - * in this case do not enable since it already is. - */ - if (engine_needs_busy_stats(engine) && - !engine->pmu.busy_stats) { - engine->pmu.busy_stats = true; - if (!cancel_delayed_work(&engine->pmu.disable_busy_stats)) - intel_enable_engine_stats(engine); - } - } + engine->pmu.enable_count[sample]++; } /* @@ -509,19 +604,11 @@ static void i915_pmu_enable(struct perf_event *event) * for all listeners. Even when the event was already enabled and has * an existing non-zero value. */ - local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); + local64_set(&event->hw.prev_count, __i915_pmu_event_read(event, true)); spin_unlock_irqrestore(&i915->pmu.lock, flags); } -static void __disable_busy_stats(struct work_struct *work) -{ - struct intel_engine_cs *engine = - container_of(work, typeof(*engine), pmu.disable_busy_stats.work); - - intel_disable_engine_stats(engine); -} - static void i915_pmu_disable(struct perf_event *event) { struct drm_i915_private *i915 = @@ -545,26 +632,8 @@ static void i915_pmu_disable(struct perf_event *event) * Decrement the reference count and clear the enabled * bitmask when the last listener on an event goes away. */ - if (--engine->pmu.enable_count[sample] == 0) { + if (--engine->pmu.enable_count[sample] == 0) engine->pmu.enable &= ~BIT(sample); - if (!engine_needs_busy_stats(engine) && - engine->pmu.busy_stats) { - engine->pmu.busy_stats = false; - /* - * We request a delayed disable to handle the - * rapid on/off cycles on events, which can - * happen when tools like perf stat start, in a - * nicer way. - * - * In addition, this also helps with busy stats - * accuracy with background CPU offline/online - * migration events. - */ - queue_delayed_work(system_wq, - &engine->pmu.disable_busy_stats, - round_jiffies_up_relative(HZ)); - } - } } GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); @@ -797,8 +866,6 @@ static void i915_pmu_unregister_cpuhp_state(struct drm_i915_private *i915) void i915_pmu_register(struct drm_i915_private *i915) { - struct intel_engine_cs *engine; - enum intel_engine_id id; int ret; if (INTEL_GEN(i915) <= 2) { @@ -820,10 +887,6 @@ void i915_pmu_register(struct drm_i915_private *i915) hrtimer_init(&i915->pmu.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); i915->pmu.timer.function = i915_sample; - for_each_engine(engine, i915, id) - INIT_DELAYED_WORK(&engine->pmu.disable_busy_stats, - __disable_busy_stats); - ret = perf_pmu_register(&i915->pmu.base, "i915", -1); if (ret) goto err; @@ -843,9 +906,6 @@ err: void i915_pmu_unregister(struct drm_i915_private *i915) { - struct intel_engine_cs *engine; - enum intel_engine_id id; - if (!i915->pmu.base.event_init) return; @@ -853,11 +913,6 @@ void i915_pmu_unregister(struct drm_i915_private *i915) hrtimer_cancel(&i915->pmu.timer); - for_each_engine(engine, i915, id) { - GEM_BUG_ON(engine->pmu.busy_stats); - flush_delayed_work(&engine->pmu.disable_busy_stats); - } - i915_pmu_unregister_cpuhp_state(i915); perf_pmu_unregister(&i915->pmu.base); diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 40c154d13565..bb62df15afa4 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -27,6 +27,8 @@ enum { __I915_SAMPLE_FREQ_ACT = 0, __I915_SAMPLE_FREQ_REQ, + __I915_SAMPLE_RC6, + __I915_SAMPLE_RC6_ESTIMATED, __I915_NUM_PMU_SAMPLERS }; @@ -94,6 +96,10 @@ struct i915_pmu { * struct intel_engine_cs. */ struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS]; + /** + * @suspended_jiffies_last: Cached suspend time from PM core. + */ + unsigned long suspended_jiffies_last; }; #ifdef CONFIG_PERF_EVENTS diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index f7f771749e48..b49a2df44430 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -947,6 +947,86 @@ static int goto_next_sequence_v3(const u8 *data, int index, int total) return 0; } +/* + * Get len of pre-fixed deassert fragment from a v1 init OTP sequence, + * skip all delay + gpio operands and stop at the first DSI packet op. + */ +static int get_init_otp_deassert_fragment_len(struct drm_i915_private *dev_priv) +{ + const u8 *data = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP]; + int index, len; + + if (WARN_ON(!data || dev_priv->vbt.dsi.seq_version != 1)) + return 0; + + /* index = 1 to skip sequence byte */ + for (index = 1; data[index] != MIPI_SEQ_ELEM_END; index += len) { + switch (data[index]) { + case MIPI_SEQ_ELEM_SEND_PKT: + return index == 1 ? 0 : index; + case MIPI_SEQ_ELEM_DELAY: + len = 5; /* 1 byte for operand + uint32 */ + break; + case MIPI_SEQ_ELEM_GPIO: + len = 3; /* 1 byte for op, 1 for gpio_nr, 1 for value */ + break; + default: + return 0; + } + } + + return 0; +} + +/* + * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence. + * The deassert must be done before calling intel_dsi_device_ready, so for + * these devices we split the init OTP sequence into a deassert sequence and + * the actual init OTP part. + */ +static void fixup_mipi_sequences(struct drm_i915_private *dev_priv) +{ + u8 *init_otp; + int len; + + /* Limit this to VLV for now. */ + if (!IS_VALLEYVIEW(dev_priv)) + return; + + /* Limit this to v1 vid-mode sequences */ + if (dev_priv->vbt.dsi.config->is_cmd_mode || + dev_priv->vbt.dsi.seq_version != 1) + return; + + /* Only do this if there are otp and assert seqs and no deassert seq */ + if (!dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] || + !dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET] || + dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) + return; + + /* The deassert-sequence ends at the first DSI packet */ + len = get_init_otp_deassert_fragment_len(dev_priv); + if (!len) + return; + + DRM_DEBUG_KMS("Using init OTP fragment to deassert reset\n"); + + /* Copy the fragment, update seq byte and terminate it */ + init_otp = (u8 *)dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP]; + dev_priv->vbt.dsi.deassert_seq = kmemdup(init_otp, len + 1, GFP_KERNEL); + if (!dev_priv->vbt.dsi.deassert_seq) + return; + dev_priv->vbt.dsi.deassert_seq[0] = MIPI_SEQ_DEASSERT_RESET; + dev_priv->vbt.dsi.deassert_seq[len] = MIPI_SEQ_ELEM_END; + /* Use the copy for deassert */ + dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET] = + dev_priv->vbt.dsi.deassert_seq; + /* Replace the last byte of the fragment with init OTP seq byte */ + init_otp[len - 1] = MIPI_SEQ_INIT_OTP; + /* And make MIPI_MIPI_SEQ_INIT_OTP point to it */ + dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1; +} + static void parse_mipi_sequence(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) @@ -1016,6 +1096,8 @@ parse_mipi_sequence(struct drm_i915_private *dev_priv, dev_priv->vbt.dsi.size = seq_size; dev_priv->vbt.dsi.seq_version = sequence->version; + fixup_mipi_sequences(dev_priv); + DRM_DEBUG_DRIVER("MIPI related VBT parsing complete\n"); return; @@ -1589,6 +1671,29 @@ out: } /** + * intel_bios_cleanup - Free any resources allocated by intel_bios_init() + * @dev_priv: i915 device instance + */ +void intel_bios_cleanup(struct drm_i915_private *dev_priv) +{ + kfree(dev_priv->vbt.child_dev); + dev_priv->vbt.child_dev = NULL; + dev_priv->vbt.child_dev_num = 0; + kfree(dev_priv->vbt.sdvo_lvds_vbt_mode); + dev_priv->vbt.sdvo_lvds_vbt_mode = NULL; + kfree(dev_priv->vbt.lfp_lvds_vbt_mode); + dev_priv->vbt.lfp_lvds_vbt_mode = NULL; + kfree(dev_priv->vbt.dsi.data); + dev_priv->vbt.dsi.data = NULL; + kfree(dev_priv->vbt.dsi.pps); + dev_priv->vbt.dsi.pps = NULL; + kfree(dev_priv->vbt.dsi.config); + dev_priv->vbt.dsi.config = NULL; + kfree(dev_priv->vbt.dsi.deassert_seq); + dev_priv->vbt.dsi.deassert_seq = NULL; +} + +/** * intel_bios_is_tv_present - is integrated TV present in VBT * @dev_priv: i915 device instance * diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index bd40fea16b4f..f54ddda9fdad 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -594,29 +594,16 @@ void intel_engine_remove_wait(struct intel_engine_cs *engine, spin_unlock_irq(&b->rb_lock); } -static bool signal_valid(const struct drm_i915_gem_request *request) -{ - return intel_wait_check_request(&request->signaling.wait, request); -} - static bool signal_complete(const struct drm_i915_gem_request *request) { if (!request) return false; - /* If another process served as the bottom-half it may have already - * signalled that this wait is already completed. - */ - if (intel_wait_complete(&request->signaling.wait)) - return signal_valid(request); - - /* Carefully check if the request is complete, giving time for the + /* + * Carefully check if the request is complete, giving time for the * seqno to be visible or if the GPU hung. */ - if (__i915_request_irq_complete(request)) - return true; - - return false; + return __i915_request_irq_complete(request); } static struct drm_i915_gem_request *to_signaler(struct rb_node *rb) @@ -659,9 +646,13 @@ static int intel_breadcrumbs_signaler(void *arg) request = i915_gem_request_get_rcu(request); rcu_read_unlock(); if (signal_complete(request)) { - local_bh_disable(); - dma_fence_signal(&request->fence); - local_bh_enable(); /* kick start the tasklets */ + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &request->fence.flags)) { + local_bh_disable(); + dma_fence_signal(&request->fence); + GEM_BUG_ON(!i915_gem_request_completed(request)); + local_bh_enable(); /* kick start the tasklets */ + } spin_lock_irq(&b->rb_lock); diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 5dc118f26b51..1704c8897afd 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -1952,6 +1952,14 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9) min_cdclk = max(2 * 96000, min_cdclk); + /* + * On Valleyview some DSI panels lose (v|h)sync when the clock is lower + * than 320000KHz. + */ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) && + IS_VALLEYVIEW(dev_priv)) + min_cdclk = max(320000, min_cdclk); + if (min_cdclk > dev_priv->max_cdclk_freq) { DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n", min_cdclk, dev_priv->max_cdclk_freq); diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index d790bdc227ff..fa960cfd2764 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1458,7 +1458,9 @@ static bool ring_is_idle(struct intel_engine_cs *engine) struct drm_i915_private *dev_priv = engine->i915; bool idle = true; - intel_runtime_pm_get(dev_priv); + /* If the whole device is asleep, the engine must be idle */ + if (!intel_runtime_pm_get_if_in_use(dev_priv)) + return true; /* First check that no commands are left in the ring */ if ((I915_READ_HEAD(engine) & HEAD_ADDR) != @@ -1943,16 +1945,22 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance) */ int intel_enable_engine_stats(struct intel_engine_cs *engine) { + struct intel_engine_execlists *execlists = &engine->execlists; unsigned long flags; + int err = 0; if (!intel_engine_supports_stats(engine)) return -ENODEV; + tasklet_disable(&execlists->tasklet); spin_lock_irqsave(&engine->stats.lock, flags); - if (engine->stats.enabled == ~0) - goto busy; + + if (unlikely(engine->stats.enabled == ~0)) { + err = -EBUSY; + goto unlock; + } + if (engine->stats.enabled++ == 0) { - struct intel_engine_execlists *execlists = &engine->execlists; const struct execlist_port *port = execlists->port; unsigned int num_ports = execlists_num_ports(execlists); @@ -1967,14 +1975,12 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) if (engine->stats.active) engine->stats.start = engine->stats.enabled_at; } - spin_unlock_irqrestore(&engine->stats.lock, flags); - - return 0; -busy: +unlock: spin_unlock_irqrestore(&engine->stats.lock, flags); + tasklet_enable(&execlists->tasklet); - return -EBUSY; + return err; } static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index c5ff203e42d6..a0e7a6c2a57c 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -366,20 +366,6 @@ struct intel_engine_cs { */ #define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1) struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX]; - /** - * @busy_stats: Has enablement of engine stats tracking been - * requested. - */ - bool busy_stats; - /** - * @disable_busy_stats: Work item for busy stats disabling. - * - * Same as with @enable_busy_stats action, with the difference - * that we delay it in case there are rapid enable-disable - * actions, which can happen during tool startup (like perf - * stat). - */ - struct delayed_work disable_busy_stats; } pmu; /* diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c index bf62303571b3..3695cde669f8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c @@ -301,7 +301,7 @@ nvkm_therm_attr_set(struct nvkm_therm *therm, void nvkm_therm_clkgate_enable(struct nvkm_therm *therm) { - if (!therm->func->clkgate_enable || !therm->clkgating_enabled) + if (!therm || !therm->func->clkgate_enable || !therm->clkgating_enabled) return; nvkm_debug(&therm->subdev, @@ -312,7 +312,7 @@ nvkm_therm_clkgate_enable(struct nvkm_therm *therm) void nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend) { - if (!therm->func->clkgate_fini || !therm->clkgating_enabled) + if (!therm || !therm->func->clkgate_fini || !therm->clkgating_enabled) return; nvkm_debug(&therm->subdev, @@ -395,7 +395,7 @@ void nvkm_therm_clkgate_init(struct nvkm_therm *therm, const struct nvkm_therm_clkgate_pack *p) { - if (!therm->func->clkgate_init || !therm->clkgating_enabled) + if (!therm || !therm->func->clkgate_init || !therm->clkgating_enabled) return; therm->func->clkgate_init(therm, p); diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 4bdbf77f7197..72c338eb5fae 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -269,13 +269,13 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) for (i = 0; i < ARRAY_SIZE(tjmax_model_table); i++) { const struct tjmax_model *tm = &tjmax_model_table[i]; if (c->x86_model == tm->model && - (tm->mask == ANY || c->x86_mask == tm->mask)) + (tm->mask == ANY || c->x86_stepping == tm->mask)) return tm->tjmax; } /* Early chips have no MSR for TjMax */ - if (c->x86_model == 0xf && c->x86_mask < 4) + if (c->x86_model == 0xf && c->x86_stepping < 4) usemsr_ee = 0; if (c->x86_model > 0xe && usemsr_ee) { @@ -426,7 +426,7 @@ static int chk_ucode_version(unsigned int cpu) * Readings might stop update when processor visited too deep sleep, * fixed for stepping D0 (6EC). */ - if (c->x86_model == 0xe && c->x86_mask < 0xc && c->microcode < 0x39) { + if (c->x86_model == 0xe && c->x86_stepping < 0xc && c->microcode < 0x39) { pr_err("Errata AE18 not fixed, update BIOS or microcode of the CPU!\n"); return -ENODEV; } diff --git a/drivers/hwmon/hwmon-vid.c b/drivers/hwmon/hwmon-vid.c index ef91b8a67549..84e91286fc4f 100644 --- a/drivers/hwmon/hwmon-vid.c +++ b/drivers/hwmon/hwmon-vid.c @@ -293,7 +293,7 @@ u8 vid_which_vrm(void) if (c->x86 < 6) /* Any CPU with family lower than 6 */ return 0; /* doesn't have VID */ - vrm_ret = find_vrm(c->x86, c->x86_model, c->x86_mask, c->x86_vendor); + vrm_ret = find_vrm(c->x86, c->x86_model, c->x86_stepping, c->x86_vendor); if (vrm_ret == 134) vrm_ret = get_via_model_d_vrm(); if (vrm_ret == 0) diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 06b4e1c78bd8..051a72eecb24 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -129,7 +129,10 @@ static ssize_t temp1_input_show(struct device *dev, data->read_tempreg(data->pdev, ®val); temp = (regval >> 21) * 125; - temp -= data->temp_offset; + if (temp > data->temp_offset) + temp -= data->temp_offset; + else + temp = 0; return sprintf(buf, "%u\n", temp); } @@ -227,7 +230,7 @@ static bool has_erratum_319(struct pci_dev *pdev) * and AM3 formats, but that's the best we can do. */ return boot_cpu_data.x86_model < 4 || - (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask <= 2); + (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_stepping <= 2); } static int k10temp_probe(struct pci_dev *pdev, diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c index 5a632bcf869b..e59f9113fb93 100644 --- a/drivers/hwmon/k8temp.c +++ b/drivers/hwmon/k8temp.c @@ -187,7 +187,7 @@ static int k8temp_probe(struct pci_dev *pdev, return -ENOMEM; model = boot_cpu_data.x86_model; - stepping = boot_cpu_data.x86_mask; + stepping = boot_cpu_data.x86_stepping; /* feature available since SH-C0, exclude older revisions */ if ((model == 4 && stepping == 0) || diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 55cfb986225b..faf734ff4cf3 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -339,9 +339,6 @@ int __init bcm7038_l1_of_init(struct device_node *dn, goto out_unmap; } - pr_info("registered BCM7038 L1 intc (mem: 0x%p, IRQs: %d)\n", - intc->cpus[0]->map_base, IRQS_PER_WORD * intc->n_words); - return 0; out_unmap: diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index 983640eba418..8968e5e93fcb 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -318,9 +318,6 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, } } - pr_info("registered %s intc (mem: 0x%p, parent IRQ(s): %d)\n", - intc_name, data->map_base[0], data->num_parent_irqs); - return 0; out_free_domain: diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 691d20eb0bec..0e65f609352e 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -262,9 +262,6 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, ct->chip.irq_set_wake = irq_gc_set_wake; } - pr_info("registered L2 intc (mem: 0x%p, parent irq: %d)\n", - base, parent_irq); - return 0; out_free_domain: diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 993a8426a453..1ff38aff9f29 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -94,7 +94,7 @@ static struct irq_chip gicv2m_msi_irq_chip = { static struct msi_domain_info gicv2m_msi_domain_info = { .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX), + MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI), .chip = &gicv2m_msi_irq_chip, }; @@ -155,18 +155,12 @@ static int gicv2m_irq_gic_domain_alloc(struct irq_domain *domain, return 0; } -static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq) +static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq, + int nr_irqs) { - int pos; - - pos = hwirq - v2m->spi_start; - if (pos < 0 || pos >= v2m->nr_spis) { - pr_err("Failed to teardown msi. Invalid hwirq %d\n", hwirq); - return; - } - spin_lock(&v2m_lock); - __clear_bit(pos, v2m->bm); + bitmap_release_region(v2m->bm, hwirq - v2m->spi_start, + get_count_order(nr_irqs)); spin_unlock(&v2m_lock); } @@ -174,13 +168,13 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *args) { struct v2m_data *v2m = NULL, *tmp; - int hwirq, offset, err = 0; + int hwirq, offset, i, err = 0; spin_lock(&v2m_lock); list_for_each_entry(tmp, &v2m_nodes, entry) { - offset = find_first_zero_bit(tmp->bm, tmp->nr_spis); - if (offset < tmp->nr_spis) { - __set_bit(offset, tmp->bm); + offset = bitmap_find_free_region(tmp->bm, tmp->nr_spis, + get_count_order(nr_irqs)); + if (offset >= 0) { v2m = tmp; break; } @@ -192,16 +186,21 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, hwirq = v2m->spi_start + offset; - err = gicv2m_irq_gic_domain_alloc(domain, virq, hwirq); - if (err) { - gicv2m_unalloc_msi(v2m, hwirq); - return err; - } + for (i = 0; i < nr_irqs; i++) { + err = gicv2m_irq_gic_domain_alloc(domain, virq + i, hwirq + i); + if (err) + goto fail; - irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &gicv2m_irq_chip, v2m); + irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, + &gicv2m_irq_chip, v2m); + } return 0; + +fail: + irq_domain_free_irqs_parent(domain, virq, nr_irqs); + gicv2m_unalloc_msi(v2m, hwirq, get_count_order(nr_irqs)); + return err; } static void gicv2m_irq_domain_free(struct irq_domain *domain, @@ -210,8 +209,7 @@ static void gicv2m_irq_domain_free(struct irq_domain *domain, struct irq_data *d = irq_domain_get_irq_data(domain, virq); struct v2m_data *v2m = irq_data_get_irq_chip_data(d); - BUG_ON(nr_irqs != 1); - gicv2m_unalloc_msi(v2m, d->hwirq); + gicv2m_unalloc_msi(v2m, d->hwirq, nr_irqs); irq_domain_free_irqs_parent(domain, virq, nr_irqs); } diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index 14a8c0a7e095..25a98de5cfb2 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -132,6 +132,8 @@ static int __init its_pci_of_msi_init(void) for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) continue; diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c index 833a90fe33ae..8881a053c173 100644 --- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c @@ -154,6 +154,8 @@ static void __init its_pmsi_of_init(void) for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) continue; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 06f025fd5726..1d3056f53747 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3314,6 +3314,8 @@ static int __init its_of_probe(struct device_node *node) for (np = of_find_matching_node(node, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) { pr_warn("%pOF: no msi-controller property, ITS ignored\n", np); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index a57c0fbbd34a..d99cc07903ec 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -673,7 +673,7 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) MPIDR_TO_SGI_RS(cluster_id) | tlist << ICC_SGI1R_TARGET_LIST_SHIFT); - pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); + pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); gic_write_sgi1r(val); } @@ -688,7 +688,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ - smp_wmb(); + wmb(); for_each_cpu(cpu, mask) { u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu)); diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index ef92a4d2038e..d32268cc1174 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -424,8 +424,6 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); - gic_clear_pcpu_masks(intr); - set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); irq_data_update_effective_affinity(data, cpumask_of(cpu)); spin_unlock_irqrestore(&gic_lock, flags); diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 62f541f968f6..07074820a167 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -375,6 +375,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, dev->ofdev.dev.of_node = np; dev->ofdev.archdata.dma_mask = 0xffffffffUL; dev->ofdev.dev.dma_mask = &dev->ofdev.archdata.dma_mask; + dev->ofdev.dev.coherent_dma_mask = dev->ofdev.archdata.dma_mask; dev->ofdev.dev.parent = parent; dev->ofdev.dev.bus = &macio_bus_type; dev->ofdev.dev.release = macio_release_dev; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index d6de00f367ef..68136806d365 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -903,7 +903,8 @@ static void dec_pending(struct dm_io *io, blk_status_t error) queue_io(md, bio); } else { /* done with normal IO or empty flush */ - bio->bi_status = io_error; + if (io_error) + bio->bi_status = io_error; bio_endio(bio); } } diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index d9aa407db06a..2dd2db9bc1c9 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -277,7 +277,7 @@ static ssize_t afu_read(struct file *file, char __user *buf, size_t count, struct ocxl_context *ctx = file->private_data; struct ocxl_kernel_event_header header; ssize_t rc; - size_t used = 0; + ssize_t used = 0; DEFINE_WAIT(event_wait); memset(&header, 0, sizeof(header)); diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 229dc18f0581..768972af8b85 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1265,7 +1265,8 @@ static int bcm2835_add_host(struct bcm2835_host *host) char pio_limit_string[20]; int ret; - mmc->f_max = host->max_clk; + if (!mmc->f_max || mmc->f_max > host->max_clk) + mmc->f_max = host->max_clk; mmc->f_min = host->max_clk / SDCDIV_MAX_CDIV; mmc->max_busy_timeout = ~0 / (mmc->f_max / 1000); diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 22438ebfe4e6..4f972b879fe6 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -717,22 +717,6 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode, static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct meson_host *host = mmc_priv(mmc); - int ret; - - /* - * If this is the initial tuning, try to get a sane Rx starting - * phase before doing the actual tuning. - */ - if (!mmc->doing_retune) { - ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); - - if (ret) - return ret; - } - - ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk); - if (ret) - return ret; return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); } @@ -763,9 +747,8 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (!IS_ERR(mmc->supply.vmmc)) mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd); - /* Reset phases */ + /* Reset rx phase */ clk_set_phase(host->rx_clk, 0); - clk_set_phase(host->tx_clk, 270); break; diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index 46b29d277804..19a2b283fbbe 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -285,7 +285,7 @@ config MTD_NAND_MARVELL tristate "NAND controller support on Marvell boards" depends on PXA3xx || ARCH_MMP || PLAT_ORION || ARCH_MVEBU || \ COMPILE_TEST - depends on HAS_IOMEM + depends on HAS_IOMEM && HAS_DMA help This enables the NAND flash controller driver for Marvell boards, including: diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 7872a9ed3df8..d5a22fc96878 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -862,10 +862,8 @@ static int vf610_nfc_probe(struct platform_device *pdev) if (mtd->oobsize > 64) mtd->oobsize = 64; - /* - * mtd->ecclayout is not specified here because we're using the - * default large page ECC layout defined in NAND core. - */ + /* Use default large page ECC layout defined in NAND core */ + mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops); if (chip->ecc.strength == 32) { nfc->ecc_mode = ECC_60_BYTE; chip->ecc.bytes = 60; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f431c32774f3..0fe7ea35c221 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -120,8 +120,12 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) int ret; ret = nvme_reset_ctrl(ctrl); - if (!ret) + if (!ret) { flush_work(&ctrl->reset_work); + if (ctrl->state != NVME_CTRL_LIVE) + ret = -ENETRESET; + } + return ret; } EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync); @@ -265,7 +269,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (new_state) { case NVME_CTRL_ADMIN_ONLY: switch (old_state) { - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; /* FALLTHRU */ default: @@ -276,7 +280,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (old_state) { case NVME_CTRL_NEW: case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; /* FALLTHRU */ default: @@ -294,9 +298,9 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, break; } break; - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: switch (old_state) { - case NVME_CTRL_LIVE: + case NVME_CTRL_NEW: case NVME_CTRL_RESETTING: changed = true; /* FALLTHRU */ @@ -309,7 +313,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, case NVME_CTRL_LIVE: case NVME_CTRL_ADMIN_ONLY: case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: changed = true; /* FALLTHRU */ default: @@ -518,9 +522,11 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; - range[n].cattr = cpu_to_le32(0); - range[n].nlb = cpu_to_le32(nlb); - range[n].slba = cpu_to_le64(slba); + if (n < segments) { + range[n].cattr = cpu_to_le32(0); + range[n].nlb = cpu_to_le32(nlb); + range[n].slba = cpu_to_le64(slba); + } n++; } @@ -794,13 +800,9 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) static int nvme_keep_alive(struct nvme_ctrl *ctrl) { - struct nvme_command c; struct request *rq; - memset(&c, 0, sizeof(c)); - c.common.opcode = nvme_admin_keep_alive; - - rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED, + rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, BLK_MQ_REQ_RESERVED, NVME_QID_ANY); if (IS_ERR(rq)) return PTR_ERR(rq); @@ -832,6 +834,8 @@ void nvme_start_keep_alive(struct nvme_ctrl *ctrl) return; INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work); + memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); + ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive; schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); } EXPORT_SYMBOL_GPL(nvme_start_keep_alive); @@ -1117,14 +1121,19 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static void nvme_update_formats(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns; + struct nvme_ns *ns, *next; + LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->disk && nvme_revalidate_disk(ns->disk)) - nvme_ns_remove(ns); + if (ns->disk && nvme_revalidate_disk(ns->disk)) { + list_move_tail(&ns->list, &rm_list); + } } mutex_unlock(&ctrl->namespaces_mutex); + + list_for_each_entry_safe(ns, next, &rm_list, list) + nvme_ns_remove(ns); } static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) @@ -2687,7 +2696,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev, [NVME_CTRL_LIVE] = "live", [NVME_CTRL_ADMIN_ONLY] = "only-admin", [NVME_CTRL_RESETTING] = "resetting", - [NVME_CTRL_RECONNECTING]= "reconnecting", + [NVME_CTRL_CONNECTING] = "connecting", [NVME_CTRL_DELETING] = "deleting", [NVME_CTRL_DEAD] = "dead", }; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 25b19f722f5b..a3145d90c1d2 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -171,13 +171,14 @@ static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl, cmd->common.opcode != nvme_fabrics_command || cmd->fabrics.fctype != nvme_fabrics_type_connect) { /* - * Reconnecting state means transport disruption, which can take - * a long time and even might fail permanently, fail fast to - * give upper layers a chance to failover. + * Connecting state means transport disruption or initial + * establishment, which can take a long time and even might + * fail permanently, fail fast to give upper layers a chance + * to failover. * Deleting state means that the ctrl will never accept commands * again, fail it permanently. */ - if (ctrl->state == NVME_CTRL_RECONNECTING || + if (ctrl->state == NVME_CTRL_CONNECTING || ctrl->state == NVME_CTRL_DELETING) { nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b856d7c919d2..7f51f8414b97 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -55,9 +55,7 @@ struct nvme_fc_queue { enum nvme_fcop_flags { FCOP_FLAGS_TERMIO = (1 << 0), - FCOP_FLAGS_RELEASED = (1 << 1), - FCOP_FLAGS_COMPLETE = (1 << 2), - FCOP_FLAGS_AEN = (1 << 3), + FCOP_FLAGS_AEN = (1 << 1), }; struct nvmefc_ls_req_op { @@ -532,7 +530,7 @@ nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl) { switch (ctrl->ctrl.state) { case NVME_CTRL_NEW: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: /* * As all reconnects were suppressed, schedule a * connect. @@ -777,7 +775,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) } break; - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: /* * The association has already been terminated and the * controller is attempting reconnects. No need to do anything @@ -1470,7 +1468,6 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) /* *********************** NVME Ctrl Routines **************************** */ -static void __nvme_fc_final_op_cleanup(struct request *rq); static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg); static int @@ -1512,13 +1509,19 @@ nvme_fc_exit_request(struct blk_mq_tag_set *set, struct request *rq, static int __nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op) { - int state; + unsigned long flags; + int opstate; + + spin_lock_irqsave(&ctrl->lock, flags); + opstate = atomic_xchg(&op->state, FCPOP_STATE_ABORTED); + if (opstate != FCPOP_STATE_ACTIVE) + atomic_set(&op->state, opstate); + else if (ctrl->flags & FCCTRL_TERMIO) + ctrl->iocnt++; + spin_unlock_irqrestore(&ctrl->lock, flags); - state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED); - if (state != FCPOP_STATE_ACTIVE) { - atomic_set(&op->state, state); + if (opstate != FCPOP_STATE_ACTIVE) return -ECANCELED; - } ctrl->lport->ops->fcp_abort(&ctrl->lport->localport, &ctrl->rport->remoteport, @@ -1532,60 +1535,26 @@ static void nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl) { struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops; - unsigned long flags; - int i, ret; - - for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { - if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE) - continue; - - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) { - ctrl->iocnt++; - aen_op->flags |= FCOP_FLAGS_TERMIO; - } - spin_unlock_irqrestore(&ctrl->lock, flags); - - ret = __nvme_fc_abort_op(ctrl, aen_op); - if (ret) { - /* - * if __nvme_fc_abort_op failed the io wasn't - * active. Thus this call path is running in - * parallel to the io complete. Treat as non-error. - */ + int i; - /* back out the flags/counters */ - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) - ctrl->iocnt--; - aen_op->flags &= ~FCOP_FLAGS_TERMIO; - spin_unlock_irqrestore(&ctrl->lock, flags); - return; - } - } + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) + __nvme_fc_abort_op(ctrl, aen_op); } -static inline int +static inline void __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl, - struct nvme_fc_fcp_op *op) + struct nvme_fc_fcp_op *op, int opstate) { unsigned long flags; - bool complete_rq = false; - spin_lock_irqsave(&ctrl->lock, flags); - if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) { + if (opstate == FCPOP_STATE_ABORTED) { + spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->flags & FCCTRL_TERMIO) { if (!--ctrl->iocnt) wake_up(&ctrl->ioabort_wait); } + spin_unlock_irqrestore(&ctrl->lock, flags); } - if (op->flags & FCOP_FLAGS_RELEASED) - complete_rq = true; - else - op->flags |= FCOP_FLAGS_COMPLETE; - spin_unlock_irqrestore(&ctrl->lock, flags); - - return complete_rq; } static void @@ -1601,6 +1570,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) __le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1); union nvme_result result; bool terminate_assoc = true; + int opstate; /* * WARNING: @@ -1639,11 +1609,12 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) * association to be terminated. */ + opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE); + fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma, sizeof(op->rsp_iu), DMA_FROM_DEVICE); - if (atomic_read(&op->state) == FCPOP_STATE_ABORTED || - op->flags & FCOP_FLAGS_TERMIO) + if (opstate == FCPOP_STATE_ABORTED) status = cpu_to_le16(NVME_SC_ABORT_REQ << 1); else if (freq->status) status = cpu_to_le16(NVME_SC_INTERNAL << 1); @@ -1708,7 +1679,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) done: if (op->flags & FCOP_FLAGS_AEN) { nvme_complete_async_event(&queue->ctrl->ctrl, status, &result); - __nvme_fc_fcpop_chk_teardowns(ctrl, op); + __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); atomic_set(&op->state, FCPOP_STATE_IDLE); op->flags = FCOP_FLAGS_AEN; /* clear other flags */ nvme_fc_ctrl_put(ctrl); @@ -1722,13 +1693,11 @@ done: if (status && (blk_queue_dying(rq->q) || ctrl->ctrl.state == NVME_CTRL_NEW || - ctrl->ctrl.state == NVME_CTRL_RECONNECTING)) + ctrl->ctrl.state == NVME_CTRL_CONNECTING)) status |= cpu_to_le16(NVME_SC_DNR << 1); - if (__nvme_fc_fcpop_chk_teardowns(ctrl, op)) - __nvme_fc_final_op_cleanup(rq); - else - nvme_end_request(rq, status, result); + __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); + nvme_end_request(rq, status, result); check_error: if (terminate_assoc) @@ -2415,46 +2384,16 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg) } static void -__nvme_fc_final_op_cleanup(struct request *rq) +nvme_fc_complete_rq(struct request *rq) { struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); struct nvme_fc_ctrl *ctrl = op->ctrl; atomic_set(&op->state, FCPOP_STATE_IDLE); - op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED | - FCOP_FLAGS_COMPLETE); nvme_fc_unmap_data(ctrl, rq, op); nvme_complete_rq(rq); nvme_fc_ctrl_put(ctrl); - -} - -static void -nvme_fc_complete_rq(struct request *rq) -{ - struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); - struct nvme_fc_ctrl *ctrl = op->ctrl; - unsigned long flags; - bool completed = false; - - /* - * the core layer, on controller resets after calling - * nvme_shutdown_ctrl(), calls complete_rq without our - * calling blk_mq_complete_request(), thus there may still - * be live i/o outstanding with the LLDD. Means transport has - * to track complete calls vs fcpio_done calls to know what - * path to take on completes and dones. - */ - spin_lock_irqsave(&ctrl->lock, flags); - if (op->flags & FCOP_FLAGS_COMPLETE) - completed = true; - else - op->flags |= FCOP_FLAGS_RELEASED; - spin_unlock_irqrestore(&ctrl->lock, flags); - - if (completed) - __nvme_fc_final_op_cleanup(rq); } /* @@ -2476,35 +2415,11 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved) struct nvme_ctrl *nctrl = data; struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req); - unsigned long flags; - int status; if (!blk_mq_request_started(req)) return; - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) { - ctrl->iocnt++; - op->flags |= FCOP_FLAGS_TERMIO; - } - spin_unlock_irqrestore(&ctrl->lock, flags); - - status = __nvme_fc_abort_op(ctrl, op); - if (status) { - /* - * if __nvme_fc_abort_op failed the io wasn't - * active. Thus this call path is running in - * parallel to the io complete. Treat as non-error. - */ - - /* back out the flags/counters */ - spin_lock_irqsave(&ctrl->lock, flags); - if (ctrl->flags & FCCTRL_TERMIO) - ctrl->iocnt--; - op->flags &= ~FCOP_FLAGS_TERMIO; - spin_unlock_irqrestore(&ctrl->lock, flags); - return; - } + __nvme_fc_abort_op(ctrl, op); } @@ -2943,7 +2858,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ; bool recon = true; - if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) return; if (portptr->port_state == FC_OBJSTATE_ONLINE) @@ -2991,10 +2906,10 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) /* will block will waiting for io to terminate */ nvme_fc_delete_association(ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: error_recovery: Couldn't change state " - "to RECONNECTING\n", ctrl->cnum); + "to CONNECTING\n", ctrl->cnum); return; } @@ -3195,7 +3110,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, * transport errors (frame drop, LS failure) inherently must kill * the association. The transport is coded so that any command used * to create the association (prior to a LIVE state transition - * while NEW or RECONNECTING) will fail if it completes in error or + * while NEW or CONNECTING) will fail if it completes in error or * times out. * * As such: as the connect request was mostly likely due to a diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 8e4550fa08f8..0521e4707d1c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -123,7 +123,7 @@ enum nvme_ctrl_state { NVME_CTRL_LIVE, NVME_CTRL_ADMIN_ONLY, /* Only admin queue live */ NVME_CTRL_RESETTING, - NVME_CTRL_RECONNECTING, + NVME_CTRL_CONNECTING, NVME_CTRL_DELETING, NVME_CTRL_DEAD, }; @@ -183,6 +183,7 @@ struct nvme_ctrl { struct work_struct scan_work; struct work_struct async_event_work; struct delayed_work ka_work; + struct nvme_command ka_cmd; struct work_struct fw_act_work; /* Power saving configuration */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 6fe7af00a1f4..73036d2fbbd5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1141,7 +1141,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) /* If there is a reset/reinit ongoing, we shouldn't reset again. */ switch (dev->ctrl.state) { case NVME_CTRL_RESETTING: - case NVME_CTRL_RECONNECTING: + case NVME_CTRL_CONNECTING: return false; default: break; @@ -1215,13 +1215,17 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) * cancellation error. All outstanding requests are completed on * shutdown, so we return BLK_EH_HANDLED. */ - if (dev->ctrl.state == NVME_CTRL_RESETTING) { + switch (dev->ctrl.state) { + case NVME_CTRL_CONNECTING: + case NVME_CTRL_RESETTING: dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, disable controller\n", req->tag, nvmeq->qid); nvme_dev_disable(dev, false); nvme_req(req)->flags |= NVME_REQ_CANCELLED; return BLK_EH_HANDLED; + default: + break; } /* @@ -1364,18 +1368,14 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues, static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq, int qid, int depth) { - if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) { - unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth), - dev->ctrl.page_size); - nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; - nvmeq->sq_cmds_io = dev->cmb + offset; - } else { - nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), - &nvmeq->sq_dma_addr, GFP_KERNEL); - if (!nvmeq->sq_cmds) - return -ENOMEM; - } + /* CMB SQEs will be mapped before creation */ + if (qid && dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) + return 0; + nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), + &nvmeq->sq_dma_addr, GFP_KERNEL); + if (!nvmeq->sq_cmds) + return -ENOMEM; return 0; } @@ -1449,6 +1449,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) struct nvme_dev *dev = nvmeq->dev; int result; + if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) { + unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth), + dev->ctrl.page_size); + nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; + nvmeq->sq_cmds_io = dev->cmb + offset; + } + nvmeq->cq_vector = qid - 1; result = adapter_alloc_cq(dev, qid, nvmeq); if (result < 0) @@ -2288,12 +2295,12 @@ static void nvme_reset_work(struct work_struct *work) nvme_dev_disable(dev, false); /* - * Introduce RECONNECTING state from nvme-fc/rdma transports to mark the + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the * initializing procedure here. */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { dev_warn(dev->ctrl.device, - "failed to mark controller RECONNECTING\n"); + "failed to mark controller CONNECTING\n"); goto out; } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 2bc059f7d73c..3a51ed50eff2 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -887,7 +887,7 @@ free_ctrl: static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) { /* If we are resetting/deleting then do nothing */ - if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) { + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW || ctrl->ctrl.state == NVME_CTRL_LIVE); return; @@ -973,7 +973,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); nvme_start_queues(&ctrl->ctrl); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { /* state change failure should never happen */ WARN_ON_ONCE(1); return; @@ -1756,7 +1756,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) nvme_stop_ctrl(&ctrl->ctrl); nvme_rdma_shutdown_ctrl(ctrl, false); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { /* state change failure should never happen */ WARN_ON_ONCE(1); return; @@ -1784,11 +1784,8 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) return; out_fail: - dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl, true); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + ++ctrl->ctrl.nr_reconnects; + nvme_rdma_reconnect_or_remove(ctrl); } static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { @@ -1942,6 +1939,9 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, if (!ctrl->queues) goto out_uninit_ctrl; + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING); + WARN_ON_ONCE(!changed); + ret = nvme_rdma_configure_admin_queue(ctrl, true); if (ret) goto out_kfree_queues; diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c index 0a4372a016f2..28bbdff4a88b 100644 --- a/drivers/nvme/target/io-cmd.c +++ b/drivers/nvme/target/io-cmd.c @@ -105,10 +105,13 @@ static void nvmet_execute_flush(struct nvmet_req *req) static u16 nvmet_discard_range(struct nvmet_ns *ns, struct nvme_dsm_range *range, struct bio **bio) { - if (__blkdev_issue_discard(ns->bdev, + int ret; + + ret = __blkdev_issue_discard(ns->bdev, le64_to_cpu(range->slba) << (ns->blksize_shift - 9), le32_to_cpu(range->nlb) << (ns->blksize_shift - 9), - GFP_KERNEL, 0, bio)) + GFP_KERNEL, 0, bio); + if (ret && ret != -EOPNOTSUPP) return NVME_SC_INTERNAL | NVME_SC_DNR; return 0; } diff --git a/drivers/of/property.c b/drivers/of/property.c index 36ed84e26d9c..f46828e3b082 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -977,11 +977,11 @@ static int of_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, return 0; } -static void * +static const void * of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { - return (void *)of_device_get_match_data(dev); + return of_device_get_match_data(dev); } const struct fwnode_operations of_fwnode_ops = { diff --git a/drivers/opp/cpu.c b/drivers/opp/cpu.c index 2d87bc1adf38..0c0910709435 100644 --- a/drivers/opp/cpu.c +++ b/drivers/opp/cpu.c @@ -55,7 +55,7 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev, if (max_opps <= 0) return max_opps ? max_opps : -ENODATA; - freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC); + freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_KERNEL); if (!freq_table) return -ENOMEM; diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index 2a68f59d2228..c52c6723374b 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -127,24 +127,6 @@ static const struct dmi_system_id dell_device_table[] __initconst = { }, }, { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_CHASSIS_TYPE, "30"), /*Tablet*/ - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /*Convertible*/ - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_CHASSIS_TYPE, "32"), /*Detachable*/ - }, - }, - { .ident = "Dell Computer Corporation", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), @@ -1279,7 +1261,7 @@ static int kbd_get_state(struct kbd_state *state) struct calling_interface_buffer buffer; int ret; - dell_fill_request(&buffer, 0, 0, 0, 0); + dell_fill_request(&buffer, 0x1, 0, 0, 0); ret = dell_send_request(&buffer, CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); if (ret) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 5b6f18b18801..535199c9e6bc 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -113,7 +113,7 @@ MODULE_PARM_DESC(no_bt_rfkill, "No rfkill for bluetooth."); /* * ACPI Helpers */ -#define IDEAPAD_EC_TIMEOUT (100) /* in ms */ +#define IDEAPAD_EC_TIMEOUT (200) /* in ms */ static int read_method_int(acpi_handle handle, const char *method, int *val) { diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index daa68acbc900..c0c8945603cb 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -933,7 +933,7 @@ static int wmi_dev_probe(struct device *dev) goto probe_failure; } - buf = kmalloc(strlen(wdriver->driver.name) + 4, GFP_KERNEL); + buf = kmalloc(strlen(wdriver->driver.name) + 5, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto probe_string_failure; diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index ba2e0856d22c..8f5c1d7f751a 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -1297,6 +1297,9 @@ static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event) vcdev->device_lost = true; rc = NOTIFY_DONE; break; + case CIO_OPER: + rc = NOTIFY_OK; + break; default: rc = NOTIFY_DONE; break; @@ -1309,6 +1312,27 @@ static struct ccw_device_id virtio_ids[] = { {}, }; +#ifdef CONFIG_PM_SLEEP +static int virtio_ccw_freeze(struct ccw_device *cdev) +{ + struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); + + return virtio_device_freeze(&vcdev->vdev); +} + +static int virtio_ccw_restore(struct ccw_device *cdev) +{ + struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev); + int ret; + + ret = virtio_ccw_set_transport_rev(vcdev); + if (ret) + return ret; + + return virtio_device_restore(&vcdev->vdev); +} +#endif + static struct ccw_driver virtio_ccw_driver = { .driver = { .owner = THIS_MODULE, @@ -1321,6 +1345,11 @@ static struct ccw_driver virtio_ccw_driver = { .set_online = virtio_ccw_online, .notify = virtio_ccw_cio_notify, .int_class = IRQIO_VIR, +#ifdef CONFIG_PM_SLEEP + .freeze = virtio_ccw_freeze, + .thaw = virtio_ccw_restore, + .restore = virtio_ccw_restore, +#endif }; static int __init pure_hex(char **cp, unsigned int *val, int min_digit, diff --git a/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c b/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c index 5064d5ddf581..fc2013aade51 100644 --- a/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c +++ b/drivers/staging/fsl-mc/bus/irq-gic-v3-its-fsl-mc-msi.c @@ -73,6 +73,8 @@ static int __init its_fsl_mc_msi_init(void) for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { + if (!of_device_is_available(np)) + continue; if (!of_property_read_bool(np, "msi-controller")) continue; diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig index f699abab1787..148f3ee70286 100644 --- a/drivers/usb/Kconfig +++ b/drivers/usb/Kconfig @@ -19,6 +19,12 @@ config USB_EHCI_BIG_ENDIAN_MMIO config USB_EHCI_BIG_ENDIAN_DESC bool +config USB_UHCI_BIG_ENDIAN_MMIO + bool + +config USB_UHCI_BIG_ENDIAN_DESC + bool + menuconfig USB_SUPPORT bool "USB support" depends on HAS_IOMEM diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index 6150bed7cfa8..4fcfb3084b36 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -633,14 +633,6 @@ config USB_UHCI_ASPEED bool default y if ARCH_ASPEED -config USB_UHCI_BIG_ENDIAN_MMIO - bool - default y if SPARC_LEON - -config USB_UHCI_BIG_ENDIAN_DESC - bool - default y if SPARC_LEON - config USB_FHCI_HCD tristate "Freescale QE USB Host Controller support" depends on OF_GPIO && QE_GPIO && QUICC_ENGINE diff --git a/drivers/video/fbdev/geode/video_gx.c b/drivers/video/fbdev/geode/video_gx.c index 6082f653c68a..67773e8bbb95 100644 --- a/drivers/video/fbdev/geode/video_gx.c +++ b/drivers/video/fbdev/geode/video_gx.c @@ -127,7 +127,7 @@ void gx_set_dclk_frequency(struct fb_info *info) int timeout = 1000; /* Rev. 1 Geode GXs use a 14 MHz reference clock instead of 48 MHz. */ - if (cpu_data(0).x86_mask == 1) { + if (cpu_data(0).x86_stepping == 1) { pll_table = gx_pll_table_14MHz; pll_table_len = ARRAY_SIZE(gx_pll_table_14MHz); } else { diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 753d9cb437d0..aedbee3b2838 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -60,6 +60,7 @@ struct sock_mapping { bool active_socket; struct list_head list; struct socket *sock; + atomic_t refcount; union { struct { int irq; @@ -93,6 +94,32 @@ struct sock_mapping { }; }; +static inline struct sock_mapping *pvcalls_enter_sock(struct socket *sock) +{ + struct sock_mapping *map; + + if (!pvcalls_front_dev || + dev_get_drvdata(&pvcalls_front_dev->dev) == NULL) + return ERR_PTR(-ENOTCONN); + + map = (struct sock_mapping *)sock->sk->sk_send_head; + if (map == NULL) + return ERR_PTR(-ENOTSOCK); + + pvcalls_enter(); + atomic_inc(&map->refcount); + return map; +} + +static inline void pvcalls_exit_sock(struct socket *sock) +{ + struct sock_mapping *map; + + map = (struct sock_mapping *)sock->sk->sk_send_head; + atomic_dec(&map->refcount); + pvcalls_exit(); +} + static inline int get_request(struct pvcalls_bedata *bedata, int *req_id) { *req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1); @@ -369,31 +396,23 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *)sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } ret = create_active(map, &evtchn); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -423,7 +442,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, smp_rmb(); ret = bedata->rsp[req_id].ret; bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID; - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -488,23 +507,15 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, if (flags & (MSG_CONFIRM|MSG_DONTROUTE|MSG_EOR|MSG_OOB)) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - mutex_lock(&map->active.out_mutex); if ((flags & MSG_DONTWAIT) && !pvcalls_front_write_todo(map)) { mutex_unlock(&map->active.out_mutex); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EAGAIN; } if (len > INT_MAX) @@ -526,7 +537,7 @@ again: tot_sent = sent; mutex_unlock(&map->active.out_mutex); - pvcalls_exit(); + pvcalls_exit_sock(sock); return tot_sent; } @@ -591,19 +602,11 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC)) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - mutex_lock(&map->active.in_mutex); if (len > XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER)) len = XEN_FLEX_RING_SIZE(PVCALLS_RING_ORDER); @@ -623,7 +626,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ret = 0; mutex_unlock(&map->active.in_mutex); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -637,24 +640,16 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) if (addr->sa_family != AF_INET || sock->type != SOCK_STREAM) return -EOPNOTSUPP; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (map == NULL) { - pvcalls_exit(); - return -ENOTSOCK; - } - spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } req = RING_GET_REQUEST(&bedata->ring, req_id); @@ -684,7 +679,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID; map->passive.status = PVCALLS_STATUS_BIND; - pvcalls_exit(); + pvcalls_exit_sock(sock); return 0; } @@ -695,21 +690,13 @@ int pvcalls_front_listen(struct socket *sock, int backlog) struct xen_pvcalls_request *req; int notify, req_id, ret; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - if (map->passive.status != PVCALLS_STATUS_BIND) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EOPNOTSUPP; } @@ -717,7 +704,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog) ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } req = RING_GET_REQUEST(&bedata->ring, req_id); @@ -741,7 +728,7 @@ int pvcalls_front_listen(struct socket *sock, int backlog) bedata->rsp[req_id].req_id = PVCALLS_INVALID_ID; map->passive.status = PVCALLS_STATUS_LISTEN; - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -753,21 +740,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) struct xen_pvcalls_request *req; int notify, req_id, ret, evtchn, nonblock; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -ENOTCONN; - } + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) + return PTR_ERR(map); bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return -ENOTSOCK; - } - if (map->passive.status != PVCALLS_STATUS_LISTEN) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EINVAL; } @@ -785,13 +764,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) goto received; } if (nonblock) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EAGAIN; } if (wait_event_interruptible(map->passive.inflight_accept_req, !test_and_set_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags))) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EINTR; } } @@ -802,7 +781,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } map2 = kzalloc(sizeof(*map2), GFP_ATOMIC); @@ -810,7 +789,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -ENOMEM; } ret = create_active(map2, &evtchn); @@ -819,7 +798,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } list_add_tail(&map2->list, &bedata->socket_mappings); @@ -841,13 +820,13 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) /* We could check if we have received a response before returning. */ if (nonblock) { WRITE_ONCE(map->passive.inflight_req_id, req_id); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EAGAIN; } if (wait_event_interruptible(bedata->inflight_req, READ_ONCE(bedata->rsp[req_id].req_id) == req_id)) { - pvcalls_exit(); + pvcalls_exit_sock(sock); return -EINTR; } /* read req_id, then the content */ @@ -862,7 +841,7 @@ received: clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); pvcalls_front_free_map(bedata, map2); - pvcalls_exit(); + pvcalls_exit_sock(sock); return -ENOMEM; } newsock->sk->sk_send_head = (void *)map2; @@ -874,7 +853,7 @@ received: clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); wake_up(&map->passive.inflight_accept_req); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -965,23 +944,16 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, struct sock_mapping *map; __poll_t ret; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) return EPOLLNVAL; - } bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (!map) { - pvcalls_exit(); - return EPOLLNVAL; - } if (map->active_socket) ret = pvcalls_front_poll_active(file, bedata, map, wait); else ret = pvcalls_front_poll_passive(file, bedata, map, wait); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } @@ -995,25 +967,20 @@ int pvcalls_front_release(struct socket *sock) if (sock->sk == NULL) return 0; - pvcalls_enter(); - if (!pvcalls_front_dev) { - pvcalls_exit(); - return -EIO; + map = pvcalls_enter_sock(sock); + if (IS_ERR(map)) { + if (PTR_ERR(map) == -ENOTCONN) + return -EIO; + else + return 0; } - bedata = dev_get_drvdata(&pvcalls_front_dev->dev); - map = (struct sock_mapping *) sock->sk->sk_send_head; - if (map == NULL) { - pvcalls_exit(); - return 0; - } - spin_lock(&bedata->socket_lock); ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - pvcalls_exit(); + pvcalls_exit_sock(sock); return ret; } sock->sk->sk_send_head = NULL; @@ -1043,14 +1010,20 @@ int pvcalls_front_release(struct socket *sock) /* * We need to make sure that sendmsg/recvmsg on this socket have * not started before we've cleared sk_send_head here. The - * easiest (though not optimal) way to guarantee this is to see - * that no pvcall (other than us) is in progress. + * easiest way to guarantee this is to see that no pvcalls + * (other than us) is in progress on this socket. */ - while (atomic_read(&pvcalls_refcount) > 1) + while (atomic_read(&map->refcount) > 1) cpu_relax(); pvcalls_front_free_map(bedata, map); } else { + wake_up(&bedata->inflight_req); + wake_up(&map->passive.inflight_accept_req); + + while (atomic_read(&map->refcount) > 1) + cpu_relax(); + spin_lock(&bedata->socket_lock); list_del(&map->list); spin_unlock(&bedata->socket_lock); diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 149c5e7efc89..092981171df1 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -76,6 +76,7 @@ struct xb_req_data { struct list_head list; wait_queue_head_t wq; struct xsd_sockmsg msg; + uint32_t caller_req_id; enum xsd_sockmsg_type type; char *body; const struct kvec *vec; diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index 5b081a01779d..d239fc3c5e3d 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,6 +309,7 @@ static int process_msg(void) goto out; if (req->state == xb_req_state_wait_reply) { + req->msg.req_id = req->caller_req_id; req->msg.type = state.msg.type; req->msg.len = state.msg.len; req->body = state.body; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 3e59590c7254..3f3b29398ab8 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -227,6 +227,8 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->state = xb_req_state_queued; init_waitqueue_head(&req->wq); + /* Save the caller req_id and restore it later in the reply */ + req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); mutex_lock(&xb_write_mutex); @@ -310,6 +312,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; + msg.req_id = 0; msg.tx_id = t.id; msg.type = type; msg.len = 0; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e4054e533f6d..f94b2d8c744a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1264,7 +1264,16 @@ again: while (node) { ref = rb_entry(node, struct prelim_ref, rbnode); node = rb_next(&ref->rbnode); - WARN_ON(ref->count < 0); + /* + * ref->count < 0 can happen here if there are delayed + * refs with a node->action of BTRFS_DROP_DELAYED_REF. + * prelim_ref_insert() relies on this when merging + * identical refs to keep the overall count correct. + * prelim_ref_insert() will merge only those refs + * which compare identically. Any refs having + * e.g. different offsets would not be merged, + * and would retain their original ref->count < 0. + */ if (roots && ref->count && ref->root_id && ref->parent == 0) { if (sc && sc->root_objectid && ref->root_id != sc->root_objectid) { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index a1a40cf382e3..7ab5e0128f0c 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -821,7 +821,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, spin_unlock(&delayed_refs->lock); if (qrecord_inserted) - return btrfs_qgroup_trace_extent_post(fs_info, record); + btrfs_qgroup_trace_extent_post(fs_info, record); + return 0; free_head_ref: diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 05751a677da4..c1618ab9fecf 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2147,6 +2147,10 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 bytes; struct request_queue *req_q; + if (!stripe->dev->bdev) { + ASSERT(btrfs_test_opt(fs_info, DEGRADED)); + continue; + } req_q = bdev_get_queue(stripe->dev->bdev); if (!blk_queue_discard(req_q)) continue; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 53ca025655fc..a79299a89b7d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1335,8 +1335,11 @@ next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); - if (ret < 0) + if (ret < 0) { + if (cow_start != (u64)-1) + cur_offset = cow_start; goto error; + } if (ret > 0) break; leaf = path->nodes[0]; @@ -3385,6 +3388,11 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, ret = btrfs_orphan_reserve_metadata(trans, inode); ASSERT(!ret); if (ret) { + /* + * dec doesn't need spin_lock as ->orphan_block_rsv + * would be released only if ->orphan_inodes is + * zero. + */ atomic_dec(&root->orphan_inodes); clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); @@ -3399,12 +3407,17 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, if (insert >= 1) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret) { - atomic_dec(&root->orphan_inodes); if (reserve) { clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); btrfs_orphan_release_metadata(inode); } + /* + * btrfs_orphan_commit_root may race with us and set + * ->orphan_block_rsv to zero, in order to avoid that, + * decrease ->orphan_inodes after everything is done. + */ + atomic_dec(&root->orphan_inodes); if (ret != -EEXIST) { clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &inode->runtime_flags); @@ -3436,28 +3449,26 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; int delete_item = 0; - int release_rsv = 0; int ret = 0; - spin_lock(&root->orphan_lock); if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &inode->runtime_flags)) delete_item = 1; + if (delete_item && trans) + ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); + if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags)) - release_rsv = 1; - spin_unlock(&root->orphan_lock); + btrfs_orphan_release_metadata(inode); - if (delete_item) { + /* + * btrfs_orphan_commit_root may race with us and set ->orphan_block_rsv + * to zero, in order to avoid that, decrease ->orphan_inodes after + * everything is done. + */ + if (delete_item) atomic_dec(&root->orphan_inodes); - if (trans) - ret = btrfs_del_orphan_item(trans, root, - btrfs_ino(inode)); - } - - if (release_rsv) - btrfs_orphan_release_metadata(inode); return ret; } @@ -5281,7 +5292,7 @@ void btrfs_evict_inode(struct inode *inode) trace_btrfs_inode_evict(inode); if (!root) { - kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode)); + clear_inode(inode); return; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9e61dd624f7b..aa259d6986e1 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1442,8 +1442,13 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, int ret; ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false); - if (ret < 0) - return ret; + if (ret < 0) { + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + btrfs_warn(fs_info, +"error accounting new delayed refs extent (err code: %d), quota inconsistent", + ret); + return 0; + } /* * Here we don't need to get the lock of diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index afadaadab18e..4fd19b4d6675 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -29,6 +29,7 @@ #include "hash.h" #include "compression.h" #include "qgroup.h" +#include "inode-map.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -2472,6 +2473,9 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(root_owner != @@ -2552,6 +2556,9 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID); @@ -2630,6 +2637,9 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); + } else { + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) + clear_extent_buffer_dirty(next); } WARN_ON(log->root_key.objectid != @@ -3018,13 +3028,14 @@ static void free_log_tree(struct btrfs_trans_handle *trans, while (1) { ret = find_first_extent_bit(&log->dirty_log_pages, - 0, &start, &end, EXTENT_DIRTY | EXTENT_NEW, + 0, &start, &end, + EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT, NULL); if (ret) break; clear_extent_bits(&log->dirty_log_pages, start, end, - EXTENT_DIRTY | EXTENT_NEW); + EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); } /* @@ -5677,6 +5688,23 @@ again: path); } + if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { + struct btrfs_root *root = wc.replay_dest; + + btrfs_release_path(path); + + /* + * We have just replayed everything, and the highest + * objectid of fs roots probably has changed in case + * some inode_item's got replayed. + * + * root->objectid_mutex is not acquired as log replay + * could only happen during mount. + */ + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + } + key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b5036bd69e6a..2ceb924ca0d6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -645,6 +645,7 @@ static void btrfs_free_stale_devices(const char *path, btrfs_sysfs_remove_fsid(fs_devs); list_del(&fs_devs->list); free_fs_devices(fs_devs); + break; } else { fs_devs->num_devices--; list_del(&dev->dev_list); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 86863792f36a..86d6a4435c87 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -716,7 +716,7 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, __be64 *ptr; sector_t lblock; sector_t lend; - int ret; + int ret = 0; int eob; unsigned int len; struct buffer_head *bh; @@ -728,12 +728,14 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, goto out; } - if ((flags & IOMAP_REPORT) && gfs2_is_stuffed(ip)) { - gfs2_stuffed_iomap(inode, iomap); - if (pos >= iomap->length) - return -ENOENT; - ret = 0; - goto out; + if (gfs2_is_stuffed(ip)) { + if (flags & IOMAP_REPORT) { + gfs2_stuffed_iomap(inode, iomap); + if (pos >= iomap->length) + ret = -ENOENT; + goto out; + } + BUG_ON(!(flags & IOMAP_WRITE)); } lblock = pos >> inode->i_blkbits; @@ -744,7 +746,7 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type = IOMAP_HOLE; iomap->length = (u64)(lend - lblock) << inode->i_blkbits; iomap->flags = IOMAP_F_MERGED; - bmap_lock(ip, 0); + bmap_lock(ip, flags & IOMAP_WRITE); /* * Directory data blocks have a struct gfs2_meta_header header, so the @@ -787,27 +789,28 @@ int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->flags |= IOMAP_F_BOUNDARY; iomap->length = (u64)len << inode->i_blkbits; - ret = 0; - out_release: release_metapath(&mp); - bmap_unlock(ip, 0); + bmap_unlock(ip, flags & IOMAP_WRITE); out: trace_gfs2_iomap_end(ip, iomap, ret); return ret; do_alloc: - if (!(flags & IOMAP_WRITE)) { - if (pos >= i_size_read(inode)) { + if (flags & IOMAP_WRITE) { + ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); + } else if (flags & IOMAP_REPORT) { + loff_t size = i_size_read(inode); + if (pos >= size) ret = -ENOENT; - goto out_release; - } - ret = 0; - iomap->length = hole_size(inode, lblock, &mp); - goto out_release; + else if (height <= ip->i_height) + iomap->length = hole_size(inode, lblock, &mp); + else + iomap->length = size - pos; + } else { + if (height <= ip->i_height) + iomap->length = hole_size(inode, lblock, &mp); } - - ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); goto out_release; } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e8a93bc8285d..d1e82761de81 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -510,6 +510,10 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) return -EFAULT; + } else if (m->type == KCORE_USER) { + /* User page is handled prior to normal kernel page: */ + if (copy_to_user(buffer, (char *)start, tsz)) + return -EFAULT; } else { if (kern_addr_valid(start)) { /* diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index bc397573c43a..67ab280ad134 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -7,7 +7,8 @@ * @nr: Bit to set * @addr: Address to count from * - * This operation is atomic and provides acquire barrier semantics. + * This operation is atomic and provides acquire barrier semantics if + * the returned value is 0. * It can be used to implement bit locks. */ #define test_and_set_bit_lock(nr, addr) test_and_set_bit(nr, addr) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 64e10746f282..968173ec2726 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -587,7 +587,7 @@ extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); -void *acpi_get_match_data(const struct device *dev); +const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); @@ -766,7 +766,7 @@ static inline const struct acpi_device_id *acpi_match_device( return NULL; } -static inline void *acpi_get_match_data(const struct device *dev) +static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4f3df807cf8f..ed63f3b69c12 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -49,7 +49,7 @@ struct blk_stat_callback; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ -/* Must be consisitent with blk_mq_poll_stats_bkt() */ +/* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 /* diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 631354acfa72..73bc63e0a1c4 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -167,8 +167,6 @@ #if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) - -#define __nostackprotector __attribute__((__optimize__("no-stack-protector"))) #endif #if GCC_VERSION >= 40300 @@ -196,6 +194,11 @@ #endif /* __CHECKER__ */ #endif /* GCC_VERSION >= 40300 */ +#if GCC_VERSION >= 40400 +#define __optimize(level) __attribute__((__optimize__(level))) +#define __nostackprotector __optimize("no-stack-protector") +#endif /* GCC_VERSION >= 40400 */ + #if GCC_VERSION >= 40500 #ifndef __CHECKER__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c2cc57a2f508..e835fc0423ec 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -277,6 +277,10 @@ unsigned long read_word_at_a_time(const void *addr) #endif /* __ASSEMBLY__ */ +#ifndef __optimize +# define __optimize(level) +#endif + /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 871f9e21810c..0b3fc229086c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -225,7 +225,7 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, } #endif -#ifdef CONFIG_ARCH_HAS_CPU_RELAX +#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_ARCH_HAS_CPU_RELAX) void cpuidle_poll_state_init(struct cpuidle_driver *drv); #else static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {} diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d4a2a7dcd72d..bf53d893ad02 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -170,6 +170,8 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) +#define for_each_cpu_wrap(cpu, mask, start) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start)) #define for_each_cpu_and(cpu, mask, and) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and) #else diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 34fe8463d10e..eb9eab4ecd6d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -578,7 +578,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) /* * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please - * don't use this is new code. + * don't use this in new code. */ #ifndef arch_dma_supported #define arch_dma_supported(dev, mask) (1) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 4fa1a489efe4..4fe8f289b3f6 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -73,8 +73,8 @@ struct fwnode_operations { struct fwnode_handle *(*get)(struct fwnode_handle *fwnode); void (*put)(struct fwnode_handle *fwnode); bool (*device_is_available)(const struct fwnode_handle *fwnode); - void *(*device_get_match_data)(const struct fwnode_handle *fwnode, - const struct device *dev); + const void *(*device_get_match_data)(const struct fwnode_handle *fwnode, + const struct device *dev); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 7ff25a808fef..80db19d3a505 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -10,6 +10,7 @@ enum kcore_type { KCORE_VMALLOC, KCORE_RAM, KCORE_VMEMMAP, + KCORE_USER, KCORE_OTHER, }; diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index c30b32e3c862..10191c28fc04 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -127,10 +127,4 @@ static __always_inline enum lru_list page_lru(struct page *page) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) -#ifdef arch_unmap_kpfn -extern void arch_unmap_kpfn(unsigned long pfn); -#else -static __always_inline void arch_unmap_kpfn(unsigned long pfn) { } -#endif - #endif diff --git a/include/linux/nospec.h b/include/linux/nospec.h index b99bced39ac2..fbc98e2c8228 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -20,20 +20,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, unsigned long size) { /* - * Warn developers about inappropriate array_index_nospec() usage. - * - * Even if the CPU speculates past the WARN_ONCE branch, the - * sign bit of @index is taken into account when generating the - * mask. - * - * This warning is compiled out when the compiler can infer that - * @index and @size are less than LONG_MAX. - */ - if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, - "array_index_nospec() limited to range of [0, LONG_MAX]\n")) - return 0; - - /* * Always calculate and emit the mask even if the compiler * thinks the mask is not needed. The compiler does not take * into account the value of @index under speculation. @@ -44,6 +30,26 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #endif /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ +#define array_index_mask_nospec_check(index, size) \ +({ \ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, \ + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) \ + _mask = 0; \ + else \ + _mask = array_index_mask_nospec(index, size); \ + _mask; \ +}) + +/* * array_index_nospec - sanitize an array index after a bounds check * * For a code sequence like: @@ -61,7 +67,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, ({ \ typeof(index) _i = (index); \ typeof(size) _s = (size); \ - unsigned long _mask = array_index_mask_nospec(_i, _s); \ + unsigned long _mask = array_index_mask_nospec_check(_i, _s); \ \ BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ diff --git a/include/linux/property.h b/include/linux/property.h index 769d372c1edf..2eea4b310fc2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -283,7 +283,7 @@ bool device_dma_supported(struct device *dev); enum dev_dma_attr device_get_dma_attr(struct device *dev); -void *device_get_match_data(struct device *dev); +const void *device_get_match_data(struct device *dev); int device_get_phy_mode(struct device *dev); diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index dc368b8ce215..11c86fbfeb98 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -4,7 +4,7 @@ * * Distributed under the terms of the GNU GPL, version 2 * - * Please see kernel/semaphore.c for documentation of these functions + * Please see kernel/locking/semaphore.c for documentation of these functions */ #ifndef __LINUX_SEMAPHORE_H #define __LINUX_SEMAPHORE_H diff --git a/include/sound/ac97/regs.h b/include/sound/ac97/regs.h index 4bb86d379bd5..9a4fa0c3264a 100644 --- a/include/sound/ac97/regs.h +++ b/include/sound/ac97/regs.h @@ -31,7 +31,7 @@ #define AC97_HEADPHONE 0x04 /* Headphone Volume (optional) */ #define AC97_MASTER_MONO 0x06 /* Master Volume Mono (optional) */ #define AC97_MASTER_TONE 0x08 /* Master Tone (Bass & Treble) (optional) */ -#define AC97_PC_BEEP 0x0a /* PC Beep Volume (optinal) */ +#define AC97_PC_BEEP 0x0a /* PC Beep Volume (optional) */ #define AC97_PHONE 0x0c /* Phone Volume (optional) */ #define AC97_MIC 0x0e /* MIC Volume */ #define AC97_LINE 0x10 /* Line In Volume */ diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index b8adf05c534e..7dd8f34c37df 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -368,7 +368,7 @@ TRACE_EVENT(xen_mmu_flush_tlb, TP_printk("%s", "") ); -TRACE_EVENT(xen_mmu_flush_tlb_single, +TRACE_EVENT(xen_mmu_flush_tlb_one_user, TP_PROTO(unsigned long addr), TP_ARGS(addr), TP_STRUCT__entry( diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e6a9c36470ee..82b8b18ee1eb 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1726,25 +1726,14 @@ static int irq_domain_debug_show(struct seq_file *m, void *p) irq_domain_debug_show_one(m, d, 0); return 0; } - -static int irq_domain_debug_open(struct inode *inode, struct file *file) -{ - return single_open(file, irq_domain_debug_show, inode->i_private); -} - -static const struct file_operations dfs_domain_ops = { - .open = irq_domain_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(irq_domain_debug); static void debugfs_add_domain_dir(struct irq_domain *d) { if (!d->name || !domain_dir || d->debugfs_file) return; d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d, - &dfs_domain_ops); + &irq_domain_debug_fops); } static void debugfs_remove_domain_dir(struct irq_domain *d) @@ -1760,7 +1749,8 @@ void __init irq_domain_debugfs_init(struct dentry *root) if (!domain_dir) return; - debugfs_create_file("default", 0444, domain_dir, NULL, &dfs_domain_ops); + debugfs_create_file("default", 0444, domain_dir, NULL, + &irq_domain_debug_fops); mutex_lock(&irq_domain_mutex); list_for_each_entry(d, &irq_domain_list, link) debugfs_add_domain_dir(d); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index da2ccf142358..102160ff5c66 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -978,67 +978,90 @@ static int prepare_kprobe(struct kprobe *p) } /* Caller must lock kprobe_mutex */ -static void arm_kprobe_ftrace(struct kprobe *p) +static int arm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); - WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); - kprobe_ftrace_enabled++; - if (kprobe_ftrace_enabled == 1) { + if (ret) { + pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; + } + + if (kprobe_ftrace_enabled == 0) { ret = register_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (ret) { + pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); + goto err_ftrace; + } } + + kprobe_ftrace_enabled++; + return ret; + +err_ftrace: + /* + * Note: Since kprobe_ftrace_ops has IPMODIFY set, and ftrace requires a + * non-empty filter_hash for IPMODIFY ops, we're safe from an accidental + * empty filter_hash which would undesirably trace all functions. + */ + ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); + return ret; } /* Caller must lock kprobe_mutex */ -static void disarm_kprobe_ftrace(struct kprobe *p) +static int disarm_kprobe_ftrace(struct kprobe *p) { - int ret; + int ret = 0; - kprobe_ftrace_enabled--; - if (kprobe_ftrace_enabled == 0) { + if (kprobe_ftrace_enabled == 1) { ret = unregister_ftrace_function(&kprobe_ftrace_ops); - WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) + return ret; } + + kprobe_ftrace_enabled--; + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ #define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) do {} while (0) -#define disarm_kprobe_ftrace(p) do {} while (0) +#define arm_kprobe_ftrace(p) (-ENODEV) +#define disarm_kprobe_ftrace(p) (-ENODEV) #endif /* Arm a kprobe with text_mutex */ -static void arm_kprobe(struct kprobe *kp) +static int arm_kprobe(struct kprobe *kp) { - if (unlikely(kprobe_ftrace(kp))) { - arm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return arm_kprobe_ftrace(kp); + cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* Disarm a kprobe with text_mutex */ -static void disarm_kprobe(struct kprobe *kp, bool reopt) +static int disarm_kprobe(struct kprobe *kp, bool reopt) { - if (unlikely(kprobe_ftrace(kp))) { - disarm_kprobe_ftrace(kp); - return; - } + if (unlikely(kprobe_ftrace(kp))) + return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); + + return 0; } /* @@ -1362,9 +1385,15 @@ out: if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) + if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ - arm_kprobe(ap); + ret = arm_kprobe(ap); + if (ret) { + ap->flags |= KPROBE_FLAG_DISABLED; + list_del_rcu(&p->list); + synchronize_sched(); + } + } } return ret; } @@ -1573,8 +1602,14 @@ int register_kprobe(struct kprobe *p) hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); - if (!kprobes_all_disarmed && !kprobe_disabled(p)) - arm_kprobe(p); + if (!kprobes_all_disarmed && !kprobe_disabled(p)) { + ret = arm_kprobe(p); + if (ret) { + hlist_del_rcu(&p->hlist); + synchronize_sched(); + goto out; + } + } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); @@ -1608,11 +1643,12 @@ static int aggr_kprobe_disabled(struct kprobe *ap) static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; + int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) - return NULL; + return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ @@ -1626,8 +1662,13 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) * should have already been disarmed, so * skip unneed disarming process. */ - if (!kprobes_all_disarmed) - disarm_kprobe(orig_p, true); + if (!kprobes_all_disarmed) { + ret = disarm_kprobe(orig_p, true); + if (ret) { + p->flags &= ~KPROBE_FLAG_DISABLED; + return ERR_PTR(ret); + } + } orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -1644,8 +1685,8 @@ static int __unregister_kprobe_top(struct kprobe *p) /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); - if (ap == NULL) - return -EINVAL; + if (IS_ERR(ap)) + return PTR_ERR(ap); if (ap == p) /* @@ -2078,12 +2119,14 @@ static void kill_kprobe(struct kprobe *p) int disable_kprobe(struct kprobe *kp) { int ret = 0; + struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ - if (__disable_kprobe(kp) == NULL) - ret = -EINVAL; + p = __disable_kprobe(kp); + if (IS_ERR(p)) + ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; @@ -2116,7 +2159,9 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; - arm_kprobe(p); + ret = arm_kprobe(p); + if (ret) + p->flags |= KPROBE_FLAG_DISABLED; } out: mutex_unlock(&kprobe_mutex); @@ -2407,11 +2452,12 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = { .release = seq_release, }; -static void arm_all_kprobes(void) +static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); @@ -2428,46 +2474,74 @@ static void arm_all_kprobes(void) /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) - if (!kprobe_disabled(p)) - arm_kprobe(p); + /* Arm all kprobes on a best-effort basis */ + hlist_for_each_entry_rcu(p, head, hlist) { + if (!kprobe_disabled(p)) { + err = arm_kprobe(p); + if (err) { + errors++; + ret = err; + } + total++; + } + } } - printk(KERN_INFO "Kprobes globally enabled\n"); + if (errors) + pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); - return; + return ret; } -static void disarm_all_kprobes(void) +static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; - unsigned int i; + unsigned int i, total = 0, errors = 0; + int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); - return; + return 0; } kprobes_all_disarmed = true; - printk(KERN_INFO "Kprobes globally disabled\n"); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; + /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry_rcu(p, head, hlist) { - if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - disarm_kprobe(p, false); + if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { + err = disarm_kprobe(p, false); + if (err) { + errors++; + ret = err; + } + total++; + } } } + + if (errors) + pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", + errors, total); + else + pr_info("Kprobes globally disabled\n"); + mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); + + return ret; } /* @@ -2494,6 +2568,7 @@ static ssize_t write_enabled_file_bool(struct file *file, { char buf[32]; size_t buf_size; + int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) @@ -2504,17 +2579,20 @@ static ssize_t write_enabled_file_bool(struct file *file, case 'y': case 'Y': case '1': - arm_all_kprobes(); + ret = arm_all_kprobes(); break; case 'n': case 'N': case '0': - disarm_all_kprobes(); + ret = disarm_all_kprobes(); break; default: return -EINVAL; } + if (ret) + return ret; + return count; } diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 38ece035039e..d880296245c5 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -379,6 +379,14 @@ queue: tail = encode_tail(smp_processor_id(), idx); node += idx; + + /* + * Ensure that we increment the head node->count before initialising + * the actual node. If the compiler is kind enough to reorder these + * stores, then an IRQ could overwrite our assignments. + */ + barrier(); + node->locked = 0; node->next = NULL; pv_init_node(node); @@ -408,14 +416,15 @@ queue: */ if (old & _Q_TAIL_MASK) { prev = decode_tail(old); + /* - * The above xchg_tail() is also a load of @lock which - * generates, through decode_tail(), a pointer. The address - * dependency matches the RELEASE of xchg_tail() such that - * the subsequent access to @prev happens after. + * We must ensure that the stores to @node are observed before + * the write to prev->next. The address dependency from + * xchg_tail is not sufficient to ensure this because the read + * component of xchg_tail is unordered with respect to the + * initialisation of @node. */ - - WRITE_ONCE(prev->next, node); + smp_store_release(&prev->next, node); pv_wait_node(node, prev); arch_mcs_spin_lock_contended(&node->locked); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bf724c1952ea..e7c535eee0a6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2601,19 +2601,31 @@ static inline void finish_task(struct task_struct *prev) #endif } -static inline void finish_lock_switch(struct rq *rq) +static inline void +prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf) { + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ + rq_unpin_lock(rq, rf); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ - rq->lock.owner = current; + rq->lock.owner = next; #endif +} + +static inline void finish_lock_switch(struct rq *rq) +{ /* * If we are tracking spinlock dependencies then we have to * fix up the runqueue lock - which gets 'carried over' from * prev into current: */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - raw_spin_unlock_irq(&rq->lock); } @@ -2844,14 +2856,7 @@ context_switch(struct rq *rq, struct task_struct *prev, rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); - /* - * Since the runqueue lock will be released by the next - * task (which is an invalid locking op but in the case - * of the scheduler it's an obvious special-case), so we - * do an early lockdep release here: - */ - rq_unpin_lock(rq, rf); - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + prepare_lock_switch(rq, next, rf); /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index dd062a1c8cf0..7936f548e071 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -19,8 +19,6 @@ #include "sched.h" -#define SUGOV_KTHREAD_PRIORITY 50 - struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 9bb0e0c412ec..9df09782025c 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1153,6 +1153,7 @@ static void update_curr_dl(struct rq *rq) struct sched_dl_entity *dl_se = &curr->dl; u64 delta_exec, scaled_delta_exec; int cpu = cpu_of(rq); + u64 now; if (!dl_task(curr) || !on_dl_rq(dl_se)) return; @@ -1165,7 +1166,8 @@ static void update_curr_dl(struct rq *rq) * natural solution, but the full ramifications of this * approach need further study. */ - delta_exec = rq_clock_task(rq) - curr->se.exec_start; + now = rq_clock_task(rq); + delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) { if (unlikely(dl_se->dl_yielded)) goto throttle; @@ -1178,7 +1180,7 @@ static void update_curr_dl(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq_clock_task(rq); + curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 663b2355a3aa..aad49451584e 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -950,12 +950,13 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - u64 now = rq_clock_task(rq); u64 delta_exec; + u64 now; if (curr->sched_class != &rt_sched_class) return; + now = rq_clock_task(rq); delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; diff --git a/lib/dma-direct.c b/lib/dma-direct.c index 40b1f92f2214..c9e8e21cb334 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -84,6 +84,10 @@ again: return page_address(page); } +/* + * NOTE: this function must never look at the dma_addr argument, because we want + * to be able to use it as a helper for iommu implementations as well. + */ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { @@ -152,5 +156,6 @@ const struct dma_map_ops dma_direct_ops = { .map_sg = dma_direct_map_sg, .dma_supported = dma_direct_supported, .mapping_error = dma_direct_mapping_error, + .is_phys = 1, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4b80ccee4535..8291b75f42c8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1139,8 +1139,6 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - arch_unmap_kpfn(pfn); - orig_head = hpage = compound_head(p); num_poisoned_pages_inc(); diff --git a/mm/memory.c b/mm/memory.c index dd8de96f5547..5fcfc24904d1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -80,7 +80,7 @@ #include "internal.h" -#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS +#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index f3a4efcf1456..3aa5a93ad107 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -160,7 +160,8 @@ static void req_done(struct virtqueue *vq) spin_unlock_irqrestore(&chan->lock, flags); /* Wakeup if anyone waiting for VirtIO ring space. */ wake_up(chan->vc_wq); - p9_client_cb(chan->client, req, REQ_STATUS_RCVD); + if (len) + p9_client_cb(chan->client, req, REQ_STATUS_RCVD); } } diff --git a/sound/ac97/Kconfig b/sound/ac97/Kconfig index f8a64e15e5bf..baa5f8ef89d2 100644 --- a/sound/ac97/Kconfig +++ b/sound/ac97/Kconfig @@ -5,7 +5,6 @@ config AC97_BUS_NEW tristate - select AC97 help This is the new AC97 bus type, successor of AC97_BUS. The ported drivers which benefit from the AC97 automatic probing should "select" diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 60db32785f62..04d4db44fae5 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1003,7 +1003,7 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, { struct snd_seq_client *client = file->private_data; int written = 0, len; - int err = -EINVAL; + int err; struct snd_seq_event event; if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT)) @@ -1018,11 +1018,15 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, /* allocate the pool now if the pool is not allocated yet */ if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { - if (snd_seq_pool_init(client->pool) < 0) + mutex_lock(&client->ioctl_mutex); + err = snd_seq_pool_init(client->pool); + mutex_unlock(&client->ioctl_mutex); + if (err < 0) return -ENOMEM; } /* only process whole events */ + err = -EINVAL; while (count >= sizeof(struct snd_seq_event)) { /* Read in the event header from the user */ len = sizeof(event); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 23475888192b..ce28f7ce64e6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3465,6 +3465,19 @@ static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec, spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; } +static void alc269_fixup_pincfg_U7x7_headset_mic(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + unsigned int cfg_headphone = snd_hda_codec_get_pincfg(codec, 0x21); + unsigned int cfg_headset_mic = snd_hda_codec_get_pincfg(codec, 0x19); + + if (cfg_headphone && cfg_headset_mic == 0x411111f0) + snd_hda_codec_set_pincfg(codec, 0x19, + (cfg_headphone & ~AC_DEFCFG_DEVICE) | + (AC_JACK_MIC_IN << AC_DEFCFG_DEVICE_SHIFT)); +} + static void alc269_fixup_hweq(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4972,6 +4985,28 @@ static void alc_fixup_tpt440_dock(struct hda_codec *codec, } } +static void alc_fixup_tpt470_dock(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const struct hda_pintbl pincfgs[] = { + { 0x17, 0x21211010 }, /* dock headphone */ + { 0x19, 0x21a11010 }, /* dock mic */ + { } + }; + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; + /* Enable DOCK device */ + snd_hda_codec_write(codec, 0x17, 0, + AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); + /* Enable DOCK device */ + snd_hda_codec_write(codec, 0x19, 0, + AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); + snd_hda_apply_pincfgs(codec, pincfgs); + } +} + static void alc_shutup_dell_xps13(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -5351,6 +5386,7 @@ enum { ALC269_FIXUP_LIFEBOOK_EXTMIC, ALC269_FIXUP_LIFEBOOK_HP_PIN, ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT, + ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -5446,6 +5482,7 @@ enum { ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, + ALC298_FIXUP_TPT470_DOCK, }; static const struct hda_fixup alc269_fixups[] = { @@ -5556,6 +5593,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_no_hp_to_lineout, }, + [ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_pincfg_U7x7_headset_mic, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6271,6 +6312,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC274_FIXUP_DELL_BIND_DACS }, + [ALC298_FIXUP_TPT470_DOCK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_tpt470_dock, + .chained = true, + .chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6321,6 +6368,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -6422,6 +6471,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x159f, "Lifebook E780", ALC269_FIXUP_LIFEBOOK_NO_HP_TO_LINEOUT), SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), + SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), @@ -6450,8 +6500,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x222d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x222e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x224b, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -6472,7 +6530,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x5051, "Thinkpad L460", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x505d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x505f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x5062, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ @@ -6735,6 +6798,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x14, 0x90170110}, {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x14, 0x01011020}, + {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC, {0x14, 0x90170110}, @@ -6803,6 +6871,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60120}, {0x14, 0x90170110}, {0x21, 0x0321101f}), + SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0xb7a60130}, + {0x14, 0x90170110}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1, ALC290_STANDARD_PINS, {0x15, 0x04211040}, diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 9afb8ab524c7..06b22624ab7a 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -347,17 +347,20 @@ static int get_ctl_value_v2(struct usb_mixer_elem_info *cval, int request, int validx, int *value_ret) { struct snd_usb_audio *chip = cval->head.mixer->chip; - unsigned char buf[4 + 3 * sizeof(__u32)]; /* enough space for one range */ + /* enough space for one range */ + unsigned char buf[sizeof(__u16) + 3 * sizeof(__u32)]; unsigned char *val; - int idx = 0, ret, size; + int idx = 0, ret, val_size, size; __u8 bRequest; + val_size = uac2_ctl_value_size(cval->val_type); + if (request == UAC_GET_CUR) { bRequest = UAC2_CS_CUR; - size = uac2_ctl_value_size(cval->val_type); + size = val_size; } else { bRequest = UAC2_CS_RANGE; - size = sizeof(buf); + size = sizeof(__u16) + 3 * val_size; } memset(buf, 0, sizeof(buf)); @@ -390,16 +393,17 @@ error: val = buf + sizeof(__u16); break; case UAC_GET_MAX: - val = buf + sizeof(__u16) * 2; + val = buf + sizeof(__u16) + val_size; break; case UAC_GET_RES: - val = buf + sizeof(__u16) * 3; + val = buf + sizeof(__u16) + val_size * 2; break; default: return -EINVAL; } - *value_ret = convert_signed_value(cval, snd_usb_combine_bytes(val, sizeof(__u16))); + *value_ret = convert_signed_value(cval, + snd_usb_combine_bytes(val, val_size)); return 0; } diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index b9c9a19f9588..3cbfae6604f9 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -357,6 +357,15 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, alts = &iface->altsetting[1]; goto add_sync_ep; + case USB_ID(0x1397, 0x0002): + ep = 0x81; + iface = usb_ifnum_to_if(dev, 1); + + if (!iface || iface->num_altsetting == 0) + return -EINVAL; + + alts = &iface->altsetting[1]; + goto add_sync_ep; } if (attr == USB_ENDPOINT_SYNC_ASYNC && diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index a66ef5777887..ea8f3de92fa4 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1363,8 +1363,11 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; - /* Amanero Combo384 USB interface with native DSD support */ - case USB_ID(0x16d0, 0x071a): + /* Amanero Combo384 USB based DACs with native DSD support */ + case USB_ID(0x16d0, 0x071a): /* Amanero - Combo384 */ + case USB_ID(0x2ab6, 0x0004): /* T+A DAC8DSD-V2.0, MP1000E-V2.0, MP2000R-V2.0, MP2500R-V2.0, MP3100HV-V2.0 */ + case USB_ID(0x2ab6, 0x0005): /* T+A USB HD Audio 1 */ + case USB_ID(0x2ab6, 0x0006): /* T+A USB HD Audio 2 */ if (fp->altsetting == 2) { switch (le16_to_cpu(chip->dev->descriptor.bcdDevice)) { case 0x199: diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 637b7263cb86..833ed9a16adf 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) #define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) +#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/tools/arch/s390/include/uapi/asm/unistd.h b/tools/arch/s390/include/uapi/asm/unistd.h deleted file mode 100644 index 725120939051..000000000000 --- a/tools/arch/s390/include/uapi/asm/unistd.h +++ /dev/null @@ -1,412 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * S390 version - * - * Derived from "include/asm-i386/unistd.h" - */ - -#ifndef _UAPI_ASM_S390_UNISTD_H_ -#define _UAPI_ASM_S390_UNISTD_H_ - -/* - * This file contains the system call numbers. - */ - -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_restart_syscall 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_brk 45 -#define __NR_signal 48 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_setpgid 57 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_symlink 83 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_lookup_dcookie 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 /* Syscall for Andrew File System */ -#define __NR_getdents 141 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_query_module 167 -#define __NR_poll 168 -#define __NR_nfsservctl 169 -#define __NR_prctl 172 -#define __NR_rt_sigreturn 173 -#define __NR_rt_sigaction 174 -#define __NR_rt_sigprocmask 175 -#define __NR_rt_sigpending 176 -#define __NR_rt_sigtimedwait 177 -#define __NR_rt_sigqueueinfo 178 -#define __NR_rt_sigsuspend 179 -#define __NR_pread64 180 -#define __NR_pwrite64 181 -#define __NR_getcwd 183 -#define __NR_capget 184 -#define __NR_capset 185 -#define __NR_sigaltstack 186 -#define __NR_sendfile 187 -#define __NR_getpmsg 188 -#define __NR_putpmsg 189 -#define __NR_vfork 190 -#define __NR_pivot_root 217 -#define __NR_mincore 218 -#define __NR_madvise 219 -#define __NR_getdents64 220 -#define __NR_readahead 222 -#define __NR_setxattr 224 -#define __NR_lsetxattr 225 -#define __NR_fsetxattr 226 -#define __NR_getxattr 227 -#define __NR_lgetxattr 228 -#define __NR_fgetxattr 229 -#define __NR_listxattr 230 -#define __NR_llistxattr 231 -#define __NR_flistxattr 232 -#define __NR_removexattr 233 -#define __NR_lremovexattr 234 -#define __NR_fremovexattr 235 -#define __NR_gettid 236 -#define __NR_tkill 237 -#define __NR_futex 238 -#define __NR_sched_setaffinity 239 -#define __NR_sched_getaffinity 240 -#define __NR_tgkill 241 -/* Number 242 is reserved for tux */ -#define __NR_io_setup 243 -#define __NR_io_destroy 244 -#define __NR_io_getevents 245 -#define __NR_io_submit 246 -#define __NR_io_cancel 247 -#define __NR_exit_group 248 -#define __NR_epoll_create 249 -#define __NR_epoll_ctl 250 -#define __NR_epoll_wait 251 -#define __NR_set_tid_address 252 -#define __NR_fadvise64 253 -#define __NR_timer_create 254 -#define __NR_timer_settime 255 -#define __NR_timer_gettime 256 -#define __NR_timer_getoverrun 257 -#define __NR_timer_delete 258 -#define __NR_clock_settime 259 -#define __NR_clock_gettime 260 -#define __NR_clock_getres 261 -#define __NR_clock_nanosleep 262 -/* Number 263 is reserved for vserver */ -#define __NR_statfs64 265 -#define __NR_fstatfs64 266 -#define __NR_remap_file_pages 267 -#define __NR_mbind 268 -#define __NR_get_mempolicy 269 -#define __NR_set_mempolicy 270 -#define __NR_mq_open 271 -#define __NR_mq_unlink 272 -#define __NR_mq_timedsend 273 -#define __NR_mq_timedreceive 274 -#define __NR_mq_notify 275 -#define __NR_mq_getsetattr 276 -#define __NR_kexec_load 277 -#define __NR_add_key 278 -#define __NR_request_key 279 -#define __NR_keyctl 280 -#define __NR_waitid 281 -#define __NR_ioprio_set 282 -#define __NR_ioprio_get 283 -#define __NR_inotify_init 284 -#define __NR_inotify_add_watch 285 -#define __NR_inotify_rm_watch 286 -#define __NR_migrate_pages 287 -#define __NR_openat 288 -#define __NR_mkdirat 289 -#define __NR_mknodat 290 -#define __NR_fchownat 291 -#define __NR_futimesat 292 -#define __NR_unlinkat 294 -#define __NR_renameat 295 -#define __NR_linkat 296 -#define __NR_symlinkat 297 -#define __NR_readlinkat 298 -#define __NR_fchmodat 299 -#define __NR_faccessat 300 -#define __NR_pselect6 301 -#define __NR_ppoll 302 -#define __NR_unshare 303 -#define __NR_set_robust_list 304 -#define __NR_get_robust_list 305 -#define __NR_splice 306 -#define __NR_sync_file_range 307 -#define __NR_tee 308 -#define __NR_vmsplice 309 -#define __NR_move_pages 310 -#define __NR_getcpu 311 -#define __NR_epoll_pwait 312 -#define __NR_utimes 313 -#define __NR_fallocate 314 -#define __NR_utimensat 315 -#define __NR_signalfd 316 -#define __NR_timerfd 317 -#define __NR_eventfd 318 -#define __NR_timerfd_create 319 -#define __NR_timerfd_settime 320 -#define __NR_timerfd_gettime 321 -#define __NR_signalfd4 322 -#define __NR_eventfd2 323 -#define __NR_inotify_init1 324 -#define __NR_pipe2 325 -#define __NR_dup3 326 -#define __NR_epoll_create1 327 -#define __NR_preadv 328 -#define __NR_pwritev 329 -#define __NR_rt_tgsigqueueinfo 330 -#define __NR_perf_event_open 331 -#define __NR_fanotify_init 332 -#define __NR_fanotify_mark 333 -#define __NR_prlimit64 334 -#define __NR_name_to_handle_at 335 -#define __NR_open_by_handle_at 336 -#define __NR_clock_adjtime 337 -#define __NR_syncfs 338 -#define __NR_setns 339 -#define __NR_process_vm_readv 340 -#define __NR_process_vm_writev 341 -#define __NR_s390_runtime_instr 342 -#define __NR_kcmp 343 -#define __NR_finit_module 344 -#define __NR_sched_setattr 345 -#define __NR_sched_getattr 346 -#define __NR_renameat2 347 -#define __NR_seccomp 348 -#define __NR_getrandom 349 -#define __NR_memfd_create 350 -#define __NR_bpf 351 -#define __NR_s390_pci_mmio_write 352 -#define __NR_s390_pci_mmio_read 353 -#define __NR_execveat 354 -#define __NR_userfaultfd 355 -#define __NR_membarrier 356 -#define __NR_recvmmsg 357 -#define __NR_sendmmsg 358 -#define __NR_socket 359 -#define __NR_socketpair 360 -#define __NR_bind 361 -#define __NR_connect 362 -#define __NR_listen 363 -#define __NR_accept4 364 -#define __NR_getsockopt 365 -#define __NR_setsockopt 366 -#define __NR_getsockname 367 -#define __NR_getpeername 368 -#define __NR_sendto 369 -#define __NR_sendmsg 370 -#define __NR_recvfrom 371 -#define __NR_recvmsg 372 -#define __NR_shutdown 373 -#define __NR_mlock2 374 -#define __NR_copy_file_range 375 -#define __NR_preadv2 376 -#define __NR_pwritev2 377 -#define __NR_s390_guarded_storage 378 -#define __NR_statx 379 -#define __NR_s390_sthyi 380 -#define NR_syscalls 381 - -/* - * There are some system calls that are not present on 64 bit, some - * have a different name although they do the same (e.g. __NR_chown32 - * is __NR_chown on 64 bit). - */ -#ifndef __s390x__ - -#define __NR_time 13 -#define __NR_lchown 16 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_getrlimit 76 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_fchown 95 -#define __NR_ioperm 101 -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR__newselect 142 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_setresgid 170 -#define __NR_getresgid 171 -#define __NR_chown 182 -#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */ -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#define __NR_lchown32 198 -#define __NR_getuid32 199 -#define __NR_getgid32 200 -#define __NR_geteuid32 201 -#define __NR_getegid32 202 -#define __NR_setreuid32 203 -#define __NR_setregid32 204 -#define __NR_getgroups32 205 -#define __NR_setgroups32 206 -#define __NR_fchown32 207 -#define __NR_setresuid32 208 -#define __NR_getresuid32 209 -#define __NR_setresgid32 210 -#define __NR_getresgid32 211 -#define __NR_chown32 212 -#define __NR_setuid32 213 -#define __NR_setgid32 214 -#define __NR_setfsuid32 215 -#define __NR_setfsgid32 216 -#define __NR_fcntl64 221 -#define __NR_sendfile64 223 -#define __NR_fadvise64_64 264 -#define __NR_fstatat64 293 - -#else - -#define __NR_select 142 -#define __NR_getrlimit 191 /* SuS compliant getrlimit */ -#define __NR_lchown 198 -#define __NR_getuid 199 -#define __NR_getgid 200 -#define __NR_geteuid 201 -#define __NR_getegid 202 -#define __NR_setreuid 203 -#define __NR_setregid 204 -#define __NR_getgroups 205 -#define __NR_setgroups 206 -#define __NR_fchown 207 -#define __NR_setresuid 208 -#define __NR_getresuid 209 -#define __NR_setresgid 210 -#define __NR_getresgid 211 -#define __NR_chown 212 -#define __NR_setuid 213 -#define __NR_setgid 214 -#define __NR_setfsuid 215 -#define __NR_setfsgid 216 -#define __NR_newfstatat 293 - -#endif - -#endif /* _UAPI_ASM_S390_UNISTD_H_ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 1d9199e1c2ad..0dfe4d3f74e2 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -210,6 +210,7 @@ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ +#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index ac3c6503ca27..536ee4febd74 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -86,6 +86,62 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; +/* + * Different engines serve different roles, and there may be more than one + * engine serving each role. enum drm_i915_gem_engine_class provides a + * classification of the role of the engine, which may be used when requesting + * operations to be performed on a certain subset of engines, or for providing + * information about that group. + */ +enum drm_i915_gem_engine_class { + I915_ENGINE_CLASS_RENDER = 0, + I915_ENGINE_CLASS_COPY = 1, + I915_ENGINE_CLASS_VIDEO = 2, + I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + + I915_ENGINE_CLASS_INVALID = -1 +}; + +/** + * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 + * + */ + +enum drm_i915_pmu_engine_sample { + I915_SAMPLE_BUSY = 0, + I915_SAMPLE_WAIT = 1, + I915_SAMPLE_SEMA = 2 +}; + +#define I915_PMU_SAMPLE_BITS (4) +#define I915_PMU_SAMPLE_MASK (0xf) +#define I915_PMU_SAMPLE_INSTANCE_BITS (8) +#define I915_PMU_CLASS_SHIFT \ + (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS) + +#define __I915_PMU_ENGINE(class, instance, sample) \ + ((class) << I915_PMU_CLASS_SHIFT | \ + (instance) << I915_PMU_SAMPLE_BITS | \ + (sample)) + +#define I915_PMU_ENGINE_BUSY(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY) + +#define I915_PMU_ENGINE_WAIT(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT) + +#define I915_PMU_ENGINE_SEMA(class, instance) \ + __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) + +#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) + +#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) +#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) +#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) +#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) + +#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY + /* Each region is a minimum of 16k, and there are at most 255 of them. */ #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use @@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 +/* + * Query whether every context (both per-file default and user created) is + * isolated (insofar as HW supports). If this parameter is not true, then + * freshly created contexts may inherit values from an existing context, + * rather than default HW values. If true, it also ensures (insofar as HW + * supports) that all state set by this context will not leak to any other + * context. + * + * As not every engine across every gen support contexts, the returned + * value reports the support of context isolation for individual engines by + * returning a bitmask of each engine class set to true if that class supports + * isolation. + */ +#define I915_PARAM_HAS_CONTEXT_ISOLATION 50 + +/* Frequency of the command streamer timestamps given by the *_TIMESTAMP + * registers. This used to be fixed per platform but from CNL onwards, this + * might vary depending on the parts. + */ +#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51 + typedef struct drm_i915_getparam { __s32 param; /* diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8616131e2c61..6d9447700e18 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -163,6 +163,7 @@ enum { IFLA_IF_NETNSID, IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, __IFLA_MAX }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 8fb90a0819c3..0fb5ef939732 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1362,6 +1362,96 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_S390_CMMA_MIGRATION */ #define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) +/* Memory Encryption Commands */ +#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long) + +struct kvm_enc_region { + __u64 addr; + __u64 size; +}; + +#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region) +#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region) + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; +}; #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index b00b1896547e..a8cb69a26576 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -852,8 +852,14 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func, * This is a fairly uncommon pattern which is new for GCC 6. As of this * writing, there are 11 occurrences of it in the allmodconfig kernel. * + * As of GCC 7 there are quite a few more of these and the 'in between' code + * is significant. Esp. with KASAN enabled some of the code between the mov + * and jmpq uses .rodata itself, which can confuse things. + * * TODO: Once we have DWARF CFI and smarter instruction decoding logic, * ensure the same register is used in the mov and jump instructions. + * + * NOTE: RETPOLINE made it harder still to decode dynamic jumps. */ static struct rela *find_switch_table(struct objtool_file *file, struct symbol *func, @@ -875,12 +881,25 @@ static struct rela *find_switch_table(struct objtool_file *file, text_rela->addend + 4); if (!rodata_rela) return NULL; + file->ignore_unreachables = true; return rodata_rela; } /* case 3 */ - func_for_each_insn_continue_reverse(file, func, insn) { + /* + * Backward search using the @first_jump_src links, these help avoid + * much of the 'in between' code. Which avoids us getting confused by + * it. + */ + for (insn = list_prev_entry(insn, list); + + &insn->list != &file->insn_list && + insn->sec == func->sec && + insn->offset >= func->offset; + + insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { + if (insn->type == INSN_JUMP_DYNAMIC) break; @@ -910,14 +929,32 @@ static struct rela *find_switch_table(struct objtool_file *file, return NULL; } + static int add_func_switch_tables(struct objtool_file *file, struct symbol *func) { - struct instruction *insn, *prev_jump = NULL; + struct instruction *insn, *last = NULL, *prev_jump = NULL; struct rela *rela, *prev_rela = NULL; int ret; func_for_each_insn(file, func, insn) { + if (!last) + last = insn; + + /* + * Store back-pointers for unconditional forward jumps such + * that find_switch_table() can back-track using those and + * avoid some potentially confusing code. + */ + if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest && + insn->offset > last->offset && + insn->jump_dest->offset > insn->offset && + !insn->jump_dest->first_jump_src) { + + insn->jump_dest->first_jump_src = insn; + last = insn->jump_dest; + } + if (insn->type != INSN_JUMP_DYNAMIC) continue; @@ -1899,13 +1936,19 @@ static bool ignore_unreachable_insn(struct instruction *insn) if (is_kasan_insn(insn) || is_ubsan_insn(insn)) return true; - if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) { - insn = insn->jump_dest; - continue; + if (insn->type == INSN_JUMP_UNCONDITIONAL) { + if (insn->jump_dest && + insn->jump_dest->func == insn->func) { + insn = insn->jump_dest; + continue; + } + + break; } if (insn->offset + insn->len >= insn->func->offset + insn->func->len) break; + insn = list_next_entry(insn, list); } diff --git a/tools/objtool/check.h b/tools/objtool/check.h index dbadb304a410..23a1d065cae1 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -47,6 +47,7 @@ struct instruction { bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; struct symbol *call_dest; struct instruction *jump_dest; + struct instruction *first_jump_src; struct list_head alts; struct symbol *func; struct stack_op stack_op; diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt index f0796a47dfa3..90bb4aabe4f8 100644 --- a/tools/perf/Documentation/perf-data.txt +++ b/tools/perf/Documentation/perf-data.txt @@ -30,6 +30,10 @@ OPTIONS for 'convert' -i:: Specify input perf data file path. +-f:: +--force:: + Don't complain, do it. + -v:: --verbose:: Be more verbose (show counter open errors, etc). diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 48228de415d0..dfa6e3103437 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -10,15 +10,19 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/s390/include/generated/asm header := $(out)/syscalls_64.c -sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/ +syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl +sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls +sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@ + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B $(sysdef) $(syskrn) >/dev/null) \ + || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ clean:: $(call QUIET_CLEAN, s390) $(RM) $(header) diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl index 7fa0d0abd419..72ecbb676370 100755 --- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl @@ -3,25 +3,23 @@ # # Generate system call table for perf # -# -# Copyright IBM Corp. 2017 +# Copyright IBM Corp. 2017, 2018 # Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> # -gcc=$1 -input=$2 +SYSCALL_TBL=$1 -if ! test -r $input; then +if ! test -r $SYSCALL_TBL; then echo "Could not read input file" >&2 exit 1 fi create_table() { - local max_nr + local max_nr nr abi sc discard echo 'static const char *syscalltbl_s390_64[] = {' - while read sc nr; do + while read nr abi sc discard; do printf '\t[%d] = "%s",\n' $nr $sc max_nr=$nr done @@ -29,8 +27,6 @@ create_table() echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr" } - -$gcc -m64 -E -dM -x c $input \ - |sed -ne 's/^#define __NR_//p' \ - |sort -t' ' -k2 -nu \ +grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL \ + |sort -k1 -n \ |create_table diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..b38d48464368 --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -0,0 +1,390 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# System call table for s390 +# +# Format: +# +# <nr> <abi> <syscall> <entry-64bit> <compat-entry> +# +# where <abi> can be common, 64, or 32 + +1 common exit sys_exit sys_exit +2 common fork sys_fork sys_fork +3 common read sys_read compat_sys_s390_read +4 common write sys_write compat_sys_s390_write +5 common open sys_open compat_sys_open +6 common close sys_close sys_close +7 common restart_syscall sys_restart_syscall sys_restart_syscall +8 common creat sys_creat compat_sys_creat +9 common link sys_link compat_sys_link +10 common unlink sys_unlink compat_sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir compat_sys_chdir +13 32 time - compat_sys_time +14 common mknod sys_mknod compat_sys_mknod +15 common chmod sys_chmod compat_sys_chmod +16 32 lchown - compat_sys_s390_lchown16 +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid sys_getpid +21 common mount sys_mount compat_sys_mount +22 common umount sys_oldumount compat_sys_oldumount +23 32 setuid - compat_sys_s390_setuid16 +24 32 getuid - compat_sys_s390_getuid16 +25 32 stime - compat_sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm sys_alarm +29 common pause sys_pause sys_pause +30 common utime sys_utime compat_sys_utime +33 common access sys_access compat_sys_access +34 common nice sys_nice sys_nice +36 common sync sys_sync sys_sync +37 common kill sys_kill sys_kill +38 common rename sys_rename compat_sys_rename +39 common mkdir sys_mkdir compat_sys_mkdir +40 common rmdir sys_rmdir compat_sys_rmdir +41 common dup sys_dup sys_dup +42 common pipe sys_pipe compat_sys_pipe +43 common times sys_times compat_sys_times +45 common brk sys_brk compat_sys_brk +46 32 setgid - compat_sys_s390_setgid16 +47 32 getgid - compat_sys_s390_getgid16 +48 common signal sys_signal compat_sys_signal +49 32 geteuid - compat_sys_s390_geteuid16 +50 32 getegid - compat_sys_s390_getegid16 +51 common acct sys_acct compat_sys_acct +52 common umount2 sys_umount compat_sys_umount +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +57 common setpgid sys_setpgid sys_setpgid +60 common umask sys_umask sys_umask +61 common chroot sys_chroot compat_sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 sys_dup2 +64 common getppid sys_getppid sys_getppid +65 common getpgrp sys_getpgrp sys_getpgrp +66 common setsid sys_setsid sys_setsid +67 common sigaction sys_sigaction compat_sys_sigaction +70 32 setreuid - compat_sys_s390_setreuid16 +71 32 setregid - compat_sys_s390_setregid16 +72 common sigsuspend sys_sigsuspend compat_sys_sigsuspend +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname compat_sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 32 getrlimit - compat_sys_old_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 32 getgroups - compat_sys_s390_getgroups16 +81 32 setgroups - compat_sys_s390_setgroups16 +83 common symlink sys_symlink compat_sys_symlink +85 common readlink sys_readlink compat_sys_readlink +86 common uselib sys_uselib compat_sys_uselib +87 common swapon sys_swapon compat_sys_swapon +88 common reboot sys_reboot compat_sys_reboot +89 common readdir - compat_sys_old_readdir +90 common mmap sys_old_mmap compat_sys_s390_old_mmap +91 common munmap sys_munmap compat_sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod sys_fchmod +95 32 fchown - compat_sys_s390_fchown16 +96 common getpriority sys_getpriority sys_getpriority +97 common setpriority sys_setpriority sys_setpriority +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +101 32 ioperm - - +102 common socketcall sys_socketcall compat_sys_socketcall +103 common syslog sys_syslog compat_sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +110 common lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +111 common vhangup sys_vhangup sys_vhangup +112 common idle - - +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff compat_sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 common ipc sys_s390_ipc compat_sys_s390_ipc +118 common fsync sys_fsync sys_fsync +119 common sigreturn sys_sigreturn compat_sys_sigreturn +120 common clone sys_clone compat_sys_clone +121 common setdomainname sys_setdomainname compat_sys_setdomainname +122 common uname sys_newuname compat_sys_newuname +124 common adjtimex sys_adjtimex compat_sys_adjtimex +125 common mprotect sys_mprotect compat_sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +127 common create_module - - +128 common init_module sys_init_module compat_sys_init_module +129 common delete_module sys_delete_module compat_sys_delete_module +130 common get_kernel_syms - - +131 common quotactl sys_quotactl compat_sys_quotactl +132 common getpgid sys_getpgid sys_getpgid +133 common fchdir sys_fchdir sys_fchdir +134 common bdflush sys_bdflush compat_sys_bdflush +135 common sysfs sys_sysfs compat_sys_sysfs +136 common personality sys_s390_personality sys_s390_personality +137 common afs_syscall - - +138 32 setfsuid - compat_sys_s390_setfsuid16 +139 32 setfsgid - compat_sys_s390_setfsgid16 +140 32 _llseek - compat_sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 32 _newselect - compat_sys_select +142 64 select sys_select - +143 common flock sys_flock sys_flock +144 common msync sys_msync compat_sys_msync +145 common readv sys_readv compat_sys_readv +146 common writev sys_writev compat_sys_writev +147 common getsid sys_getsid sys_getsid +148 common fdatasync sys_fdatasync sys_fdatasync +149 common _sysctl sys_sysctl compat_sys_sysctl +150 common mlock sys_mlock compat_sys_mlock +151 common munlock sys_munlock compat_sys_munlock +152 common mlockall sys_mlockall sys_mlockall +153 common munlockall sys_munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam compat_sys_sched_setparam +155 common sched_getparam sys_sched_getparam compat_sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler compat_sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep compat_sys_nanosleep +163 common mremap sys_mremap compat_sys_mremap +164 32 setresuid - compat_sys_s390_setresuid16 +165 32 getresuid - compat_sys_s390_getresuid16 +167 common query_module - - +168 common poll sys_poll compat_sys_poll +169 common nfsservctl - - +170 32 setresgid - compat_sys_s390_setresgid16 +171 32 getresgid - compat_sys_s390_getresgid16 +172 common prctl sys_prctl compat_sys_prctl +173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common pread64 sys_pread64 compat_sys_s390_pread64 +181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 +182 32 chown - compat_sys_s390_chown16 +183 common getcwd sys_getcwd compat_sys_getcwd +184 common capget sys_capget compat_sys_capget +185 common capset sys_capset compat_sys_capset +186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +187 common sendfile sys_sendfile64 compat_sys_sendfile +188 common getpmsg - - +189 common putpmsg - - +190 common vfork sys_vfork sys_vfork +191 32 ugetrlimit - compat_sys_getrlimit +191 64 getrlimit sys_getrlimit - +192 32 mmap2 - compat_sys_s390_mmap2 +193 32 truncate64 - compat_sys_s390_truncate64 +194 32 ftruncate64 - compat_sys_s390_ftruncate64 +195 32 stat64 - compat_sys_s390_stat64 +196 32 lstat64 - compat_sys_s390_lstat64 +197 32 fstat64 - compat_sys_s390_fstat64 +198 32 lchown32 - compat_sys_lchown +198 64 lchown sys_lchown - +199 32 getuid32 - sys_getuid +199 64 getuid sys_getuid - +200 32 getgid32 - sys_getgid +200 64 getgid sys_getgid - +201 32 geteuid32 - sys_geteuid +201 64 geteuid sys_geteuid - +202 32 getegid32 - sys_getegid +202 64 getegid sys_getegid - +203 32 setreuid32 - sys_setreuid +203 64 setreuid sys_setreuid - +204 32 setregid32 - sys_setregid +204 64 setregid sys_setregid - +205 32 getgroups32 - compat_sys_getgroups +205 64 getgroups sys_getgroups - +206 32 setgroups32 - compat_sys_setgroups +206 64 setgroups sys_setgroups - +207 32 fchown32 - sys_fchown +207 64 fchown sys_fchown - +208 32 setresuid32 - sys_setresuid +208 64 setresuid sys_setresuid - +209 32 getresuid32 - compat_sys_getresuid +209 64 getresuid sys_getresuid - +210 32 setresgid32 - sys_setresgid +210 64 setresgid sys_setresgid - +211 32 getresgid32 - compat_sys_getresgid +211 64 getresgid sys_getresgid - +212 32 chown32 - compat_sys_chown +212 64 chown sys_chown - +213 32 setuid32 - sys_setuid +213 64 setuid sys_setuid - +214 32 setgid32 - sys_setgid +214 64 setgid sys_setgid - +215 32 setfsuid32 - sys_setfsuid +215 64 setfsuid sys_setfsuid - +216 32 setfsgid32 - sys_setfsgid +216 64 setfsgid sys_setfsgid - +217 common pivot_root sys_pivot_root compat_sys_pivot_root +218 common mincore sys_mincore compat_sys_mincore +219 common madvise sys_madvise compat_sys_madvise +220 common getdents64 sys_getdents64 compat_sys_getdents64 +221 32 fcntl64 - compat_sys_fcntl64 +222 common readahead sys_readahead compat_sys_s390_readahead +223 32 sendfile64 - compat_sys_sendfile64 +224 common setxattr sys_setxattr compat_sys_setxattr +225 common lsetxattr sys_lsetxattr compat_sys_lsetxattr +226 common fsetxattr sys_fsetxattr compat_sys_fsetxattr +227 common getxattr sys_getxattr compat_sys_getxattr +228 common lgetxattr sys_lgetxattr compat_sys_lgetxattr +229 common fgetxattr sys_fgetxattr compat_sys_fgetxattr +230 common listxattr sys_listxattr compat_sys_listxattr +231 common llistxattr sys_llistxattr compat_sys_llistxattr +232 common flistxattr sys_flistxattr compat_sys_flistxattr +233 common removexattr sys_removexattr compat_sys_removexattr +234 common lremovexattr sys_lremovexattr compat_sys_lremovexattr +235 common fremovexattr sys_fremovexattr compat_sys_fremovexattr +236 common gettid sys_gettid sys_gettid +237 common tkill sys_tkill sys_tkill +238 common futex sys_futex compat_sys_futex +239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +241 common tgkill sys_tgkill sys_tgkill +243 common io_setup sys_io_setup compat_sys_io_setup +244 common io_destroy sys_io_destroy compat_sys_io_destroy +245 common io_getevents sys_io_getevents compat_sys_io_getevents +246 common io_submit sys_io_submit compat_sys_io_submit +247 common io_cancel sys_io_cancel compat_sys_io_cancel +248 common exit_group sys_exit_group sys_exit_group +249 common epoll_create sys_epoll_create sys_epoll_create +250 common epoll_ctl sys_epoll_ctl compat_sys_epoll_ctl +251 common epoll_wait sys_epoll_wait compat_sys_epoll_wait +252 common set_tid_address sys_set_tid_address compat_sys_set_tid_address +253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 +254 common timer_create sys_timer_create compat_sys_timer_create +255 common timer_settime sys_timer_settime compat_sys_timer_settime +256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun +258 common timer_delete sys_timer_delete sys_timer_delete +259 common clock_settime sys_clock_settime compat_sys_clock_settime +260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime +261 common clock_getres sys_clock_getres compat_sys_clock_getres +262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 +265 common statfs64 sys_statfs64 compat_sys_statfs64 +266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +267 common remap_file_pages sys_remap_file_pages compat_sys_remap_file_pages +268 common mbind sys_mbind compat_sys_mbind +269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +271 common mq_open sys_mq_open compat_sys_mq_open +272 common mq_unlink sys_mq_unlink compat_sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend +274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +275 common mq_notify sys_mq_notify compat_sys_mq_notify +276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +277 common kexec_load sys_kexec_load compat_sys_kexec_load +278 common add_key sys_add_key compat_sys_add_key +279 common request_key sys_request_key compat_sys_request_key +280 common keyctl sys_keyctl compat_sys_keyctl +281 common waitid sys_waitid compat_sys_waitid +282 common ioprio_set sys_ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get sys_ioprio_get +284 common inotify_init sys_inotify_init sys_inotify_init +285 common inotify_add_watch sys_inotify_add_watch compat_sys_inotify_add_watch +286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch +287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages +288 common openat sys_openat compat_sys_openat +289 common mkdirat sys_mkdirat compat_sys_mkdirat +290 common mknodat sys_mknodat compat_sys_mknodat +291 common fchownat sys_fchownat compat_sys_fchownat +292 common futimesat sys_futimesat compat_sys_futimesat +293 32 fstatat64 - compat_sys_s390_fstatat64 +293 64 newfstatat sys_newfstatat - +294 common unlinkat sys_unlinkat compat_sys_unlinkat +295 common renameat sys_renameat compat_sys_renameat +296 common linkat sys_linkat compat_sys_linkat +297 common symlinkat sys_symlinkat compat_sys_symlinkat +298 common readlinkat sys_readlinkat compat_sys_readlinkat +299 common fchmodat sys_fchmodat compat_sys_fchmodat +300 common faccessat sys_faccessat compat_sys_faccessat +301 common pselect6 sys_pselect6 compat_sys_pselect6 +302 common ppoll sys_ppoll compat_sys_ppoll +303 common unshare sys_unshare compat_sys_unshare +304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +306 common splice sys_splice compat_sys_splice +307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range +308 common tee sys_tee compat_sys_tee +309 common vmsplice sys_vmsplice compat_sys_vmsplice +310 common move_pages sys_move_pages compat_sys_move_pages +311 common getcpu sys_getcpu compat_sys_getcpu +312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +313 common utimes sys_utimes compat_sys_utimes +314 common fallocate sys_fallocate compat_sys_s390_fallocate +315 common utimensat sys_utimensat compat_sys_utimensat +316 common signalfd sys_signalfd compat_sys_signalfd +317 common timerfd - - +318 common eventfd sys_eventfd sys_eventfd +319 common timerfd_create sys_timerfd_create sys_timerfd_create +320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime +321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +323 common eventfd2 sys_eventfd2 sys_eventfd2 +324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 +325 common pipe2 sys_pipe2 compat_sys_pipe2 +326 common dup3 sys_dup3 sys_dup3 +327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 +328 common preadv sys_preadv compat_sys_preadv +329 common pwritev sys_pwritev compat_sys_pwritev +330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +331 common perf_event_open sys_perf_event_open compat_sys_perf_event_open +332 common fanotify_init sys_fanotify_init sys_fanotify_init +333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +334 common prlimit64 sys_prlimit64 compat_sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at compat_sys_name_to_handle_at +336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +338 common syncfs sys_syncfs sys_syncfs +339 common setns sys_setns sys_setns +340 common process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr +343 common kcmp sys_kcmp compat_sys_kcmp +344 common finit_module sys_finit_module compat_sys_finit_module +345 common sched_setattr sys_sched_setattr compat_sys_sched_setattr +346 common sched_getattr sys_sched_getattr compat_sys_sched_getattr +347 common renameat2 sys_renameat2 compat_sys_renameat2 +348 common seccomp sys_seccomp compat_sys_seccomp +349 common getrandom sys_getrandom compat_sys_getrandom +350 common memfd_create sys_memfd_create compat_sys_memfd_create +351 common bpf sys_bpf compat_sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write compat_sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read compat_sys_s390_pci_mmio_read +354 common execveat sys_execveat compat_sys_execveat +355 common userfaultfd sys_userfaultfd sys_userfaultfd +356 common membarrier sys_membarrier sys_membarrier +357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +359 common socket sys_socket sys_socket +360 common socketpair sys_socketpair compat_sys_socketpair +361 common bind sys_bind compat_sys_bind +362 common connect sys_connect compat_sys_connect +363 common listen sys_listen sys_listen +364 common accept4 sys_accept4 compat_sys_accept4 +365 common getsockopt sys_getsockopt compat_sys_getsockopt +366 common setsockopt sys_setsockopt compat_sys_setsockopt +367 common getsockname sys_getsockname compat_sys_getsockname +368 common getpeername sys_getpeername compat_sys_getpeername +369 common sendto sys_sendto compat_sys_sendto +370 common sendmsg sys_sendmsg compat_sys_sendmsg +371 common recvfrom sys_recvfrom compat_sys_recvfrom +372 common recvmsg sys_recvmsg compat_sys_recvmsg +373 common shutdown sys_shutdown sys_shutdown +374 common mlock2 sys_mlock2 compat_sys_mlock2 +375 common copy_file_range sys_copy_file_range compat_sys_copy_file_range +376 common preadv2 sys_preadv2 compat_sys_preadv2 +377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage +379 common statx sys_statx compat_sys_statx +380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index c0815a37fdb5..539c3d460158 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2245,7 +2245,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help"); + key = hist_browser__run(browser, "? - help", true); switch (key) { case 's': @@ -2314,7 +2314,7 @@ static int perf_c2c__hists_browse(struct hists *hists) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help"); + key = hist_browser__run(browser, "? - help", true); switch (key) { case 'q': diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 42a52dcc41cd..4ad5dc649716 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -530,7 +530,8 @@ static int report__browse_hists(struct report *rep) case 1: ret = perf_evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, - &session->header.env); + &session->header.env, + true); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c6ccda52117d..b7c823ba8374 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -283,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top) printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - if (hists->stats.nr_lost_warned != - hists->stats.nr_events[PERF_RECORD_LOST]) { + if (!top->record_opts.overwrite && + (hists->stats.nr_lost_warned != + hists->stats.nr_events[PERF_RECORD_LOST])) { hists->stats.nr_lost_warned = hists->stats.nr_events[PERF_RECORD_LOST]; color_fprintf(stdout, PERF_COLOR_RED, @@ -611,7 +612,8 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, - &top->session->header.env); + &top->session->header.env, + !top->record_opts.overwrite); done = 1; return NULL; @@ -807,15 +809,23 @@ static void perf_event__process_sample(struct perf_tool *tool, static void perf_top__mmap_read_idx(struct perf_top *top, int idx) { + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; struct perf_sample sample; struct perf_evsel *evsel; + struct perf_mmap *md; struct perf_session *session = top->session; union perf_event *event; struct machine *machine; + u64 end, start; int ret; - while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) { - ret = perf_evlist__parse_sample(top->evlist, event, &sample); + md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx]; + if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0) + return; + + while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) { + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); goto next_event; @@ -869,16 +879,120 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) } else ++session->evlist->stats.nr_unknown_events; next_event: - perf_evlist__mmap_consume(top->evlist, idx); + perf_mmap__consume(md, opts->overwrite); } + + perf_mmap__read_done(md); } static void perf_top__mmap_read(struct perf_top *top) { + bool overwrite = top->record_opts.overwrite; + struct perf_evlist *evlist = top->evlist; + unsigned long long start, end; int i; + start = rdclock(); + if (overwrite) + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); + for (i = 0; i < top->evlist->nr_mmaps; i++) perf_top__mmap_read_idx(top, i); + + if (overwrite) { + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + } + end = rdclock(); + + if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC) + ui__warning("Too slow to read ring buffer.\n" + "Please try increasing the period (-c) or\n" + "decreasing the freq (-F) or\n" + "limiting the number of CPUs (-C)\n"); +} + +/* + * Check per-event overwrite term. + * perf top should support consistent term for all events. + * - All events don't have per-event term + * E.g. "cpu/cpu-cycles/,cpu/instructions/" + * Nothing change, return 0. + * - All events have same per-event term + * E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/ + * Using the per-event setting to replace the opts->overwrite if + * they are different, then return 0. + * - Events have different per-event term + * E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/" + * Return -1 + * - Some of the event set per-event term, but some not. + * E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/" + * Return -1 + */ +static int perf_top__overwrite_check(struct perf_top *top) +{ + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; + struct perf_evsel_config_term *term; + struct list_head *config_terms; + struct perf_evsel *evsel; + int set, overwrite = -1; + + evlist__for_each_entry(evlist, evsel) { + set = -1; + config_terms = &evsel->config_terms; + list_for_each_entry(term, config_terms, list) { + if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE) + set = term->val.overwrite ? 1 : 0; + } + + /* no term for current and previous event (likely) */ + if ((overwrite < 0) && (set < 0)) + continue; + + /* has term for both current and previous event, compare */ + if ((overwrite >= 0) && (set >= 0) && (overwrite != set)) + return -1; + + /* no term for current event but has term for previous one */ + if ((overwrite >= 0) && (set < 0)) + return -1; + + /* has term for current event */ + if ((overwrite < 0) && (set >= 0)) { + /* if it's first event, set overwrite */ + if (evsel == perf_evlist__first(evlist)) + overwrite = set; + else + return -1; + } + } + + if ((overwrite >= 0) && (opts->overwrite != overwrite)) + opts->overwrite = overwrite; + + return 0; +} + +static int perf_top_overwrite_fallback(struct perf_top *top, + struct perf_evsel *evsel) +{ + struct record_opts *opts = &top->record_opts; + struct perf_evlist *evlist = top->evlist; + struct perf_evsel *counter; + + if (!opts->overwrite) + return 0; + + /* only fall back when first event fails */ + if (evsel != perf_evlist__first(evlist)) + return 0; + + evlist__for_each_entry(evlist, counter) + counter->attr.write_backward = false; + opts->overwrite = false; + ui__warning("fall back to non-overwrite mode\n"); + return 1; } static int perf_top__start_counters(struct perf_top *top) @@ -888,12 +1002,33 @@ static int perf_top__start_counters(struct perf_top *top) struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; + if (perf_top__overwrite_check(top)) { + ui__error("perf top only support consistent per-event " + "overwrite setting for all events\n"); + goto out_err; + } + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, counter) { try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { + + /* + * Specially handle overwrite fall back. + * Because perf top is the only tool which has + * overwrite mode by default, support + * both overwrite and non-overwrite mode, and + * require consistent mode for all events. + * + * May move it to generic code with more tools + * have similar attribute. + */ + if (perf_missing_features.write_backward && + perf_top_overwrite_fallback(top, counter)) + goto try_again; + if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); @@ -1033,7 +1168,7 @@ static int __cmd_top(struct perf_top *top) perf_top__mmap_read(top); - if (hits == top->samples) + if (opts->overwrite || (hits == top->samples)) ret = perf_evlist__poll(top->evlist, 100); if (resize) { @@ -1127,6 +1262,7 @@ int cmd_top(int argc, const char **argv) .uses_mmap = true, }, .proc_map_timeout = 500, + .overwrite = 1, }, .max_stack = sysctl_perf_event_max_stack, .sym_pcnt_filter = 5, diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 51abdb0a4047..790ec25919a0 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -33,7 +33,6 @@ arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm_perf.h arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h -arch/s390/include/uapi/asm/unistd.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h arch/alpha/include/uapi/asm/errno.h diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json new file mode 100644 index 000000000000..3b6208763e50 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json @@ -0,0 +1,27 @@ +[ + {, + "EventCode": "0x7A", + "EventName": "BR_INDIRECT_SPEC", + "BriefDescription": "Branch speculatively executed - Indirect branch" + }, + {, + "EventCode": "0xC9", + "EventName": "BR_COND", + "BriefDescription": "Conditional branch executed" + }, + {, + "EventCode": "0xCA", + "EventName": "BR_INDIRECT_MISPRED", + "BriefDescription": "Indirect branch mispredicted" + }, + {, + "EventCode": "0xCB", + "EventName": "BR_INDIRECT_MISPRED_ADDR", + "BriefDescription": "Indirect branch mispredicted because of address miscompare" + }, + {, + "EventCode": "0xCC", + "EventName": "BR_COND_MISPRED", + "BriefDescription": "Conditional branch mispredicted" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json new file mode 100644 index 000000000000..480d9f7460ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json @@ -0,0 +1,22 @@ +[ + {, + "EventCode": "0x60", + "EventName": "BUS_ACCESS_LD", + "BriefDescription": "Bus access - Read" + }, + {, + "EventCode": "0x61", + "EventName": "BUS_ACCESS_ST", + "BriefDescription": "Bus access - Write" + }, + {, + "EventCode": "0xC0", + "EventName": "EXT_MEM_REQ", + "BriefDescription": "External memory request" + }, + {, + "EventCode": "0xC1", + "EventName": "EXT_MEM_REQ_NC", + "BriefDescription": "Non-cacheable external memory request" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json new file mode 100644 index 000000000000..11baad6344b9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json @@ -0,0 +1,27 @@ +[ + {, + "EventCode": "0xC2", + "EventName": "PREFETCH_LINEFILL", + "BriefDescription": "Linefill because of prefetch" + }, + {, + "EventCode": "0xC3", + "EventName": "PREFETCH_LINEFILL_DROP", + "BriefDescription": "Instruction Cache Throttle occurred" + }, + {, + "EventCode": "0xC4", + "EventName": "READ_ALLOC_ENTER", + "BriefDescription": "Entering read allocate mode" + }, + {, + "EventCode": "0xC5", + "EventName": "READ_ALLOC", + "BriefDescription": "Read allocate mode" + }, + {, + "EventCode": "0xC8", + "EventName": "EXT_SNOOP", + "BriefDescription": "SCU Snooped data from another CPU for this CPU" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json new file mode 100644 index 000000000000..480d9f7460ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json @@ -0,0 +1,22 @@ +[ + {, + "EventCode": "0x60", + "EventName": "BUS_ACCESS_LD", + "BriefDescription": "Bus access - Read" + }, + {, + "EventCode": "0x61", + "EventName": "BUS_ACCESS_ST", + "BriefDescription": "Bus access - Write" + }, + {, + "EventCode": "0xC0", + "EventName": "EXT_MEM_REQ", + "BriefDescription": "External memory request" + }, + {, + "EventCode": "0xC1", + "EventName": "EXT_MEM_REQ_NC", + "BriefDescription": "Non-cacheable external memory request" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json new file mode 100644 index 000000000000..73a22402d003 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json @@ -0,0 +1,32 @@ +[ + {, + "EventCode": "0x86", + "EventName": "EXC_IRQ", + "BriefDescription": "Exception taken, IRQ" + }, + {, + "EventCode": "0x87", + "EventName": "EXC_FIQ", + "BriefDescription": "Exception taken, FIQ" + }, + {, + "EventCode": "0xC6", + "EventName": "PRE_DECODE_ERR", + "BriefDescription": "Pre-decode error" + }, + {, + "EventCode": "0xD0", + "EventName": "L1I_CACHE_ERR", + "BriefDescription": "L1 Instruction Cache (data or tag) memory error" + }, + {, + "EventCode": "0xD1", + "EventName": "L1D_CACHE_ERR", + "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable" + }, + {, + "EventCode": "0xD2", + "EventName": "TLB_ERR", + "BriefDescription": "TLB memory error" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json new file mode 100644 index 000000000000..3149fb90555a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json @@ -0,0 +1,52 @@ +[ + {, + "EventCode": "0xC7", + "EventName": "STALL_SB_FULL", + "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full" + }, + {, + "EventCode": "0xE0", + "EventName": "OTHER_IQ_DEP_STALL", + "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error" + }, + {, + "EventCode": "0xE1", + "EventName": "IC_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed" + }, + {, + "EventCode": "0xE2", + "EventName": "IUTLB_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed" + }, + {, + "EventCode": "0xE3", + "EventName": "DECODE_DEP_STALL", + "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed" + }, + {, + "EventCode": "0xE4", + "EventName": "OTHER_INTERLOCK_STALL", + "BriefDescription": "Cycles there is an interlock other than Advanced SIMD/Floating-point instructions or load/store instruction" + }, + {, + "EventCode": "0xE5", + "EventName": "AGU_DEP_STALL", + "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU" + }, + {, + "EventCode": "0xE6", + "EventName": "SIMD_DEP_STALL", + "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation." + }, + {, + "EventCode": "0xE7", + "EventName": "LD_DEP_STALL", + "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss" + }, + {, + "EventCode": "0xE8", + "EventName": "ST_DEP_STALL", + "BriefDescription": "Cycles there is a stall in the Wr stage because of a store" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 219d6756134e..e61c9ca6cf9e 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -13,3 +13,4 @@ # #Family-model,Version,Filename,EventType 0x00000000420f5160,v1,cavium,core +0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 4035d43523c3..e0b1b414d466 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -31,10 +31,12 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, int i; for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *map = &evlist->overwrite_mmap[i]; union perf_event *event; + u64 start, end; - perf_mmap__read_catchup(&evlist->overwrite_mmap[i]); - while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) { + perf_mmap__read_init(map, true, &start, &end); + while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) { const u32 type = event->header.type; switch (type) { @@ -49,6 +51,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, return TEST_FAIL; } } + perf_mmap__read_done(map); } return TEST_OK; } diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh index 8b3da21a08f1..c446c894b297 100755 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -22,10 +22,23 @@ trace_libc_inet_pton_backtrace() { expected[4]="rtt min.*" expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" expected[6]=".*inet_pton[[:space:]]\($libc\)$" - expected[7]="getaddrinfo[[:space:]]\($libc\)$" - expected[8]=".*\(.*/bin/ping.*\)$" - - perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do + case "$(uname -m)" in + s390x) + eventattr='call-graph=dwarf' + expected[7]="gaih_inet[[:space:]]\(inlined\)$" + expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$" + expected[9]="main[[:space:]]\(.*/bin/ping.*\)$" + expected[10]="__libc_start_main[[:space:]]\($libc\)$" + expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$" + ;; + *) + eventattr='max-stack=3' + expected[7]="getaddrinfo[[:space:]]\($libc\)$" + expected[8]=".*\(.*/bin/ping.*\)$" + ;; + esac + + perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do echo $line echo "$line" | egrep -q "${expected[$idx]}" if [ $? -ne 0 ] ; then @@ -33,7 +46,7 @@ trace_libc_inet_pton_backtrace() { exit 1 fi let idx+=1 - [ $idx -eq 9 ] && break + [ -z "${expected[$idx]}" ] && break done } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 68146f4620a5..6495ee55d9c3 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -608,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si return browser->title ? browser->title(browser, bf, size) : 0; } -int hist_browser__run(struct hist_browser *browser, const char *help) +int hist_browser__run(struct hist_browser *browser, const char *help, + bool warn_lost_event) { int key; char title[160]; @@ -638,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help) nr_entries = hist_browser__nr_entries(browser); ui_browser__update_nr_entries(&browser->b, nr_entries); - if (browser->hists->stats.nr_lost_warned != - browser->hists->stats.nr_events[PERF_RECORD_LOST]) { + if (warn_lost_event && + (browser->hists->stats.nr_lost_warned != + browser->hists->stats.nr_events[PERF_RECORD_LOST])) { browser->hists->stats.nr_lost_warned = browser->hists->stats.nr_events[PERF_RECORD_LOST]; ui_browser__warn_lost_events(&browser->b); @@ -2763,7 +2765,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { struct hists *hists = evsel__hists(evsel); struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env); @@ -2844,7 +2847,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options = 0; - key = hist_browser__run(browser, helpline); + key = hist_browser__run(browser, helpline, + warn_lost_event); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -3184,7 +3188,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser, static int perf_evsel_menu__run(struct perf_evsel_menu *menu, int nr_events, const char *help, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + bool warn_lost_event) { struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; @@ -3203,7 +3208,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, case K_TIMER: hbt->timer(hbt->arg); - if (!menu->lost_events_warned && menu->lost_events) { + if (!menu->lost_events_warned && + menu->lost_events && + warn_lost_event) { ui_browser__warn_lost_events(&menu->b); menu->lost_events_warned = true; } @@ -3224,7 +3231,8 @@ browse_hists: key = perf_evsel__hists_browse(pos, nr_events, help, true, hbt, menu->min_pcnt, - menu->env); + menu->env, + warn_lost_event); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3282,7 +3290,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, int nr_entries, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -3309,13 +3318,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, menu.b.width = line_len; } - return perf_evsel_menu__run(&menu, nr_entries, help, hbt); + return perf_evsel_menu__run(&menu, nr_entries, help, + hbt, warn_lost_event); } int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env) + struct perf_env *env, + bool warn_lost_event) { int nr_entries = evlist->nr_entries; @@ -3325,7 +3336,7 @@ single_entry: return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, - env); + env, warn_lost_event); } if (symbol_conf.event_group) { @@ -3342,5 +3353,6 @@ single_entry: } return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, - hbt, min_pcnt, env); + hbt, min_pcnt, env, + warn_lost_event); } diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index ba431777f559..9428bee076f2 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -28,7 +28,8 @@ struct hist_browser { struct hist_browser *hist_browser__new(struct hists *hists); void hist_browser__delete(struct hist_browser *browser); -int hist_browser__run(struct hist_browser *browser, const char *help); +int hist_browser__run(struct hist_browser *browser, const char *help, + bool warn_lost_event); void hist_browser__init(struct hist_browser *browser, struct hists *hists); #endif /* _PERF_UI_BROWSER_HISTS_H_ */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ac35cd214feb..e5fc14e53c05 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -715,28 +715,11 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int return perf_mmap__read_forward(md); } -union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) -{ - struct perf_mmap *md = &evlist->mmap[idx]; - - /* - * No need to check messup for backward ring buffer: - * We can always read arbitrary long data from a backward - * ring buffer unless we forget to pause it before reading. - */ - return perf_mmap__read_backward(md); -} - union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { return perf_evlist__mmap_read_forward(evlist, idx); } -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) -{ - perf_mmap__read_catchup(&evlist->mmap[idx]); -} - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) { perf_mmap__consume(&evlist->mmap[idx], false); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 75f8e0ad5d76..336b838e6957 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -133,10 +133,6 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx); -union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, - int idx); -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx); - void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ff359c9ece2e..ef351688b797 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -41,17 +41,7 @@ #include "sane_ctype.h" -static struct { - bool sample_id_all; - bool exclude_guest; - bool mmap2; - bool cloexec; - bool clockid; - bool clockid_wrong; - bool lbr_flags; - bool write_backward; - bool group_read; -} perf_missing_features; +struct perf_missing_features perf_missing_features; static clockid_t clockid; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 846e41644525..a7487c6d1866 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -149,6 +149,20 @@ union u64_swap { u32 val32[2]; }; +struct perf_missing_features { + bool sample_id_all; + bool exclude_guest; + bool mmap2; + bool cloexec; + bool clockid; + bool clockid_wrong; + bool lbr_flags; + bool write_backward; + bool group_read; +}; + +extern struct perf_missing_features perf_missing_features; + struct cpu_map; struct target; struct thread_map; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index f6630cb95eff..02721b579746 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -430,7 +430,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env); + struct perf_env *env, + bool warn_lost_event); int script_browse(const char *script_opt); #else static inline @@ -438,7 +439,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, - struct perf_env *env __maybe_unused) + struct perf_env *env __maybe_unused, + bool warn_lost_event __maybe_unused) { return 0; } diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 05076e683938..91531a7c8fbf 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -22,29 +22,27 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map) /* When check_messup is true, 'end' must points to a good entry */ static union perf_event *perf_mmap__read(struct perf_mmap *map, - u64 start, u64 end, u64 *prev) + u64 *startp, u64 end) { unsigned char *data = map->base + page_size; union perf_event *event = NULL; - int diff = end - start; + int diff = end - *startp; if (diff >= (int)sizeof(event->header)) { size_t size; - event = (union perf_event *)&data[start & map->mask]; + event = (union perf_event *)&data[*startp & map->mask]; size = event->header.size; - if (size < sizeof(event->header) || diff < (int)size) { - event = NULL; - goto broken_event; - } + if (size < sizeof(event->header) || diff < (int)size) + return NULL; /* * Event straddles the mmap boundary -- header should always * be inside due to u64 alignment of output. */ - if ((start & map->mask) + size != ((start + size) & map->mask)) { - unsigned int offset = start; + if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { + unsigned int offset = *startp; unsigned int len = min(sizeof(*event), size), cpy; void *dst = map->event_copy; @@ -59,20 +57,19 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, event = (union perf_event *)map->event_copy; } - start += size; + *startp += size; } -broken_event: - if (prev) - *prev = start; - return event; } +/* + * legacy interface for mmap read. + * Don't use it. Use perf_mmap__read_event(). + */ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) { u64 head; - u64 old = map->prev; /* * Check if event was unmapped due to a POLLHUP/POLLERR. @@ -82,13 +79,26 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) head = perf_mmap__read_head(map); - return perf_mmap__read(map, old, head, &map->prev); + return perf_mmap__read(map, &map->prev, head); } -union perf_event *perf_mmap__read_backward(struct perf_mmap *map) +/* + * Read event from ring buffer one by one. + * Return one event for each call. + * + * Usage: + * perf_mmap__read_init() + * while(event = perf_mmap__read_event()) { + * //process the event + * perf_mmap__consume() + * } + * perf_mmap__read_done() + */ +union perf_event *perf_mmap__read_event(struct perf_mmap *map, + bool overwrite, + u64 *startp, u64 end) { - u64 head, end; - u64 start = map->prev; + union perf_event *event; /* * Check if event was unmapped due to a POLLHUP/POLLERR. @@ -96,40 +106,19 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map) if (!refcount_read(&map->refcnt)) return NULL; - head = perf_mmap__read_head(map); - if (!head) + if (startp == NULL) return NULL; - /* - * 'head' pointer starts from 0. Kernel minus sizeof(record) form - * it each time when kernel writes to it, so in fact 'head' is - * negative. 'end' pointer is made manually by adding the size of - * the ring buffer to 'head' pointer, means the validate data can - * read is the whole ring buffer. If 'end' is positive, the ring - * buffer has not fully filled, so we must adjust 'end' to 0. - * - * However, since both 'head' and 'end' is unsigned, we can't - * simply compare 'end' against 0. Here we compare '-head' and - * the size of the ring buffer, where -head is the number of bytes - * kernel write to the ring buffer. - */ - if (-head < (u64)(map->mask + 1)) - end = 0; - else - end = head + map->mask + 1; - - return perf_mmap__read(map, start, end, &map->prev); -} + /* non-overwirte doesn't pause the ringbuffer */ + if (!overwrite) + end = perf_mmap__read_head(map); -void perf_mmap__read_catchup(struct perf_mmap *map) -{ - u64 head; + event = perf_mmap__read(map, startp, end); - if (!refcount_read(&map->refcnt)) - return; + if (!overwrite) + map->prev = *startp; - head = perf_mmap__read_head(map); - map->prev = head; + return event; } static bool perf_mmap__empty(struct perf_mmap *map) @@ -267,41 +256,60 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6 return -1; } -int perf_mmap__push(struct perf_mmap *md, bool overwrite, - void *to, int push(void *to, void *buf, size_t size)) +/* + * Report the start and end of the available data in ringbuffer + */ +int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, + u64 *startp, u64 *endp) { u64 head = perf_mmap__read_head(md); u64 old = md->prev; - u64 end = head, start = old; unsigned char *data = md->base + page_size; unsigned long size; - void *buf; - int rc = 0; - start = overwrite ? head : old; - end = overwrite ? old : head; + *startp = overwrite ? head : old; + *endp = overwrite ? old : head; - if (start == end) - return 0; + if (*startp == *endp) + return -EAGAIN; - size = end - start; + size = *endp - *startp; if (size > (unsigned long)(md->mask) + 1) { if (!overwrite) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); md->prev = head; perf_mmap__consume(md, overwrite); - return 0; + return -EAGAIN; } /* * Backward ring buffer is full. We still have a chance to read * most of data from it. */ - if (overwrite_rb_find_range(data, md->mask, head, &start, &end)) - return -1; + if (overwrite_rb_find_range(data, md->mask, head, startp, endp)) + return -EINVAL; } + return 0; +} + +int perf_mmap__push(struct perf_mmap *md, bool overwrite, + void *to, int push(void *to, void *buf, size_t size)) +{ + u64 head = perf_mmap__read_head(md); + u64 end, start; + unsigned char *data = md->base + page_size; + unsigned long size; + void *buf; + int rc = 0; + + rc = perf_mmap__read_init(md, overwrite, &start, &end); + if (rc < 0) + return (rc == -EAGAIN) ? 0 : -1; + + size = end - start; + if ((start & md->mask) + size != (end & md->mask)) { buf = &data[start & md->mask]; size = md->mask + 1 - (start & md->mask); @@ -327,3 +335,14 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, out: return rc; } + +/* + * Mandatory for overwrite mode + * The direction of overwrite mode is backward. + * The last perf_mmap__read() will set tail to map->prev. + * Need to correct the map->prev to head which is the end of next read. + */ +void perf_mmap__read_done(struct perf_mmap *map) +{ + map->prev = perf_mmap__read_head(map); +} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index e43d7b55a55f..ec7d3a24e276 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -65,8 +65,6 @@ void perf_mmap__put(struct perf_mmap *map); void perf_mmap__consume(struct perf_mmap *map, bool overwrite); -void perf_mmap__read_catchup(struct perf_mmap *md); - static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; @@ -87,11 +85,17 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) } union perf_event *perf_mmap__read_forward(struct perf_mmap *map); -union perf_event *perf_mmap__read_backward(struct perf_mmap *map); + +union perf_event *perf_mmap__read_event(struct perf_mmap *map, + bool overwrite, + u64 *startp, u64 end); int perf_mmap__push(struct perf_mmap *md, bool backward, void *to, int push(void *to, void *buf, size_t size)); size_t perf_mmap__mmap_len(struct perf_mmap *map); +int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, + u64 *startp, u64 *endp); +void perf_mmap__read_done(struct perf_mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 443892dabedb..1019bbc5dbd8 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -340,35 +340,15 @@ size_t hex_width(u64 v) return n; } -static int hex(char ch) -{ - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - /* * While we find nice hex chars, build a long_val. * Return number of chars processed. */ int hex2u64(const char *ptr, u64 *long_val) { - const char *p = ptr; - *long_val = 0; - - while (*p) { - const int hex_val = hex(*p); + char *p; - if (hex_val < 0) - break; - - *long_val = (*long_val << 4) | hex_val; - p++; - } + *long_val = strtoull(ptr, &p, 16); return p - ptr; } diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index 39fd362415cf..0f2698f9fd6d 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -57,7 +57,7 @@ volatile int gotsig; void sighandler(int sig, siginfo_t *info, void *ctx) { - struct ucontext *ucp = ctx; + ucontext_t *ucp = ctx; if (!testing) { signal(sig, SIG_DFL); diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 10ca46df1449..d744991c0f4f 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -5,16 +5,26 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean -TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ - check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \ +UNAME_M := $(shell uname -m) +CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) + +TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ + check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \ protection_keys test_vdso test_vsyscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer -TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl +TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip +# Some selftests require 32bit support enabled also on 64bit systems +TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall -TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) +TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) $(TARGETS_C_32BIT_NEEDED) TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) +ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),11) +TARGETS_C_64BIT_ALL += $(TARGETS_C_32BIT_NEEDED) +endif + BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) @@ -23,10 +33,6 @@ BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie -UNAME_M := $(shell uname -m) -CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) -CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) - define gen-target-rule-32 $(1) $(1)_32: $(OUTPUT)/$(1)_32 .PHONY: $(1) $(1)_32 @@ -40,12 +46,14 @@ endef ifeq ($(CAN_BUILD_I386),1) all: all_32 TEST_PROGS += $(BINARIES_32) +EXTRA_CFLAGS += -DCAN_BUILD_32 $(foreach t,$(TARGETS_C_32BIT_ALL),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) all: all_64 TEST_PROGS += $(BINARIES_64) +EXTRA_CFLAGS += -DCAN_BUILD_64 $(foreach t,$(TARGETS_C_64BIT_ALL),$(eval $(call gen-target-rule-64,$(t)))) endif diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c index ec0f6b45ce8b..9c0325e1ea68 100644 --- a/tools/testing/selftests/x86/mpx-mini-test.c +++ b/tools/testing/selftests/x86/mpx-mini-test.c @@ -315,11 +315,39 @@ static inline void *__si_bounds_upper(siginfo_t *si) return si->si_upper; } #else + +/* + * This deals with old version of _sigfault in some distros: + * + +old _sigfault: + struct { + void *si_addr; + } _sigfault; + +new _sigfault: + struct { + void __user *_addr; + int _trapno; + short _addr_lsb; + union { + struct { + void __user *_lower; + void __user *_upper; + } _addr_bnd; + __u32 _pkey; + }; + } _sigfault; + * + */ + static inline void **__si_bounds_hack(siginfo_t *si) { void *sigfault = &si->_sifields._sigfault; void *end_sigfault = sigfault + sizeof(si->_sifields._sigfault); - void **__si_lower = end_sigfault; + int *trapno = (int*)end_sigfault; + /* skip _trapno and _addr_lsb */ + void **__si_lower = (void**)(trapno + 2); return __si_lower; } @@ -331,7 +359,7 @@ static inline void *__si_bounds_lower(siginfo_t *si) static inline void *__si_bounds_upper(siginfo_t *si) { - return (*__si_bounds_hack(si)) + sizeof(void *); + return *(__si_bounds_hack(si) + 1); } #endif diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index bc1b0735bb50..f15aa5a76fe3 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -393,34 +393,6 @@ pid_t fork_lazy_child(void) return forkret; } -void davecmp(void *_a, void *_b, int len) -{ - int i; - unsigned long *a = _a; - unsigned long *b = _b; - - for (i = 0; i < len / sizeof(*a); i++) { - if (a[i] == b[i]) - continue; - - dprintf3("[%3d]: a: %016lx b: %016lx\n", i, a[i], b[i]); - } -} - -void dumpit(char *f) -{ - int fd = open(f, O_RDONLY); - char buf[100]; - int nr_read; - - dprintf2("maps fd: %d\n", fd); - do { - nr_read = read(fd, &buf[0], sizeof(buf)); - write(1, buf, nr_read); - } while (nr_read > 0); - close(fd); -} - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c index a48da95c18fd..ddfdd635de16 100644 --- a/tools/testing/selftests/x86/single_step_syscall.c +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -119,7 +119,9 @@ static void check_result(void) int main() { +#ifdef CAN_BUILD_32 int tmp; +#endif sethandler(SIGTRAP, sigtrap, 0); @@ -139,12 +141,13 @@ int main() : : "c" (post_nop) : "r11"); check_result(); #endif - +#ifdef CAN_BUILD_32 printf("[RUN]\tSet TF and check int80\n"); set_eflags(get_eflags() | X86_EFLAGS_TF); asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid) : INT80_CLOBBERS); check_result(); +#endif /* * This test is particularly interesting if fast syscalls use diff --git a/tools/testing/selftests/x86/test_mremap_vdso.c b/tools/testing/selftests/x86/test_mremap_vdso.c index bf0d687c7db7..64f11c8d9b76 100644 --- a/tools/testing/selftests/x86/test_mremap_vdso.c +++ b/tools/testing/selftests/x86/test_mremap_vdso.c @@ -90,8 +90,12 @@ int main(int argc, char **argv, char **envp) vdso_size += PAGE_SIZE; } +#ifdef __i386__ /* Glibc is likely to explode now - exit with raw syscall */ asm volatile ("int $0x80" : : "a" (__NR_exit), "b" (!!ret)); +#else /* __x86_64__ */ + syscall(SYS_exit, ret); +#endif } else { int status; diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c index 29973cde06d3..235259011704 100644 --- a/tools/testing/selftests/x86/test_vdso.c +++ b/tools/testing/selftests/x86/test_vdso.c @@ -26,20 +26,59 @@ # endif #endif +/* max length of lines in /proc/self/maps - anything longer is skipped here */ +#define MAPS_LINE_LEN 128 + int nerrs = 0; +typedef long (*getcpu_t)(unsigned *, unsigned *, void *); + +getcpu_t vgetcpu; +getcpu_t vdso_getcpu; + +static void *vsyscall_getcpu(void) +{ #ifdef __x86_64__ -# define VSYS(x) (x) + FILE *maps; + char line[MAPS_LINE_LEN]; + bool found = false; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) /* might still be present, but ignore it here, as we test vDSO not vsyscall */ + return NULL; + + while (fgets(line, MAPS_LINE_LEN, maps)) { + char r, x; + void *start, *end; + char name[MAPS_LINE_LEN]; + + /* sscanf() is safe here as strlen(name) >= strlen(line) */ + if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", + &start, &end, &r, &x, name) != 5) + continue; + + if (strcmp(name, "[vsyscall]")) + continue; + + /* assume entries are OK, as we test vDSO here not vsyscall */ + found = true; + break; + } + + fclose(maps); + + if (!found) { + printf("Warning: failed to find vsyscall getcpu\n"); + return NULL; + } + return (void *) (0xffffffffff600800); #else -# define VSYS(x) 0 + return NULL; #endif +} -typedef long (*getcpu_t)(unsigned *, unsigned *, void *); - -const getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800); -getcpu_t vdso_getcpu; -void fill_function_pointers() +static void fill_function_pointers() { void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); @@ -54,6 +93,8 @@ void fill_function_pointers() vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu"); if (!vdso_getcpu) printf("Warning: failed to find getcpu in vDSO\n"); + + vgetcpu = (getcpu_t) vsyscall_getcpu(); } static long sys_getcpu(unsigned * cpu, unsigned * node, diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index 7a744fa7b786..be81621446f0 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -33,6 +33,9 @@ # endif #endif +/* max length of lines in /proc/self/maps - anything longer is skipped here */ +#define MAPS_LINE_LEN 128 + static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { @@ -98,7 +101,7 @@ static int init_vsys(void) #ifdef __x86_64__ int nerrs = 0; FILE *maps; - char line[128]; + char line[MAPS_LINE_LEN]; bool found = false; maps = fopen("/proc/self/maps", "r"); @@ -108,10 +111,12 @@ static int init_vsys(void) return 0; } - while (fgets(line, sizeof(line), maps)) { + while (fgets(line, MAPS_LINE_LEN, maps)) { char r, x; void *start, *end; - char name[128]; + char name[MAPS_LINE_LEN]; + + /* sscanf() is safe here as strlen(name) >= strlen(line) */ if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", &start, &end, &r, &x, name) != 5) continue; |