diff options
87 files changed, 331 insertions, 612 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index ed42cb65a19b..66de4da2d244 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3086,6 +3086,7 @@ M: Stephen Boyd <sboyd@codeaurora.org> L: linux-clk@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git S: Maintained +F: Documentation/devicetree/bindings/clock/ F: drivers/clk/ X: drivers/clk/clkdev.c F: include/linux/clk-pr* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0dcbacfdea4b..0d3e59f56974 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -61,7 +61,7 @@ config RWSEM_GENERIC_SPINLOCK def_bool y config ARCH_DISCONTIGMEM_ENABLE - def_bool y + def_bool n config ARCH_FLATMEM_ENABLE def_bool y @@ -186,9 +186,6 @@ if SMP config ARC_HAS_COH_CACHES def_bool n -config ARC_HAS_REENTRANT_IRQ_LV2 - def_bool n - config ARC_MCIP bool "ARConnect Multicore IP (MCIP) Support " depends on ISA_ARCV2 @@ -366,25 +363,10 @@ config NODES_SHIFT if ISA_ARCOMPACT config ARC_COMPACT_IRQ_LEVELS - bool "ARCompact IRQ Priorities: High(2)/Low(1)" + bool "Setup Timer IRQ as high Priority" default n - # Timer HAS to be high priority, for any other high priority config - select ARC_IRQ3_LV2 # if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy - depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2 - -if ARC_COMPACT_IRQ_LEVELS - -config ARC_IRQ3_LV2 - bool - -config ARC_IRQ5_LV2 - bool - -config ARC_IRQ6_LV2 - bool - -endif #ARC_COMPACT_IRQ_LEVELS + depends on !SMP config ARC_FPU_SAVE_RESTORE bool "Enable FPU state persistence across context switch" @@ -407,11 +389,6 @@ config ARC_HAS_LLSC default y depends on !ARC_CANT_LLSC -config ARC_STAR_9000923308 - bool "Workaround for llock/scond livelock" - default n - depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC - config ARC_HAS_SWAPE bool "Insn: SWAPE (endian-swap)" default y @@ -471,7 +448,7 @@ config LINUX_LINK_BASE config HIGHMEM bool "High Memory Support" - select DISCONTIGMEM + select ARCH_DISCONTIGMEM_ENABLE help With ARC 2G:2G address split, only upper 2G is directly addressable by kernel. Enable this to potentially allow access to rest of 2G and PAE diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 02fabef2891c..d4df6be66d58 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -127,7 +127,7 @@ libs-y += arch/arc/lib/ $(LIBGCC) boot := arch/arc/boot -#default target for make without any arguements. +#default target for make without any arguments. KBUILD_IMAGE := bootpImage all: $(KBUILD_IMAGE) diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi index 3942634f805a..02410b211433 100644 --- a/arch/arc/boot/dts/abilis_tb100.dtsi +++ b/arch/arc/boot/dts/abilis_tb100.dtsi @@ -23,8 +23,6 @@ / { - clock-frequency = <500000000>; /* 500 MHZ */ - soc100 { bus-frequency = <166666666>; diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi index b0467229a5c4..f9e7686044eb 100644 --- a/arch/arc/boot/dts/abilis_tb101.dtsi +++ b/arch/arc/boot/dts/abilis_tb101.dtsi @@ -23,8 +23,6 @@ / { - clock-frequency = <500000000>; /* 500 MHZ */ - soc100 { bus-frequency = <166666666>; diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 3e02f152edcb..6ae2c476ad82 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -15,7 +15,6 @@ / { compatible = "snps,arc"; - clock-frequency = <750000000>; /* 750 MHZ */ #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index 378e455a94c4..14df46f141bf 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -14,7 +14,6 @@ / { compatible = "snps,arc"; - clock-frequency = <90000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 64c94b2860ab..3d6cfa32bf51 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -14,7 +14,6 @@ / { compatible = "snps,arc"; - clock-frequency = <90000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/eznps.dts b/arch/arc/boot/dts/eznps.dts index b89f6c3eb352..1e0d225791c1 100644 --- a/arch/arc/boot/dts/eznps.dts +++ b/arch/arc/boot/dts/eznps.dts @@ -18,7 +18,6 @@ / { compatible = "ezchip,arc-nps"; - clock-frequency = <83333333>; /* 83.333333 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&intc>; diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 5d5e373e0ebc..63970513e4ae 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsim"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index b5b060adce8a..763d66c883da 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsimosci"; - clock-frequency = <20000000>; /* 20 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts index 325e73090a18..4eb97c584b18 100644 --- a/arch/arc/boot/dts/nsimosci_hs.dts +++ b/arch/arc/boot/dts/nsimosci_hs.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsimosci_hs"; - clock-frequency = <20000000>; /* 20 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts index ee03d7126581..853f897eb2a3 100644 --- a/arch/arc/boot/dts/nsimosci_hs_idu.dts +++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsimosci_hs"; - clock-frequency = <5000000>; /* 5 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi index 3a10cc633e2b..65808fe0a290 100644 --- a/arch/arc/boot/dts/skeleton.dtsi +++ b/arch/arc/boot/dts/skeleton.dtsi @@ -13,7 +13,6 @@ / { compatible = "snps,arc"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; chosen { }; diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi index 71fd308a9298..2dfe8037dfbb 100644 --- a/arch/arc/boot/dts/skeleton_hs.dtsi +++ b/arch/arc/boot/dts/skeleton_hs.dtsi @@ -8,7 +8,6 @@ / { compatible = "snps,arc"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; chosen { }; diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi index d1cb25a66989..4c11079f3565 100644 --- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi +++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi @@ -8,7 +8,6 @@ / { compatible = "snps,arc"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; chosen { }; diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi index ad4ee43bd2ac..0fd6ba985b16 100644 --- a/arch/arc/boot/dts/vdk_axc003.dtsi +++ b/arch/arc/boot/dts/vdk_axc003.dtsi @@ -14,7 +14,6 @@ / { compatible = "snps,arc"; - clock-frequency = <50000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi index a3cb6263c581..82214cd7ba0c 100644 --- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi +++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi @@ -15,7 +15,6 @@ / { compatible = "snps,arc"; - clock-frequency = <50000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 5f3dcbbc0cc9..dd683995bc9d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -25,50 +25,17 @@ #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#ifdef CONFIG_ARC_STAR_9000923308 - -#define SCOND_FAIL_RETRY_VAR_DEF \ - unsigned int delay = 1, tmp; \ - -#define SCOND_FAIL_RETRY_ASM \ - " bz 4f \n" \ - " ; --- scond fail delay --- \n" \ - " mov %[tmp], %[delay] \n" /* tmp = delay */ \ - "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ - " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ - " rol %[delay], %[delay] \n" /* delay *= 2 */ \ - " b 1b \n" /* start over */ \ - "4: ; --- success --- \n" \ - -#define SCOND_FAIL_RETRY_VARS \ - ,[delay] "+&r" (delay),[tmp] "=&r" (tmp) \ - -#else /* !CONFIG_ARC_STAR_9000923308 */ - -#define SCOND_FAIL_RETRY_VAR_DEF - -#define SCOND_FAIL_RETRY_ASM \ - " bnz 1b \n" \ - -#define SCOND_FAIL_RETRY_VARS - -#endif - #define ATOMIC_OP(op, c_op, asm_op) \ static inline void atomic_##op(int i, atomic_t *v) \ { \ - unsigned int val; \ - SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int val; \ \ __asm__ __volatile__( \ "1: llock %[val], [%[ctr]] \n" \ " " #asm_op " %[val], %[val], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ - SCOND_FAIL_RETRY_ASM \ - \ + " bnz 1b \n" \ : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \ - SCOND_FAIL_RETRY_VARS \ : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \ [i] "ir" (i) \ : "cc"); \ @@ -77,8 +44,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ #define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ - unsigned int val; \ - SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int val; \ \ /* \ * Explicit full memory barrier needed before/after as \ @@ -90,11 +56,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ "1: llock %[val], [%[ctr]] \n" \ " " #asm_op " %[val], %[val], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ - SCOND_FAIL_RETRY_ASM \ - \ + " bnz 1b \n" \ : [val] "=&r" (val) \ - SCOND_FAIL_RETRY_VARS \ : [ctr] "r" (&v->counter), \ [i] "ir" (i) \ : "cc"); \ diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index e0e1faf03c50..14c310f2e0b1 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -76,8 +76,8 @@ * We need to be a bit more cautious here. What if a kernel bug in * L1 ISR, caused SP to go whaco (some small value which looks like * USER stk) and then we take L2 ISR. - * Above brlo alone would treat it as a valid L1-L2 sceanrio - * instead of shouting alound + * Above brlo alone would treat it as a valid L1-L2 scenario + * instead of shouting around * The only feasible way is to make sure this L2 happened in * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in * L1 ISR before it switches stack diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index 1fd467ef658f..b0b87f2447f5 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -83,7 +83,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm) local_flush_tlb_all(); /* - * Above checke for rollover of 8 bit ASID in 32 bit container. + * Above check for rollover of 8 bit ASID in 32 bit container. * If the container itself wrapped around, set it to a non zero * "generation" to distinguish from no context */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 034bbdc0ff61..858f98ef7f1b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -47,7 +47,7 @@ * Page Tables are purely for Linux VM's consumption and the bits below are * suited to that (uniqueness). Hence some are not implemented in the TLB and * some have different value in TLB. - * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in + * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in * seperate PD0 and PD1, which combined forms a translation entry) * while for PTE perspective, they are 8 and 9 respectively * with MMU v3: Most bits (except SHARED) represent the exact hardware pos diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index f9048994b22f..16b630fbeb6a 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -78,7 +78,7 @@ struct task_struct; #define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) /* - * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. + * Where about of Task's sp, fp, blink when it was last seen in kernel mode. * Look in process.c for details of kernel stack layout */ #define TSK_K_ESP(tsk) (tsk->thread.ksp) diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index 991380438d6b..89fdd1b0a76e 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void) * (1) These insn were introduced only in 4.10 release. So for older released * support needed. * - * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be + * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be * gaurantted by the platform (not something which core handles). * Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ * disabling for atomicity. diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 800e7c430ca5..cded4a9b5438 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -20,11 +20,6 @@ #ifdef CONFIG_ARC_HAS_LLSC -/* - * A normal LLOCK/SCOND based system, w/o need for livelock workaround - */ -#ifndef CONFIG_ARC_STAR_9000923308 - static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned int val; @@ -238,293 +233,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) smp_mb(); } -#else /* CONFIG_ARC_STAR_9000923308 */ - -/* - * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping - * coherency transactions in the SCU. The exclusive line state keeps rotating - * among contenting cores leading to a never ending cycle. So break the cycle - * by deferring the retry of failed exclusive access (SCOND). The actual delay - * needed is function of number of contending cores as well as the unrelated - * coherency traffic from other cores. To keep the code simple, start off with - * small delay of 1 which would suffice most cases and in case of contention - * double the delay. Eventually the delay is sufficient such that the coherency - * pipeline is drained, thus a subsequent exclusive access would succeed. - */ - -#define SCOND_FAIL_RETRY_VAR_DEF \ - unsigned int delay, tmp; \ - -#define SCOND_FAIL_RETRY_ASM \ - " ; --- scond fail delay --- \n" \ - " mov %[tmp], %[delay] \n" /* tmp = delay */ \ - "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ - " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ - " rol %[delay], %[delay] \n" /* delay *= 2 */ \ - " b 1b \n" /* start over */ \ - " \n" \ - "4: ; --- done --- \n" \ - -#define SCOND_FAIL_RETRY_VARS \ - ,[delay] "=&r" (delay), [tmp] "=&r" (tmp) \ - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned int val; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[slock]] \n" - " breq %[val], %[LOCKED], 0b \n" /* spin while LOCKED */ - " scond %[LOCKED], [%[slock]] \n" /* acquire */ - " bz 4f \n" /* done */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val) - SCOND_FAIL_RETRY_VARS - : [slock] "r" (&(lock->slock)), - [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) - : "memory", "cc"); - - smp_mb(); -} - -/* 1 - lock taken successfully */ -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned int val, got_it = 0; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[slock]] \n" - " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */ - " scond %[LOCKED], [%[slock]] \n" /* acquire */ - " bz.d 4f \n" - " mov.z %[got_it], 1 \n" /* got it */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val), - [got_it] "+&r" (got_it) - SCOND_FAIL_RETRY_VARS - : [slock] "r" (&(lock->slock)), - [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) - : "memory", "cc"); - - smp_mb(); - - return got_it; -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - smp_mb(); - - lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; - - smp_mb(); -} - -/* - * Read-write spinlocks, allowing multiple readers but only one writer. - * Unfair locking as Writers could be starved indefinitely by Reader(s) - */ - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned int val; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - /* - * zero means writer holds the lock exclusively, deny Reader. - * Otherwise grant lock to first/subseq reader - * - * if (rw->counter > 0) { - * rw->counter--; - * ret = 1; - * } - */ - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brls %[val], %[WR_LOCKED], 0b\n" /* <= 0: spin while write locked */ - " sub %[val], %[val], 1 \n" /* reader lock */ - " scond %[val], [%[rwlock]] \n" - " bz 4f \n" /* done */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); -} - -/* 1 - lock taken successfully */ -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned int val, got_it = 0; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */ - " sub %[val], %[val], 1 \n" /* counter-- */ - " scond %[val], [%[rwlock]] \n" - " bz.d 4f \n" - " mov.z %[got_it], 1 \n" /* got it */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val), - [got_it] "+&r" (got_it) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); - - return got_it; -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned int val; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - /* - * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__), - * deny writer. Otherwise if unlocked grant to writer - * Hence the claim that Linux rwlocks are unfair to writers. - * (can be starved for an indefinite time by readers). - * - * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) { - * rw->counter = 0; - * ret = 1; - * } - */ - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brne %[val], %[UNLOCKED], 0b \n" /* while !UNLOCKED spin */ - " mov %[val], %[WR_LOCKED] \n" - " scond %[val], [%[rwlock]] \n" - " bz 4f \n" - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); -} - -/* 1 - lock taken successfully */ -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned int val, got_it = 0; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */ - " mov %[val], %[WR_LOCKED] \n" - " scond %[val], [%[rwlock]] \n" - " bz.d 4f \n" - " mov.z %[got_it], 1 \n" /* got it */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val), - [got_it] "+&r" (got_it) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); - - return got_it; -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned int val; - - smp_mb(); - - /* - * rw->counter++; - */ - __asm__ __volatile__( - "1: llock %[val], [%[rwlock]] \n" - " add %[val], %[val], 1 \n" - " scond %[val], [%[rwlock]] \n" - " bnz 1b \n" - " \n" - : [val] "=&r" (val) - : [rwlock] "r" (&(rw->counter)) - : "memory", "cc"); - - smp_mb(); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - unsigned int val; - - smp_mb(); - - /* - * rw->counter = __ARCH_RW_LOCK_UNLOCKED__; - */ - __asm__ __volatile__( - "1: llock %[val], [%[rwlock]] \n" - " scond %[UNLOCKED], [%[rwlock]]\n" - " bnz 1b \n" - " \n" - : [val] "=&r" (val) - : [rwlock] "r" (&(rw->counter)), - [UNLOCKED] "r" (__ARCH_RW_LOCK_UNLOCKED__) - : "memory", "cc"); - - smp_mb(); -} - -#undef SCOND_FAIL_RETRY_VAR_DEF -#undef SCOND_FAIL_RETRY_ASM -#undef SCOND_FAIL_RETRY_VARS - -#endif /* CONFIG_ARC_STAR_9000923308 */ - #else /* !CONFIG_ARC_HAS_LLSC */ static inline void arch_spin_lock(arch_spinlock_t *lock) diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 3af67455659a..2d79e527fa50 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -103,7 +103,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) /* * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it. - * SYSCALL_TRACE is anways seperately/unconditionally tested right after a + * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a * syscall, so all that reamins to be tested is _TIF_WORK_MASK */ diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index d1da6032b715..a78d5670884f 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -32,7 +32,7 @@ #define __kernel_ok (segment_eq(get_fs(), KERNEL_DS)) /* - * Algorthmically, for __user_ok() we want do: + * Algorithmically, for __user_ok() we want do: * (start < TASK_SIZE) && (start+len < TASK_SIZE) * where TASK_SIZE could either be retrieved from thread_info->addr_limit or * emitted directly in code. diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h index 095599a73195..71f3918b0fc3 100644 --- a/arch/arc/include/uapi/asm/swab.h +++ b/arch/arc/include/uapi/asm/swab.h @@ -74,7 +74,7 @@ __tmp ^ __in; \ }) -#elif (ARC_BSWAP_TYPE == 2) /* Custom single cycle bwap instruction */ +#elif (ARC_BSWAP_TYPE == 2) /* Custom single cycle bswap instruction */ #define __arch_swab32(x) \ ({ \ diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S index 0cb0abaa0479..98812c1248df 100644 --- a/arch/arc/kernel/entry-compact.S +++ b/arch/arc/kernel/entry-compact.S @@ -91,27 +91,13 @@ VECTOR mem_service ; 0x8, Mem exception (0x1) VECTOR instr_service ; 0x10, Instrn Error (0x2) ; ******************** Device ISRs ********************** -#ifdef CONFIG_ARC_IRQ3_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -VECTOR handle_interrupt_level1 - -#ifdef CONFIG_ARC_IRQ5_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -#ifdef CONFIG_ARC_IRQ6_LV2 +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS VECTOR handle_interrupt_level2 #else VECTOR handle_interrupt_level1 #endif -.rept 25 +.rept 28 VECTOR handle_interrupt_level1 ; Other devices .endr diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index c5cceca36118..ce9deb953ca9 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -28,10 +28,8 @@ void arc_init_IRQ(void) { int level_mask = 0; - /* setup any high priority Interrupts (Level2 in ARCompact jargon) */ - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3; - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5; - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6; + /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */ + level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ; /* * Write to register, even if no LV2 IRQs configured to reset it diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 6fd48021324b..08f03d9b5b3e 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -108,7 +108,7 @@ static void arc_perf_event_update(struct perf_event *event, int64_t delta = new_raw_count - prev_raw_count; /* - * We don't afaraid of hwc->prev_count changing beneath our feet + * We aren't afraid of hwc->prev_count changing beneath our feet * because there's no way for us to re-enter this function anytime. */ local64_set(&hwc->prev_count, new_raw_count); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index f63b8bfefb0c..2ee7a4d758a8 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -392,7 +392,7 @@ void __init setup_arch(char **cmdline_p) /* * If we are here, it is established that @uboot_arg didn't * point to DT blob. Instead if u-boot says it is cmdline, - * Appent to embedded DT cmdline. + * append to embedded DT cmdline. * setup_machine_fdt() would have populated @boot_command_line */ if (uboot_tag == 1) { diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 004b7f0bc76c..6cb3736b6b83 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -34,7 +34,7 @@ * -ViXS were still seeing crashes when using insmod to load drivers. * It turned out that the code to change Execute permssions for TLB entries * of user was not guarded for interrupts (mod_tlb_permission) - * This was cauing TLB entries to be overwritten on unrelated indexes + * This was causing TLB entries to be overwritten on unrelated indexes * * Vineetg: July 15th 2008: Bug #94183 * -Exception happens in Delay slot of a JMP, and before user space resumes, diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index a6f91e88ce36..934150e7ac48 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -276,7 +276,7 @@ static int tlb_stats_open(struct inode *inode, struct file *file) return 0; } -/* called on user read(): display the couters */ +/* called on user read(): display the counters */ static ssize_t tlb_stats_output(struct file *file, /* file descriptor */ char __user *user_buf, /* user buffer */ size_t len, /* length of buffer */ diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 9e5eddbb856f..5a294b2c3cb3 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -215,7 +215,7 @@ slc_chk: * ------------------ * This ver of MMU supports variable page sizes (1k-16k): although Linux will * only support 8k (default), 16k and 4k. - * However from hardware perspective, smaller page sizes aggrevate aliasing + * However from hardware perspective, smaller page sizes aggravate aliasing * meaning more vaddr bits needed to disambiguate the cache-line-op ; * the existing scheme of piggybacking won't work for certain configurations. * Two new registers IC_PTAG and DC_PTAG inttoduced. @@ -302,7 +302,7 @@ void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr, /* * This is technically for MMU v4, using the MMU v3 programming model - * Special work for HS38 aliasing I-cache configuratino with PAE40 + * Special work for HS38 aliasing I-cache configuration with PAE40 * - upper 8 bits of paddr need to be written into PTAG_HI * - (and needs to be written before the lower 32 bits) * Note that PTAG_HI is hoisted outside the line loop @@ -936,7 +936,7 @@ void arc_cache_init(void) ic->ver, CONFIG_ARC_MMU_VER); /* - * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG + * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG * pair to provide vaddr/paddr respectively, just as in MMU v3 */ if (is_isa_arcv2() && ic->alias) diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 8c8e36fa5659..73d7e4c75b7d 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -10,7 +10,7 @@ * DMA Coherent API Notes * * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is - * implemented by accessintg it using a kernel virtual address, with + * implemented by accessing it using a kernel virtual address, with * Cache bit off in the TLB entry. * * The default DMA address == Phy address which is 0x8000_0000 based. diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 5766ce2be32b..8409cab3f760 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -547,7 +547,7 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev) init.name = dev_name(cpu_dev); init.ops = &clk_spc_ops; - init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE; + init.flags = CLK_GET_RATE_NOCACHE; init.num_parents = 0; return devm_clk_register(cpu_dev, &spc->hw); diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index c50ea76ba66c..6081fbd75330 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -221,7 +221,7 @@ static bool soc_has_mclk_mux0_canin(void) /* convenience wrappers around the common clk API */ static inline struct clk *mpc512x_clk_fixed(const char *name, int rate) { - return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate); + return clk_register_fixed_rate(NULL, name, NULL, 0, rate); } static inline struct clk *mpc512x_clk_factor( diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 84fb984f29c1..85c85eb3e245 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -172,7 +172,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, if (rc < 0) goto out; - skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos; + skip = roundup(cprm->pos - total + sz, 4) - cprm->pos; if (!dump_skip(cprm, skip)) goto Eio; out: diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 53ddba26578c..98efbfcdb503 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -175,6 +175,7 @@ config COMMON_CLK_KEYSTONE config COMMON_CLK_NXP def_bool COMMON_CLK && (ARCH_LPC18XX || ARCH_LPC32XX) select REGMAP_MMIO if ARCH_LPC32XX + select MFD_SYSCON if ARCH_LPC18XX ---help--- Support for clock providers on NXP platforms. diff --git a/drivers/clk/microchip/clk-pic32mzda.c b/drivers/clk/microchip/clk-pic32mzda.c index 020a29acc5b0..51f54380474b 100644 --- a/drivers/clk/microchip/clk-pic32mzda.c +++ b/drivers/clk/microchip/clk-pic32mzda.c @@ -180,15 +180,15 @@ static int pic32mzda_clk_probe(struct platform_device *pdev) /* register fixed rate clocks */ clks[POSCCLK] = clk_register_fixed_rate(&pdev->dev, "posc_clk", NULL, - CLK_IS_ROOT, 24000000); + 0, 24000000); clks[FRCCLK] = clk_register_fixed_rate(&pdev->dev, "frc_clk", NULL, - CLK_IS_ROOT, 8000000); + 0, 8000000); clks[BFRCCLK] = clk_register_fixed_rate(&pdev->dev, "bfrc_clk", NULL, - CLK_IS_ROOT, 8000000); + 0, 8000000); clks[LPRCCLK] = clk_register_fixed_rate(&pdev->dev, "lprc_clk", NULL, - CLK_IS_ROOT, 32000); + 0, 32000); clks[UPLLCLK] = clk_register_fixed_rate(&pdev->dev, "usbphy_clk", NULL, - CLK_IS_ROOT, 24000000); + 0, 24000000); /* fixed rate (optional) clock */ if (of_find_property(np, "microchip,pic32mzda-sosc", NULL)) { pr_info("pic32-clk: dt requests SOSC.\n"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 0d159b513469..ee367e9b7d2e 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1460,6 +1460,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_clear_update_util_hook(policy->cpu); + pr_debug("set_policy cpuinfo.max %u policy->max %u\n", + policy->cpuinfo.max_freq, policy->max); + cpu = all_cpu_data[0]; if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate && policy->max < policy->cpuinfo.max_freq && @@ -1495,13 +1498,13 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits->max_sysfs_pct); limits->max_perf_pct = max(limits->min_policy_pct, limits->max_perf_pct); - limits->max_perf = round_up(limits->max_perf, FRAC_BITS); /* Make sure min_perf_pct <= max_perf_pct */ limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); limits->min_perf = div_fp(limits->min_perf_pct, 100); limits->max_perf = div_fp(limits->max_perf_pct, 100); + limits->max_perf = round_up(limits->max_perf, FRAC_BITS); out: intel_pstate_set_update_util_hook(policy->cpu); @@ -1558,8 +1561,11 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; - policy->cpuinfo.max_freq = - cpu->pstate.turbo_pstate * cpu->pstate.scaling; + update_turbo_state(); + policy->cpuinfo.max_freq = limits->turbo_disabled ? + cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; + policy->cpuinfo.max_freq *= cpu->pstate.scaling; + intel_pstate_init_acpi_perf_limits(policy); policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 6aa256b0a1ed..c3ee3ad98a63 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -565,7 +565,8 @@ void edac_mc_reset_delay_period(unsigned long value) list_for_each(item, &mc_devices) { mci = list_entry(item, struct mem_ctl_info, link); - edac_mod_work(&mci->work, value); + if (mci->op_state == OP_RUNNING_POLL) + edac_mod_work(&mci->work, value); } mutex_unlock(&mem_ctls_mutex); } diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index b4d0bf6534cf..6744d88bdea8 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -239,8 +239,11 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = { { 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc }, }; -#define RIR_RNK_TGT(reg) GET_BITFIELD(reg, 16, 19) -#define RIR_OFFSET(reg) GET_BITFIELD(reg, 2, 14) +#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \ + GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19)) + +#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \ + GET_BITFIELD(reg, 2, 15) : GET_BITFIELD(reg, 2, 14)) /* Device 16, functions 2-7 */ @@ -326,6 +329,7 @@ struct pci_id_descr { struct pci_id_table { const struct pci_id_descr *descr; int n_devs; + enum type type; }; struct sbridge_dev { @@ -394,9 +398,14 @@ static const struct pci_id_descr pci_dev_descr_sbridge[] = { { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0) }, }; -#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) } +#define PCI_ID_TABLE_ENTRY(A, T) { \ + .descr = A, \ + .n_devs = ARRAY_SIZE(A), \ + .type = T \ +} + static const struct pci_id_table pci_dev_descr_sbridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge), + PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -463,7 +472,7 @@ static const struct pci_id_descr pci_dev_descr_ibridge[] = { }; static const struct pci_id_table pci_dev_descr_ibridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge), + PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -536,7 +545,7 @@ static const struct pci_id_descr pci_dev_descr_haswell[] = { }; static const struct pci_id_table pci_dev_descr_haswell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell), + PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL), {0,} /* 0 terminated list. */ }; @@ -580,7 +589,7 @@ static const struct pci_id_descr pci_dev_descr_knl[] = { }; static const struct pci_id_table pci_dev_descr_knl_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_knl), + PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING), {0,} }; @@ -648,7 +657,7 @@ static const struct pci_id_descr pci_dev_descr_broadwell[] = { }; static const struct pci_id_table pci_dev_descr_broadwell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell), + PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL), {0,} /* 0 terminated list. */ }; @@ -1894,14 +1903,14 @@ static void get_memory_layout(const struct mem_ctl_info *mci) pci_read_config_dword(pvt->pci_tad[i], rir_offset[j][k], ®); - tmp_mb = RIR_OFFSET(reg) << 6; + tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6; gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n", i, j, k, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - (u32)RIR_RNK_TGT(reg), + (u32)RIR_RNK_TGT(pvt->info.type, reg), reg); } } @@ -2234,7 +2243,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], rir_offset[n_rir][idx], ®); - *rank = RIR_RNK_TGT(reg); + *rank = RIR_RNK_TGT(pvt->info.type, reg); edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n", n_rir, @@ -3357,12 +3366,12 @@ fail0: #define ICPU(model, table) \ { X86_VENDOR_INTEL, 6, model, 0, (unsigned long)&table } -/* Order here must match "enum type" */ static const struct x86_cpu_id sbridge_cpuids[] = { ICPU(0x2d, pci_dev_descr_sbridge_table), /* SANDY_BRIDGE */ ICPU(0x3e, pci_dev_descr_ibridge_table), /* IVY_BRIDGE */ ICPU(0x3f, pci_dev_descr_haswell_table), /* HASWELL */ ICPU(0x4f, pci_dev_descr_broadwell_table), /* BROADWELL */ + ICPU(0x56, pci_dev_descr_broadwell_table), /* BROADWELL-DE */ ICPU(0x57, pci_dev_descr_knl_table), /* KNIGHTS_LANDING */ { } }; @@ -3398,7 +3407,7 @@ static int sbridge_probe(const struct x86_cpu_id *id) mc, mc + 1, num_mc); sbridge_dev->mc = mc++; - rc = sbridge_register_mci(sbridge_dev, id - sbridge_cpuids); + rc = sbridge_register_mci(sbridge_dev, ptable->type); if (unlikely(rc < 0)) goto fail1; } diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index c2e257d97eff..040966775f40 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -178,6 +178,7 @@ static int write_gid(struct ib_device *ib_dev, u8 port, { int ret = 0; struct net_device *old_net_dev; + enum ib_gid_type old_gid_type; /* in rdma_cap_roce_gid_table, this funciton should be protected by a * sleep-able lock. @@ -199,6 +200,7 @@ static int write_gid(struct ib_device *ib_dev, u8 port, } old_net_dev = table->data_vec[ix].attr.ndev; + old_gid_type = table->data_vec[ix].attr.gid_type; if (old_net_dev && old_net_dev != attr->ndev) dev_put(old_net_dev); /* if modify_gid failed, just delete the old gid */ @@ -207,10 +209,14 @@ static int write_gid(struct ib_device *ib_dev, u8 port, attr = &zattr; table->data_vec[ix].context = NULL; } - if (default_gid) - table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT; + memcpy(&table->data_vec[ix].gid, gid, sizeof(*gid)); memcpy(&table->data_vec[ix].attr, attr, sizeof(*attr)); + if (default_gid) { + table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT; + if (action == GID_TABLE_WRITE_ACTION_DEL) + table->data_vec[ix].attr.gid_type = old_gid_type; + } if (table->data_vec[ix].attr.ndev && table->data_vec[ix].attr.ndev != old_net_dev) dev_hold(table->data_vec[ix].attr.ndev); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 1d92e091e22e..c99525512b34 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3452,14 +3452,14 @@ static int cm_establish(struct ib_cm_id *cm_id) work->cm_event.event = IB_CM_USER_ESTABLISHED; /* Check if the device started its remove_one */ - spin_lock_irq(&cm.lock); + spin_lock_irqsave(&cm.lock, flags); if (!cm_dev->going_down) { queue_delayed_work(cm.wq, &work->work, 0); } else { kfree(work); ret = -ENODEV; } - spin_unlock_irq(&cm.lock); + spin_unlock_irqrestore(&cm.lock, flags); out: return ret; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 5516fb070344..5c155fa91eec 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -661,6 +661,9 @@ int ib_query_port(struct ib_device *device, if (err || port_attr->subnet_prefix) return err; + if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND) + return 0; + err = ib_query_gid(device, port_num, 0, &gid, NULL); if (err) return err; @@ -1024,7 +1027,8 @@ static int __init ib_core_init(void) goto err_mad; } - if (ib_add_ibnl_clients()) { + ret = ib_add_ibnl_clients(); + if (ret) { pr_warn("Couldn't register ibnl clients\n"); goto err_sa; } diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 43e3fa27102b..1c41b95cefec 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -506,7 +506,7 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb, if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); - return -EINVAL; + return -EINVAL; } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 82fb511112da..2d49228f28b2 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -1638,9 +1638,9 @@ static void remove_mad_reg_req(struct ib_mad_agent_private *agent_priv) /* Now, check to see if there are any methods still in use */ if (!check_method_table(method)) { /* If not, release management method table */ - kfree(method); - class->method_table[mgmt_class] = NULL; - /* Any management classes left ? */ + kfree(method); + class->method_table[mgmt_class] = NULL; + /* Any management classes left ? */ if (!check_class_table(class)) { /* If not, release management class table */ kfree(class); diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 5e573bb18660..a5793c8f1590 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -889,9 +889,9 @@ static struct attribute *alloc_hsa_lifespan(char *name, u8 port_num) static void setup_hw_stats(struct ib_device *device, struct ib_port *port, u8 port_num) { - struct attribute_group *hsag = NULL; + struct attribute_group *hsag; struct rdma_hw_stats *stats; - int i = 0, ret; + int i, ret; stats = device->alloc_hw_stats(device, port_num); @@ -899,19 +899,22 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port, return; if (!stats->names || stats->num_counters <= 0) - goto err; + goto err_free_stats; + /* + * Two extra attribue elements here, one for the lifespan entry and + * one to NULL terminate the list for the sysfs core code + */ hsag = kzalloc(sizeof(*hsag) + - // 1 extra for the lifespan config entry - sizeof(void *) * (stats->num_counters + 1), + sizeof(void *) * (stats->num_counters + 2), GFP_KERNEL); if (!hsag) - return; + goto err_free_stats; ret = device->get_hw_stats(device, stats, port_num, stats->num_counters); if (ret != stats->num_counters) - goto err; + goto err_free_hsag; stats->timestamp = jiffies; @@ -922,10 +925,13 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port, hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]); if (!hsag->attrs[i]) goto err; + sysfs_attr_init(hsag->attrs[i]); } /* treat an error here as non-fatal */ hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num); + if (hsag->attrs[i]) + sysfs_attr_init(hsag->attrs[i]); if (port) { struct kobject *kobj = &port->kobj; @@ -946,10 +952,12 @@ static void setup_hw_stats(struct ib_device *device, struct ib_port *port, return; err: - kfree(stats); for (; i >= 0; i--) kfree(hsag->attrs[i]); +err_free_hsag: kfree(hsag); +err_free_stats: + kfree(stats); return; } diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 6e7050ab9e16..14d7eeb09be6 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -300,16 +300,15 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) const struct cpumask *node_mask, *proc_mask = tsk_cpus_allowed(current); struct cpu_mask_set *set = &dd->affinity->proc; - char buf[1024]; /* * check whether process/context affinity has already * been set */ if (cpumask_weight(proc_mask) == 1) { - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask)); - hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %s", - current->pid, current->comm, buf); + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); /* * Mark the pre-set CPU as used. This is atomic so we don't * need the lock @@ -318,9 +317,9 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) cpumask_set_cpu(cpu, &set->used); goto done; } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) { - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask)); - hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %s", - current->pid, current->comm, buf); + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); goto done; } @@ -356,8 +355,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) cpumask_or(intrs, intrs, (dd->affinity->rcv_intr.gen ? &dd->affinity->rcv_intr.mask : &dd->affinity->rcv_intr.used)); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(intrs)); - hfi1_cdbg(PROC, "CPUs used by interrupts: %s", buf); + hfi1_cdbg(PROC, "CPUs used by interrupts: %*pbl", + cpumask_pr_args(intrs)); /* * If we don't have a NUMA node requested, preference is towards @@ -366,18 +365,16 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) if (node == -1) node = dd->node; node_mask = cpumask_of_node(node); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(node_mask)); - hfi1_cdbg(PROC, "device on NUMA %u, CPUs %s", node, buf); + hfi1_cdbg(PROC, "device on NUMA %u, CPUs %*pbl", node, + cpumask_pr_args(node_mask)); /* diff will hold all unused cpus */ cpumask_andnot(diff, &set->mask, &set->used); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(diff)); - hfi1_cdbg(PROC, "unused CPUs (all) %s", buf); + hfi1_cdbg(PROC, "unused CPUs (all) %*pbl", cpumask_pr_args(diff)); /* get cpumask of available CPUs on preferred NUMA */ cpumask_and(mask, diff, node_mask); - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask)); - hfi1_cdbg(PROC, "available cpus on NUMA %s", buf); + hfi1_cdbg(PROC, "available cpus on NUMA %*pbl", cpumask_pr_args(mask)); /* * At first, we don't want to place processes on the same @@ -395,8 +392,8 @@ int hfi1_get_proc_affinity(struct hfi1_devdata *dd, int node) cpumask_andnot(diff, &set->mask, &set->used); cpumask_andnot(mask, diff, node_mask); } - scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask)); - hfi1_cdbg(PROC, "possible CPUs for process %s", buf); + hfi1_cdbg(PROC, "possible CPUs for process %*pbl", + cpumask_pr_args(mask)); cpu = cpumask_first(mask); if (cpu >= nr_cpu_ids) /* empty */ diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 3b876da745a1..81619fbb5842 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -7832,8 +7832,8 @@ static void handle_dcc_err(struct hfi1_devdata *dd, u32 unused, u64 reg) * save first 2 flits in the packet that caused * the error */ - dd->err_info_rcvport.packet_flit1 = hdr0; - dd->err_info_rcvport.packet_flit2 = hdr1; + dd->err_info_rcvport.packet_flit1 = hdr0; + dd->err_info_rcvport.packet_flit2 = hdr1; } switch (info) { case 1: @@ -11906,7 +11906,7 @@ static void update_synth_timer(unsigned long opaque) hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit); } -mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME); + mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME); } #define C_MAX_NAME 13 /* 12 chars + one for /0 */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 5cc492e5776d..0d28a5a40fae 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1337,7 +1337,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) dma_free_coherent(&dd->pcidev->dev, sizeof(u64), (void *)dd->rcvhdrtail_dummy_kvaddr, dd->rcvhdrtail_dummy_physaddr); - dd->rcvhdrtail_dummy_kvaddr = NULL; + dd->rcvhdrtail_dummy_kvaddr = NULL; } for (ctxt = 0; tmp && ctxt < dd->num_rcv_contexts; ctxt++) { diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c index 79b2952c0dfb..4cfb13771897 100644 --- a/drivers/infiniband/hw/hfi1/trace.c +++ b/drivers/infiniband/hw/hfi1/trace.c @@ -214,19 +214,6 @@ const char *print_u32_array( return ret; } -const char *print_u64_array( - struct trace_seq *p, - u64 *arr, int len) -{ - int i; - const char *ret = trace_seq_buffer_ptr(p); - - for (i = 0; i < len; i++) - trace_seq_printf(p, "%s0x%016llx", i == 0 ? "" : " ", arr[i]); - trace_seq_putc(p, 0); - return ret; -} - __hfi1_trace_fn(PKT); __hfi1_trace_fn(PROC); __hfi1_trace_fn(SDMA); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 29f4795f866c..47ffd273ecbd 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -183,7 +183,7 @@ struct user_sdma_iovec { struct sdma_mmu_node *node; }; -#define SDMA_CACHE_NODE_EVICT BIT(0) +#define SDMA_CACHE_NODE_EVICT 0 struct sdma_mmu_node { struct mmu_rb_node rb; @@ -1355,11 +1355,11 @@ static int set_txreq_header(struct user_sdma_request *req, */ SDMA_DBG(req, "TID offset %ubytes %uunits om%u", req->tidoffset, req->tidoffset / req->omfactor, - !!(req->omfactor - KDETH_OM_SMALL)); + req->omfactor != KDETH_OM_SMALL); KDETH_SET(hdr->kdeth.ver_tid_offset, OFFSET, req->tidoffset / req->omfactor); KDETH_SET(hdr->kdeth.ver_tid_offset, OM, - !!(req->omfactor - KDETH_OM_SMALL)); + req->omfactor != KDETH_OM_SMALL); } done: trace_hfi1_sdma_user_header(pq->dd, pq->ctxt, pq->subctxt, diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index b01ef6eee6e8..0eb09e104542 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B; else props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A; - if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) - props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; } + if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) + props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM; diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index dabcc65bd65e..9c0e67bd2ba7 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -822,7 +822,8 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int eqn; int err; - if (entries < 0) + if (entries < 0 || + (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))) return ERR_PTR(-EINVAL); if (check_cq_create_flags(attr->flags)) @@ -1168,11 +1169,16 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) return -ENOSYS; } - if (entries < 1) + if (entries < 1 || + entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) { + mlx5_ib_warn(dev, "wrong entries number %d, max %d\n", + entries, + 1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)); return -EINVAL; + } entries = roundup_pow_of_two(entries + 1); - if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1) + if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1) return -EINVAL; if (entries == ibcq->cqe + 1) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c72797cd9e4f..b48ad85315dc 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -524,6 +524,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, MLX5_CAP_ETH(dev->mdev, scatter_fcs)) props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS; + if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS)) + props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING; + props->vendor_part_id = mdev->pdev->device; props->hw_ver = mdev->pdev->revision; @@ -915,7 +918,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE; gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE; resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp); - resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size); + if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf)) + resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size); resp.cache_line_size = L1_CACHE_BYTES; resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq); resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq); @@ -988,7 +992,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (field_avail(typeof(resp), cqe_version, udata->outlen)) resp.response_length += sizeof(resp.cqe_version); - if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) { + /* + * We don't want to expose information from the PCI bar that is located + * after 4096 bytes, so if the arch only supports larger pages, let's + * pretend we don't support reading the HCA's core clock. This is also + * forced by mmap function. + */ + if (PAGE_SIZE <= 4096 && + field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) { resp.comp_mask |= MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET; resp.hca_core_clock_offset = @@ -1798,7 +1809,7 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr, { struct mlx5_ib_dev *dev = container_of(device, struct mlx5_ib_dev, ib_dev.dev); - return sprintf(buf, "%d.%d.%d\n", fw_rev_maj(dev->mdev), + return sprintf(buf, "%d.%d.%04d\n", fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev)); } @@ -1866,14 +1877,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, break; case MLX5_DEV_EVENT_PORT_DOWN: + case MLX5_DEV_EVENT_PORT_INITIALIZED: ibev.event = IB_EVENT_PORT_ERR; port = (u8)param; break; - case MLX5_DEV_EVENT_PORT_INITIALIZED: - /* not used by ULPs */ - return; - case MLX5_DEV_EVENT_LID_CHANGE: ibev.event = IB_EVENT_LID_CHANGE; port = (u8)param; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 504117657d41..ce434228a5ea 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -235,6 +235,8 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap, qp->rq.max_gs = 0; qp->rq.wqe_cnt = 0; qp->rq.wqe_shift = 0; + cap->max_recv_wr = 0; + cap->max_recv_sge = 0; } else { if (ucmd) { qp->rq.wqe_cnt = ucmd->rq_wqe_count; @@ -1851,13 +1853,15 @@ static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev, static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, const struct ib_ah_attr *ah, struct mlx5_qp_path *path, u8 port, int attr_mask, - u32 path_flags, const struct ib_qp_attr *attr) + u32 path_flags, const struct ib_qp_attr *attr, + bool alt) { enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port); int err; if (attr_mask & IB_QP_PKEY_INDEX) - path->pkey_index = attr->pkey_index; + path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index : + attr->pkey_index); if (ah->ah_flags & IB_AH_GRH) { if (ah->grh.sgid_index >= @@ -1877,9 +1881,9 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, ah->grh.sgid_index); path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4; } else { - path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0; - path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 : - 0; + path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0; + path->fl_free_ar |= + (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x40 : 0; path->rlid = cpu_to_be16(ah->dlid); path->grh_mlid = ah->src_path_bits & 0x7f; if (ah->ah_flags & IB_AH_GRH) @@ -1903,7 +1907,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, path->port = port; if (attr_mask & IB_QP_TIMEOUT) - path->ackto_lt = attr->timeout << 3; + path->ackto_lt = (alt ? attr->alt_timeout : attr->timeout) << 3; if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt) return modify_raw_packet_eth_prio(dev->mdev, @@ -2264,7 +2268,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, context->log_pg_sz_remote_qpn = cpu_to_be32(attr->dest_qp_num); if (attr_mask & IB_QP_PKEY_INDEX) - context->pri_path.pkey_index = attr->pkey_index; + context->pri_path.pkey_index = cpu_to_be16(attr->pkey_index); /* todo implement counter_index functionality */ @@ -2277,7 +2281,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (attr_mask & IB_QP_AV) { err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path, attr_mask & IB_QP_PORT ? attr->port_num : qp->port, - attr_mask, 0, attr); + attr_mask, 0, attr, false); if (err) goto out; } @@ -2288,7 +2292,9 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, if (attr_mask & IB_QP_ALT_PATH) { err = mlx5_set_path(dev, qp, &attr->alt_ah_attr, &context->alt_path, - attr->alt_port_num, attr_mask, 0, attr); + attr->alt_port_num, + attr_mask | IB_QP_PKEY_INDEX | IB_QP_TIMEOUT, + 0, attr, true); if (err) goto out; } @@ -4013,11 +4019,12 @@ static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) { to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path); to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path); - qp_attr->alt_pkey_index = context->alt_path.pkey_index & 0x7f; + qp_attr->alt_pkey_index = + be16_to_cpu(context->alt_path.pkey_index); qp_attr->alt_port_num = qp_attr->alt_ah_attr.port_num; } - qp_attr->pkey_index = context->pri_path.pkey_index & 0x7f; + qp_attr->pkey_index = be16_to_cpu(context->pri_path.pkey_index); qp_attr->port_num = context->pri_path.port; /* qp_attr->en_sqd_async_notify is only applicable in modify qp */ @@ -4079,17 +4086,19 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->cap.max_recv_sge = qp->rq.max_gs; if (!ibqp->uobject) { - qp_attr->cap.max_send_wr = qp->sq.wqe_cnt; + qp_attr->cap.max_send_wr = qp->sq.max_post; qp_attr->cap.max_send_sge = qp->sq.max_gs; + qp_init_attr->qp_context = ibqp->qp_context; } else { qp_attr->cap.max_send_wr = 0; qp_attr->cap.max_send_sge = 0; } - /* We don't support inline sends for kernel QPs (yet), and we - * don't know what userspace's value should be. - */ - qp_attr->cap.max_inline_data = 0; + qp_init_attr->qp_type = ibqp->qp_type; + qp_init_attr->recv_cq = ibqp->recv_cq; + qp_init_attr->send_cq = ibqp->send_cq; + qp_init_attr->srq = ibqp->srq; + qp_attr->cap.max_inline_data = qp->max_inline_data; qp_init_attr->cap = qp_attr->cap; diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 7209fbc03ccb..a0b6ebee4d8a 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -36,7 +36,6 @@ #include <linux/dma-mapping.h> #include <linux/sched.h> #include <linux/hugetlb.h> -#include <linux/dma-attrs.h> #include <linux/iommu.h> #include <linux/workqueue.h> #include <linux/list.h> @@ -112,10 +111,6 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable, int i; int flags; dma_addr_t pa; - DEFINE_DMA_ATTRS(attrs); - - if (dmasync) - dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); if (!can_do_mlock()) return -EPERM; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 5fa4d4d81ee0..7de5134bec85 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -502,6 +502,12 @@ static void rvt_remove_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp) */ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, enum ib_qp_type type) + __releases(&qp->s_lock) + __releases(&qp->s_hlock) + __releases(&qp->r_lock) + __acquires(&qp->r_lock) + __acquires(&qp->s_hlock) + __acquires(&qp->s_lock) { if (qp->state != IB_QPS_RESET) { qp->state = IB_QPS_RESET; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index bab7db6fa9ab..4f7d9b48df64 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -94,6 +94,7 @@ enum { IPOIB_NEIGH_TBL_FLUSH = 12, IPOIB_FLAG_DEV_ADDR_SET = 13, IPOIB_FLAG_DEV_ADDR_CTRL = 14, + IPOIB_FLAG_GOING_DOWN = 15, IPOIB_MAX_BACKOFF_SECONDS = 16, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index b2f42835d76d..951d9abcca8b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1486,6 +1486,10 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr, { struct net_device *dev = to_net_dev(d); int ret; + struct ipoib_dev_priv *priv = netdev_priv(dev); + + if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags)) + return -EPERM; if (!rtnl_trylock()) return restart_syscall(); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 45c40a17d6a6..dc6d241b9406 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1015,7 +1015,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv) if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL)) return false; - netif_addr_lock(priv->dev); + netif_addr_lock_bh(priv->dev); /* The subnet prefix may have changed, update it now so we won't have * to do it later @@ -1026,12 +1026,12 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv) search_gid.global.interface_id = priv->local_gid.global.interface_id; - netif_addr_unlock(priv->dev); + netif_addr_unlock_bh(priv->dev); err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB, priv->dev, &port, &index); - netif_addr_lock(priv->dev); + netif_addr_lock_bh(priv->dev); if (search_gid.global.interface_id != priv->local_gid.global.interface_id) @@ -1092,7 +1092,7 @@ static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv) } out: - netif_addr_unlock(priv->dev); + netif_addr_unlock_bh(priv->dev); return ret; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 2d7c16346648..5f58c41ef787 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1206,7 +1206,9 @@ struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) neigh = NULL; goto out_unlock; } - neigh->alive = jiffies; + + if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) + neigh->alive = jiffies; goto out_unlock; } } @@ -1851,7 +1853,7 @@ static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; - netif_addr_lock(netdev); + netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, @@ -1859,7 +1861,7 @@ static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) memcpy(netdev->dev_addr + 4, &priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); - netif_addr_unlock(netdev); + netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { down_read(&priv->vlan_rwsem); @@ -1875,7 +1877,7 @@ static int ipoib_check_lladdr(struct net_device *dev, union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; - netif_addr_lock(dev); + netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. @@ -1885,7 +1887,7 @@ static int ipoib_check_lladdr(struct net_device *dev, gid->global.interface_id == 0) ret = -EINVAL; - netif_addr_unlock(dev); + netif_addr_unlock_bh(dev); return ret; } @@ -2141,6 +2143,9 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) ib_unregister_event_handler(&priv->event_handler); flush_workqueue(ipoib_workqueue); + /* mark interface in the middle of destruction */ + set_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags); + rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP); rtnl_unlock(); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 82fbc9442608..d3394b6add24 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -582,13 +582,13 @@ void ipoib_mcast_join_task(struct work_struct *work) return; } priv->local_lid = port_attr.lid; - netif_addr_lock(dev); + netif_addr_lock_bh(dev); if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) { - netif_addr_unlock(dev); + netif_addr_unlock_bh(dev); return; } - netif_addr_unlock(dev); + netif_addr_unlock_bh(dev); spin_lock_irq(&priv->lock); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 64a35595eab8..a2f9f29c6ab5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -131,6 +131,9 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) ppriv = netdev_priv(pdev); + if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags)) + return -EPERM; + snprintf(intf_name, sizeof intf_name, "%s.%04x", ppriv->dev->name, pkey); priv = ipoib_intf_alloc(intf_name); @@ -183,6 +186,9 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) ppriv = netdev_priv(pdev); + if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags)) + return -EPERM; + if (!rtnl_trylock()) return restart_syscall(); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 646de170ec12..3322ed750172 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1457,7 +1457,6 @@ static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch, { unsigned int sg_offset = 0; - state->desc = req->indirect_desc; state->fr.next = req->fr_list; state->fr.end = req->fr_list + ch->target->mr_per_cmd; state->sg = scat; @@ -1489,7 +1488,6 @@ static int srp_map_sg_dma(struct srp_map_state *state, struct srp_rdma_ch *ch, struct scatterlist *sg; int i; - state->desc = req->indirect_desc; for_each_sg(scat, sg, count, i) { srp_map_desc(state, ib_sg_dma_address(dev->dev, sg), ib_sg_dma_len(dev->dev, sg), @@ -1655,6 +1653,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch, target->indirect_size, DMA_TO_DEVICE); memset(&state, 0, sizeof(state)); + state.desc = req->indirect_desc; if (dev->use_fast_reg) ret = srp_map_sg_fr(&state, ch, req, scat, count); else if (dev->use_fmr) @@ -3526,7 +3525,7 @@ static void srp_add_one(struct ib_device *device) int mr_page_shift, p; u64 max_pages_per_mr; - srp_dev = kmalloc(sizeof *srp_dev, GFP_KERNEL); + srp_dev = kzalloc(sizeof(*srp_dev), GFP_KERNEL); if (!srp_dev) return; @@ -3586,8 +3585,6 @@ static void srp_add_one(struct ib_device *device) IB_ACCESS_REMOTE_WRITE); if (IS_ERR(srp_dev->global_mr)) goto err_pd; - } else { - srp_dev->global_mr = NULL; } for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index e158b22ef32f..a7a28110dc80 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2275,7 +2275,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto end_coredump; /* Align to page */ - if (!dump_skip(cprm, dataoff - cprm->file->f_pos)) + if (!dump_skip(cprm, dataoff - cprm->pos)) goto end_coredump; for (i = 0, vma = first_vma(current, gate_vma); vma != NULL; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 71ade0e556b7..203589311bf8 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1787,7 +1787,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) goto end_coredump; } - if (!dump_skip(cprm, dataoff - cprm->file->f_pos)) + if (!dump_skip(cprm, dataoff - cprm->pos)) goto end_coredump; if (!elf_fdpic_dump_segments(cprm)) diff --git a/fs/coredump.c b/fs/coredump.c index 38a7ab87e10a..281b768000e6 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -794,6 +794,7 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr) return 0; file->f_pos = pos; cprm->written += n; + cprm->pos += n; nr -= n; } return 1; @@ -808,6 +809,7 @@ int dump_skip(struct coredump_params *cprm, size_t nr) if (dump_interrupted() || file->f_op->llseek(file, nr, SEEK_CUR) < 0) return 0; + cprm->pos += nr; return 1; } else { while (nr > PAGE_SIZE) { @@ -822,7 +824,7 @@ EXPORT_SYMBOL(dump_skip); int dump_align(struct coredump_params *cprm, int align) { - unsigned mod = cprm->file->f_pos & (align - 1); + unsigned mod = cprm->pos & (align - 1); if (align & (align - 1)) return 0; return mod ? dump_skip(cprm, align - mod) : 1; diff --git a/fs/dcache.c b/fs/dcache.c index ad4a542e9bab..817c243c1ff1 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1636,7 +1636,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; - + dentry->d_flags |= DCACHE_RCUACCESS; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject @@ -2358,7 +2358,6 @@ static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b) { BUG_ON(!d_unhashed(entry)); hlist_bl_lock(b); - entry->d_flags |= DCACHE_RCUACCESS; hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } @@ -2843,6 +2842,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, /* ... and switch them in the tree */ if (IS_ROOT(dentry)) { /* splicing a tree */ + dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_parent = target->d_parent; target->d_parent = target; list_del_init(&target->d_child); diff --git a/fs/namei.c b/fs/namei.c index 6a82fb7e2127..70580ab1445c 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3030,9 +3030,13 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, } if (*opened & FILE_CREATED) fsnotify_create(dir, dentry); - path->dentry = dentry; - path->mnt = nd->path.mnt; - return 1; + if (unlikely(d_is_negative(dentry))) { + error = -ENOENT; + } else { + path->dentry = dentry; + path->mnt = nd->path.mnt; + return 1; + } } } dput(dentry); @@ -3201,9 +3205,7 @@ static int do_last(struct nameidata *nd, int acc_mode = op->acc_mode; unsigned seq; struct inode *inode; - struct path save_parent = { .dentry = NULL, .mnt = NULL }; struct path path; - bool retried = false; int error; nd->flags &= ~LOOKUP_PARENT; @@ -3246,7 +3248,6 @@ static int do_last(struct nameidata *nd, return -EISDIR; } -retry_lookup: if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { error = mnt_want_write(nd->path.mnt); if (!error) @@ -3298,6 +3299,10 @@ retry_lookup: got_write = false; } + error = follow_managed(&path, nd); + if (unlikely(error < 0)) + return error; + if (unlikely(d_is_negative(path.dentry))) { path_to_nameidata(&path, nd); return -ENOENT; @@ -3313,10 +3318,6 @@ retry_lookup: return -EEXIST; } - error = follow_managed(&path, nd); - if (unlikely(error < 0)) - return error; - seq = 0; /* out of RCU mode, so the value doesn't matter */ inode = d_backing_inode(path.dentry); finish_lookup: @@ -3327,23 +3328,14 @@ finish_lookup: if (unlikely(error)) return error; - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { - path_to_nameidata(&path, nd); - } else { - save_parent.dentry = nd->path.dentry; - save_parent.mnt = mntget(path.mnt); - nd->path.dentry = path.dentry; - - } + path_to_nameidata(&path, nd); nd->inode = inode; nd->seq = seq; /* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */ finish_open: error = complete_walk(nd); - if (error) { - path_put(&save_parent); + if (error) return error; - } audit_inode(nd->name, nd->path.dentry, 0); error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) @@ -3366,13 +3358,9 @@ finish_open_created: goto out; BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ error = vfs_open(&nd->path, file, current_cred()); - if (!error) { - *opened |= FILE_OPENED; - } else { - if (error == -EOPENSTALE) - goto stale_open; + if (error) goto out; - } + *opened |= FILE_OPENED; opened: error = open_check_o_direct(file); if (!error) @@ -3388,26 +3376,7 @@ out: } if (got_write) mnt_drop_write(nd->path.mnt); - path_put(&save_parent); return error; - -stale_open: - /* If no saved parent or already retried then can't retry */ - if (!save_parent.dentry || retried) - goto out; - - BUG_ON(save_parent.dentry != dir); - path_put(&nd->path); - nd->path = save_parent; - nd->inode = dir->d_inode; - save_parent.mnt = NULL; - save_parent.dentry = NULL; - if (got_write) { - mnt_drop_write(nd->path.mnt); - got_write = false; - } - retried = true; - goto retry_lookup; } static int do_tmpfile(struct nameidata *nd, unsigned flags, diff --git a/fs/namespace.c b/fs/namespace.c index 4fb1691b4355..a7ec92c051f5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2409,8 +2409,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } if (type->fs_flags & FS_USERNS_VISIBLE) { - if (!fs_fully_visible(type, &mnt_flags)) + if (!fs_fully_visible(type, &mnt_flags)) { + put_filesystem(type); return -EPERM; + } } } @@ -3271,7 +3273,7 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ - if (!(mnt_flags & MNT_LOCKED)) + if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 576e4639ca60..314b3caa701c 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -65,6 +65,7 @@ struct coredump_params { unsigned long limit; unsigned long mm_flags; loff_t written; + loff_t pos; }; /* diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 0c72204c75fc..fb39d5add173 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -25,7 +25,7 @@ #define CLK_SET_PARENT_GATE BIT(1) /* must be gated across re-parent */ #define CLK_SET_RATE_PARENT BIT(2) /* propagate rate change up one level */ #define CLK_IGNORE_UNUSED BIT(3) /* do not gate even if unused */ -#define CLK_IS_ROOT BIT(4) /* Deprecated: Don't use */ + /* unused */ #define CLK_IS_BASIC BIT(5) /* Basic clk, can't do a to_clk_foo() */ #define CLK_GET_RATE_NOCACHE BIT(6) /* do not use the cached clk rate */ #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */ diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 786ad32631a6..07b83d32f66c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -152,6 +152,8 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); +static inline struct cpuidle_device *cpuidle_get_device(void) +{return __this_cpu_read(cpuidle_devices); } #else static inline void disable_cpuidle(void) { } static inline bool cpuidle_not_available(struct cpuidle_driver *drv, @@ -187,6 +189,7 @@ static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } static inline struct cpuidle_driver *cpuidle_get_cpu_driver( struct cpuidle_device *dev) {return NULL; } +static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #endif #if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND) diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 64221027bf1f..e4e29882fdfd 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -460,10 +460,9 @@ struct mlx5_core_qp { }; struct mlx5_qp_path { - u8 fl; + u8 fl_free_ar; u8 rsvd3; - u8 free_ar; - u8 pkey_index; + __be16 pkey_index; u8 rsvd0; u8 grh_mlid; __be16 rlid; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 432bed510369..7e440d41487a 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -217,10 +217,10 @@ enum ib_device_cap_flags { IB_DEVICE_CROSS_CHANNEL = (1 << 27), IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), IB_DEVICE_SIGNATURE_HANDOVER = (1 << 30), - IB_DEVICE_ON_DEMAND_PAGING = (1 << 31), + IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31), IB_DEVICE_SG_GAPS_REG = (1ULL << 32), - IB_DEVICE_VIRTUAL_FUNCTION = ((u64)1 << 33), - IB_DEVICE_RAW_SCATTER_FCS = ((u64)1 << 34), + IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33), + IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), }; enum ib_signature_prot_cap { diff --git a/kernel/relay.c b/kernel/relay.c index 074994bcfa9b..04d7cf3ef8cf 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -614,6 +614,7 @@ free_bufs: kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); + kfree(chan); return NULL; } EXPORT_SYMBOL_GPL(relay_open); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index bd12c6c714ec..c5aeedf4e93a 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, */ static void cpuidle_idle_call(void) { - struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_device *dev = cpuidle_get_device(); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; diff --git a/mm/fadvise.c b/mm/fadvise.c index b8024fa7101d..6c707bfe02fd 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -126,6 +126,17 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) */ start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT; end_index = (endbyte >> PAGE_SHIFT); + if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK) { + /* First page is tricky as 0 - 1 = -1, but pgoff_t + * is unsigned, so the end_index >= start_index + * check below would be true and we'll discard the whole + * file cache which is not what was asked. + */ + if (end_index == 0) + break; + + end_index--; + } if (end_index >= start_index) { unsigned long count = invalidate_mapping_pages(mapping, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d26162e81fea..388c2bb9b55c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -832,8 +832,27 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) * Only the process that called mmap() has reserves for * private mappings. */ - if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) - return true; + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + /* + * Like the shared case above, a hole punch or truncate + * could have been performed on the private mapping. + * Examine the value of chg to determine if reserves + * actually exist or were previously consumed. + * Very Subtle - The value of chg comes from a previous + * call to vma_needs_reserves(). The reserve map for + * private mappings has different (opposite) semantics + * than that of shared mappings. vma_needs_reserves() + * has already taken this difference in semantics into + * account. Therefore, the meaning of chg is the same + * as in the shared case above. Code could easily be + * combined, but keeping it separate draws attention to + * subtle differences. + */ + if (chg) + return false; + else + return true; + } return false; } @@ -1816,6 +1835,25 @@ static long __vma_reservation_common(struct hstate *h, if (vma->vm_flags & VM_MAYSHARE) return ret; + else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { + /* + * In most cases, reserves always exist for private mappings. + * However, a file associated with mapping could have been + * hole punched or truncated after reserves were consumed. + * As subsequent fault on such a range will not use reserves. + * Subtle - The reserve map for private mappings has the + * opposite meaning than that of shared mappings. If NO + * entry is in the reserve map, it means a reservation exists. + * If an entry exists in the reserve map, it means the + * reservation has already been consumed. As a result, the + * return value of this routine is the opposite of the + * value returned from reserve map manipulation routines above. + */ + if (ret) + return 0; + else + return 1; + } else return ret < 0 ? ret : 0; } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 18b6a2b8d183..28439acda6ec 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -763,8 +763,8 @@ static int kasan_mem_notifier(struct notifier_block *nb, static int __init kasan_memhotplug_init(void) { - pr_err("WARNING: KASAN doesn't support memory hot-add\n"); - pr_err("Memory hot-add will be disabled\n"); + pr_info("WARNING: KASAN doesn't support memory hot-add\n"); + pr_info("Memory hot-add will be disabled\n"); hotplug_memory_notifier(kasan_mem_notifier, 0); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 58c69c94402a..75e74408cc8f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1608,7 +1608,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { - if (!current->memcg_may_oom || current->memcg_in_oom) + if (!current->memcg_may_oom) return; /* * We are in the middle of the charge context here, so we diff --git a/mm/swap.c b/mm/swap.c index 95916142fc46..59f5fafa6e1f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -667,6 +667,24 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); +/* + * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM + * workqueue, aiding in getting memory freed. + */ +static struct workqueue_struct *lru_add_drain_wq; + +static int __init lru_init(void) +{ + lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0); + + if (WARN(!lru_add_drain_wq, + "Failed to create workqueue lru_add_drain_wq")) + return -ENOMEM; + + return 0; +} +early_initcall(lru_init); + void lru_add_drain_all(void) { static DEFINE_MUTEX(lock); @@ -686,7 +704,7 @@ void lru_add_drain_all(void) pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); - schedule_work_on(cpu, work); + queue_work_on(cpu, lru_add_drain_wq, work); cpumask_set_cpu(cpu, &has_work); } } diff --git a/mm/swap_state.c b/mm/swap_state.c index 0d457e7db8d6..c99463ac02fb 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -252,7 +252,10 @@ static inline void free_swap_cache(struct page *page) void free_page_and_swap_cache(struct page *page) { free_swap_cache(page); - put_page(page); + if (is_huge_zero_page(page)) + put_huge_zero_page(); + else + put_page(page); } /* |