diff options
46 files changed, 544 insertions, 572 deletions
diff --git a/Documentation/ABI/testing/ppc-memtrace b/Documentation/ABI/testing/ppc-memtrace index 9606aed33137..2de9fd18715e 100644 --- a/Documentation/ABI/testing/ppc-memtrace +++ b/Documentation/ABI/testing/ppc-memtrace @@ -3,7 +3,7 @@ Date: Aug 2017 KernelVersion: 4.14 Contact: linuxppc-dev@lists.ozlabs.org Description: This folder contains the relevant debugfs files for the - hardware trace macro to use. CONFIG_PPC64_HARDWARE_TRACING + hardware trace macro to use. CONFIG_PPC_MEMTRACE must be set. What: /sys/kernel/debug/powerpc/memtrace/enable diff --git a/Documentation/arch/powerpc/papr_hcalls.rst b/Documentation/arch/powerpc/papr_hcalls.rst index 14e39f095a1c..44c9c8b32ae3 100644 --- a/Documentation/arch/powerpc/papr_hcalls.rst +++ b/Documentation/arch/powerpc/papr_hcalls.rst @@ -305,8 +305,8 @@ like core instruction, core LLAT and nest. | Input: authorization, objectlabel, objectlabellen, policy, out, outlen | Out: *Hypervisor Generated Key, or None when the wrapping key policy is set* | Return Value: *H_SUCCESS, H_Function, H_State, H_R_State, H_Parameter, H_P2, - H_P3, H_P4, H_P5, H_P6, H_Authority, H_Nomem, H_Busy, H_Resource, - H_Aborted* + H_P3, H_P4, H_P5, H_P6, H_Authority, H_Nomem, H_Busy, + H_Resource, H_Aborted* H_PKS_GEN_KEY is used to have the hypervisor generate a new random key. This key is stored as an object in the Power LPAR Platform KeyStore with @@ -321,8 +321,8 @@ the user. Generation of wrapping keys is supported only for a key size of | inlen, out, outlen, continue-token | Out: *continue-token, byte size of wrapped object, wrapped object* | Return Value: *H_SUCCESS, H_Function, H_State, H_R_State, H_Parameter, H_P2, - H_P3, H_P4, H_P5, H_P6, H_P7, H_P8, H_P9, H_Authority, H_Invalid_Key, - H_NOT_FOUND, H_Busy, H_LongBusy, H_Aborted* + H_P3, H_P4, H_P5, H_P6, H_P7, H_P8, H_P9, H_Authority, + H_Invalid_Key, H_NOT_FOUND, H_Busy, H_LongBusy, H_Aborted* H_PKS_WRAP_OBJECT is used to wrap an object using a wrapping key stored in the Power LPAR Platform KeyStore and return the wrapped object to the caller. The @@ -331,16 +331,16 @@ which must have been previously created with H_PKS_GEN_KEY. The provided object is then encrypted with the wrapping key and additional metadata and the result is returned to the caller. - **H_PKS_UNWRAP_OBJECT** | Input: authorization, objectwrapflags, in, inlen, out, outlen, continue-token | Out: *continue-token, byte size of unwrapped object, unwrapped object* | Return Value: *H_SUCCESS, H_Function, H_State, H_R_State, H_Parameter, H_P2, - H_P3, H_P4, H_P5, H_P6, H_P7, H_Authority, H_Unsupported, H_Bad_Data, - H_NOT_FOUND, H_Invalid_Key, H_Busy, H_LongBusy, H_Aborted* + H_P3, H_P4, H_P5, H_P6, H_P7, H_Authority, H_Unsupported, + H_Bad_Data, H_NOT_FOUND, H_Invalid_Key, H_Busy, H_LongBusy, + H_Aborted* -H_PKS_UNWRAP_OBJECT is used to unwrap an object that was previously warapped with +H_PKS_UNWRAP_OBJECT is used to unwrap an object that was previously wrapped with H_PKS_WRAP_OBJECT. References diff --git a/MAINTAINERS b/MAINTAINERS index b4bfb698fd1e..b4c1b751698d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14555,7 +14555,7 @@ S: Supported F: include/keys/trusted_dcp.h F: security/keys/trusted-keys/trusted_dcp.c -KEYS-TRUSTED-PLPKS +KEYS-TRUSTED-PKWM M: Srish Srinivasan <ssrish@linux.ibm.com> M: Nayna Jain <nayna@linux.ibm.com> L: linux-integrity@vger.kernel.org diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts index 5d8877e1f4ad..05fcf08df1ca 100644 --- a/arch/powerpc/boot/dts/ac14xx.dts +++ b/arch/powerpc/boot/dts/ac14xx.dts @@ -148,19 +148,6 @@ compatible = "fsl,mpc5121rev2-clock", "fsl,mpc5121-clock"; }; - /* - * GPIO PIC: - * interrupts cell = <pin nr, sense> - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change - */ - gpio_pic: gpio@1100 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - }; - sdhc@1500 { cd-gpios = <&gpio_pic 23 0>; /* card detect */ wp-gpios = <&gpio_pic 24 0>; /* write protect */ diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi index a278fb7b9e71..9c5dacb94b92 100644 --- a/arch/powerpc/boot/dts/mpc5121.dtsi +++ b/arch/powerpc/boot/dts/mpc5121.dtsi @@ -146,10 +146,14 @@ interrupts = <83 0x8>; }; - gpio@1100 { + gpio_pic: gpio@1100 { compatible = "fsl,mpc5121-gpio"; reg = <0x1100 0x100>; interrupts = <78 0x8>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; can@1300 { diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts index 67c3b9db75d7..05e93ca294ee 100644 --- a/arch/powerpc/boot/dts/pdm360ng.dts +++ b/arch/powerpc/boot/dts/pdm360ng.dts @@ -9,6 +9,7 @@ * Copyright 2008 Freescale Semiconductor Inc. */ +#include <dt-bindings/gpio/gpio.h> #include "mpc5121.dtsi" / { @@ -176,11 +177,12 @@ /* ADS7845 touch screen controller */ ts@0 { - compatible = "ti,ads7846"; + compatible = "ti,ads7845"; reg = <0x0>; spi-max-frequency = <3000000>; - /* pen irq is GPIO25 */ - interrupts = <78 0x8>; + interrupt-parent = <&gpio_pic>; + interrupts = <25 0x8>; + pendown-gpio = <&gpio_pic 25 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index f133b5930ae1..be6cd5aab016 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -5,24 +5,33 @@ #include <linux/threads.h> #include <linux/irq.h> -typedef struct { - unsigned int __softirq_pending; - unsigned int timer_irqs_event; - unsigned int broadcast_irqs_event; - unsigned int timer_irqs_others; - unsigned int pmu_irqs; - unsigned int mce_exceptions; - unsigned int spurious_irqs; - unsigned int sreset_irqs; +enum irq_stat_counts { + IRQ_COUNT_LOC_TIMER, + IRQ_COUNT_BCT_TIMER, + IRQ_COUNT_OTHER_TIMER, + IRQ_COUNT_SPURIOUS, + IRQ_COUNT_PMI, + IRQ_COUNT_MCE, + IRQ_COUNT_NMI_SRESET, #ifdef CONFIG_PPC_WATCHDOG - unsigned int soft_nmi_irqs; + IRQ_COUNT_WATCHDOG, #endif #ifdef CONFIG_PPC_DOORBELL - unsigned int doorbell_irqs; + IRQ_COUNT_DOORBELL, #endif + IRQ_COUNT_MAX, +}; + +typedef struct { + unsigned int counts[IRQ_COUNT_MAX]; } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +DECLARE_PER_CPU(unsigned int, __softirq_pending); +#define local_softirq_pending_ref __softirq_pending + +#define inc_irq_stat(index) __this_cpu_inc(irq_stat.counts[IRQ_COUNT_##index]) +void inc_irq_stat_and_enable(enum irq_stat_counts which); #define __ARCH_IRQ_STAT #define __ARCH_IRQ_EXIT_IRQS_DISABLED diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 1b45a49e9bed..c7d0e71eac83 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -70,6 +70,7 @@ #include <linux/irq-entry-common.h> #include <asm/kprobes.h> +#include <asm/mmu.h> #include <asm/runlatch.h> #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG @@ -290,7 +291,7 @@ interrupt_handler long func(struct pt_regs *regs) \ state = irqentry_nmi_enter(regs); \ } else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && \ firmware_has_feature(FW_FEATURE_LPAR) && \ - !radix_enabled()) { \ + !early_radix_enabled()) { \ /* no nmi_entry for a pseries hash guest \ * taking a real mode exception */ \ } else if (IS_ENABLED(CONFIG_KASAN)) { \ @@ -301,13 +302,12 @@ interrupt_handler long func(struct pt_regs *regs) \ state = irqentry_nmi_enter(regs); \ } \ ret = ____##func (regs); \ - arch_interrupt_nmi_exit_prepare(regs, &nmi_state); \ if (mfmsr() & MSR_DR) { \ /* nmi_exit if relocations are on */ \ irqentry_nmi_exit(regs, state); \ } else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && \ firmware_has_feature(FW_FEATURE_LPAR) && \ - !radix_enabled()) { \ + !early_radix_enabled()) { \ /* no nmi_exit for a pseries hash guest \ * taking a real mode exception */ \ } else if (IS_ENABLED(CONFIG_KASAN)) { \ @@ -317,6 +317,7 @@ interrupt_handler long func(struct pt_regs *regs) \ } else { \ irqentry_nmi_exit(regs, state); \ } \ + arch_interrupt_nmi_exit_prepare(regs, &nmi_state); \ \ return ret; \ } \ diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index a690e7da53c2..599a9e02af02 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -2,21 +2,6 @@ #ifndef __ASM_KASAN_H #define __ASM_KASAN_H -#if defined(CONFIG_KASAN) && !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) -#define _GLOBAL_KASAN(fn) \ - _GLOBAL(fn); \ - _GLOBAL(__##fn) -#define _GLOBAL_TOC_KASAN(fn) \ - _GLOBAL_TOC(fn); \ - _GLOBAL_TOC(__##fn) -#define EXPORT_SYMBOL_KASAN(fn) \ - EXPORT_SYMBOL(__##fn) -#else /* CONFIG_KASAN && !CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */ -#define _GLOBAL_KASAN(fn) _GLOBAL(fn) -#define _GLOBAL_TOC_KASAN(fn) _GLOBAL_TOC(fn) -#define EXPORT_SYMBOL_KASAN(fn) -#endif /* CONFIG_KASAN && !CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */ - #ifndef __ASSEMBLER__ #include <asm/page.h> diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index 1981bd4036b5..161b949683b3 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -29,29 +29,10 @@ extern void * memchr(const void *,int,__kernel_size_t); void memcpy_flushcache(void *dest, const void *src, size_t size); #ifdef CONFIG_KASAN -/* __mem variants are used by KASAN to implement instrumented meminstrinsics. */ -#ifdef CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX +/* Used by mm/kasan as raw backends to bypass KASAN checking. */ #define __memset memset #define __memcpy memcpy #define __memmove memmove -#else /* CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */ -void *__memset(void *s, int c, __kernel_size_t count); -void *__memcpy(void *to, const void *from, __kernel_size_t n); -void *__memmove(void *to, const void *from, __kernel_size_t n); -#ifndef __SANITIZE_ADDRESS__ -/* - * For files that are not instrumented (e.g. mm/slub.c) we - * should use not instrumented version of mem* functions. - */ -#define memcpy(dst, src, len) __memcpy(dst, src, len) -#define memmove(dst, src, len) __memmove(dst, src, len) -#define memset(s, c, n) __memset(s, c, n) - -#ifndef __NO_FORTIFY -#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ -#endif -#endif /* !__SANITIZE_ADDRESS__ */ -#endif /* CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */ #endif /* CONFIG_KASAN */ #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 44ec416fa489..02c3c9ab3ea9 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -71,6 +71,7 @@ extern void map_cpu_to_node(int cpu, int node); extern void unmap_cpu_from_node(unsigned long cpu); #endif /* CONFIG_HOTPLUG_CPU */ +int cpu_to_coregroup_id(int cpu); #else static inline int early_cpu_to_node(int cpu) { return 0; } @@ -107,14 +108,6 @@ static inline void map_cpu_to_node(int cpu, int node) {} static inline void unmap_cpu_from_node(unsigned long cpu) {} #endif /* CONFIG_HOTPLUG_CPU */ #endif /* CONFIG_SMP */ - -#endif /* CONFIG_NUMA */ - -#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) -void find_and_update_cpu_nid(int cpu); -extern int cpu_to_coregroup_id(int cpu); -#else -static inline void find_and_update_cpu_nid(int cpu) {} static inline int cpu_to_coregroup_id(int cpu) { #ifdef CONFIG_SMP @@ -124,6 +117,12 @@ static inline int cpu_to_coregroup_id(int cpu) #endif } +#endif /* CONFIG_NUMA */ + +#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) +void find_and_update_cpu_nid(int cpu); +#else +static inline void find_and_update_cpu_nid(int cpu) {} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #include <asm-generic/topology.h> diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 6f6801da9dc1..4731e27bb7bc 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -35,12 +35,7 @@ void __init set_cur_cpu_spec(struct cpu_spec *s) struct cpu_spec *t = &the_cpu_spec; t = PTRRELOC(t); - /* - * use memcpy() instead of *t = *s so that GCC replaces it - * by __memcpy() when KASAN is active - */ - memcpy(t, s, sizeof(*t)); - + *t = *s; *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; } @@ -53,11 +48,8 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, t = PTRRELOC(t); old = *t; - /* - * Copy everything, then do fixups. Use memcpy() instead of *t = *s - * so that GCC replaces it by __memcpy() when KASAN is active - */ - memcpy(t, s, sizeof(*t)); + /* Copy everything, then do fixups. */ + *t = *s; /* * If we are overriding a previous value derived from the real diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 5712dd846263..f5e298a4c4c0 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -31,7 +31,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception) do_hard_irq_enable(); kvmppc_clear_host_ipi(smp_processor_id()); - __this_cpu_inc(irq_stat.doorbell_irqs); + inc_irq_stat(DOORBELL); smp_ipi_demux_relaxed(); /* already performed the barrier */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 15a3c3fd8e70..bce546931a13 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -73,6 +73,7 @@ DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); +DEFINE_PER_CPU(unsigned int, __softirq_pending); #ifdef CONFIG_PPC32 atomic_t ppc_n_lost_interrupts; @@ -83,105 +84,105 @@ u32 tau_interrupts(unsigned long cpu); #endif #endif /* CONFIG_PPC32 */ +struct irq_stat_info { + const char *symbol; + const char *text; + int optional; +}; + +/* ISE - IRQ STAT ENABLED, ISC - IRQ STAT CONDITIONAL */ +#define ISE(idx, sym, txt)[IRQ_COUNT_##idx] = { .symbol = sym, .text = txt, .optional = 0} +#define ISC(idx, sym, txt)[IRQ_COUNT_##idx] = { .symbol = sym, .text = txt, .optional = 1} + + +static struct irq_stat_info irq_stat_info[IRQ_COUNT_MAX] __ro_after_init = { + ISE(LOC_TIMER, "LOC", " Local timer interrupts for timer event device\n"), + ISE(BCT_TIMER, "BCT", " Broadcast timer interrupts for timer event device\n"), + ISE(OTHER_TIMER, "LOC", " Local timer interrupts for others\n"), + ISE(SPURIOUS, "SPU", " Spurious interrupts\n"), + ISE(PMI, "PMI", " Performance monitoring interrupts\n"), + ISC(MCE, "MCE", " Machine check exceptions\n"), + ISC(NMI_SRESET, "NMI", " System Reset interrupts\n"), +#ifdef CONFIG_PPC_WATCHDOG + ISE(WATCHDOG, "WDG", " Watchdog soft-NMI interrupts\n"), +#endif +#ifdef CONFIG_PPC_DOORBELL + ISE(DOORBELL, "DBL", " Doorbell interrupts\n"), +#endif +}; + +/* + * Used for default disabled counters to increment the stats and to enable the + * entry for /proc/interrupts output. + */ +static DECLARE_BITMAP(irq_stat_count_show, IRQ_COUNT_MAX) __read_mostly; +void inc_irq_stat_and_enable(enum irq_stat_counts which) +{ + __this_cpu_inc(irq_stat.counts[which]); + set_bit(which, irq_stat_count_show); +} + int arch_show_interrupts(struct seq_file *p, int prec) { - int j; + const struct irq_stat_info *info = irq_stat_info; + + for (unsigned int i = 0; i < ARRAY_SIZE(irq_stat_info); i++, info++) { + if (info->optional && !test_bit(i, irq_stat_count_show)) + continue; + + seq_printf(p, "%*s:", prec, info->symbol); + irq_proc_emit_counts(p, &irq_stat.counts[i]); + seq_puts(p, info->text); + } #if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT) if (tau_initialized) { + int j; seq_printf(p, "%*s:", prec, "TAU"); for_each_online_cpu(j) seq_put_decimal_ull_width(p, " ", tau_interrupts(j), 10); seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n"); } #endif /* CONFIG_PPC32 && CONFIG_TAU_INT */ - - seq_printf(p, "%*s:", prec, "LOC"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).timer_irqs_event, 10); - seq_printf(p, " Local timer interrupts for timer event device\n"); - - seq_printf(p, "%*s:", prec, "BCT"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).broadcast_irqs_event, 10); - seq_printf(p, " Broadcast timer interrupts for timer event device\n"); - - seq_printf(p, "%*s:", prec, "LOC"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).timer_irqs_others, 10); - seq_printf(p, " Local timer interrupts for others\n"); - - seq_printf(p, "%*s:", prec, "SPU"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).spurious_irqs, 10); - seq_printf(p, " Spurious interrupts\n"); - - seq_printf(p, "%*s:", prec, "PMI"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).pmu_irqs, 10); - seq_printf(p, " Performance monitoring interrupts\n"); - - seq_printf(p, "%*s:", prec, "MCE"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).mce_exceptions, 10); - seq_printf(p, " Machine check exceptions\n"); - #ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_HVMODE)) { + int j; seq_printf(p, "%*s:", prec, "HMI"); for_each_online_cpu(j) seq_put_decimal_ull_width(p, " ", paca_ptrs[j]->hmi_irqs, 10); seq_printf(p, " Hypervisor Maintenance Interrupts\n"); } #endif + return 0; +} - seq_printf(p, "%*s:", prec, "NMI"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).sreset_irqs, 10); - seq_printf(p, " System Reset interrupts\n"); - -#ifdef CONFIG_PPC_WATCHDOG - seq_printf(p, "%*s:", prec, "WDG"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).soft_nmi_irqs, 10); - seq_printf(p, " Watchdog soft-NMI interrupts\n"); -#endif +static int __init irq_init_stats(void) +{ + struct irq_stat_info *info = irq_stat_info; -#ifdef CONFIG_PPC_DOORBELL - if (cpu_has_feature(CPU_FTR_DBELL)) { - seq_printf(p, "%*s:", prec, "DBL"); - for_each_online_cpu(j) - seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).doorbell_irqs, 10); - seq_printf(p, " Doorbell interrupts\n"); + for (unsigned int i = 0; i < ARRAY_SIZE(irq_stat_info); i++, info++) { + if (info->optional == 0) + set_bit(i, irq_stat_count_show); } -#endif return 0; } +late_initcall(irq_init_stats); /* * /proc/stat helpers */ u64 arch_irq_stat_cpu(unsigned int cpu) { - u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event; + irq_cpustat_t *p = per_cpu_ptr(&irq_stat, cpu); + u64 sum = 0; + + for (unsigned int i = 0; i < ARRAY_SIZE(irq_stat_info); i++) + sum += p->counts[i]; - sum += per_cpu(irq_stat, cpu).broadcast_irqs_event; - sum += per_cpu(irq_stat, cpu).pmu_irqs; - sum += per_cpu(irq_stat, cpu).mce_exceptions; - sum += per_cpu(irq_stat, cpu).spurious_irqs; - sum += per_cpu(irq_stat, cpu).timer_irqs_others; #ifdef CONFIG_PPC_BOOK3S_64 sum += paca_ptrs[cpu]->hmi_irqs; #endif - sum += per_cpu(irq_stat, cpu).sreset_irqs; -#ifdef CONFIG_PPC_WATCHDOG - sum += per_cpu(irq_stat, cpu).soft_nmi_irqs; -#endif -#ifdef CONFIG_PPC_DOORBELL - sum += per_cpu(irq_stat, cpu).doorbell_irqs; -#endif - return sum; } @@ -251,7 +252,7 @@ static void __do_irq(struct pt_regs *regs, unsigned long oldsp) /* And finally process it */ if (unlikely(!irq)) - __this_cpu_inc(irq_stat.spurious_irqs); + inc_irq_stat(SPURIOUS); else generic_handle_irq(irq); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index eb9f556b0937..e8e071024da5 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1362,14 +1362,8 @@ static void __init prom_check_platform_support(void) int prop_len = prom_getproplen(prom.chosen, "ibm,arch-vec-5-platform-support"); - /* - * First copy the architecture vec template - * - * use memcpy() instead of *vec = *vec_template so that GCC replaces it - * by __memcpy() when KASAN is active - */ - memcpy(&ibm_architecture_vec, &ibm_architecture_vec_template, - sizeof(ibm_architecture_vec)); + /* First copy the architecture vec template */ + ibm_architecture_vec = ibm_architecture_vec_template; prom_strscpy_pad(ibm_architecture_vec.vec7.os_id, linux_banner, 256); diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 3090b97258ae..3155cc722e48 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -13,21 +13,8 @@ # If you really need to reference something from prom_init.o add # it to the list below: -has_renamed_memintrinsics() -{ - grep -q "^CONFIG_KASAN=y$" "${KCONFIG_CONFIG}" && \ - ! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" "${KCONFIG_CONFIG}" -} - -if has_renamed_memintrinsics -then - MEM_FUNCS="__memcpy __memset" -else - MEM_FUNCS="memcpy memset" -fi - WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush -_end enter_prom $MEM_FUNCS reloc_offset __secondary_hold +_end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start logo_linux_clut224 btext_prepare_BAT reloc_got2 kernstart_addr memstart_addr linux_banner _stext diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index fbefe1927b10..8529827d697f 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -18,14 +18,12 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) long ret; syscall_fn f; - if (unlikely(!syscall_enter_from_user_mode_randomize_stack(regs, &r0))) { + if (unlikely(!syscall_enter_from_user_mode_randomize_stack(regs, &r0) || + test_thread_flag(TIF_SYSCALL_RET))) { clear_thread_flag(TIF_SYSCALL_RET); return syscall_get_error(current, regs); } - if (unlikely(test_and_clear_thread_flag(TIF_SYSCALL_RET))) - return syscall_get_error(current, regs); - if (unlikely(r0 >= NR_syscalls)) { if (unlikely(trap_is_unsupported_scv(regs))) { /* Unsupported scv vector */ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 329c1690b5ed..2100c5e2c821 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -338,7 +338,7 @@ static ssize_t show_pw20_wait_time(struct device *dev, time = pw20_wt; } - return sysfs_emit(buf, "%llu\n", time > 0 ? time : 0); + return sysfs_emit(buf, "%llu\n", time); } static void set_pw20_wait_entry_bit(void *val) @@ -460,7 +460,7 @@ static ssize_t show_altivec_idle_wait_time(struct device *dev, time = altivec_idle_wt; } - return sysfs_emit(buf, "%llu\n", time > 0 ? time : 0); + return sysfs_emit(buf, "%llu\n", time); } static void set_altivec_idle_wait_entry_bit(void *val) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 11145c40183d..e00dcda8240b 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -615,13 +615,13 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) now = get_tb(); if (now >= *next_tb) { evt->event_handler(evt); - __this_cpu_inc(irq_stat.timer_irqs_event); + inc_irq_stat(LOC_TIMER); } else { now = *next_tb - now; if (now > decrementer_max) now = decrementer_max; set_dec_or_work(now); - __this_cpu_inc(irq_stat.timer_irqs_others); + inc_irq_stat(OTHER_TIMER); } trace_timer_interrupt_exit(regs); @@ -634,7 +634,7 @@ EXPORT_SYMBOL(timer_interrupt); void timer_broadcast_interrupt(void) { tick_receive_broadcast(); - __this_cpu_inc(irq_stat.broadcast_irqs_event); + inc_irq_stat(BCT_TIMER); } #endif diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S index 6599fe3c6234..5eb8eee32549 100644 --- a/arch/powerpc/kernel/trace/ftrace_entry.S +++ b/arch/powerpc/kernel/trace/ftrace_entry.S @@ -220,7 +220,13 @@ /* Restore gprs */ .if \allregs == 1 +#ifdef CONFIG_PPC64 + REST_GPRS(2, 12, r1) + /* Do not restore a stale PACA pointer if the task migrated */ + REST_GPRS(14, 31, r1) +#else REST_GPRS(2, 31, r1) +#endif .else REST_GPRS(3, 10, r1) #if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 629f2a2d4780..3a8f5416e3f6 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -459,8 +459,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception) } hv_nmi_check_nonrecoverable(regs); - - __this_cpu_inc(irq_stat.sreset_irqs); + inc_irq_stat_and_enable(IRQ_COUNT_NMI_SRESET); /* See if any machine dependent calls */ if (ppc_md.system_reset_exception) { @@ -817,7 +816,7 @@ static void __machine_check_exception(struct pt_regs *regs) { int recover = 0; - __this_cpu_inc(irq_stat.mce_exceptions); + inc_irq_stat_and_enable(IRQ_COUNT_MCE); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); @@ -1932,8 +1931,7 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm) DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi); DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi) { - __this_cpu_inc(irq_stat.pmu_irqs); - + inc_irq_stat(PMI); perf_irq(regs); return 0; @@ -1943,8 +1941,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi) DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async); DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async) { - __this_cpu_inc(irq_stat.pmu_irqs); - + inc_irq_stat(PMI); perf_irq(regs); } diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index c40c69368476..582ee3fd71c1 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -381,7 +381,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) return 0; - __this_cpu_inc(irq_stat.soft_nmi_irqs); + inc_irq_stat(WATCHDOG); tb = get_tb(); if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index de05d721edc4..140eadb76dfe 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1159,6 +1159,38 @@ static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu, return H_SUCCESS; } +static long kvmppc_pseries_do_hpt_hcall(struct kvm_vcpu *vcpu, unsigned long req) +{ + switch (req) { + case H_REMOVE: + return kvmppc_h_remove(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + case H_ENTER: + return kvmppc_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7)); + case H_READ: + return kvmppc_h_read(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + case H_CLEAR_MOD: + return kvmppc_h_clear_mod(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + case H_CLEAR_REF: + return kvmppc_h_clear_ref(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + case H_PROTECT: + return kvmppc_h_protect(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + case H_BULK_REMOVE: + return kvmppc_h_bulk_remove(vcpu); + } + + return H_FUNCTION; +} + int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; @@ -1174,47 +1206,17 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) switch (req) { case H_REMOVE: - ret = kvmppc_h_remove(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); - if (ret == H_TOO_HARD) - return RESUME_HOST; - break; case H_ENTER: - ret = kvmppc_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6), - kvmppc_get_gpr(vcpu, 7)); - if (ret == H_TOO_HARD) - return RESUME_HOST; - break; case H_READ: - ret = kvmppc_h_read(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5)); - if (ret == H_TOO_HARD) - return RESUME_HOST; - break; case H_CLEAR_MOD: - ret = kvmppc_h_clear_mod(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5)); - if (ret == H_TOO_HARD) - return RESUME_HOST; - break; case H_CLEAR_REF: - ret = kvmppc_h_clear_ref(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5)); - if (ret == H_TOO_HARD) - return RESUME_HOST; - break; case H_PROTECT: - ret = kvmppc_h_protect(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); - if (ret == H_TOO_HARD) - return RESUME_HOST; - break; case H_BULK_REMOVE: - ret = kvmppc_h_bulk_remove(vcpu); + preempt_disable(); + idx = srcu_read_lock(&kvm->srcu); + ret = kvmppc_pseries_do_hpt_hcall(vcpu, req); + srcu_read_unlock(&kvm->srcu, idx); + preempt_enable(); if (ret == H_TOO_HARD) return RESUME_HOST; break; @@ -1834,8 +1836,10 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, else vsid = vcpu->arch.fault_gpa; + preempt_disable(); err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar, vsid, vcpu->arch.fault_dsisr, true); + preempt_enable(); if (err == 0) { r = RESUME_GUEST; } else if (err == -1 || err == -2) { @@ -1881,8 +1885,10 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, else vsid = vcpu->arch.fault_gpa; + preempt_disable(); err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar, vsid, vcpu->arch.fault_dsisr, false); + preempt_enable(); if (err == 0) { r = RESUME_GUEST; } else if (err == -1) { diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c index bc39c76c9d9f..532f96293de0 100644 --- a/arch/powerpc/kvm/book3s_paired_singles.c +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -479,12 +479,7 @@ static bool kvmppc_inst_is_paired_single(struct kvm_vcpu *vcpu, u32 inst) static int get_d_signext(u32 inst) { - int d = inst & 0x8ff; - - if (d & 0x800) - return -(d & 0x7ff); - - return (d & 0x7ff); + return sign_extend32(inst & 0xfff, 11); } static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc, diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 1d67237783b7..d348365df72d 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -961,9 +961,11 @@ static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio) */ rc = xive_native_configure_queue(xc->vp_id, q, prio, qpage, xive->q_order, true); - if (rc) + if (rc) { pr_err("Failed to configure queue %d for VCPU %d\n", prio, xc->server_num); + free_pages((unsigned long)qpage, xive->q_page_order); + } return rc; } diff --git a/arch/powerpc/kvm/guest-state-buffer.c b/arch/powerpc/kvm/guest-state-buffer.c index 42843eca6727..aeb586ba4523 100644 --- a/arch/powerpc/kvm/guest-state-buffer.c +++ b/arch/powerpc/kvm/guest-state-buffer.c @@ -598,7 +598,7 @@ EXPORT_SYMBOL_GPL(kvmppc_gsm_fill_info); int kvmppc_gsm_refresh_info(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_buff *gsb) { - if (!gsm->ops->fill_info) + if (!gsm->ops->refresh_info) return -EINVAL; return gsm->ops->refresh_info(gsm, gsb); diff --git a/arch/powerpc/kvm/trace_book3s.h b/arch/powerpc/kvm/trace_book3s.h index 9260ddbd557f..4ee35c6d01aa 100644 --- a/arch/powerpc/kvm/trace_book3s.h +++ b/arch/powerpc/kvm/trace_book3s.h @@ -7,6 +7,7 @@ */ #define kvm_trace_symbol_exit \ + {0x0, "RETURN_TO_HOST"}, \ {0x100, "SYSTEM_RESET"}, \ {0x200, "MACHINE_CHECK"}, \ {0x300, "DATA_STORAGE"}, \ @@ -28,6 +29,7 @@ {0xea0, "H_VIRT"}, \ {0xf00, "PERFMON"}, \ {0xf20, "ALTIVEC"}, \ - {0xf40, "VSX"} + {0xf40, "VSX"}, \ + {0xf80, "H_FAC_UNAVAIL"} #endif diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index 933b685e7ab6..97eb9ca0cc23 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -10,7 +10,6 @@ #include <asm/errno.h> #include <asm/ppc_asm.h> #include <asm/code-patching-asm.h> -#include <asm/kasan.h> #define COPY_16_BYTES \ lwz r7,4(r4); \ @@ -87,7 +86,7 @@ EXPORT_SYMBOL(memset16) * We therefore skip the optimised bloc that uses dcbz. This jump is * replaced by a nop once cache is active. This is done in machine_init() */ -_GLOBAL_KASAN(memset) +_GLOBAL(memset) cmplwi 0,r5,4 blt 7f @@ -147,7 +146,6 @@ _GLOBAL_KASAN(memset) bdnz 9b blr EXPORT_SYMBOL(memset) -EXPORT_SYMBOL_KASAN(memset) /* * This version uses dcbz on the complete cache lines in the @@ -160,12 +158,12 @@ EXPORT_SYMBOL_KASAN(memset) * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is * replaced by a nop once cache is active. This is done in machine_init() */ -_GLOBAL_KASAN(memmove) +_GLOBAL(memmove) cmplw 0,r3,r4 bgt backwards_memcpy /* fall through */ -_GLOBAL_KASAN(memcpy) +_GLOBAL(memcpy) 1: b generic_memcpy patch_site 1b, patch__memcpy_nocache @@ -241,8 +239,6 @@ _GLOBAL_KASAN(memcpy) 65: blr EXPORT_SYMBOL(memcpy) EXPORT_SYMBOL(memmove) -EXPORT_SYMBOL_KASAN(memcpy) -EXPORT_SYMBOL_KASAN(memmove) generic_memcpy: srwi. r7,r5,3 diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S index 6fd06cd20faa..40eaedd31486 100644 --- a/arch/powerpc/lib/mem_64.S +++ b/arch/powerpc/lib/mem_64.S @@ -8,7 +8,6 @@ #include <asm/processor.h> #include <asm/errno.h> #include <asm/ppc_asm.h> -#include <asm/kasan.h> #ifndef CONFIG_KASAN _GLOBAL(__memset16) @@ -29,7 +28,7 @@ EXPORT_SYMBOL(__memset32) EXPORT_SYMBOL(__memset64) #endif -_GLOBAL_KASAN(memset) +_GLOBAL(memset) neg r0,r3 rlwimi r4,r4,8,16,23 andi. r0,r0,7 /* # bytes to be 8-byte aligned */ @@ -95,9 +94,8 @@ _GLOBAL_KASAN(memset) stb r4,0(r6) blr EXPORT_SYMBOL(memset) -EXPORT_SYMBOL_KASAN(memset) -_GLOBAL_TOC_KASAN(memmove) +_GLOBAL_TOC(memmove) cmplw 0,r3,r4 bgt backwards_memcpy b memcpy @@ -139,4 +137,3 @@ _GLOBAL(backwards_memcpy) mtctr r7 b 1b EXPORT_SYMBOL(memmove) -EXPORT_SYMBOL_KASAN(memmove) diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index b5a67e20143f..0cedd455231a 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -7,7 +7,6 @@ #include <asm/ppc_asm.h> #include <asm/asm-compat.h> #include <asm/feature-fixups.h> -#include <asm/kasan.h> #ifndef SELFTEST_CASE /* For big-endian, 0 == most CPUs, 1 == POWER6, 2 == Cell */ @@ -15,7 +14,7 @@ #endif .align 7 -_GLOBAL_TOC_KASAN(memcpy) +_GLOBAL_TOC(memcpy) BEGIN_FTR_SECTION #ifdef __LITTLE_ENDIAN__ cmpdi cr7,r5,0 @@ -227,4 +226,3 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) blr #endif EXPORT_SYMBOL(memcpy) -EXPORT_SYMBOL_KASAN(memcpy) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index f0d6aa657c1a..d49b2ef5d763 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -47,7 +47,7 @@ extern void conv_sp_to_dp(const float *sp, double *dp); extern void conv_dp_to_sp(const double *dp, float *sp); #endif -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 /* * Functions in quad.S */ @@ -134,7 +134,7 @@ static nokprobe_inline unsigned long dform_ea(unsigned int instr, return ea; } -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 /* * Calculate effective address for a DS-form instruction */ @@ -168,7 +168,7 @@ static nokprobe_inline unsigned long dqform_ea(unsigned int instr, return ea; } -#endif /* __powerpc64 */ +#endif /* CONFIG_PPC64 */ /* * Calculate effective address for an X-form instruction @@ -250,7 +250,7 @@ static nokprobe_inline unsigned long byterev_4(unsigned long x) ((x & 0xff00) << 8) | ((x & 0xff) << 24); } -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 static nokprobe_inline unsigned long byterev_8(unsigned long x) { return (byterev_4(x) << 32) | byterev_4(x >> 32); @@ -266,7 +266,7 @@ static nokprobe_inline void do_byte_reverse(void *ptr, int nb) case 4: *(u32 *)ptr = byterev_4(*(u32 *)ptr); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: *(unsigned long *)ptr = byterev_8(*(unsigned long *)ptr); break; @@ -312,7 +312,7 @@ __read_mem_aligned(unsigned long *dest, unsigned long ea, int nb, struct pt_regs case 4: unsafe_get_user(x, (unsigned int __user *)ea, Efault); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: unsafe_get_user(x, (unsigned long __user *)ea, Efault); break; @@ -364,7 +364,7 @@ static __always_inline int __copy_mem_in(u8 *dest, unsigned long ea, int nb, str case 4: unsafe_get_user(*(u32 *)dest, (u32 __user *)ea, Efault); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: unsafe_get_user(*(u64 *)dest, (u64 __user *)ea, Efault); break; @@ -443,7 +443,7 @@ __write_mem_aligned(unsigned long val, unsigned long ea, int nb, struct pt_regs case 4: unsafe_put_user(val, (unsigned int __user *)ea, Efault); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: unsafe_put_user(val, (unsigned long __user *)ea, Efault); break; @@ -494,7 +494,7 @@ static __always_inline int __copy_mem_out(u8 *dest, unsigned long ea, int nb, st case 4: unsafe_put_user(*(u32 *)dest, (u32 __user *)ea, Efault); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: unsafe_put_user(*(u64 *)dest, (u64 __user *)ea, Efault); break; @@ -722,7 +722,7 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea, } #endif /* CONFIG_ALTIVEC */ -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 static nokprobe_inline int emulate_lq(struct pt_regs *regs, unsigned long ea, int reg, bool cross_endian) { @@ -765,7 +765,7 @@ static nokprobe_inline int emulate_stq(struct pt_regs *regs, unsigned long ea, err = write_mem(vals[IS_BE], ea + 8, 8, regs); return err; } -#endif /* __powerpc64 */ +#endif /* CONFIG_PPC64 */ #ifdef CONFIG_VSX static nokprobe_inline void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg, @@ -1316,7 +1316,7 @@ static nokprobe_inline int trap_compare(long v1, long v2) */ #define MASK32(mb, me) ((0xffffffffUL >> (mb)) + \ ((signed long)-0x80000000L >> (me)) + ((me) >= (mb))) -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 #define MASK64_L(mb) (~0UL >> (mb)) #define MASK64_R(me) ((signed long)-0x8000000000000000L >> (me)) #define MASK64(mb, me) (MASK64_L(mb) + MASK64_R(me) + ((me) >= (mb))) @@ -1342,16 +1342,19 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, { #ifdef CONFIG_PPC64 unsigned int suffixopcode, prefixtype, prefix_r; + unsigned int rc, suffix; #endif - unsigned int opcode, ra, rb, rc, rd, spr, u; + unsigned int opcode, ra, rb, rd, spr, u; unsigned long int imm; unsigned long int val, val2; unsigned int mb, me, sh; - unsigned int word, suffix; + unsigned int word; long ival; word = ppc_inst_val(instr); +#ifdef CONFIG_PPC64 suffix = ppc_inst_suffix(instr); +#endif op->type = COMPUTE; @@ -1447,7 +1450,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, switch ((word >> 1) & 0x3ff) { case 598: /* sync */ op->type = BARRIER + BARRIER_SYNC; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 switch ((word >> 21) & 3) { case 1: /* lwsync */ op->type = BARRIER + BARRIER_LWSYNC; @@ -1469,10 +1472,12 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, rd = (word >> 21) & 0x1f; ra = (word >> 16) & 0x1f; rb = (word >> 11) & 0x1f; +#ifdef CONFIG_PPC64 rc = (word >> 6) & 0x1f; +#endif switch (opcode) { -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 1: if (!cpu_has_feature(CPU_FTR_ARCH_31)) goto unknown_opcode; @@ -1506,7 +1511,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, goto trap; return 1; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 4: /* * There are very many instructions with this primary opcode @@ -1555,7 +1560,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 10: /* cmpli */ imm = (unsigned short) word; val = regs->gpr[ra]; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 if ((rd & 1) == 0) val = (unsigned int) val; #endif @@ -1565,7 +1570,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 11: /* cmpi */ imm = (short) word; val = regs->gpr[ra]; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 if ((rd & 1) == 0) val = (int) val; #endif @@ -1662,7 +1667,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, set_cr0(regs, op); goto logical_done_nocc; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 30: /* rld* */ mb = ((word >> 6) & 0x1f) | (word & 0x20); val = regs->gpr[rd]; @@ -1720,7 +1725,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, (int)regs->gpr[rb]))) goto trap; return 1; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 68: /* td */ if (rd & trap_compare(regs->gpr[ra], regs->gpr[rb])) goto trap; @@ -1826,7 +1831,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 0: /* cmp */ val = regs->gpr[ra]; val2 = regs->gpr[rb]; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 if ((rd & 1) == 0) { /* word (32-bit) compare */ val = (int) val; @@ -1839,7 +1844,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 32: /* cmpl */ val = regs->gpr[ra]; val2 = regs->gpr[rb]; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 if ((rd & 1) == 0) { /* word (32-bit) compare */ val = (unsigned int) val; @@ -1860,7 +1865,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, add_with_carry(regs, op, rd, ~regs->gpr[ra], regs->gpr[rb], 1); goto arith_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 9: /* mulhdu */ asm("mulhdu %0,%1,%2" : "=r" (op->val) : "r" (regs->gpr[ra]), "r" (regs->gpr[rb])); @@ -1879,7 +1884,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 40: /* subf */ op->val = regs->gpr[rb] - regs->gpr[ra]; goto arith_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 73: /* mulhd */ asm("mulhd %0,%1,%2" : "=r" (op->val) : "r" (regs->gpr[ra]), "r" (regs->gpr[rb])); @@ -1918,7 +1923,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, add_with_carry(regs, op, rd, ~regs->gpr[ra], -1L, regs->xer & XER_CA); goto arith_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 233: /* mulld */ op->val = regs->gpr[ra] * regs->gpr[rb]; goto arith_done; @@ -1933,7 +1938,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, (int) regs->gpr[rb]; goto arith_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 265: /* modud */ if (!cpu_has_feature(CPU_FTR_ARCH_300)) goto unknown_opcode; @@ -1950,7 +1955,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->val = (unsigned int) regs->gpr[ra] % (unsigned int) regs->gpr[rb]; goto compute_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 457: /* divdu */ op->val = regs->gpr[ra] / regs->gpr[rb]; goto arith_done; @@ -1959,7 +1964,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->val = (unsigned int) regs->gpr[ra] / (unsigned int) regs->gpr[rb]; goto arith_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 489: /* divd */ op->val = (long int) regs->gpr[ra] / (long int) regs->gpr[rb]; @@ -1969,7 +1974,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->val = (int) regs->gpr[ra] / (int) regs->gpr[rb]; goto arith_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 425: /* divde[.] */ asm volatile(PPC_DIVDE(%0, %1, %2) : "=r" (op->val) : "r" (regs->gpr[ra]), @@ -2002,7 +2007,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, } goto unknown_opcode; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 777: /* modsd */ if (!cpu_has_feature(CPU_FTR_ARCH_300)) goto unknown_opcode; @@ -2025,7 +2030,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, val = (unsigned int) regs->gpr[rd]; op->val = ( val ? __builtin_clz(val) : 32 ); goto logical_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 58: /* cntlzd */ val = regs->gpr[rd]; op->val = ( val ? __builtin_clzl(val) : 64 ); @@ -2093,7 +2098,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, val = (unsigned int) regs->gpr[rd]; op->val = (val ? __builtin_ctz(val) : 32); goto logical_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 570: /* cnttzd */ if (!cpu_has_feature(CPU_FTR_ARCH_300)) goto unknown_opcode; @@ -2108,7 +2113,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 954: /* extsb */ op->val = (signed char) regs->gpr[rd]; goto logical_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 986: /* extsw */ op->val = (signed int) regs->gpr[rd]; goto logical_done; @@ -2159,7 +2164,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, set_ca32(op, op->xerval & XER_CA); goto logical_done; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 27: /* sld */ sh = regs->gpr[rb] & 0x7f; if (sh < 64) @@ -2216,7 +2221,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->val = val; goto logical_done; -#endif /* __powerpc64__ */ +#endif /* CONFIG_PPC64 */ /* * Cache instructions @@ -2296,7 +2301,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->type = MKOP(STCX, 0, 2); break; #endif -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 84: /* ldarx */ op->type = MKOP(LARX, 0, 8); break; @@ -2373,7 +2378,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, break; #endif /* CONFIG_ALTIVEC */ -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 21: /* ldx */ case 53: /* ldux */ op->type = MKOP(LOAD, u, 8); @@ -2400,7 +2405,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->type = MKOP(LOAD, u, 2); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 341: /* lwax */ case 373: /* lwaux */ op->type = MKOP(LOAD, SIGNEXT | u, 4); @@ -2417,7 +2422,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->type = MKOP(STORE, u, 2); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 532: /* ldbrx */ op->type = MKOP(LOAD, BYTEREV, 8); break; @@ -2459,7 +2464,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->type = MKOP(STORE_FP, u, 8); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 791: /* lfdpx */ op->type = MKOP(LOAD_FP, 0, 16); break; @@ -2479,10 +2484,10 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 983: /* stfiwx */ op->type = MKOP(STORE_FP, 0, 4); break; -#endif /* __powerpc64 */ +#endif /* CONFIG_PPC64 */ #endif /* CONFIG_PPC_FPU */ -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 660: /* stdbrx */ op->type = MKOP(STORE, BYTEREV, 8); op->val = byterev_8(regs->gpr[rd]); @@ -2820,7 +2825,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, break; #endif -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 56: /* lq */ if (!((rd & 1) || (rd == ra))) op->type = MKOP(LOAD, 0, 16); @@ -2857,7 +2862,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, break; #endif /* CONFIG_VSX */ -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 58: /* ld[u], lwa */ op->ea = dsform_ea(word, regs); switch (word & 3) { @@ -2946,7 +2951,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, break; #endif /* CONFIG_VSX */ -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 62: /* std[u] */ op->ea = dsform_ea(word, regs); switch (word & 3) { @@ -3099,7 +3104,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 3: /* Type 11 Modified Register-to-Register */ break; } -#endif /* __powerpc64__ */ +#endif /* CONFIG_PPC64 */ } @@ -3200,7 +3205,7 @@ static nokprobe_inline void do_byterev(unsigned long *valp, int size) case 4: *valp = byterev_4(*valp); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: *valp = byterev_8(*valp); break; @@ -3341,7 +3346,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) case 4: __get_user_asmx(val, ea, err, "lwarx"); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: __get_user_asmx(val, ea, err, "ldarx"); break; @@ -3367,7 +3372,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) return -EFAULT; err = 0; switch (size) { -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 1: __put_user_asmx(op->val, ea, err, "stbcx.", cr); break; @@ -3378,7 +3383,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) case 4: __put_user_asmx(op->val, ea, err, "stwcx.", cr); break; -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 case 8: __put_user_asmx(op->val, ea, err, "stdcx.", cr); break; @@ -3399,7 +3404,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) break; case LOAD: -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 if (size == 16) { err = emulate_lq(regs, ea, op->reg, cross_endian); break; @@ -3473,7 +3478,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) break; case STORE: -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64 if (size == 16) { err = emulate_stq(regs, ea, op->reg, cross_endian); break; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index f4cf3ae036de..e97b624203ea 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -432,7 +432,7 @@ static void __init initialize_form2_numa_distance_lookup_table(void) static int __init find_primary_domain_index(void) { - int index; + int index = -1; struct device_node *root; /* @@ -502,12 +502,9 @@ static int __init find_primary_domain_index(void) distance_ref_points_depth = MAX_DISTANCE_REF_POINTS; } - of_node_put(root); - return index; - err: of_node_put(root); - return -1; + return index; } static void __init get_n_mem_cells(int *n_addr_cells, int *n_size_cells) @@ -892,12 +889,32 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, return 0; } +/* + * If hierarchy extends beyond primary_domain_index + 1, then next + * level corresponds to coregroup. + */ +static int detect_and_enable_coregroup(const __be32 *associativity, int index) +{ + if (!associativity || index == -1) + goto out; + + index = of_read_number(associativity, 1); + + if (index > primary_domain_index + 1) { + coregroup_enabled = 1; + return index; + } +out: + coregroup_enabled = 0; + return -1; +} + static int __init parse_numa_properties(void) { struct device_node *memory, *pci; - int default_nid = 0; - unsigned long i; + int default_nid = 0, index = 0; const __be32 *associativity; + unsigned long i; if (numa_enabled == 0) { pr_warn("disabled by user\n"); @@ -930,7 +947,6 @@ static int __init parse_numa_properties(void) */ for_each_present_cpu(i) { __be32 vphn_assoc[VPHN_ASSOC_BUFSIZE]; - struct device_node *cpu; int nid = NUMA_NO_NODE; memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32)); @@ -938,7 +954,9 @@ static int __init parse_numa_properties(void) if (__vphn_get_associativity(i, vphn_assoc) == 0) { nid = associativity_to_nid(vphn_assoc); initialize_form1_numa_distance(vphn_assoc); + index = detect_and_enable_coregroup(vphn_assoc, index); } else { + struct device_node *cpu; /* * Don't fall back to default_nid yet -- we will plug @@ -951,6 +969,7 @@ static int __init parse_numa_properties(void) associativity = of_get_associativity(cpu); if (associativity) { nid = associativity_to_nid(associativity); + index = detect_and_enable_coregroup(associativity, index); initialize_form1_numa_distance(associativity); } of_node_put(cpu); @@ -1431,9 +1450,26 @@ void find_and_update_cpu_nid(int cpu) pr_debug("%s:%d cpu %d nid %d\n", __func__, __LINE__, cpu, new_nid); } +static int topology_update_init(void) +{ + topology_inited = 1; + return 0; +} +device_initcall(topology_update_init); + +#else +static long vphn_get_associativity(unsigned long cpu, + __be32 *associativity) +{ + return -1; +} +#endif /* CONFIG_PPC_SPLPAR */ + int cpu_to_coregroup_id(int cpu) { - __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; + int coregroup_id = cpu_to_core_id(cpu); + struct device_node *cpunode = NULL; + const __be32 *associativity; int index; if (cpu < 0 || cpu > nr_cpu_ids) @@ -1442,24 +1478,31 @@ int cpu_to_coregroup_id(int cpu) if (!coregroup_enabled) goto out; - if (!firmware_has_feature(FW_FEATURE_VPHN)) - goto out; + if (firmware_has_feature(FW_FEATURE_VPHN)) { + __be32 tmp[VPHN_ASSOC_BUFSIZE] = {0}; - if (vphn_get_associativity(cpu, associativity)) + if (vphn_get_associativity(cpu, tmp)) + goto out; + + associativity = tmp; + + } else { + cpunode = of_get_cpu_node(cpu, NULL); + if (!cpunode) + goto out; + + associativity = of_get_associativity(cpunode); + } + if (!associativity) goto out; index = of_read_number(associativity, 1); if (index > primary_domain_index + 1) - return of_read_number(&associativity[index - 1], 1); + coregroup_id = of_read_number(&associativity[index - 1], 1); out: - return cpu_to_core_id(cpu); -} + if (cpunode) + of_node_put(cpunode); -static int topology_update_init(void) -{ - topology_inited = 1; - return 0; + return coregroup_id; } -device_initcall(topology_update_init); -#endif /* CONFIG_PPC_SPLPAR */ diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index f32de8704d4d..4da8bde92e1e 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -14,6 +14,13 @@ #include <asm/ppc-opcode.h> #include <linux/build_bug.h> +/* + * We need at least 2 passes for proper code generation, and may need + * additional passes if code size changes between passes. + */ +#define CODEGEN_MIN_PASSES 2 +#define CODEGEN_MAX_PASSES 3 + #ifdef CONFIG_PPC64_ELF_ABI_V1 #define FUNCTION_DESCR_SIZE 24 #else @@ -188,6 +195,12 @@ struct codegen_context { #define bpf_to_ppc(r) (ctx->b2p[r]) +#ifdef CONFIG_PPC64 +#define PPC_RAW_CMPLLI(a, i) PPC_RAW_CMPLDI(a, i) +#else +#define PPC_RAW_CMPLLI(a, i) PPC_RAW_CMPLWI(a, i) +#endif + #ifdef CONFIG_PPC32 #define BPF_FIXUP_LEN 3 /* Three instructions => 12 bytes */ #else @@ -214,10 +227,11 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context * int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx, u32 *addrs, int pass, bool extra_pass); void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx); -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx); -void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx); +void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx); +void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx); void bpf_jit_realloc_regs(struct codegen_context *ctx); -int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr); +int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx, int tmp_reg, + long exit_addr); void prepare_for_fsession_fentry(u32 *image, struct codegen_context *ctx, int cookie_cnt, int cookie_off, int retval_off); void store_func_meta(u32 *image, struct codegen_context *ctx, u64 func_meta, int func_meta_off); diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 7a612688e7a2..cfe01c3544db 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -49,11 +49,35 @@ asm ( " .popsection ;" ); -void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx) +void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx) { int ool_stub_idx, long_branch_stub_idx; + int stub_sz; /* + * The dummy_tramp_addr field is placed at bottom of Long branch stub. + * Align the mis-aligned dummy_tramp_addr field in the fimage. + * The alignment NOP must appear before OOL stub, to make + * ool_stub_idx & long_branch_stub_idx constant from end. + * + * The fimage can be non 8-byte aligned, so final alignment depends + * on start of fimage and the stub's instruction count. The + * stubs block has 11 instructions (with CONFIG_PPC_FTRACE_OUT_OF_LINE) + * or 10 instructions (without) before dummy_tramp_addr field. Emit a + * NOP if the address of dummy_tramp_addr is non aligned. + * + * In pass=0 when image==NULL, conservatively account for space + * required to accommodate alignment NOP. In case final pass skips + * emitting alignment NOP, the image buffer have 4 spare bytes and + * jited_len signifies correct program size. + */ + + stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 44 : 40; + if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + stub_sz, SZL)) + EMIT(PPC_RAW_NOP()); + + /* + * nop // optional, for alignment of dummy_tramp_addr * Out-of-line stub: * mflr r0 * [b|bl] tramp @@ -70,44 +94,46 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx) /* * Long branch stub: - * .long <dummy_tramp_addr> * mflr r11 * bcl 20,31,$+4 - * mflr r12 - * ld r12, -8-SZL(r12) + * mflr r12 // lr/r12 stores pc of current(this) inst. + * ld r12, 20(r12) // offset(dummy_tramp_addr) from prev inst. is 20 * mtctr r12 - * mtlr r11 // needed to retain ftrace ABI + * mtlr r11 // needed to retain ftrace ABI * bctr + * .long <dummy_tramp_addr> // SZL bytes aligned */ - if (image) - *((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp; - ctx->idx += SZL / 4; long_branch_stub_idx = ctx->idx; EMIT(PPC_RAW_MFLR(_R11)); EMIT(PPC_RAW_BCL4()); EMIT(PPC_RAW_MFLR(_R12)); - EMIT(PPC_RAW_LL(_R12, _R12, -8-SZL)); + EMIT(PPC_RAW_LL(_R12, _R12, 20)); EMIT(PPC_RAW_MTCTR(_R12)); EMIT(PPC_RAW_MTLR(_R11)); EMIT(PPC_RAW_BCTR()); + if (image) + *((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp; + + ctx->idx += SZL / 4; + if (!bpf_jit_ool_stub) { bpf_jit_ool_stub = (ctx->idx - ool_stub_idx) * 4; bpf_jit_long_branch_stub = (ctx->idx - long_branch_stub_idx) * 4; } } -int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr) +int bpf_jit_emit_exit_insn(u32 *image, u32 *fimage, struct codegen_context *ctx, + int tmp_reg, long exit_addr) { - if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) { + if (exit_addr && is_offset_in_branch_range(exit_addr - (long)(ctx->idx * 4))) { PPC_JMP(exit_addr); - } else if (ctx->alt_exit_addr) { - if (WARN_ON(!is_offset_in_branch_range((long)ctx->alt_exit_addr - (ctx->idx * 4)))) - return -1; + } else if (ctx->alt_exit_addr && is_offset_in_branch_range( + (long)(ctx->alt_exit_addr) - (long)(ctx->idx * 4))) { PPC_JMP(ctx->alt_exit_addr); } else { ctx->alt_exit_addr = ctx->idx * 4; - bpf_jit_build_epilogue(image, ctx); + bpf_jit_build_epilogue(image, fimage, ctx); } return 0; @@ -274,6 +300,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr */ if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) { cgctx.idx = 0; + cgctx.alt_exit_addr = 0; if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) goto out_err; } @@ -286,7 +313,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr */ bpf_jit_build_prologue(NULL, &cgctx); addrs[fp->len] = cgctx.idx * 4; - bpf_jit_build_epilogue(NULL, &cgctx); + bpf_jit_build_epilogue(NULL, NULL, &cgctx); fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4; extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry); @@ -306,10 +333,13 @@ skip_init_ctx: code_base = (u32 *)(image + FUNCTION_DESCR_SIZE); fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE); - /* Code generation passes 1-2 */ - for (pass = 1; pass < 3; pass++) { + /* Code generation passes 1-2+, loop until program size converges. */ + for (pass = 1; pass <= CODEGEN_MAX_PASSES; pass++) { + u32 prev_proglen = proglen; + /* Now build the prologue, body code & epilogue for real. */ cgctx.idx = 0; + cgctx.exentry_idx = 0; cgctx.alt_exit_addr = 0; bpf_jit_build_prologue(code_base, &cgctx); if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx, addrs, pass, @@ -318,11 +348,26 @@ skip_init_ctx: bpf_jit_binary_pack_free(fhdr, hdr); goto out_err; } - bpf_jit_build_epilogue(code_base, &cgctx); + addrs[fp->len] = cgctx.idx * 4; + bpf_jit_build_epilogue(code_base, fcode_base, &cgctx); + + proglen = cgctx.idx * 4; if (bpf_jit_enable > 1) pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass, - proglen - (cgctx.idx * 4), cgctx.seen); + prev_proglen - proglen, cgctx.seen); + + /* Check if program size has converged, but ensure minimum passes */ + if (pass >= CODEGEN_MIN_PASSES && proglen == prev_proglen) + break; + + if (pass == CODEGEN_MAX_PASSES && proglen != prev_proglen) { + pr_err("BPF JIT: Program did not converge after %d passes\n", + CODEGEN_MAX_PASSES); + bpf_arch_text_copy(&fhdr->size, &hdr->size, sizeof(hdr->size)); + bpf_jit_binary_pack_free(fhdr, hdr); + goto out_err; + } } if (bpf_jit_enable > 1) @@ -357,7 +402,7 @@ skip_init_ctx: (void *)fimage + FUNCTION_DESCR_SIZE); out_addrs: - if (!image && priv_stack_ptr) { + if (!fp->jited && priv_stack_ptr) { fp->aux->priv_stack_ptr = NULL; free_percpu(priv_stack_ptr); } @@ -399,7 +444,7 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass u32 *fixup; /* Populate extable entries only in the last pass */ - if (pass != 2) + if (pass < CODEGEN_MIN_PASSES) return 0; if (!fp->aux->extable || @@ -747,7 +792,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte * Setting the tail_call_info in trampoline's frame * depending on if previous frame had value or reference. */ - EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT)); + EMIT(PPC_RAW_CMPLLI(_R3, MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_GT, 8); EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL)); @@ -1266,6 +1311,7 @@ static void do_isync(void *info __maybe_unused) * bpf_func: * [nop|b] ool_stub * 2. Out-of-line stub: + * nop // optional nop for alignment * ool_stub: * mflr r0 * [b|bl] <bpf_prog>/<long_branch_stub> @@ -1273,14 +1319,14 @@ static void do_isync(void *info __maybe_unused) * b bpf_func + 4 * 3. Long branch stub: * long_branch_stub: - * .long <branch_addr>/<dummy_tramp> * mflr r11 * bcl 20,31,$+4 * mflr r12 - * ld r12, -16(r12) + * ld r12, 20(r12) * mtctr r12 * mtlr r11 // needed to retain ftrace ABI * bctr + * .long <branch_addr>/<dummy_tramp> * * dummy_tramp is used to reduce synchronization requirements. * @@ -1382,10 +1428,12 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, * 1. Update the address in the long branch stub: * If new_addr is out of range, we will have to use the long branch stub, so patch new_addr * here. Otherwise, revert to dummy_tramp, but only if we had patched old_addr here. + * + * dummy_tramp_addr moved to bottom of long branch stub. */ if ((new_addr && !is_offset_in_branch_range(new_addr - ip)) || (old_addr && !is_offset_in_branch_range(old_addr - ip))) - ret = patch_ulong((void *)(bpf_func_end - bpf_jit_long_branch_stub - SZL), + ret = patch_ulong((void *)(bpf_func_end - SZL), /* SZL: dummy_tramp_addr offset */ (new_addr && !is_offset_in_branch_range(new_addr - ip)) ? (unsigned long)new_addr : (unsigned long)dummy_tramp); if (ret) diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index bfdc50740da8..f5b9441cf46a 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -229,7 +229,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx } -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx) { EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); @@ -237,7 +237,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); - bpf_jit_build_fentry_stubs(image, ctx); + bpf_jit_build_fentry_stubs(image, fimage, ctx); } /* Relative offset needs to be calculated based on final image location */ @@ -1149,7 +1149,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * we'll just fall through to the epilogue. */ if (i != flen - 1) { - ret = bpf_jit_emit_exit_insn(image, ctx, _R0, exit_addr); + ret = bpf_jit_emit_exit_insn(image, fimage, + ctx, _R0, exit_addr); if (ret) return ret; } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index fc9db691e820..c1e86fe0bd79 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -276,7 +276,7 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) */ EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, 0)); EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), -(BPF_PPC_TAILCALL))); - EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_GT, 8); EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), -(BPF_PPC_TAILCALL))); @@ -398,7 +398,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx } } -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx) { bpf_jit_emit_common_epilogue(image, ctx); @@ -407,7 +407,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); - bpf_jit_build_fentry_stubs(image, ctx); + bpf_jit_build_fentry_stubs(image, fimage, ctx); } /* @@ -662,7 +662,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC_SHORT(COND_GE, out); EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallinfo_offset(ctx))); - EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_LE, 8); /* dereference TMP_REG_1 */ @@ -672,7 +672,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o * if (tail_call_info == MAX_TAIL_CALL_CNT) * goto out; */ - EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); PPC_BCC_SHORT(COND_EQ, out); /* @@ -707,7 +707,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o * tail_call_info. */ EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, bpf_jit_stack_tailcallinfo_offset(ctx))); - EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT)); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT)); PPC_BCC_CONST_SHORT(COND_GT, 8); /* First get address of tail_call_info */ @@ -1737,7 +1737,8 @@ emit_clear: * we'll just fall through to the epilogue. */ if (i != flen - 1) { - ret = bpf_jit_emit_exit_insn(image, ctx, tmp1_reg, exit_addr); + ret = bpf_jit_emit_exit_insn(image, fimage, ctx, + tmp1_reg, exit_addr); if (ret) return ret; } diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index deecede78776..9d46d791af05 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -32,11 +32,12 @@ config MPC512x_GENERIC which do not need custom platform specific setup. Compatible boards include: Protonic LVT base boards (ZANMCU - and VICVT2), Freescale MPC5125 Tower system. + and VICVT2), Freescale MPC5125 Tower system, IFM PDM360NG. config PDM360NG bool "ifm PDM360NG board" depends on PPC_MPC512x + select MPC512x_GENERIC select DEFAULT_UIMAGE help This option enables support for the PDM360NG board. diff --git a/arch/powerpc/platforms/512x/Makefile b/arch/powerpc/platforms/512x/Makefile index 2daf22ee26a0..4da6f6923d8f 100644 --- a/arch/powerpc/platforms/512x/Makefile +++ b/arch/powerpc/platforms/512x/Makefile @@ -7,4 +7,3 @@ obj-y += mpc512x_shared.o obj-$(CONFIG_MPC5121_ADS) += mpc5121_ads.o mpc5121_ads_cpld.o obj-$(CONFIG_MPC512x_GENERIC) += mpc512x_generic.o obj-$(CONFIG_MPC512x_LPBFIFO) += mpc512x_lpbfifo.o -obj-$(CONFIG_PDM360NG) += pdm360ng.o diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c index d4fa6c302ccf..d330d3d85887 100644 --- a/arch/powerpc/platforms/512x/mpc512x_generic.c +++ b/arch/powerpc/platforms/512x/mpc512x_generic.c @@ -24,6 +24,7 @@ static const char * const board[] __initconst = { "prt,prtlvt", "fsl,mpc5125ads", "ifm,ac14xx", + "ifm,pdm360ng", NULL }; diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c deleted file mode 100644 index 8bbbf78bb42b..000000000000 --- a/arch/powerpc/platforms/512x/pdm360ng.c +++ /dev/null @@ -1,126 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2010 DENX Software Engineering - * - * Anatolij Gustschin, <agust@denx.de> - * - * PDM360NG board setup - */ - -#include <linux/device.h> -#include <linux/kernel.h> -#include <linux/io.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_fdt.h> - -#include <asm/machdep.h> -#include <asm/ipic.h> - -#include "mpc512x.h" - -#if defined(CONFIG_TOUCHSCREEN_ADS7846) || \ - defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE) -#include <linux/interrupt.h> -#include <linux/spi/ads7846.h> -#include <linux/spi/spi.h> -#include <linux/notifier.h> - -static void *pdm360ng_gpio_base; - -static int pdm360ng_get_pendown_state(void) -{ - u32 reg; - - reg = in_be32(pdm360ng_gpio_base + 0xc); - if (reg & 0x40) - setbits32(pdm360ng_gpio_base + 0xc, 0x40); - - reg = in_be32(pdm360ng_gpio_base + 0x8); - - /* return 1 if pen is down */ - return (reg & 0x40) == 0; -} - -static struct ads7846_platform_data pdm360ng_ads7846_pdata = { - .model = 7845, - .get_pendown_state = pdm360ng_get_pendown_state, - .irq_flags = IRQF_TRIGGER_LOW, -}; - -static int __init pdm360ng_penirq_init(void) -{ - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-gpio"); - if (!np) { - pr_err("%s: Can't find 'mpc5121-gpio' node\n", __func__); - return -ENODEV; - } - - pdm360ng_gpio_base = of_iomap(np, 0); - of_node_put(np); - if (!pdm360ng_gpio_base) { - pr_err("%s: Can't map gpio regs.\n", __func__); - return -ENODEV; - } - out_be32(pdm360ng_gpio_base + 0xc, 0xffffffff); - setbits32(pdm360ng_gpio_base + 0x18, 0x2000); - setbits32(pdm360ng_gpio_base + 0x10, 0x40); - - return 0; -} - -static int pdm360ng_touchscreen_notifier_call(struct notifier_block *nb, - unsigned long event, void *__dev) -{ - struct device *dev = __dev; - - if ((event == BUS_NOTIFY_ADD_DEVICE) && - of_device_is_compatible(dev->of_node, "ti,ads7846")) { - dev->platform_data = &pdm360ng_ads7846_pdata; - return NOTIFY_OK; - } - return NOTIFY_DONE; -} - -static struct notifier_block pdm360ng_touchscreen_nb = { - .notifier_call = pdm360ng_touchscreen_notifier_call, -}; - -static void __init pdm360ng_touchscreen_init(void) -{ - if (pdm360ng_penirq_init()) - return; - - bus_register_notifier(&spi_bus_type, &pdm360ng_touchscreen_nb); -} -#else -static inline void __init pdm360ng_touchscreen_init(void) -{ -} -#endif /* CONFIG_TOUCHSCREEN_ADS7846 */ - -static void __init pdm360ng_init(void) -{ - mpc512x_init(); - pdm360ng_touchscreen_init(); -} - -static int __init pdm360ng_probe(void) -{ - mpc512x_init_early(); - - return 1; -} - -define_machine(pdm360ng) { - .name = "PDM360NG", - .compatible = "ifm,pdm360ng", - .probe = pdm360ng_probe, - .setup_arch = mpc512x_setup_arch, - .init = pdm360ng_init, - .init_IRQ = mpc512x_init_IRQ, - .get_irq = ipic_get_irq, - .restart = mpc512x_restart, -}; diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index a4ad4b49eef7..358611638258 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -184,8 +184,7 @@ static int ps3_virq_setup(enum ps3_cpu_binding cpu, unsigned long outlet, if (!*virq) { FAIL("%s:%d: irq_create_mapping failed: outlet %lu\n", __func__, __LINE__, outlet); - result = -ENOMEM; - goto fail_create; + return -ENOMEM; } DBG("%s:%d: outlet %lu => cpu %u, virq %u\n", __func__, __LINE__, @@ -196,17 +195,13 @@ static int ps3_virq_setup(enum ps3_cpu_binding cpu, unsigned long outlet, if (result) { FAIL("%s:%d: irq_set_chip_data failed\n", __func__, __LINE__); - goto fail_set; + irq_dispose_mapping(*virq); + return result; } ps3_chip_mask(irq_get_irq_data(*virq)); return result; - -fail_set: - irq_dispose_mapping(*virq); -fail_create: - return result; } /** @@ -250,7 +245,7 @@ int ps3_irq_plug_setup(enum ps3_cpu_binding cpu, unsigned long outlet, if (result) { FAIL("%s:%d: ps3_virq_setup failed\n", __func__, __LINE__); - goto fail_setup; + return result; } pd = irq_get_chip_data(*virq); @@ -263,16 +258,11 @@ int ps3_irq_plug_setup(enum ps3_cpu_binding cpu, unsigned long outlet, if (result) { FAIL("%s:%d: lv1_connect_irq_plug_ext failed: %s\n", __func__, __LINE__, ps3_result(result)); - result = -EPERM; - goto fail_connect; + ps3_virq_destroy(*virq); + return -EPERM; } return result; - -fail_connect: - ps3_virq_destroy(*virq); -fail_setup: - return result; } EXPORT_SYMBOL_GPL(ps3_irq_plug_setup); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 272e9aab66d4..32d414c2cb84 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -69,6 +69,8 @@ static struct iommu_table *iommu_pseries_alloc_table(int node) return tbl; } +static phys_addr_t pseries_ddw_max_ram __ro_after_init; + #ifdef CONFIG_IOMMU_API static struct iommu_table_group_ops spapr_tce_table_group_ops; #endif @@ -1284,15 +1286,19 @@ struct failed_ddw_pdn { static LIST_HEAD(failed_ddw_pdn_list); -static phys_addr_t ddw_memory_hotplug_max(void) +static phys_addr_t __init ddw_memory_hotplug_max(void) { - resource_size_t max_addr; + resource_size_t max_addr = memory_hotplug_max(); + struct device_node *memory; -#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG) - max_addr = hot_add_drconf_memory_max(); -#else - max_addr = memblock_end_of_DRAM(); -#endif + for_each_node_by_type(memory, "memory") { + struct resource res; + + if (of_address_to_resource(memory, 0, &res)) + continue; + + max_addr = max_t(resource_size_t, max_addr, res.end + 1); + } return max_addr; } @@ -1447,7 +1453,7 @@ static struct property *ddw_property_create(const char *propname, u32 liobn, u64 static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64 dma_mask) { int len = 0, ret; - int max_ram_len = order_base_2(ddw_memory_hotplug_max()); + int max_ram_len = order_base_2(pseries_ddw_max_ram); struct ddw_query_response query; struct ddw_create_response create; int page_shift; @@ -1617,12 +1623,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64 dma_mas if (default_win_removed && pmem_present && !direct_mapping) { /* DDW is big enough to be split */ if ((1ULL << ddw_sz) >= - MIN_DDW_VPMEM_DMA_WINDOW + (1ULL << max_ram_len)) { + MIN_DDW_VPMEM_DMA_WINDOW + pseries_ddw_max_ram) { direct_mapping = true; /* offset of the Dynamic part of DDW */ - dynamic_offset = 1ULL << max_ram_len; + dynamic_offset = pseries_ddw_max_ram; } /* DDW will at least have dynamic allocation */ @@ -1669,7 +1675,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64 dma_mas if (direct_mapping) { /* DDW maps the whole partition, so enable direct DMA mapping */ - ret = walk_system_ram_range(0, ddw_memory_hotplug_max() >> PAGE_SHIFT, + ret = walk_system_ram_range(0, pseries_ddw_max_ram >> PAGE_SHIFT, win64->value, tce_setrange_multi_pSeriesLP_walk); if (ret) { dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n", @@ -1772,8 +1778,7 @@ out_unlock: /* For pre-mapped memory, set bus_dma_limit to the max RAM */ if (direct_mapping) - dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + - (1ULL << max_ram_len); + dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + pseries_ddw_max_ram; dev_info(&dev->dev, "lsa_required: %x, lsa_enabled: %x, direct mapping: %x\n", limited_addr_req, limited_addr_enabled, direct_mapping); @@ -2420,23 +2425,35 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action, { struct dma_win *window; struct memory_notify *arg = data; + unsigned long limit = arg->nr_pages; + unsigned long max_ram_pages = pseries_ddw_max_ram >> PAGE_SHIFT; int ret = 0; /* This notifier can get called when onlining persistent memory as well. * TCEs are not pre-mapped for persistent memory. Persistent memory will - * always be above ddw_memory_hotplug_max() + * always be above pseries_ddw_max_ram */ + if (arg->start_pfn >= max_ram_pages) + return NOTIFY_OK; + + /* RAM is being DLPAR'ed. The range should never exceed max ram. + * Just in case, clamp the range and throw a warning. + */ + if (arg->start_pfn + limit > max_ram_pages) { + limit = max_ram_pages - arg->start_pfn; + WARN_ONCE(1, "Limiting Page Range %lx - %lx to Max Mem Pages: %lx\n", + arg->start_pfn, arg->start_pfn + arg->nr_pages, + max_ram_pages); + } switch (action) { case MEM_GOING_ONLINE: spin_lock(&dma_win_list_lock); list_for_each_entry(window, &dma_win_list, list) { - if (window->direct && (arg->start_pfn << PAGE_SHIFT) < - ddw_memory_hotplug_max()) { + if (window->direct) { ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn, - arg->nr_pages, window->prop); + limit, window->prop); } - /* XXX log error */ } spin_unlock(&dma_win_list_lock); break; @@ -2444,12 +2461,10 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action, case MEM_OFFLINE: spin_lock(&dma_win_list_lock); list_for_each_entry(window, &dma_win_list, list) { - if (window->direct && (arg->start_pfn << PAGE_SHIFT) < - ddw_memory_hotplug_max()) { + if (window->direct) { ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn, - arg->nr_pages, window->prop); + limit, window->prop); } - /* XXX log error */ } spin_unlock(&dma_win_list_lock); break; @@ -2533,6 +2548,14 @@ void __init iommu_init_early_pSeries(void) register_memory_notifier(&iommu_mem_nb); set_pci_dma_ops(&dma_iommu_ops); + + /* During init determine the max memory an LPAR can have and set it. This + * will be used for pre-mapping RAM in DDW. memblock_end_of_DRAM() can + * change during the running of LPAR - daxctl can add pmemory as + * "system-ram". This memory range should not be pre-mapped in DDW since + * the address of pmemory can be much higher than the DDW size. + */ + pseries_ddw_max_ram = ddw_memory_hotplug_max(); } static int __init disable_multitce(char *str) diff --git a/arch/powerpc/platforms/pseries/plpks-sysfs.c b/arch/powerpc/platforms/pseries/plpks-sysfs.c index c2ebcbb41ae3..f2436229f323 100644 --- a/arch/powerpc/platforms/pseries/plpks-sysfs.c +++ b/arch/powerpc/platforms/pseries/plpks-sysfs.c @@ -45,6 +45,16 @@ static const struct attribute *config_attrs[] = { static struct kobject *plpks_kobj, *plpks_config_kobj; +static umode_t plpks_config_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + if (attr == &attr_wrapping_features.attr && + !plpks_wrapping_is_supported()) + return 0; + + return attr->mode; +} + int plpks_config_create_softlink(struct kobject *from) { if (!plpks_config_kobj) @@ -52,13 +62,13 @@ int plpks_config_create_softlink(struct kobject *from) return sysfs_create_link(from, plpks_config_kobj, "config"); } +static const struct attribute_group config_group = { + .attrs = (struct attribute **)config_attrs, + .is_visible = plpks_config_attr_is_visible, +}; + static __init int plpks_sysfs_config(struct kobject *kobj) { - struct attribute_group config_group = { - .name = NULL, - .attrs = (struct attribute **)config_attrs, - }; - return sysfs_create_group(kobj, &config_group); } diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index 23e4e2a922fc..240cd5632446 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -10,7 +10,7 @@ #define pr_fmt(fmt) "plpks: " fmt #define PLPKS_WRAPKEY_COMPONENT "PLPKSWR" -#define PLPKS_WRAPKEY_NAME "default-wrapping-key" +#define PLPKS_DEFAULT_WRAPKEY_LABEL "default-wrapping-key" /* * To 4K align the {input, output} buffers to the {UN}WRAP H_CALLs @@ -576,7 +576,7 @@ static int plpks_confirm_object_flushed(struct label *label, virt_to_phys(auth), virt_to_phys(label), label->size); - status = retbuf[0]; + status = (u8)retbuf[0]; if (rc) { timed_out = false; if (rc == H_NOT_FOUND && status == 1) @@ -637,6 +637,9 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags) u64 continuetoken = 0; u64 timeout = 0; + if (!var) + return -EINVAL; + if (!var->data || var->datalen <= 0 || var->namelen > PLPKS_MAX_NAME_SIZE) return -EINVAL; @@ -682,7 +685,7 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags) kfree(label); out: - kfree(auth); + kfree_sensitive(auth); return rc; } @@ -751,7 +754,7 @@ int plpks_write_var(struct plpks_var var) rc = pseries_status_to_err(rc); kfree(label); out: - kfree(auth); + kfree_sensitive(auth); return rc; } @@ -809,7 +812,7 @@ int plpks_remove_var(char *component, u8 varos, struct plpks_var_name vname) rc = pseries_status_to_err(rc); kfree(label); out: - kfree(auth); + kfree_sensitive(auth); return rc; } @@ -822,11 +825,14 @@ static int plpks_read_var(u8 consumer, struct plpks_var *var) u8 *output; int rc; + if (!var) + return -EINVAL; + if (var->namelen > PLPKS_MAX_NAME_SIZE) return -EINVAL; if (var->policy & PLPKS_WRAPPINGKEY) - return -EINVAL; + return -EPERM; auth = construct_auth(consumer); if (IS_ERR(auth)) @@ -856,28 +862,27 @@ static int plpks_read_var(u8 consumer, struct plpks_var *var) virt_to_phys(var->name), var->namelen, virt_to_phys(output), maxobjsize); - if (rc != H_SUCCESS) { rc = pseries_status_to_err(rc); - goto out_free_output; + if (rc != -EPERM || !retbuf[1]) + goto out_free_output; + goto out_copy_policy; } if (!var->data || var->datalen > retbuf[0]) - var->datalen = retbuf[0]; - - var->policy = retbuf[1]; + var->datalen = (u16)retbuf[0]; if (var->data) memcpy(var->data, output, var->datalen); - rc = 0; - +out_copy_policy: + var->policy = (u32)retbuf[1]; out_free_output: - kfree(output); + kfree_sensitive(output); out_free_label: kfree(label); out_free_auth: - kfree(auth); + kfree_sensitive(auth); return rc; } @@ -933,8 +938,8 @@ int plpks_gen_wrapping_key(void) struct label *label; int rc = 0, pseries_status = 0; struct plpks_var var = { - .name = PLPKS_WRAPKEY_NAME, - .namelen = strlen(var.name), + .name = PLPKS_DEFAULT_WRAPKEY_LABEL, + .namelen = sizeof(PLPKS_DEFAULT_WRAPKEY_LABEL) - 1, .policy = PLPKS_WRAPPINGKEY, .os = PLPKS_VAR_LINUX, .component = PLPKS_WRAPKEY_COMPONENT @@ -970,7 +975,7 @@ int plpks_gen_wrapping_key(void) kfree(label); out: - kfree(auth); + kfree_sensitive(auth); return rc; } EXPORT_SYMBOL_GPL(plpks_gen_wrapping_key); @@ -1028,8 +1033,8 @@ int plpks_wrap_object(u8 **input_buf, u32 input_len, u16 wrap_flags, bool sb_audit_or_enforce_bit = wrap_flags & BIT(0); bool sb_enforce_bit = wrap_flags & BIT(1); struct plpks_var var = { - .name = PLPKS_WRAPKEY_NAME, - .namelen = strlen(var.name), + .name = PLPKS_DEFAULT_WRAPKEY_LABEL, + .namelen = sizeof(PLPKS_DEFAULT_WRAPKEY_LABEL) - 1, .os = PLPKS_VAR_LINUX, .component = PLPKS_WRAPKEY_COMPONENT }; @@ -1095,7 +1100,7 @@ int plpks_wrap_object(u8 **input_buf, u32 input_len, u16 wrap_flags, out_free_label: kfree(label); out: - kfree(auth); + kfree_sensitive(auth); return rc; } EXPORT_SYMBOL_GPL(plpks_wrap_object); @@ -1172,14 +1177,14 @@ int plpks_unwrap_object(u8 **input_buf, u32 input_len, u8 **output_buf, if (rc) { pr_err("H_PKS_UNWRAP_OBJECT failed. pseries_status=%d, rc=%d", pseries_status, rc); - kfree(*output_buf); + kfree_sensitive(*output_buf); *output_buf = NULL; } else { *output_len = retbuf[1]; } out: - kfree(auth); + kfree_sensitive(auth); return rc; } EXPORT_SYMBOL_GPL(plpks_unwrap_object); diff --git a/arch/powerpc/platforms/pseries/plpks_sed_ops.c b/arch/powerpc/platforms/pseries/plpks_sed_ops.c index 7c873c9589ef..ac3ec2ca7fbe 100644 --- a/arch/powerpc/platforms/pseries/plpks_sed_ops.c +++ b/arch/powerpc/platforms/pseries/plpks_sed_ops.c @@ -84,14 +84,16 @@ int sed_read_key(char *keyname, char *key, u_int *keylen) ret = plpks_read_os_var(&var); if (ret != 0) - return ret; + goto out; len = min_t(u16, be32_to_cpu(data.key_len), var.datalen); memcpy(key, data.key, len); key[len] = '\0'; *keylen = len; - return 0; +out: + memzero_explicit(&data, sizeof(data)); + return ret; } /* @@ -102,6 +104,7 @@ int sed_write_key(char *keyname, char *key, u_int keylen) struct plpks_var var; struct plpks_sed_object_data data; struct plpks_var_name vname; + int ret; plpks_init_var(&var, keyname); @@ -127,5 +130,8 @@ int sed_write_key(char *keyname, char *key, u_int keylen) vname.name = var.name; plpks_remove_var(var.component, var.os, vname); - return plpks_write_var(var); + ret = plpks_write_var(var); + memzero_explicit(&data, sizeof(data)); + + return ret; } diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c index 3bb4ac2ab6cc..9b9e09f3d900 100644 --- a/arch/powerpc/platforms/pseries/rtas-fadump.c +++ b/arch/powerpc/platforms/pseries/rtas-fadump.c @@ -459,6 +459,8 @@ static int __init rtas_fadump_process(struct fw_dump *fadump_conf) /* Check if the dump data is valid. */ for (int i = 0; i < be16_to_cpu(fdm_active->header.dump_num_sections); i++) { int type = be16_to_cpu(fdm_active->rgn[i].source_data_type); + uint64_t bytes_dumped = be64_to_cpu(fdm_active->rgn[i].bytes_dumped); + uint64_t source_len = be64_to_cpu(fdm_active->rgn[i].source_len); int rc = 0; switch (type) { @@ -469,10 +471,20 @@ static int __init rtas_fadump_process(struct fw_dump *fadump_conf) pr_err("Dump taken by platform is not valid (%d)\n", i); rc = -EINVAL; } - if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len) { - pr_err("Dump taken by platform is incomplete (%d)\n", i); + + /* + * Make sure that dump is collected for entire region. + * CPU_STATE_DATA region is allowed to dump less than allocated space. + */ + if (!(bytes_dumped == source_len || + (type == RTAS_FADUMP_CPU_STATE_DATA && bytes_dumped <= source_len))) { + pr_err("Dump taken by platform is %s (%d)\n", + (bytes_dumped < source_len ? "incomplete" : "corrupted"), i); + pr_debug("type -> %d, bytes_dumped -> %llx, source_len -> %llx\n", + type, bytes_dumped, source_len); rc = -EINVAL; } + if (rc) { pr_warn("Region type: %u src addr: 0x%llx dest addr: 0x%llx\n", be16_to_cpu(fdm_active->rgn[i].source_data_type), @@ -482,7 +494,7 @@ static int __init rtas_fadump_process(struct fw_dump *fadump_conf) } break; case RTAS_FADUMP_PARAM_AREA: - if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len || + if (bytes_dumped != source_len || fdm_active->rgn[i].error_flags != 0) { pr_warn("Failed to process additional parameters! Proceeding anyway..\n"); fadump_conf->param_area = 0; |